feat(runner): let root_instructions_override replace the root's scan prompt

.github/workflows/build-release.yml

@@ -32,7 +32,6 @@ jobs:
             wheel-platform: win_amd64
 
     runs-on: ${{ matrix.os }}
-    timeout-minutes: 45
 
     steps:
       - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4.4.0
@@ -111,7 +110,6 @@ jobs:
     if: startsWith(github.ref, 'refs/tags/')
     needs: build
     runs-on: ubuntu-latest
-    timeout-minutes: 10
     permissions:
       contents: write
 

.github/workflows/ci-package.yml

@@ -1,39 +1,48 @@
-name: Binary
+name: Package
 
 on:
-  pull_request:
-    paths:
-      - pyproject.toml
-      - uv.lock
-      - strix.spec
-      - scripts/**
-      - strix/interface/tui/**
-      - .github/actions/**
-      - .github/workflows/binary.yml
-  push:
-    branches:
-      - main
-    paths:
-      - pyproject.toml
-      - uv.lock
-      - strix.spec
-      - scripts/**
-      - strix/interface/tui/**
-      - .github/actions/**
-      - .github/workflows/binary.yml
-  workflow_dispatch:
+  workflow_call:
 
 permissions:
   contents: read
 
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
 jobs:
+  wheel:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4.4.0
+        with:
+          persist-credentials: false
+      - uses: actions/setup-go@44694675825211faa026b3c33043df3e48a5fa00  # v6.0.0
+        with:
+          go-version-file: strix/interface/tui/go.mod
+          cache-dependency-path: strix/interface/tui/go.sum
+      - uses: ./.github/actions/setup-python-env
+      - run: uv build --wheel
+      - name: Wheel ships the TUI sidecar and the viewer bundle
+        run: |
+          uv run --frozen python - <<'PY'
+          import glob, zipfile
+          (wheel,) = glob.glob("dist/*.whl")
+          names = zipfile.ZipFile(wheel).namelist()
+          assert "strix/bin/strix-tui" in names, names
+          assert "strix/interface/viewer/static/index.html" in names, names
+          assert not any(name.startswith("strix/interface/viewer/frontend/") for name in names)
+          assert not any(name.startswith("strix/interface/tui/cmd/") for name in names)
+          PY
+      - name: Install into a clean environment and run the CLI
+        env:
+          UV_EXCLUDE_NEWER: 5 days
+        run: |
+          uv venv --python 3.12 /tmp/strix-smoke
+          uv pip install --python /tmp/strix-smoke/bin/python dist/*.whl
+          /tmp/strix-smoke/bin/strix --version
+          /tmp/strix-smoke/bin/strix --help >/dev/null
+      - name: Vertex AI and Bedrock dependencies install with the wheel
+        run: /tmp/strix-smoke/bin/python -c "import google.auth.transport.requests, boto3"
+
   binary:
     runs-on: ubuntu-latest
-    timeout-minutes: 20
     steps:
       - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4.4.0
         with:

.github/workflows/ci-python.yml

@@ -0,0 +1,61 @@
+name: Python
+
+on:
+  workflow_call:
+
+permissions:
+  contents: read
+
+jobs:
+  lock:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4.4.0
+        with:
+          persist-credentials: false
+      - uses: astral-sh/setup-uv@d4b2f3b6ecc6e67c4457f6d3e41ec42d3d0fcb86  # v5.4.2
+      - run: uv lock --check
+
+  ruff:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4.4.0
+        with:
+          persist-credentials: false
+      - uses: ./.github/actions/setup-python-env
+      - run: uv run --frozen ruff check .
+      - run: uv run --frozen ruff format --check .
+
+  mypy:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4.4.0
+        with:
+          persist-credentials: false
+      - uses: ./.github/actions/setup-python-env
+      - run: uv run --frozen mypy strix/
+
+  bandit:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4.4.0
+        with:
+          persist-credentials: false
+      - uses: ./.github/actions/setup-python-env
+      - run: uv run --frozen bandit -r strix/ -c pyproject.toml
+
+  pytest:
+    name: pytest (${{ matrix.python-version }})
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ['3.12', '3.13', '3.14']
+    steps:
+      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4.4.0
+        with:
+          persist-credentials: false
+      - uses: ./.github/actions/setup-python-env
+        with:
+          python-version: ${{ matrix.python-version }}
+      - run: uv run --frozen pytest -q

.github/workflows/ci-tui.yml

@@ -0,0 +1,26 @@
+name: TUI
+
+on:
+  workflow_call:
+
+permissions:
+  contents: read
+
+jobs:
+  go:
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        working-directory: strix/interface/tui
+    steps:
+      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4.4.0
+        with:
+          persist-credentials: false
+      - uses: actions/setup-go@44694675825211faa026b3c33043df3e48a5fa00  # v6.0.0
+        with:
+          go-version-file: strix/interface/tui/go.mod
+          cache-dependency-path: strix/interface/tui/go.sum
+      - run: test -z "$(gofmt -l .)"
+      - run: go vet ./...
+      - run: CGO_ENABLED=0 go build -trimpath -o /dev/null ./cmd/strix-tui
+      - run: go test -race ./...

.github/workflows/ci-viewer.yml

@@ -0,0 +1,27 @@
+name: Viewer
+
+on:
+  workflow_call:
+
+permissions:
+  contents: read
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        working-directory: strix/interface/viewer/frontend
+    steps:
+      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4.4.0
+        with:
+          persist-credentials: false
+      - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020  # v7.0.0
+        with:
+          node-version: '24'
+          cache: npm
+          cache-dependency-path: strix/interface/viewer/frontend/package-lock.json
+      - run: npm ci --no-audit --no-fund
+      - run: npm run build
+      - name: Committed viewer bundle matches the build
+        run: git -C "$GITHUB_WORKSPACE" diff --exit-code --stat -- strix/interface/viewer/static && test -z "$(git -C "$GITHUB_WORKSPACE" status --porcelain -- strix/interface/viewer/static)"

.github/workflows/ci-workflows.yml

@@ -1,27 +1,14 @@
 name: Workflows
 
 on:
-  pull_request:
-    paths:
-      - .github/**
-  push:
-    branches:
-      - main
-    paths:
-      - .github/**
-  workflow_dispatch:
+  workflow_call:
 
 permissions:
   contents: read
 
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
 jobs:
   actionlint:
     runs-on: ubuntu-latest
-    timeout-minutes: 10
     env:
       ACTIONLINT_VERSION: 1.7.12
       ACTIONLINT_SCRIPT_REF: 914e7df21a07ef503a81201c76d2b11c789d3fca  # v1.7.12
@@ -40,7 +27,6 @@ jobs:
 
   zizmor:
     runs-on: ubuntu-latest
-    timeout-minutes: 10
     steps:
       - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4.4.0
         with:

.github/workflows/ci.yml

@@ -15,107 +15,38 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
-  lint:
-    runs-on: ubuntu-latest
-    timeout-minutes: 15
-    steps:
-      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4.4.0
-        with:
-          persist-credentials: false
-      - uses: ./.github/actions/setup-python-env
-      - run: uv lock --check
-      - run: uv run --frozen ruff check .
-      - run: uv run --frozen ruff format --check .
-      - run: uv run --frozen mypy strix/
-      - run: uv run --frozen bandit -r strix/ -c pyproject.toml
-
-  pytest:
-    name: pytest (${{ matrix.python-version }})
-    runs-on: ubuntu-latest
-    timeout-minutes: 15
-    strategy:
-      fail-fast: false
-      matrix:
-        python-version: ['3.12', '3.14']
-    steps:
-      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4.4.0
-        with:
-          persist-credentials: false
-      - uses: ./.github/actions/setup-python-env
-        with:
-          python-version: ${{ matrix.python-version }}
-      - run: uv run --frozen pytest -q
+  python:
+    uses: ./.github/workflows/ci-python.yml
 
   tui:
-    runs-on: ubuntu-latest
-    timeout-minutes: 15
-    defaults:
-      run:
-        working-directory: strix/interface/tui
-    steps:
-      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4.4.0
-        with:
-          persist-credentials: false
-      - uses: actions/setup-go@44694675825211faa026b3c33043df3e48a5fa00  # v6.0.0
-        with:
-          go-version-file: strix/interface/tui/go.mod
-          cache-dependency-path: strix/interface/tui/go.sum
-      - run: test -z "$(gofmt -l .)"
-      - run: go vet ./...
-      - run: CGO_ENABLED=0 go build -trimpath -o /dev/null ./cmd/strix-tui
-      - run: go test -race ./...
+    uses: ./.github/workflows/ci-tui.yml
 
   viewer:
-    runs-on: ubuntu-latest
-    timeout-minutes: 15
-    defaults:
-      run:
-        working-directory: strix/interface/viewer/frontend
-    steps:
-      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4.4.0
-        with:
-          persist-credentials: false
-      - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020  # v7.0.0
-        with:
-          node-version: '24'
-          cache: npm
-          cache-dependency-path: strix/interface/viewer/frontend/package-lock.json
-      - run: npm ci --no-audit --no-fund
-      - run: npm run build
-      - name: Committed viewer bundle matches the build
-        run: git -C "$GITHUB_WORKSPACE" diff --exit-code --stat -- strix/interface/viewer/static && test -z "$(git -C "$GITHUB_WORKSPACE" status --porcelain -- strix/interface/viewer/static)"
+    uses: ./.github/workflows/ci-viewer.yml
 
-  wheel:
+  package:
+    uses: ./.github/workflows/ci-package.yml
+
+  workflows:
+    uses: ./.github/workflows/ci-workflows.yml
+
+  ci-passed:
+    name: ci-passed
+    if: always()
+    needs:
+      - python
+      - tui
+      - viewer
+      - package
+      - workflows
     runs-on: ubuntu-latest
-    timeout-minutes: 15
     steps:
-      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4.4.0
-        with:
-          persist-credentials: false
-      - uses: actions/setup-go@44694675825211faa026b3c33043df3e48a5fa00  # v6.0.0
-        with:
-          go-version-file: strix/interface/tui/go.mod
-          cache-dependency-path: strix/interface/tui/go.sum
-      - uses: ./.github/actions/setup-python-env
-      - run: uv build --wheel
-      - name: Wheel ships the TUI sidecar and the viewer bundle
-        run: |
-          uv run --frozen python - <<'PY'
-          import glob, zipfile
-          (wheel,) = glob.glob("dist/*.whl")
-          names = zipfile.ZipFile(wheel).namelist()
-          assert "strix/bin/strix-tui" in names, names
-          assert "strix/interface/viewer/static/index.html" in names, names
-          assert not any(name.startswith("strix/interface/viewer/frontend/") for name in names)
-          assert not any(name.startswith("strix/interface/tui/cmd/") for name in names)
-          PY
-      - name: Install into a clean environment and run the CLI
+      - name: Every job succeeded
         env:
-          UV_EXCLUDE_NEWER: 5 days
+          NEEDS: ${{ toJSON(needs) }}
         run: |
-          uv venv --python 3.12 /tmp/strix-smoke
-          uv pip install --python /tmp/strix-smoke/bin/python dist/*.whl
-          /tmp/strix-smoke/bin/strix --version
-          /tmp/strix-smoke/bin/strix --help >/dev/null
-      - name: Vertex AI and Bedrock dependencies install with the wheel
-        run: /tmp/strix-smoke/bin/python -c "import google.auth.transport.requests, boto3"
+          failing=$(jq -r 'to_entries[] | select(.value.result != "success") | "\(.key): \(.value.result)"' <<< "$NEEDS")
+          if [ -n "$failing" ]; then
+            echo "$failing"
+            exit 1
+          fi

.pre-commit-config.yaml

@@ -45,3 +45,23 @@ repos:
     hooks:
       - id: bandit
         args: [-c, pyproject.toml]
+
+  # Additional Python code quality checks
+  - repo: https://github.com/asottile/pyupgrade
+    rev: v3.21.2
+    hooks:
+      - id: pyupgrade
+        args: [--py312-plus]
+
+ci:
+  autofix_commit_msg: |
+    [pre-commit.ci] auto fixes from pre-commit.com hooks
+
+    for more information, see https://pre-commit.ci
+  autofix_prs: true
+  autoupdate_branch: ""
+  autoupdate_commit_msg: "[pre-commit.ci] pre-commit autoupdate"
+  autoupdate_schedule: weekly
+  # pre-commit.ci cannot run `language: system` hooks; mypy runs via `make check-all`.
+  skip: [mypy]
+  submodules: false

AGENTS.md

@@ -28,7 +28,7 @@ Target-specific workflows built on the same engine:
 - **Open-source CLI (self-hosted):** free, fully local, BYO LLM key, needs Docker. Best for local dev loops, air-gapped/offline, and full control.
   ```bash
   curl -sSL https://strix.ai/install | bash        # install
-  export STRIX_LLM="openrouter/z-ai/glm-5.3"        # any LiteLLM model id, or vercel_ai_gateway/zai/glm-5.3
+  export STRIX_LLM="openrouter/z-ai/glm-5.3"        # any LiteLLM model id
   export LLM_API_KEY="<key>"
   strix -n -t ./ --scan-mode quick --max-budget 10  # headless scan; always use -n
   ```

CONTRIBUTING.md

@@ -31,7 +31,7 @@ Thank you for your interest in contributing to Strix! This guide will help you g
 
 3. **Configure your LLM provider**
    ```bash
-   export STRIX_LLM="openrouter/z-ai/glm-5.3"   # or vercel_ai_gateway/zai/glm-5.3
+   export STRIX_LLM="openrouter/z-ai/glm-5.3"
    export LLM_API_KEY="your-api-key"
    ```
 

README.md

@@ -84,8 +84,7 @@ Strix are autonomous AI penetration testing agents that act just like real hacke
 curl -sSL https://strix.ai/install | bash
 
 # Configure your AI provider
-export STRIX_LLM="vercel_ai_gateway/zai/glm-5.3"   # Vercel AI Gateway
-# export STRIX_LLM="openrouter/z-ai/glm-5.3"       # OpenRouter
+export STRIX_LLM="openrouter/z-ai/glm-5.3"
 export LLM_API_KEY="your-api-key"
 
 # Run your first security assessment
@@ -297,8 +296,7 @@ jobs:
 ### Configuration
 
 ```bash
-export STRIX_LLM="vercel_ai_gateway/zai/glm-5.3"   # Vercel AI Gateway
-# export STRIX_LLM="openrouter/z-ai/glm-5.3"       # OpenRouter
+export STRIX_LLM="openrouter/z-ai/glm-5.3"
 export LLM_API_KEY="your-api-key"
 
 # Optional
@@ -354,14 +352,12 @@ Each server's tools are namespaced by `name`, for example `github_list_issues`.
 
 **Recommended models for best results:**
 
-- [Z.ai GLM-5.3 on Vercel AI Gateway](https://vercel.com/ai-gateway/models/glm-5.3) - `vercel_ai_gateway/zai/glm-5.3` (recommended)
-- [Z.ai GLM-5.3 on OpenRouter](https://openrouter.ai/z-ai/glm-5.3) - `openrouter/z-ai/glm-5.3` (recommended)
-- [DeepSeek V4.1 Flash on OpenRouter](https://openrouter.ai/deepseek/deepseek-v4.1-flash-1017) - `openrouter/deepseek/deepseek-v4.1-flash-1017`
-- [OpenAI GPT-6.1 Sol](https://openai.com/api/) - `openai/gpt-6.1-sol` (needs [Daybreak](https://openai.com/daybreak/) access)
-- [Anthropic Claude Opus 5.5](https://claude.com/platform/api) - `anthropic/claude-opus-5-5` (needs [CVP](https://support.claude.com/en/articles/14604842-cyber-verification-program) access)
-- [Google Gemini 4 Argon](https://cloud.google.com/vertex-ai) - `vertex_ai/gemini-4-argon` (needs [Fairwind](https://deepmind.google/fairwind-program/) access)
+- [Z.ai GLM-5.3 on OpenRouter](https://openrouter.ai/z-ai/glm-5.3) - `openrouter/z-ai/glm-5.3` (the default pick)
+- [OpenAI GPT-5.4](https://openai.com/api/) - `openai/gpt-5.4`
+- [Anthropic Claude Sonnet 4.6](https://claude.com/platform/api) - `anthropic/claude-sonnet-4-6`
+- [Google Gemini 3 Pro Preview](https://cloud.google.com/vertex-ai) - `vertex_ai/gemini-3-pro-preview`
 - [DeepSeek V4 Pro](https://platform.deepseek.com) - `deepseek/deepseek-v4-pro`
-- [Moonshot Kimi K3.1 Pro](https://platform.kimi.ai) - `moonshot/kimi-k3.1-pro`
+- [Moonshot Kimi K3](https://platform.kimi.ai) - `moonshot/kimi-k3`
 
 See the [LLM Providers documentation](https://docs.strix.ai/llm-providers/overview) for all supported providers including Vertex AI, Bedrock, Azure, and local models.
 

containers/Dockerfile

@@ -186,84 +186,20 @@ RUN set -eux; \
         aarch64|arm64) GITLEAKS_ARCH="arm64" ;; \
         *) echo "Unsupported architecture: $ARCH" >&2; exit 1 ;; \
     esac; \
-    TAG="$(curl -fsSLI -o /dev/null -w '%{url_effective}' https://github.com/gitleaks/gitleaks/releases/latest | sed 's#.*/##')"; \
+    TAG="$(curl -fsSL https://api.github.com/repos/gitleaks/gitleaks/releases/latest | jq -r .tag_name)"; \
     curl -fsSL "https://github.com/gitleaks/gitleaks/releases/download/${TAG}/gitleaks_${TAG#v}_linux_${GITLEAKS_ARCH}.tar.gz" -o /tmp/gitleaks.tgz; \
     tar -xzf /tmp/gitleaks.tgz -C /tmp; \
     install -m 0755 /tmp/gitleaks /usr/local/bin/gitleaks; \
     rm -f /tmp/gitleaks /tmp/gitleaks.tgz
 
-ARG TRIVY_VERSION=0.76.1
-ARG TRIVY_SHA256_X86=c7cbe3137fb8a48a17574bede3dd6beb16742d1e9772929940fc90082c39d9c0
-ARG TRIVY_SHA256_AARCH64=e174dff2a6dba5e3ae41f8d0537a6324405bd08132497340304c6b20e0f16a1f
-RUN set -eux; \
-    case "$(uname -m)" in \
-        x86_64) TRIVY_ARCH="64bit"; TRIVY_SHA256="${TRIVY_SHA256_X86}" ;; \
-        aarch64|arm64) TRIVY_ARCH="ARM64"; TRIVY_SHA256="${TRIVY_SHA256_AARCH64}" ;; \
-        *) echo "Unsupported architecture: $(uname -m)" >&2; exit 1 ;; \
-    esac; \
-    curl -fsSL "https://github.com/aquasecurity/trivy/releases/download/v${TRIVY_VERSION}/trivy_${TRIVY_VERSION}_Linux-${TRIVY_ARCH}.tar.gz" -o /tmp/trivy.tgz; \
-    echo "${TRIVY_SHA256}  /tmp/trivy.tgz" | sha256sum -c -; \
-    tar -xzf /tmp/trivy.tgz -C /tmp trivy; \
-    install -m 0755 /tmp/trivy /usr/local/bin/trivy; \
-    rm -f /tmp/trivy /tmp/trivy.tgz; \
-    trivy --version
+RUN curl -sfL https://raw.githubusercontent.com/aquasecurity/trivy/main/contrib/install.sh | sh -s -- -b /usr/local/bin
 
 RUN apt-get install -y wapiti
 
-# CVE-2026-111497: out-of-bounds write in the brotli decoder, fixed in brotli
-# 1.2.1 / Debian 1.2.0-4.1. kali-rolling still ships 1.2.0-4, and node, curl and
-# python3 in this image all load the shared libbrotlidec, so every HTTP client here
-# would decode a malicious `Content-Encoding: br` response with the vulnerable
-# code. Install the fixed Debian packages until Kali picks them up.
-ARG BROTLI_DEB_VERSION=1.2.0-4.1
-RUN set -eux; \
-    ARCH="$(dpkg --print-architecture)"; \
-    for pkg in libbrotli1 python3-brotli; do \
-        curl -fsSL "https://deb.debian.org/debian/pool/main/b/brotli/${pkg}_${BROTLI_DEB_VERSION}_${ARCH}.deb" -o "/tmp/${pkg}.deb"; \
-    done; \
-    dpkg -i /tmp/libbrotli1.deb /tmp/python3-brotli.deb; \
-    rm -f /tmp/libbrotli1.deb /tmp/python3-brotli.deb; \
-    test "$(dpkg-query -W -f='${Version}' libbrotli1)" = "${BROTLI_DEB_VERSION}"; \
-    node -e 'const z=require("zlib");z.brotliDecompressSync(z.brotliCompressSync(Buffer.from("ok")))'
-
-ARG OPENGREP_VERSION=1.31.0
-ARG OPENGREP_SHA256_X86=dbbe3c2058dbe600c449a8ba22ea79a1643a6660658400090d0323a8d0d31147
-ARG OPENGREP_SHA256_AARCH64=2b713a29a00237f85408b83002fc111db5b94c7fa8d263f0a93184a960655d9d
-RUN set -eux; \
-    case "$(uname -m)" in \
-        x86_64) OPENGREP_ARCH="x86"; OPENGREP_SHA256="${OPENGREP_SHA256_X86}" ;; \
-        aarch64|arm64) OPENGREP_ARCH="aarch64"; OPENGREP_SHA256="${OPENGREP_SHA256_AARCH64}" ;; \
-        *) echo "Unsupported architecture: $(uname -m)" >&2; exit 1 ;; \
-    esac; \
-    curl -fsSL "https://github.com/opengrep/opengrep/releases/download/v${OPENGREP_VERSION}/opengrep_manylinux_${OPENGREP_ARCH}" -o /tmp/opengrep; \
-    echo "${OPENGREP_SHA256}  /tmp/opengrep" | sha256sum -c -; \
-    install -m 0755 /tmp/opengrep /usr/local/bin/opengrep; \
-    rm -f /tmp/opengrep; \
-    opengrep --version
-
-# Opengrep ships no rule registry of its own; bake the community ruleset so
-# scans run offline. Keep only rule YAML and LICENSE; drop tests, fixtures,
-# tooling, and rules marked with a proprietary license.
-ARG OPENGREP_RULES_REF=f1d2b562b414783763fd02a6ed2736eaed622efa
-RUN set -eux; \
-    mkdir -p /opt/opengrep-rules; \
-    curl -fsSL "https://codeload.github.com/opengrep/opengrep-rules/tar.gz/${OPENGREP_RULES_REF}" \
-        | tar -xz --strip-components=1 -C /opt/opengrep-rules; \
-    cd /opt/opengrep-rules; \
-    rm -rf .github scripts stats; \
-    find . -maxdepth 1 -type f ! -name LICENSE -delete; \
-    find . -mindepth 2 -type f \( ! \( -name '*.yaml' -o -name '*.yml' \) -o -name '*.test.yaml' -o -name '*.test.yml' -o -name '.*' \) -delete; \
-    grep -rlZ 'license: proprietary' . | xargs -0 -r rm -f; \
-    find . -type d -empty -delete; \
-    chmod -R a+rX /opt/opengrep-rules
-
-# Strix-authored rules that close gaps in the community ruleset.
-COPY containers/opengrep-rules/ /opt/opengrep-rules/strix/
-RUN chmod -R a+rX /opt/opengrep-rules/strix
-
 USER pentester
 
-RUN pipx install bandit
+RUN pipx install semgrep && \
+    pipx install bandit
 
 RUN npm install -g jshint
 

containers/opengrep-rules/github-owned-action-not-pinned-to-commit-sha.yaml

@@ -1,37 +0,0 @@
-rules:
-  - id: github-owned-action-not-pinned-to-commit-sha
-    patterns:
-      - pattern-inside: "{steps: ...}"
-      - pattern: |
-          uses: "$USES"
-      - metavariable-regex:
-          metavariable: $USES
-          regex: '^(actions|github)/'
-      - metavariable-pattern:
-          metavariable: $USES
-          language: generic
-          patterns:
-            - pattern-not-regex: "@[0-9a-f]{40}$"
-    message: >-
-      GitHub-owned action `$USES` is referenced by a mutable tag or branch
-      instead of a full-length commit SHA. Tags can be moved, so a compromised
-      or force-pushed release changes what this workflow runs. Pin to the
-      commit SHA of the release you reviewed and let a bot keep it current.
-    languages:
-      - yaml
-    severity: WARNING
-    metadata:
-      cwe:
-        - "CWE-1357: Reliance on Insufficiently Trustworthy Component"
-        - "CWE-353: Missing Support for Integrity Check"
-      owasp: A06:2021 - Vulnerable and Outdated Components
-      references:
-        - https://docs.github.com/en/actions/security-guides/security-hardening-for-github-actions#using-third-party-actions
-      category: security
-      technology:
-        - github-actions
-      subcategory:
-        - vuln
-      likelihood: LOW
-      impact: LOW
-      confidence: HIGH

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 (e.g., `openrouter/z-ai/glm-5.3`, `openai/gpt-6.1-sol`).
+  Model name in LiteLLM format (e.g., `openrouter/z-ai/glm-5.3`, `openai/gpt-5.4`).
 </ParamField>
 
 <ParamField path="LLM_API_KEY" type="string">
@@ -19,29 +19,10 @@ Configure Strix using environment variables or a config file.
   Custom API base URL. Also accepts `OPENAI_API_BASE`, `LITELLM_BASE_URL`, or `OLLAMA_API_BASE`.
 </ParamField>
 
-<ParamField path="STRIX_LLM_INPUT_COST_PER_MTOK" type="number">
-  Price per 1M input tokens in USD for `STRIX_LLM`. Use it for gateway or self-hosted model ids that LiteLLM can't price.
-</ParamField>
-
-<ParamField path="STRIX_LLM_OUTPUT_COST_PER_MTOK" type="number">
-  Price per 1M output tokens in USD for `STRIX_LLM`.
-</ParamField>
-
-<ParamField path="STRIX_LLM_CACHED_INPUT_COST_PER_MTOK" type="number">
-  Price per 1M cached input tokens in USD for `STRIX_LLM`. If unset, cached tokens use the input price.
-</ParamField>
-
-<Note>
-  Setting any of these prices replaces the provider-reported and LiteLLM cost for `STRIX_LLM` in reports and `--max-budget`. An unset input or output price counts as `0`, so set both. A separate `STRIX_DEDUPE_MODEL` keeps its LiteLLM price.
-</Note>
-
 <ParamField path="STRIX_API_TYPE" type="string">
   Select the OpenAI API path for the model: `responses` or `chat_completions`.
-  By default the model decides: Responses when LiteLLM's model catalog lists
-  `/v1/responses` for it (e.g. `gpt-5`), chat completions otherwise. A custom
-  `LLM_API_BASE` does not change this, so set `STRIX_API_TYPE=chat_completions`
-  when your gateway only serves chat completions. Applies to bare and `openai/`
-  model names. Also accepts `STRIX_FORCE_API`.
+  By default, a custom `LLM_API_BASE` uses chat completions. Set this variable
+  when your gateway requires the other API. Also accepts `STRIX_FORCE_API`.
 </ParamField>
 
 <ParamField path="LLM_EXTRA_HEADERS" type="string">
@@ -186,7 +167,7 @@ When remote vars are set, Strix dual-writes telemetry to both local JSONL and th
 
 ## Docker Configuration
 
-<ParamField path="STRIX_IMAGE" default="ghcr.io/usestrix/strix-sandbox:1.4.0" type="string">
+<ParamField path="STRIX_IMAGE" default="ghcr.io/usestrix/strix-sandbox:1.3.0" type="string">
   Docker image to use for the sandbox container.
 </ParamField>
 

docs/docs.json

@@ -35,8 +35,8 @@
               "llm-providers/overview",
               "llm-providers/openai",
               "llm-providers/anthropic",
-              "llm-providers/vercel-ai-gateway",
               "llm-providers/openrouter",
+              "llm-providers/vercel-ai-gateway",
               "llm-providers/vertex",
               "llm-providers/bedrock",
               "llm-providers/azure",

docs/index.mdx

@@ -73,20 +73,7 @@ Strix uses a graph of specialized agents for comprehensive security testing:
 
 ## Quick Example
 
-<CodeGroup>
-```bash Vercel AI Gateway
-# Install
-curl -sSL https://strix.ai/install | bash
-
-# Configure
-export STRIX_LLM="vercel_ai_gateway/zai/glm-5.3"
-export LLM_API_KEY="your-api-key"
-
-# Scan
-strix --target ./your-app
-```
-
-```bash OpenRouter
+```bash
 # Install
 curl -sSL https://strix.ai/install | bash
 
@@ -97,7 +84,6 @@ export LLM_API_KEY="your-api-key"
 # Scan
 strix --target ./your-app
 ```
-</CodeGroup>
 
 ## Community
 

docs/llm-providers/anthropic.mdx

@@ -6,7 +6,7 @@ description: "Configure Strix with Claude models"
 ## Setup
 
 ```bash
-export STRIX_LLM="anthropic/claude-sonnet-5-5"
+export STRIX_LLM="anthropic/claude-sonnet-4-6"
 export LLM_API_KEY="sk-ant-..."
 ```
 
@@ -14,12 +14,8 @@ export LLM_API_KEY="sk-ant-..."
 
 | Model | Description |
 |-------|-------------|
-| `anthropic/claude-sonnet-5-5` | Best balance of intelligence and speed |
-| `anthropic/claude-opus-5-5` | Maximum capability for deep analysis |
-
-<Note>
-Security testing with Claude needs the [Cyber Verification Program](https://support.claude.com/en/articles/14604842-cyber-verification-program) (CVP). Without it the safety classifiers block most offensive tasks. Red Team Access covers authorized penetration testing.
-</Note>
+| `anthropic/claude-sonnet-4-6` | Best balance of intelligence and speed |
+| `anthropic/claude-opus-4-6` | Maximum capability for deep analysis |
 
 ## Get API Key
 

docs/llm-providers/azure.mdx

@@ -6,7 +6,7 @@ description: "Configure Strix with OpenAI models via Azure"
 ## Setup
 
 ```bash
-export STRIX_LLM="azure/your-gpt6-deployment"
+export STRIX_LLM="azure/your-gpt5-deployment"
 export AZURE_API_KEY="your-azure-api-key"
 export AZURE_API_BASE="https://your-resource.openai.azure.com"
 export AZURE_API_VERSION="2025-11-01-preview"
@@ -24,7 +24,7 @@ export AZURE_API_VERSION="2025-11-01-preview"
 ## Example
 
 ```bash
-export STRIX_LLM="azure/gpt-6.1-sol-deployment"
+export STRIX_LLM="azure/gpt-5.4-deployment"
 export AZURE_API_KEY="abc123..."
 export AZURE_API_BASE="https://mycompany.openai.azure.com"
 export AZURE_API_VERSION="2025-11-01-preview"
@@ -33,9 +33,5 @@ export AZURE_API_VERSION="2025-11-01-preview"
 ## Prerequisites
 
 1. Create an Azure OpenAI resource
-2. Deploy a model such as GPT-6.1 Sol
+2. Deploy a model (e.g., GPT-5.4)
 3. Get the endpoint URL and API key from the Azure portal
-
-<Note>
-Security testing with OpenAI models needs [Daybreak](https://openai.com/daybreak/) access, also on Azure.
-</Note>

docs/llm-providers/bedrock.mdx

@@ -6,7 +6,7 @@ description: "Configure Strix with models via AWS Bedrock"
 ## Setup
 
 ```bash
-export STRIX_LLM="bedrock/us.anthropic.claude-sonnet-5-5"
+export STRIX_LLM="bedrock/anthropic.claude-4-5-sonnet-20251022-v1:0"
 ```
 
 No API key required—uses AWS credentials from environment.
@@ -36,13 +36,10 @@ Automatically uses instance role credentials.
 
 | Model | Description |
 |-------|-------------|
-| `bedrock/us.anthropic.claude-sonnet-5-5` | Claude Sonnet 5.5 |
-| `bedrock/us.anthropic.claude-opus-5-5` | Claude Opus 5.5 |
-| `bedrock/us.anthropic.claude-haiku-5-5` | Claude Haiku 5.5 |
-
-<Note>
-Security testing with Claude needs the [Cyber Verification Program](https://support.claude.com/en/articles/14604842-cyber-verification-program) (CVP), also on Bedrock.
-</Note>
+| `bedrock/anthropic.claude-4-5-sonnet-20251022-v1:0` | Claude 4.5 Sonnet |
+| `bedrock/anthropic.claude-4-5-opus-20251022-v1:0` | Claude 4.5 Opus |
+| `bedrock/anthropic.claude-4-5-haiku-20251022-v1:0` | Claude 4.5 Haiku |
+| `bedrock/amazon.titan-text-premier-v2:0` | Amazon Titan Premier v2 |
 
 ## Prerequisites
 

docs/llm-providers/novita.mdx

@@ -8,7 +8,7 @@ description: "Configure Strix with Novita AI models"
 ## Setup
 
 ```bash
-export STRIX_LLM="openai/zai-org/glm-5.3"
+export STRIX_LLM="openai/moonshotai/kimi-k2.5"
 export LLM_API_KEY="your-novita-api-key"
 export LLM_API_BASE="https://api.novita.ai/openai"
 ```
@@ -18,12 +18,11 @@ export LLM_API_BASE="https://api.novita.ai/openai"
 | Model | Configuration |
 |-------|---------------|
 | GLM-5.3 | `openai/zai-org/glm-5.3` |
-| Kimi K3.1 Pro | `openai/moonshotai/kimi-k3.1-pro` |
 | Kimi K3 | `openai/moonshotai/kimi-k3` |
-| DeepSeek V4.1 Flash | `openai/deepseek/deepseek-v4.1-flash-1017` |
 | DeepSeek V4 Pro | `openai/deepseek/deepseek-v4-pro` |
-| MiniMax M3.1 Flash | `openai/minimax/minimax-m3.1-flash` |
-| GLM-5.3 Flash | `openai/zai-org/glm-5.3-flash` |
+| Kimi K2.5 | `openai/moonshotai/kimi-k2.5` |
+| GLM-5 | `openai/zai-org/glm-5` |
+| MiniMax M2.5 | `openai/minimax/minimax-m2.5` |
 
 ## Get API Key
 

docs/llm-providers/openai.mdx

@@ -6,23 +6,13 @@ description: "Configure Strix with OpenAI models"
 ## Setup
 
 ```bash
-export STRIX_LLM="openai/gpt-6.1-sol"
+export STRIX_LLM="openai/gpt-5.4"
 export LLM_API_KEY="sk-..."
 ```
 
 ## Available Models
 
-| Model | Description |
-|-------|-------------|
-| `openai/gpt-6.1-sol` | Best balance of capability and cost for agentic security work |
-| `openai/gpt-6-astra` | Flagship, maximum capability |
-| `openai/gpt-6-luna` | Fast and cheap |
-
-See [OpenAI Models Documentation](https://platform.openai.com/docs/models) for the full list.
-
-<Note>
-Security testing with OpenAI models needs [Daybreak](https://openai.com/daybreak/) (Trusted Access for Cyber). Without it the models refuse most offensive tasks. [Request access](https://openai.com/form/enterprise-trusted-access-for-cyber/).
-</Note>
+See [OpenAI Models Documentation](https://platform.openai.com/docs/models) for the full list of available models.
 
 ## Get API Key
 
@@ -35,7 +25,7 @@ Security testing with OpenAI models needs [Daybreak](https://openai.com/daybreak
 For OpenAI-compatible APIs:
 
 ```bash
-export STRIX_LLM="openai/gpt-6.1-sol"
+export STRIX_LLM="openai/gpt-5.4"
 export LLM_API_KEY="your-key"
 export LLM_API_BASE="https://your-proxy.com/v1"
 ```

docs/llm-providers/openrouter.mdx

@@ -18,19 +18,13 @@ Access any model on OpenRouter using the format `openrouter/<provider>/<model>`:
 
 | Model | Configuration |
 |-------|---------------|
-| GLM-5.3 (recommended) | `openrouter/z-ai/glm-5.3` |
-| GPT-6.1 Sol | `openrouter/openai/gpt-6.1-sol` |
-| GPT-6 Astra | `openrouter/openai/gpt-6-astra` |
-| Claude Opus 5.5 | `openrouter/anthropic/claude-opus-5.5` |
-| Claude Sonnet 5.5 | `openrouter/anthropic/claude-sonnet-5.5` |
-| Gemini 4 Argon | `openrouter/google/gemini-4-argon` |
-| Gemini 3.8 Flash | `openrouter/google/gemini-3.8-flash` |
-| DeepSeek V4.1 Flash | `openrouter/deepseek/deepseek-v4.1-flash-1017` |
+| GLM-5.3 (default) | `openrouter/z-ai/glm-5.3` |
+| GPT-5.4 | `openrouter/openai/gpt-5.4` |
+| Claude Sonnet 4.6 | `openrouter/anthropic/claude-sonnet-4.6` |
+| Gemini 3 Pro | `openrouter/google/gemini-3-pro-preview` |
 | DeepSeek V4 Pro | `openrouter/deepseek/deepseek-v4-pro` |
-| Kimi K3.1 Pro | `openrouter/moonshotai/kimi-k3.1-pro` |
-| GLM-5.3 Flash | `openrouter/z-ai/glm-5.3-flash` |
-
-OpenAI, Anthropic and Gemini models keep their provider safeguards on OpenRouter. Security testing with them needs [Daybreak](https://openai.com/daybreak/), [CVP](https://support.claude.com/en/articles/14604842-cyber-verification-program) or [Fairwind](https://deepmind.google/fairwind-program/) access.
+| Kimi K3 | `openrouter/moonshotai/kimi-k3` |
+| GLM-4.7 | `openrouter/z-ai/glm-4.7` |
 
 ## Get API Key
 

docs/llm-providers/overview.mdx

@@ -9,33 +9,19 @@ Strix uses [LiteLLM](https://docs.litellm.ai/docs/providers) for model compatibi
 
 Set your model and API key:
 
-| Model                 | Provider                  | Configuration                    |
-| --------------------- | ------------------------- | -------------------------------- |
-| GLM-5.3 (recommended) | Vercel AI Gateway         | `vercel_ai_gateway/zai/glm-5.3`  |
-| GLM-5.3 (recommended) | OpenRouter                | `openrouter/z-ai/glm-5.3`        |
-| GPT-6.1 Sol           | OpenAI                    | `openai/gpt-6.1-sol`             |
-| Claude Opus 5.5       | Anthropic                 | `anthropic/claude-opus-5-5`      |
-| Claude Sonnet 5.5     | Anthropic                 | `anthropic/claude-sonnet-5-5`    |
-| Gemini 4 Argon        | Google Vertex             | `vertex_ai/gemini-4-argon`       |
-| DeepSeek V4.1 Flash   | DeepSeek                  | `deepseek/deepseek-flash`        |
-| DeepSeek V4 Pro       | DeepSeek                  | `deepseek/deepseek-v4-pro`       |
-| Kimi K3.1 Pro         | Moonshot                  | `moonshot/kimi-k3.1-pro`         |
+| Model                | Provider          | Configuration                    |
+| -------------------- | ----------------- | -------------------------------- |
+| GLM-5.3 (default)    | Z.ai (OpenRouter) | `openrouter/z-ai/glm-5.3`        |
+| GPT-5.4              | OpenAI            | `openai/gpt-5.4`                 |
+| Claude Sonnet 4.6    | Anthropic         | `anthropic/claude-sonnet-4-6`    |
+| Gemini 3 Pro         | Google Vertex     | `vertex_ai/gemini-3-pro-preview` |
+| DeepSeek V4 Pro      | DeepSeek          | `deepseek/deepseek-v4-pro`       |
+| Kimi K3              | Moonshot          | `moonshot/kimi-k3`               |
 
-<Note>
-Frontier OpenAI, Anthropic and Gemini models need a cyber access program for security testing: [Daybreak](https://openai.com/daybreak/) for OpenAI, the [Cyber Verification Program](https://support.claude.com/en/articles/14604842-cyber-verification-program) for Anthropic, and the [Fairwind Program](https://deepmind.google/fairwind-program/) for Gemini.
-</Note>
-
-<CodeGroup>
-```bash Vercel AI Gateway
-export STRIX_LLM="vercel_ai_gateway/zai/glm-5.3"
-export LLM_API_KEY="your-api-key"
-```
-
-```bash OpenRouter
+```bash
 export STRIX_LLM="openrouter/z-ai/glm-5.3"
 export LLM_API_KEY="your-api-key"
 ```
-</CodeGroup>
 
 ## Local Models
 
@@ -61,7 +47,7 @@ See the [Local Models guide](/llm-providers/local) for setup instructions and re
     Access 100+ models through a single API.
   </Card>
   <Card title="Vercel AI Gateway" href="/llm-providers/vercel-ai-gateway">
-    Access 100+ models through one OpenAI-compatible endpoint.
+    Access models from multiple providers through one endpoint.
   </Card>
   <Card title="Google Vertex AI" href="/llm-providers/vertex">
     Gemini 3 models via Google Cloud.
@@ -83,9 +69,9 @@ Use LiteLLM's `provider/model-name` format:
 
 ```
 openrouter/z-ai/glm-5.3
-openai/gpt-6.1-sol
-anthropic/claude-sonnet-5-5
-vertex_ai/gemini-4-argon
-bedrock/us.anthropic.claude-sonnet-5-5
+openai/gpt-5.4
+anthropic/claude-sonnet-4-6
+vertex_ai/gemini-3-pro-preview
+bedrock/anthropic.claude-4-5-sonnet-20251022-v1:0
 ollama/llama4
 ```

docs/llm-providers/vercel-ai-gateway.mdx

@@ -1,47 +1,32 @@
 ---
 title: "Vercel AI Gateway"
-description: "Configure Strix with models through Vercel AI Gateway"
+description: "Configure Strix with models via Vercel AI Gateway"
 ---
 
-[Vercel AI Gateway](https://vercel.com/docs/ai-gateway) provides access to 100+ models from multiple providers through one OpenAI-compatible API.
+[Vercel AI Gateway](https://vercel.com/docs/ai-gateway) provides an OpenAI-compatible API for models from multiple providers.
 
 ## Setup
 
 Create an [AI Gateway API key](https://vercel.com/docs/ai-gateway/authentication-and-byok), then configure Strix:
 
 ```bash
-export STRIX_LLM="vercel_ai_gateway/zai/glm-5.3"
+export STRIX_LLM="openai/anthropic/claude-opus-5"
 export LLM_API_KEY="your-ai-gateway-api-key"
+export LLM_API_BASE="https://ai-gateway.vercel.sh/v1"
 ```
 
-The `vercel_ai_gateway/` prefix selects the Gateway. The remaining value is the [AI Gateway model ID](https://vercel.com/docs/ai-gateway/models-and-providers).
+The first `openai/` segment tells Strix to use its OpenAI-compatible client. The remaining value is the [AI Gateway model ID](https://vercel.com/docs/ai-gateway/models-and-providers).
 
 ## Available Models
 
-Access any model on the Gateway using the format `vercel_ai_gateway/<provider>/<model>`:
-
-| Model | Configuration |
-|-------|---------------|
-| GLM-5.3 (recommended) | `vercel_ai_gateway/zai/glm-5.3` |
-| GPT-6.1 Sol | `vercel_ai_gateway/openai/gpt-6.1-sol` |
-| GPT-6 Astra | `vercel_ai_gateway/openai/gpt-6-astra` |
-| Claude Opus 5.5 | `vercel_ai_gateway/anthropic/claude-opus-5.5` |
-| Claude Sonnet 5.5 | `vercel_ai_gateway/anthropic/claude-sonnet-5.5` |
-| Gemini 4 Argon | `vercel_ai_gateway/google/gemini-4-argon` |
-| Gemini 3.8 Flash | `vercel_ai_gateway/google/gemini-3.8-flash` |
-| DeepSeek V4.1 Flash | `vercel_ai_gateway/deepseek/deepseek-v4.1-flash-1017` |
-| DeepSeek V4 Pro | `vercel_ai_gateway/deepseek/deepseek-v4-pro` |
-| Kimi K3.1 Pro | `vercel_ai_gateway/moonshotai/kimi-k3.1-pro` |
-| GLM-5.3 Flash | `vercel_ai_gateway/zai/glm-5.3-flash` |
-
-OpenAI, Anthropic and Gemini models keep their provider safeguards on the Gateway. Security testing with them needs [Daybreak](https://openai.com/daybreak/), [CVP](https://support.claude.com/en/articles/14604842-cyber-verification-program) or [Fairwind](https://deepmind.google/fairwind-program/) access.
-
-The full list is at the [AI Gateway models page](https://vercel.com/ai-gateway/models) or the models endpoint:
+Use any language model returned by the AI Gateway models endpoint:
 
 ```text
 https://ai-gateway.vercel.sh/v1/models
 ```
 
+Prefix its model ID with `openai/` when setting `STRIX_LLM`. For example, the Gateway model ID `anthropic/claude-opus-5` becomes `openai/anthropic/claude-opus-5` in Strix.
+
 ## Get API Key
 
 1. Open the [AI Gateway API key settings](https://vercel.com/docs/ai-gateway/authentication-and-byok)
@@ -50,6 +35,5 @@ https://ai-gateway.vercel.sh/v1/models
 
 ## Benefits
 
-- **Single API** — Access models from OpenAI, Anthropic, Google, Z.ai, and more
-- **Bring your own keys** — Route through your own provider accounts when you want
-- **Cost tracking** — Monitor Gateway usage and cost in Vercel
+- Access models from multiple providers through one endpoint
+- Track Gateway usage and cost in Vercel

docs/llm-providers/vertex.mdx

@@ -6,7 +6,7 @@ description: "Configure Strix with Gemini models via Google Cloud"
 ## Setup
 
 ```bash
-export STRIX_LLM="vertex_ai/gemini-4-argon"
+export STRIX_LLM="vertex_ai/gemini-3-pro-preview"
 ```
 
 No API key required—uses Google Cloud Application Default Credentials.
@@ -29,12 +29,8 @@ export GOOGLE_APPLICATION_CREDENTIALS="/path/to/service-account.json"
 
 | Model | Description |
 |-------|-------------|
-| `vertex_ai/gemini-4-argon` | Best overall performance for security testing |
-| `vertex_ai/gemini-3.8-flash` | Faster and cheaper |
-
-<Note>
-Security testing with Gemini needs the [Fairwind Program](https://deepmind.google/fairwind-program/). Without it the cyber guardrails block most offensive tasks.
-</Note>
+| `vertex_ai/gemini-3-pro-preview` | Best overall performance for security testing |
+| `vertex_ai/gemini-3-flash-preview` | Faster and cheaper |
 
 ## Project Configuration
 

docs/quickstart.mdx

@@ -25,22 +25,15 @@ description: "Install Strix and run your first security scan"
 
 ## Configuration
 
-Set your LLM provider. We recommend GLM-5.3 through [Vercel AI Gateway](/llm-providers/vercel-ai-gateway) or [OpenRouter](/llm-providers/openrouter):
+Set your LLM provider:
 
-<CodeGroup>
-```bash Vercel AI Gateway
-export STRIX_LLM="vercel_ai_gateway/zai/glm-5.3"
-export LLM_API_KEY="your-api-key"
-```
-
-```bash OpenRouter
+```bash
 export STRIX_LLM="openrouter/z-ai/glm-5.3"
 export LLM_API_KEY="your-api-key"
 ```
-</CodeGroup>
 
 <Tip>
-For best results, use `zai/glm-5.3`, `deepseek/deepseek-v4.1-flash-1017`, `anthropic/claude-opus-5-5` (needs [CVP](https://support.claude.com/en/articles/14604842-cyber-verification-program) access), or `openai/gpt-6.1-sol` (needs [Daybreak](https://openai.com/daybreak/) access).
+For best results, use `openrouter/z-ai/glm-5.3` (the default pick), `openai/gpt-5.4`, `anthropic/claude-opus-4-6`, or `openai/gpt-5.2`.
 </Tip>
 
 ## Run Your First Scan

docs/tools/sandbox.mdx

@@ -49,7 +49,7 @@ Strix runs inside a Kali Linux-based Docker container with a comprehensive set o
 
 | Tool                                                    | Description                                   |
 | ------------------------------------------------------- | --------------------------------------------- |
-| [Opengrep](https://github.com/opengrep/opengrep)        | Fast SAST and custom rule matching            |
+| [Semgrep](https://github.com/semgrep/semgrep)          | Fast SAST and custom rule matching            |
 | [ast-grep](https://ast-grep.github.io)                 | Structural AST/CST-aware code search (`sg`)   |
 | [Tree-sitter](https://tree-sitter.github.io/tree-sitter/) | Syntax tree parsing and symbol extraction (Java/JS/TS/Python/Go/Bash/JSON/YAML grammars pre-configured) |
 | [Bandit](https://bandit.readthedocs.io)                | Python security linter                        |

docs/tools/terminal.mdx

@@ -33,7 +33,7 @@ sqlmap -u "https://example.com/page?id=1"
 
 ```bash
 # Fast SAST triage
-opengrep scan --config /opt/opengrep-rules ./src
+semgrep --config auto ./src
 
 # Structural AST search
 sg scan ./src

docs/usage/scan-modes.mdx

@@ -46,7 +46,7 @@ Thorough penetration testing. Best for:
 
 **Duration**: 1-4 hours depending on target complexity
 
-**White-box behavior**: Runs broad source-aware triage (`opengrep`, AST structural search, secrets, supply-chain checks) and then systematically validates top candidates dynamically.
+**White-box behavior**: Runs broad source-aware triage (`semgrep`, AST structural search, secrets, supply-chain checks) and then systematically validates top candidates dynamically.
 
 <Note>
 Deep mode is the default. It explores edge cases, chained vulnerabilities, and complex attack paths.

scripts/install.sh

@@ -4,7 +4,7 @@ set -euo pipefail
 
 APP=strix
 REPO="usestrix/strix"
-STRIX_IMAGE="ghcr.io/usestrix/strix-sandbox:1.4.0"
+STRIX_IMAGE="ghcr.io/usestrix/strix-sandbox:1.3.0"
 
 MUTED='\033[0;2m'
 RED='\033[0;31m'

skills/ci-security-scanning-with-strix/SKILL.md

@@ -63,7 +63,7 @@ jobs:
           fi
 ```
 
-Then tell the user to add two repository secrets: `STRIX_LLM` (model id, for example `openrouter/z-ai/glm-5.3`) and `LLM_API_KEY` (the provider key). Do not create these values yourself.
+Then tell the user to add two repository secrets: `STRIX_LLM` (model id, for example `openai/gpt-5.4`) and `LLM_API_KEY` (the provider key). Do not create these values yourself.
 
 Notes:
 - In CI/headless runs Strix automatically scopes to the PR's changed files (`--scope-mode auto`). If diff resolution fails, keep `fetch-depth: 0` or set `--diff-base` to the PR's actual base branch — use `origin/${{ github.base_ref }}` in GitHub Actions rather than a hard-coded `origin/main`, since repos use different default branches.

skills/penetration-testing-with-strix/SKILL.md

@@ -47,7 +47,7 @@ If unsure and the user has (or will create) an app.strix.ai account, prefer **Cl
    ```
 3. **LLM configured** — two environment variables:
    ```bash
-   export STRIX_LLM="openrouter/z-ai/glm-5.3"      # any LiteLLM model id (openai/..., anthropic/..., openrouter/...)
+   export STRIX_LLM="openai/gpt-5.4"      # any LiteLLM model id (openai/..., anthropic/..., openrouter/...)
    export LLM_API_KEY="<provider api key>"
    ```
    Ask the user for these if unset. Never hardcode or commit keys.

strix/agents/prompts/system_prompt.jinja

@@ -115,11 +115,11 @@ BLACK-BOX TESTING (domain/subdomain only):
 
 WHITE-BOX TESTING (code provided):
 - MUST perform BOTH static AND dynamic analysis
-- Static: Use source-aware triage first to map risk quickly (`opengrep`, `ast-grep`, Tree-sitter tooling, `gitleaks`, `trufflehog`, `trivy fs`). Then review code for vulnerabilities
+- Static: Use source-aware triage first to map risk quickly (`semgrep`, `ast-grep`, Tree-sitter tooling, `gitleaks`, `trufflehog`, `trivy fs`). Then review code for vulnerabilities
 - Static coverage floor: execute at least one structural AST mapping pass (`sg` and/or Tree-sitter) per repository and keep artifact output
-- Static coverage target per repository: run one `opengrep` pass, one secrets pass (`gitleaks` and/or `trufflehog`), one `trivy fs` pass, and one AST-structural pass (`sg` and/or Tree-sitter)
+- Static coverage target per repository: run one `semgrep` pass, one secrets pass (`gitleaks` and/or `trufflehog`), one `trivy fs` pass, and one AST-structural pass (`sg` and/or Tree-sitter)
 - Keep AST artifacts bounded and high-signal: scope to relevant paths/hypotheses, avoid whole-repo generic function dumps
-- AST target selection rule: build `sg-targets.txt` from `opengrep.json` scope first (`paths.scanned`, fallback to unique `results[].path`), then run `xargs ... sg run` against that file list. Only use path-heuristic fallback if opengrep scope is unavailable.
+- AST target selection rule: build `sg-targets.txt` from `semgrep.json` scope first (`paths.scanned`, fallback to unique `results[].path`), then run `xargs ... sg run` against that file list. Only use path-heuristic fallback if semgrep scope is unavailable.
 - Dynamic: Run the application and test live to validate exploitability
 - NEVER rely solely on static code analysis when dynamic validation is possible
 - Begin with fast source triage and dynamic run preparation in parallel; use static findings to prioritize live testing.
@@ -188,7 +188,7 @@ EFFICIENCY TACTICS:
 - For Caido proxy automation inside Python, explicitly import from
   `caido_api`:
   `from caido_api import list_requests, view_request, repeat_request, list_sitemap, view_sitemap_entry, scope_rules`
-- Prefer established fuzzers/scanners where applicable: ffuf, sqlmap, nuclei, wapiti, arjun, httpx, katana, opengrep, bandit, trufflehog, nmap. Use scripts mainly to coordinate or validate around them, not to replace them without reason
+- Prefer established fuzzers/scanners where applicable: ffuf, sqlmap, nuclei, wapiti, arjun, httpx, katana, semgrep, bandit, trufflehog, nmap. Use scripts mainly to coordinate or validate around them, not to replace them without reason
 - For trial-heavy vectors (SQLi, XSS, XXE, SSRF, RCE, auth/JWT, deserialization), DO NOT iterate payloads manually in the browser. Always spray payloads via Python scripts through `exec_command` or terminal tools.
 - When using established fuzzers/scanners, use the proxy for inspection where helpful
 - Generate/adapt large payload corpora: combine encodings (URL, unicode, base64), comment styles, wrappers, time-based/differential probes. Expand with wordlists/templates
@@ -458,7 +458,7 @@ JAVASCRIPT ANALYSIS:
 - js-beautify - JS beautifier/deobfuscator
 
 CODE ANALYSIS:
-- opengrep - Static analysis/SAST (bundled rules in /opt/opengrep-rules)
+- semgrep - Static analysis/SAST
 - ast-grep (sg) - Structural AST/CST-aware code search
 - tree-sitter - Syntax-aware parsing and symbol extraction support
 - bandit - Python security linter

strix/config/models.py

@@ -713,7 +713,7 @@ def configure_sdk_model_defaults(settings: Settings) -> None:
     if codex.subscription_model(llm.model):
         return
     _configure_litellm_compatibility()
-    _configure_attribution(llm.model)
+    _configure_openrouter_attribution(llm.model)
     if llm.api_key:
         set_default_openai_key(llm.api_key, use_for_tracing=False)
         _configure_litellm_default("api_key", llm.api_key)
@@ -884,13 +884,9 @@ def _openrouter_error_type(error: object) -> object:
     return None
 
 
-APP_ATTRIBUTION_HEADERS = {
+OPENROUTER_ATTRIBUTION_HEADERS = {
     "HTTP-Referer": "https://strix.ai",
     "X-Title": "Strix",
-}
-
-OPENROUTER_ATTRIBUTION_HEADERS = {
-    **APP_ATTRIBUTION_HEADERS,
     "X-OpenRouter-Categories": "cli-agent",
 }
 
@@ -899,25 +895,20 @@ def is_openrouter_model(model_name: str | None) -> bool:
     return bool(model_name) and "openrouter/" in (model_name or "").strip().lower()
 
 
-def is_vercel_ai_gateway_model(model_name: str | None) -> bool:
-    return (model_name or "").strip().lower().startswith("vercel_ai_gateway/")
-
-
-def attribution_headers(model_name: str | None) -> dict[str, str]:
-    if is_openrouter_model(model_name):
-        return OPENROUTER_ATTRIBUTION_HEADERS
-    if is_vercel_ai_gateway_model(model_name):
-        return APP_ATTRIBUTION_HEADERS
-    return {}
-
-
-def _configure_attribution(model_name: str | None) -> None:
+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 {}
-    remaining = {k: v for k, v in existing.items() if k not in OPENROUTER_ATTRIBUTION_HEADERS}
-    litellm.headers = {**remaining, **attribution_headers(model_name)} or None  # type: ignore[assignment]
+    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
+            }
+            litellm.headers = remaining or None  # type: ignore[assignment]
+        return
+
+    litellm.headers = {**existing, **OPENROUTER_ATTRIBUTION_HEADERS}  # type: ignore[assignment]
 
 
 def _configure_extra_headers(llm: LlmSettings) -> None:

strix/config/settings.py

@@ -61,15 +61,6 @@ class LlmSettings(BaseSettings):
         repr=False,
     )
     reasoning_effort: ReasoningEffort = Field(default="high", alias="STRIX_REASONING_EFFORT")
-    input_cost_per_mtok: float | None = Field(
-        default=None, ge=0, allow_inf_nan=False, alias="STRIX_LLM_INPUT_COST_PER_MTOK"
-    )
-    output_cost_per_mtok: float | None = Field(
-        default=None, ge=0, allow_inf_nan=False, alias="STRIX_LLM_OUTPUT_COST_PER_MTOK"
-    )
-    cached_input_cost_per_mtok: float | None = Field(
-        default=None, ge=0, allow_inf_nan=False, alias="STRIX_LLM_CACHED_INPUT_COST_PER_MTOK"
-    )
     force_required_tool_choice: bool = Field(
         default=False,
         alias="STRIX_FORCE_REQUIRED_TOOL_CHOICE",
@@ -164,7 +155,7 @@ class RuntimeSettings(BaseSettings):
     model_config = _BASE_CONFIG
 
     image: str = Field(
-        default="ghcr.io/usestrix/strix-sandbox:1.4.0",
+        default="ghcr.io/usestrix/strix-sandbox:1.3.0",
         alias="STRIX_IMAGE",
     )
     backend: str = Field(default="docker", alias="STRIX_RUNTIME_BACKEND")

strix/core/inputs.py

@@ -10,11 +10,12 @@ from openai.types.shared import Reasoning
 
 from strix.config.models import (
     DEFAULT_MODEL_RETRY,
-    attribution_headers,
+    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,
     routes_through_litellm,
@@ -286,7 +287,9 @@ def make_model_settings(
 def _request_headers(
     model_name: str, extra_headers: dict[str, str] | None
 ) -> dict[str, str] | None:
-    headers: dict[str, str] = dict(attribution_headers(model_name))
+    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

strix/core/runner.py

@@ -181,7 +181,7 @@ def _compose_root_instructions_override(
     supports_images: bool,
     report_tool: str,
     coverage_tools: bool,
-    replace_scan_prompt: bool = False,
+    replace_scan_prompt: bool,
 ) -> str | None:
     if root_instructions_override is None:
         return None

strix/report/dedupe.py

@@ -300,15 +300,7 @@ def _parse_dedupe_response(content: str) -> dict[str, Any]:
         raise ValueError(f"No JSON object found in dedupe response: {content[:500]}")
     parsed = json.loads(text[start : end + 1])
 
-    is_duplicate = parsed.get("is_duplicate")
-    if not isinstance(is_duplicate, bool):
-        raise TypeError("is_duplicate must be a boolean")
-    duplicate_id = parsed.get("duplicate_id") or ""
-    if is_duplicate and (not isinstance(duplicate_id, str) or not duplicate_id):
-        raise ValueError("A duplicate decision must name an existing report ID")
-    # Keep the ID verbatim: truncating or stripping it could turn an unknown ID
-    # into a different, existing one before the membership check below.
-    duplicate_id = str(duplicate_id)
+    duplicate_id = str(parsed.get("duplicate_id") or "")[:64]
     reason = str(parsed.get("reason") or "")[:500]
     try:
         confidence = float(parsed.get("confidence", 0.0))
@@ -316,22 +308,13 @@ def _parse_dedupe_response(content: str) -> dict[str, Any]:
         confidence = 0.0
 
     return {
-        "is_duplicate": is_duplicate,
+        "is_duplicate": bool(parsed.get("is_duplicate", False)),
         "duplicate_id": duplicate_id,
         "confidence": confidence,
         "reason": reason,
     }
 
 
-def _validate_duplicate_reference(
-    result: dict[str, Any], existing_reports: list[dict[str, Any]]
-) -> None:
-    if result["is_duplicate"] and not any(
-        report.get("id") == result["duplicate_id"] for report in existing_reports
-    ):
-        raise ValueError("Duplicate decision refers to an unknown report ID")
-
-
 def _extract_text(response: ModelResponse) -> str:
     parts: list[str] = []
     for item in response.output:
@@ -414,7 +397,6 @@ async def check_duplicate(
             }
 
         result = _parse_dedupe_response(content)
-        _validate_duplicate_reference(result, existing_reports)
 
         logger.info(
             "Deduplication check: is_duplicate=%s, confidence=%.2f, reason=%s",

strix/report/usage.py

@@ -8,38 +8,11 @@ from typing import Any
 from agents.usage import Usage, deserialize_usage, serialize_usage
 from pydantic import BaseModel, TypeAdapter, ValidationError
 
-from strix.config.loader import load_settings
 from strix.report.pricing import resolve_litellm_model
 
 
 logger = logging.getLogger(__name__)
 
-Prices = tuple[float | None, float | None, float | None]
-
-
-def _configured_prices() -> tuple[str | None, Prices | None]:
-    llm = load_settings().llm
-    prices = (llm.input_cost_per_mtok, llm.output_cost_per_mtok, llm.cached_input_cost_per_mtok)
-    if all(price is None for price in prices):
-        return None, None
-    return (llm.model or "").strip() or None, prices
-
-
-def _configured_usage_cost(usage: Usage, prices: Prices) -> float:
-    input_rate, output_rate, cached_rate = prices
-    input_tokens = max(0, _int_or_zero(getattr(usage, "input_tokens", 0)))
-    cached_details = getattr(usage, "input_tokens_details", None)
-    cached_tokens = max(0, _int_or_zero(getattr(cached_details, "cached_tokens", 0)))
-    cached_tokens = min(cached_tokens, input_tokens)
-    output_tokens = max(0, _int_or_zero(getattr(usage, "output_tokens", 0)))
-    billable_input = input_tokens - cached_tokens
-    cost = (
-        billable_input * (input_rate or 0)
-        + cached_tokens * (cached_rate if cached_rate is not None else input_rate or 0)
-        + output_tokens * (output_rate or 0)
-    ) / 1_000_000
-    return _round_cost(cost)
-
 
 class ProviderUsage(BaseModel):
     """Running totals for one upstream provider OpenRouter routed calls to."""
@@ -64,7 +37,6 @@ class LLMUsageLedger:
         self._total_usage = Usage()
         self._agent_usage: dict[str, Usage] = {}
         self._agent_metadata: dict[str, dict[str, str]] = {}
-        self._agent_estimated_cost: dict[str, float] = {}
         self._observed_cost = 0.0
         self._estimated_cost = 0.0
         self._has_observed_cost = False
@@ -101,9 +73,6 @@ class LLMUsageLedger:
             estimated = _estimate_litellm_cost(usage, model)
             if estimated:
                 self._estimated_cost += estimated
-                self._agent_estimated_cost[normalized_agent_id] = (
-                    self._agent_estimated_cost.get(normalized_agent_id, 0.0) + estimated
-                )
 
         return True
 
@@ -145,23 +114,11 @@ class LLMUsageLedger:
     def total_cost(self) -> float:
         if self.zero_cost:
             return 0.0
-        model, prices = _configured_prices()
-        if prices is not None:
-            return _round_cost(
-                sum(self._configured_agent_cost(aid, model, prices) for aid in self._agent_usage)
-            )
         return _round_cost(self._observed_cost if self._has_observed_cost else self._estimated_cost)
 
-    def _configured_agent_cost(self, agent_id: str, model: str | None, prices: Prices) -> float:
-        if self._agent_metadata.get(agent_id, {}).get("model") == model:
-            return _configured_usage_cost(self._agent_usage[agent_id], prices)
-        return self._agent_estimated_cost.get(agent_id, 0.0)
-
     def to_record(self) -> dict[str, Any]:
         record = serialize_usage(self._total_usage)
-        model, prices = _configured_prices()
-        total_cost = self.total_cost
-        record["cost"] = total_cost
+        record["cost"] = self.total_cost
         record["providers"] = {name: tally.model_dump() for name, tally in self._providers.items()}
         record["agents"] = []
 
@@ -171,11 +128,7 @@ class LLMUsageLedger:
             usage = self._agent_usage[agent_id]
             metadata = self._agent_metadata.get(agent_id, {})
             agent_cost = (
-                self._configured_agent_cost(agent_id, model, prices)
-                if prices is not None and not self.zero_cost
-                else 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)
@@ -195,7 +148,6 @@ class LLMUsageLedger:
         self._total_usage = Usage()
         self._agent_usage.clear()
         self._agent_metadata.clear()
-        self._agent_estimated_cost.clear()
         self._observed_cost = 0.0
         self._estimated_cost = 0.0
         self._has_observed_cost = False
@@ -231,7 +183,6 @@ class LLMUsageLedger:
                 logger.exception("Failed to hydrate llm_usage for agent %s", agent_id)
                 self._agent_usage[agent_id] = Usage()
 
-            self._agent_estimated_cost[agent_id] = _float_or_zero(raw_agent.get("cost"))
             metadata: dict[str, str] = {}
             agent_name = raw_agent.get("agent_name")
             model = raw_agent.get("model")

strix/skills/README.md

@@ -40,7 +40,7 @@ The skills are dynamically injected into the agent's system prompt, allowing it
 
 Notable source-aware skills:
 - `source_aware_whitebox` (coordination): white-box orchestration playbook
-- `source_aware_sast` (custom): opengrep/AST/secrets/supply-chain static triage workflow
+- `source_aware_sast` (custom): semgrep/AST/secrets/supply-chain static triage workflow
 - `dependency_cve_scanning` (custom): trivy-based SCA workflow for reporting known dependency CVEs via `create_dependency_report`
 - `npx_confusion` (custom): npx/npm exec/bunx fallback and adjacent package-runner identity confusion, with runner-specific registry and reporting gates
 - `semantic_confusion` (vulnerabilities): cross-boundary parser, normalization, and representation mismatch analysis

strix/skills/coordination/source_aware_whitebox.md

@@ -14,22 +14,22 @@ Increase white-box coverage by combining source-aware triage with dynamic valida
 ## Recommended Workflow
 
 1. Build a quick source map before deep exploitation, including at least one AST-structural pass (`sg` or `tree-sitter`) scoped to relevant paths.
-   - For `sg` baseline, derive `sg-targets.txt` from `opengrep.json` scope first (`paths.scanned`, fallback to unique `results[].path`) and run `xargs ... sg run` on that list.
-   - Only fall back to path heuristics when opengrep scope is unavailable.
+   - For `sg` baseline, derive `sg-targets.txt` from `semgrep.json` scope first (`paths.scanned`, fallback to unique `results[].path`) and run `xargs ... sg run` on that list.
+   - Only fall back to path heuristics when semgrep scope is unavailable.
 2. Run first-pass static triage to rank high-risk paths.
 3. Use triage outputs to prioritize dynamic PoC validation.
 4. Keep findings evidence-driven: no report without validation.
 
 ## Source-Aware Triage Stack
 
-- `opengrep`: fast security-first triage and custom pattern scans
+- `semgrep`: fast security-first triage and custom pattern scans
 - `ast-grep` (`sg`): structural pattern hunting and targeted repo mapping
 - `tree-sitter`: syntax-aware parsing support for symbol and route extraction
 - `gitleaks` + `trufflehog`: complementary secret detection (working tree and history coverage)
 - `trivy fs`: dependency, misconfiguration, license, and secret checks
 
 Coverage target per repository:
-- one `opengrep` pass
+- one `semgrep` pass
 - one AST structural pass (`sg` and/or `tree-sitter`)
 - one secrets pass (`gitleaks` and/or `trufflehog`)
 - one `trivy fs` pass

strix/skills/custom/dependency_cve_scanning.md

@@ -114,103 +114,99 @@ not just "upgrade <vulnerable pkg> to <fixed>".
 
 ### Usage / reachability analysis (required for every dependency CVE)
 
-Every CVE you report carries a verdict in `reachability`, the proof in
-`reachability_evidence`, and every usage site in `code_locations` (see
-Reporting). The verdict answers one question for THIS advisory in THIS
-codebase: does the vulnerable code run here? There are three answers and no
-"unknown". The tool rejects a report without a verdict or without evidence,
-so finish the analysis before you file.
+For every CVE you are about to report, run a static usage analysis and record
+the result in the structured `reachability` + `reachability_evidence` fields,
+and report every usage site you find as a `code_locations` entry (see Reporting).
+The level is an **evidence ladder, never an exploitability verdict** — claim
+only what you proved, and cite the proof. It never changes severity (that is
+`advisory_cvss` alone); it exists so the reader can prioritize.
 
-- **`reachable`** — the advisory's vulnerable code executes in this codebase:
-  application code, or a package it calls on the application's behalf, calls
-  the affected function, mode or feature. Evidence: the call site as
-  `file:line` and the source-to-sink trace (step 3).
-- **`not_reachable`** — the package is loaded by the shipped code, but this
-  CVE's vulnerable path does not execute here. Evidence: what you checked and
-  why the path is dead. Typical reasons: no caller of the affected API after
-  a complete search; the only call site is behind a condition that is false
-  here (a polyfill for an older runtime, a flag that is off, a dev-only
-  command); the parent package of a transitive dependency never references
-  the affected API; the flaw sits in a mode or option this code never uses;
-  the argument that triggers the flaw is a constant here.
-- **`not_applicable`** — the advisory does not apply to this codebase at all:
-  nothing the shipped code loads imports the package; it is build, test or
-  dev tooling the artifact never executes; the installed copy is a patched or
-  unaffected build; the flaw is specific to a platform this code does not run
-  on; or the only code that could use it cannot be inspected (a compiled
-  blob, a private bundle with no source) and nothing you can inspect reaches
-  it. Evidence: the search scope and the negative result.
+**Go — use govulncheck (real call-graph analysis):**
 
-The verdict is per CVE, not per package. Sibling CVEs on one package usually
-affect different symbols or modes (one hits a parser, another a header
-check): run the check against each advisory's own affected functions and
-never copy one CVE's verdict or evidence onto another. The import check
-(step 1) is the only step shared across a package's CVEs.
+```bash
+# Symbol-level: reports only vulnerabilities whose vulnerable functions are
+# actually reachable from application code. Needs the Go toolchain + module
+# deps; if either is missing, fall back to the checks below rather than
+# claiming a level.
+if command -v govulncheck >/dev/null && go version >/dev/null 2>&1; then
+  govulncheck -format json ./... > "$ART/govulncheck.json" || true
+fi
+```
 
-`reachable` is not an exploit, and `not_reachable` / `not_applicable` are
-not proof of safety (dynamic `import()`, reflection and framework wiring
-evade static search). Say what you checked; never write "not exploitable".
+- A finding with a call stack ⇒ `reachability=reachable_call_path`, put the
+  call-path excerpt (entrypoint → vulnerable function) in
+  `reachability_evidence`.
+- Listed as affecting a required module but with no reachable symbol ⇒ fall
+  back to the import/symbol checks below (`imported` / `not_imported`).
 
-**Procedure**
+**All other ecosystems — import check, then symbol match:**
 
 1. **Import check.** Search application code (exclude lockfiles, vendored
-   deps, `node_modules`, build output) for imports of the vulnerable package
-   under its ecosystem import name (`PyYAML` → `yaml`): `ast-grep`/`rg` for
-   `import`/`require`/`from X import`. For a **transitive** dependency nothing
-   in application code imports it, so walk every introducing chain from the
-   lockfile (e.g. `express > body-parser > qs`) and inspect the code of the
-   package one hop above the vulnerable one on each chain (`body-parser`, not
-   just `express`; its installed sources, or the class references of its
-   jar). Nothing imports it and no chain loads it ⇒ `not_applicable`, citing
-   the scope you searched. Loaded ⇒ continue.
-2. **Affected-symbol check, per CVE.** Read the advisory (GHSA/NVD/OSV
-   `affected[].ecosystem_specific.imports`, the advisory text, the fix commit
-   when the text is vague) for the functions, classes, options or modes that
-   trigger the flaw. Search application code, and the parent package of a
-   transitive dependency, for them (`ast-grep` pattern or `rg -n`; sibling
-   CVEs can share one multi-pattern search per package). No caller after a
-   complete search ⇒ `not_reachable`, citing the symbols and the scope. A
-   caller ⇒ step 3. When the flaw is in code every use of the package runs
-   (the parser the package exists for), the import itself is the call site ⇒
-   step 3.
-3. **Source-to-sink trace.** Start at the sink (the exact line that calls the
-   affected function) and walk backwards hop by hop to the source: the entry
-   point that carries the input (HTTP route, CLI argument, queue or webhook
-   payload, uploaded file, config value). Read each intermediate function;
-   when a hop is a thin wrapper, go one step deeper — never stop at the first
-   caller. Read what reaches the function: a constant argument that cannot
-   contain the triggering pattern, a flag that is off, a runtime-version
-   gate, a path only a dev tool runs means the vulnerable path does not run
-   ⇒ `not_reachable`, citing the condition. Otherwise ⇒ `reachable`. Write
-   the chain into `reachability_evidence` as
-   `entry point -> intermediate call -> package call` with a repo-relative
-   `file:line` for every hop, what each hop enforces (authentication, a role
-   check, validation, a size or type limit), and who controls the input. A
-   trusted or operator-only source does not soften the verdict: the code
-   runs, so it is `reachable`, and the trace is what tells the reader who can
-   reach it; the contextual CVSS carries that.
-4. **Go — govulncheck first.** When the Go toolchain and module deps are
-   present, `govulncheck -format json ./... > "$ART/govulncheck.json"` gives a
-   real call graph: a finding with a call stack ⇒ `reachable`, with the call
-   path (entrypoint → vulnerable function) as the trace; an affected module
-   with no reachable symbol ⇒ `not_reachable` when application code imports
-   it (cite the govulncheck result and the import), `not_applicable` when
-   nothing imports it. When govulncheck cannot analyze the module (build
-   errors, missing deps), run steps 1–3 instead of guessing.
+   deps, `node_modules`, build output) for imports of the vulnerable package:
+   `ast-grep`/`rg` for `import`/`require`/`from X import` of the package (and
+   its ecosystem import name, which may differ from the registry name, e.g.
+   `PyYAML` → `yaml`). No hits ⇒ `not_imported`, with the search scope stated
+   in `reachability_evidence`. For a **transitive** dependency, the check is
+   whether application code imports it directly; if not, it is reachable only
+   through the direct dependency — check whether the direct dep's usage can
+   hit it (if unclear, use `imported` when the direct dep is used at all).
+2. **Symbol match — per CVE, not per package.** Read each CVE's own advisory
+   (GHSA/NVD/OSV `affected[].ecosystem_specific.imports` or the advisory
+   text) for the affected functions/classes/APIs. Search application code for
+   those symbols (`ast-grep` pattern or `rg -n`). Hits ⇒
+   `vulnerable_symbol_used`, with repo-relative `file:line` of each hit (up
+   to a handful) in `reachability_evidence`. Imported but no affected-symbol
+   usage found (or the advisory names no symbols) ⇒ `imported`.
+   Different CVEs on the same package usually affect **different** symbols
+   (one hits a parser, another a header check) — never copy one CVE's
+   verdict/evidence onto its siblings; run the symbol search against each
+   CVE's own affected-symbol list. The import check (step 1) is the only
+   part shared across a package's CVEs.
+3. **Source-to-sink trace — do this whenever step 2 found a symbol hit.** A
+   symbol hit alone says the code calls the vulnerable API; it does not say
+   who can reach it. Start at the sink (the exact line that calls the
+   vulnerable function) and walk backwards hop by hop to the source: the
+   entry point that carries untrusted input (HTTP route, CLI argument, queue
+   or webhook payload, uploaded file, config value). Read each intermediate
+   function; when a hop is a thin wrapper, go one step deeper — never stop at
+   the first caller. Record what each hop enforces: authentication, a role
+   check, validation, a feature flag, a size or type limit, a default that is
+   off in production.
+   Write the chain into `reachability_evidence` as
+   `entry point -> intermediate call -> package call` with a
+   repository-relative `file:line` for every hop, and say who controls the
+   input. If no source reaches the sink, say that too — the level stays
+   `vulnerable_symbol_used` (the call is real), and the trace is what tells
+   the reader it is only reachable from, say, an operator CLI.
+4. If the analysis was not performed or is inconclusive (obfuscated code,
+   dynamic loading, unparsable sources) ⇒ `unknown` and say why in
+   `assumptions`.
 
-Work in severity order (critical, high and KEV first) so that if time runs
-out the low tail is what is missing, and name that tail in the scan summary.
-A CVE whose analysis you did not finish is neither filed with a guessed
-verdict nor filed as `not_applicable`: finish it, or report the gap. Never let
-the usage analysis silently drop a CVE: every advisory the scanner matched is
-either filed with a verdict or named in the summary as not analyzed.
+Cheap-first budgeting: the import check is one search per package — always do
+it. Do the per-CVE symbol match for every CVE whose advisory names affected
+symbols (they can be batched into one multi-pattern search per package);
+prioritize `critical`/`high`/KEV when the budget is tight; a CVE whose symbol
+search was skipped may still be reported as `imported` (the import check is
+real evidence), but its `reachability_evidence` must state that the
+affected-symbol check was not performed, so a skipped search is never
+mistaken for a completed one with no hits. Never let this analysis stall
+reporting — `unknown` with a reason beats an unverified claim.
 
-### Reachability is a verdict on the code path, not on severity
+Anti-overclaim rules:
 
-Do NOT suppress or downgrade a known CVE because its vulnerable code path is
-not reached. Report it with its verdict, set `advisory_cvss` from the
-advisory, put what the analysis proved in `reachability_evidence`, and use
-`assumptions` for anything softer. If you *can* actually trigger the
+- `not_imported` still does NOT mean safe (dynamic `import()`/reflection/
+  framework wiring evade static search) — never phrase it as "not exploitable".
+- `reachable_call_path` is reserved for call-graph tools (govulncheck); a
+  symbol grep hit is `vulnerable_symbol_used`, no matter how convinced you are.
+- The tool rejects any level other than `unknown` without
+  `reachability_evidence`.
+
+### Reachability is a confidence modifier, not a gate
+
+Do NOT suppress or downgrade a known CVE just because you could not prove the
+vulnerable code path is reachable. Report it, set `advisory_cvss` from the
+advisory, record the usage analysis in `reachability`/`reachability_evidence`,
+and use `assumptions` for anything softer. If you *can* actually trigger the
 vulnerable path or chain it into a dynamic exploit, additionally report that
 as a normal dynamic finding with `create_vulnerability_report` (the standalone
 CVE stays in its own `create_dependency_report`).
@@ -234,8 +230,8 @@ findings and rejects empty PoC fields):
   pins the vulnerable version. Each entry needs the repo-relative `file`, the
   exact `start_line` / `end_line`, the verbatim `snippet` at those lines, and a
   short `label` (e.g. "imports js-yaml", "calls yaml.load on CLI input"). Read
-  the real file to confirm the lines; never guess. When the verdict is
-  `not_applicable`, the manifest line is the only entry. If an entry carries
+  the real file to confirm the lines; never guess. When the package is
+  `not_imported`, the manifest line is the only entry. If an entry carries
   `fix_before` / `fix_after`, also fill `fix_verification`.
 - **Always fill the structured dependency fields** (they power the dedicated
   dependency-report card; do not leave them only in free-text):
@@ -264,8 +260,9 @@ findings and rejects empty PoC fields):
 - Do NOT cap severity at LOW just because there is no dynamic reproduction — use
   the advisory score.
 - Set `reachability` + `reachability_evidence` from the usage analysis above —
-  the tool rejects a report without a verdict or without evidence; use
-  `assumptions` for anything softer (confidence, caveats, analysis limits).
+  the tool rejects a report with no evidence, so for `unknown` write what you
+  searched and why the result is inconclusive;
+  use `assumptions` for anything softer (confidence, caveats, analysis limits).
 - **Always set `contextual_cvss_breakdown` + `contextual_cvss_reasoning`.** Every
   dependency finding carries a contextual rating of the CVE in this codebase
   (see below). Start from the published metrics and change only what your
@@ -299,8 +296,8 @@ evidence proves is different in this codebase:
   deployment requires before the path is reachable.
 - `scope` `U`/`C` — whether exploitation here escapes the component boundary.
 - `confidentiality`/`integrity`/`availability` `N`/`L`/`H` — the impact in this
-  codebase. A `not_applicable` package the build still ships is usually `N`
-  across all three.
+  codebase. `not_imported` code the build still ships is usually `N` across all
+  three.
 
 Ground every metric in the **source-to-sink trace** from the usage analysis
 (step 3 above), not in a general impression of the package. Derive the metrics
@@ -311,7 +308,7 @@ preconditions the hops enforce; `confidentiality`, `integrity`, and
 
 When you have no source-to-sink trace, still rate the finding: copy the
 published metrics, change only the metrics the usage level itself proves, and
-say so in the reasoning. For example, for a `not_applicable` package that the
+say so in the reasoning. For example, for a `not_imported` package that the
 build still ships, keep the published metrics and lower `confidentiality`,
 `integrity`, and `availability` to `N`, because no code path reaches the
 vulnerable symbol. Never invent a hop you did not read.
@@ -347,8 +344,8 @@ hallucinate a CVE id.
 - Do not silently drop a known CVE because it lacks a dynamic PoC — that is the
   exact failure this skill prevents.
 - Do not downgrade advisory severity for lack of dynamic reproduction.
-- Do not claim a `reachability` verdict the evidence does not prove, and do
-  not file a CVE whose analysis you did not finish — report the gap instead.
+- Do not claim a `reachability` level the evidence does not prove — `unknown`
+  with a reason is always acceptable; an overclaimed level never is.
 - Do not send a report without `contextual_cvss_breakdown` and
   `contextual_cvss_reasoning` — the reader rates and ranks the finding with them.
 - Do not use the contextual breakdown to quietly de-rate a CVE you could not

strix/skills/custom/source_aware_sast.md

@@ -1,6 +1,6 @@
 ---
 name: source-aware-sast
-description: Practical source-aware SAST and AST playbook for opengrep, ast-grep, gitleaks, and trivy fs
+description: Practical source-aware SAST and AST playbook for semgrep, ast-grep, gitleaks, and trivy fs
 ---
 
 # Source-Aware SAST Playbook
@@ -23,19 +23,19 @@ Run this baseline once per repository before deep narrowing:
 ART=/workspace/.source-aware
 mkdir -p "$ART"
 
-opengrep scan --config /opt/opengrep-rules --taint-intrafile \
-  --json --output "$ART/opengrep.json" .
-# Build deterministic AST targets from opengrep scope (no hardcoded path guessing)
+semgrep scan --config p/default --config p/golang --config p/secrets \
+  --metrics=off --json --output "$ART/semgrep.json" .
+# Build deterministic AST targets from semgrep scope (no hardcoded path guessing)
 python3 - <<'PY'
 import json
 from pathlib import Path
 
 art = Path("/workspace/.source-aware")
-opengrep_json = art / "opengrep.json"
+semgrep_json = art / "semgrep.json"
 targets_file = art / "sg-targets.txt"
 
 try:
-    data = json.loads(opengrep_json.read_text(encoding="utf-8"))
+    data = json.loads(semgrep_json.read_text(encoding="utf-8"))
 except Exception:
     targets_file.write_text("", encoding="utf-8")
     raise
@@ -63,18 +63,17 @@ trivy fs --scanners vuln,misconfig --timeout 30m --offline-scan \
   --format json --output "$ART/trivy-fs.json" . || true
 ```
 
-## Opengrep First Pass
+## Semgrep First Pass
 
-Use Opengrep as the default static triage pass. Rules are bundled offline in `/opt/opengrep-rules` (one directory per language, plus `generic/secrets`):
+Use Semgrep as the default static triage pass:
 
 ```bash
-# Full bundled ruleset
-opengrep scan --config /opt/opengrep-rules --taint-intrafile \
-  --json --output /workspace/.source-aware/opengrep.json .
+# Preferred deterministic profile set (works with --metrics=off)
+semgrep scan --config p/default --config p/golang --config p/secrets \
+  --metrics=off --json --output /workspace/.source-aware/semgrep.json .
 
-# Narrow to the target stack when the full set is slow or noisy
-opengrep scan --config /opt/opengrep-rules/python --config /opt/opengrep-rules/generic/secrets \
-  --taint-intrafile --json --output /workspace/.source-aware/opengrep-python.json .
+# If you choose auto config, do not combine it with --metrics=off
+semgrep scan --config auto --json --output /workspace/.source-aware/semgrep-auto.json .
 ```
 
 If diff scope is active, restrict to changed files first, then expand only when needed.

strix/skills/frameworks/django.md

@@ -205,10 +205,10 @@ Jinja2 backend without autoescape: `{{7*7}}`, RCE gadgets if sandbox misconfigur
 
 ## Tooling
 
-Static analysis is the fastest way to reach the sinks above in white-box scope. The sandbox ships `python`/`pipx`, `opengrep`, `bandit`, `ast-grep`, and `ripgrep`.
+Static analysis is the fastest way to reach the sinks above in white-box scope. The sandbox ships `python`/`pipx`, `semgrep`, `bandit`, `ast-grep`, and `ripgrep`.
 
 - **bandit** (preinstalled) — Python security linter; flags `mark_safe`, `extra()`, `RawSQL`, `subprocess`, weak crypto, hardcoded secrets: `bandit -r . -ll`
-- **opengrep** (preinstalled) with the bundled Django rules — higher-signal than bandit for framework-specific bugs (`.extra()`, `RawSQL`, `|safe`, `csrf_exempt`, `ALLOWED_HOSTS=['*']`): `opengrep scan --config /opt/opengrep-rules/python/django .`
+- **semgrep** (preinstalled) with the Django ruleset — higher-signal than bandit for framework-specific bugs (`.extra()`, `RawSQL`, `|safe`, `csrf_exempt`, `ALLOWED_HOSTS=['*']`): `semgrep --config p/django .`
 - **pip-audit** (PyPA) — dependency CVE scanner for known-vuln Django/DRF/simplejwt versions: `pipx install pip-audit && pip-audit -r requirements.txt`
 - **ast-grep** (preinstalled) — quick structural grep for risky calls without a full SAST run: `ast-grep run -p 'mark_safe($X)' -l python`
 

strix/skills/scan_modes/deep.md

@@ -15,7 +15,7 @@ Thorough understanding before exploitation. Test every parameter, every endpoint
 
 **Whitebox (source available)**
 - Map every file, module, and code path in the repository
-- Start with broad source-aware triage (`opengrep`, `ast-grep`, `gitleaks`, `trufflehog`, `trivy fs`) and use outputs to drive deep review
+- Start with broad source-aware triage (`semgrep`, `ast-grep`, `gitleaks`, `trufflehog`, `trivy fs`) and use outputs to drive deep review
 - Execute at least one structural AST pass (`sg` and/or Tree-sitter) per repository and store artifacts for reuse
 - Keep AST artifacts bounded and query-driven (target relevant paths/sinks first; avoid whole-repo generic function dumps)
 - Use syntax-aware parsing (Tree-sitter tooling) to improve symbol, route, and sink extraction quality

strix/skills/scan_modes/quick.md

@@ -15,7 +15,7 @@ Optimize for fast feedback on critical security issues. Skip exhaustive enumerat
 
 **Whitebox (source available)**
 - Focus on recent changes: git diffs, new commits, modified files—these are most likely to contain fresh bugs
-- Run a fast static triage on changed files first (`opengrep`, then targeted `sg` queries)
+- Run a fast static triage on changed files first (`semgrep`, then targeted `sg` queries)
 - Run at least one lightweight AST pass (`sg` or Tree-sitter) so structural mapping is not skipped
 - Keep AST commands tightly scoped to changed or high-risk paths; avoid broad repository-wide pattern dumps
 - Run quick secret and dependency checks (`gitleaks`, `trufflehog`, `trivy fs`) scoped to changed areas when possible

strix/skills/scan_modes/standard.md

@@ -15,7 +15,7 @@ Systematic testing across the full attack surface. Understand the application be
 
 **Whitebox (source available)**
 - Map codebase structure: modules, entry points, routing
-- Run `opengrep` first-pass triage to prioritize risky flows before deep manual review
+- Run `semgrep` first-pass triage to prioritize risky flows before deep manual review
 - Run at least one AST-structural mapping pass (`sg` and/or Tree-sitter), then use outputs for route, sink, and trust-boundary mapping
 - Keep AST output bounded to relevant paths and hypotheses; avoid whole-repo generic function dumps
 - Identify architecture pattern (MVC, microservices, monolith)

strix/skills/tooling/agent_browser.md

@@ -207,7 +207,7 @@ agent-browser snapshot -i
 ```
 
 Credentials in shell history are a leak. For anything sensitive, use the
-auth vault (see `references/authentication.md`):
+auth vault (see [references/authentication.md](references/authentication.md)):
 
 ```bash
 agent-browser auth save my-app --url https://app.example.com/login \
@@ -367,7 +367,7 @@ agent-browser click @e3
 agent-browser record stop
 ```
 
-See `references/video-recording.md` for
+See [references/video-recording.md](references/video-recording.md) for
 codec options, GIF export, and more.
 
 ### Iframes
@@ -491,8 +491,8 @@ snapshot — fall back to `eval` in the iframe's origin or use the
 
 **Authentication expires mid-workflow**
 Use `--session-name <name>` or `state save`/`state load` so your session
-survives browser restarts. See `references/session-management.md`
-and `references/authentication.md`.
+survives browser restarts. See [references/session-management.md](references/session-management.md)
+and [references/authentication.md](references/authentication.md).
 
 ## Global flags worth knowing
 

strix/skills/tooling/opengrep.md

@@ -1,69 +0,0 @@
----
-name: opengrep
-description: Exact Opengrep CLI structure, bundled offline rules, scoped rule selection, taint mode, and automation-safe output patterns.
----
-
-# Opengrep CLI Playbook
-
-Official docs:
-- https://github.com/opengrep/opengrep
-- https://github.com/opengrep/opengrep-rules
-
-Canonical syntax:
-`opengrep scan [flags] [targets]`
-
-Bundled rules:
-- `/opt/opengrep-rules` holds the full ruleset, one directory per language (`python`, `javascript`, `typescript`, `go`, `java`, `php`, `ruby`, …) plus `generic/secrets`, `dockerfile`, `terraform`, `yaml`, and `strix` (Strix-authored rules, e.g. GitHub-owned actions not pinned to a commit SHA)
-- Framework rules sit under the language (`python/django`, `python/flask`, `javascript/express`, …)
-
-High-signal flags:
-- `--config <path>` rule file or directory; repeat for several
-- `--taint-intrafile` intra-file inter-procedural taint (follows data across functions in one file)
-- `--json` / `--sarif` output format
-- `--output <file>` write findings to file
-- `--severity <level>` filter by severity (`INFO`, `WARNING`, `ERROR`)
-- `--error` return non-zero exit when findings exist
-- `--quiet` suppress progress noise
-- `--jobs <n>` parallel workers
-- `--timeout <seconds>` per-rule, per-file timeout
-- `--exclude <pattern>` / `--include <pattern>` path filters
-- `--exclude-rule <rule_id>` suppress specific rule
-- `--baseline-commit <sha>` only report findings introduced after baseline
-
-Agent-safe baseline for automation:
-`opengrep scan --config /opt/opengrep-rules --taint-intrafile --json --output opengrep.json --quiet --jobs 4 --timeout 20 /workspace`
-
-Common patterns:
-- Full bundled scan:
-  `opengrep scan --config /opt/opengrep-rules --json --output opengrep.json --quiet /workspace`
-- High-severity focused pass:
-  `opengrep scan --config /opt/opengrep-rules --severity ERROR --json --output opengrep_high.json --quiet /workspace`
-- SARIF output:
-  `opengrep scan --config /opt/opengrep-rules --sarif --output opengrep.sarif --quiet /workspace`
-- Language- or framework-specific rules:
-  `opengrep scan --config /opt/opengrep-rules/python --config /opt/opengrep-rules/generic/secrets --json --output opengrep_python.json --quiet /workspace`
-- Scoped directory scan:
-  `opengrep scan --config /opt/opengrep-rules --json --output opengrep_api.json --quiet /workspace/services/api`
-- Custom rule:
-  `opengrep scan --config ./rules/my-rule.yaml --json --output opengrep_custom.json --quiet /workspace`
-
-Critical correctness rules:
-- Always provide an explicit `--config` from `/opt/opengrep-rules` or a local rule file. Registry shorthands (`p/...`, `auto`) fetch rules from the network; do not use them.
-- Opengrep has no telemetry; there is no `--metrics` flag, and passing one fails the scan.
-- Prefer `--json --output <file>` or `--sarif --output <file>` for machine-readable downstream processing. JSON keeps `paths.scanned` and `results[].path`.
-- Keep the target path explicit; use an absolute or clearly scoped workspace path instead of `.` when possible.
-
-Usage rules:
-- Start with the full `/opt/opengrep-rules` set unless the task clearly calls for a narrower language or framework directory.
-- Add `--taint-intrafile` for injection-class hunting (SQLi, command injection, SSRF, path traversal) in supported languages.
-- Use `--quiet` in automation to reduce noisy logs.
-- Use `--jobs` and `--timeout` explicitly for reproducible runtime behavior.
-- `PartialParsing` errors on templates are normal; they do not invalidate the run.
-
-Failure recovery:
-- If scans are too slow, narrow the target path and the rule directories before changing engine settings.
-- If scans time out, increase `--timeout` modestly or lower `--jobs`.
-- If output is too broad, scope `--config`, add `--severity`, or exclude known irrelevant paths.
-
-If uncertain, query web_search with:
-`site:github.com/opengrep/opengrep <flag>`

strix/skills/tooling/semgrep.md

@@ -0,0 +1,72 @@
+---
+name: semgrep
+description: Exact Semgrep CLI structure, metrics-off scanning, scoped ruleset selection, and automation-safe output patterns.
+---
+
+# Semgrep CLI Playbook
+
+Official docs:
+- https://semgrep.dev/docs/cli-reference
+- https://semgrep.dev/docs/getting-started/cli
+- https://semgrep.dev/docs/semgrep-code/semgrep-pro-engine-intro
+
+Canonical syntax:
+`semgrep scan [flags]`
+
+High-signal flags:
+- `--config <rule_or_ruleset>` ruleset, registry pack, local rule file, or directory
+- `--metrics=off` disable telemetry and metrics reporting
+- `--json` JSON output
+- `--sarif` SARIF output
+- `--output <file>` write findings to file
+- `--severity <level>` filter by severity
+- `--error` return non-zero exit when findings exist
+- `--quiet` suppress progress noise
+- `--jobs <n>` parallel workers
+- `--timeout <seconds>` per-file timeout
+- `--exclude <pattern>` exclude path pattern
+- `--include <pattern>` include path pattern
+- `--exclude-rule <rule_id>` suppress specific rule
+- `--baseline-commit <sha>` only report findings introduced after baseline
+- `--pro` enable Pro engine if available
+- `--oss-only` force OSS engine only
+
+Agent-safe baseline for automation:
+`semgrep scan --config p/default --metrics=off --json --output semgrep.json --quiet --jobs 4 --timeout 20 /workspace`
+
+Common patterns:
+- Default security scan:
+  `semgrep scan --config p/default --metrics=off --json --output semgrep.json --quiet /workspace`
+- High-severity focused pass:
+  `semgrep scan --config p/default --severity ERROR --metrics=off --json --output semgrep_high.json --quiet /workspace`
+- OWASP-oriented scan:
+  `semgrep scan --config p/owasp-top-ten --metrics=off --sarif --output semgrep.sarif --quiet /workspace`
+- Language- or framework-specific rules:
+  `semgrep scan --config p/python --config p/secrets --metrics=off --json --output semgrep_python.json --quiet /workspace`
+- Scoped directory scan:
+  `semgrep scan --config p/default --metrics=off --json --output semgrep_api.json --quiet /workspace/services/api`
+- Pro engine check or run:
+  `semgrep scan --config p/default --pro --metrics=off --json --output semgrep_pro.json --quiet /workspace`
+
+Critical correctness rules:
+- Always include `--metrics=off`; Semgrep sends telemetry by default.
+- Always provide an explicit `--config`; do not rely on vague or implied defaults.
+- Prefer `--json --output <file>` or `--sarif --output <file>` for machine-readable downstream processing.
+- Keep the target path explicit; use an absolute or clearly scoped workspace path instead of `.` when possible.
+- If Pro availability matters, check it explicitly with a bounded command before assuming cross-file analysis exists.
+
+Usage rules:
+- Start with `p/default` unless the task clearly calls for a narrower pack.
+- Add focused packs such as `p/secrets`, `p/python`, or `p/javascript` only when they match the target stack.
+- Use `--quiet` in automation to reduce noisy logs.
+- Use `--jobs` and `--timeout` explicitly for reproducible runtime behavior.
+- Do not use `-h`/`--help` for routine operation unless absolutely necessary.
+
+Failure recovery:
+- If scans are too slow, narrow the target path and reduce the active rulesets before changing engine settings.
+- If scans time out, increase `--timeout` modestly or lower `--jobs`.
+- If output is too broad, scope `--config`, add `--severity`, or exclude known irrelevant paths.
+- If Pro mode fails, rerun with `--oss-only` or without `--pro` and note the loss of cross-file coverage.
+
+If uncertain, query web_search with:
+`site:semgrep.dev semgrep <flag> cli`

strix/skills/vulnerabilities/semantic_confusion.md

@@ -1,6 +1,6 @@
 ---
 name: semantic-confusion
-description: Cross-component semantic confusion testing for parser differentials, normalization mismatches, email and IDNA identity drift, overloaded fields, lifecycle state drift, internal redirects, protocol translation, and validator-to-sink inconsistencies
+description: Cross-component semantic confusion testing for parser differentials, normalization mismatches, overloaded fields, lifecycle state drift, internal redirects, protocol translation, and validator-to-sink inconsistencies
 ---
 
 # Semantic Confusion
@@ -59,27 +59,6 @@ The highest-signal condition is `security_check(value_A)` followed by `sink(tran
 - Test malformed Unicode and replacement behavior; a rejected code point may become an allowed delimiter or wildcard later.
 - Test path, query, and fragment separately. Browsers and routers commonly transform each source differently.
 
-### Email and Account Identity Drift
-
-Treat an email address as both a principal selector and a delivery destination. Trace the complete boundary before testing:
-
-```text
-submitted or identity-provider address
-  -> application normalization / IDNA
-  -> database comparison and collation
-  -> selected local principal
-  -> token, session, invitation, or link binding
-  -> recipient or linked identity consumed by the final service
-```
-
-- Cover recovery, magic links, invitations, registration uniqueness, email changes, and OAuth/OIDC account linking. Test case/accent-insensitive collations, Unicode normalization, IDNA U-label/A-label conversion, trailing dots, and provider canonicalization only when the observed stack supports them.
-- In black-box testing, report the observed equivalence and routing behavior. Do not name a specific collation, normalizer, or provider algorithm without source, configuration, or version evidence.
-- Determine whether two non-identical addresses can select the same protected principal while SMTP or an identity provider routes them to different owners. The address that receives authority must identify the same principal selected by the security check.
-- In recovery flows, compare the submitted address with the selected account's stored canonical address. A fuzzy lookup followed by delivery to the submitted value is high risk; an exact lookup plus delivery to the stored value is the primary negative control.
-- Use only an explicitly authorized attacker-controlled mailbox or test domain. Derive a bounded variant set from the deployed collation and canonicalizers rather than spraying external domains or the Unicode range.
-
-For a recovery, magic-link, or invitation finding, a generic success response is not proof. Demonstrate that the variant selects the protected principal, the issued authority reaches the controlled mailbox or identity, and redemption yields the protected principal's access. If delivery or redemption cannot be observed, keep the path `needs_follow_up`.
-
 ### Field and Type Overloading
 
 - Identify shared fields reused for different concepts: path vs URL, content type vs handler, display name vs executable name, route vs filesystem location.
@@ -191,8 +170,6 @@ A valid confusion finding should include:
 - Different error messages with identical final authorization and sink behavior
 - A parser accepts odd syntax but downstream consumers preserve the same safe meaning
 - A normalization difference visible only in logs, with no security decision between representations
-- A Unicode or Punycode lookalike that neither selects another principal nor receives authority intended for that principal
-- A permissive database comparison where recovery delivery still uses the selected account's stored canonical address
 - WAF bypass where the application itself rejects the request identically
 - Version-specific behavior claimed as universal without testing the relevant deployment
 - A search-path candidate that is attacker-named but cannot be created, claimed, loaded, or executed

strix/tools/mcp/auth.py

@@ -1,56 +0,0 @@
-"""In-memory bearer refresh for HTTP MCP connections."""
-
-from __future__ import annotations
-
-import asyncio
-import logging
-from typing import TYPE_CHECKING
-
-import httpx
-
-
-if TYPE_CHECKING:
-    from collections.abc import AsyncGenerator, Awaitable, Callable
-
-
-logger = logging.getLogger(__name__)
-
-
-class RefreshingBearerAuth(httpx.Auth):
-    def __init__(
-        self, token: str | None, refresh_token: Callable[[], Awaitable[str | None]]
-    ) -> None:
-        self._token = token
-        self._refresh_token = refresh_token
-        self._lock = asyncio.Lock()
-        self._refresh_generation = 0
-
-    def _authorize(self, request: httpx.Request, token: str | None) -> None:
-        if token:
-            request.headers["Authorization"] = f"Bearer {token}"
-        else:
-            request.headers.pop("Authorization", None)
-
-    async def async_auth_flow(
-        self, request: httpx.Request
-    ) -> AsyncGenerator[httpx.Request, httpx.Response]:
-        sent_token = self._token
-        sent_generation = self._refresh_generation
-        self._authorize(request, sent_token)
-        response = yield request
-        if response.status_code != 401:
-            return
-        async with self._lock:
-            if self._token == sent_token and self._refresh_generation == sent_generation:
-                try:
-                    token = await self._refresh_token()
-                except Exception as exc:  # noqa: BLE001
-                    logger.warning("MCP bearer refresh failed (%s)", type(exc).__name__)
-                    token = None
-                self._refresh_generation += 1
-                if token and token != sent_token:
-                    self._token = token
-            retry_token = self._token
-        if retry_token and retry_token != sent_token:
-            self._authorize(request, retry_token)
-            yield request

strix/tools/mcp/client.py

@@ -39,11 +39,10 @@ from strix.tools.mcp.session import McpConnectionUnavailableError, SupervisedMcp
 
 
 if TYPE_CHECKING:
-    from collections.abc import Awaitable, Callable, Mapping
+    from collections.abc import Callable
 
     import httpx
 
-    from strix.tools.mcp.auth import RefreshingBearerAuth
     from strix.tools.mcp.config import McpConnectionConfig
     from strix.tools.mcp.registry import McpConnectionRequest, McpRegistry
 
@@ -122,9 +121,7 @@ class _QuietMCPServerStdio(MCPServerStdio):
         return _quiet_stdio_streams(self.params)
 
 
-def _build_server(
-    config: McpConnectionConfig, bearer_auth: RefreshingBearerAuth | None = None
-) -> BuiltMcpServer:
+def _build_server(config: McpConnectionConfig) -> BuiltMcpServer:
     """Construct (but do not connect) the SDK server for one connection.
 
     The returned tuple carries the server and, for HTTP connections, a recorder
@@ -164,13 +161,13 @@ def _build_server(
         timeout: httpx.Timeout | None = None,
         auth: httpx.Auth | None = None,
     ) -> httpx.AsyncClient:
-        client = create_mcp_http_client(headers=headers, timeout=timeout, auth=bearer_auth or auth)
+        client = create_mcp_http_client(headers=headers, timeout=timeout, auth=auth)
         client.event_hooks.setdefault("response", []).append(recorder)
         return client
 
     http_params: MCPServerStreamableHttpParams = {
         "url": cast("str", config.url),
-        "headers": {} if bearer_auth is not None else _auth_headers(config),
+        "headers": _auth_headers(config),
         "timeout": config.http_timeout_seconds,
         "sse_read_timeout": config.sse_read_timeout_seconds,
         "httpx_client_factory": httpx_client_factory,
@@ -303,12 +300,9 @@ async def connect_mcp_servers(
     configs: list[McpConnectionConfig],
     *,
     max_concurrency: int = 6,
-    token_refreshers: Mapping[str, Callable[[], Awaitable[str | None]]] | None = None,
 ) -> list[ConnectedMcpServer]:
     """Connect MCP configs concurrently under a fixed bound.
 
-    ``token_refreshers`` optionally supplies a bearer refresher by connection name.
-
     Each connection becomes a :class:`~strix.tools.mcp.session.SupervisedMcpSession`
     that owns ``connect()``, the held-open session, and ``cleanup()`` on one
     dedicated task, so a later background failure in one session is contained to
@@ -331,10 +325,7 @@ async def connect_mcp_servers(
 
     async def connect_one(config: McpConnectionConfig) -> ConnectedMcpServer | None:
         async with semaphore:
-            session = SupervisedMcpSession(
-                config,
-                refresh_token=token_refreshers.get(config.name) if token_refreshers else None,
-            )
+            session = SupervisedMcpSession(config)
             sessions.append(session)
             try:
                 if not await session.start():
@@ -390,14 +381,7 @@ async def attach_mcp_requests(
     ends).
     """
     request_by_name = {request.config.name: request for request in requests}
-    connections = await connect_mcp_servers(
-        [request.config for request in requests],
-        token_refreshers={
-            request.config.name: request.refresh_token
-            for request in requests
-            if request.refresh_token is not None
-        },
-    )
+    connections = await connect_mcp_servers([request.config for request in requests])
     for connection in connections:
         request = request_by_name[connection.name]
         registry.add(
@@ -407,6 +391,5 @@ async def attach_mcp_requests(
             purpose=request.purpose or connection.notes,
             provider=request.provider,
             result_transform=request.result_transform,
-            refresh_token=request.refresh_token,
         )
     return connections

strix/tools/mcp/failures.py

@@ -129,20 +129,12 @@ def classify(exc: BaseException) -> FailureInfo:
 
 
 class HttpStatusRecorder:
-    """Capture the last non-success response from one HTTP connection.
-
-    A later success clears a recorded 401, so a bearer refreshed and retried
-    in the auth flow does not leave a stale auth failure behind.
-    """
+    """Capture the last non-success response from one HTTP connection."""
 
     def __init__(self) -> None:
         self._failure: FailureInfo | None = None
 
     async def __call__(self, response: httpx.Response) -> None:
-        if 200 <= response.status_code < 300:
-            if self._failure is not None and self._failure.kind == "auth":
-                self._failure = None
-            return
         if not 200 <= response.status_code < 300:
             request = response.request
             self._failure = _from_status(

strix/tools/mcp/registry.py

@@ -32,7 +32,7 @@ from strix.tools.mcp.session import McpConnectionUnavailableError, SupervisedMcp
 
 
 if TYPE_CHECKING:
-    from collections.abc import Awaitable, Callable
+    from collections.abc import Callable
 
     from agents.mcp import MCPServer
 
@@ -96,9 +96,6 @@ class McpConnectionEntry:
     tool_count: int = 0
     result_transform: ResultTransform | None = None
     provider: str | None = None
-    refresh_token: Callable[[], Awaitable[str | None]] | None = dataclasses.field(
-        default=None, repr=False
-    )
     state: McpConnectionState = "configured"
     _catalog: list[Any] | None = dataclasses.field(default=None, repr=False)
     _connect_task: asyncio.Task[SupervisedMcpSession] | None = dataclasses.field(
@@ -183,7 +180,7 @@ class McpConnectionEntry:
                 f"MCP connection {self.name!r} has no connection configuration."
             )
         self._set_state("connecting")
-        session = SupervisedMcpSession(config, refresh_token=self.refresh_token)
+        session = SupervisedMcpSession(config)
         try:
             started = await session.start()
         except BaseException:
@@ -301,17 +298,12 @@ class McpConnectionRequest:
     at the single dispatch point (strix-pro's sanitizer; empty for the
     command-line path). ``purpose`` is the human label ``list_mcps`` reports as the
     connection's description; when unset it falls back to ``config.notes``.
-    ``refresh_token`` optionally fetches a new bearer asynchronously after an HTTP
-    401; returning no token or the current token leaves the failure unchanged.
     """
 
     config: McpConnectionConfig
     provider: str | None = None
     result_transform: ResultTransform | None = None
     purpose: str | None = None
-    refresh_token: Callable[[], Awaitable[str | None]] | None = dataclasses.field(
-        default=None, repr=False
-    )
 
 
 class McpCallInfo(NamedTuple):
@@ -345,7 +337,6 @@ class McpRegistry:
             purpose=request.purpose or request.config.notes,
             result_transform=request.result_transform,
             provider=request.provider,
-            refresh_token=request.refresh_token,
         )
         entry.set_status_sink(self._status_sink)
         self._entries[entry.name] = entry
@@ -362,7 +353,6 @@ class McpRegistry:
         tool_count: int = 0,
         result_transform: ResultTransform | None = None,
         provider: str | None = None,
-        refresh_token: Callable[[], Awaitable[str | None]] | None = None,
     ) -> McpConnectionEntry:
         """Register one connection under ``name`` (last write wins).
 
@@ -384,7 +374,6 @@ class McpRegistry:
             tool_count=tool_count,
             result_transform=result_transform,
             provider=provider,
-            refresh_token=refresh_token,
             state="connected",
         )
         entry.set_status_sink(self._status_sink)

strix/tools/mcp/session.py

@@ -54,7 +54,6 @@ import time
 import weakref
 from typing import TYPE_CHECKING, Any, Literal, cast
 
-from strix.tools.mcp.auth import RefreshingBearerAuth
 from strix.tools.mcp.config import DEFAULT_MAX_CONCURRENT_CALLS
 from strix.tools.mcp.failures import FailureInfo, HttpStatusRecorder, classify
 
@@ -158,19 +157,9 @@ class SupervisedMcpSession:
     :attr:`name`, :attr:`server`, :attr:`config`, :attr:`is_dead`.
     """
 
-    def __init__(
-        self,
-        config: McpConnectionConfig,
-        *,
-        refresh_token: Callable[[], Awaitable[str | None]] | None = None,
-    ) -> None:
+    def __init__(self, config: McpConnectionConfig) -> None:
         self._name = config.name
         self._config: McpConnectionConfig | None = config
-        self._bearer_auth = (
-            RefreshingBearerAuth(config.auth.token if config.auth else None, refresh_token)
-            if refresh_token is not None and config.transport == "http"
-            else None
-        )
         self._server: MCPServer | None = None
         self._supervised = True
         self._task: asyncio.Task[None] | None = None
@@ -204,7 +193,6 @@ class SupervisedMcpSession:
         self = cls.__new__(cls)
         self._name = name
         self._config = config
-        self._bearer_auth = None
         self._server = server
         self._supervised = False
         self._task = None
@@ -713,11 +701,7 @@ class SupervisedMcpSession:
 
         if self._config is None:
             raise RuntimeError(f"MCP connection {self._name!r} has no config to connect")
-        built = (
-            _build_server(self._config, self._bearer_auth)
-            if self._bearer_auth is not None
-            else _build_server(self._config)
-        )
+        built = _build_server(self._config)
         server = built.server
         self._recorder = built.recorder
         try:

strix/tools/reporting/tool.py

@@ -1689,7 +1689,15 @@ def _dependency_severity(advisory_cvss: float | None) -> tuple[float, str]:
     return score, "none"
 
 
-_VALID_REACHABILITY = frozenset({"reachable", "not_reachable", "not_applicable"})
+_VALID_REACHABILITY = frozenset(
+    {
+        "not_imported",
+        "imported",
+        "vulnerable_symbol_used",
+        "reachable_call_path",
+        "unknown",
+    }
+)
 
 
 def _validate_manifest_path(manifest_path: str | None) -> str | None:
@@ -1830,13 +1838,11 @@ def _build_dependency_metadata(
 
 
 _REACHABILITY_EVIDENCE_LABELS = {
-    "reachable": "the advisory's vulnerable code runs in this codebase",
-    "not_reachable": (
-        "the package is loaded, but this advisory's vulnerable code does not run here"
-    ),
-    "not_applicable": (
-        "the advisory does not apply here: the vulnerable package is not loaded, "
-        "or the installed copy is not affected"
+    "not_imported": "not imported by application code",
+    "imported": "imported by application code; affected API usage unconfirmed",
+    "vulnerable_symbol_used": "the advisory's affected API is used in application code",
+    "reachable_call_path": (
+        "a call path from application code to the vulnerable function was proven"
     ),
 }
 
@@ -1893,7 +1899,7 @@ async def _do_create_dependency(  # noqa: PLR0912, PLR0915
     introduced_by: str | None = None,
     dependency_path: str | None = None,
     manifest_path: str | None = None,
-    reachability: str | None = None,
+    reachability: str = "unknown",
     reachability_evidence: str | None = None,
     code_locations: list[dict[str, Any]] | None = None,
     fix_verification: str | None = None,
@@ -1949,22 +1955,17 @@ async def _do_create_dependency(  # noqa: PLR0912, PLR0915
         )
     errors.extend(_validate_fix_verification(parsed_locations, fix_verification))
 
-    reachability = (reachability or "").strip().lower()
-    if not reachability:
-        errors.append(
-            "reachability is required: 'reachable', 'not_reachable' or 'not_applicable'. "
-            "There is no 'unknown': finish the usage analysis for this CVE before filing it."
-        )
-    elif reachability not in _VALID_REACHABILITY:
+    reachability = (reachability or "unknown").strip().lower()
+    if reachability not in _VALID_REACHABILITY:
         errors.append(
             f"Invalid reachability: {reachability!r}. Must be one of: {sorted(_VALID_REACHABILITY)}"
         )
     elif not (reachability_evidence or "").strip():
         errors.append(
-            "reachability_evidence is required: cite the concrete proof (the call site "
-            "and its source-to-sink trace for 'reachable'; the complete search or the "
-            "condition that keeps the vulnerable path from running for 'not_reachable'; "
-            "the search scope for 'not_applicable'). Never claim a verdict without evidence."
+            "reachability_evidence is required: cite the concrete proof (import "
+            "file:line, matched symbol usage, or govulncheck call path), or, for "
+            "'unknown', say what you searched and why the result is inconclusive. "
+            "Never claim a reachability level without evidence."
         )
 
     errors.extend(_validate_contextual_cvss(contextual_cvss_breakdown, contextual_cvss_reasoning))
@@ -2114,7 +2115,7 @@ async def create_dependency_report(
     fix_effort: str = "low",
     introduced_by: str | None = None,
     dependency_path: str | None = None,
-    reachability: str | None = None,
+    reachability: str = "unknown",
     reachability_evidence: str | None = None,
     code_locations: list[dict[str, Any]] | None = None,
     fix_verification: str | None = None,
@@ -2144,26 +2145,23 @@ async def create_dependency_report(
     - Re-reporting the same CVE/package already filed.
 
     **Reachability**: do NOT silently downgrade or suppress a finding
-    because the vulnerable code path is not reached — report it, and record
-    the verdict of the usage analysis in the structured ``reachability`` +
-    ``reachability_evidence`` fields (see the dependency-cve-scanning skill
-    for the procedure). The verdict answers one question for this advisory
-    in this codebase, "does the vulnerable code run here?", and the tool
-    rejects a report without it or without evidence:
+    because the vulnerable code path may be unreachable — report it, and
+    record what the usage analysis showed via the structured
+    ``reachability`` + ``reachability_evidence`` fields (see the
+    dependency-cve-scanning skill for the analysis procedure). The level
+    is an evidence ladder, never an exploitability verdict:
 
-    - ``reachable`` — the advisory's vulnerable code executes here:
-      application code, or a package it calls on the application's behalf,
-      calls the affected function, mode or feature.
-    - ``not_reachable`` — the package is loaded, but this advisory's
-      vulnerable path does not execute here (no caller of the affected API
-      after a complete search, a call behind a condition that is false here,
-      a parent package that never references the affected API, a mode this
-      code never uses, a triggering argument that is a constant here).
-    - ``not_applicable`` — the advisory does not apply to this codebase:
-      nothing the shipped code loads imports the package, it is build or
-      test tooling the artifact never runs, the installed copy is a patched
-      or unaffected build, or the flaw is specific to a platform this code
-      does not run on.
+    - ``not_imported`` — the package is never imported/required by
+      application code (strongest de-prioritization signal; still not
+      proof of safety — dynamic loading, reflection, or framework wiring
+      can evade static search).
+    - ``imported`` — application code imports the package, but usage of
+      the advisory's affected API was not confirmed.
+    - ``vulnerable_symbol_used`` — the advisory's affected
+      function/class/API appears in application code.
+    - ``reachable_call_path`` — a call-graph tool (e.g. ``govulncheck``)
+      proved a path from application code to the vulnerable function.
+    - ``unknown`` — usage analysis was not performed or was inconclusive.
 
     Severity comes from ``contextual_cvss_breakdown`` when you provide one
     (computed exactly like a normal finding's ``cvss_breakdown``), otherwise
@@ -2211,24 +2209,26 @@ async def create_dependency_report(
             checkout directory prefix so the path is relative to the
             repository root. This binds the finding to its exact file so
             remediation can target the right repository.
-        reachability: **Required.** The verdict of the usage analysis for
-            this CVE — ``reachable`` / ``not_reachable`` / ``not_applicable``.
-            Claim only what the evidence proves; there is no ``unknown``,
-            finish the analysis before filing.
+        reachability: Usage-evidence level from static analysis — one of
+            ``not_imported`` / ``imported`` / ``vulnerable_symbol_used`` /
+            ``reachable_call_path`` / ``unknown``. Claim only what the
+            evidence proves; when in doubt use ``unknown``.
         reachability_evidence: **Required.** The concrete proof for the
-            verdict: repo-relative ``file:line`` of the import and of the
-            call that reaches the affected symbol, the search scope and
-            negative result behind ``not_applicable``, or the condition that
-            keeps the vulnerable path from running behind ``not_reachable``.
-            Whenever the affected symbol is called, also give the
+            claimed level, or, for ``unknown``, what you searched and why
+            the result is inconclusive: repo-relative
+            ``file:line`` of the import or symbol usage, the matched
+            advisory symbols, or the govulncheck call-path excerpt.
+            Whenever you found the vulnerable symbol in use, also give the
             **source-to-sink trace** here: start at the vulnerable package
             call site and walk backwards hop by hop to the entry point
-            that carries the input (HTTP route, CLI argument, queue
+            that carries untrusted input (HTTP route, CLI argument, queue
             message, webhook, config file), going one step deeper whenever
             a hop is a wrapper. Write it as ``entry point -> intermediate
             call -> package call`` with a ``file:line`` per hop, name what
             each hop enforces (auth, role check, validation, a flag that
-            is off in production), and say who controls the input.
+            is off in production), and say who controls the input. State
+            it plainly when no entry point reaches the sink — that is the
+            most useful result a reader can get.
         code_locations: Where application code imports or calls the package —
             the evidence behind your ``reachability`` claim. List of dicts,
             same shape as ``create_vulnerability_report``::

tests/test_dedupe_decisions.py

@@ -1,159 +0,0 @@
-"""Only validated model decisions may suppress a finding."""
-
-from __future__ import annotations
-
-import json
-from typing import TYPE_CHECKING, Any
-from unittest.mock import AsyncMock
-
-import pytest
-from agents.items import ModelResponse
-from agents.usage import Usage
-from openai.types.responses import ResponseOutputMessage, ResponseOutputText
-
-from strix.config import loader
-from strix.report import dedupe
-from strix.report.state import ReportState, get_global_report_state, set_global_report_state
-from strix.tools.reporting.tool import _do_create
-
-
-if TYPE_CHECKING:
-    from collections.abc import Iterator
-    from pathlib import Path
-
-
-@pytest.fixture
-def report_state(tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> Iterator[ReportState]:
-    monkeypatch.chdir(tmp_path)
-    previous = get_global_report_state()
-    state = ReportState(run_name="dedupe-decisions")
-    set_global_report_state(state)
-    state.add_vulnerability_report(title="Existing finding", severity="low")
-    try:
-        yield state
-    finally:
-        set_global_report_state(previous)
-
-
-def _mock_judge(monkeypatch: pytest.MonkeyPatch, decision: dict[str, Any]) -> AsyncMock:
-    settings = loader.load_settings().model_copy(deep=True)
-    settings.llm.model = "openai/synthetic-model"
-    model = AsyncMock()
-    model.get_response.return_value = ModelResponse(
-        output=[
-            ResponseOutputMessage(
-                id="msg_synthetic",
-                type="message",
-                role="assistant",
-                status="completed",
-                content=[
-                    ResponseOutputText(
-                        type="output_text",
-                        annotations=[],
-                        text=json.dumps({"confidence": 0.95, "reason": "Synthetic", **decision}),
-                    )
-                ],
-            )
-        ],
-        usage=Usage(),
-        response_id="synthetic",
-    )
-    monkeypatch.setattr(dedupe, "load_settings", lambda: settings)
-    monkeypatch.setattr(dedupe, "configure_sdk_model_defaults", lambda _: None)
-    monkeypatch.setattr(dedupe, "resolve_dedupe_model", lambda *_: model)
-    return model
-
-
-async def _file_finding() -> dict[str, Any]:
-    return await _do_create(
-        title="New finding",
-        description="The endpoint reflects unencoded input.",
-        impact="The reflected script executes in a victim's browser.",
-        target="https://example.invalid",
-        technical_analysis="Input is interpolated into HTML without encoding.",
-        poc_description="Open the endpoint with the reflected parameter.",
-        poc_script_code="print('synthetic reproduction')",
-        remediation_steps="Encode output for its HTML context.",
-        evidence="The synthetic response contains the unencoded parameter.",
-        assumptions="A victim follows the crafted link.",
-        counterevidence="No encoding or content security policy is present.",
-        confidence="high",
-        severity_change_conditions="A strict content security policy would lower the impact.",
-        fix_effort="low",
-        cvss_breakdown={
-            "attack_vector": "N",
-            "attack_complexity": "L",
-            "privileges_required": "N",
-            "user_interaction": "R",
-            "scope": "U",
-            "confidentiality": "L",
-            "integrity": "L",
-            "availability": "N",
-        },
-        endpoint="/search",
-        method="GET",
-        cve=None,
-        cwe="CWE-79",
-        code_locations=None,
-    )
-
-
-@pytest.mark.parametrize("value", ["false", "true", 0, 1, None, [], {}])
-def test_dedupe_parser_requires_a_boolean(value: Any) -> None:
-    with pytest.raises(TypeError, match="is_duplicate"):
-        dedupe._parse_dedupe_response(json.dumps({"is_duplicate": value}))
-
-
-@pytest.mark.parametrize(
-    "decision",
-    [
-        {"is_duplicate": "false", "duplicate_id": "vuln-0001"},
-        {"is_duplicate": "true", "duplicate_id": "vuln-0001"},
-        {"is_duplicate": 1, "duplicate_id": "vuln-0001"},
-        {"is_duplicate": True, "duplicate_id": "vuln-9999"},
-        {"is_duplicate": True, "duplicate_id": ""},
-        {"is_duplicate": True, "duplicate_id": None},
-        {"is_duplicate": True, "duplicate_id": ["vuln-0001"]},
-        {"is_duplicate": True},
-    ],
-)
-async def test_invalid_dedupe_decision_does_not_suppress_finding(
-    report_state: ReportState, monkeypatch: pytest.MonkeyPatch, decision: dict[str, Any]
-) -> None:
-    model = _mock_judge(monkeypatch, decision)
-
-    result = await _file_finding()
-
-    assert result["success"] is True
-    model.get_response.assert_awaited_once()
-    saved = json.loads((report_state.get_run_dir() / "vulnerabilities.json").read_text())
-    assert [report["title"] for report in saved] == ["Existing finding", "New finding"]
-    assert (report_state.get_run_dir() / "vulnerabilities" / "vuln-0002.md").is_file()
-
-
-@pytest.mark.parametrize("is_duplicate", [False, True])
-async def test_valid_dedupe_decisions_keep_their_meaning(
-    report_state: ReportState, monkeypatch: pytest.MonkeyPatch, is_duplicate: bool
-) -> None:
-    # An extraneous ID must not turn a valid false decision into a duplicate.
-    _mock_judge(monkeypatch, {"is_duplicate": is_duplicate, "duplicate_id": "vuln-0001"})
-
-    result = await _file_finding()
-
-    assert result["success"] is not is_duplicate
-    saved = json.loads((report_state.get_run_dir() / "vulnerabilities.json").read_text())
-    assert len(saved) == (1 if is_duplicate else 2)
-    if is_duplicate:
-        assert result["duplicate_of"] == "vuln-0001"
-
-
-async def test_dedupe_id_is_matched_without_truncation(monkeypatch: pytest.MonkeyPatch) -> None:
-    existing_id = "x" * 64
-    _mock_judge(monkeypatch, {"is_duplicate": True, "duplicate_id": existing_id + "-unknown"})
-
-    result = await dedupe.check_duplicate(
-        {"title": "New finding"}, [{"id": existing_id, "title": "Existing finding"}]
-    )
-
-    assert result["is_duplicate"] is False
-    assert "error" in result

tests/test_hooks.py

@@ -2,14 +2,11 @@
 
 from __future__ import annotations
 
-from types import SimpleNamespace
-from typing import TYPE_CHECKING, Any
+from typing import Any
 from unittest.mock import MagicMock, patch
 
 import pytest
-from agents.usage import Usage
 
-from strix.config import loader
 from strix.core.agents import AgentCoordinator
 from strix.core.hooks import (
     BudgetExceededError,
@@ -18,11 +15,6 @@ from strix.core.hooks import (
     SubagentBudgetReservedError,
     recomputed_budget_flags,
 )
-from strix.report.usage import LLMUsageLedger
-
-
-if TYPE_CHECKING:
-    from pathlib import Path
 
 
 def _make_hooks(max_budget: float | None) -> ReportUsageHooks:
@@ -93,38 +85,6 @@ async def test_over_budget_raises() -> None:
         await hooks.on_llm_end(_make_context(), MagicMock(), MagicMock())
 
 
-@pytest.mark.asyncio
-async def test_manual_rates_make_unpriced_model_trip_budget(
-    monkeypatch: pytest.MonkeyPatch, tmp_path: Path
-) -> None:
-    monkeypatch.setenv("STRIX_LLM", "test-model")
-    monkeypatch.setenv("STRIX_LLM_INPUT_COST_PER_MTOK", "10")
-    monkeypatch.delenv("STRIX_LLM_OUTPUT_COST_PER_MTOK", raising=False)
-    monkeypatch.delenv("STRIX_LLM_CACHED_INPUT_COST_PER_MTOK", raising=False)
-    monkeypatch.setattr(loader, "_override", tmp_path / "missing.json")
-    monkeypatch.setattr(loader, "_cached", None)
-    usage = Usage()
-    usage.requests = 1
-    usage.input_tokens = 1000
-    usage.total_tokens = 1000
-    ledger = LLMUsageLedger()
-
-    class ReportState:
-        def record_sdk_usage(self, **kwargs: Any) -> None:
-            ledger.record(**kwargs)
-
-        def get_total_llm_cost(self) -> float:
-            return ledger.total_cost
-
-    hooks = _make_hooks(0.005)
-    response: Any = SimpleNamespace(usage=usage)
-    with (
-        patch("strix.core.hooks.get_global_report_state", return_value=ReportState()),
-        pytest.raises(BudgetExceededError),
-    ):
-        await hooks.on_llm_end(_make_context(), MagicMock(), response)
-
-
 @pytest.mark.asyncio
 async def test_budget_check_uses_live_cost_accessor() -> None:
     # The check must read the live ledger, not the persisted run-record snapshot,

tests/test_inputs.py

@@ -474,11 +474,6 @@ def test_openrouter_attribution_rides_on_the_request_headers() -> None:
     }
 
 
-def test_vercel_ai_gateway_attribution_rides_on_the_request_headers() -> None:
-    headers = make_model_settings(None, model_name="vercel_ai_gateway/zai/glm-5.3").extra_headers
-    assert headers == {"HTTP-Referer": "https://strix.ai", "X-Title": "Strix"}
-
-
 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
 

tests/test_mcp_auth.py

@@ -1,223 +0,0 @@
-"""HTTP bearer refresh regressions without network access."""
-
-from __future__ import annotations
-
-import asyncio
-from typing import Any, cast
-from unittest.mock import AsyncMock
-
-import httpx
-import pytest
-from mcp.types import CallToolResult, TextContent, Tool
-
-from strix.tools.mcp import BearerAuth, McpConnectionConfig, McpConnectionRequest, McpRegistry
-from strix.tools.mcp import client as mcp_client
-from strix.tools.mcp import session as mcp_session
-from strix.tools.mcp.auth import RefreshingBearerAuth
-
-
-def _config() -> McpConnectionConfig:
-    return McpConnectionConfig(
-        name="refresh",
-        url="https://example.test/mcp",
-        auth=BearerAuth(token="old"),  # noqa: S106  # nosec B106
-    )
-
-
-def _client(auth: RefreshingBearerAuth | None, handler: Any) -> httpx.AsyncClient:
-    built = mcp_client._build_server(_config(), auth)
-    params = cast("Any", built.server).params
-    assert params["headers"] == ({} if auth else {"Authorization": "Bearer old"})
-    client = cast("httpx.AsyncClient", params["httpx_client_factory"](headers=params["headers"]))
-    client._transport = httpx.MockTransport(handler)
-    return client
-
-
-@pytest.mark.asyncio
-async def test_refresh_retries_once_and_persists_across_server_builds() -> None:
-    refresh = AsyncMock(return_value="new")
-    session = mcp_session.SupervisedMcpSession(_config(), refresh_token=refresh)
-    seen: list[str] = []
-
-    def handler(request: httpx.Request) -> httpx.Response:
-        seen.append(request.headers["Authorization"])
-        return httpx.Response(200 if seen[-1] == "Bearer new" else 401)
-
-    for _ in range(2):
-        async with _client(session._bearer_auth, handler) as client:
-            response = await client.post("https://example.test/mcp", content=b"payload")
-            assert response.status_code == 200
-    assert seen == ["Bearer old", "Bearer new", "Bearer new"]
-    refresh.assert_awaited_once()
-
-
-@pytest.mark.asyncio
-@pytest.mark.parametrize("replacement", ["new", None, "old", "raises"])
-async def test_concurrent_unauthorized_requests_share_refresh(replacement: str | None) -> None:
-    refresh = AsyncMock(return_value=replacement)
-    if replacement == "raises":
-        refresh.side_effect = ValueError("refresh unavailable")
-    auth = RefreshingBearerAuth("old", refresh)
-    both_sent = asyncio.Event()
-    old_requests = 0
-
-    async def handler(request: httpx.Request) -> httpx.Response:
-        nonlocal old_requests
-        if request.headers["Authorization"] == "Bearer old":
-            old_requests += 1
-            if old_requests == 5:
-                both_sent.set()
-            await both_sent.wait()
-            return httpx.Response(401)
-        return httpx.Response(200)
-
-    async with _client(auth, handler) as client:
-        responses = await asyncio.wait_for(
-            asyncio.gather(*(client.get("https://example.test/mcp") for _ in range(5))),
-            timeout=2,
-        )
-    assert [response.status_code for response in responses] == [
-        200 if replacement == "new" else 401
-    ] * 5
-    assert old_requests == 5
-    refresh.assert_awaited_once()
-
-
-@pytest.mark.parametrize("replacement", [None, "", "old", "new", "raises", "disabled"])
-@pytest.mark.asyncio
-async def test_unrecovered_401_still_retires_connection(
-    replacement: str | None, caplog: pytest.LogCaptureFixture
-) -> None:
-    refresh = AsyncMock(return_value=replacement)
-    if replacement == "raises":
-        refresh.side_effect = ValueError("private-token-value")
-    auth = None if replacement == "disabled" else RefreshingBearerAuth("old", refresh)
-    seen: list[str] = []
-
-    def handler(request: httpx.Request) -> httpx.Response:
-        seen.append(request.headers["Authorization"])
-        return httpx.Response(401)
-
-    async with _client(auth, handler) as client:
-        server = AsyncMock()
-
-        async def call_tool(*_args: Any, **_kwargs: Any) -> None:
-            response = await client.get("https://example.test/mcp")
-            response.raise_for_status()
-
-        server.call_tool = call_tool
-        session = mcp_session.SupervisedMcpSession.adopt(server, name="refresh")
-        result = await session.dispatch("read", {}, label="refresh_read")
-        assert result["success"] is False
-        assert session.is_dead
-        await session.aclose()
-    assert seen == (["Bearer old", "Bearer new"] if replacement == "new" else ["Bearer old"])
-    assert refresh.await_count == (0 if replacement == "disabled" else 1)
-    assert "private-token-value" not in caplog.text
-    if replacement == "raises":
-        assert "ValueError" in caplog.text
-
-
-@pytest.mark.asyncio
-async def test_non_401_does_not_refresh() -> None:
-    refresh = AsyncMock(return_value="new")
-    auth = RefreshingBearerAuth("old", refresh)
-    async with _client(auth, lambda _: httpx.Response(403)) as client:
-        assert (await client.get("https://example.test/mcp")).status_code == 403
-    refresh.assert_not_awaited()
-
-
-@pytest.mark.asyncio
-async def test_registry_passes_refresher_to_session(monkeypatch: pytest.MonkeyPatch) -> None:
-    refresh = AsyncMock(return_value="new")
-    registry = McpRegistry()
-    entry = registry.register(McpConnectionRequest(_config(), refresh_token=refresh))
-    server = AsyncMock()
-    captured: list[RefreshingBearerAuth] = []
-
-    def build(_config: McpConnectionConfig, auth: RefreshingBearerAuth) -> Any:
-        captured.append(auth)
-        return mcp_client.BuiltMcpServer(server, None)
-
-    monkeypatch.setattr(mcp_client, "_build_server", build)
-    session = await entry.ensure_connected()
-    assert entry.refresh_token is refresh
-    assert captured == [session._bearer_auth]
-    await session._open()
-    assert captured == [session._bearer_auth, session._bearer_auth]
-    await session.aclose()
-
-
-@pytest.mark.asyncio
-async def test_refreshed_token_can_refresh_again_after_expiry() -> None:
-    refresh = AsyncMock(side_effect=["new", "newer"])
-    auth = RefreshingBearerAuth("old", refresh)
-    valid = "new"
-
-    def handler(request: httpx.Request) -> httpx.Response:
-        return httpx.Response(200 if request.headers["Authorization"] == f"Bearer {valid}" else 401)
-
-    async with _client(auth, handler) as client:
-        assert (await client.get("https://example.test/mcp")).status_code == 200
-        valid = "newer"
-        assert (await client.get("https://example.test/mcp")).status_code == 200
-    assert refresh.await_count == 2
-
-
-@pytest.mark.parametrize("with_refresher", [True, False])
-@pytest.mark.asyncio
-async def test_eager_attachment_preserves_bearer_refresh(
-    monkeypatch: pytest.MonkeyPatch, with_refresher: bool
-) -> None:
-    refresh = AsyncMock(return_value="new")
-    original_build = mcp_client._build_server
-    valid = "old"
-
-    def handler(request: httpx.Request) -> httpx.Response:
-        return httpx.Response(200 if request.headers["Authorization"] == f"Bearer {valid}" else 401)
-
-    def build(config: McpConnectionConfig, auth: RefreshingBearerAuth | None = None) -> Any:
-        built = original_build(config, auth)
-        params = cast("Any", built.server).params
-        client = params["httpx_client_factory"](headers=params["headers"])
-        client._transport = httpx.MockTransport(handler)
-        server = AsyncMock()
-        server.use_structured_content = False
-        server.list_tools.return_value = [Tool(name="read", inputSchema={"type": "object"})]
-        server.cleanup.side_effect = client.aclose
-
-        async def call_tool(*_args: Any, **_kwargs: Any) -> CallToolResult:
-            response = await client.post("https://example.test/mcp")
-            response.raise_for_status()
-            return CallToolResult(content=[TextContent(type="text", text="ok")])
-
-        server.call_tool = call_tool
-        return mcp_client.BuiltMcpServer(server, built.recorder)
-
-    monkeypatch.setattr(mcp_client, "_build_server", build)
-    registry = McpRegistry()
-    try:
-        connections = await mcp_client.attach_mcp_requests(
-            [McpConnectionRequest(_config(), refresh_token=refresh if with_refresher else None)],
-            registry,
-        )
-        assert len(connections) == 1
-        entry = registry.get("refresh")
-        assert entry is not None
-        assert entry.refresh_token is (refresh if with_refresher else None)
-        session = await entry.ensure_connected()
-        assert await session.dispatch("read", {}, label="refresh_read") == {
-            "type": "text",
-            "text": "ok",
-        }
-        valid = "new"
-        result = await session.dispatch("read", {}, label="refresh_read")
-        if with_refresher:
-            assert result == {"type": "text", "text": "ok"}
-            assert not session.is_dead
-            refresh.assert_awaited_once()
-        else:
-            assert result["success"] is False
-            assert session.is_dead
-    finally:
-        await registry.close()

tests/test_mcp_resilience.py

@@ -111,15 +111,6 @@ async def test_retry_after_parses_seconds_and_http_date() -> None:
     assert 0 <= retry_after <= 20
 
 
-@pytest.mark.asyncio
-async def test_successful_response_clears_previous_auth_failure() -> None:
-    recorder = HttpStatusRecorder()
-    await recorder(_http_error(401).response)
-    request = httpx.Request("POST", "https://provider.example/tools")
-    await recorder(httpx.Response(200, request=request))
-    assert recorder.take() is None
-
-
 @pytest.mark.asyncio
 async def test_recorder_only_keeps_non_sensitive_request_metadata() -> None:
     recorder = HttpStatusRecorder()

tests/test_pricing.py

@@ -1,50 +1,14 @@
 from __future__ import annotations
 
-import json
-from typing import TYPE_CHECKING
 from unittest.mock import patch
 
 import litellm
-import pytest
 from agents.usage import Usage
-from pydantic import ValidationError
 
-from strix.config import loader
-from strix.config.settings import LlmSettings
 from strix.report.pricing import resolve_litellm_model
 from strix.report.usage import LLMUsageLedger
 
 
-if TYPE_CHECKING:
-    from pathlib import Path
-
-
-PRICE_ENV = (
-    "STRIX_LLM_INPUT_COST_PER_MTOK",
-    "STRIX_LLM_OUTPUT_COST_PER_MTOK",
-    "STRIX_LLM_CACHED_INPUT_COST_PER_MTOK",
-)
-
-
-@pytest.fixture(autouse=True)
-def _isolated_settings(monkeypatch: pytest.MonkeyPatch, tmp_path: Path) -> None:
-    for name in PRICE_ENV:
-        monkeypatch.delenv(name, raising=False)
-    monkeypatch.setenv("STRIX_LLM", "gateway/unpriced-model")
-    monkeypatch.setattr(loader, "_override", tmp_path / "missing.json")
-    monkeypatch.setattr(loader, "_cached", None)
-
-
-def _usage(input_tokens: int, output_tokens: int = 0, cached_tokens: int = 0) -> Usage:
-    usage = Usage()
-    usage.requests = 1
-    usage.input_tokens = input_tokens
-    usage.output_tokens = output_tokens
-    usage.total_tokens = input_tokens + output_tokens
-    usage.input_tokens_details.cached_tokens = cached_tokens
-    return usage
-
-
 def test_resolves_common_bare_model_names() -> None:
     resolve_litellm_model.cache_clear()
     assert resolve_litellm_model("deepseek-v4-flash") == "deepseek/deepseek-v4-flash"
@@ -96,112 +60,6 @@ def test_ledger_prefers_observed_cost_over_estimate() -> None:
     assert ledger.total_cost == 0.17
 
 
-def test_unpriced_model_without_manual_rates_costs_zero() -> None:
-    ledger = LLMUsageLedger()
-
-    ledger.record(agent_id="a", usage=_usage(1000, 200), model="gateway/unpriced-model")
-
-    assert ledger.total_cost == 0.0
-
-
-def test_manual_rates_price_usage_and_override_observed_cost(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    monkeypatch.setenv("STRIX_LLM_INPUT_COST_PER_MTOK", "2")
-    monkeypatch.setenv("STRIX_LLM_OUTPUT_COST_PER_MTOK", "8")
-    ledger = LLMUsageLedger()
-
-    ledger.record(agent_id="a", usage=_usage(1000, 200), model="gateway/unpriced-model")
-    ledger.record_observed_cost(0.17)
-
-    assert ledger.total_cost == 0.0036
-    assert ledger.to_record()["agents"][0]["cost"] == 0.0036
-
-
-def test_manual_rates_from_config_file(tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
-    path = tmp_path / "config.json"
-    path.write_text(
-        json.dumps(
-            {
-                "env": {
-                    "STRIX_LLM_INPUT_COST_PER_MTOK": "2",
-                    "STRIX_LLM_OUTPUT_COST_PER_MTOK": "8",
-                }
-            }
-        ),
-        encoding="utf-8",
-    )
-    monkeypatch.setattr(loader, "_override", path)
-    ledger = LLMUsageLedger()
-
-    ledger.record(agent_id="a", usage=_usage(1000, 200), model="gateway/unpriced-model")
-
-    assert ledger.total_cost == 0.0036
-
-
-def test_manual_rates_only_price_the_configured_model(monkeypatch: pytest.MonkeyPatch) -> None:
-    monkeypatch.setenv("STRIX_LLM_INPUT_COST_PER_MTOK", "2")
-    monkeypatch.setenv("STRIX_LLM_OUTPUT_COST_PER_MTOK", "8")
-    ledger = LLMUsageLedger()
-
-    ledger.record(agent_id="a", usage=_usage(1000, 200), model="gateway/unpriced-model")
-    with patch("litellm.completion_cost", return_value=0.42):
-        ledger.record(agent_id="dedupe", usage=_usage(500, 50), model="deepseek/deepseek-v4-flash")
-    record = ledger.to_record()
-
-    assert ledger.total_cost == 0.4236
-    assert {agent["agent_id"]: agent["cost"] for agent in record["agents"]} == {
-        "a": 0.0036,
-        "dedupe": 0.42,
-    }
-
-
-def test_cached_tokens_fall_back_to_input_rate(monkeypatch: pytest.MonkeyPatch) -> None:
-    monkeypatch.setenv("STRIX_LLM_INPUT_COST_PER_MTOK", "5")
-    monkeypatch.setenv("STRIX_LLM_OUTPUT_COST_PER_MTOK", "7")
-    ledger = LLMUsageLedger()
-
-    ledger.record(
-        agent_id="a", usage=_usage(10, 1, cached_tokens=2), model="gateway/unpriced-model"
-    )
-
-    assert ledger.total_cost == 0.000057
-
-
-def test_hydrated_usage_uses_configured_rates_not_persisted_cost(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    monkeypatch.setenv("STRIX_LLM_INPUT_COST_PER_MTOK", "2")
-    monkeypatch.setenv("STRIX_LLM_OUTPUT_COST_PER_MTOK", "8")
-    original = LLMUsageLedger()
-    original.record(agent_id="a", usage=_usage(1000, 200), model="gateway/unpriced-model")
-    persisted = original.to_record()
-    persisted["cost"] = 42.0
-    persisted["agents"][0]["cost"] = 42.0
-    hydrated = LLMUsageLedger()
-
-    hydrated.hydrate(persisted)
-
-    assert hydrated.total_cost == 0.0036
-
-
-@pytest.mark.parametrize("value", ["invalid", "-1", "nan", "inf"])
-def test_invalid_manual_rate_is_rejected(value: str, monkeypatch: pytest.MonkeyPatch) -> None:
-    monkeypatch.setenv("STRIX_LLM_INPUT_COST_PER_MTOK", value)
-    with pytest.raises(ValidationError):
-        LlmSettings()
-
-
-def test_zero_cost_overrides_manual_rates(monkeypatch: pytest.MonkeyPatch) -> None:
-    monkeypatch.setenv("STRIX_LLM_INPUT_COST_PER_MTOK", "10")
-    ledger = LLMUsageLedger()
-    ledger.zero_cost = True
-
-    ledger.record(agent_id="a", usage=_usage(1000), model="gateway/unpriced-model")
-
-    assert ledger.total_cost == 0.0
-
-
 def test_hydrated_estimate_continues_accumulating_new_estimates() -> None:
     usage = Usage()
     usage.requests = 1

tests/test_reporting_fields.py

@@ -336,7 +336,7 @@ async def test_dependency_report_sets_class_and_metadata(report_state: ReportSta
         advisory_cvss=7.2,
         technical_analysis=None,
         fix_effort="trivial",
-        reachability="not_reachable",
+        reachability="imported",
         reachability_evidence=_DEP_EVIDENCE,
         contextual_cvss_breakdown=_DEP_CONTEXT,
         contextual_cvss_reasoning=_DEP_REASONING,
@@ -357,7 +357,7 @@ async def test_dependency_report_sets_class_and_metadata(report_state: ReportSta
         "package_ecosystem": "npm",
         "manifest_path": "package-lock.json",
         "fixed_version": "4.17.21",
-        "reachability": "not_reachable",
+        "reachability": "imported",
         "reachability_evidence": _DEP_EVIDENCE,
         "contextual_cvss_breakdown": _DEP_CONTEXT,
         "contextual_cvss_score": pytest.approx(7.5, abs=0.05),
@@ -386,7 +386,7 @@ async def test_dependency_report_records_transitive_chain(report_state: ReportSt
         fix_effort="trivial",
         introduced_by="[email protected]",
         dependency_path="[email protected] > [email protected] > [email protected]",
-        reachability="not_reachable",
+        reachability="imported",
         reachability_evidence=_DEP_EVIDENCE,
         contextual_cvss_breakdown=_DEP_CONTEXT,
         contextual_cvss_reasoning=_DEP_REASONING,
@@ -427,7 +427,7 @@ async def test_dependency_report_persists_code_locations(report_state: ReportSta
         advisory_cvss=7.2,
         technical_analysis=None,
         fix_effort="trivial",
-        reachability="reachable",
+        reachability="vulnerable_symbol_used",
         reachability_evidence=_DEP_EVIDENCE,
         code_locations=[
             {
@@ -468,7 +468,7 @@ async def test_dependency_report_fix_locations_require_verification(
         advisory_cvss=7.2,
         technical_analysis=None,
         fix_effort="trivial",
-        reachability="not_reachable",
+        reachability="imported",
         reachability_evidence=_DEP_EVIDENCE,
         code_locations=[
             {
@@ -509,7 +509,7 @@ async def test_dependency_report_fix_locations_persist_with_verification(
         advisory_cvss=7.2,
         technical_analysis=None,
         fix_effort="trivial",
-        reachability="not_reachable",
+        reachability="imported",
         reachability_evidence=_DEP_EVIDENCE,
         code_locations=[
             {
@@ -556,7 +556,7 @@ async def test_dependency_report_rejects_unusable_locations(
         advisory_cvss=7.2,
         technical_analysis=None,
         fix_effort="trivial",
-        reachability="not_reachable",
+        reachability="imported",
         reachability_evidence=_DEP_EVIDENCE,
         code_locations=[{"file": "/abs/path.ts", "snippet": "require('lodash')"}],
         contextual_cvss_breakdown=_DEP_CONTEXT,
@@ -587,7 +587,7 @@ async def test_dependency_report_omits_blank_chain_fields(report_state: ReportSt
         fix_effort="trivial",
         introduced_by="  ",
         dependency_path=None,
-        reachability="not_reachable",
+        reachability="imported",
         reachability_evidence=_DEP_EVIDENCE,
         contextual_cvss_breakdown=_DEP_CONTEXT,
         contextual_cvss_reasoning=_DEP_REASONING,
@@ -618,7 +618,7 @@ async def test_dependency_report_with_no_contextual_impact_is_info(
         advisory_cvss=0.0,
         technical_analysis=None,
         fix_effort="low",
-        reachability="not_applicable",
+        reachability="not_imported",
         reachability_evidence="No file imports the package.",
         contextual_cvss_breakdown={**_DEP_CONTEXT, "availability": "N"},
         contextual_cvss_reasoning="No application code imports the package.",
@@ -649,7 +649,7 @@ async def test_dependency_report_records_reachability(report_state: ReportState)
         advisory_cvss=7.2,
         technical_analysis=None,
         fix_effort="low",
-        reachability="reachable",
+        reachability="vulnerable_symbol_used",
         reachability_evidence="src/render.ts:14 calls `_.template()`.",
         contextual_cvss_breakdown=_DEP_CONTEXT,
         contextual_cvss_reasoning=_DEP_REASONING,
@@ -657,7 +657,7 @@ async def test_dependency_report_records_reachability(report_state: ReportState)
 
     assert result["success"] is True
     report = report_state.vulnerability_reports[0]
-    assert report["dependency_metadata"]["reachability"] == "reachable"
+    assert report["dependency_metadata"]["reachability"] == "vulnerable_symbol_used"
     assert (
         report["dependency_metadata"]["reachability_evidence"]
         == "src/render.ts:14 calls `_.template()`."
@@ -688,7 +688,7 @@ async def test_dependency_report_rejects_reachability_without_evidence(
         advisory_cvss=5.0,
         technical_analysis=None,
         fix_effort="low",
-        reachability="not_applicable",
+        reachability="not_imported",
     )
 
     assert result["success"] is False
@@ -725,7 +725,7 @@ async def test_dependency_report_rejects_unknown_reachability_level(
     assert not report_state.vulnerability_reports
 
 
-async def test_dependency_report_requires_a_reachability_verdict(report_state: ReportState) -> None:
+async def test_dependency_report_records_unknown_reachability(report_state: ReportState) -> None:
     result = await _do_create_dependency(
         title="CVE-2024-0001 in sample 1.0.0",
         description="Published advisory affects the pinned version.",
@@ -748,9 +748,10 @@ async def test_dependency_report_requires_a_reachability_verdict(report_state: R
         contextual_cvss_reasoning=_DEP_REASONING,
     )
 
-    assert result["success"] is False, result
-    assert any("reachability is required" in e for e in result["errors"])
-    assert not report_state.vulnerability_reports
+    assert result["success"] is True, result
+    metadata = report_state.vulnerability_reports[0]["dependency_metadata"]
+    assert metadata["reachability"] == "unknown"
+    assert metadata["reachability_evidence"] == "Grep for the package found no import."
 
 
 async def test_dependency_report_requires_advisory_cvss(report_state: ReportState) -> None:
@@ -827,7 +828,7 @@ async def test_dependency_report_dedupe_candidate_includes_dependency_metadata(
         advisory_cvss=0.0,
         technical_analysis=None,
         fix_effort="low",
-        reachability="not_reachable",
+        reachability="imported",
         reachability_evidence=_DEP_EVIDENCE,
         contextual_cvss_breakdown=_DEP_CONTEXT,
         contextual_cvss_reasoning=_DEP_REASONING,
@@ -846,7 +847,7 @@ async def test_dependency_report_dedupe_candidate_includes_dependency_metadata(
             "package_ecosystem": "npm",
             "manifest_path": "package-lock.json",
             "fixed_version": "1.0.1",
-            "reachability": "not_reachable",
+            "reachability": "imported",
             "reachability_evidence": _DEP_EVIDENCE,
             "contextual_cvss_breakdown": _DEP_CONTEXT,
             "contextual_cvss_score": pytest.approx(7.5, abs=0.05),
@@ -1380,7 +1381,7 @@ async def test_dependency_report_computes_contextual_cvss(
         cwe="CWE-94",
         fix_effort="trivial",
         manifest_path="package-lock.json",
-        reachability="reachable",
+        reachability="vulnerable_symbol_used",
         reachability_evidence="scripts/import.py:88 calls `_.template()`.",
         contextual_cvss_breakdown=_CONTEXTUAL_BREAKDOWN,
         contextual_cvss_reasoning="Only scripts/import.py reaches the sink.",
@@ -1420,7 +1421,7 @@ async def test_dependency_report_requires_contextual_breakdown(
         cwe="CWE-94",
         fix_effort="trivial",
         manifest_path="package-lock.json",
-        reachability="not_reachable",
+        reachability="imported",
         reachability_evidence=_DEP_EVIDENCE,
     )
     assert result["success"] is False