mirror of
https://github.com/usestrix/strix.git
synced 2026-08-16 17:27:26 +02:00
Compare commits
1
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 0xallam
|
106b463e85 |
@@ -6,9 +6,6 @@ on:
|
||||
- 'v*'
|
||||
workflow_dispatch:
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
jobs:
|
||||
build:
|
||||
strategy:
|
||||
@@ -21,23 +18,19 @@ jobs:
|
||||
target: macos-x86_64
|
||||
- os: ubuntu-22.04
|
||||
target: linux-x86_64
|
||||
- os: ubuntu-22.04-arm
|
||||
target: linux-arm64
|
||||
- os: windows-latest
|
||||
target: windows-x86_64
|
||||
|
||||
runs-on: ${{ matrix.os }}
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4.4.0
|
||||
with:
|
||||
persist-credentials: false
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
|
||||
- uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: '3.12'
|
||||
|
||||
- uses: astral-sh/setup-uv@d4b2f3b6ecc6e67c4457f6d3e41ec42d3d0fcb86 # v5.4.2
|
||||
- uses: astral-sh/setup-uv@v5
|
||||
|
||||
- name: Build
|
||||
shell: bash
|
||||
@@ -45,20 +38,6 @@ jobs:
|
||||
uv sync --frozen
|
||||
uv run pyinstaller strix.spec --noconfirm
|
||||
|
||||
if [[ "${{ runner.os }}" == "Windows" ]]; then
|
||||
dist/strix.exe --version
|
||||
else
|
||||
dist/strix --version
|
||||
fi
|
||||
|
||||
if [[ "${{ matrix.target }}" == "linux-arm64" ]]; then
|
||||
file dist/strix
|
||||
file dist/strix | grep -q "ARM aarch64" || {
|
||||
echo "::error::linux-arm64 artifact is not an ARM aarch64 binary"
|
||||
exit 1
|
||||
}
|
||||
fi
|
||||
|
||||
VERSION=$(grep '^version' pyproject.toml | head -1 | sed 's/.*"\(.*\)"/\1/')
|
||||
mkdir -p dist/release
|
||||
|
||||
@@ -71,7 +50,7 @@ jobs:
|
||||
tar -C dist/release -czvf "dist/release/strix-${VERSION}-${{ matrix.target }}.tar.gz" "strix-${VERSION}-${{ matrix.target }}"
|
||||
fi
|
||||
|
||||
- uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
|
||||
- uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: strix-${{ matrix.target }}
|
||||
path: |
|
||||
@@ -86,13 +65,13 @@ jobs:
|
||||
contents: write
|
||||
|
||||
steps:
|
||||
- uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
|
||||
- uses: actions/download-artifact@v4
|
||||
with:
|
||||
path: release
|
||||
merge-multiple: true
|
||||
|
||||
- name: Create Release
|
||||
uses: softprops/action-gh-release@3bb12739c298aeb8a4eeaf626c5b8d85266b0e65 # v2.6.2
|
||||
uses: softprops/action-gh-release@v2
|
||||
with:
|
||||
prerelease: ${{ !startsWith(github.ref, 'refs/tags/') }}
|
||||
generate_release_notes: true
|
||||
|
||||
@@ -1,112 +0,0 @@
|
||||
name: Sandbox Image
|
||||
|
||||
on:
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
tag:
|
||||
description: 'Image tag to publish (e.g. 1.2.0)'
|
||||
required: true
|
||||
latest:
|
||||
description: 'Also tag as latest'
|
||||
type: boolean
|
||||
default: true
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
env:
|
||||
IMAGE: ghcr.io/${{ github.repository_owner }}/strix-sandbox
|
||||
|
||||
jobs:
|
||||
build:
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
include:
|
||||
- os: ubuntu-22.04
|
||||
platform: linux/amd64
|
||||
- os: ubuntu-22.04-arm
|
||||
platform: linux/arm64
|
||||
|
||||
runs-on: ${{ matrix.os }}
|
||||
permissions:
|
||||
contents: read
|
||||
packages: write
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
|
||||
with:
|
||||
persist-credentials: false
|
||||
|
||||
- uses: docker/setup-buildx-action@bb05f3f5519dd87d3ba754cc423b652a5edd6d2c # v4.2.0
|
||||
|
||||
- uses: docker/login-action@dbcb813823bdd20940b903addbd779551569679f # v4.6.0
|
||||
with:
|
||||
registry: ghcr.io
|
||||
username: ${{ github.actor }}
|
||||
password: ${{ secrets.GITHUB_TOKEN }}
|
||||
|
||||
- name: Build and push by digest
|
||||
id: build
|
||||
uses: docker/build-push-action@53b7df96c91f9c12dcc8a07bcb9ccacbed38856a # v7.3.0
|
||||
with:
|
||||
context: .
|
||||
file: containers/Dockerfile
|
||||
platforms: ${{ matrix.platform }}
|
||||
provenance: mode=max
|
||||
sbom: true
|
||||
outputs: type=image,name=${{ env.IMAGE }},push-by-digest=true,name-canonical=true,push=true
|
||||
|
||||
- name: Export digest
|
||||
env:
|
||||
DIGEST: ${{ steps.build.outputs.digest }}
|
||||
run: |
|
||||
set -euo pipefail
|
||||
mkdir -p /tmp/digests
|
||||
touch "/tmp/digests/${DIGEST#sha256:}"
|
||||
|
||||
- uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
|
||||
with:
|
||||
name: digest-${{ runner.arch }}
|
||||
path: /tmp/digests/*
|
||||
if-no-files-found: error
|
||||
retention-days: 1
|
||||
|
||||
publish:
|
||||
needs: build
|
||||
runs-on: ubuntu-latest
|
||||
permissions:
|
||||
contents: read
|
||||
packages: write
|
||||
|
||||
steps:
|
||||
- uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
|
||||
with:
|
||||
path: /tmp/digests
|
||||
pattern: digest-*
|
||||
merge-multiple: true
|
||||
|
||||
- uses: docker/setup-buildx-action@bb05f3f5519dd87d3ba754cc423b652a5edd6d2c # v4.2.0
|
||||
|
||||
- uses: docker/login-action@dbcb813823bdd20940b903addbd779551569679f # v4.6.0
|
||||
with:
|
||||
registry: ghcr.io
|
||||
username: ${{ github.actor }}
|
||||
password: ${{ secrets.GITHUB_TOKEN }}
|
||||
|
||||
- name: Create manifest list
|
||||
env:
|
||||
TAG: ${{ inputs.tag }}
|
||||
ALSO_LATEST: ${{ inputs.latest }}
|
||||
run: |
|
||||
set -euo pipefail
|
||||
tags=(-t "${IMAGE}:${TAG}")
|
||||
if [ "${ALSO_LATEST}" = "true" ]; then
|
||||
tags+=(-t "${IMAGE}:latest")
|
||||
fi
|
||||
digests=()
|
||||
for file in /tmp/digests/*; do
|
||||
digests+=("${IMAGE}@sha256:$(basename "$file")")
|
||||
done
|
||||
docker buildx imagetools create "${tags[@]}" "${digests[@]}"
|
||||
docker buildx imagetools inspect "${IMAGE}:${TAG}"
|
||||
+3
-3
@@ -1,8 +1,8 @@
|
||||
# Node / local-viewer SPA source (the built bundle in
|
||||
# strix/interface/viewer/static/ is committed and shipped; do not ignore it)
|
||||
# strix/viewer/static/ is committed and shipped; do not ignore it)
|
||||
node_modules/
|
||||
strix/interface/viewer/frontend/node_modules/
|
||||
strix/interface/viewer/frontend/.vite/
|
||||
strix/viewer/frontend/node_modules/
|
||||
strix/viewer/frontend/.vite/
|
||||
|
||||
# Python
|
||||
__pycache__/
|
||||
|
||||
+5
-5
@@ -102,16 +102,16 @@ We welcome feature ideas! Please:
|
||||
## 🖥️ Local viewer SPA
|
||||
|
||||
`strix view` serves a prebuilt web UI whose source lives in
|
||||
`strix/interface/viewer/frontend/` (a Vite + React project) and whose built output is
|
||||
committed to `strix/interface/viewer/static/` and shipped in the package. End users never
|
||||
run a JS build. If you change anything under `strix/interface/viewer/frontend/`, rebuild
|
||||
`strix/viewer/frontend/` (a Vite + React project) and whose built output is
|
||||
committed to `strix/viewer/static/` and shipped in the package. End users never
|
||||
run a JS build. If you change anything under `strix/viewer/frontend/`, rebuild
|
||||
and commit the output:
|
||||
|
||||
```bash
|
||||
make viewer # or: cd strix/interface/viewer/frontend && npm ci && npm run build
|
||||
make viewer # or: cd strix/viewer/frontend && npm ci && npm run build
|
||||
```
|
||||
|
||||
Commit both the source change and the regenerated `strix/interface/viewer/static/`.
|
||||
Commit both the source change and the regenerated `strix/viewer/static/`.
|
||||
|
||||
## 🤝 Community
|
||||
|
||||
|
||||
@@ -69,8 +69,8 @@ clean:
|
||||
|
||||
viewer:
|
||||
@echo "🖥️ Building the local-viewer SPA..."
|
||||
cd strix/interface/viewer/frontend && npm ci && npm run build
|
||||
@echo "✅ Viewer built to strix/interface/viewer/static/ (commit the changes)."
|
||||
cd strix/viewer/frontend && npm ci && npm run build
|
||||
@echo "✅ Viewer built to strix/viewer/static/ (commit the changes)."
|
||||
|
||||
dev: format lint type-check
|
||||
@echo "✅ Development cycle complete!"
|
||||
|
||||
@@ -267,20 +267,6 @@ export STRIX_REASONING_EFFORT="high" # control thinking effort (default: high,
|
||||
> [!NOTE]
|
||||
> Strix automatically saves your configuration to `~/.strix/cli-config.json`, so you don't have to re-enter it on every run.
|
||||
|
||||
#### Sign in with a ChatGPT subscription
|
||||
|
||||
Instead of a metered API key, you can run Strix on your ChatGPT Plus/Pro subscription:
|
||||
|
||||
```bash
|
||||
strix auth login chatgpt # sign in with your ChatGPT account
|
||||
|
||||
export STRIX_LLM="chatgpt/gpt-5.4" # chatgpt/<model> runs on the subscription
|
||||
strix --target ./app-directory
|
||||
|
||||
strix auth status # show the active sign-in
|
||||
strix auth logout # forget the sign-in
|
||||
```
|
||||
|
||||
**Recommended models for best results:**
|
||||
|
||||
- [OpenAI GPT-5.4](https://openai.com/api/) - `openai/gpt-5.4`
|
||||
|
||||
@@ -162,7 +162,6 @@ USER root
|
||||
ARG TRUFFLEHOG_VERSION=3.95.9
|
||||
RUN curl -sSfL https://raw.githubusercontent.com/trufflesecurity/trufflehog/main/scripts/install.sh | sh -s -- -b /home/pentester/.local/bin "v${TRUFFLEHOG_VERSION}" && \
|
||||
chown -R pentester:pentester /home/pentester/.local
|
||||
ARG GITLEAKS_VERSION=8.30.1
|
||||
RUN set -eux; \
|
||||
ARCH="$(uname -m)"; \
|
||||
case "$ARCH" in \
|
||||
@@ -170,7 +169,8 @@ RUN set -eux; \
|
||||
aarch64|arm64) GITLEAKS_ARCH="arm64" ;; \
|
||||
*) echo "Unsupported architecture: $ARCH" >&2; exit 1 ;; \
|
||||
esac; \
|
||||
curl -fsSL "https://github.com/gitleaks/gitleaks/releases/download/v${GITLEAKS_VERSION}/gitleaks_${GITLEAKS_VERSION}_linux_${GITLEAKS_ARCH}.tar.gz" -o /tmp/gitleaks.tgz; \
|
||||
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
|
||||
|
||||
@@ -1,22 +1,6 @@
|
||||
#!/bin/bash
|
||||
set -e
|
||||
|
||||
if [ -n "${STRIX_HOST_UID:-}" ] && [ "${STRIX_HOST_UID}" != "0" ] && [ "${STRIX_HOST_UID}" != "$(id -u)" ]; then
|
||||
exec sudo -E -- bash -c '
|
||||
set -e
|
||||
gid="${STRIX_HOST_GID:-$STRIX_HOST_UID}"
|
||||
old_uid="$1"
|
||||
old_gid="$2"
|
||||
export PATH="$3"
|
||||
shift 3
|
||||
sed -i "s|^pentester:x:${old_uid}:${old_gid}:|pentester:x:${STRIX_HOST_UID}:${gid}:|" /etc/passwd
|
||||
sed -i "s|^pentester:x:${old_gid}:|pentester:x:${gid}:|" /etc/group
|
||||
chown -R "${STRIX_HOST_UID}:${gid}" /home/pentester /app/certs
|
||||
chown "${STRIX_HOST_UID}:${gid}" /workspace
|
||||
exec setpriv --reuid "${STRIX_HOST_UID}" --regid "${gid}" --init-groups "$0" "$@"
|
||||
' "$0" "$(id -u)" "$(id -g)" "$PATH" "$@"
|
||||
fi
|
||||
|
||||
CAIDO_PORT=48080
|
||||
CAIDO_LOG="/tmp/caido_startup.log"
|
||||
|
||||
|
||||
@@ -19,14 +19,6 @@ 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="LLM_EXTRA_HEADERS" type="string">
|
||||
Extra HTTP headers sent on every LLM request, as a JSON object (e.g.
|
||||
`{"X-Feature-Key":"value","X-Tenant":"acme"}`). Useful for OpenAI-compatible
|
||||
gateways that require attribution or routing headers in addition to the bearer
|
||||
token. The bearer token itself still comes from `LLM_API_KEY`. Applies to both
|
||||
the LiteLLM and native OpenAI routing paths.
|
||||
</ParamField>
|
||||
|
||||
<ParamField path="LLM_TIMEOUT" default="300" type="integer">
|
||||
Request timeout in seconds for LLM calls.
|
||||
</ParamField>
|
||||
@@ -36,44 +28,13 @@ Configure Strix using environment variables or a config file.
|
||||
</ParamField>
|
||||
|
||||
<ParamField path="STRIX_REASONING_EFFORT" default="high" type="string">
|
||||
Control thinking effort for reasoning models. Valid values: `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, `max`. Defaults to `medium` for quick scan mode.
|
||||
Control thinking effort for reasoning models. Valid values: `none`, `minimal`, `low`, `medium`, `high`, `xhigh`. Defaults to `medium` for quick scan mode.
|
||||
</ParamField>
|
||||
|
||||
<ParamField path="STRIX_MEMORY_COMPRESSOR_TIMEOUT" default="30" type="integer">
|
||||
Timeout in seconds for memory compression operations (context summarization).
|
||||
</ParamField>
|
||||
|
||||
### Dedicated deduplication model
|
||||
|
||||
Finding deduplication is a cheap, structured classification task. By default it
|
||||
runs on the main model, but you can route it to a smaller/cheaper model without
|
||||
affecting the agents that do the actual testing.
|
||||
|
||||
<ParamField path="STRIX_DEDUPE_MODEL" type="string">
|
||||
Model used to judge whether a candidate finding duplicates an existing report.
|
||||
Falls back to `STRIX_LLM` when unset.
|
||||
</ParamField>
|
||||
|
||||
<ParamField path="DEDUPE_LLM_API_KEY" type="string">
|
||||
Optional provider key for the deduplication model.
|
||||
</ParamField>
|
||||
|
||||
<ParamField path="DEDUPE_LLM_API_BASE" type="string">
|
||||
Optional custom API base URL for the deduplication model. Use when the dedupe
|
||||
model runs on a different endpoint than the main model.
|
||||
</ParamField>
|
||||
|
||||
<ParamField path="DEDUPE_LLM_EXTRA_HEADERS" type="string">
|
||||
Optional JSON object of extra HTTP headers sent on every deduplication-model
|
||||
request, e.g. `{"X-Feature-Key":"value"}`. A dedicated dedupe model never
|
||||
inherits `LLM_EXTRA_HEADERS`; set this when its endpoint needs custom headers.
|
||||
</ParamField>
|
||||
|
||||
<ParamField path="STRIX_DEDUPE_REASONING_EFFORT" type="string">
|
||||
Reasoning effort for the deduplication model. Defaults to the model's own
|
||||
baseline when unset.
|
||||
</ParamField>
|
||||
|
||||
## Optional Features
|
||||
|
||||
<ParamField path="PERPLEXITY_API_KEY" type="string">
|
||||
@@ -106,7 +67,7 @@ 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:1.2.0" type="string">
|
||||
<ParamField path="STRIX_IMAGE" default="ghcr.io/usestrix/strix-sandbox:1.0.0" type="string">
|
||||
Docker image to use for the sandbox container.
|
||||
</ParamField>
|
||||
|
||||
@@ -118,6 +79,10 @@ When remote vars are set, Strix dual-writes telemetry to both local JSONL and th
|
||||
Runtime backend for the sandbox environment.
|
||||
</ParamField>
|
||||
|
||||
<ParamField path="STRIX_MAX_LOCAL_COPY_MB" default="1024" type="integer">
|
||||
Maximum size (in MB) of a local directory target that Strix will copy into the sandbox file-by-file. Larger targets exit early with a suggestion to use `--mount` instead. Set to `0` to disable the check.
|
||||
</ParamField>
|
||||
|
||||
## Sandbox Configuration
|
||||
|
||||
<ParamField path="STRIX_SANDBOX_EXECUTION_TIMEOUT" default="120" type="integer">
|
||||
|
||||
@@ -54,55 +54,3 @@ If you use LM Studio, vLLM, or other runners:
|
||||
export STRIX_LLM="openai/local-model"
|
||||
export LLM_API_BASE="http://localhost:1234/v1" # Adjust port as needed
|
||||
```
|
||||
|
||||
### Gateways that require custom headers
|
||||
|
||||
Some OpenAI-compatible gateways require extra HTTP headers (for attribution or
|
||||
tenant routing) alongside the bearer token. Set them with `LLM_EXTRA_HEADERS` as
|
||||
a JSON object — they are sent on every request:
|
||||
|
||||
```bash
|
||||
export STRIX_LLM="openai/your-model"
|
||||
export LLM_API_BASE="https://your-gateway.example/v1"
|
||||
export LLM_API_KEY="your-bearer-token" # sent as Authorization: Bearer ...
|
||||
export LLM_EXTRA_HEADERS='{"X-Feature-Key":"value","X-Tenant":"acme"}'
|
||||
```
|
||||
|
||||
For endpoints behind a private CA, point Strix at your certificate bundle with
|
||||
the standard `SSL_CERT_FILE=/path/to/ca-bundle.pem` — never disable TLS
|
||||
verification against a real endpoint.
|
||||
|
||||
## Tool calling must return structured `tool_calls`
|
||||
|
||||
Strix is entirely tool-driven: every working turn must be a **native** function/tool call. If your inference server returns the tool call as plain assistant text instead of a structured `tool_calls` field, Strix never sees a call it can execute, so the agent makes no real progress — it re-prompts the model for a tool call and gives up once its recovery attempts are exhausted.
|
||||
|
||||
This is almost always an **inference-server configuration** problem, not a model or Strix problem. Common symptoms are the model printing a call as text such as:
|
||||
|
||||
```text
|
||||
<tool_call>{"name": "exec_command", "arguments": {"cmd": "nmap ..."}}</tool_call>
|
||||
exec_command(cmd="nmap ...", timeout=180)
|
||||
{"action": "exec_command", "params": {"cmd": "nmap ..."}}
|
||||
```
|
||||
|
||||
The fix belongs on the inference server: it must be configured to parse the model's tool tokens into structured `tool_calls`. A correctly configured endpoint either returns a structured call or rejects the request outright — it never leaks the call as text.
|
||||
|
||||
### Fixes by server
|
||||
|
||||
**llama.cpp (`llama-server`)**
|
||||
- Run with `--jinja` and a correct tool-use chat template (`--chat-template` / `--chat-template-file` matching the model). Recent builds enable `--jinja` by default — **upgrade** if yours doesn't.
|
||||
- For thinking models, align or disable reasoning (`--reasoning-format`, `-rea off`) so it doesn't break tool-call parsing.
|
||||
- A low temperature (e.g. `--temp 0.2`) improves tool-call reliability.
|
||||
|
||||
**Ollama**
|
||||
- Use a recent Ollama and a model whose template wires tools. Modern Ollama refuses tools (`tools param requires --jinja flag`) if the template lacks tool support.
|
||||
- For reasoning models (e.g. qwen3), disable the model's **thinking** mode — thinking left on frequently pushes the tool call into the text `content` instead of the structured `tool_calls` field. Turn it off on the Ollama side (a non-thinking model variant, or `think: false` in the model's parameters / `Modelfile`).
|
||||
- Raise **`num_ctx`** to at least 16k–32k. Strix sends a large system prompt plus many tool schemas; at Ollama's small default context the tool definitions are truncated out of the prompt and the model stops emitting valid calls. A short test prompt can look fine while a real scan fails, so set this explicitly rather than inferring it from a quick check.
|
||||
|
||||
**vLLM**
|
||||
- Start with `--enable-auto-tool-choice`, a matching `--tool-call-parser` (`hermes`, `qwen3_xml`, or `llama3_json`), and a matching `--reasoning-parser` for reasoning models.
|
||||
|
||||
A low sampling temperature (roughly 0.2–0.6, depending on the family) also measurably reduces malformed tool calls on open-weight models. Set it on the server or in your model's parameters.
|
||||
|
||||
<Warning>
|
||||
Even correctly configured, small models (< ~30B) emit malformed or text-form tool calls far more often than frontier models. Prefer a capable model for reliable agentic behavior.
|
||||
</Warning>
|
||||
|
||||
+23
-44
@@ -6,23 +6,33 @@ description: "Command-line options for Strix"
|
||||
## Basic Usage
|
||||
|
||||
```bash
|
||||
strix (--target <target> | --target-list <path>) [options]
|
||||
strix (--target <target> | --target-list <path> | --mount <path>) [options]
|
||||
```
|
||||
|
||||
## Options
|
||||
|
||||
<ParamField path="--target, -t" type="string">
|
||||
Target to test. Accepts URLs, repositories, local directories, domains, or IP addresses. Can be specified multiple times. Fresh runs require at least one target source: `--target` or `--target-list`.
|
||||
|
||||
<Note>
|
||||
A local directory is mounted into the sandbox live and **writable**, so the agent edits your real files (`.git` excepted). Commit or stash first.
|
||||
</Note>
|
||||
Target to test. Accepts URLs, repositories, local directories, domains, or IP addresses. Can be specified multiple times. Fresh runs require at least one target source: `--target`, `--target-list`, or `--mount`.
|
||||
</ParamField>
|
||||
|
||||
<ParamField path="--target-list" type="string">
|
||||
Path to a file containing targets, one per non-empty, non-comment line. Lines starting with `#` are ignored. Can be specified multiple times and combined with `--target`.
|
||||
</ParamField>
|
||||
|
||||
<ParamField path="--mount" type="string">
|
||||
Bind-mount a local directory into the sandbox (read-only) instead of copying it in file-by-file. Use this for large repositories that are too big to stream into the container. Can be specified multiple times.
|
||||
|
||||
Strix copies local `--target` directories into the sandbox one file at a time, which stalls on very large trees. When a local target exceeds the copy limit (see `STRIX_MAX_LOCAL_COPY_MB`, default 1024 MB) Strix exits early and asks you to re-run with `--mount`.
|
||||
|
||||
<Note>
|
||||
The mount is read-only to protect your source from accidental modification. This is not a hard security boundary: a root process inside the container can remount it writable, so treat `--mount` as "scan my own code", not as isolation from untrusted code.
|
||||
</Note>
|
||||
|
||||
<Note>
|
||||
The size pre-flight only covers local directory targets. Remote repositories (cloned at scan time) are not size-checked.
|
||||
</Note>
|
||||
</ParamField>
|
||||
|
||||
<ParamField path="--instruction" type="string">
|
||||
Custom instructions for the scan. Use for credentials, focus areas, or specific testing approaches.
|
||||
</ParamField>
|
||||
@@ -51,28 +61,11 @@ strix (--target <target> | --target-list <path>) [options]
|
||||
Path to a custom config file (JSON) to use instead of `~/.strix/cli-config.json`.
|
||||
</ParamField>
|
||||
|
||||
<ParamField path="--max-budget" type="number">
|
||||
<ParamField path="--max-budget-usd" type="number">
|
||||
Maximum LLM spend in USD for the whole scan, counted cumulatively across the
|
||||
root agent and every child agent. The budget is checked after each model
|
||||
response.
|
||||
|
||||
In non-interactive mode (`-n`), once the running cost reaches the threshold,
|
||||
the scan stops cleanly with a `stopped` status (not a failure) and the sandbox
|
||||
is torn down. Sub-agents are stopped early, at 90% of the budget, reserving
|
||||
the final slice for the root agent to wind down and produce the final report.
|
||||
|
||||
In interactive mode, reaching the budget pauses the scan instead of ending
|
||||
it: every agent parks, and sending any message resumes the scan with the cap
|
||||
extended by the original budget amount. There is no sub-agent reserve in
|
||||
interactive mode.
|
||||
|
||||
As the budget is approached, graduated wrap-up warnings are surfaced to
|
||||
**every** agent so they can finish their work and call their lifecycle tool
|
||||
before the hard stop. The bands sit just below each role's own stop point: the
|
||||
root is warned at **70%, 85% and 95%** (it stops at 100%), while sub-agents are
|
||||
warned at **75%, 80% and 85%** (they stop at the 90% reserve). In interactive
|
||||
mode every agent uses the **70%, 85% and 95%** bands. Percentages shown in the
|
||||
warnings are the real cumulative spend against the full budget.
|
||||
response; once the running cost reaches the threshold, the scan stops cleanly
|
||||
with a `stopped` status (not a failure) and the sandbox is torn down.
|
||||
|
||||
Must be greater than `0`. Omit the flag for no limit.
|
||||
|
||||
@@ -91,19 +84,6 @@ strix (--target <target> | --target-list <path>) [options]
|
||||
counts.
|
||||
</ParamField>
|
||||
|
||||
<ParamField path="--max-turns" type="integer" default="500">
|
||||
Maximum number of turns (one model response plus its tool round) allotted to
|
||||
**each** agent, applied per run. When an agent reaches this limit it is
|
||||
force-stopped.
|
||||
|
||||
As the limit is approached, graduated wrap-up warnings (at 70%, 85% and 95%)
|
||||
are injected into that agent's next model turn so it can prioritise its
|
||||
remaining work and call its lifecycle tool (`finish_scan` for the root agent,
|
||||
`agent_finish` for sub-agents) before the hard stop.
|
||||
|
||||
Must be greater than `0`.
|
||||
</ParamField>
|
||||
|
||||
## Examples
|
||||
|
||||
```bash
|
||||
@@ -119,9 +99,6 @@ strix --target api.example.com --instruction "Focus on IDOR and auth bypass"
|
||||
# CI/CD mode
|
||||
strix -n --target ./ --scan-mode quick
|
||||
|
||||
# Cap cost and per-agent turns
|
||||
strix --target https://example.com --max-budget 25 --max-turns 300
|
||||
|
||||
# Force diff-scope against a specific base ref
|
||||
strix -n --target ./ --scan-mode quick --scope-mode diff --diff-base origin/main
|
||||
|
||||
@@ -130,12 +107,14 @@ strix -t https://github.com/org/app -t https://staging.example.com
|
||||
|
||||
# Targets from a file
|
||||
strix --target-list ./targets.txt
|
||||
|
||||
# Large local repository — bind-mount instead of copying it in
|
||||
strix --mount ./huge-monorepo
|
||||
```
|
||||
|
||||
## Exit Codes
|
||||
|
||||
| Code | Meaning |
|
||||
|------|---------|
|
||||
| 0 | Scan completed successfully (interactive mode always exits `0`; in headless mode, `0` means no vulnerabilities were found) |
|
||||
| 1 | A fatal error occurred before or during the scan (e.g. missing environment variables, Docker unavailable, invalid config file, diff-scope resolution failure, or an unhandled error) |
|
||||
| 0 | Scan completed, no vulnerabilities found |
|
||||
| 2 | Vulnerabilities found (headless mode only) |
|
||||
|
||||
+9
-24
@@ -1,6 +1,6 @@
|
||||
[project]
|
||||
name = "strix-agent"
|
||||
version = "1.4.1"
|
||||
version = "1.3.0"
|
||||
description = "Open-source AI Hackers for your apps"
|
||||
readme = "README.md"
|
||||
license = "Apache-2.0"
|
||||
@@ -46,9 +46,7 @@ dependencies = [
|
||||
"caido-sdk-client>=0.2.0",
|
||||
"reportlab>=4.0",
|
||||
"pypdf>=5.0",
|
||||
# Cap <49: 49.x drops the universal2 macOS wheel (arm64-only), which breaks
|
||||
# the Intel macOS (macos-x86_64) release build's `uv sync --frozen`.
|
||||
"cryptography>=48.0.1,<49",
|
||||
"cryptography>=42",
|
||||
]
|
||||
|
||||
[project.optional-dependencies]
|
||||
@@ -79,10 +77,10 @@ build-backend = "hatchling.build"
|
||||
|
||||
[tool.hatch.build.targets.wheel]
|
||||
packages = ["strix"]
|
||||
# The prebuilt viewer bundle under strix/interface/viewer/static/ ships automatically
|
||||
# The prebuilt viewer bundle under strix/viewer/static/ ships automatically
|
||||
# (hatchling includes non-.py files under the package). The Vite SOURCE lives
|
||||
# under the package dir too (strix/interface/viewer/frontend/) but must never ship in the wheel.
|
||||
exclude = ["strix/interface/viewer/frontend", "strix/interface/viewer/frontend/**"]
|
||||
# under the package dir too (strix/viewer/frontend/) but must never ship in the wheel.
|
||||
exclude = ["strix/viewer/frontend", "strix/viewer/frontend/**"]
|
||||
|
||||
# ============================================================================
|
||||
# Type Checking Configuration
|
||||
@@ -122,7 +120,6 @@ module = [
|
||||
"pydantic_settings.*",
|
||||
"reportlab.*",
|
||||
"pypdf.*",
|
||||
"pygments.*",
|
||||
]
|
||||
ignore_missing_imports = true
|
||||
disable_error_code = ["import-untyped"]
|
||||
@@ -216,17 +213,12 @@ ignore = [
|
||||
# Test doubles use fixture tokens/passwords and match a callee signature whose
|
||||
# args they intentionally ignore.
|
||||
"tests/test_viewer_auth.py" = ["S105", "S106", "ARG001"]
|
||||
"tests/test_codex_auth.py" = ["S105", "S106", "SLF001"]
|
||||
# Stdlib HTTP handler overrides (do_GET/do_POST).
|
||||
"strix/interface/auth_cli.py" = ["N802"]
|
||||
"tests/test_codex_streaming.py" = ["N802"]
|
||||
"tests/test_disable_streaming.py" = ["N802"]
|
||||
"tests/test_report_pdf.py" = ["S105", "S106"]
|
||||
# Stdlib HTTP handler overrides (do_GET/do_POST) and lazy imports that avoid a
|
||||
# circular dependency with strix.telemetry / strix.interface.viewer.report_pdf.
|
||||
"strix/interface/viewer/server.py" = ["N802", "PLC0415"]
|
||||
# circular dependency with strix.telemetry / strix.viewer.report_pdf.
|
||||
"strix/viewer/server.py" = ["N802", "PLC0415"]
|
||||
# Lazy telemetry import to avoid importing PostHog before the viewer starts.
|
||||
"strix/interface/viewer/cli.py" = ["PLC0415"]
|
||||
"strix/viewer/cli.py" = ["PLC0415"]
|
||||
# Lazy imports inside functions to avoid circular dependency with
|
||||
# strix.telemetry / strix.report.dedupe / cvss.
|
||||
"strix/tools/notes/tools.py" = ["PLC0415", "TC002"]
|
||||
@@ -259,16 +251,9 @@ ignore = [
|
||||
"strix/core/runner.py" = ["TC003", "PLR0912", "PLR0915", "PLC0415"]
|
||||
# ReportState carries scan artifact/report fields and
|
||||
# a runtime ``Callable`` annotation on ``vulnerability_found_callback``.
|
||||
"strix/report/state.py" = ["TC003", "PLR0912", "PLR0915", "E501", "PERF401", "PLC0415"]
|
||||
"strix/report/state.py" = ["TC003", "PLR0912", "PLR0915", "E501", "PERF401"]
|
||||
"strix/report/usage.py" = ["PLC0415"]
|
||||
# Lazy import of strix.config.models avoids a circular dependency between the
|
||||
# report pipeline and the config layer.
|
||||
"strix/report/dedupe.py" = ["PLC0415"]
|
||||
"strix/telemetry/logging.py" = ["PLC0415"]
|
||||
"strix/config/models.py" = ["PLC0415"]
|
||||
# Heavy inference deps (httpx, openai) imported lazily so auth-status checks
|
||||
# don't pull them in.
|
||||
"strix/config/codex.py" = ["PLC0415"]
|
||||
# Interface utility branches per scope-mode / target-type combination;
|
||||
# splitting would obscure the decision tree without simplifying it.
|
||||
"strix/interface/utils.py" = ["PLR0912", "BLE001", "PLC0415"]
|
||||
|
||||
+2
-2
@@ -4,7 +4,7 @@ set -euo pipefail
|
||||
|
||||
APP=strix
|
||||
REPO="usestrix/strix"
|
||||
STRIX_IMAGE="ghcr.io/usestrix/strix-sandbox:1.2.0"
|
||||
STRIX_IMAGE="ghcr.io/usestrix/strix-sandbox:1.0.0"
|
||||
|
||||
MUTED='\033[0;2m'
|
||||
RED='\033[0;31m'
|
||||
@@ -41,7 +41,7 @@ fi
|
||||
|
||||
combo="$os-$arch"
|
||||
case "$combo" in
|
||||
linux-x86_64|linux-arm64|macos-x86_64|macos-arm64|windows-x86_64)
|
||||
linux-x86_64|macos-x86_64|macos-arm64|windows-x86_64)
|
||||
;;
|
||||
*)
|
||||
echo -e "${RED}Unsupported OS/Arch: $os/$arch${NC}"
|
||||
|
||||
+7
-7
@@ -26,7 +26,7 @@ for tcss_file in strix_root.rglob('*.tcss'):
|
||||
datas.append((str(tcss_file), str(rel_path.parent)))
|
||||
|
||||
# Prebuilt local-viewer SPA (served by `strix view`).
|
||||
viewer_static = strix_root / 'interface' / 'viewer' / 'static'
|
||||
viewer_static = strix_root / 'viewer' / 'static'
|
||||
for asset in viewer_static.rglob('*'):
|
||||
if asset.is_file():
|
||||
rel_path = asset.relative_to(project_root)
|
||||
@@ -158,12 +158,12 @@ hiddenimports = [
|
||||
'strix.report.dedupe',
|
||||
'strix.report.state',
|
||||
'strix.report.writer',
|
||||
'strix.interface.viewer',
|
||||
'strix.interface.viewer.auth',
|
||||
'strix.interface.viewer.cli',
|
||||
'strix.interface.viewer.report_pdf',
|
||||
'strix.interface.viewer.server',
|
||||
'strix.interface.viewer.transcript',
|
||||
'strix.viewer',
|
||||
'strix.viewer.auth',
|
||||
'strix.viewer.cli',
|
||||
'strix.viewer.report_pdf',
|
||||
'strix.viewer.server',
|
||||
'strix.viewer.transcript',
|
||||
|
||||
# PDF report generation + encryption
|
||||
'reportlab',
|
||||
|
||||
+18
-185
@@ -16,14 +16,13 @@ from agents.tool import CustomTool, FunctionTool, Tool
|
||||
from pydantic import ValidationError
|
||||
|
||||
from strix.agents.prompt import render_system_prompt
|
||||
from strix.config import load_settings
|
||||
from strix.tools.agents_graph.tools import (
|
||||
agent_finish,
|
||||
create_agent,
|
||||
send_message_to_agent,
|
||||
stop_agent,
|
||||
view_agent_graph,
|
||||
wait_for_agents,
|
||||
wait_for_message,
|
||||
)
|
||||
from strix.tools.finish.tool import finish_scan
|
||||
from strix.tools.load_skill.tool import load_skill
|
||||
@@ -34,7 +33,6 @@ from strix.tools.notes.tools import (
|
||||
list_notes,
|
||||
update_note,
|
||||
)
|
||||
from strix.tools.output_store import bound_and_store, bound_text
|
||||
from strix.tools.proxy.tools import (
|
||||
list_requests,
|
||||
list_sitemap,
|
||||
@@ -43,13 +41,7 @@ from strix.tools.proxy.tools import (
|
||||
view_request,
|
||||
view_sitemap_entry,
|
||||
)
|
||||
from strix.tools.reporting.tool import (
|
||||
create_dependency_report,
|
||||
create_vulnerability_report,
|
||||
get_report,
|
||||
list_reports,
|
||||
)
|
||||
from strix.tools.respond.tool import respond_to_user
|
||||
from strix.tools.reporting.tool import create_dependency_report, create_vulnerability_report
|
||||
from strix.tools.thinking.tool import think
|
||||
from strix.tools.todo.tools import (
|
||||
create_todo,
|
||||
@@ -111,113 +103,8 @@ def _extract_custom_input(tool: CustomTool, raw_input: str | dict[str, Any]) ->
|
||||
return value if isinstance(value, str) else ""
|
||||
|
||||
|
||||
def _tool_output_limits() -> tuple[int, int]:
|
||||
context = load_settings().context
|
||||
return context.tool_output_max_lines, context.tool_output_max_bytes
|
||||
|
||||
|
||||
async def _bound_result(result: Any) -> Any:
|
||||
if not isinstance(result, str):
|
||||
return result
|
||||
max_lines, max_bytes = _tool_output_limits()
|
||||
return await bound_and_store(result, max_lines=max_lines, max_bytes=max_bytes)
|
||||
|
||||
|
||||
def _format_tool_error(exc: Exception) -> str:
|
||||
message = str(exc) or exc.__class__.__name__
|
||||
max_lines, max_bytes = _tool_output_limits()
|
||||
return bound_text(message, max_lines=max_lines, max_bytes=max_bytes)
|
||||
|
||||
|
||||
def _with_bounded_result(tool: FunctionTool) -> FunctionTool:
|
||||
"""Cap a tool's result size before it enters history (idempotent)."""
|
||||
if getattr(tool, "_strix_bounded", False):
|
||||
return tool
|
||||
invoke_tool = tool.on_invoke_tool
|
||||
|
||||
async def invoke(ctx: Any, raw_input: str) -> Any:
|
||||
return await _bound_result(await invoke_tool(ctx, raw_input))
|
||||
|
||||
tool.on_invoke_tool = invoke
|
||||
tool._strix_bounded = True # type: ignore[attr-defined]
|
||||
return tool
|
||||
|
||||
|
||||
def _schema_types(spec: dict[str, Any]) -> set[str]:
|
||||
types: set[str] = set()
|
||||
raw = spec.get("type")
|
||||
if isinstance(raw, str):
|
||||
types.add(raw)
|
||||
elif isinstance(raw, list):
|
||||
types.update(t for t in raw if isinstance(t, str))
|
||||
for variant in spec.get("anyOf") or ():
|
||||
if isinstance(variant, dict):
|
||||
types |= _schema_types(variant)
|
||||
types.discard("null")
|
||||
return types
|
||||
|
||||
|
||||
def _decode_structured(value: str, types: set[str]) -> Any:
|
||||
stripped = value.strip()
|
||||
if not stripped:
|
||||
return value
|
||||
try:
|
||||
decoded = json.loads(stripped)
|
||||
except json.JSONDecodeError:
|
||||
return value
|
||||
wanted = list if "array" in types else dict
|
||||
return decoded if isinstance(decoded, wanted) else value
|
||||
|
||||
|
||||
def _coerce_argument(value: Any, spec: dict[str, Any]) -> Any:
|
||||
types = _schema_types(spec)
|
||||
if not types or value is None:
|
||||
return value
|
||||
if isinstance(value, list | dict) and "string" in types and not types & {"array", "object"}:
|
||||
return json.dumps(value, ensure_ascii=False)
|
||||
if isinstance(value, str) and types & {"array", "object"} and "string" not in types:
|
||||
return _decode_structured(value, types)
|
||||
return value
|
||||
|
||||
|
||||
def _coerce_arguments(raw_input: str, schema: dict[str, Any]) -> str:
|
||||
properties = schema.get("properties")
|
||||
if not isinstance(properties, dict) or not properties:
|
||||
return raw_input
|
||||
try:
|
||||
payload = json.loads(raw_input) if raw_input else None
|
||||
except json.JSONDecodeError:
|
||||
return raw_input
|
||||
if not isinstance(payload, dict):
|
||||
return raw_input
|
||||
|
||||
changed = False
|
||||
for key, value in payload.items():
|
||||
spec = properties.get(key)
|
||||
if not isinstance(spec, dict):
|
||||
continue
|
||||
coerced = _coerce_argument(value, spec)
|
||||
if coerced is not value:
|
||||
payload[key] = coerced
|
||||
changed = True
|
||||
|
||||
if not changed:
|
||||
return raw_input
|
||||
return json.dumps(payload, ensure_ascii=False)
|
||||
|
||||
|
||||
def _with_coerced_arguments(tool: FunctionTool) -> FunctionTool:
|
||||
if getattr(tool, "_strix_coerced", False):
|
||||
return tool
|
||||
invoke_tool = tool.on_invoke_tool
|
||||
schema = tool.params_json_schema
|
||||
|
||||
async def invoke(ctx: Any, raw_input: str) -> Any:
|
||||
return await invoke_tool(ctx, _coerce_arguments(raw_input, schema))
|
||||
|
||||
tool.on_invoke_tool = invoke
|
||||
tool._strix_coerced = True # type: ignore[attr-defined]
|
||||
return tool
|
||||
return str(exc) or exc.__class__.__name__
|
||||
|
||||
|
||||
def _function_tool_with_error_result(tool: FunctionTool) -> FunctionTool:
|
||||
@@ -225,7 +112,7 @@ def _function_tool_with_error_result(tool: FunctionTool) -> FunctionTool:
|
||||
|
||||
async def invoke(ctx: Any, raw_input: str) -> Any:
|
||||
try:
|
||||
return await _bound_result(await invoke_tool(ctx, raw_input))
|
||||
return await invoke_tool(ctx, raw_input)
|
||||
except Exception as exc: # noqa: BLE001 - tool errors should be model-visible results.
|
||||
logger.debug("Tool %s failed; returning error as result", tool.name, exc_info=True)
|
||||
return _format_tool_error(exc)
|
||||
@@ -240,7 +127,7 @@ def _custom_tool_as_function_tool(tool: CustomTool) -> FunctionTool:
|
||||
if not custom_input:
|
||||
return f"`{_custom_tool_input_field(tool)}` must be a non-empty string."
|
||||
try:
|
||||
return await _bound_result(await tool.on_invoke_tool(ctx, custom_input))
|
||||
return await tool.on_invoke_tool(ctx, custom_input)
|
||||
except Exception as exc: # noqa: BLE001 - matches SDK CustomTool error-as-result behavior.
|
||||
logger.debug("Tool %s failed; returning error as result", tool.name, exc_info=True)
|
||||
return _format_tool_error(exc)
|
||||
@@ -272,37 +159,12 @@ def _custom_tool_as_function_tool(tool: CustomTool) -> FunctionTool:
|
||||
)
|
||||
|
||||
|
||||
def _bound_custom_tool(tool: CustomTool) -> CustomTool:
|
||||
"""Bound a native ``CustomTool`` result in place (Responses path)."""
|
||||
invoke_tool = tool.on_invoke_tool
|
||||
|
||||
async def invoke(ctx: Any, raw_input: str) -> Any:
|
||||
return await _bound_result(await invoke_tool(ctx, raw_input))
|
||||
|
||||
tool.on_invoke_tool = invoke
|
||||
return tool
|
||||
|
||||
|
||||
def _configure_filesystem_tools(toolset: Any, *, chat_completions: bool) -> None:
|
||||
def _configure_chat_completions_filesystem_tools(toolset: Any) -> None:
|
||||
for name, tool in vars(toolset).items():
|
||||
if chat_completions:
|
||||
if isinstance(tool, CustomTool):
|
||||
setattr(toolset, name, _custom_tool_as_function_tool(tool))
|
||||
elif isinstance(tool, FunctionTool):
|
||||
setattr(
|
||||
toolset, name, _function_tool_with_error_result(_with_coerced_arguments(tool))
|
||||
)
|
||||
elif isinstance(tool, CustomTool):
|
||||
setattr(toolset, name, _bound_custom_tool(tool))
|
||||
if isinstance(tool, CustomTool):
|
||||
setattr(toolset, name, _custom_tool_as_function_tool(tool))
|
||||
elif isinstance(tool, FunctionTool):
|
||||
setattr(toolset, name, _with_bounded_result(_with_coerced_arguments(tool)))
|
||||
|
||||
|
||||
def _make_filesystem_configurator(*, chat_completions: bool) -> Any:
|
||||
def configure(toolset: Any) -> None:
|
||||
_configure_filesystem_tools(toolset, chat_completions=chat_completions)
|
||||
|
||||
return configure
|
||||
setattr(toolset, name, _function_tool_with_error_result(tool))
|
||||
|
||||
|
||||
_CHARS_ESCAPE_RE = re.compile(r"\\(?:u[0-9a-fA-F]{4}|x[0-9a-fA-F]{2}|[0abtnvfr\\])")
|
||||
@@ -343,16 +205,6 @@ def _format_validation_error(tool_name: str, exc: ValidationError) -> str:
|
||||
return f"{tool_name}: invalid arguments — " + "; ".join(parts)
|
||||
|
||||
|
||||
def _apply_shell_output_cap(parsed: dict[str, Any]) -> None:
|
||||
"""Clamp the SDK shell tools' ``max_output_tokens`` to the configured
|
||||
ceiling; a smaller explicit value is respected."""
|
||||
ceiling = load_settings().context.tool_output_max_tokens
|
||||
requested = parsed.get("max_output_tokens")
|
||||
parsed["max_output_tokens"] = (
|
||||
ceiling if not isinstance(requested, int) or requested > ceiling else requested
|
||||
)
|
||||
|
||||
|
||||
def _wrap_exec_command(tool: FunctionTool) -> FunctionTool:
|
||||
invoke_tool = tool.on_invoke_tool
|
||||
|
||||
@@ -361,10 +213,8 @@ def _wrap_exec_command(tool: FunctionTool) -> FunctionTool:
|
||||
parsed = json.loads(raw_input)
|
||||
except (json.JSONDecodeError, TypeError):
|
||||
parsed = None
|
||||
if isinstance(parsed, dict):
|
||||
if "shell" not in parsed:
|
||||
parsed["shell"] = "bash"
|
||||
_apply_shell_output_cap(parsed)
|
||||
if isinstance(parsed, dict) and "shell" not in parsed:
|
||||
parsed["shell"] = "bash"
|
||||
raw_input = json.dumps(parsed)
|
||||
try:
|
||||
return await invoke_tool(ctx, raw_input)
|
||||
@@ -390,10 +240,8 @@ def _wrap_write_stdin(tool: FunctionTool) -> FunctionTool:
|
||||
parsed = json.loads(raw_input)
|
||||
except json.JSONDecodeError:
|
||||
parsed = None
|
||||
if isinstance(parsed, dict):
|
||||
if isinstance(parsed.get("chars"), str):
|
||||
parsed["chars"] = _decode_chars_escape(parsed["chars"])
|
||||
_apply_shell_output_cap(parsed)
|
||||
if isinstance(parsed, dict) and isinstance(parsed.get("chars"), str):
|
||||
parsed["chars"] = _decode_chars_escape(parsed["chars"])
|
||||
raw_input = json.dumps(parsed)
|
||||
try:
|
||||
return await invoke_tool(ctx, raw_input)
|
||||
@@ -408,7 +256,7 @@ def _configure_shell_tools(toolset: Any, *, chat_completions: bool) -> None:
|
||||
for name, tool in vars(toolset).items():
|
||||
if not isinstance(tool, FunctionTool):
|
||||
continue
|
||||
wrapped = _with_coerced_arguments(tool)
|
||||
wrapped = tool
|
||||
if tool.name == "exec_command":
|
||||
wrapped = _wrap_exec_command(wrapped)
|
||||
elif tool.name == "write_stdin":
|
||||
@@ -425,10 +273,6 @@ def _make_shell_configurator(*, chat_completions: bool) -> Any:
|
||||
return configure
|
||||
|
||||
|
||||
# Tools that hand control away by parking the agent rather than ending the scan.
|
||||
_PARKING_TOOLS: frozenset[str] = frozenset({"respond_to_user", "wait_for_agents"})
|
||||
|
||||
|
||||
def _lifecycle_tool_completed(tool_name: str, output: Any) -> bool:
|
||||
if tool_name == "agent_finish":
|
||||
completion_key = "agent_completed"
|
||||
@@ -447,7 +291,7 @@ def _lifecycle_tool_completed(tool_name: str, output: Any) -> bool:
|
||||
|
||||
|
||||
def _wait_tool_parked(tool_name: str, output: Any) -> bool:
|
||||
if tool_name not in _PARKING_TOOLS or not isinstance(output, str):
|
||||
if tool_name != "wait_for_message" or not isinstance(output, str):
|
||||
return False
|
||||
try:
|
||||
parsed = json.loads(output)
|
||||
@@ -499,8 +343,6 @@ _BASE_TOOLS: tuple[Tool, ...] = (
|
||||
web_search,
|
||||
create_vulnerability_report,
|
||||
create_dependency_report,
|
||||
list_reports,
|
||||
get_report,
|
||||
list_requests,
|
||||
view_request,
|
||||
repeat_request,
|
||||
@@ -509,7 +351,7 @@ _BASE_TOOLS: tuple[Tool, ...] = (
|
||||
scope_rules,
|
||||
view_agent_graph,
|
||||
send_message_to_agent,
|
||||
wait_for_agents,
|
||||
wait_for_message,
|
||||
create_agent,
|
||||
stop_agent,
|
||||
)
|
||||
@@ -593,20 +435,11 @@ def build_strix_agent(
|
||||
)
|
||||
|
||||
agent_tools = [*_EXTRA_TOOLS, *(extra_tools or [])]
|
||||
if interactive:
|
||||
# Yielding to the user is only meaningful when one is attached.
|
||||
agent_tools.append(respond_to_user)
|
||||
if is_root:
|
||||
tools: list[Tool] = [*_BASE_TOOLS, *agent_tools, finish_scan]
|
||||
else:
|
||||
tools = [*_BASE_TOOLS, *agent_tools, agent_finish]
|
||||
_ensure_unique_tool_names(tools)
|
||||
tools = [
|
||||
_with_bounded_result(_with_coerced_arguments(tool))
|
||||
if isinstance(tool, FunctionTool)
|
||||
else tool
|
||||
for tool in tools
|
||||
]
|
||||
|
||||
logger.info(
|
||||
"Built %s agent '%s' (skills=%d, tools=%d, scan_mode=%s, whitebox=%s)",
|
||||
@@ -626,8 +459,8 @@ def build_strix_agent(
|
||||
model=None,
|
||||
capabilities=[
|
||||
Filesystem(
|
||||
configure_tools=_make_filesystem_configurator(
|
||||
chat_completions=chat_completions_tools,
|
||||
configure_tools=(
|
||||
_configure_chat_completions_filesystem_tools if chat_completions_tools else None
|
||||
),
|
||||
),
|
||||
Shell(
|
||||
|
||||
@@ -31,26 +31,28 @@ INTER-AGENT MESSAGES:
|
||||
|
||||
{% if interactive %}
|
||||
INTERACTIVE BEHAVIOR:
|
||||
- You are in an interactive conversation with a user.
|
||||
- HOW EXECUTION ENDS: your turn ends ONLY when you make an explicit lifecycle tool call. Plain text NEVER ends your turn and NEVER hands control to the user — text is shown to the user, and then execution continues.
|
||||
- To answer the user and hand control back, call respond_to_user. It delivers your message AND parks you for their reply in one call, so there is no way to answer and then forget to stop. This is the ONLY way to yield to the user.
|
||||
- To wait on another AGENT (a child's report, a peer's reply), call wait_for_agents. That is not a way to reach the user.
|
||||
- To end the whole engagement, call the lifecycle tool: finish_scan (root) or agent_finish (subagent).
|
||||
- A turn that ends with plain text and no tool call does NOT stop you: the system nudges you to continue and will re-run you. Do not rely on going silent to pause — it will not pause you.
|
||||
- Answering a user question: put the answer in respond_to_user's message. Do not write the answer as plain text and then fall silent — that does not reach a stopping point, it just triggers a continuation nudge.
|
||||
- You may include brief explanatory text before a tool call, and you can narrate while you work — plain text is shown to the user as you go. Narrating is free; respond_to_user is specifically the act of WAITING for the user, so do not call it just to give a status update.
|
||||
- Respond naturally when the user asks questions or gives instructions.
|
||||
- While actively working on a task, every turn should carry exactly one tool call — use think to plan, the appropriate tool to act, and respond_to_user only when you genuinely need the user.
|
||||
- Never loop through think or other tools just to prepare, polish, confirm, or announce an answer. Once you know the answer, send it with respond_to_user.
|
||||
- You are in an interactive conversation with a user
|
||||
- CRITICAL: A message WITHOUT a tool call IMMEDIATELY STOPS your entire execution and waits for user input. This is a HARD SYSTEM CONSTRAINT, not a suggestion.
|
||||
- Statements like "Planning the assessment..." or "I'll now scan..." or "Starting with..." WITHOUT a tool call will HALT YOUR WORK COMPLETELY. The system interprets no-tool-call as "I'm done, waiting for the user."
|
||||
- If you want to plan, call the think tool. If you want to act, call the appropriate tool. There is NO valid reason to output text without a tool call while working on a task.
|
||||
- The ONLY time you may send a message without a tool call is when you are genuinely DONE and presenting final results, or when you NEED the user to answer a question before continuing.
|
||||
- EVERY message while working MUST contain exactly one tool call — this is what keeps execution moving. No tool call = execution stops.
|
||||
- You may include brief explanatory text BEFORE the tool call
|
||||
- Respond naturally when the user asks questions or gives instructions
|
||||
- For simple conversation, acknowledgements, or direct questions that you can answer from current context, reply in plain text and stop. Do NOT call think just to prepare wording.
|
||||
- If you use a tool to answer a user question (for example list_todos, view_agent_graph, or a file read), then after the tool result arrives, provide the answer in plain text and stop unless the user explicitly asked you to continue working.
|
||||
- Never loop through think or other tools just to prepare, polish, confirm, or announce a final answer. Once you know the answer, say it.
|
||||
- NEVER send empty messages — if you have nothing to do or say, call the wait_for_message tool
|
||||
- If you catch yourself about to describe multiple steps without a tool call, STOP and call the think tool instead
|
||||
{% else %}
|
||||
AUTONOMOUS BEHAVIOR:
|
||||
- Work autonomously by default
|
||||
- You should NOT ask for user input or confirmation - you should always proceed with your task autonomously.
|
||||
- Minimize user messaging: avoid redundancy and repetition; consolidate updates into a single concise message
|
||||
- NEVER send an empty or blank message. If you have no content to output or need to wait for subagent results, you MUST call the wait_for_agents tool (or another appropriate tool) instead of emitting an empty response.
|
||||
- There is no user attached to this run, so there is nobody to ask and nothing to yield to. If there is nothing left to execute: do NOT send filler/repetitive text — either call wait_for_agents (only if you are genuinely expecting another agent to message you) or finish your work (subagents: agent_finish; root: finish_scan)
|
||||
- While the agent loop is running, almost every output MUST be a tool call. Do NOT send plain text messages; act via tools. If waiting on another agent, use wait_for_agents; when done, use agent_finish (subagents) or finish_scan (root)
|
||||
- A text-only turn does nothing: it neither ends the run nor yields — it just wastes a turn and forces a retry. The lifecycle tools (``finish_scan`` for root, ``agent_finish`` for subagents) are the ONLY way to terminate, and the report flows through them. If you find yourself wanting to say "Done!" or "Scan complete" without a tool call, call the lifecycle tool instead.
|
||||
- NEVER send an empty or blank message. If you have no content to output or need to wait (for user input, subagent results, or any other reason), you MUST call the wait_for_message tool (or another appropriate tool) instead of emitting an empty response.
|
||||
- If there is nothing to execute and no user query to answer any more: do NOT send filler/repetitive text — either call wait_for_message or finish your work (subagents: agent_finish; root: finish_scan)
|
||||
- While the agent loop is running, almost every output MUST be a tool call. Do NOT send plain text messages; act via tools. If idle, use wait_for_message; when done, use agent_finish (subagents) or finish_scan (root)
|
||||
- A text-only turn — even one — IMMEDIATELY ends the scan/run with no report written. The lifecycle tools (``finish_scan`` for root, ``agent_finish`` for subagents) are the ONLY valid way to terminate. If you find yourself wanting to say "Done!" or "Scan complete" without a tool call, call the lifecycle tool instead — the report and termination signal both flow through it.
|
||||
{% endif %}
|
||||
</communication_rules>
|
||||
|
||||
@@ -186,7 +188,7 @@ EFFICIENCY TACTICS:
|
||||
script fail with `ModuleNotFoundError`.
|
||||
- `exec_command` runs each command in a fresh non-interactive shell (plain
|
||||
pipes, no TTY). To drive an interactive or long-running process with
|
||||
`write_stdin` — REPLs, `ssh`/`nc`/`ftp`, `sqlmap`, or to send Ctrl-C —
|
||||
`write_stdin` — REPLs, `ssh`/`nc`/`ftp`, `msfconsole`, or to send Ctrl-C —
|
||||
you MUST start it with `exec_command(cmd="...", tty=true)` and then
|
||||
`write_stdin(session_id=<id>, chars="...")`. Calling `write_stdin` on a
|
||||
default (non-TTY) command or on a process that has already exited fails with
|
||||
@@ -213,7 +215,6 @@ VALIDATION REQUIREMENTS:
|
||||
- A vulnerability is ONLY considered reported when a reporting agent uses create_vulnerability_report (or create_dependency_report for known-CVE dependency/supply-chain findings) with full details. Mentions in agent_finish, finish_scan, or generic messages are NOT sufficient
|
||||
- Reporting and fixing are ONE step, not two: when source is available, the reporting agent derives the concrete fix and files it INLINE via create_vulnerability_report (`code_locations` with `fix_before`/`fix_after` + `fix_pr_body`) — the report is not complete without it. Do NOT report first and then spawn a separate downstream agent to re-derive and re-apply the same patch; that just re-does the analysis and wastes tokens. (Do not silently patch a finding WITHOUT filing a report — the report, with its embedded fix, is the deliverable.)
|
||||
- DEDUPLICATION: The create_vulnerability_report tool uses LLM-based deduplication. If it rejects your report as a duplicate, DO NOT attempt to re-submit the same vulnerability. Accept the rejection and move on to testing other areas. The vulnerability has already been reported by another agent
|
||||
- REVIEWING FILED FINDINGS (orchestrator/root agent): use list_reports to see every vulnerability filed so far in this scan (by any agent, root or child) — metadata-first with per-severity counts — and get_report to read one finding in full by its id. These are read-only orchestration tools: the root agent uses them to track coverage, avoid dispatching work on already-covered ground, assemble the finish_scan executive summary, and reason about attack-chaining across confirmed findings. Leaf/specialist agents should NOT call them — just do your assigned testing and file findings. Each entry shows which agent filed it (agent_name), and your own entries are flagged by_you. list_notes/get_note do the same for notes.
|
||||
</execution_guidelines>
|
||||
|
||||
<vulnerability_focus>
|
||||
@@ -444,19 +445,8 @@ PROXY & INTERCEPTION:
|
||||
- Caido CLI - Modern web proxy (already running). Use the proxy tools
|
||||
directly, or import `caido_api` from sandbox Python scripts.
|
||||
- HTTPQL filters (for `list_requests`): quote string values, leave integers unquoted (`resp.code.eq:200`, not `"200"`); combine terms with `AND`/`OR` (there is no `NOT` — use the negated operator `ne`/`ncont`/`nregex`). Numeric fields (`resp.code`, `req.port`) use `eq`/`ne`/`gt`/`gte`/`lt`/`lte`; text fields (`req.host`, `req.path`, `req.method`, `req.raw`) use `cont`/`ncont`/`eq`/`regex`. Example: `resp.code.gte:200 AND resp.code.lt:300 AND req.host.cont:"api"`.
|
||||
|
||||
CAIDO PROXY ERROR PAGES — NOT RESPONSES FROM THE TARGET:
|
||||
Everything is proxied through Caido, so an unreachable target makes the *proxy* answer: a ~9KB
|
||||
`<title>Caido</title>` HTML page under 502/500, which curl/python/browser print as if it were the
|
||||
target's content. The request never reached a server. It also appears in `list_requests` with no
|
||||
response at all (`resp` null), unlike a real 502.
|
||||
- Don't dump it; extract the cause with `curl -s ... | grep -A8 'c-title"'`.
|
||||
- The `c-details` cause says what to fix: "Failed to query DNS" — host doesn't resolve, check
|
||||
`dig +short <host>`, then correct or drop it; "Connection refused" — nothing on that port, check
|
||||
`nc -z -v <host> <port>`; "TLS handshake"/"wrong version number" — scheme/port mismatch, flip
|
||||
http/https; timeout — filtered or unreachable from the sandbox.
|
||||
- NEVER treat these as target behavior: not a finding, not evidence, not a WAF, not a server
|
||||
error. Fix the url/host/port/scheme and retry, or move on — do not keep re-requesting a dead host.
|
||||
- NOTE: If you are seeing proxy errors when sending requests, it usually means you are not sending requests to a correct url/host/port.
|
||||
- Ignore Caido proxy-generated 50x HTML error pages; these are proxy issues (might happen when requesting a wrong host or SSL/TLS issues, etc).
|
||||
|
||||
PROGRAMMING:
|
||||
- Python 3, uv, Node.js/npm
|
||||
|
||||
@@ -17,8 +17,6 @@ from strix.config.loader import (
|
||||
persist_current,
|
||||
)
|
||||
from strix.config.settings import (
|
||||
ContextSettings,
|
||||
DedupeSettings,
|
||||
IntegrationSettings,
|
||||
LlmSettings,
|
||||
RuntimeSettings,
|
||||
@@ -28,8 +26,6 @@ from strix.config.settings import (
|
||||
|
||||
|
||||
__all__ = [
|
||||
"ContextSettings",
|
||||
"DedupeSettings",
|
||||
"IntegrationSettings",
|
||||
"LlmSettings",
|
||||
"RuntimeSettings",
|
||||
|
||||
@@ -1,404 +0,0 @@
|
||||
"""ChatGPT (Codex) subscription auth: OAuth login, token refresh, and the OpenAI
|
||||
client that routes inference through the ChatGPT backend.
|
||||
|
||||
Mirrors OpenAI's Codex CLI: OAuth 2.0 + PKCE against ``auth.openai.com``, with the
|
||||
access token sent as a ``Bearer`` token to ``chatgpt.com/backend-api/codex``. Using
|
||||
a ChatGPT subscription outside OpenAI's own products is not officially supported by
|
||||
OpenAI; the user chooses this path knowingly. The OAuth constants are OpenAI's own
|
||||
Codex CLI values (the backend only accepts that client).
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import base64
|
||||
import contextlib
|
||||
import hashlib
|
||||
import json
|
||||
import logging
|
||||
import secrets
|
||||
import threading
|
||||
import time
|
||||
import urllib.parse
|
||||
from pathlib import Path
|
||||
from typing import TYPE_CHECKING, Any
|
||||
|
||||
import requests
|
||||
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from collections.abc import Iterator
|
||||
|
||||
from openai import AsyncOpenAI
|
||||
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
PROVIDER = "codex"
|
||||
|
||||
CLIENT_ID = "app_EMoamEEZ73f0CkXaXp7hrann"
|
||||
AUTHORIZE_URL = "https://auth.openai.com/oauth/authorize"
|
||||
TOKEN_URL = "https://auth.openai.com/oauth/token" # noqa: S105 # nosec B105 - URL, not a secret
|
||||
CALLBACK_HOST = "localhost"
|
||||
CALLBACK_PORT = 1455
|
||||
CALLBACK_PATH = "/auth/callback"
|
||||
REDIRECT_URI = f"http://{CALLBACK_HOST}:{CALLBACK_PORT}{CALLBACK_PATH}"
|
||||
SCOPE = "openid profile email offline_access"
|
||||
|
||||
CODEX_BASE_URL = "https://chatgpt.com/backend-api/codex"
|
||||
ORIGINATOR = "codex_cli_rs"
|
||||
_ACCOUNT_CLAIM = "https://api.openai.com/auth"
|
||||
|
||||
_TOKEN_TIMEOUT = 30
|
||||
_EXPIRY_SKEW_S = 300
|
||||
|
||||
_refresh_lock = threading.Lock()
|
||||
|
||||
# Kept separate from cli-config.json so OAuth tokens never land in the env-var config.
|
||||
AUTH_PATH = Path.home() / ".strix" / "subscription-auth.json"
|
||||
|
||||
|
||||
def _read_store() -> dict[str, Any]:
|
||||
try:
|
||||
data = json.loads(AUTH_PATH.read_text(encoding="utf-8"))
|
||||
except (OSError, json.JSONDecodeError):
|
||||
return {}
|
||||
return data if isinstance(data, dict) else {}
|
||||
|
||||
|
||||
def _write_store(data: dict[str, Any]) -> None:
|
||||
AUTH_PATH.parent.mkdir(parents=True, exist_ok=True)
|
||||
tmp = AUTH_PATH.with_suffix(".json.tmp")
|
||||
tmp.write_text(json.dumps(data, indent=2), encoding="utf-8")
|
||||
with contextlib.suppress(OSError):
|
||||
tmp.chmod(0o600)
|
||||
tmp.replace(AUTH_PATH)
|
||||
with contextlib.suppress(OSError):
|
||||
AUTH_PATH.chmod(0o600)
|
||||
|
||||
|
||||
def read_record() -> dict[str, Any] | None:
|
||||
record = _read_store().get(PROVIDER)
|
||||
if not isinstance(record, dict) or record.get("type") != "oauth":
|
||||
return None
|
||||
if not (record.get("access") and record.get("refresh") and record.get("account_id")):
|
||||
return None
|
||||
return record
|
||||
|
||||
|
||||
def is_authenticated() -> bool:
|
||||
return read_record() is not None
|
||||
|
||||
|
||||
def save_record(record: dict[str, Any]) -> None:
|
||||
data = _read_store()
|
||||
data[PROVIDER] = record
|
||||
_write_store(data)
|
||||
|
||||
|
||||
def logout() -> None:
|
||||
data = _read_store()
|
||||
if PROVIDER not in data:
|
||||
return
|
||||
del data[PROVIDER]
|
||||
if data:
|
||||
_write_store(data)
|
||||
return
|
||||
with contextlib.suppress(OSError):
|
||||
AUTH_PATH.unlink()
|
||||
|
||||
|
||||
@contextlib.contextmanager
|
||||
def _refresh_guard() -> Iterator[None]:
|
||||
"""Serialize token refresh within (lock) and across (flock) Strix processes,
|
||||
so concurrent runs can't both spend the single-use refresh token."""
|
||||
with _refresh_lock:
|
||||
try:
|
||||
import fcntl
|
||||
|
||||
lock_path = AUTH_PATH.with_suffix(".lock")
|
||||
lock_path.parent.mkdir(parents=True, exist_ok=True)
|
||||
handle = lock_path.open("w")
|
||||
except (ImportError, OSError):
|
||||
yield
|
||||
return
|
||||
try:
|
||||
with contextlib.suppress(OSError):
|
||||
fcntl.flock(handle.fileno(), fcntl.LOCK_EX)
|
||||
yield
|
||||
finally:
|
||||
with contextlib.suppress(OSError):
|
||||
fcntl.flock(handle.fileno(), fcntl.LOCK_UN)
|
||||
handle.close()
|
||||
|
||||
|
||||
class CodexAuthError(Exception):
|
||||
def __init__(self, code: str, message: str | None = None) -> None:
|
||||
self.code = code
|
||||
super().__init__(message or code)
|
||||
|
||||
|
||||
class CodexContentGuardrailError(Exception):
|
||||
"""The ChatGPT backend refused a request via its content guardrail.
|
||||
Terminal — retrying identical content never clears the block."""
|
||||
|
||||
def __init__(self, model: str, original: BaseException | None = None) -> None:
|
||||
self.model = model
|
||||
self.original = original
|
||||
super().__init__(
|
||||
f"'{model}' was blocked by ChatGPT's content guardrails "
|
||||
f"(flagged as a possible cybersecurity risk). "
|
||||
f"Set STRIX_LLM to a model that isn't blocked and re-run."
|
||||
)
|
||||
|
||||
|
||||
_GUARDRAIL_MARKERS = (
|
||||
"flagged for possible cybersecurity risk",
|
||||
"trusted access for cyber",
|
||||
)
|
||||
|
||||
|
||||
def is_content_guardrail_error(exc: BaseException) -> bool:
|
||||
if isinstance(exc, CodexContentGuardrailError):
|
||||
return True
|
||||
text = str(exc).lower()
|
||||
return any(marker in text for marker in _GUARDRAIL_MARKERS)
|
||||
|
||||
|
||||
def _b64url(raw: bytes) -> str:
|
||||
return base64.urlsafe_b64encode(raw).rstrip(b"=").decode("ascii")
|
||||
|
||||
|
||||
def generate_pkce() -> tuple[str, str]:
|
||||
verifier = _b64url(secrets.token_bytes(64))
|
||||
challenge = _b64url(hashlib.sha256(verifier.encode("ascii")).digest())
|
||||
return verifier, challenge
|
||||
|
||||
|
||||
def create_state() -> str:
|
||||
return secrets.token_hex(16)
|
||||
|
||||
|
||||
def build_authorize_url(challenge: str, state: str) -> str:
|
||||
params = {
|
||||
"response_type": "code",
|
||||
"client_id": CLIENT_ID,
|
||||
"redirect_uri": REDIRECT_URI,
|
||||
"scope": SCOPE,
|
||||
"code_challenge": challenge,
|
||||
"code_challenge_method": "S256",
|
||||
"state": state,
|
||||
"id_token_add_organizations": "true",
|
||||
"codex_cli_simplified_flow": "true",
|
||||
"originator": ORIGINATOR,
|
||||
}
|
||||
return f"{AUTHORIZE_URL}?{urllib.parse.urlencode(params)}"
|
||||
|
||||
|
||||
def parse_redirect_input(value: str) -> tuple[str | None, str | None]:
|
||||
"""Extract ``(code, state)`` from a pasted redirect URL, ``code#state``,
|
||||
query string, or bare code."""
|
||||
value = (value or "").strip()
|
||||
if not value:
|
||||
return None, None
|
||||
with contextlib.suppress(ValueError):
|
||||
parsed = urllib.parse.urlparse(value)
|
||||
if parsed.scheme and parsed.query:
|
||||
query = urllib.parse.parse_qs(parsed.query)
|
||||
return _first(query, "code"), _first(query, "state")
|
||||
if "#" in value:
|
||||
code, _, state = value.partition("#")
|
||||
return code or None, state or None
|
||||
if "code=" in value:
|
||||
query = urllib.parse.parse_qs(value)
|
||||
return _first(query, "code"), _first(query, "state")
|
||||
return value, None
|
||||
|
||||
|
||||
def _first(query: dict[str, list[str]], key: str) -> str | None:
|
||||
values = query.get(key)
|
||||
return values[0] if values else None
|
||||
|
||||
|
||||
def _post_form(payload: dict[str, str]) -> dict[str, Any]:
|
||||
try:
|
||||
response = requests.post(
|
||||
TOKEN_URL,
|
||||
data=payload,
|
||||
headers={"Accept": "application/json"},
|
||||
timeout=_TOKEN_TIMEOUT,
|
||||
)
|
||||
except requests.RequestException as exc:
|
||||
raise CodexAuthError("unavailable", str(exc)) from exc
|
||||
if response.status_code >= 400:
|
||||
detail = response.text[:300]
|
||||
raise CodexAuthError("token_http_error", f"HTTP {response.status_code}: {detail}")
|
||||
data = json.loads(response.content or b"{}")
|
||||
if not isinstance(data, dict):
|
||||
raise CodexAuthError("bad_response", "token endpoint returned non-object")
|
||||
return data
|
||||
|
||||
|
||||
def _record_from_token_response(
|
||||
data: dict[str, Any], refresh_fallback: str | None = None
|
||||
) -> dict[str, Any]:
|
||||
access = data.get("access_token")
|
||||
# A refresh response may omit refresh_token when it isn't rotated; keep the old one.
|
||||
refresh = data.get("refresh_token") or refresh_fallback
|
||||
expires_in = data.get("expires_in")
|
||||
if not isinstance(access, str) or not access:
|
||||
raise CodexAuthError("bad_response", "token response missing access_token")
|
||||
if not isinstance(refresh, str) or not refresh:
|
||||
raise CodexAuthError("bad_response", "token response missing refresh_token")
|
||||
account_id = _account_id_from_jwt(access) or _account_id_from_jwt(
|
||||
data.get("id_token") if isinstance(data.get("id_token"), str) else ""
|
||||
)
|
||||
if not account_id:
|
||||
raise CodexAuthError("no_account_id", "could not read chatgpt_account_id from token")
|
||||
ttl = expires_in if isinstance(expires_in, int | float) else 3600
|
||||
return {
|
||||
"type": "oauth",
|
||||
"provider": PROVIDER,
|
||||
"access": access,
|
||||
"refresh": refresh,
|
||||
"account_id": account_id,
|
||||
"expires_at": time.time() + ttl,
|
||||
}
|
||||
|
||||
|
||||
def exchange_code(code: str, verifier: str) -> dict[str, Any]:
|
||||
data = _post_form(
|
||||
{
|
||||
"grant_type": "authorization_code",
|
||||
"client_id": CLIENT_ID,
|
||||
"code": code,
|
||||
"code_verifier": verifier,
|
||||
"redirect_uri": REDIRECT_URI,
|
||||
}
|
||||
)
|
||||
return _record_from_token_response(data)
|
||||
|
||||
|
||||
def refresh_tokens(refresh_token: str) -> dict[str, Any]:
|
||||
data = _post_form(
|
||||
{
|
||||
"grant_type": "refresh_token",
|
||||
"client_id": CLIENT_ID,
|
||||
"refresh_token": refresh_token,
|
||||
}
|
||||
)
|
||||
return _record_from_token_response(data, refresh_fallback=refresh_token)
|
||||
|
||||
|
||||
def _account_id_from_jwt(token: str | None) -> str | None:
|
||||
"""Read the account id claim without verifying the JWT (the server enforces
|
||||
authenticity on use); it feeds the ``chatgpt-account-id`` header."""
|
||||
if not token or token.count(".") != 2:
|
||||
return None
|
||||
payload_b64 = token.split(".")[1]
|
||||
padding = "=" * (-len(payload_b64) % 4)
|
||||
try:
|
||||
payload = json.loads(base64.urlsafe_b64decode(payload_b64 + padding))
|
||||
except (ValueError, json.JSONDecodeError):
|
||||
return None
|
||||
if not isinstance(payload, dict):
|
||||
return None
|
||||
auth = payload.get(_ACCOUNT_CLAIM)
|
||||
if isinstance(auth, dict):
|
||||
account_id = auth.get("chatgpt_account_id")
|
||||
if isinstance(account_id, str) and account_id:
|
||||
return account_id
|
||||
organizations = payload.get("organizations")
|
||||
if isinstance(organizations, list) and organizations and isinstance(organizations[0], dict):
|
||||
org_id = organizations[0].get("id")
|
||||
if isinstance(org_id, str) and org_id:
|
||||
return org_id
|
||||
return None
|
||||
|
||||
|
||||
def _near_expiry(record: dict[str, Any]) -> bool:
|
||||
expires_at = record.get("expires_at")
|
||||
if not isinstance(expires_at, int | float):
|
||||
return True
|
||||
return expires_at - _EXPIRY_SKEW_S <= time.time()
|
||||
|
||||
|
||||
def get_valid_token() -> tuple[str, str]:
|
||||
"""Return ``(access_token, account_id)``, refreshing under the cross-process
|
||||
guard if near expiry."""
|
||||
record = read_record()
|
||||
if record is None:
|
||||
raise CodexAuthError("not_authenticated", "not signed in; run: strix auth login")
|
||||
if not _near_expiry(record):
|
||||
return record["access"], record["account_id"]
|
||||
with _refresh_guard():
|
||||
record = read_record()
|
||||
if record is None:
|
||||
raise CodexAuthError("not_authenticated", "not signed in; run: strix auth login")
|
||||
if not _near_expiry(record):
|
||||
return record["access"], record["account_id"]
|
||||
try:
|
||||
refreshed = refresh_tokens(record["refresh"])
|
||||
except CodexAuthError:
|
||||
# A peer process may have already spent this single-use refresh token.
|
||||
latest = read_record()
|
||||
if latest and latest["refresh"] != record["refresh"] and not _near_expiry(latest):
|
||||
return latest["access"], latest["account_id"]
|
||||
raise
|
||||
save_record(refreshed)
|
||||
return refreshed["access"], refreshed["account_id"]
|
||||
|
||||
|
||||
def build_openai_client() -> AsyncOpenAI:
|
||||
"""An ``AsyncOpenAI`` for the ChatGPT backend. A per-request hook re-stamps a
|
||||
fresh bearer token so long scans survive token expiry."""
|
||||
import asyncio
|
||||
|
||||
import httpx
|
||||
from openai import AsyncOpenAI
|
||||
|
||||
get_valid_token() # fail fast at configure time if the sign-in is dead
|
||||
|
||||
async def _auth_hook(request: httpx.Request) -> None:
|
||||
access, account_id = await asyncio.to_thread(get_valid_token)
|
||||
request.headers["Authorization"] = f"Bearer {access}"
|
||||
request.headers["chatgpt-account-id"] = account_id
|
||||
|
||||
http_client = httpx.AsyncClient(
|
||||
timeout=httpx.Timeout(600.0, connect=30.0),
|
||||
event_hooks={"request": [_auth_hook]},
|
||||
)
|
||||
return AsyncOpenAI(
|
||||
api_key="strix-codex-oauth", # placeholder; the hook overwrites Authorization
|
||||
base_url=CODEX_BASE_URL,
|
||||
http_client=http_client,
|
||||
default_headers={
|
||||
"OpenAI-Beta": "responses=experimental",
|
||||
"originator": ORIGINATOR,
|
||||
},
|
||||
)
|
||||
|
||||
|
||||
_subscription_client: AsyncOpenAI | None = None
|
||||
|
||||
|
||||
def get_subscription_client() -> AsyncOpenAI:
|
||||
global _subscription_client # noqa: PLW0603
|
||||
if _subscription_client is None:
|
||||
_subscription_client = build_openai_client()
|
||||
return _subscription_client
|
||||
|
||||
|
||||
SUBSCRIPTION_PREFIX = "chatgpt/"
|
||||
|
||||
|
||||
def subscription_model(model_name: str | None) -> str | None:
|
||||
"""The model slug behind a ``chatgpt/<model>`` STRIX_LLM, or None."""
|
||||
name = (model_name or "").strip()
|
||||
if not name.lower().startswith(SUBSCRIPTION_PREFIX):
|
||||
return None
|
||||
return name[len(SUBSCRIPTION_PREFIX) :] or None
|
||||
|
||||
|
||||
def auth_mode(model_name: str | None) -> str:
|
||||
return "subscription" if subscription_model(model_name) else "api_key"
|
||||
+12
-393
@@ -2,50 +2,23 @@
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import contextlib
|
||||
import inspect
|
||||
import os
|
||||
import time
|
||||
from typing import TYPE_CHECKING, Any
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
from agents import (
|
||||
set_default_openai_api,
|
||||
set_default_openai_key,
|
||||
set_tracing_disabled,
|
||||
)
|
||||
from agents.model_settings import ModelSettings
|
||||
from agents.models.fake_id import FAKE_RESPONSES_ID
|
||||
from agents.models.interface import Model
|
||||
from agents import set_default_openai_api, set_default_openai_key, set_tracing_disabled
|
||||
from agents.models.multi_provider import MultiProvider
|
||||
from agents.models.openai_responses import OpenAIResponsesModel
|
||||
from agents.retry import (
|
||||
ModelRetryBackoffSettings,
|
||||
ModelRetrySettings,
|
||||
RetryPolicyContext,
|
||||
retry_policies,
|
||||
)
|
||||
from openai.types.responses import Response, ResponseCompletedEvent
|
||||
from openai.types.responses.response_usage import ResponseUsage
|
||||
from openai.types.shared import Reasoning
|
||||
|
||||
from strix.config import codex
|
||||
from strix.config.loader import load_settings
|
||||
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from collections.abc import AsyncIterator
|
||||
from agents.models.interface import ModelProvider
|
||||
|
||||
from agents.agent_output import AgentOutputSchemaBase
|
||||
from agents.handoffs import Handoff
|
||||
from agents.items import ModelResponse, TResponseInputItem, TResponseStreamEvent
|
||||
from agents.models.interface import ModelProvider, ModelTracing
|
||||
from agents.retry import ModelRetryAdvice, ModelRetryAdviceRequest
|
||||
from agents.tool import Tool
|
||||
from agents.usage import Usage
|
||||
from openai import AsyncOpenAI
|
||||
from openai.types.responses.response_prompt_param import ResponsePromptParam
|
||||
|
||||
from strix.config.settings import LlmSettings, ReasoningEffort, Settings
|
||||
from strix.config.settings import Settings
|
||||
|
||||
|
||||
def request_timeout_extra_args(timeout_s: float | None) -> dict[str, float] | None:
|
||||
@@ -60,214 +33,9 @@ def _retry_statusless_provider_errors(context: RetryPolicyContext) -> bool:
|
||||
normalized = context.normalized
|
||||
if normalized.is_abort:
|
||||
return False
|
||||
if codex.is_content_guardrail_error(context.error):
|
||||
return False
|
||||
return normalized.status_code is None
|
||||
|
||||
|
||||
class _CodexResponsesModel(OpenAIResponsesModel):
|
||||
"""Responses model for the ChatGPT subscription backend (always streamed, stateless)."""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
model: str,
|
||||
openai_client: AsyncOpenAI,
|
||||
*,
|
||||
reasoning_effort: ReasoningEffort | None = None,
|
||||
) -> None:
|
||||
super().__init__(model, openai_client)
|
||||
self._reasoning_effort = reasoning_effort
|
||||
|
||||
def _codex_settings(self, model_settings: ModelSettings) -> ModelSettings:
|
||||
overrides = ModelSettings(store=False, response_include=["reasoning.encrypted_content"])
|
||||
effort = self._reasoning_effort
|
||||
if effort and effort != "none":
|
||||
# Clamp to efforts the backend accepts.
|
||||
match effort:
|
||||
case "minimal":
|
||||
effort = "low"
|
||||
case "xhigh" | "max":
|
||||
effort = "high"
|
||||
case _:
|
||||
pass
|
||||
overrides = overrides.resolve(ModelSettings(reasoning=Reasoning(effort=effort)))
|
||||
return model_settings.resolve(overrides)
|
||||
|
||||
async def _fetch_response(self, *args: Any, stream: bool = False, **kwargs: Any) -> Any:
|
||||
if len(args) >= 3: # model_settings is positional arg 2
|
||||
args = (*args[:2], self._codex_settings(args[2]), *args[3:])
|
||||
try:
|
||||
events = await super()._fetch_response(*args, stream=True, **kwargs) # type: ignore[call-overload]
|
||||
except Exception as exc:
|
||||
guardrail = self._as_guardrail(exc)
|
||||
if guardrail is not None:
|
||||
raise guardrail from exc
|
||||
raise
|
||||
guarded = self._guarded(events)
|
||||
if stream:
|
||||
return guarded
|
||||
final_response = None
|
||||
async for event in guarded:
|
||||
if getattr(event, "type", None) == "response.completed":
|
||||
final_response = event.response
|
||||
if final_response is None:
|
||||
msg = "ChatGPT backend stream ended without a completed response"
|
||||
raise RuntimeError(msg)
|
||||
return final_response
|
||||
|
||||
def _as_guardrail(self, exc: BaseException) -> codex.CodexContentGuardrailError | None:
|
||||
if isinstance(exc, codex.CodexContentGuardrailError):
|
||||
return exc
|
||||
if codex.is_content_guardrail_error(exc):
|
||||
return codex.CodexContentGuardrailError(self.model, exc)
|
||||
return None
|
||||
|
||||
async def _guarded(self, events: Any) -> AsyncIterator[Any]:
|
||||
"""Convert mid-stream guardrail rejections and close the stream on exit."""
|
||||
try:
|
||||
async for event in events:
|
||||
yield event
|
||||
except Exception as exc:
|
||||
guardrail = self._as_guardrail(exc)
|
||||
if guardrail is not None:
|
||||
raise guardrail from exc
|
||||
raise
|
||||
finally:
|
||||
await self._aclose(events)
|
||||
|
||||
@staticmethod
|
||||
async def _aclose(events: Any) -> None:
|
||||
aclose = getattr(events, "aclose", None)
|
||||
if callable(aclose):
|
||||
with contextlib.suppress(Exception):
|
||||
await aclose()
|
||||
return
|
||||
close = getattr(events, "close", None)
|
||||
if callable(close):
|
||||
with contextlib.suppress(Exception):
|
||||
result = close()
|
||||
if inspect.isawaitable(result):
|
||||
await result
|
||||
|
||||
|
||||
class _NonStreamingModel(Model):
|
||||
"""Serve the SDK's streamed run loop from a single non-streaming request.
|
||||
|
||||
Some OpenAI-compatible gateways do not support Server-Sent Events, or
|
||||
deliver them unreliably (dropping structured tool-call deltas, or stalling
|
||||
mid-stream so the whole turn waits out the read timeout). The SDK run loop
|
||||
Strix uses only issues streamed requests, so such a gateway fails every
|
||||
turn. Opt in with ``LLM_DISABLE_STREAMING=true`` to wrap the resolved model
|
||||
so each turn makes one non-streaming ``get_response`` (``stream:false`` on
|
||||
the wire) and the completed result is replayed as a single terminal stream
|
||||
event. The run loop then executes tools and emits run items from that final
|
||||
response exactly as it would for a real stream, so nothing else changes.
|
||||
"""
|
||||
|
||||
def __init__(self, inner: Model) -> None:
|
||||
self._inner = inner
|
||||
|
||||
async def close(self) -> None:
|
||||
await self._inner.close()
|
||||
|
||||
def get_retry_advice(self, request: ModelRetryAdviceRequest) -> ModelRetryAdvice | None:
|
||||
return self._inner.get_retry_advice(request)
|
||||
|
||||
async def get_response(
|
||||
self,
|
||||
system_instructions: str | None,
|
||||
input: str | list[TResponseInputItem], # noqa: A002
|
||||
model_settings: ModelSettings,
|
||||
tools: list[Tool],
|
||||
output_schema: AgentOutputSchemaBase | None,
|
||||
handoffs: list[Handoff],
|
||||
tracing: ModelTracing,
|
||||
*,
|
||||
previous_response_id: str | None,
|
||||
conversation_id: str | None,
|
||||
prompt: ResponsePromptParam | None,
|
||||
) -> ModelResponse:
|
||||
return await self._inner.get_response(
|
||||
system_instructions,
|
||||
input,
|
||||
model_settings,
|
||||
tools,
|
||||
output_schema,
|
||||
handoffs,
|
||||
tracing,
|
||||
previous_response_id=previous_response_id,
|
||||
conversation_id=conversation_id,
|
||||
prompt=prompt,
|
||||
)
|
||||
|
||||
async def stream_response(
|
||||
self,
|
||||
system_instructions: str | None,
|
||||
input: str | list[TResponseInputItem], # noqa: A002
|
||||
model_settings: ModelSettings,
|
||||
tools: list[Tool],
|
||||
output_schema: AgentOutputSchemaBase | None,
|
||||
handoffs: list[Handoff],
|
||||
tracing: ModelTracing,
|
||||
*,
|
||||
previous_response_id: str | None,
|
||||
conversation_id: str | None,
|
||||
prompt: ResponsePromptParam | None,
|
||||
) -> AsyncIterator[TResponseStreamEvent]:
|
||||
response = await self._inner.get_response(
|
||||
system_instructions,
|
||||
input,
|
||||
model_settings,
|
||||
tools,
|
||||
output_schema,
|
||||
handoffs,
|
||||
tracing,
|
||||
previous_response_id=previous_response_id,
|
||||
conversation_id=conversation_id,
|
||||
prompt=prompt,
|
||||
)
|
||||
yield _completed_stream_event(response, getattr(self._inner, "model", None))
|
||||
|
||||
|
||||
def _completed_stream_event(
|
||||
model_response: ModelResponse, model_name: object | None
|
||||
) -> TResponseStreamEvent:
|
||||
"""Wrap a non-streamed ``ModelResponse`` as the terminal event of a stream.
|
||||
|
||||
The run loop builds its authoritative per-turn response solely from the
|
||||
``response.completed`` event, so a single event carrying the full output
|
||||
and usage is all it needs.
|
||||
"""
|
||||
response = Response(
|
||||
id=model_response.response_id or FAKE_RESPONSES_ID,
|
||||
created_at=time.time(),
|
||||
model=str(model_name) if model_name else "",
|
||||
object="response",
|
||||
output=list(model_response.output),
|
||||
tool_choice="auto",
|
||||
tools=[],
|
||||
parallel_tool_calls=False,
|
||||
usage=_response_usage(model_response.usage),
|
||||
)
|
||||
return ResponseCompletedEvent(
|
||||
response=response,
|
||||
sequence_number=0,
|
||||
type="response.completed",
|
||||
)
|
||||
|
||||
|
||||
def _response_usage(usage: Usage | None) -> ResponseUsage | None:
|
||||
if usage is None:
|
||||
return None
|
||||
return ResponseUsage(
|
||||
input_tokens=usage.input_tokens,
|
||||
output_tokens=usage.output_tokens,
|
||||
total_tokens=usage.total_tokens,
|
||||
input_tokens_details=usage.input_tokens_details,
|
||||
output_tokens_details=usage.output_tokens_details,
|
||||
)
|
||||
|
||||
|
||||
class StrixProvider(MultiProvider):
|
||||
"""Route any non-OpenAI prefix through LiteLLM with the prefix preserved,
|
||||
so users type ``deepseek/deepseek-chat`` rather than
|
||||
@@ -291,23 +59,6 @@ class StrixProvider(MultiProvider):
|
||||
return self._get_fallback_provider("litellm"), f"ollama_chat/{stripped_model_name}"
|
||||
return self._get_fallback_provider("litellm"), original_model_name
|
||||
|
||||
def get_model(self, model_name: str | None) -> Model:
|
||||
llm = load_settings().llm
|
||||
slug = codex.subscription_model(model_name)
|
||||
if slug:
|
||||
# The ChatGPT subscription backend is always streamed; it has no
|
||||
# non-streaming mode to fall back to, so LLM_DISABLE_STREAMING
|
||||
# does not apply here.
|
||||
return _CodexResponsesModel(
|
||||
slug,
|
||||
codex.get_subscription_client(),
|
||||
reasoning_effort=llm.reasoning_effort,
|
||||
)
|
||||
model = super().get_model(model_name)
|
||||
if llm.disable_streaming:
|
||||
return _NonStreamingModel(model)
|
||||
return model
|
||||
|
||||
|
||||
DEFAULT_MODEL_RETRY = ModelRetrySettings(
|
||||
max_retries=5,
|
||||
@@ -326,42 +77,39 @@ DEFAULT_MODEL_RETRY = ModelRetrySettings(
|
||||
)
|
||||
|
||||
RECOMMENDED_MODEL_NAMES = (
|
||||
"openai/gpt-5.6",
|
||||
"openai/gpt-5.6-sol",
|
||||
"openai/gpt-5.6-terra",
|
||||
"openai/gpt-5.6-luna",
|
||||
"openai/gpt-5.6",
|
||||
"openai/gpt-5.5-pro",
|
||||
"openai/gpt-5.5",
|
||||
"openai/gpt-5.5-pro",
|
||||
"openai/gpt-5.4",
|
||||
"openai/gpt-5.3-codex",
|
||||
"anthropic/claude-fable-5",
|
||||
"anthropic/claude-opus-5",
|
||||
"anthropic/claude-opus-4-8",
|
||||
"anthropic/claude-opus-4-7",
|
||||
"anthropic/claude-sonnet-5",
|
||||
"anthropic/claude-sonnet-4-6",
|
||||
"vertex_ai/gemini-3.1-pro-preview",
|
||||
"gemini/gemini-3.1-pro-preview",
|
||||
"gemini/gemini-3.6-flash",
|
||||
"deepseek/deepseek-v4-pro",
|
||||
"deepseek/deepseek-v4-flash",
|
||||
"dashscope/qwen3.8-max",
|
||||
"dashscope/qwen3.7-max-2026-06-08",
|
||||
"moonshot/kimi-k3",
|
||||
"moonshot/kimi-k2.7-code",
|
||||
"moonshot/kimi-k2.6",
|
||||
)
|
||||
|
||||
_RECOMMENDED_MODEL_NAME_SET = frozenset(name.lower() for name in RECOMMENDED_MODEL_NAMES)
|
||||
|
||||
FRONTIER_MODEL_FAMILIES = (
|
||||
(("azure", "azure_ai", "bedrock_mantle", "chatgpt", "openai"), ("gpt-5",)),
|
||||
(("azure", "azure_ai", "bedrock_mantle", "openai"), ("gpt-5",)),
|
||||
(
|
||||
("anthropic", "azure_ai", "bedrock", "claude", "databricks", "snowflake", "vertex_ai"),
|
||||
("claude-fable-5", "claude-opus-5", "claude-opus-4", "claude-sonnet-5", "claude-sonnet-4"),
|
||||
("claude-fable-5", "claude-opus-4", "claude-sonnet-5", "claude-sonnet-4"),
|
||||
),
|
||||
(("google", "gemini", "vertex_ai"), ("gemini-3",)),
|
||||
(("deepseek",), ("deepseek-v4", "deepseek-r1", "deepseek-reasoner")),
|
||||
(("alibaba", "dashscope", "qwen"), ("qwen3.8", "qwen3.7", "qwen3-max")),
|
||||
(("moonshot", "moonshotai", "kimi"), ("kimi-k3", "kimi-k2.7", "kimi-k2.6")),
|
||||
(("alibaba", "dashscope", "qwen"), ("qwen3.7", "qwen3.5", "qwen3-max")),
|
||||
(("moonshot", "moonshotai", "kimi"), ("kimi-k2.7", "kimi-k2.6", "kimi-k2.5")),
|
||||
)
|
||||
|
||||
|
||||
@@ -369,8 +117,6 @@ def configure_sdk_model_defaults(settings: Settings) -> None:
|
||||
"""Apply Strix config to SDK-native defaults."""
|
||||
llm = settings.llm
|
||||
set_tracing_disabled(True)
|
||||
if codex.subscription_model(llm.model):
|
||||
return
|
||||
_configure_litellm_compatibility()
|
||||
_configure_openrouter_attribution(llm.model)
|
||||
if llm.api_key:
|
||||
@@ -383,7 +129,6 @@ def configure_sdk_model_defaults(settings: Settings) -> None:
|
||||
set_default_openai_api("chat_completions")
|
||||
else:
|
||||
set_default_openai_api("responses")
|
||||
_configure_extra_headers(llm)
|
||||
|
||||
|
||||
def _mirror_api_key_to_provider_env(model_name: str | None, api_key: str) -> None:
|
||||
@@ -418,51 +163,6 @@ def _configure_litellm_compatibility() -> None:
|
||||
litellm.suppress_debug_info = True
|
||||
|
||||
_register_litellm_cost_callback()
|
||||
_install_openrouter_stream_cost_capture()
|
||||
|
||||
|
||||
def _install_openrouter_stream_cost_capture() -> None:
|
||||
"""Preserve OpenRouter's per-stream cost, which LiteLLM drops when streaming.
|
||||
|
||||
OpenRouter reports the real charge in ``usage.cost`` of the final stream
|
||||
chunk, but LiteLLM rebuilds streamed responses from token-only fields and
|
||||
discards it (its non-streamed path stashes the cost in hidden params; the
|
||||
streaming path does not). Every scan streams, so without this the cost is
|
||||
lost and Strix falls back to a cost-map estimate that is missing entirely
|
||||
for new models (e.g. kimi-k3), reporting $0. Subclass the OpenRouter
|
||||
streaming handler to record the cost keyed by response id so the cost
|
||||
callback can recover the exact charge for the matching rebuilt response.
|
||||
"""
|
||||
import litellm
|
||||
from litellm.llms.openrouter.chat.transformation import (
|
||||
OpenRouterChatCompletionStreamingHandler,
|
||||
OpenrouterConfig,
|
||||
)
|
||||
|
||||
from strix.report.state import streamed_openrouter_costs
|
||||
|
||||
class _StrixOpenRouterStreamingHandler(OpenRouterChatCompletionStreamingHandler):
|
||||
def chunk_parser(self, chunk: dict[str, Any]) -> Any:
|
||||
stream = super().chunk_parser(chunk)
|
||||
streamed_openrouter_costs.remember(
|
||||
chunk.get("id") or getattr(stream, "id", None), chunk.get("usage")
|
||||
)
|
||||
return stream
|
||||
|
||||
class _StrixOpenrouterConfig(OpenrouterConfig):
|
||||
def get_model_response_iterator(
|
||||
self, streaming_response: Any, sync_stream: bool, json_mode: bool | None = False
|
||||
) -> Any:
|
||||
return _StrixOpenRouterStreamingHandler(
|
||||
streaming_response=streaming_response,
|
||||
sync_stream=sync_stream,
|
||||
json_mode=json_mode,
|
||||
)
|
||||
|
||||
# LiteLLM's provider-config factory reads litellm.OpenrouterConfig at call
|
||||
# time, so overriding the attribute is enough for the subclass to take
|
||||
# effect. (type: ignore — mypy rejects reassigning a class attribute.)
|
||||
litellm.OpenrouterConfig = _StrixOpenrouterConfig # type: ignore[misc]
|
||||
|
||||
|
||||
_OPENROUTER_ATTRIBUTION_HEADERS = {
|
||||
@@ -488,43 +188,6 @@ def _configure_openrouter_attribution(model_name: str | None) -> None:
|
||||
litellm.headers = {**existing, **_OPENROUTER_ATTRIBUTION_HEADERS} # type: ignore[assignment]
|
||||
|
||||
|
||||
def _configure_extra_headers(llm: LlmSettings) -> None:
|
||||
"""Send user-provided default headers on every LLM request.
|
||||
|
||||
Some OpenAI-compatible endpoints require extra HTTP headers (e.g. request
|
||||
attribution or tenant routing) alongside the bearer token. Users supply
|
||||
them via ``LLM_EXTRA_HEADERS``; they are applied to both routing paths:
|
||||
the LiteLLM route (``litellm.headers``) and the SDK-native OpenAI route
|
||||
(a default client carrying ``default_headers``), so they take effect
|
||||
regardless of the ``STRIX_LLM`` prefix.
|
||||
"""
|
||||
headers = llm.extra_headers
|
||||
if not headers:
|
||||
return
|
||||
_merge_litellm_headers(headers)
|
||||
_register_openai_client_with_headers(llm, headers)
|
||||
|
||||
|
||||
def _merge_litellm_headers(headers: dict[str, str]) -> None:
|
||||
import litellm
|
||||
|
||||
current: object = litellm.headers
|
||||
existing: dict[str, str] = current if isinstance(current, dict) else {}
|
||||
litellm.headers = {**existing, **headers} # type: ignore[assignment]
|
||||
|
||||
|
||||
def _register_openai_client_with_headers(llm: LlmSettings, headers: dict[str, str]) -> None:
|
||||
from agents import set_default_openai_client
|
||||
from openai import AsyncOpenAI
|
||||
|
||||
client = AsyncOpenAI(
|
||||
api_key=llm.api_key or "not-needed",
|
||||
base_url=llm.api_base,
|
||||
default_headers=dict(headers),
|
||||
)
|
||||
set_default_openai_client(client, use_for_tracing=False)
|
||||
|
||||
|
||||
def _register_litellm_cost_callback() -> None:
|
||||
import litellm
|
||||
|
||||
@@ -548,8 +211,6 @@ def _configure_litellm_default(name: str, value: str) -> None:
|
||||
|
||||
def uses_chat_completions_tool_schema(model_name: str, settings: Settings) -> bool:
|
||||
"""Return whether the resolved SDK route can only receive JSON function tools."""
|
||||
if codex.subscription_model(model_name):
|
||||
return False
|
||||
model = model_name.strip().lower()
|
||||
if "/" in model and not model.startswith("openai/"):
|
||||
return True
|
||||
@@ -652,45 +313,3 @@ def is_known_openai_bare_model(model_name: str) -> bool:
|
||||
return False
|
||||
entry = litellm.model_cost.get(name)
|
||||
return bool(entry and entry.get("litellm_provider") == "openai")
|
||||
|
||||
|
||||
def is_claude_model(model_name: str) -> bool:
|
||||
return "claude" in (model_name or "").strip().lower()
|
||||
|
||||
|
||||
def is_bedrock_route(model_name: str) -> bool:
|
||||
name = (model_name or "").strip().lower()
|
||||
return name.startswith("bedrock/") or "anthropic." in name
|
||||
|
||||
|
||||
def _prompt_cache_name_candidates(model_name: str) -> list[str]:
|
||||
# LiteLLM's model map keys the same model under several names; strip the
|
||||
# route prefix, then leading dotted segments (region, provider).
|
||||
name = (model_name or "").strip().lower()
|
||||
for prefix in ("litellm/", "bedrock/"):
|
||||
if name.startswith(prefix):
|
||||
name = name[len(prefix) :]
|
||||
break
|
||||
candidates = [name]
|
||||
rest = name
|
||||
while "." in rest:
|
||||
rest = rest.split(".", 1)[1]
|
||||
candidates.append(rest)
|
||||
return candidates
|
||||
|
||||
|
||||
def bedrock_route_supports_prompt_caching(model_name: str) -> bool:
|
||||
# Bedrock rejects the cache marker for models LiteLLM's map doesn't
|
||||
# recognise as cache-capable, so callers withhold it unless confirmed here.
|
||||
import litellm
|
||||
|
||||
checker = getattr(getattr(litellm, "utils", None), "supports_prompt_caching", None)
|
||||
for cand in _prompt_cache_name_candidates(model_name):
|
||||
if checker is not None:
|
||||
with contextlib.suppress(Exception):
|
||||
if checker(cand):
|
||||
return True
|
||||
entry = litellm.model_cost.get(cand)
|
||||
if entry and entry.get("supports_prompt_caching"):
|
||||
return True
|
||||
return False
|
||||
|
||||
@@ -8,9 +8,7 @@ from pydantic import AliasChoices, Field
|
||||
from pydantic_settings import BaseSettings, SettingsConfigDict
|
||||
|
||||
|
||||
ReasoningEffort = Literal["none", "minimal", "low", "medium", "high", "xhigh", "max"]
|
||||
|
||||
DEFAULT_MAX_TURNS = 500
|
||||
ReasoningEffort = Literal["none", "minimal", "low", "medium", "high", "xhigh"]
|
||||
|
||||
_BASE_CONFIG = SettingsConfigDict(
|
||||
case_sensitive=False,
|
||||
@@ -37,70 +35,27 @@ class LlmSettings(BaseSettings):
|
||||
"OLLAMA_API_BASE",
|
||||
),
|
||||
)
|
||||
extra_headers: dict[str, str] | None = Field(
|
||||
default=None,
|
||||
alias="LLM_EXTRA_HEADERS",
|
||||
)
|
||||
reasoning_effort: ReasoningEffort = Field(default="high", alias="STRIX_REASONING_EFFORT")
|
||||
force_required_tool_choice: bool = Field(
|
||||
default=False,
|
||||
alias="STRIX_FORCE_REQUIRED_TOOL_CHOICE",
|
||||
)
|
||||
prompt_cache: bool = Field(
|
||||
default=True,
|
||||
alias="STRIX_PROMPT_CACHE",
|
||||
)
|
||||
disable_streaming: bool = Field(
|
||||
default=False,
|
||||
alias="LLM_DISABLE_STREAMING",
|
||||
)
|
||||
timeout: int = Field(default=300, alias="LLM_TIMEOUT")
|
||||
|
||||
|
||||
class DedupeSettings(BaseSettings):
|
||||
model_config = _BASE_CONFIG
|
||||
|
||||
model: str | None = Field(default=None, alias="STRIX_DEDUPE_MODEL")
|
||||
reasoning_effort: ReasoningEffort | None = Field(
|
||||
default=None,
|
||||
alias="STRIX_DEDUPE_REASONING_EFFORT",
|
||||
)
|
||||
api_key: str | None = Field(default=None, alias="DEDUPE_LLM_API_KEY")
|
||||
api_base: str | None = Field(default=None, alias="DEDUPE_LLM_API_BASE")
|
||||
extra_headers: dict[str, str] | None = Field(
|
||||
default=None,
|
||||
alias="DEDUPE_LLM_EXTRA_HEADERS",
|
||||
)
|
||||
|
||||
|
||||
class ContextSettings(BaseSettings):
|
||||
"""Context-window management: per-tool-output caps and history compaction."""
|
||||
|
||||
model_config = _BASE_CONFIG
|
||||
|
||||
auto_compact: bool = Field(default=True, alias="STRIX_CONTEXT_AUTO_COMPACT")
|
||||
compact_buffer_tokens: int = Field(default=20_000, gt=0, alias="STRIX_CONTEXT_BUFFER_TOKENS")
|
||||
keep_tokens: int = Field(default=8_000, gt=0, alias="STRIX_CONTEXT_KEEP_TOKENS")
|
||||
fallback_context_tokens: int = Field(
|
||||
default=200_000, gt=0, alias="STRIX_CONTEXT_FALLBACK_TOKENS"
|
||||
)
|
||||
summary_max_tokens: int = Field(default=4_096, gt=0, alias="STRIX_CONTEXT_SUMMARY_TOKENS")
|
||||
tool_output_max_tokens: int = Field(default=8_000, gt=0, alias="STRIX_TOOL_OUTPUT_MAX_TOKENS")
|
||||
tool_output_max_lines: int = Field(default=2_000, gt=0, alias="STRIX_TOOL_OUTPUT_MAX_LINES")
|
||||
# Floor above the truncation-notice size so a preview always fits.
|
||||
tool_output_max_bytes: int = Field(
|
||||
default=50 * 1024, ge=1024, alias="STRIX_TOOL_OUTPUT_MAX_BYTES"
|
||||
)
|
||||
|
||||
|
||||
class RuntimeSettings(BaseSettings):
|
||||
model_config = _BASE_CONFIG
|
||||
|
||||
image: str = Field(
|
||||
default="ghcr.io/usestrix/strix-sandbox:1.2.0",
|
||||
default="ghcr.io/usestrix/strix-sandbox:1.0.0",
|
||||
alias="STRIX_IMAGE",
|
||||
)
|
||||
backend: str = Field(default="docker", alias="STRIX_RUNTIME_BACKEND")
|
||||
# Hard cap on a local target's size before we refuse to stream it into the
|
||||
# sandbox file-by-file (the SDK copies every file individually, which stalls
|
||||
# on large repos). Above this, the user must bind-mount via ``--mount``.
|
||||
# Set to 0 (or less) to disable the pre-flight check entirely.
|
||||
max_local_copy_mb: int = Field(default=1024, alias="STRIX_MAX_LOCAL_COPY_MB")
|
||||
# Max screenshot/image tool outputs kept live per agent context (0 = none).
|
||||
max_context_images: int = Field(default=3, ge=0, alias="STRIX_MAX_CONTEXT_IMAGES")
|
||||
|
||||
@@ -130,9 +85,7 @@ class Settings(BaseSettings):
|
||||
model_config = _BASE_CONFIG
|
||||
|
||||
llm: LlmSettings = Field(default_factory=LlmSettings)
|
||||
dedupe: DedupeSettings = Field(default_factory=DedupeSettings)
|
||||
runtime: RuntimeSettings = Field(default_factory=RuntimeSettings)
|
||||
context: ContextSettings = Field(default_factory=ContextSettings)
|
||||
telemetry: TelemetrySettings = Field(default_factory=TelemetrySettings)
|
||||
integrations: IntegrationSettings = Field(default_factory=IntegrationSettings)
|
||||
viewer: ViewerSettings = Field(default_factory=ViewerSettings)
|
||||
|
||||
+40
-250
@@ -14,20 +14,13 @@ from strix.core.sessions import session_write_lock
|
||||
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from collections.abc import Callable
|
||||
|
||||
from agents.items import TResponseInputItem
|
||||
from agents.memory import Session
|
||||
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
Status = Literal["running", "waiting", "completed", "stopped", "crashed", "failed", "budget_paused"]
|
||||
|
||||
# Why an agent parked. The user can message any agent, so this - not the agent's
|
||||
# position in the tree - decides whether waiting is bounded: only an agent waiting
|
||||
# on other agents is re-checked on a timer.
|
||||
WaitKind = Literal["user", "agents", "stalled"]
|
||||
Status = Literal["running", "waiting", "completed", "stopped", "crashed", "failed"]
|
||||
|
||||
|
||||
@dataclass(slots=True)
|
||||
@@ -37,8 +30,6 @@ class AgentRuntime:
|
||||
stream: Any | None = None
|
||||
interrupt_on_message: bool = False
|
||||
wake: asyncio.Event = field(default_factory=asyncio.Event)
|
||||
mailbox: list[dict[str, Any]] = field(default_factory=list)
|
||||
user_wake_required: bool = False
|
||||
|
||||
|
||||
class AgentCoordinator:
|
||||
@@ -50,19 +41,11 @@ class AgentCoordinator:
|
||||
self.names: dict[str, str] = {}
|
||||
self.metadata: dict[str, dict[str, Any]] = {}
|
||||
self.pending_counts: dict[str, int] = {}
|
||||
self.errors: dict[str, str] = {}
|
||||
self.recovery_counts: dict[str, int] = {}
|
||||
self.idle_resume_counts: dict[str, int] = {}
|
||||
self.wait_kinds: dict[str, WaitKind] = {}
|
||||
self.runtimes: dict[str, AgentRuntime] = {}
|
||||
self._parent_notified: set[str] = set()
|
||||
self._lock = asyncio.Lock()
|
||||
self._snapshot_path: Path | None = None
|
||||
self.is_shutting_down = False
|
||||
self._budget_stopped = False
|
||||
self._reserve_stopped = False
|
||||
self._budget_paused = False
|
||||
self._extend_budget: Callable[[], None] | None = None
|
||||
|
||||
def set_snapshot_path(self, path: Path) -> None:
|
||||
self._snapshot_path = path
|
||||
@@ -81,71 +64,6 @@ class AgentCoordinator:
|
||||
for runtime in self.runtimes.values():
|
||||
runtime.wake.set()
|
||||
|
||||
@property
|
||||
def reserve_stopped(self) -> bool:
|
||||
return self._reserve_stopped
|
||||
|
||||
@property
|
||||
def budget_paused(self) -> bool:
|
||||
return self._budget_paused
|
||||
|
||||
def set_budget_extender(self, extend: Callable[[], None]) -> None:
|
||||
self._extend_budget = extend
|
||||
|
||||
async def pause_for_budget(self, agent_id: str) -> None:
|
||||
async with self._lock:
|
||||
self._budget_paused = True
|
||||
await self.set_status(agent_id, "budget_paused")
|
||||
|
||||
async def resume_from_budget_pause(self, *, exclude: str | None = None) -> None:
|
||||
async with self._lock:
|
||||
if not self._budget_paused:
|
||||
return
|
||||
self._budget_paused = False
|
||||
paused = [aid for aid, status in self.statuses.items() if status == "budget_paused"]
|
||||
if self._extend_budget is not None:
|
||||
self._extend_budget()
|
||||
for aid in paused:
|
||||
await self.set_status(aid, "waiting")
|
||||
if aid != exclude:
|
||||
await self.send(
|
||||
aid,
|
||||
{
|
||||
"from": "system",
|
||||
"type": "budget_extended",
|
||||
"content": (
|
||||
"[Budget] The user extended the scan budget \u2014 continue your "
|
||||
"current task."
|
||||
),
|
||||
},
|
||||
)
|
||||
|
||||
async def reset_budget_stops(
|
||||
self,
|
||||
*,
|
||||
budget_stopped: bool,
|
||||
reserve_stopped: bool,
|
||||
budget_paused: bool = False,
|
||||
) -> None:
|
||||
async with self._lock:
|
||||
self._budget_stopped = budget_stopped
|
||||
self._reserve_stopped = reserve_stopped
|
||||
if not budget_paused:
|
||||
self._budget_paused = False
|
||||
for aid, status in self.statuses.items():
|
||||
if status == "budget_paused":
|
||||
self.statuses[aid] = "waiting"
|
||||
await self._maybe_snapshot()
|
||||
|
||||
async def claim_reserve_notification(self) -> str | None:
|
||||
async with self._lock:
|
||||
if self._reserve_stopped:
|
||||
return None
|
||||
self._reserve_stopped = True
|
||||
for runtime in self.runtimes.values():
|
||||
runtime.wake.set()
|
||||
return next((aid for aid, parent in self.parent_of.items() if parent is None), None)
|
||||
|
||||
async def register(
|
||||
self,
|
||||
agent_id: str,
|
||||
@@ -189,136 +107,62 @@ class AgentCoordinator:
|
||||
async with self._lock:
|
||||
if agent_id in self.statuses:
|
||||
self.statuses[agent_id] = "running"
|
||||
self.errors.pop(agent_id, None)
|
||||
self.wait_kinds.pop(agent_id, None)
|
||||
self.runtimes.setdefault(agent_id, AgentRuntime()).user_wake_required = False
|
||||
self._parent_notified.discard(agent_id)
|
||||
await self._maybe_snapshot()
|
||||
|
||||
async def park_waiting(self, agent_id: str, *, wait_kind: WaitKind) -> None:
|
||||
"""Park an agent, recording what it is waiting on so the driver can time it."""
|
||||
async with self._lock:
|
||||
if agent_id in self.statuses:
|
||||
self.wait_kinds[agent_id] = wait_kind
|
||||
async def park_waiting(self, agent_id: str) -> None:
|
||||
await self.set_status(agent_id, "waiting")
|
||||
|
||||
async def wait_kind_of(self, agent_id: str) -> WaitKind | None:
|
||||
async with self._lock:
|
||||
return self.wait_kinds.get(agent_id)
|
||||
|
||||
async def record_recovery(self, agent_id: str) -> int:
|
||||
"""Count a turn that ended without a lifecycle tool call; return the new total.
|
||||
|
||||
Persisted so a resumed agent cannot earn a fresh nudge budget on every
|
||||
auto-resume and loop forever.
|
||||
"""
|
||||
async with self._lock:
|
||||
count = self.recovery_counts.get(agent_id, 0) + 1
|
||||
self.recovery_counts[agent_id] = count
|
||||
await self._maybe_snapshot()
|
||||
return count
|
||||
|
||||
async def reset_recovery(self, agent_id: str) -> None:
|
||||
"""Clear the nudge budget after real progress (new message or a lifecycle tool)."""
|
||||
async with self._lock:
|
||||
if self.recovery_counts.pop(agent_id, None) is None:
|
||||
return
|
||||
await self._maybe_snapshot()
|
||||
|
||||
async def record_idle_resume(self, agent_id: str) -> int:
|
||||
"""Count an auto-resume that no message triggered; return the new total.
|
||||
|
||||
An agent that parks again after every auto-resume would otherwise burn a
|
||||
model turn per timeout for the rest of the scan.
|
||||
"""
|
||||
async with self._lock:
|
||||
count = self.idle_resume_counts.get(agent_id, 0) + 1
|
||||
self.idle_resume_counts[agent_id] = count
|
||||
await self._maybe_snapshot()
|
||||
return count
|
||||
|
||||
async def reset_idle_resumes(self, agent_id: str) -> None:
|
||||
async with self._lock:
|
||||
if self.idle_resume_counts.pop(agent_id, None) is None:
|
||||
return
|
||||
await self._maybe_snapshot()
|
||||
|
||||
async def set_status(
|
||||
self, agent_id: str, status: Status | str, *, error: str | None = None
|
||||
) -> None:
|
||||
async def set_status(self, agent_id: str, status: Status | str) -> None:
|
||||
async with self._lock:
|
||||
if agent_id not in self.statuses:
|
||||
return
|
||||
self.statuses[agent_id] = status # type: ignore[assignment]
|
||||
if error is not None:
|
||||
self.errors[agent_id] = error
|
||||
elif status == "running":
|
||||
self.errors.pop(agent_id, None)
|
||||
if status == "running":
|
||||
# Running again means a fresh stint that owes its parent its own notice.
|
||||
self._parent_notified.discard(agent_id)
|
||||
runtime = self.runtimes.setdefault(agent_id, AgentRuntime())
|
||||
runtime.user_wake_required = status in {"failed", "crashed"}
|
||||
runtime.wake.set()
|
||||
logger.info("agent.status %s=%s", agent_id, status)
|
||||
await self._maybe_snapshot()
|
||||
|
||||
async def claim_parent_notice(self, agent_id: str) -> bool:
|
||||
"""Reserve the one notice a child owes its parent when it stops running.
|
||||
|
||||
A completion report and a terminal notice carry the same information, so
|
||||
whichever comes first claims the slot and the other is skipped.
|
||||
"""
|
||||
async with self._lock:
|
||||
if agent_id in self._parent_notified:
|
||||
return False
|
||||
self._parent_notified.add(agent_id)
|
||||
return True
|
||||
|
||||
async def send(
|
||||
self, target_agent_id: str, message: dict[str, Any], *, interrupt: bool = True
|
||||
) -> bool:
|
||||
"""Queue a user/peer message in the target's mailbox and wake it."""
|
||||
from_user = message.get("from") == "user"
|
||||
if from_user and self._budget_paused:
|
||||
await self.resume_from_budget_pause(exclude=target_agent_id)
|
||||
async def send(self, target_agent_id: str, message: dict[str, Any]) -> bool:
|
||||
"""Deliver a user/peer message by appending it to the target SDK session."""
|
||||
async with self._lock:
|
||||
if target_agent_id not in self.statuses:
|
||||
logger.debug("agent.send dropped unknown target=%s", target_agent_id)
|
||||
return False
|
||||
runtime = self.runtimes.setdefault(target_agent_id, AgentRuntime())
|
||||
runtime.mailbox.append(dict(message))
|
||||
self.pending_counts[target_agent_id] = self.pending_counts.get(target_agent_id, 0) + 1
|
||||
if from_user:
|
||||
runtime.user_wake_required = False
|
||||
runtime.wake.set()
|
||||
session = runtime.session
|
||||
stream = runtime.stream
|
||||
interrupt_on_message = runtime.interrupt_on_message
|
||||
if stream is not None and interrupt and interrupt_on_message:
|
||||
interrupt = runtime.interrupt_on_message
|
||||
if session is None:
|
||||
logger.warning(
|
||||
"agent.send dropped target=%s because its SDK session is not attached",
|
||||
target_agent_id,
|
||||
)
|
||||
return False
|
||||
try:
|
||||
async with session_write_lock(session):
|
||||
await session.add_items([self._message_to_session_item(message)])
|
||||
except Exception:
|
||||
logger.exception(
|
||||
"agent.send failed to append to SDK session target=%s",
|
||||
target_agent_id,
|
||||
)
|
||||
return False
|
||||
async with self._lock:
|
||||
self.pending_counts[target_agent_id] = self.pending_counts.get(target_agent_id, 0) + 1
|
||||
self.runtimes.setdefault(target_agent_id, AgentRuntime()).wake.set()
|
||||
if stream is not None and interrupt:
|
||||
stream.cancel(mode="immediate")
|
||||
await self._maybe_snapshot()
|
||||
return True
|
||||
|
||||
async def wait_for_message(self, agent_id: str, *, timeout: float | None = None) -> bool:
|
||||
"""Wait until a message is ready for ``agent_id``; False on ``timeout``."""
|
||||
async def wait_for_message(self, agent_id: str) -> None:
|
||||
while True:
|
||||
async with self._lock:
|
||||
runtime = self.runtimes.setdefault(agent_id, AgentRuntime())
|
||||
reserve_exit = self._reserve_stopped and self.parent_of.get(agent_id) is not None
|
||||
pending_ready = (
|
||||
self.pending_counts.get(agent_id, 0) > 0 and not runtime.user_wake_required
|
||||
)
|
||||
if self._budget_stopped or reserve_exit or pending_ready:
|
||||
return True
|
||||
wake = runtime.wake
|
||||
if self._budget_stopped or self.pending_counts.get(agent_id, 0) > 0:
|
||||
return
|
||||
wake = self.runtimes.setdefault(agent_id, AgentRuntime()).wake
|
||||
wake.clear()
|
||||
if timeout is None:
|
||||
await wake.wait()
|
||||
else:
|
||||
try:
|
||||
await asyncio.wait_for(wake.wait(), timeout)
|
||||
except TimeoutError:
|
||||
return False
|
||||
await wake.wait()
|
||||
|
||||
async def consume_pending(
|
||||
self,
|
||||
@@ -326,38 +170,17 @@ class AgentCoordinator:
|
||||
*,
|
||||
include_items: bool = False,
|
||||
) -> tuple[int, list[Any]]:
|
||||
"""Drain the agent's mailbox into its own SDK session."""
|
||||
async with self._lock:
|
||||
runtime = self.runtimes.setdefault(agent_id, AgentRuntime())
|
||||
queued = list(runtime.mailbox)
|
||||
runtime.mailbox.clear()
|
||||
count = max(self.pending_counts.get(agent_id, 0), len(queued))
|
||||
count = self.pending_counts.get(agent_id, 0)
|
||||
self.pending_counts[agent_id] = 0
|
||||
session = runtime.session
|
||||
session = self.runtimes.get(agent_id, AgentRuntime()).session
|
||||
if count <= 0:
|
||||
return 0, []
|
||||
items = [self._message_to_session_item(m) for m in queued]
|
||||
if items:
|
||||
if session is None:
|
||||
logger.warning(
|
||||
"agent %s has no SDK session attached; %d queued messages were not persisted",
|
||||
agent_id,
|
||||
len(items),
|
||||
)
|
||||
else:
|
||||
try:
|
||||
async with session_write_lock(session):
|
||||
await session.add_items(items)
|
||||
except Exception:
|
||||
logger.exception(
|
||||
"failed to append %d queued messages to the session of %s",
|
||||
len(items),
|
||||
agent_id,
|
||||
)
|
||||
await self._maybe_snapshot()
|
||||
if not include_items:
|
||||
if not include_items or session is None:
|
||||
return count, []
|
||||
return count, items
|
||||
items = await session.get_items()
|
||||
return count, list(items[-count:])
|
||||
|
||||
async def request_stop(self, agent_id: str) -> None:
|
||||
async with self._lock:
|
||||
@@ -383,15 +206,12 @@ class AgentCoordinator:
|
||||
if tasks:
|
||||
await asyncio.gather(*tasks, return_exceptions=True)
|
||||
|
||||
async def cancel_descendants_graceful(self, agent_id: str) -> list[str]:
|
||||
"""Stop a subtree leaves-first and report which agents were stopped."""
|
||||
async def cancel_descendants_graceful(self, agent_id: str) -> None:
|
||||
async with self._lock:
|
||||
order = self._subtree_order_locked(agent_id)
|
||||
stopped = list(reversed(order))
|
||||
for aid in stopped:
|
||||
for aid in reversed(order):
|
||||
await self.request_stop(aid)
|
||||
await self._maybe_snapshot()
|
||||
return stopped
|
||||
|
||||
async def attach_stream(
|
||||
self,
|
||||
@@ -426,14 +246,9 @@ class AgentCoordinator:
|
||||
|
||||
async def graph_snapshot(
|
||||
self,
|
||||
) -> tuple[dict[str, str | None], dict[str, Status], dict[str, str], dict[str, str]]:
|
||||
) -> tuple[dict[str, str | None], dict[str, Status], dict[str, str]]:
|
||||
async with self._lock:
|
||||
return (
|
||||
dict(self.parent_of),
|
||||
dict(self.statuses),
|
||||
dict(self.names),
|
||||
dict(self.errors),
|
||||
)
|
||||
return dict(self.parent_of), dict(self.statuses), dict(self.names)
|
||||
|
||||
def _message_to_session_item(self, message: dict[str, Any]) -> TResponseInputItem:
|
||||
sender = str(message.get("from", "unknown"))
|
||||
@@ -471,18 +286,6 @@ class AgentCoordinator:
|
||||
"names": dict(self.names),
|
||||
"metadata": {aid: dict(md) for aid, md in self.metadata.items()},
|
||||
"pending_counts": dict(self.pending_counts),
|
||||
"recovery_counts": dict(self.recovery_counts),
|
||||
"idle_resume_counts": dict(self.idle_resume_counts),
|
||||
"wait_kinds": dict(self.wait_kinds),
|
||||
"mailboxes": {
|
||||
aid: [dict(m) for m in runtime.mailbox]
|
||||
for aid, runtime in self.runtimes.items()
|
||||
if runtime.mailbox
|
||||
},
|
||||
"errors": dict(self.errors),
|
||||
"budget_stopped": self._budget_stopped,
|
||||
"reserve_stopped": self._reserve_stopped,
|
||||
"budget_paused": self._budget_paused,
|
||||
}
|
||||
|
||||
async def restore(self, snap: dict[str, Any]) -> None:
|
||||
@@ -492,19 +295,6 @@ class AgentCoordinator:
|
||||
self.names = dict(snap.get("names", {}))
|
||||
self.metadata = {aid: dict(md) for aid, md in snap.get("metadata", {}).items()}
|
||||
self.pending_counts = dict(snap.get("pending_counts", {}))
|
||||
self.errors = dict(snap.get("errors", {}))
|
||||
self.recovery_counts = dict(snap.get("recovery_counts", {}))
|
||||
self.idle_resume_counts = dict(snap.get("idle_resume_counts", {}))
|
||||
self.wait_kinds = dict(snap.get("wait_kinds", {}))
|
||||
mailboxes = snap.get("mailboxes", {})
|
||||
if isinstance(mailboxes, dict):
|
||||
for aid, msgs in mailboxes.items():
|
||||
if isinstance(msgs, list):
|
||||
runtime = self.runtimes.setdefault(aid, AgentRuntime())
|
||||
runtime.mailbox = [dict(m) for m in msgs if isinstance(m, dict)]
|
||||
self._budget_stopped = bool(snap.get("budget_stopped", False))
|
||||
self._reserve_stopped = bool(snap.get("reserve_stopped", False))
|
||||
self._budget_paused = bool(snap.get("budget_paused", False))
|
||||
for aid in self.statuses:
|
||||
self.runtimes.setdefault(aid, AgentRuntime())
|
||||
|
||||
|
||||
+110
-552
@@ -9,32 +9,19 @@ import uuid
|
||||
from collections.abc import Callable
|
||||
from typing import TYPE_CHECKING, Any, cast
|
||||
|
||||
import litellm
|
||||
from agents import RunConfig, Runner
|
||||
from agents.exceptions import AgentsException, MaxTurnsExceeded, UserError
|
||||
from agents.sandbox.errors import ExecTransportError
|
||||
from docker import errors as docker_errors # type: ignore[import-untyped, unused-ignore]
|
||||
from openai import (
|
||||
APIConnectionError,
|
||||
APIError,
|
||||
APITimeoutError,
|
||||
)
|
||||
from openai import APIError
|
||||
|
||||
from strix.config import codex
|
||||
from strix.core.hooks import (
|
||||
BudgetExceededError,
|
||||
BudgetPausedError,
|
||||
SubagentBudgetReservedError,
|
||||
)
|
||||
from strix.core.hooks import BudgetExceededError
|
||||
from strix.core.inputs import child_initial_input
|
||||
from strix.core.sessions import (
|
||||
enforce_image_budget,
|
||||
open_agent_session,
|
||||
replace_session_items,
|
||||
seed_initial_input,
|
||||
strip_all_images_from_session,
|
||||
)
|
||||
from strix.llm.compaction import is_context_overflow, maybe_compact
|
||||
|
||||
|
||||
if TYPE_CHECKING:
|
||||
@@ -53,120 +40,6 @@ logger = logging.getLogger(__name__)
|
||||
StreamEventSink = Callable[[str, Any], None]
|
||||
|
||||
_INPUT_REJECTION_CODES = frozenset({400, 404, 422})
|
||||
_MAX_COMPACTIONS_PER_CYCLE = 2
|
||||
|
||||
|
||||
class ProviderRefusalError(AgentsException):
|
||||
"""Raised when a provider returns a structured refusal instead of an exception."""
|
||||
|
||||
|
||||
def _structured_provider_refusal(result: Any) -> str | None:
|
||||
for item in getattr(result, "new_items", ()) or ():
|
||||
raw_item = getattr(item, "raw_item", None)
|
||||
for content in getattr(raw_item, "content", ()) or ():
|
||||
if getattr(content, "type", None) != "refusal":
|
||||
continue
|
||||
refusal = getattr(content, "refusal", None)
|
||||
if isinstance(refusal, str) and refusal.strip():
|
||||
return refusal.strip()
|
||||
return "The model provider refused this request."
|
||||
return None
|
||||
|
||||
|
||||
def _run_config_model(run_config: RunConfig) -> str | None:
|
||||
return run_config.model if isinstance(run_config.model, str) else None
|
||||
|
||||
|
||||
def _agent_instructions(agent: Any) -> str:
|
||||
instructions = getattr(agent, "instructions", None)
|
||||
return instructions if isinstance(instructions, str) else ""
|
||||
|
||||
|
||||
def _agent_tools_text(agent: Any) -> str:
|
||||
parts: list[str] = []
|
||||
for tool in getattr(agent, "tools", []) or []:
|
||||
name = getattr(tool, "name", "")
|
||||
description = getattr(tool, "description", "") or ""
|
||||
schema = getattr(tool, "params_json_schema", "") or ""
|
||||
parts.append(f"{name} {description} {schema}")
|
||||
return "\n".join(parts)
|
||||
|
||||
|
||||
async def _compact_session(
|
||||
agent: Any, session: Session, run_config: RunConfig, *, force: bool
|
||||
) -> bool:
|
||||
model = _run_config_model(run_config)
|
||||
if session is None or model is None:
|
||||
return False
|
||||
return await maybe_compact(
|
||||
session,
|
||||
model=model,
|
||||
instructions=_agent_instructions(agent),
|
||||
tools_text=_agent_tools_text(agent),
|
||||
force=force,
|
||||
)
|
||||
|
||||
|
||||
_MAX_TRANSIENT_MODEL_RETRIES = 5
|
||||
_TRANSIENT_MODEL_RETRY_BASE_DELAY_S = 2.0
|
||||
_TRANSIENT_MODEL_RETRY_MAX_DELAY_S = 90.0
|
||||
|
||||
|
||||
def _model_error_status_code(exc: BaseException) -> int | None:
|
||||
code = getattr(exc, "status_code", None)
|
||||
return code if isinstance(code, int) else None
|
||||
|
||||
|
||||
def _is_transient_model_error(exc: BaseException) -> bool:
|
||||
if codex.is_content_guardrail_error(exc):
|
||||
return False
|
||||
if isinstance(
|
||||
exc, APITimeoutError | APIConnectionError | TimeoutError | ConnectionError | OSError
|
||||
):
|
||||
return True
|
||||
code = _model_error_status_code(exc)
|
||||
if code is not None:
|
||||
return bool(litellm._should_retry(code))
|
||||
return isinstance(exc, APIError)
|
||||
|
||||
|
||||
def _transient_model_retry_delay(attempt: int) -> float:
|
||||
delay = _TRANSIENT_MODEL_RETRY_BASE_DELAY_S * float(2 ** (attempt - 1))
|
||||
return min(delay, _TRANSIENT_MODEL_RETRY_MAX_DELAY_S)
|
||||
|
||||
|
||||
async def _salvage_stream_to_session(
|
||||
session: Session,
|
||||
pre_run_items: list[Any],
|
||||
stream: Any,
|
||||
agent_id: str,
|
||||
) -> None:
|
||||
"""Persist a crashed run's full history so a revived agent loses no context."""
|
||||
if stream is None:
|
||||
return
|
||||
try:
|
||||
replay = list(stream.to_input_list())
|
||||
except Exception:
|
||||
logger.exception("could not build salvage history for %s", agent_id)
|
||||
return
|
||||
desired = list(pre_run_items) + replay
|
||||
if len(desired) <= len(pre_run_items):
|
||||
return
|
||||
try:
|
||||
await replace_session_items(session, desired)
|
||||
except Exception:
|
||||
logger.exception("salvaging crashed run history failed for %s", agent_id)
|
||||
|
||||
|
||||
async def _seed_and_prepare_first_input(
|
||||
session: Session | None, initial_input: Any, *, start_parked: bool
|
||||
) -> Any:
|
||||
"""Persist the opening input up front so it survives a first-turn crash."""
|
||||
if initial_input and session is not None and not start_parked:
|
||||
with contextlib.suppress(Exception):
|
||||
if await seed_initial_input(session, initial_input):
|
||||
return []
|
||||
return initial_input
|
||||
|
||||
|
||||
async def run_agent_loop(
|
||||
@@ -191,29 +64,13 @@ async def run_agent_loop(
|
||||
)
|
||||
result: RunResultBase | None = None
|
||||
|
||||
first_cycle_input = await _seed_and_prepare_first_input(
|
||||
session, initial_input, start_parked=start_parked
|
||||
)
|
||||
|
||||
budget_stopped = coordinator.budget_stopped
|
||||
reserve_stopped = coordinator.reserve_stopped
|
||||
if budget_stopped:
|
||||
await coordinator.set_status(agent_id, "stopped")
|
||||
raise BudgetExceededError("scan budget reached")
|
||||
if reserve_stopped and context.get("parent_id") is not None:
|
||||
await coordinator.set_status(agent_id, "stopped")
|
||||
raise SubagentBudgetReservedError("scan reached the sub-agent budget reserve")
|
||||
|
||||
if reserve_stopped and start_parked and interactive and context.get("parent_id") is None:
|
||||
await coordinator.send(agent_id, _reserve_notice())
|
||||
|
||||
if not (start_parked and interactive):
|
||||
with contextlib.suppress(BudgetPausedError):
|
||||
result = await _run_until_lifecycle(
|
||||
if interactive:
|
||||
result = await _run_cycle(
|
||||
agent,
|
||||
coordinator,
|
||||
agent_id,
|
||||
initial_input=first_cycle_input,
|
||||
input_data=initial_input,
|
||||
run_config=run_config,
|
||||
context=context,
|
||||
max_turns=max_turns,
|
||||
@@ -222,14 +79,26 @@ async def run_agent_loop(
|
||||
event_sink=event_sink,
|
||||
hooks=hooks,
|
||||
)
|
||||
else:
|
||||
result = await _run_noninteractive_until_lifecycle(
|
||||
agent,
|
||||
coordinator,
|
||||
agent_id,
|
||||
initial_input=initial_input,
|
||||
run_config=run_config,
|
||||
context=context,
|
||||
max_turns=max_turns,
|
||||
session=session,
|
||||
event_sink=event_sink,
|
||||
hooks=hooks,
|
||||
)
|
||||
|
||||
if not interactive:
|
||||
return result
|
||||
|
||||
while True:
|
||||
timeout = await _plain_waiting_timeout(coordinator, agent_id)
|
||||
try:
|
||||
woke = await coordinator.wait_for_message(agent_id, timeout=timeout)
|
||||
await coordinator.wait_for_message(agent_id)
|
||||
except asyncio.CancelledError:
|
||||
return result
|
||||
|
||||
@@ -237,53 +106,20 @@ async def run_agent_loop(
|
||||
await coordinator.set_status(agent_id, "stopped")
|
||||
raise BudgetExceededError("scan budget reached")
|
||||
|
||||
if coordinator.reserve_stopped and context.get("parent_id") is not None:
|
||||
await coordinator.set_status(agent_id, "stopped")
|
||||
raise SubagentBudgetReservedError("scan reached the sub-agent budget reserve")
|
||||
|
||||
if woke:
|
||||
# Real input is real progress, so the nudge budget starts over. A bare
|
||||
# auto-resume is not: it must not hand a wedged agent a fresh budget.
|
||||
await coordinator.reset_recovery(agent_id)
|
||||
await coordinator.reset_idle_resumes(agent_id)
|
||||
else:
|
||||
idle_resumes = await coordinator.record_idle_resume(agent_id)
|
||||
if idle_resumes >= _MAX_IDLE_AUTO_RESUMES:
|
||||
logger.warning(
|
||||
"agent %s auto-resumed %d times without hearing from anyone; "
|
||||
"leaving it parked until a real message arrives",
|
||||
agent_id,
|
||||
idle_resumes,
|
||||
)
|
||||
await coordinator.park_waiting(agent_id, wait_kind="stalled")
|
||||
await _notify_parent_on_stall(coordinator, agent_id)
|
||||
continue
|
||||
logger.info("agent %s reached its waiting timeout; auto-resuming", agent_id)
|
||||
await coordinator.send(
|
||||
agent_id,
|
||||
{
|
||||
"from": "system",
|
||||
"type": "auto_resume",
|
||||
"content": "Waiting timeout reached. Resuming execution.",
|
||||
},
|
||||
interrupt=False,
|
||||
)
|
||||
|
||||
await coordinator.consume_pending(agent_id)
|
||||
with contextlib.suppress(BudgetPausedError):
|
||||
result = await _run_until_lifecycle(
|
||||
agent,
|
||||
coordinator,
|
||||
agent_id,
|
||||
initial_input=[],
|
||||
run_config=run_config,
|
||||
context=context,
|
||||
max_turns=max_turns,
|
||||
session=session,
|
||||
interactive=True,
|
||||
event_sink=event_sink,
|
||||
hooks=hooks,
|
||||
)
|
||||
result = await _run_cycle(
|
||||
agent,
|
||||
coordinator,
|
||||
agent_id,
|
||||
input_data=[],
|
||||
run_config=run_config,
|
||||
context=context,
|
||||
max_turns=max_turns,
|
||||
session=session,
|
||||
interactive=interactive,
|
||||
event_sink=event_sink,
|
||||
hooks=hooks,
|
||||
)
|
||||
|
||||
|
||||
async def spawn_child_agent(
|
||||
@@ -431,10 +267,7 @@ async def respawn_subagents(
|
||||
await coordinator.set_status(child_id, "crashed")
|
||||
|
||||
|
||||
_INTERACTIVE_TOOL_RECOVERY_LIMIT = 3
|
||||
|
||||
|
||||
async def _run_until_lifecycle(
|
||||
async def _run_noninteractive_until_lifecycle(
|
||||
agent: Any,
|
||||
coordinator: AgentCoordinator,
|
||||
agent_id: str,
|
||||
@@ -444,167 +277,21 @@ async def _run_until_lifecycle(
|
||||
context: dict[str, Any],
|
||||
max_turns: int,
|
||||
session: Session | None,
|
||||
interactive: bool,
|
||||
event_sink: StreamEventSink | None,
|
||||
hooks: RunHooks[dict[str, Any]] | None,
|
||||
) -> RunResultBase | None:
|
||||
"""Drive an agent until an explicit lifecycle tool settles its status.
|
||||
|
||||
A turn that ends without ``finish_scan``, ``agent_finish``,
|
||||
``respond_to_user``, or ``wait_for_agents`` leaves the agent ``running``:
|
||||
plain text never terminates a run and never yields to the user. Such a turn
|
||||
is nudged back into a tool call, bounded by a recovery limit.
|
||||
"""
|
||||
"""Non-chat mode keeps running until finish_scan / agent_finish settles status."""
|
||||
result: RunResultBase | None = None
|
||||
input_data: Any = initial_input
|
||||
recovery_limit = _INTERACTIVE_TOOL_RECOVERY_LIMIT if interactive else max(1, max_turns)
|
||||
invalid_final_outputs = 0
|
||||
invalid_final_output_limit = max(1, max_turns)
|
||||
|
||||
while True:
|
||||
if coordinator.budget_stopped:
|
||||
await coordinator.set_status(agent_id, "stopped")
|
||||
raise BudgetExceededError("scan budget reached")
|
||||
|
||||
if coordinator.reserve_stopped and context.get("parent_id") is not None:
|
||||
await coordinator.set_status(agent_id, "stopped")
|
||||
raise SubagentBudgetReservedError("scan reached the sub-agent budget reserve")
|
||||
|
||||
if interactive:
|
||||
result = await _run_cycle_parked(
|
||||
agent,
|
||||
coordinator,
|
||||
agent_id,
|
||||
input_data=input_data,
|
||||
run_config=run_config,
|
||||
context=context,
|
||||
max_turns=max_turns,
|
||||
session=session,
|
||||
event_sink=event_sink,
|
||||
hooks=hooks,
|
||||
)
|
||||
else:
|
||||
result = await _run_cycle(
|
||||
agent,
|
||||
coordinator,
|
||||
agent_id,
|
||||
input_data=input_data,
|
||||
run_config=run_config,
|
||||
context=context,
|
||||
max_turns=max_turns,
|
||||
session=session,
|
||||
interactive=False,
|
||||
event_sink=event_sink,
|
||||
hooks=hooks,
|
||||
)
|
||||
|
||||
status = await _agent_status(coordinator, agent_id)
|
||||
if status != "running":
|
||||
await coordinator.reset_recovery(agent_id)
|
||||
return result
|
||||
|
||||
recoveries = await coordinator.record_recovery(agent_id)
|
||||
logger.warning(
|
||||
"agent %s ended a turn without a lifecycle tool call (interactive=%s); "
|
||||
"forcing tool continuation (%d/%d): %s",
|
||||
agent_id,
|
||||
interactive,
|
||||
recoveries,
|
||||
recovery_limit,
|
||||
_final_output_preview(result),
|
||||
)
|
||||
|
||||
if recoveries >= recovery_limit:
|
||||
return await _exhausted_recovery(coordinator, agent_id, result, interactive=interactive)
|
||||
|
||||
input_data = await _append_tool_required_message(
|
||||
session=session,
|
||||
context=context,
|
||||
attempt=recoveries,
|
||||
limit=recovery_limit,
|
||||
interactive=interactive,
|
||||
)
|
||||
|
||||
|
||||
async def _exhausted_recovery(
|
||||
coordinator: AgentCoordinator,
|
||||
agent_id: str,
|
||||
result: RunResultBase | None,
|
||||
*,
|
||||
interactive: bool,
|
||||
) -> RunResultBase | None:
|
||||
"""Settle an agent that never recovered into a tool call.
|
||||
|
||||
Interactive runs park instead of dying: a human is attached and can message
|
||||
any agent, so the scan stays resumable. Autonomous runs have nobody to
|
||||
resume them, so they fail loudly.
|
||||
"""
|
||||
if not interactive:
|
||||
await coordinator.set_status(agent_id, "crashed")
|
||||
await notify_parent_on_terminal(coordinator, agent_id, "crashed")
|
||||
raise MaxTurnsExceeded(
|
||||
"Agent exhausted recovery attempts without calling finish_scan or agent_finish."
|
||||
)
|
||||
|
||||
logger.warning(
|
||||
"agent %s exhausted tool-call recovery attempts; parking until a message arrives",
|
||||
agent_id,
|
||||
)
|
||||
await coordinator.park_waiting(agent_id, wait_kind="stalled")
|
||||
# A parked child owes its parent a completion report it can no longer send. The
|
||||
# parent is an agent, not a watching human, so nothing else tells it to stop
|
||||
# waiting and it burns its full timeout on a message that is never coming.
|
||||
await _notify_parent_on_stall(coordinator, agent_id)
|
||||
return result
|
||||
|
||||
|
||||
_WAITING_AUTO_RESUME_TIMEOUT_S = 300.0
|
||||
|
||||
# An agent that parks again after every auto-resume makes no progress, so stop
|
||||
# spending a model turn per timeout and leave it parked for a real message.
|
||||
_MAX_IDLE_AUTO_RESUMES = 3
|
||||
|
||||
|
||||
async def _plain_waiting_timeout(
|
||||
coordinator: AgentCoordinator,
|
||||
agent_id: str,
|
||||
) -> float | None:
|
||||
"""Auto-resume timeout for a parked agent; None waits until a message arrives.
|
||||
|
||||
Driven by what the agent is waiting on, not by where it sits in the graph:
|
||||
the user can message any agent, so an agent awaiting a human parks
|
||||
indefinitely whether or not it is the root. Only an agent awaiting other
|
||||
agents is re-checked on a timer, and only until it has spent its idle
|
||||
budget re-parking without hearing anything.
|
||||
"""
|
||||
async with coordinator._lock:
|
||||
status = coordinator.statuses.get(agent_id)
|
||||
has_error = agent_id in coordinator.errors
|
||||
runtime = coordinator.runtimes.get(agent_id)
|
||||
gated = runtime.user_wake_required if runtime is not None else False
|
||||
wait_kind = coordinator.wait_kinds.get(agent_id)
|
||||
idle_resumes = coordinator.idle_resume_counts.get(agent_id, 0)
|
||||
if status != "waiting" or has_error or gated:
|
||||
return None
|
||||
if wait_kind != "agents" or idle_resumes >= _MAX_IDLE_AUTO_RESUMES:
|
||||
return None
|
||||
return _WAITING_AUTO_RESUME_TIMEOUT_S
|
||||
|
||||
|
||||
async def _run_cycle_parked(
|
||||
agent: Any,
|
||||
coordinator: AgentCoordinator,
|
||||
agent_id: str,
|
||||
*,
|
||||
input_data: Any,
|
||||
run_config: RunConfig,
|
||||
context: dict[str, Any],
|
||||
max_turns: int,
|
||||
session: Session | None,
|
||||
event_sink: StreamEventSink | None,
|
||||
hooks: RunHooks[dict[str, Any]] | None,
|
||||
) -> RunResultBase | None:
|
||||
"""Interactive run cycle that parks on any error instead of killing the runner."""
|
||||
try:
|
||||
return await _run_cycle(
|
||||
result = await _run_cycle(
|
||||
agent,
|
||||
coordinator,
|
||||
agent_id,
|
||||
@@ -613,17 +300,39 @@ async def _run_cycle_parked(
|
||||
context=context,
|
||||
max_turns=max_turns,
|
||||
session=session,
|
||||
interactive=True,
|
||||
interactive=False,
|
||||
event_sink=event_sink,
|
||||
hooks=hooks,
|
||||
)
|
||||
except (BudgetExceededError, BudgetPausedError, SubagentBudgetReservedError):
|
||||
raise
|
||||
except Exception as exc:
|
||||
logger.exception("error escaped the run cycle for %s; parking as failed", agent_id)
|
||||
await coordinator.set_status(agent_id, "failed", error=str(exc) or type(exc).__name__)
|
||||
await notify_parent_on_terminal(coordinator, agent_id, "failed")
|
||||
return None
|
||||
|
||||
status = await _agent_status(coordinator, agent_id)
|
||||
if status != "running":
|
||||
return result
|
||||
|
||||
invalid_final_outputs += 1
|
||||
logger.warning(
|
||||
"agent %s produced non-lifecycle final output in non-interactive mode; "
|
||||
"forcing tool continuation (%d/%d): %s",
|
||||
agent_id,
|
||||
invalid_final_outputs,
|
||||
invalid_final_output_limit,
|
||||
_final_output_preview(result),
|
||||
)
|
||||
|
||||
if invalid_final_outputs >= invalid_final_output_limit:
|
||||
await coordinator.set_status(agent_id, "crashed")
|
||||
await _notify_parent_on_crash(coordinator, agent_id, "crashed")
|
||||
raise MaxTurnsExceeded(
|
||||
"Agent exhausted non-interactive recovery attempts without calling "
|
||||
"finish_scan or agent_finish."
|
||||
)
|
||||
|
||||
input_data = await _append_noninteractive_tool_required_message(
|
||||
session=session,
|
||||
context=context,
|
||||
attempt=invalid_final_outputs,
|
||||
limit=invalid_final_output_limit,
|
||||
)
|
||||
|
||||
|
||||
async def _run_cycle( # noqa: PLR0912, PLR0915
|
||||
@@ -641,11 +350,7 @@ async def _run_cycle( # noqa: PLR0912, PLR0915
|
||||
hooks: RunHooks[dict[str, Any]] | None,
|
||||
) -> RunResultBase | None:
|
||||
image_strips = 0
|
||||
compactions = 0
|
||||
model_retries = 0
|
||||
while True:
|
||||
stream: Any = None
|
||||
pre_run_items: list[Any] = []
|
||||
try:
|
||||
await coordinator.mark_running(agent_id)
|
||||
if session is not None:
|
||||
@@ -655,12 +360,6 @@ async def _run_cycle( # noqa: PLR0912, PLR0915
|
||||
await enforce_image_budget(session, max_images)
|
||||
except Exception:
|
||||
logger.exception("image-budget enforcement failed for %s", agent_id)
|
||||
try:
|
||||
await _compact_session(agent, session, run_config, force=False)
|
||||
except Exception:
|
||||
logger.exception("proactive compaction failed for %s", agent_id)
|
||||
with contextlib.suppress(Exception):
|
||||
pre_run_items = list(await session.get_items())
|
||||
stream = Runner.run_streamed(
|
||||
agent,
|
||||
input=input_data,
|
||||
@@ -681,9 +380,9 @@ async def _run_cycle( # noqa: PLR0912, PLR0915
|
||||
logger.exception("stream event sink failed for %s", agent_id)
|
||||
if stream.run_loop_exception is not None:
|
||||
raise stream.run_loop_exception
|
||||
if refusal := _structured_provider_refusal(stream):
|
||||
raise ProviderRefusalError(refusal)
|
||||
except (BudgetExceededError, BudgetPausedError, SubagentBudgetReservedError):
|
||||
except BudgetExceededError:
|
||||
# A RuntimeError subclass: re-raise explicitly so it is never
|
||||
# mistaken for the LiteLLM "after shutdown" race below.
|
||||
raise
|
||||
except RuntimeError as stream_exc:
|
||||
if "after shutdown" not in str(stream_exc):
|
||||
@@ -702,15 +401,6 @@ async def _run_cycle( # noqa: PLR0912, PLR0915
|
||||
)
|
||||
finally:
|
||||
await coordinator.detach_stream(agent_id, stream)
|
||||
except BudgetPausedError as exc:
|
||||
logger.info("agent %s paused at the scan budget limit: %s", agent_id, exc)
|
||||
await coordinator.pause_for_budget(agent_id)
|
||||
raise
|
||||
except SubagentBudgetReservedError as exc:
|
||||
logger.info("sub-agent %s stopped at the budget reserve: %s", agent_id, exc)
|
||||
await coordinator.set_status(agent_id, "stopped")
|
||||
await _notify_root_on_budget_reserve(coordinator)
|
||||
raise
|
||||
except BudgetExceededError as exc:
|
||||
logger.info(
|
||||
"agent %s reached the scan budget limit; stopping the scan: %s", agent_id, exc
|
||||
@@ -738,48 +428,6 @@ async def _run_cycle( # noqa: PLR0912, PLR0915
|
||||
)
|
||||
input_data = []
|
||||
continue
|
||||
if (
|
||||
compactions < _MAX_COMPACTIONS_PER_CYCLE
|
||||
and session is not None
|
||||
and is_context_overflow(exc)
|
||||
):
|
||||
try:
|
||||
compacted = await _compact_session(agent, session, run_config, force=True)
|
||||
except Exception:
|
||||
logger.exception("overflow compaction recovery failed for %s", agent_id)
|
||||
compacted = False
|
||||
if compacted:
|
||||
compactions += 1
|
||||
logger.info(
|
||||
"Compacted %s session after context overflow; retrying (%d)",
|
||||
agent_id,
|
||||
compactions,
|
||||
)
|
||||
input_data = []
|
||||
continue
|
||||
if model_retries < _MAX_TRANSIENT_MODEL_RETRIES and _is_transient_model_error(exc):
|
||||
model_retries += 1
|
||||
delay = _transient_model_retry_delay(model_retries)
|
||||
logger.warning(
|
||||
"transient model/provider error for %s; replaying turn "
|
||||
"(attempt %d/%d, backoff %.1fs): %r",
|
||||
agent_id,
|
||||
model_retries,
|
||||
_MAX_TRANSIENT_MODEL_RETRIES,
|
||||
delay,
|
||||
exc,
|
||||
)
|
||||
await asyncio.sleep(delay)
|
||||
if session is not None:
|
||||
input_data = []
|
||||
continue
|
||||
if session is not None:
|
||||
await _salvage_stream_to_session(session, pre_run_items, stream, agent_id)
|
||||
if isinstance(exc, ProviderRefusalError):
|
||||
logger.warning("agent %s refused by the model provider: %s", agent_id, exc)
|
||||
await coordinator.set_status(agent_id, "failed", error=str(exc))
|
||||
await notify_parent_on_terminal(coordinator, agent_id, "failed")
|
||||
return None
|
||||
if not interactive:
|
||||
raise
|
||||
if isinstance(exc, MaxTurnsExceeded):
|
||||
@@ -789,11 +437,31 @@ async def _run_cycle( # noqa: PLR0912, PLR0915
|
||||
else:
|
||||
status = "crashed"
|
||||
logger.exception("agent run failed for %s; parking as %s", agent_id, status)
|
||||
await coordinator.set_status(agent_id, status, error=str(exc) or type(exc).__name__)
|
||||
await notify_parent_on_terminal(coordinator, agent_id, status)
|
||||
await coordinator.set_status(agent_id, status)
|
||||
await _notify_parent_on_crash(coordinator, agent_id, status)
|
||||
if context.get("parent_id") is None and status in {"failed", "crashed"}:
|
||||
raise
|
||||
return None
|
||||
else:
|
||||
return cast("RunResultBase | None", stream)
|
||||
await _settle_run_result(coordinator, agent_id, interactive)
|
||||
return stream
|
||||
|
||||
|
||||
async def _settle_run_result(
|
||||
coordinator: AgentCoordinator,
|
||||
agent_id: str,
|
||||
interactive: bool,
|
||||
) -> None:
|
||||
async with coordinator._lock:
|
||||
current_status = coordinator.statuses.get(agent_id)
|
||||
|
||||
if current_status != "running":
|
||||
return
|
||||
|
||||
if not interactive:
|
||||
return
|
||||
|
||||
await coordinator.set_status(agent_id, "waiting")
|
||||
|
||||
|
||||
async def _agent_status(coordinator: AgentCoordinator, agent_id: str) -> Status | None:
|
||||
@@ -811,37 +479,23 @@ def _final_output_preview(result: RunResultBase | None) -> str:
|
||||
return text[:300]
|
||||
|
||||
|
||||
async def _append_tool_required_message(
|
||||
async def _append_noninteractive_tool_required_message(
|
||||
*,
|
||||
session: Session | None,
|
||||
context: dict[str, Any],
|
||||
attempt: int,
|
||||
limit: int,
|
||||
interactive: bool,
|
||||
) -> list[dict[str, str]]:
|
||||
finish_tool = "finish_scan" if context.get("parent_id") is None else "agent_finish"
|
||||
if interactive:
|
||||
message = (
|
||||
"Your previous message ended a turn without a tool call. Plain text never ends "
|
||||
"execution and never hands control to the user: it is shown to the user, and the "
|
||||
"run continues. Continue immediately and call exactly one tool. "
|
||||
"If you have something to tell the user and nothing to do until they reply, "
|
||||
"call respond_to_user. "
|
||||
"If you are blocked waiting for another agent, call wait_for_agents. "
|
||||
f"If the whole engagement is complete, call {finish_tool}. "
|
||||
"Otherwise use the appropriate execution or planning tool. "
|
||||
f"This is recovery attempt {attempt}/{limit}."
|
||||
)
|
||||
else:
|
||||
message = (
|
||||
"Your previous response ended the autonomous Strix run without a lifecycle tool "
|
||||
"call. That is invalid in non-interactive mode; plain text final answers are "
|
||||
"ignored. Continue immediately and call exactly one tool. "
|
||||
f"If your work is complete, call {finish_tool}. "
|
||||
"If you are blocked waiting for another agent, call wait_for_agents. "
|
||||
"Otherwise use the appropriate execution or planning tool. "
|
||||
f"This is recovery attempt {attempt}/{limit}."
|
||||
)
|
||||
message = (
|
||||
"Your previous response ended the autonomous Strix run without a lifecycle tool call. "
|
||||
"That is invalid in non-interactive mode; plain text final answers are ignored. "
|
||||
"Continue immediately and call exactly one tool. "
|
||||
f"If your work is complete, call {finish_tool}. "
|
||||
"If you are blocked waiting for another agent, call wait_for_message. "
|
||||
"Otherwise use the appropriate execution or planning tool. "
|
||||
f"This is recovery attempt {attempt}/{limit}."
|
||||
)
|
||||
item = {"role": "user", "content": message}
|
||||
if session is None:
|
||||
return [item]
|
||||
@@ -850,123 +504,32 @@ async def _append_tool_required_message(
|
||||
return []
|
||||
|
||||
|
||||
_TERMINAL_NOTICE = {
|
||||
"completed": (
|
||||
"[Agent completed] {name} ({agent_id}) finished and is no longer running, but it "
|
||||
"sent no completion report. Stop waiting on this child; ask it directly if you "
|
||||
"need its results."
|
||||
),
|
||||
"crashed": (
|
||||
"[Agent crash] {name} ({agent_id}) terminated unexpectedly. "
|
||||
"Stop waiting on this child unless you want to message it again."
|
||||
),
|
||||
"failed": (
|
||||
"[Agent failed] {name} ({agent_id}) stopped with an error and will not "
|
||||
"send a completion report. Stop waiting on this child unless you want to "
|
||||
"message it again."
|
||||
),
|
||||
"stopped": (
|
||||
"[Agent stopped] {name} ({agent_id}) was stopped before finishing (turn limit "
|
||||
"or an explicit stop). It will not send a completion report, so stop waiting "
|
||||
"on this child; account for its unfinished subtask and continue."
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
_STALL_NOTICE = (
|
||||
"[Agent stalled] {name} ({agent_id}) kept ending turns without a tool call and is "
|
||||
"parked until it receives a message. It will not send a completion report on its "
|
||||
"own: either message it with a concrete next step to unblock it, or stop waiting on "
|
||||
"it and account for its unfinished subtask."
|
||||
)
|
||||
|
||||
|
||||
async def _notify_parent_on_stall(
|
||||
coordinator: AgentCoordinator,
|
||||
agent_id: str,
|
||||
) -> None:
|
||||
"""Tell the parent that a child parked mid-task, so it stops waiting blindly."""
|
||||
async with coordinator._lock:
|
||||
parent = coordinator.parent_of.get(agent_id)
|
||||
name = coordinator.names.get(agent_id, agent_id)
|
||||
if parent is None:
|
||||
return
|
||||
await coordinator.send(
|
||||
parent,
|
||||
{
|
||||
"from": agent_id,
|
||||
"type": "stalled",
|
||||
"priority": "high",
|
||||
"content": _STALL_NOTICE.format(name=name, agent_id=agent_id),
|
||||
},
|
||||
interrupt=False,
|
||||
)
|
||||
|
||||
|
||||
async def notify_parent_on_terminal(
|
||||
async def _notify_parent_on_crash(
|
||||
coordinator: AgentCoordinator,
|
||||
agent_id: str,
|
||||
status: str,
|
||||
) -> None:
|
||||
template = _TERMINAL_NOTICE.get(status)
|
||||
if template is None:
|
||||
if status != "crashed":
|
||||
return
|
||||
async with coordinator._lock:
|
||||
parent = coordinator.parent_of.get(agent_id)
|
||||
name = coordinator.names.get(agent_id, agent_id)
|
||||
if parent is None:
|
||||
return
|
||||
if not await coordinator.claim_parent_notice(agent_id):
|
||||
return
|
||||
await coordinator.send(
|
||||
parent,
|
||||
{
|
||||
"from": agent_id,
|
||||
"type": status,
|
||||
"type": "crash",
|
||||
"priority": "high",
|
||||
"content": template.format(name=name, agent_id=agent_id),
|
||||
"content": (
|
||||
f"[Agent crash] {name} ({agent_id}) terminated unexpectedly. "
|
||||
"Stop waiting on this child unless you want to message it again."
|
||||
),
|
||||
},
|
||||
interrupt=False,
|
||||
)
|
||||
|
||||
|
||||
def _reserve_notice() -> dict[str, Any]:
|
||||
return {
|
||||
"from": "system",
|
||||
"type": "budget_reserve_stop",
|
||||
"priority": "high",
|
||||
"content": (
|
||||
"[Budget reserve] The scan has reached the sub-agent budget reserve: every "
|
||||
"sub-agent is being force-stopped as soon as its in-flight turn completes, and "
|
||||
"none will send a completion report. Their confirmed vulnerabilities are "
|
||||
"already filed as they were found. Do not wait on any sub-agents and do not "
|
||||
"spawn new ones — wrap up now and call finish_scan."
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def _notify_root_on_budget_reserve(coordinator: AgentCoordinator) -> None:
|
||||
root = await coordinator.claim_reserve_notification()
|
||||
if root is None:
|
||||
return
|
||||
await coordinator.send(root, _reserve_notice())
|
||||
|
||||
|
||||
async def _notify_parent_on_exit(
|
||||
coordinator: AgentCoordinator,
|
||||
agent_id: str,
|
||||
) -> None:
|
||||
"""Backstop for a child whose loop ended without telling its parent.
|
||||
|
||||
Every terminal state counts, including ``completed``: a child that skips its
|
||||
completion report leaves the parent waiting on a message nobody will send.
|
||||
"""
|
||||
status = await _agent_status(coordinator, agent_id)
|
||||
if status is None:
|
||||
return
|
||||
await notify_parent_on_terminal(coordinator, agent_id, status)
|
||||
|
||||
|
||||
async def _start_child_runner(
|
||||
*,
|
||||
parent_ctx: dict[str, Any],
|
||||
@@ -1018,11 +581,6 @@ async def _start_child_runner(
|
||||
)
|
||||
except BudgetExceededError:
|
||||
logger.info("child %s stopped after reaching the scan budget limit", child_id)
|
||||
except SubagentBudgetReservedError:
|
||||
logger.info("child %s stopped at the sub-agent budget reserve", child_id)
|
||||
finally:
|
||||
if not coordinator.is_shutting_down:
|
||||
await _notify_parent_on_exit(coordinator, child_id)
|
||||
|
||||
task_handle = asyncio.create_task(_child_loop(), name=f"agent-{name}-{child_id}")
|
||||
await coordinator.attach_runtime(child_id, task=task_handle)
|
||||
|
||||
+3
-202
@@ -14,210 +14,26 @@ from strix.report.state import get_global_report_state
|
||||
if TYPE_CHECKING:
|
||||
from agents import RunContextWrapper
|
||||
from agents.agent import Agent
|
||||
from agents.items import ModelResponse, TResponseInputItem
|
||||
from agents.items import ModelResponse
|
||||
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
_STAGE_LABELS: tuple[str, ...] = ("NOTICE", "URGENT", "CRITICAL")
|
||||
_TURN_WARN_BANDS: tuple[float, ...] = (0.70, 0.85, 0.95)
|
||||
_ROOT_BUDGET_WARN_BANDS: tuple[float, ...] = (0.70, 0.85, 0.95)
|
||||
_SUBAGENT_BUDGET_WARN_BANDS: tuple[float, ...] = (0.75, 0.80, 0.85)
|
||||
_SUBAGENT_BUDGET_RESERVE = 0.90
|
||||
|
||||
|
||||
class BudgetExceededError(RuntimeError):
|
||||
"""Raised when the accumulated LLM cost reaches the configured budget."""
|
||||
|
||||
|
||||
class SubagentBudgetReservedError(RuntimeError):
|
||||
"""Raised to stop a single sub-agent once the reserve threshold is crossed."""
|
||||
|
||||
|
||||
class BudgetPausedError(RuntimeError):
|
||||
"""Raised to park one agent when an interactive scan reaches its budget."""
|
||||
|
||||
|
||||
def recomputed_budget_flags(
|
||||
cost: float,
|
||||
max_budget_usd: float | None,
|
||||
*,
|
||||
interactive: bool,
|
||||
) -> tuple[bool, bool]:
|
||||
"""Return the (budget_stopped, reserve_stopped) flags a resumed scan should carry."""
|
||||
if max_budget_usd is None:
|
||||
return False, False
|
||||
if interactive:
|
||||
return False, False
|
||||
budget_stopped = cost >= max_budget_usd
|
||||
reserve_stopped = cost >= max_budget_usd * _SUBAGENT_BUDGET_RESERVE
|
||||
return budget_stopped, reserve_stopped
|
||||
|
||||
|
||||
def _crossed_stage(fraction: float, bands: tuple[float, ...]) -> int | None:
|
||||
crossed: int | None = None
|
||||
for index, band in enumerate(bands):
|
||||
if fraction >= band:
|
||||
crossed = index
|
||||
return crossed
|
||||
|
||||
|
||||
_ROOT_DIRECTIVES: tuple[str, ...] = (
|
||||
(
|
||||
"As the root agent, begin planning your wind-down of the whole scan: avoid "
|
||||
"starting large new lines of investigation, and keep your required objectives on "
|
||||
"track so you can call finish_scan comfortably before the limit."
|
||||
),
|
||||
(
|
||||
"As the root agent, prioritize wrapping up the whole scan now: stop opening new "
|
||||
"lines of investigation, close out only what is essential, and move toward calling "
|
||||
"finish_scan to compile and deliver the final report."
|
||||
),
|
||||
(
|
||||
"As the root agent, STOP all other work on the whole scan and finish immediately: "
|
||||
"secure your findings and call finish_scan now — anything left unfinished when the "
|
||||
"limit is hit is discarded."
|
||||
),
|
||||
)
|
||||
_SUBAGENT_DIRECTIVES: tuple[str, ...] = (
|
||||
(
|
||||
"As a sub-agent, begin planning your wind-down: avoid starting large new subtasks, "
|
||||
"and if you are close to a confirmed, validated vulnerability, drive it to a result "
|
||||
"you can report."
|
||||
),
|
||||
(
|
||||
"As a sub-agent, prioritize wrapping up your task now: report any confirmed, "
|
||||
"validated vulnerability, finish work that is nearly done rather than starting "
|
||||
"anything new, and prepare to call agent_finish."
|
||||
),
|
||||
(
|
||||
"As a sub-agent, STOP all other work and finish immediately: report any confirmed "
|
||||
"vulnerability right now and call agent_finish to hand your results back to your "
|
||||
"parent before you are cut off."
|
||||
),
|
||||
)
|
||||
|
||||
|
||||
def _wrapup_directive(context: RunContextWrapper[dict[str, Any]], stage: int) -> str:
|
||||
is_root = context.context.get("parent_id") is None
|
||||
directives = _ROOT_DIRECTIVES if is_root else _SUBAGENT_DIRECTIVES
|
||||
return directives[stage]
|
||||
|
||||
|
||||
def _urgency(stage: int) -> str:
|
||||
return _STAGE_LABELS[stage]
|
||||
|
||||
|
||||
class ReportUsageHooks(RunHooks[dict[str, Any]]):
|
||||
"""Persist SDK-native usage and warn/stop as turn and cost budgets are consumed."""
|
||||
"""Persist SDK-native usage after every model response."""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
*,
|
||||
model: str,
|
||||
max_budget_usd: float | None = None,
|
||||
max_turns: int | None = None,
|
||||
interactive: bool = False,
|
||||
) -> None:
|
||||
def __init__(self, *, model: str, max_budget_usd: float | None = None) -> None:
|
||||
if max_budget_usd is not None and (
|
||||
not math.isfinite(max_budget_usd) or max_budget_usd <= 0
|
||||
):
|
||||
raise ValueError("max_budget_usd must be a finite number greater than 0")
|
||||
if max_turns is not None and max_turns <= 0:
|
||||
raise ValueError("max_turns must be a positive integer")
|
||||
self._model = model
|
||||
self._max_budget_usd = max_budget_usd
|
||||
self._budget_increment = max_budget_usd
|
||||
self._max_turns = max_turns
|
||||
self._interactive = interactive
|
||||
|
||||
def extend_budget(self) -> None:
|
||||
if self._max_budget_usd is None or self._budget_increment is None:
|
||||
return
|
||||
self._max_budget_usd += self._budget_increment
|
||||
|
||||
async def on_llm_start(
|
||||
self,
|
||||
context: RunContextWrapper[dict[str, Any]],
|
||||
agent: Agent[dict[str, Any]], # noqa: ARG002
|
||||
system_prompt: str | None, # noqa: ARG002
|
||||
input_items: list[TResponseInputItem],
|
||||
) -> None:
|
||||
try:
|
||||
self._maybe_warn_turns(context, input_items)
|
||||
self._maybe_warn_budget(context, input_items)
|
||||
except Exception:
|
||||
logger.exception("budget/turn warning injection failed")
|
||||
|
||||
def _maybe_warn_turns(
|
||||
self,
|
||||
context: RunContextWrapper[dict[str, Any]],
|
||||
input_items: list[TResponseInputItem],
|
||||
) -> None:
|
||||
if not self._max_turns:
|
||||
return
|
||||
usage = getattr(context, "usage", None)
|
||||
requests = getattr(usage, "requests", None)
|
||||
if not isinstance(requests, int):
|
||||
return
|
||||
turns_used = requests + 1
|
||||
stage = _crossed_stage(turns_used / self._max_turns, _TURN_WARN_BANDS)
|
||||
if stage is None:
|
||||
return
|
||||
remaining = max(self._max_turns - turns_used, 0)
|
||||
pct = round(100 * turns_used / self._max_turns)
|
||||
content = (
|
||||
f"[{_urgency(stage)}] Turn budget: {turns_used}/{self._max_turns} used ({pct}%). "
|
||||
f"About {remaining} turn(s) remain before this agent is force-stopped and any "
|
||||
f"in-progress work is discarded. {_wrapup_directive(context, stage)}"
|
||||
)
|
||||
input_items.append({"role": "user", "content": content})
|
||||
|
||||
def _maybe_warn_budget(
|
||||
self,
|
||||
context: RunContextWrapper[dict[str, Any]],
|
||||
input_items: list[TResponseInputItem],
|
||||
) -> None:
|
||||
if self._max_budget_usd is None:
|
||||
return
|
||||
report_state = get_global_report_state()
|
||||
if report_state is None:
|
||||
return
|
||||
cost = report_state.get_total_llm_cost()
|
||||
is_root = context.context.get("parent_id") is None
|
||||
if self._interactive:
|
||||
bands = _ROOT_BUDGET_WARN_BANDS
|
||||
else:
|
||||
bands = _ROOT_BUDGET_WARN_BANDS if is_root else _SUBAGENT_BUDGET_WARN_BANDS
|
||||
stage = _crossed_stage(cost / self._max_budget_usd, bands)
|
||||
if stage is None:
|
||||
return
|
||||
pct = round(100 * cost / self._max_budget_usd)
|
||||
reserve_pct = round(_SUBAGENT_BUDGET_RESERVE * 100)
|
||||
if self._interactive:
|
||||
content = (
|
||||
f"[{_urgency(stage)}] Scan cost budget: ${cost:.2f}/${self._max_budget_usd:.2f} "
|
||||
f"spent ({pct}%). This budget is shared across every agent in the scan; when it "
|
||||
"is reached all agents are paused until the user chooses to continue. "
|
||||
f"{_wrapup_directive(context, stage)}"
|
||||
)
|
||||
elif is_root:
|
||||
content = (
|
||||
f"[{_urgency(stage)}] Scan cost budget: ${cost:.2f}/${self._max_budget_usd:.2f} "
|
||||
f"spent ({pct}%). This budget is shared across every agent in the scan; when it "
|
||||
"is reached the whole scan is stopped immediately, and sub-agents are stopped at "
|
||||
f"{reserve_pct}% to reserve the remainder for your final report. "
|
||||
f"{_wrapup_directive(context, stage)}"
|
||||
)
|
||||
else:
|
||||
content = (
|
||||
f"[{_urgency(stage)}] Scan cost budget: ${cost:.2f}/${self._max_budget_usd:.2f} "
|
||||
f"spent ({pct}%). This budget is shared across every agent in the scan; "
|
||||
f"sub-agents are stopped at {reserve_pct}% to leave the remainder for the root "
|
||||
f"agent's final report. {_wrapup_directive(context, stage)}"
|
||||
)
|
||||
input_items.append({"role": "user", "content": content})
|
||||
|
||||
async def on_llm_end(
|
||||
self,
|
||||
@@ -250,21 +66,6 @@ class ReportUsageHooks(RunHooks[dict[str, Any]]):
|
||||
if self._max_budget_usd is not None:
|
||||
cost = report_state.get_total_llm_cost()
|
||||
if cost >= self._max_budget_usd:
|
||||
if self._interactive:
|
||||
raise BudgetPausedError(
|
||||
f"Scan budget of ${self._max_budget_usd:.2f} reached "
|
||||
f"(spent ${cost:.4f}); pausing until the user continues"
|
||||
)
|
||||
raise BudgetExceededError(
|
||||
f"Token budget of ${self._max_budget_usd:.2f} exceeded (spent ${cost:.4f})"
|
||||
)
|
||||
is_root = ctx.get("parent_id") is None
|
||||
if not self._interactive and not is_root:
|
||||
reserve_limit = self._max_budget_usd * _SUBAGENT_BUDGET_RESERVE
|
||||
if cost >= reserve_limit:
|
||||
raise SubagentBudgetReservedError(
|
||||
f"Sub-agent budget reserve reached: spent ${cost:.4f} of "
|
||||
f"${self._max_budget_usd:.2f} "
|
||||
f"(>= {round(_SUBAGENT_BUDGET_RESERVE * 100)}% reserve); stopping this "
|
||||
"sub-agent so the root agent can finish the scan."
|
||||
)
|
||||
|
||||
+6
-57
@@ -10,9 +10,6 @@ from openai.types.shared import Reasoning
|
||||
|
||||
from strix.config.models import (
|
||||
DEFAULT_MODEL_RETRY,
|
||||
bedrock_route_supports_prompt_caching,
|
||||
is_bedrock_route,
|
||||
is_claude_model,
|
||||
is_known_openai_bare_model,
|
||||
model_supports_reasoning,
|
||||
request_timeout_extra_args,
|
||||
@@ -24,6 +21,9 @@ if TYPE_CHECKING:
|
||||
from strix.config.settings import ReasoningEffort
|
||||
|
||||
|
||||
DEFAULT_MAX_TURNS = 500
|
||||
|
||||
|
||||
def _accepts_required_tool_choice(model_name: str | None) -> bool:
|
||||
name = (model_name or "").strip().lower()
|
||||
for prefix in ("litellm/", "any-llm/"):
|
||||
@@ -59,11 +59,8 @@ def build_root_task(scan_config: dict[str, Any]) -> str:
|
||||
)
|
||||
elif ttype == "local_code":
|
||||
path = details.get("target_path", "unknown")
|
||||
sections["Local Codebases"].append(
|
||||
f"- {path} (available at: {workspace_path}; "
|
||||
"this is the user's real directory, mounted live and writable — "
|
||||
".git/.agents/.codex are read-only)"
|
||||
)
|
||||
suffix = ", read-only mount" if details.get("mount") else ""
|
||||
sections["Local Codebases"].append(f"- {path} (available at: {workspace_path}{suffix})")
|
||||
elif ttype == "web_application":
|
||||
sections["URLs"].append(f"- {details.get('target_url', '')}")
|
||||
elif ttype == "ip_address":
|
||||
@@ -131,15 +128,12 @@ def make_model_settings(
|
||||
model_name: str,
|
||||
force_required_tool_choice: bool = False,
|
||||
request_timeout: float | None = None,
|
||||
prompt_cache: bool = True,
|
||||
extra_headers: dict[str, str] | None = None,
|
||||
) -> ModelSettings:
|
||||
model_settings = ModelSettings(
|
||||
parallel_tool_calls=False,
|
||||
retry=DEFAULT_MODEL_RETRY,
|
||||
include_usage=True,
|
||||
extra_args=request_timeout_extra_args(request_timeout),
|
||||
extra_headers=dict(extra_headers) if extra_headers else None,
|
||||
)
|
||||
if (
|
||||
reasoning_effort is not None
|
||||
@@ -147,58 +141,13 @@ def make_model_settings(
|
||||
and model_supports_reasoning(model_name)
|
||||
):
|
||||
model_settings = model_settings.resolve(
|
||||
_reasoning_settings(reasoning_effort, model_settings.extra_args),
|
||||
ModelSettings(reasoning=Reasoning(effort=reasoning_effort)),
|
||||
)
|
||||
if force_required_tool_choice and _accepts_required_tool_choice(model_name):
|
||||
model_settings = model_settings.resolve(ModelSettings(tool_choice="required"))
|
||||
|
||||
cache_extra_args = _prompt_cache_extra_args(model_name) if prompt_cache else None
|
||||
if cache_extra_args:
|
||||
model_settings = model_settings.resolve(
|
||||
ModelSettings(
|
||||
extra_args={**(model_settings.extra_args or {}), **cache_extra_args},
|
||||
),
|
||||
)
|
||||
return model_settings
|
||||
|
||||
|
||||
def _reasoning_settings(
|
||||
effort: ReasoningEffort,
|
||||
extra_args: dict[str, Any] | None,
|
||||
) -> ModelSettings:
|
||||
"""``max`` is not in the OpenAI SDK's ``Reasoning.effort`` enum, so send it as
|
||||
a raw body field instead — also keeping it clear of LiteLLM's DeepSeek mapping,
|
||||
which collapses every ``reasoning_effort`` level to plain thinking-enabled.
|
||||
Providers that don't support ``max`` reject the request.
|
||||
"""
|
||||
if effort != "max":
|
||||
return ModelSettings(reasoning=Reasoning(effort=effort))
|
||||
return ModelSettings(
|
||||
extra_args={**(extra_args or {}), "extra_body": {"reasoning_effort": "max"}},
|
||||
)
|
||||
|
||||
|
||||
def _prompt_cache_extra_args(model_name: str) -> dict[str, Any] | None:
|
||||
"""LiteLLM ``cache_control_injection_points`` for Claude prompt caching.
|
||||
|
||||
System prompt + rolling last-message breakpoint everywhere; ``tool_config``
|
||||
only on Bedrock Converse (the only route whose LiteLLM transform consumes
|
||||
it — elsewhere it leaks onto the wire and native Anthropic 400s). Unmapped
|
||||
Bedrock models get no points at all: Bedrock rejects the passed-through
|
||||
field outright.
|
||||
"""
|
||||
if not is_claude_model(model_name):
|
||||
return None
|
||||
if is_bedrock_route(model_name) and not bedrock_route_supports_prompt_caching(model_name):
|
||||
return None
|
||||
|
||||
points: list[dict[str, Any]] = [{"location": "message", "role": "system"}]
|
||||
if is_bedrock_route(model_name):
|
||||
points.append({"location": "tool_config"})
|
||||
points.append({"location": "message", "index": -1})
|
||||
return {"cache_control_injection_points": points}
|
||||
|
||||
|
||||
def child_initial_input(
|
||||
*,
|
||||
name: str,
|
||||
|
||||
+5
-58
@@ -3,12 +3,10 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import contextlib
|
||||
import io
|
||||
import json
|
||||
import logging
|
||||
import uuid
|
||||
from collections.abc import Callable
|
||||
from pathlib import Path
|
||||
from typing import TYPE_CHECKING, Any
|
||||
|
||||
from agents import RunConfig
|
||||
@@ -23,7 +21,6 @@ from strix.config.models import (
|
||||
configure_sdk_model_defaults,
|
||||
uses_chat_completions_tool_schema,
|
||||
)
|
||||
from strix.config.settings import DEFAULT_MAX_TURNS
|
||||
from strix.core.agents import AgentCoordinator
|
||||
from strix.core.execution import (
|
||||
respawn_subagents,
|
||||
@@ -32,29 +29,23 @@ from strix.core.execution import (
|
||||
from strix.core.execution import (
|
||||
spawn_child_agent as start_child_agent,
|
||||
)
|
||||
from strix.core.hooks import BudgetExceededError, ReportUsageHooks, recomputed_budget_flags
|
||||
from strix.core.hooks import BudgetExceededError, ReportUsageHooks
|
||||
from strix.core.inputs import (
|
||||
DEFAULT_MAX_TURNS,
|
||||
build_root_task,
|
||||
build_scope_context,
|
||||
make_model_settings,
|
||||
)
|
||||
from strix.core.paths import run_dir_for, runtime_state_dir
|
||||
from strix.core.sessions import open_agent_session
|
||||
from strix.report.state import get_global_report_state
|
||||
from strix.runtime import session_manager
|
||||
from strix.telemetry.logging import set_scan_id, setup_scan_logging
|
||||
from strix.tools.output_store import (
|
||||
WORKSPACE_SPILL_DIR,
|
||||
configure_spill_writer,
|
||||
)
|
||||
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from agents.memory import SQLiteSession
|
||||
from agents.result import RunResultBase
|
||||
|
||||
from strix.runtime.status import StatusSink
|
||||
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
@@ -122,7 +113,6 @@ async def run_strix_scan(
|
||||
event_sink: StreamEventSink | None = None,
|
||||
root_instructions_override: str | None = None,
|
||||
extra_system_prompt_context: dict[str, Any] | None = None,
|
||||
status_sink: StatusSink | None = None,
|
||||
) -> RunResultBase | None:
|
||||
"""Run or resume one Strix scan against a sandbox.
|
||||
|
||||
@@ -132,11 +122,6 @@ async def run_strix_scan(
|
||||
context before prompt rendering. Child agents keep the standard scan prompt
|
||||
and context.
|
||||
"""
|
||||
|
||||
def report(phase: str) -> None:
|
||||
if status_sink is not None:
|
||||
status_sink(phase)
|
||||
|
||||
if scan_id is None:
|
||||
scan_id = f"scan-{uuid.uuid4().hex[:8]}"
|
||||
|
||||
@@ -194,18 +179,6 @@ async def run_strix_scan(
|
||||
f"Cannot resume scan {scan_id}: missing SDK session database at {agents_db}",
|
||||
)
|
||||
await coordinator.restore(snap)
|
||||
report_state = get_global_report_state()
|
||||
if report_state is not None:
|
||||
budget_stopped, reserve_stopped = recomputed_budget_flags(
|
||||
report_state.get_total_llm_cost(),
|
||||
max_budget_usd,
|
||||
interactive=interactive,
|
||||
)
|
||||
await coordinator.reset_budget_stops(
|
||||
budget_stopped=budget_stopped,
|
||||
reserve_stopped=reserve_stopped,
|
||||
budget_paused=interactive and coordinator.budget_paused,
|
||||
)
|
||||
for aid, parent in coordinator.parent_of.items():
|
||||
if parent is None:
|
||||
root_id = aid
|
||||
@@ -227,25 +200,9 @@ async def run_strix_scan(
|
||||
scan_id,
|
||||
image=image,
|
||||
local_sources=local_sources or [],
|
||||
status_sink=status_sink,
|
||||
)
|
||||
report("Waiting for the first model response")
|
||||
logger.info("Sandbox ready for scan %s", scan_id)
|
||||
|
||||
sandbox_session = bundle["session"]
|
||||
|
||||
async def _spill_to_workspace(output_id: str, text: str) -> str | None:
|
||||
"""Write an oversized tool result into the sandbox; return its path or None."""
|
||||
path = f"{WORKSPACE_SPILL_DIR}/{output_id}.txt"
|
||||
try:
|
||||
await sandbox_session.write(Path(path), io.BytesIO(text.encode("utf-8")))
|
||||
except Exception:
|
||||
logger.exception("failed to spill tool output to sandbox workspace")
|
||||
return None
|
||||
return path
|
||||
|
||||
configure_spill_writer(_spill_to_workspace)
|
||||
|
||||
sessions_to_close: list[SQLiteSession] = []
|
||||
|
||||
try:
|
||||
@@ -259,8 +216,6 @@ async def run_strix_scan(
|
||||
model_name=resolved_model,
|
||||
force_required_tool_choice=settings.llm.force_required_tool_choice,
|
||||
request_timeout=settings.llm.timeout,
|
||||
prompt_cache=settings.llm.prompt_cache,
|
||||
extra_headers=settings.llm.extra_headers,
|
||||
)
|
||||
run_config = RunConfig(
|
||||
model=resolved_model,
|
||||
@@ -269,14 +224,7 @@ async def run_strix_scan(
|
||||
sandbox=SandboxRunConfig(client=bundle["client"], session=bundle["session"]),
|
||||
trace_include_sensitive_data=False,
|
||||
)
|
||||
hooks = ReportUsageHooks(
|
||||
model=resolved_model,
|
||||
max_budget_usd=max_budget_usd,
|
||||
max_turns=max_turns,
|
||||
interactive=interactive,
|
||||
)
|
||||
if interactive:
|
||||
coordinator.set_budget_extender(hooks.extend_budget)
|
||||
hooks = ReportUsageHooks(model=resolved_model, max_budget_usd=max_budget_usd)
|
||||
|
||||
scope_context = build_scope_context(scan_config)
|
||||
root_context = _merge_root_prompt_context(scope_context, extra_system_prompt_context)
|
||||
@@ -290,7 +238,7 @@ async def run_strix_scan(
|
||||
)
|
||||
|
||||
root_agent = build_strix_agent(
|
||||
name="Strix",
|
||||
name="strix",
|
||||
skills=skills,
|
||||
is_root=True,
|
||||
scan_mode=scan_mode,
|
||||
@@ -304,7 +252,7 @@ async def run_strix_scan(
|
||||
if not is_resume:
|
||||
await coordinator.register(
|
||||
root_id,
|
||||
"Strix",
|
||||
"strix",
|
||||
parent_id=None,
|
||||
task=root_task,
|
||||
skills=skills,
|
||||
@@ -451,7 +399,6 @@ async def run_strix_scan(
|
||||
await coordinator.set_status(root_id, "failed")
|
||||
raise
|
||||
finally:
|
||||
configure_spill_writer(None)
|
||||
for s in sessions_to_close:
|
||||
with contextlib.suppress(Exception):
|
||||
s.close()
|
||||
|
||||
@@ -7,7 +7,6 @@ import logging
|
||||
from typing import TYPE_CHECKING, Any, cast
|
||||
from weakref import WeakKeyDictionary
|
||||
|
||||
from agents.items import ItemHelpers
|
||||
from agents.memory import SQLiteSession
|
||||
|
||||
|
||||
@@ -27,18 +26,6 @@ def open_agent_session(agent_id: str, path: Path) -> SQLiteSession:
|
||||
return SQLiteSession(session_id=agent_id, db_path=path)
|
||||
|
||||
|
||||
async def seed_initial_input(session: Session, initial_input: Any) -> bool:
|
||||
"""Commit an agent's opening identity/task input before its first run cycle."""
|
||||
items = ItemHelpers.input_to_new_input_list(initial_input)
|
||||
if not items:
|
||||
return False
|
||||
async with session_write_lock(session):
|
||||
if await session.get_items():
|
||||
return False
|
||||
await session.add_items(items)
|
||||
return True
|
||||
|
||||
|
||||
_IMAGE_REJECTED_TEXT = "[image rejected by the model]"
|
||||
_IMAGE_ELIDED_TEXT = "[older screenshot elided to bound context memory]"
|
||||
_INHERITED_IMAGE_TEXT = "[screenshot omitted from inherited context]"
|
||||
@@ -105,39 +92,6 @@ async def _rewrite_session(
|
||||
return True
|
||||
|
||||
|
||||
async def replace_session_items(
|
||||
session: Session,
|
||||
new_items: list[Any],
|
||||
*,
|
||||
expected_len: int | None = None,
|
||||
) -> bool:
|
||||
"""Overwrite the session's items, restoring the originals on failure.
|
||||
|
||||
When ``expected_len`` is given, the rewrite is skipped if the session no
|
||||
longer has that many items (a concurrent writer changed it), so a slow
|
||||
compaction summary can't clobber newer turns.
|
||||
"""
|
||||
async with session_write_lock(session):
|
||||
original = list(await session.get_items())
|
||||
if expected_len is not None and len(original) != expected_len:
|
||||
logger.warning(
|
||||
"skipping session rewrite: expected %d items, found %d",
|
||||
expected_len,
|
||||
len(original),
|
||||
)
|
||||
return False
|
||||
rebuilt = cast("list[TResponseInputItem]", new_items)
|
||||
await session.clear_session()
|
||||
try:
|
||||
await session.add_items(rebuilt)
|
||||
except Exception:
|
||||
logger.exception("session rewrite failed; restoring original items")
|
||||
await session.clear_session()
|
||||
await session.add_items(original)
|
||||
raise
|
||||
return True
|
||||
|
||||
|
||||
async def strip_all_images_from_session(session: Session) -> bool:
|
||||
"""Replace every image tool output with a text placeholder (rejection recovery)."""
|
||||
|
||||
|
||||
@@ -1,419 +0,0 @@
|
||||
"""`strix auth` — ChatGPT subscription sign-in (login / status / logout).
|
||||
|
||||
Signing in only stores OAuth tokens (``~/.strix/subscription-auth.json``); model
|
||||
selection stays with ``STRIX_LLM``. A ``chatgpt/<model>`` STRIX_LLM runs on the
|
||||
subscription.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import base64
|
||||
import logging
|
||||
import threading
|
||||
import webbrowser
|
||||
from http.server import BaseHTTPRequestHandler, HTTPServer
|
||||
from pathlib import Path
|
||||
from typing import TYPE_CHECKING, Any
|
||||
from urllib.parse import parse_qs, urlparse
|
||||
|
||||
from rich.console import Console
|
||||
from rich.panel import Panel
|
||||
from rich.text import Text
|
||||
|
||||
from strix.config import codex, load_settings
|
||||
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from collections.abc import Callable
|
||||
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
_CALLBACK_TIMEOUT_S = 300
|
||||
|
||||
# CLI-facing name for the login provider. Internally this is the Codex OAuth
|
||||
# flow (``codex.PROVIDER``), but users know it as ChatGPT, so that's what the
|
||||
# command and messaging say. ``codex`` is accepted as an alias.
|
||||
LOGIN_PROVIDER = "chatgpt"
|
||||
_ACCEPTED_PROVIDERS = frozenset({LOGIN_PROVIDER, codex.PROVIDER})
|
||||
|
||||
_USAGE = "Usage:\n strix auth login chatgpt [--manual]\n strix auth status\n strix auth logout"
|
||||
|
||||
|
||||
def run_auth(argv: list[str]) -> int:
|
||||
"""Entry point for ``strix auth …``. Returns a process exit code."""
|
||||
console = Console()
|
||||
# Bare `strix auth` (no subcommand) defaults to login.
|
||||
subcommand = argv[0] if argv else "login"
|
||||
rest = argv[1:]
|
||||
|
||||
if subcommand in ("-h", "--help", "help"):
|
||||
console.print(_USAGE)
|
||||
return 0
|
||||
|
||||
handlers: dict[str, Callable[[], int]] = {
|
||||
"login": lambda: _login(console, rest),
|
||||
"status": lambda: _status(console),
|
||||
"logout": lambda: _logout(console),
|
||||
}
|
||||
handler = handlers.get(subcommand)
|
||||
if handler is not None:
|
||||
return handler()
|
||||
|
||||
console.print(f"[red]Unknown auth command:[/] {subcommand}\n")
|
||||
console.print(_USAGE)
|
||||
return 2
|
||||
|
||||
|
||||
def _login(console: Console, argv: list[str]) -> int:
|
||||
parser = argparse.ArgumentParser(prog="strix auth login", add_help=True)
|
||||
parser.add_argument(
|
||||
"provider",
|
||||
nargs="?",
|
||||
default=LOGIN_PROVIDER,
|
||||
help="Model provider to sign in with (default: chatgpt).",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--manual",
|
||||
action="store_true",
|
||||
help="Skip the local callback server and paste the redirect URL by hand.",
|
||||
)
|
||||
try:
|
||||
args = parser.parse_args(argv)
|
||||
except SystemExit as exc: # argparse already printed the message
|
||||
return int(exc.code or 2)
|
||||
|
||||
if args.provider.lower() not in _ACCEPTED_PROVIDERS:
|
||||
console.print(
|
||||
f"[red]Unsupported provider:[/] {args.provider}. "
|
||||
f"Only '{LOGIN_PROVIDER}' (ChatGPT subscription) is supported."
|
||||
)
|
||||
return 2
|
||||
|
||||
verifier, challenge = codex.generate_pkce()
|
||||
state = codex.create_state()
|
||||
authorize_url = codex.build_authorize_url(challenge, state)
|
||||
|
||||
console.print()
|
||||
console.print("[bold]Signing in with ChatGPT[/] [dim](provider: chatgpt)[/]")
|
||||
console.print(
|
||||
"[dim]This uses your ChatGPT Plus/Pro plan for inference instead of a metered API key.[/]"
|
||||
)
|
||||
console.print()
|
||||
|
||||
try:
|
||||
record = _run_oauth_flow(console, authorize_url, verifier, state, manual=args.manual)
|
||||
except codex.CodexAuthError as exc:
|
||||
return _fail(console, exc)
|
||||
except KeyboardInterrupt:
|
||||
console.print("\n[yellow]Sign-in cancelled.[/]")
|
||||
return 130
|
||||
|
||||
codex.save_record(record)
|
||||
_print_success(console)
|
||||
return 0
|
||||
|
||||
|
||||
def _run_oauth_flow(
|
||||
console: Console,
|
||||
authorize_url: str,
|
||||
verifier: str,
|
||||
state: str,
|
||||
*,
|
||||
manual: bool,
|
||||
) -> dict[str, Any]:
|
||||
"""Drive the browser (or manual) OAuth flow and return a token record."""
|
||||
server = None if manual else _try_start_callback_server()
|
||||
|
||||
console.print("Open this URL in your browser to authorize:")
|
||||
console.print(f"[cyan]{authorize_url}[/]")
|
||||
console.print()
|
||||
if not manual:
|
||||
try:
|
||||
webbrowser.open(authorize_url)
|
||||
except Exception: # noqa: BLE001 - opening a browser is best-effort
|
||||
logger.debug("could not open browser", exc_info=True)
|
||||
|
||||
if server is not None:
|
||||
console.print("[dim]Waiting for you to finish signing in…[/]")
|
||||
result = server.wait(_CALLBACK_TIMEOUT_S)
|
||||
server.shutdown()
|
||||
if result is not None:
|
||||
code, returned_state, error = result
|
||||
if error:
|
||||
raise codex.CodexAuthError("oauth_error", error)
|
||||
return _finish(code, returned_state, verifier, state, require_state=True)
|
||||
console.print("[yellow]Timed out waiting for the browser. Falling back to manual paste.[/]")
|
||||
|
||||
# Manual fallback: the user completes sign-in and pastes the redirect URL
|
||||
# (the browser lands on a localhost page that won't load if no server is up;
|
||||
# the address bar still holds the code+state).
|
||||
console.print()
|
||||
try:
|
||||
pasted = console.input("Paste the full redirect URL (or code#state): ").strip()
|
||||
except EOFError as exc:
|
||||
raise codex.CodexAuthError("no_input", "no redirect URL provided") from exc
|
||||
code, returned_state = codex.parse_redirect_input(pasted)
|
||||
return _finish(code, returned_state, verifier, state, require_state=False)
|
||||
|
||||
|
||||
def _finish(
|
||||
code: str | None,
|
||||
returned_state: str | None,
|
||||
verifier: str,
|
||||
expected_state: str,
|
||||
*,
|
||||
require_state: bool,
|
||||
) -> dict[str, Any]:
|
||||
if not code:
|
||||
raise codex.CodexAuthError("no_code", "no authorization code found in the redirect")
|
||||
# The loopback callback from OpenAI always carries state, so a missing or
|
||||
# mismatched value there is forged (CSRF) and must be rejected. Manual paste
|
||||
# is user-initiated (the user copies their own redirect), so state is only
|
||||
# validated when the pasted value includes it.
|
||||
if require_state and returned_state is None:
|
||||
raise codex.CodexAuthError("state_mismatch", "missing state in callback; possible CSRF")
|
||||
if returned_state is not None and returned_state != expected_state:
|
||||
raise codex.CodexAuthError("state_mismatch", "state did not match; possible CSRF")
|
||||
return codex.exchange_code(code, verifier)
|
||||
|
||||
|
||||
class _CallbackServer:
|
||||
"""A one-shot local HTTP server that catches the OAuth redirect."""
|
||||
|
||||
def __init__(self, httpd: HTTPServer, event: threading.Event, holder: dict[str, Any]) -> None:
|
||||
self._httpd = httpd
|
||||
self._event = event
|
||||
self._holder = holder
|
||||
self._thread = threading.Thread(target=httpd.serve_forever, daemon=True)
|
||||
self._thread.start()
|
||||
|
||||
def wait(self, timeout: float) -> tuple[str | None, str | None, str | None] | None:
|
||||
if not self._event.wait(timeout):
|
||||
return None
|
||||
return (
|
||||
self._holder.get("code"),
|
||||
self._holder.get("state"),
|
||||
self._holder.get("error"),
|
||||
)
|
||||
|
||||
def shutdown(self) -> None:
|
||||
self._httpd.shutdown()
|
||||
self._httpd.server_close()
|
||||
|
||||
|
||||
def _try_start_callback_server() -> _CallbackServer | None:
|
||||
event = threading.Event()
|
||||
holder: dict[str, Any] = {}
|
||||
|
||||
class Handler(BaseHTTPRequestHandler):
|
||||
def log_message(self, *args: Any) -> None: # silence default stderr logging
|
||||
pass
|
||||
|
||||
def do_GET(self) -> None:
|
||||
parsed = urlparse(self.path)
|
||||
if parsed.path != codex.CALLBACK_PATH:
|
||||
self.send_response(404)
|
||||
self.end_headers()
|
||||
return
|
||||
query = parse_qs(parsed.query)
|
||||
holder["code"] = _first(query, "code")
|
||||
holder["state"] = _first(query, "state")
|
||||
holder["error"] = _first(query, "error_description") or _first(query, "error")
|
||||
body = _render_callback_html().encode("utf-8")
|
||||
self.send_response(200)
|
||||
self.send_header("Content-Type", "text/html; charset=utf-8")
|
||||
self.send_header("Content-Length", str(len(body)))
|
||||
self.end_headers()
|
||||
self.wfile.write(body)
|
||||
event.set()
|
||||
|
||||
try:
|
||||
httpd = HTTPServer(("127.0.0.1", codex.CALLBACK_PORT), Handler)
|
||||
except OSError:
|
||||
logger.debug("could not bind callback port %d", codex.CALLBACK_PORT, exc_info=True)
|
||||
return None
|
||||
return _CallbackServer(httpd, event, holder)
|
||||
|
||||
|
||||
def _first(query: dict[str, list[str]], key: str) -> str | None:
|
||||
values = query.get(key)
|
||||
return values[0] if values else None
|
||||
|
||||
|
||||
def _status(console: Console) -> int:
|
||||
record = codex.read_record()
|
||||
if record is None:
|
||||
console.print("[yellow]Not signed in.[/] Run [cyan]strix auth login chatgpt[/] to sign in.")
|
||||
return 1
|
||||
settings = load_settings()
|
||||
console.print("[green]Signed in[/] with a ChatGPT subscription.")
|
||||
console.print(f" Account: [bold]{record.get('account_id')}[/]")
|
||||
if codex.subscription_model(settings.llm.model):
|
||||
console.print(f" Runs use the subscription (STRIX_LLM=[bold]{settings.llm.model}[/]).")
|
||||
else:
|
||||
console.print(
|
||||
" [yellow]Note:[/] set [cyan]STRIX_LLM[/] to e.g. [cyan]chatgpt/gpt-5.4[/] "
|
||||
"to run on the subscription."
|
||||
)
|
||||
return 0
|
||||
|
||||
|
||||
def _logout(console: Console) -> int:
|
||||
codex.logout()
|
||||
console.print("[green]Signed out.[/] Stored subscription credentials removed.")
|
||||
return 0
|
||||
|
||||
|
||||
def _fail(console: Console, exc: codex.CodexAuthError) -> int:
|
||||
error_text = Text()
|
||||
error_text.append("SIGN-IN FAILED", style="bold red")
|
||||
error_text.append("\n\n", style="white")
|
||||
error_text.append(f"{exc}", style="white")
|
||||
console.print()
|
||||
console.print(
|
||||
Panel(
|
||||
error_text,
|
||||
title="[bold white]STRIX",
|
||||
title_align="left",
|
||||
border_style="red",
|
||||
padding=(1, 2),
|
||||
)
|
||||
)
|
||||
return 1
|
||||
|
||||
|
||||
def _print_success(console: Console) -> None:
|
||||
text = Text()
|
||||
text.append("Signed in with your ChatGPT subscription", style="bold #22c55e")
|
||||
text.append("\n\n", style="white")
|
||||
text.append("Set ", style="white")
|
||||
text.append("STRIX_LLM", style="bold white")
|
||||
text.append(" to a ", style="white")
|
||||
text.append("chatgpt/", style="bold cyan")
|
||||
text.append(" model (e.g. ", style="white")
|
||||
text.append("chatgpt/gpt-5.4", style="bold cyan")
|
||||
text.append(") — runs are billed to your ChatGPT plan.", style="white")
|
||||
text.append("\n\n", style="white")
|
||||
text.append("Run a scan as usual, e.g. ", style="white")
|
||||
text.append("strix --target https://example.com", style="bold cyan")
|
||||
console.print()
|
||||
console.print(
|
||||
Panel(
|
||||
text,
|
||||
title="[bold white]STRIX",
|
||||
title_align="left",
|
||||
border_style="#22c55e",
|
||||
padding=(1, 2),
|
||||
)
|
||||
)
|
||||
console.print()
|
||||
|
||||
|
||||
_LOGO_PATH = Path(__file__).resolve().parent.parent / "viewer" / "static" / "logo.png"
|
||||
|
||||
|
||||
def _logo_img_tag() -> str:
|
||||
"""Return an ``<img>`` for the Strix logo as an inline data URI, or "".
|
||||
|
||||
The callback page is served offline by the local OAuth server, so the logo
|
||||
is embedded rather than linked. Missing/unreadable file degrades to just the
|
||||
"Strix" wordmark.
|
||||
"""
|
||||
try:
|
||||
data = _LOGO_PATH.read_bytes()
|
||||
except OSError:
|
||||
return ""
|
||||
encoded = base64.b64encode(data).decode("ascii")
|
||||
return f'<img class="logo" src="data:image/png;base64,{encoded}" alt="" />'
|
||||
|
||||
|
||||
def _render_callback_html() -> str:
|
||||
return _CALLBACK_HTML.replace("<!--LOGO-->", _logo_img_tag())
|
||||
|
||||
|
||||
_CALLBACK_HTML = """<!doctype html>
|
||||
<html lang="en"><head><meta charset="utf-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1">
|
||||
<title>Strix — signed in</title>
|
||||
<style>
|
||||
:root { color-scheme: dark; }
|
||||
* { box-sizing: border-box; }
|
||||
body {
|
||||
margin: 0; min-height: 100vh; padding: 24px;
|
||||
font-family: 'Geist', 'Geist Sans', ui-sans-serif, system-ui, -apple-system,
|
||||
"Segoe UI", Roboto, Helvetica, Arial, sans-serif;
|
||||
-webkit-font-smoothing: antialiased; -moz-osx-font-smoothing: grayscale;
|
||||
background: #000; color: #ededed;
|
||||
display: flex; flex-direction: column; align-items: center; justify-content: center;
|
||||
}
|
||||
.topbar {
|
||||
position: absolute; top: 20px; left: 22px;
|
||||
display: flex; align-items: center; gap: 6px; text-decoration: none;
|
||||
}
|
||||
.topbar .logo { width: 40px; height: 40px; display: block; }
|
||||
.topbar span {
|
||||
font-size: 1.1rem; font-weight: 600; letter-spacing: -.01em; color: #fff;
|
||||
transition: color .15s ease;
|
||||
}
|
||||
.topbar:hover span { color: #c9c9c9; }
|
||||
.brand {
|
||||
font-size: 2.1rem; font-weight: 700; letter-spacing: -.02em; color: #fff;
|
||||
text-align: center; margin: 0 0 10px;
|
||||
}
|
||||
h1 {
|
||||
font-size: 1.35rem; font-weight: 600; letter-spacing: -.01em; color: #f5f5f5;
|
||||
text-align: center; margin: 0 0 28px;
|
||||
}
|
||||
.card {
|
||||
width: 100%; max-width: 430px; text-align: center;
|
||||
background: #171717; border: 1px solid rgba(255, 255, 255, .06);
|
||||
border-radius: 24px; padding: 40px 40px 34px;
|
||||
}
|
||||
.badge {
|
||||
margin: 0 auto 22px; width: 52px; height: 52px; border-radius: 50%;
|
||||
display: flex; align-items: center; justify-content: center; font-size: 23px; color: #fff;
|
||||
background: rgba(255, 255, 255, .05); border: 1px solid rgba(255, 255, 255, .14);
|
||||
}
|
||||
.msg { margin: 0 auto; max-width: 34ch; color: #b5b5b5; line-height: 1.6; font-size: .98rem; }
|
||||
.rule { height: 1px; background: rgba(255, 255, 255, .07); margin: 26px 0 0; }
|
||||
.tagline { margin: 22px 0 0; color: #7c7c7c; font-size: .9rem; line-height: 1.55; }
|
||||
.tagline b { color: #ededed; font-weight: 500; }
|
||||
.links {
|
||||
margin-top: 18px; display: flex; gap: 8px; justify-content: center;
|
||||
align-items: center; flex-wrap: wrap; font-size: .84rem;
|
||||
}
|
||||
.links a { color: #a3a3a3; text-decoration: none; transition: color .15s ease; }
|
||||
.links a:hover { color: #fff; }
|
||||
.links .dot { color: #3a3a3a; }
|
||||
.close { margin: 24px 0 0; color: #5a5a5a; font-size: .78rem; text-align: center; }
|
||||
</style></head>
|
||||
<body>
|
||||
<a class="topbar" href="https://strix.ai" target="_blank" rel="noopener"
|
||||
aria-label="Strix — strix.ai">
|
||||
<!--LOGO-->
|
||||
<span>Strix</span>
|
||||
</a>
|
||||
<div class="brand">Strix</div>
|
||||
<h1>You're signed in</h1>
|
||||
<main class="card">
|
||||
<div class="badge">✓</div>
|
||||
<p class="msg">Strix is connected to your ChatGPT subscription. Head back to your
|
||||
terminal — your security test runs there.</p>
|
||||
<div class="rule"></div>
|
||||
<p class="tagline">Autonomous AI hackers that <b>find and fix</b> your app's
|
||||
vulnerabilities.</p>
|
||||
<nav class="links">
|
||||
<a href="https://strix.ai" target="_blank" rel="noopener">strix.ai</a>
|
||||
<span class="dot">·</span>
|
||||
<a href="https://docs.strix.ai" target="_blank" rel="noopener">docs</a>
|
||||
<span class="dot">·</span>
|
||||
<a href="https://discord.gg/strix-ai" target="_blank" rel="noopener">community</a>
|
||||
</nav>
|
||||
</main>
|
||||
<p class="close">You can close this tab.</p>
|
||||
</body></html>"""
|
||||
|
||||
|
||||
__all__ = ["run_auth"]
|
||||
@@ -13,7 +13,6 @@ from rich.panel import Panel
|
||||
from rich.text import Text
|
||||
|
||||
from strix.config import load_settings
|
||||
from strix.config.settings import DEFAULT_MAX_TURNS
|
||||
from strix.core.runner import run_strix_scan
|
||||
from strix.report.state import ReportState, set_global_report_state
|
||||
from strix.runtime import session_manager
|
||||
@@ -21,7 +20,6 @@ from strix.runtime import session_manager
|
||||
from .utils import (
|
||||
build_live_stats_text,
|
||||
format_vulnerability_report,
|
||||
has_model_response,
|
||||
)
|
||||
|
||||
|
||||
@@ -136,17 +134,11 @@ async def run_cli(args: Any) -> None: # noqa: PLR0915
|
||||
|
||||
set_global_report_state(report_state)
|
||||
|
||||
startup_phase: list[str] = ["Starting up"]
|
||||
|
||||
def create_live_status() -> Panel:
|
||||
status_text = Text()
|
||||
status_text.append("Penetration test in progress", style="bold #22c55e")
|
||||
status_text.append("\n\n")
|
||||
|
||||
if not has_model_response(report_state):
|
||||
status_text.append(f"{startup_phase[0]}...", style="dim")
|
||||
status_text.append("\n\n")
|
||||
|
||||
stats_text = build_live_stats_text(report_state)
|
||||
if stats_text:
|
||||
status_text.append(stats_text)
|
||||
@@ -159,9 +151,6 @@ async def run_cli(args: Any) -> None: # noqa: PLR0915
|
||||
padding=(1, 2),
|
||||
)
|
||||
|
||||
def _note_startup_phase(phase: str) -> None:
|
||||
startup_phase[:] = [phase]
|
||||
|
||||
try:
|
||||
console.print()
|
||||
|
||||
@@ -195,8 +184,6 @@ async def run_cli(args: Any) -> None: # noqa: PLR0915
|
||||
local_sources=getattr(args, "local_sources", None) or [],
|
||||
interactive=bool(getattr(args, "interactive", False)),
|
||||
max_budget_usd=getattr(args, "max_budget_usd", None),
|
||||
max_turns=getattr(args, "max_turns", DEFAULT_MAX_TURNS),
|
||||
status_sink=_note_startup_phase,
|
||||
)
|
||||
finally:
|
||||
stop_updates.set()
|
||||
|
||||
+135
-226
@@ -5,39 +5,43 @@ Strix Agent Interface
|
||||
|
||||
import argparse
|
||||
import asyncio
|
||||
import os
|
||||
import shutil
|
||||
import sys
|
||||
import time
|
||||
from datetime import UTC, datetime
|
||||
from pathlib import Path
|
||||
|
||||
from agents.model_settings import ModelSettings
|
||||
from agents.models.interface import ModelTracing
|
||||
from docker.errors import DockerException
|
||||
from rich.console import Console
|
||||
from rich.panel import Panel
|
||||
from rich.text import Text
|
||||
|
||||
from strix.config import (
|
||||
apply_config_override,
|
||||
codex,
|
||||
load_settings,
|
||||
persist_current,
|
||||
)
|
||||
from strix.config.settings import DEFAULT_MAX_TURNS
|
||||
from strix.core.paths import run_dir_for, runtime_state_dir
|
||||
from strix.interface.update_check import (
|
||||
is_binary_install,
|
||||
notify_update,
|
||||
prompt_update_if_available,
|
||||
self_update,
|
||||
start_background_check,
|
||||
from strix.config.models import (
|
||||
RECOMMENDED_MODEL_NAMES,
|
||||
StrixProvider,
|
||||
configure_sdk_model_defaults,
|
||||
is_known_openai_bare_model,
|
||||
is_recommended_or_frontier_model,
|
||||
)
|
||||
from strix.core.paths import run_dir_for, runtime_state_dir
|
||||
from strix.interface.cli import run_cli
|
||||
from strix.interface.tui import run_tui
|
||||
from strix.interface.utils import (
|
||||
assign_workspace_subdirs,
|
||||
build_final_stats_text,
|
||||
build_mount_targets_info,
|
||||
check_docker_connection,
|
||||
check_mountable_dir,
|
||||
clone_repository,
|
||||
collect_local_sources,
|
||||
dedupe_local_targets,
|
||||
find_oversized_local_targets,
|
||||
generate_run_name,
|
||||
image_exists,
|
||||
infer_target_type,
|
||||
@@ -48,6 +52,8 @@ from strix.interface.utils import (
|
||||
rewrite_localhost_targets,
|
||||
validate_config_file,
|
||||
)
|
||||
from strix.report.state import get_global_report_state
|
||||
from strix.report.writer import read_run_record, write_run_record
|
||||
from strix.telemetry import posthog, scarf
|
||||
from strix.telemetry.logging import configure_dependency_logging
|
||||
|
||||
@@ -79,16 +85,6 @@ def validate_environment() -> None:
|
||||
|
||||
settings = load_settings()
|
||||
|
||||
if codex.subscription_model(settings.llm.model):
|
||||
if not codex.is_authenticated():
|
||||
console.print(
|
||||
f"[red]STRIX_LLM={settings.llm.model} uses your ChatGPT subscription, "
|
||||
"but you're not signed in.[/] Run [cyan]strix auth login chatgpt[/] first."
|
||||
)
|
||||
sys.exit(1)
|
||||
logger.info("Environment OK (ChatGPT subscription)")
|
||||
return
|
||||
|
||||
if not settings.llm.model:
|
||||
missing_required_vars.append("STRIX_LLM")
|
||||
|
||||
@@ -156,8 +152,8 @@ def validate_environment() -> None:
|
||||
error_text.append("• ", style="white")
|
||||
error_text.append("STRIX_REASONING_EFFORT", style="bold cyan")
|
||||
error_text.append(
|
||||
" - Reasoning effort level: none, minimal, low, medium, high, xhigh, "
|
||||
"max (default: high)\n",
|
||||
" - Reasoning effort level: none, minimal, low, medium, high, xhigh "
|
||||
"(default: high)\n",
|
||||
style="white",
|
||||
)
|
||||
|
||||
@@ -196,7 +192,7 @@ def validate_environment() -> None:
|
||||
padding=(1, 2),
|
||||
)
|
||||
|
||||
logger.debug("Missing required env vars: %s", missing_required_vars)
|
||||
logger.error("Missing required env vars: %s", missing_required_vars)
|
||||
console.print("\n")
|
||||
console.print(panel)
|
||||
console.print()
|
||||
@@ -209,7 +205,7 @@ def validate_environment() -> None:
|
||||
|
||||
def check_docker_installed() -> None:
|
||||
if shutil.which("docker") is None:
|
||||
logger.debug("Docker CLI not found in PATH")
|
||||
logger.error("Docker CLI not found in PATH")
|
||||
console = Console()
|
||||
error_text = Text()
|
||||
error_text.append("DOCKER NOT INSTALLED", style="bold red")
|
||||
@@ -271,42 +267,7 @@ def _provider_import_hint(exc: BaseException, model: str) -> str | None:
|
||||
return None
|
||||
|
||||
|
||||
def _subscription_error_hint(exc: BaseException) -> str | None:
|
||||
"""Return an actionable hint for a known ChatGPT-subscription error, or None."""
|
||||
if not codex.subscription_model(load_settings().llm.model):
|
||||
return None
|
||||
joined = " ".join(_exception_messages(exc)).lower()
|
||||
if "not supported when using codex with a chatgpt account" in joined:
|
||||
return (
|
||||
"This model isn't available on your ChatGPT subscription. "
|
||||
"Set STRIX_LLM to a model your plan includes (e.g. chatgpt/gpt-5.4)."
|
||||
)
|
||||
if (
|
||||
"error code: 401" in joined
|
||||
or "http 401" in joined
|
||||
or "unauthorized" in joined
|
||||
or "invalid_grant" in joined
|
||||
):
|
||||
return (
|
||||
"Your ChatGPT sign-in has expired or was revoked. Sign in again:\n"
|
||||
" strix auth login chatgpt"
|
||||
)
|
||||
return None
|
||||
|
||||
|
||||
async def warm_up_llm(show_model_warning: bool = True) -> None:
|
||||
from agents.model_settings import ModelSettings
|
||||
from agents.models.interface import ModelTracing
|
||||
|
||||
from strix.config.models import (
|
||||
RECOMMENDED_MODEL_NAMES,
|
||||
StrixProvider,
|
||||
configure_sdk_model_defaults,
|
||||
is_known_openai_bare_model,
|
||||
is_recommended_or_frontier_model,
|
||||
)
|
||||
from strix.core.inputs import make_model_settings
|
||||
|
||||
console = Console()
|
||||
logger.info("Warming up LLM connection")
|
||||
|
||||
@@ -315,8 +276,8 @@ async def warm_up_llm(show_model_warning: bool = True) -> None:
|
||||
settings = load_settings()
|
||||
configure_sdk_model_defaults(settings)
|
||||
llm = settings.llm
|
||||
raw_model = (llm.model or "").strip()
|
||||
|
||||
raw_model = (llm.model or "").strip()
|
||||
if (
|
||||
raw_model
|
||||
and "/" not in raw_model
|
||||
@@ -379,13 +340,7 @@ async def warm_up_llm(show_model_warning: bool = True) -> None:
|
||||
model.get_response(
|
||||
system_instructions="You are a helpful assistant.",
|
||||
input="Reply with just 'OK'.",
|
||||
model_settings=make_model_settings(
|
||||
None,
|
||||
model_name=raw_model,
|
||||
request_timeout=llm.timeout,
|
||||
prompt_cache=False,
|
||||
extra_headers=llm.extra_headers,
|
||||
),
|
||||
model_settings=ModelSettings(),
|
||||
tools=[],
|
||||
output_schema=None,
|
||||
handoffs=[],
|
||||
@@ -398,75 +353,23 @@ async def warm_up_llm(show_model_warning: bool = True) -> None:
|
||||
)
|
||||
logger.info("LLM warm-up succeeded for model %s", (llm.model or "").strip())
|
||||
|
||||
if settings.dedupe.model:
|
||||
from strix.report.dedupe import _dedupe_extra_args
|
||||
|
||||
dedupe_model = settings.dedupe.model.strip()
|
||||
raw_model = dedupe_model
|
||||
deduper = StrixProvider().get_model(dedupe_model)
|
||||
# Match the runtime path: send the dedupe key/endpoint per call so a
|
||||
# separate-provider dedupe model authenticates during warm-up too.
|
||||
deduper_extra = _dedupe_extra_args(settings.dedupe)
|
||||
# A dedicated dedupe model may route to another provider, which must
|
||||
# never receive the main endpoint's headers; it has its own
|
||||
# DEDUPE_LLM_EXTRA_HEADERS.
|
||||
deduper_settings = make_model_settings(
|
||||
None,
|
||||
model_name=dedupe_model,
|
||||
request_timeout=llm.timeout,
|
||||
prompt_cache=False,
|
||||
extra_headers=settings.dedupe.extra_headers,
|
||||
)
|
||||
if deduper_extra:
|
||||
merged = {**(deduper_settings.extra_args or {}), **deduper_extra}
|
||||
deduper_settings = deduper_settings.resolve(ModelSettings(extra_args=merged))
|
||||
await asyncio.wait_for(
|
||||
deduper.get_response(
|
||||
system_instructions="You are a helpful assistant.",
|
||||
input="Reply with just 'OK'.",
|
||||
model_settings=deduper_settings,
|
||||
tools=[],
|
||||
output_schema=None,
|
||||
handoffs=[],
|
||||
tracing=ModelTracing.DISABLED,
|
||||
previous_response_id=None,
|
||||
conversation_id=None,
|
||||
prompt=None,
|
||||
),
|
||||
timeout=llm.timeout,
|
||||
)
|
||||
logger.info("LLM warm-up succeeded for dedupe model %s", dedupe_model)
|
||||
|
||||
except Exception as e:
|
||||
logger.debug("LLM warm-up failed", exc_info=True)
|
||||
logger.exception("LLM warm-up failed")
|
||||
error_text = Text()
|
||||
sub_hint = _subscription_error_hint(e)
|
||||
if sub_hint is not None:
|
||||
# The model/backend answered with a clear, actionable rejection —
|
||||
# show that instead of a generic "connection failed".
|
||||
border_style = "yellow"
|
||||
error_text.append("MODEL NOT AVAILABLE ON SUBSCRIPTION", style="bold yellow")
|
||||
error_text.append("\n\n", style="white")
|
||||
error_text.append(f"{sub_hint}\n", style="white")
|
||||
error_text.append(f"\nDetails: {e}", style="dim white")
|
||||
else:
|
||||
border_style = "red"
|
||||
error_text.append("LLM CONNECTION FAILED", style="bold red")
|
||||
error_text.append("\n\n", style="white")
|
||||
error_text.append(
|
||||
"Could not establish connection to the language model.\n", style="white"
|
||||
)
|
||||
error_text.append("Please check your configuration and try again.\n", style="white")
|
||||
hint = _provider_import_hint(e, raw_model)
|
||||
if hint is not None:
|
||||
error_text.append(f"\n{hint}\n", style="bold yellow")
|
||||
error_text.append(f"\nError: {e}", style="dim white")
|
||||
error_text.append("LLM CONNECTION FAILED", style="bold red")
|
||||
error_text.append("\n\n", style="white")
|
||||
error_text.append("Could not establish connection to the language model.\n", style="white")
|
||||
error_text.append("Please check your configuration and try again.\n", style="white")
|
||||
hint = _provider_import_hint(e, raw_model)
|
||||
if hint is not None:
|
||||
error_text.append(f"\n{hint}\n", style="bold yellow")
|
||||
error_text.append(f"\nError: {e}", style="dim white")
|
||||
|
||||
panel = Panel(
|
||||
error_text,
|
||||
title="[bold white]STRIX",
|
||||
title_align="left",
|
||||
border_style=border_style,
|
||||
border_style="red",
|
||||
padding=(1, 2),
|
||||
)
|
||||
|
||||
@@ -497,16 +400,6 @@ def _positive_budget(value: str) -> float:
|
||||
return budget
|
||||
|
||||
|
||||
def _positive_int(value: str) -> int:
|
||||
try:
|
||||
parsed = int(value)
|
||||
except ValueError as exc:
|
||||
raise argparse.ArgumentTypeError(f"invalid int value: {value!r}") from exc
|
||||
if parsed <= 0:
|
||||
raise argparse.ArgumentTypeError("must be an integer greater than 0")
|
||||
return parsed
|
||||
|
||||
|
||||
def parse_arguments() -> argparse.Namespace:
|
||||
parser = argparse.ArgumentParser(
|
||||
description="Strix Multi-Agent Cybersecurity Penetration Testing Tool",
|
||||
@@ -523,6 +416,9 @@ Examples:
|
||||
# Local code analysis
|
||||
strix --target ./my-project
|
||||
|
||||
# Large local repository (bind-mounted read-only instead of copied)
|
||||
strix --mount ./huge-monorepo
|
||||
|
||||
# Domain penetration test
|
||||
strix --target example.com
|
||||
|
||||
@@ -552,23 +448,14 @@ Examples:
|
||||
version=f"strix {get_version()}",
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
"--update",
|
||||
action="store_true",
|
||||
help="Update strix to the latest version and exit. Self-updates the "
|
||||
"standalone binary install; for pip/pipx/uv installs, prints the "
|
||||
"matching upgrade command instead.",
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
"-t",
|
||||
"--target",
|
||||
type=str,
|
||||
action="append",
|
||||
help="Target to test (URL, repository, local directory path, domain name, or IP address). "
|
||||
"Local directories are mounted into the sandbox writable. "
|
||||
"Can be specified multiple times for multi-target scans. "
|
||||
"Fresh runs require --target or --target-list.",
|
||||
"Fresh runs require at least one of --target, --target-list, or --mount.",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--target-list",
|
||||
@@ -578,6 +465,15 @@ Examples:
|
||||
help="Path to a file containing targets, one per non-empty, non-comment line. "
|
||||
"Can be specified multiple times and combined with --target.",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--mount",
|
||||
type=str,
|
||||
action="append",
|
||||
metavar="PATH",
|
||||
help="Bind-mount a local directory into the sandbox (read-only) instead of "
|
||||
"copying it file-by-file. Use this for large repositories that are too big to "
|
||||
"stream into the container. Can be specified multiple times.",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--instruction",
|
||||
type=str,
|
||||
@@ -651,27 +547,10 @@ Examples:
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
"--max-budget",
|
||||
dest="max_budget_usd",
|
||||
metavar="USD",
|
||||
"--max-budget-usd",
|
||||
type=_positive_budget,
|
||||
default=None,
|
||||
help=(
|
||||
"Maximum LLM cost in USD (> 0). The scan stops cleanly when this limit is reached. "
|
||||
"Graduated wrap-up warnings are sent to all agents as it is approached."
|
||||
),
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
"--max-turns",
|
||||
dest="max_turns",
|
||||
metavar="N",
|
||||
type=_positive_int,
|
||||
default=DEFAULT_MAX_TURNS,
|
||||
help=(
|
||||
"Maximum turns per agent (> 0, default %(default)s). Each agent is force-stopped "
|
||||
"when it reaches this limit, with graduated wrap-up warnings as it is approached."
|
||||
),
|
||||
help="Maximum LLM cost in USD (> 0). The scan stops cleanly when this limit is reached.",
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
@@ -687,9 +566,6 @@ Examples:
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
if args.update:
|
||||
sys.exit(0 if self_update() else 1)
|
||||
|
||||
if args.instruction and args.instruction_file:
|
||||
parser.error(
|
||||
"Cannot specify both --instruction and --instruction-file. Use one or the other."
|
||||
@@ -708,9 +584,9 @@ Examples:
|
||||
args.user_explicit_instruction = args.instruction if args.resume else None
|
||||
|
||||
if args.resume:
|
||||
if args.target or args.target_list:
|
||||
if args.target or args.target_list or args.mount:
|
||||
parser.error(
|
||||
"Cannot combine --resume with --target/--target-list. "
|
||||
"Cannot combine --resume with --target/--target-list/--mount. "
|
||||
"--resume picks up where the prior run left off, including the "
|
||||
"original target list."
|
||||
)
|
||||
@@ -724,9 +600,9 @@ Examples:
|
||||
f"or remove --resume to start over with the same targets."
|
||||
)
|
||||
else:
|
||||
if not args.target and not args.target_list:
|
||||
if not args.target and not args.target_list and not args.mount:
|
||||
parser.error(
|
||||
"the following arguments are required: -t/--target or --target-list "
|
||||
"the following arguments are required: -t/--target, --target-list, or --mount "
|
||||
"(or use --resume <run_name> to continue a prior scan)"
|
||||
)
|
||||
args.targets_info = []
|
||||
@@ -749,20 +625,37 @@ Examples:
|
||||
args.targets_info.append(
|
||||
{"type": target_type, "details": target_dict, "original": display_target}
|
||||
)
|
||||
except ValueError as e:
|
||||
parser.error(f"Invalid target '{target}': {e}")
|
||||
except ValueError:
|
||||
parser.error(f"Invalid target '{target}'")
|
||||
|
||||
try:
|
||||
args.targets_info.extend(build_mount_targets_info(args.mount or []))
|
||||
except ValueError as e:
|
||||
parser.error(str(e))
|
||||
|
||||
args.targets_info = dedupe_local_targets(args.targets_info)
|
||||
|
||||
assign_workspace_subdirs(args.targets_info)
|
||||
rewrite_localhost_targets(args.targets_info, HOST_GATEWAY_HOSTNAME)
|
||||
|
||||
max_local_copy_mb = load_settings().runtime.max_local_copy_mb
|
||||
max_copy_bytes = max_local_copy_mb * 1024 * 1024
|
||||
oversized = find_oversized_local_targets(args.targets_info, max_copy_bytes)
|
||||
if oversized:
|
||||
details = "; ".join(
|
||||
f"{path} ({size / (1024 * 1024):.0f} MB)" for path, size in oversized
|
||||
)
|
||||
parser.error(
|
||||
f"Local target too large to stream into the sandbox: {details}. "
|
||||
f"The limit is {max_local_copy_mb} MB "
|
||||
"(set STRIX_MAX_LOCAL_COPY_MB to change it). Re-run with "
|
||||
"--mount <path> to bind-mount the directory instead of copying it."
|
||||
)
|
||||
|
||||
return args
|
||||
|
||||
|
||||
def _persist_run_record(args: argparse.Namespace) -> None:
|
||||
from strix.report.writer import write_run_record
|
||||
|
||||
run_dir = run_dir_for(args.run_name)
|
||||
run_dir.mkdir(parents=True, exist_ok=True)
|
||||
run_record = {
|
||||
@@ -771,7 +664,6 @@ def _persist_run_record(args: argparse.Namespace) -> None:
|
||||
"status": "running",
|
||||
"start_time": datetime.now(UTC).isoformat(),
|
||||
"end_time": None,
|
||||
"auth_mode": codex.auth_mode(load_settings().llm.model),
|
||||
"targets_info": args.targets_info,
|
||||
"scan_mode": args.scan_mode,
|
||||
"instruction": args.instruction,
|
||||
@@ -786,8 +678,6 @@ def _persist_run_record(args: argparse.Namespace) -> None:
|
||||
|
||||
def _load_resume_state(args: argparse.Namespace, parser: argparse.ArgumentParser) -> None:
|
||||
"""Populate ``args.targets_info`` and friends from a prior run's run.json."""
|
||||
from strix.report.writer import read_run_record
|
||||
|
||||
run_dir = run_dir_for(args.resume)
|
||||
state_path = run_dir / "run.json"
|
||||
if not state_path.exists():
|
||||
@@ -808,12 +698,6 @@ def _load_resume_state(args: argparse.Namespace, parser: argparse.ArgumentParser
|
||||
if not isinstance(target, dict):
|
||||
continue
|
||||
details = target.get("details") or {}
|
||||
if target.get("type") == "local_code" and details.get("target_path"):
|
||||
try:
|
||||
check_mountable_dir(Path(details["target_path"]).expanduser())
|
||||
except ValueError as exc:
|
||||
parser.error(f"--resume {args.resume}: {exc}")
|
||||
continue
|
||||
if target.get("type") != "repository":
|
||||
continue
|
||||
cloned = details.get("cloned_repo_path")
|
||||
@@ -828,7 +712,8 @@ def _load_resume_state(args: argparse.Namespace, parser: argparse.ArgumentParser
|
||||
|
||||
if args.instruction is None:
|
||||
args.instruction = state.get("instruction")
|
||||
args.local_sources = collect_local_sources(args.targets_info)
|
||||
if state.get("local_sources"):
|
||||
args.local_sources = state.get("local_sources")
|
||||
if state.get("diff_scope"):
|
||||
args.diff_scope = state.get("diff_scope")
|
||||
persisted_scan_mode = state.get("scan_mode")
|
||||
@@ -836,9 +721,9 @@ def _load_resume_state(args: argparse.Namespace, parser: argparse.ArgumentParser
|
||||
args.scan_mode = persisted_scan_mode
|
||||
|
||||
|
||||
def display_completion_message(args: argparse.Namespace, results_path: Path) -> None:
|
||||
from strix.report.state import get_global_report_state
|
||||
|
||||
def display_completion_message(
|
||||
args: argparse.Namespace, results_path: Path, web_url: str | None = None
|
||||
) -> None:
|
||||
console = Console()
|
||||
report_state = get_global_report_state()
|
||||
|
||||
@@ -877,12 +762,28 @@ def display_completion_message(args: argparse.Namespace, results_path: Path) ->
|
||||
results_text.append(str(results_path), style="#60a5fa")
|
||||
panel_parts.extend(["\n", results_text])
|
||||
|
||||
view_text = Text()
|
||||
view_text.append("\n")
|
||||
view_text.append("View", style="dim")
|
||||
view_text.append(" ")
|
||||
view_text.append(f"strix view {args.run_name}", style="#22c55e")
|
||||
panel_parts.extend(["\n", view_text])
|
||||
if web_url:
|
||||
web_text = Text()
|
||||
web_text.append("\n")
|
||||
web_text.append("View in web", style="dim")
|
||||
web_text.append(" ")
|
||||
# OSC-8 hyperlink: clickable in modern terminals, falls back to the URL.
|
||||
web_text.append(web_url, style=f"#60a5fa link {web_url}")
|
||||
panel_parts.extend(["\n", web_text])
|
||||
|
||||
reopen_text = Text()
|
||||
reopen_text.append("\n")
|
||||
reopen_text.append("Reopen", style="dim")
|
||||
reopen_text.append(" ")
|
||||
reopen_text.append(f"strix view {args.run_name}", style="#22c55e")
|
||||
panel_parts.extend(["\n", reopen_text])
|
||||
else:
|
||||
view_text = Text()
|
||||
view_text.append("\n")
|
||||
view_text.append("View", style="dim")
|
||||
view_text.append(" ")
|
||||
view_text.append(f"strix view {args.run_name}", style="#22c55e")
|
||||
panel_parts.extend(["\n", view_text])
|
||||
|
||||
if not scan_completed:
|
||||
resume_text = Text()
|
||||
@@ -913,13 +814,9 @@ def display_completion_message(args: argparse.Namespace, results_path: Path) ->
|
||||
"[#60a5fa]discord.gg/strix-ai[/]"
|
||||
)
|
||||
console.print()
|
||||
if not args.non_interactive:
|
||||
notify_update(console)
|
||||
|
||||
|
||||
def pull_docker_image() -> None:
|
||||
from docker.errors import DockerException
|
||||
|
||||
console = Console()
|
||||
client = check_docker_connection()
|
||||
|
||||
@@ -944,7 +841,7 @@ def pull_docker_image() -> None:
|
||||
last_update = process_pull_line(line, layers_info, status, last_update)
|
||||
|
||||
except DockerException as e:
|
||||
logger.debug("Failed to pull docker image %s", image, exc_info=True)
|
||||
logger.exception("Failed to pull docker image %s", image)
|
||||
console.print()
|
||||
error_text = Text()
|
||||
error_text.append("FAILED TO PULL IMAGE", style="bold red")
|
||||
@@ -978,29 +875,16 @@ def main() -> None:
|
||||
# `strix view [<run>]` is a viewer-only subcommand, dispatched before the
|
||||
# scan argument parser (which requires a target) and before any scan setup.
|
||||
if len(sys.argv) > 1 and sys.argv[1] == "view":
|
||||
from strix.interface.viewer.cli import run_view
|
||||
from strix.viewer.cli import run_view
|
||||
|
||||
run_view(sys.argv[2:])
|
||||
return
|
||||
|
||||
# `strix auth …` manages model-subscription sign-in and exits; it needs no
|
||||
# target, Docker, or scan setup.
|
||||
if len(sys.argv) > 1 and sys.argv[1] == "auth":
|
||||
from strix.interface.auth_cli import run_auth
|
||||
|
||||
sys.exit(run_auth(sys.argv[2:]))
|
||||
|
||||
args = parse_arguments()
|
||||
|
||||
if args.config:
|
||||
apply_config_override(validate_config_file(args.config))
|
||||
|
||||
start_background_check()
|
||||
if not args.non_interactive and prompt_update_if_available(Console()):
|
||||
if is_binary_install() and sys.platform != "win32":
|
||||
os.execv(sys.executable, sys.argv) # noqa: S606 # nosec B606
|
||||
sys.exit(0)
|
||||
|
||||
check_docker_installed()
|
||||
pull_docker_image()
|
||||
|
||||
@@ -1057,7 +941,6 @@ def main() -> None:
|
||||
|
||||
_telemetry_start_kwargs = {
|
||||
"model": load_settings().llm.model,
|
||||
"auth_mode": codex.auth_mode(load_settings().llm.model),
|
||||
"scan_mode": args.scan_mode,
|
||||
"is_whitebox": is_whitebox_scan(args.targets_info),
|
||||
"interactive": not args.non_interactive,
|
||||
@@ -1066,17 +949,11 @@ def main() -> None:
|
||||
posthog.start(**_telemetry_start_kwargs)
|
||||
scarf.start(**_telemetry_start_kwargs)
|
||||
|
||||
from strix.report.state import get_global_report_state
|
||||
|
||||
exit_reason = "user_exit"
|
||||
try:
|
||||
if args.non_interactive:
|
||||
from strix.interface.cli import run_cli
|
||||
|
||||
asyncio.run(run_cli(args))
|
||||
else:
|
||||
from strix.interface.tui import run_tui
|
||||
|
||||
asyncio.run(run_tui(args))
|
||||
except KeyboardInterrupt:
|
||||
exit_reason = "interrupted"
|
||||
@@ -1098,7 +975,39 @@ def main() -> None:
|
||||
|
||||
results_path = run_dir_for(args.run_name)
|
||||
|
||||
display_completion_message(args, results_path)
|
||||
# For an interactive run, host the local viewer so the completion panel can
|
||||
# show a clickable "View in web" link. Skipped in non-interactive/CI runs
|
||||
# (no TTY to serve and it would block the process).
|
||||
viewer_httpd = None
|
||||
web_url = None
|
||||
if not args.non_interactive and sys.stdout.isatty():
|
||||
from strix.viewer.server import authorized_url, bundle_is_built, serve
|
||||
|
||||
if bundle_is_built():
|
||||
try:
|
||||
viewer_httpd, base_url, token = serve(results_path, open_browser=False)
|
||||
# The completion panel's "View in web" link must authorize the
|
||||
# browser, so hand it the tokened URL rather than the bare host.
|
||||
web_url = authorized_url(base_url, token)
|
||||
posthog.viewer_opened(source="post_scan", live=False)
|
||||
except Exception:
|
||||
logger.debug("could not start local viewer", exc_info=True)
|
||||
viewer_httpd, web_url = None, None
|
||||
|
||||
display_completion_message(args, results_path, web_url=web_url)
|
||||
|
||||
if viewer_httpd is not None:
|
||||
console = Console()
|
||||
console.print("[dim]Hosting the local viewer. Press Ctrl-C to stop.[/]")
|
||||
console.print()
|
||||
try:
|
||||
while True:
|
||||
time.sleep(1)
|
||||
except KeyboardInterrupt:
|
||||
console.print("\n[dim]Viewer stopped.[/]")
|
||||
finally:
|
||||
viewer_httpd.shutdown()
|
||||
viewer_httpd.server_close()
|
||||
|
||||
if args.non_interactive:
|
||||
report_state = get_global_report_state()
|
||||
|
||||
+26
-99
@@ -15,7 +15,6 @@ from typing import TYPE_CHECKING, Any, ClassVar
|
||||
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from pygments.token import _TokenType
|
||||
from textual.timer import Timer
|
||||
|
||||
from rich.align import Align
|
||||
@@ -34,7 +33,6 @@ from textual.widgets.tree import TreeNode
|
||||
|
||||
from strix.config import load_settings
|
||||
from strix.config.models import is_recommended_or_frontier_model
|
||||
from strix.config.settings import DEFAULT_MAX_TURNS
|
||||
from strix.core.hooks import BudgetExceededError
|
||||
from strix.core.runner import run_strix_scan
|
||||
from strix.interface.tui.live_view import TuiLiveView
|
||||
@@ -44,12 +42,6 @@ from strix.interface.tui.renderers.agent_message_renderer import AgentMessageRen
|
||||
from strix.interface.tui.renderers.user_message_renderer import UserMessageRenderer
|
||||
from strix.interface.utils import build_tui_stats_text
|
||||
from strix.report.state import ReportState, set_global_report_state
|
||||
from strix.report.writer import (
|
||||
guess_language_name,
|
||||
parse_fenced_code,
|
||||
resolve_lexer,
|
||||
safe_fence,
|
||||
)
|
||||
from strix.runtime import session_manager
|
||||
|
||||
|
||||
@@ -338,11 +330,12 @@ class VulnerabilityDetailScreen(ModalScreen): # type: ignore[misc]
|
||||
return "#65a30d"
|
||||
return "#6b7280"
|
||||
|
||||
def _highlight_python(self, code: str, language: str | None = None) -> Text:
|
||||
def _highlight_python(self, code: str) -> Text:
|
||||
try:
|
||||
from pygments.lexers import PythonLexer
|
||||
from pygments.styles import get_style_by_name
|
||||
|
||||
lexer = resolve_lexer(language, code)
|
||||
lexer = PythonLexer()
|
||||
style = get_style_by_name("native")
|
||||
colors = {
|
||||
token: f"#{style_def['color']}" for token, style_def in style if style_def["color"]
|
||||
@@ -353,7 +346,7 @@ class VulnerabilityDetailScreen(ModalScreen): # type: ignore[misc]
|
||||
if not token_value:
|
||||
continue
|
||||
color = None
|
||||
tt: _TokenType | None = token_type
|
||||
tt = token_type
|
||||
while tt:
|
||||
if tt in colors:
|
||||
color = colors[tt]
|
||||
@@ -508,11 +501,10 @@ class VulnerabilityDetailScreen(ModalScreen): # type: ignore[misc]
|
||||
|
||||
poc_script_code = vuln.get("poc_script_code", "")
|
||||
if poc_script_code:
|
||||
poc_language, poc_code = parse_fenced_code(poc_script_code)
|
||||
text.append("\n\n")
|
||||
text.append("PoC Code", style=self.FIELD_STYLE)
|
||||
text.append("\n")
|
||||
text.append_text(self._highlight_python(poc_code, poc_language))
|
||||
text.append_text(self._highlight_python(poc_script_code))
|
||||
|
||||
remediation_steps = vuln.get("remediation_steps", "")
|
||||
if remediation_steps:
|
||||
@@ -609,12 +601,9 @@ class VulnerabilityDetailScreen(ModalScreen): # type: ignore[misc]
|
||||
lines.append(vuln["poc_description"])
|
||||
lines.append("")
|
||||
if vuln.get("poc_script_code"):
|
||||
poc_language, poc_code = parse_fenced_code(vuln["poc_script_code"])
|
||||
fence_lang = poc_language or guess_language_name(poc_code)
|
||||
fence = safe_fence(poc_code)
|
||||
lines.append(f"{fence}{fence_lang}")
|
||||
lines.append(poc_code)
|
||||
lines.append(fence)
|
||||
lines.append("```python")
|
||||
lines.append(vuln["poc_script_code"])
|
||||
lines.append("```")
|
||||
|
||||
if vuln.get("code_locations"):
|
||||
lines.extend(["", "## Code Analysis", ""])
|
||||
@@ -630,9 +619,7 @@ class VulnerabilityDetailScreen(ModalScreen): # type: ignore[misc]
|
||||
if loc.get("label"):
|
||||
lines.append(f" {loc['label']}")
|
||||
if loc.get("snippet"):
|
||||
snippet = str(loc["snippet"])
|
||||
snippet_fence = safe_fence(snippet)
|
||||
lines.append(f"{snippet_fence}\n{snippet}\n{snippet_fence}")
|
||||
lines.append(f"```\n{loc['snippet']}\n```")
|
||||
if loc.get("fix_before") or loc.get("fix_after"):
|
||||
lines.append("**Suggested Fix:**")
|
||||
lines.append("```diff")
|
||||
@@ -815,10 +802,6 @@ class StrixTUIApp(App): # type: ignore[misc]
|
||||
self._scan_stop_event = threading.Event()
|
||||
self._scan_completed = threading.Event()
|
||||
self._scan_error: BaseException | None = None
|
||||
self._startup_status = "Starting up"
|
||||
self._startup_status_step = 0
|
||||
self._error_noted_agents: set[str] = set()
|
||||
self._budget_pause_notified = False
|
||||
|
||||
self._spinner_frame_index: int = 0
|
||||
self._sweep_num_squares: int = 6
|
||||
@@ -1032,50 +1015,26 @@ class StrixTUIApp(App): # type: ignore[misc]
|
||||
else:
|
||||
self._agent_graph_sync_future = None
|
||||
try:
|
||||
parent_of, statuses, names, errors = future.result()
|
||||
parent_of, statuses, names = future.result()
|
||||
except Exception:
|
||||
logger.exception("TUI agent graph sync failed")
|
||||
else:
|
||||
for agent_id, status in statuses.items():
|
||||
error = errors.get(agent_id)
|
||||
self.live_view.upsert_agent(
|
||||
agent_id,
|
||||
name=names.get(agent_id, agent_id),
|
||||
parent_id=parent_of.get(agent_id),
|
||||
status=status,
|
||||
error_message=error or "",
|
||||
)
|
||||
if error:
|
||||
if agent_id not in self._error_noted_agents:
|
||||
self._error_noted_agents.add(agent_id)
|
||||
self.live_view.record_agent_error(agent_id, error)
|
||||
else:
|
||||
self._error_noted_agents.discard(agent_id)
|
||||
self._notify_budget_pause(statuses)
|
||||
|
||||
if self._scan_loop is None or self._scan_loop.is_closed():
|
||||
return
|
||||
|
||||
async def collect() -> tuple[
|
||||
dict[str, str | None], dict[str, Any], dict[str, str], dict[str, str]
|
||||
]:
|
||||
async def collect() -> tuple[dict[str, str | None], dict[str, Any], dict[str, str]]:
|
||||
return await self.coordinator.graph_snapshot()
|
||||
|
||||
self._agent_graph_sync_future = asyncio.run_coroutine_threadsafe(collect(), self._scan_loop)
|
||||
|
||||
def _notify_budget_pause(self, statuses: dict[str, Any]) -> None:
|
||||
paused = any(status == "budget_paused" for status in statuses.values())
|
||||
if paused and not self._budget_pause_notified:
|
||||
self._budget_pause_notified = True
|
||||
self.notify(
|
||||
"Budget limit reached \u2014 agents paused. Send a message to continue "
|
||||
"(this extends the budget), or ctrl-q to quit.",
|
||||
severity="warning",
|
||||
timeout=15,
|
||||
)
|
||||
elif not paused:
|
||||
self._budget_pause_notified = False
|
||||
|
||||
def _update_agent_node(self, agent_id: str, agent_data: dict[str, Any]) -> bool:
|
||||
if agent_id not in self.agent_nodes:
|
||||
return False
|
||||
@@ -1088,10 +1047,8 @@ class StrixTUIApp(App): # type: ignore[misc]
|
||||
status_indicators = {
|
||||
"running": "⚪",
|
||||
"waiting": "⏸",
|
||||
"budget_paused": "⏸",
|
||||
"completed": "🟢",
|
||||
"failed": "🔴",
|
||||
"crashed": "🔴",
|
||||
"stopped": "■",
|
||||
}
|
||||
|
||||
@@ -1113,9 +1070,7 @@ class StrixTUIApp(App): # type: ignore[misc]
|
||||
self,
|
||||
) -> tuple[Any, str | None]:
|
||||
if not self.selected_agent_id:
|
||||
return self._get_chat_placeholder_content(
|
||||
f"{self._startup_status}...", f"placeholder-no-agent-{self._startup_status_step}"
|
||||
)
|
||||
return self._get_chat_placeholder_content("Loading...", "placeholder-no-agent")
|
||||
|
||||
events = self._gather_agent_events(self.selected_agent_id)
|
||||
|
||||
@@ -1279,30 +1234,20 @@ class StrixTUIApp(App): # type: ignore[misc]
|
||||
text.append(msg)
|
||||
return (text, Text(), False)
|
||||
|
||||
if status in {"failed", "crashed"}:
|
||||
if status == "failed":
|
||||
error_msg = agent_data.get("error_message", "")
|
||||
text = Text()
|
||||
text.append(error_msg or "Agent failed", style="red")
|
||||
text.append(" · ", style="dim")
|
||||
text.append("Send message to resume", style="dim")
|
||||
if error_msg:
|
||||
text.append(error_msg, style="red")
|
||||
else:
|
||||
text.append("Scan failed", style="red")
|
||||
self._stop_dot_animation()
|
||||
return (text, Text(), False)
|
||||
|
||||
if status in {"waiting", "budget_paused"}:
|
||||
if status == "waiting":
|
||||
text = Text()
|
||||
keymap = Text()
|
||||
if status == "budget_paused":
|
||||
text.append("Budget limit reached", style="yellow")
|
||||
text.append(" \u00b7 ", style="dim")
|
||||
text.append("Send a message to continue", style="dim")
|
||||
keymap = keymap_styled([("ctrl-q", "quit")])
|
||||
else:
|
||||
error_msg = agent_data.get("error_message") or ""
|
||||
if error_msg:
|
||||
text.append(error_msg, style="red")
|
||||
text.append(" \u00b7 ", style="dim")
|
||||
text.append("Send message to resume", style="dim")
|
||||
return (text, keymap, False)
|
||||
text.append("Send message to resume", style="dim")
|
||||
return (text, Text(), False)
|
||||
|
||||
if status == "running":
|
||||
if self._agent_has_real_activity(agent_id):
|
||||
@@ -1527,16 +1472,17 @@ class StrixTUIApp(App): # type: ignore[misc]
|
||||
coordinator=self.coordinator,
|
||||
interactive=True,
|
||||
max_budget_usd=getattr(self.args, "max_budget_usd", None),
|
||||
max_turns=getattr(self.args, "max_turns", DEFAULT_MAX_TURNS),
|
||||
event_sink=self._capture_sdk_event,
|
||||
status_sink=self._capture_startup_status,
|
||||
),
|
||||
)
|
||||
|
||||
except (KeyboardInterrupt, asyncio.CancelledError):
|
||||
logger.info("Scan interrupted by user")
|
||||
except BudgetExceededError:
|
||||
logger.info("Scan stopped: --max-budget limit reached")
|
||||
# Defensive: the runner stops the scan cleanly on budget and
|
||||
# returns, so this normally never propagates. Treat it as a
|
||||
# graceful stop, not a scan error, if it ever does.
|
||||
logger.info("Scan stopped: --max-budget-usd limit reached")
|
||||
except (ConnectionError, TimeoutError) as e:
|
||||
logging.exception("Network error during scan")
|
||||
self._scan_error = e
|
||||
@@ -1561,18 +1507,6 @@ class StrixTUIApp(App): # type: ignore[misc]
|
||||
self._scan_thread = threading.Thread(target=scan_target, daemon=True)
|
||||
self._scan_thread.start()
|
||||
|
||||
def _capture_startup_status(self, phase: str) -> None:
|
||||
try:
|
||||
self.call_from_thread(self._record_startup_status, phase)
|
||||
except RuntimeError:
|
||||
self._record_startup_status(phase)
|
||||
|
||||
def _record_startup_status(self, phase: str) -> None:
|
||||
self._startup_status = phase
|
||||
self._startup_status_step += 1
|
||||
if not self.show_splash and not self.selected_agent_id:
|
||||
self.call_later(self._update_chat_view)
|
||||
|
||||
def _capture_sdk_event(self, agent_id: str, event: Any) -> None:
|
||||
try:
|
||||
self.call_from_thread(self._record_sdk_event, agent_id, event)
|
||||
@@ -1603,10 +1537,8 @@ class StrixTUIApp(App): # type: ignore[misc]
|
||||
status_indicators = {
|
||||
"running": "⚪",
|
||||
"waiting": "⏸",
|
||||
"budget_paused": "⏸",
|
||||
"completed": "🟢",
|
||||
"failed": "🔴",
|
||||
"crashed": "🔴",
|
||||
"stopped": "■",
|
||||
}
|
||||
|
||||
@@ -1650,10 +1582,8 @@ class StrixTUIApp(App): # type: ignore[misc]
|
||||
status_indicators = {
|
||||
"running": "⚪",
|
||||
"waiting": "⏸",
|
||||
"budget_paused": "⏸",
|
||||
"completed": "🟢",
|
||||
"failed": "🔴",
|
||||
"crashed": "🔴",
|
||||
"stopped": "■",
|
||||
}
|
||||
|
||||
@@ -1775,10 +1705,7 @@ class StrixTUIApp(App): # type: ignore[misc]
|
||||
message=message,
|
||||
)
|
||||
if not submitted:
|
||||
if self._scan_completed.is_set():
|
||||
self.notify("The scan has ended; message was not sent", severity="warning")
|
||||
else:
|
||||
self.notify("Scan loop is not ready; message was not sent", severity="warning")
|
||||
self.notify("Scan loop is not ready; message was not sent", severity="warning")
|
||||
return
|
||||
|
||||
self._displayed_events.clear()
|
||||
@@ -1911,7 +1838,7 @@ class StrixTUIApp(App): # type: ignore[misc]
|
||||
webbrowser.open(self._viewer_url)
|
||||
return
|
||||
try:
|
||||
from strix.interface.viewer.server import authorized_url, bundle_is_built, serve
|
||||
from strix.viewer.server import authorized_url, bundle_is_built, serve
|
||||
|
||||
if not bundle_is_built():
|
||||
self._set_viewer_cta("[#eab308]Viewer UI not built[/]")
|
||||
|
||||
@@ -20,7 +20,7 @@ class TuiLiveView:
|
||||
self.events: list[dict[str, Any]] = []
|
||||
self._next_event_id = 1
|
||||
self._open_assistant_event_by_agent: dict[str, dict[str, Any]] = {}
|
||||
self._tool_event_by_agent_and_call_id: dict[tuple[str, str], dict[str, Any]] = {}
|
||||
self._tool_event_by_call_id: dict[str, dict[str, Any]] = {}
|
||||
|
||||
def hydrate_from_run_dir(self, run_dir: Path) -> None:
|
||||
state_dir = runtime_state_dir(run_dir)
|
||||
@@ -82,21 +82,10 @@ class TuiLiveView:
|
||||
current["parent_id"] = parent_id
|
||||
if status is not None:
|
||||
current["status"] = status
|
||||
if error_message is not None:
|
||||
if error_message:
|
||||
current["error_message"] = error_message
|
||||
current["updated_at"] = now
|
||||
|
||||
def record_agent_error(self, agent_id: str, error: str) -> None:
|
||||
self._append_event(
|
||||
agent_id,
|
||||
"chat",
|
||||
{
|
||||
"role": "assistant",
|
||||
"content": (f"An error occurred: {error}\nI'm now waiting for new instructions."),
|
||||
"metadata": {"source": "agent_error"},
|
||||
},
|
||||
)
|
||||
|
||||
def record_user_message(self, agent_id: str, content: str) -> None:
|
||||
self._append_event(
|
||||
agent_id,
|
||||
@@ -223,8 +212,7 @@ class TuiLiveView:
|
||||
timestamp: str | None = None,
|
||||
) -> None:
|
||||
call_id = call["call_id"]
|
||||
event_key = (agent_id, call_id)
|
||||
existing = self._tool_event_by_agent_and_call_id.get(event_key)
|
||||
existing = self._tool_event_by_call_id.get(call_id)
|
||||
tool_data = {
|
||||
"tool_name": call["tool_name"],
|
||||
"args": call["args"],
|
||||
@@ -234,7 +222,7 @@ class TuiLiveView:
|
||||
}
|
||||
if existing is None:
|
||||
event = self._append_event(agent_id, "tool", tool_data, timestamp=timestamp)
|
||||
self._tool_event_by_agent_and_call_id[event_key] = event
|
||||
self._tool_event_by_call_id[call_id] = event
|
||||
else:
|
||||
existing["data"].update(tool_data)
|
||||
self._bump_event(existing, timestamp=timestamp)
|
||||
@@ -250,8 +238,7 @@ class TuiLiveView:
|
||||
timestamp: str | None = None,
|
||||
) -> None:
|
||||
call_id = output["call_id"]
|
||||
event_key = (agent_id, call_id)
|
||||
event = self._tool_event_by_agent_and_call_id.get(event_key)
|
||||
event = self._tool_event_by_call_id.get(call_id)
|
||||
if event is None:
|
||||
event = self._append_event(
|
||||
agent_id,
|
||||
@@ -265,7 +252,7 @@ class TuiLiveView:
|
||||
},
|
||||
timestamp=timestamp,
|
||||
)
|
||||
self._tool_event_by_agent_and_call_id[event_key] = event
|
||||
self._tool_event_by_call_id[call_id] = event
|
||||
|
||||
result = _parse_json_value(output["output"])
|
||||
event["data"]["result"] = result
|
||||
|
||||
@@ -6,7 +6,6 @@ from . import (
|
||||
notes_renderer,
|
||||
proxy_renderer,
|
||||
reporting_renderer,
|
||||
respond_renderer,
|
||||
shell_renderer,
|
||||
thinking_renderer,
|
||||
todo_renderer,
|
||||
@@ -24,7 +23,6 @@ __all__ = [
|
||||
"proxy_renderer",
|
||||
"render_tool_widget",
|
||||
"reporting_renderer",
|
||||
"respond_renderer",
|
||||
"shell_renderer",
|
||||
"thinking_renderer",
|
||||
"todo_renderer",
|
||||
|
||||
@@ -117,8 +117,8 @@ class AgentFinishRenderer(BaseToolRenderer):
|
||||
|
||||
|
||||
@register_tool_renderer
|
||||
class WaitForAgentsRenderer(BaseToolRenderer):
|
||||
tool_name: ClassVar[str] = "wait_for_agents"
|
||||
class WaitForMessageRenderer(BaseToolRenderer):
|
||||
tool_name: ClassVar[str] = "wait_for_message"
|
||||
css_classes: ClassVar[list[str]] = ["tool-call", "agents-graph-tool"]
|
||||
|
||||
@classmethod
|
||||
|
||||
@@ -7,13 +7,6 @@ from .base_renderer import BaseToolRenderer
|
||||
from .registry import register_tool_renderer
|
||||
|
||||
|
||||
def _author_label(note: dict[str, Any]) -> str:
|
||||
if note.get("by_you"):
|
||||
return "you"
|
||||
agent_name = note.get("agent_name")
|
||||
return str(agent_name).strip() if agent_name else ""
|
||||
|
||||
|
||||
@register_tool_renderer
|
||||
class CreateNoteRenderer(BaseToolRenderer):
|
||||
tool_name: ClassVar[str] = "create_note"
|
||||
@@ -130,9 +123,6 @@ class ListNotesRenderer(BaseToolRenderer):
|
||||
text.append("\n - ")
|
||||
text.append(title)
|
||||
text.append(f" ({category})", style="dim")
|
||||
author = _author_label(note)
|
||||
if author:
|
||||
text.append(f" by {author}", style="dim")
|
||||
|
||||
if note_content:
|
||||
text.append("\n ")
|
||||
@@ -166,9 +156,6 @@ class GetNoteRenderer(BaseToolRenderer):
|
||||
text.append("\n ")
|
||||
text.append(title)
|
||||
text.append(f" ({category})", style="dim")
|
||||
author = _author_label(note)
|
||||
if author:
|
||||
text.append(f" by {author}", style="dim")
|
||||
if content:
|
||||
text.append("\n ")
|
||||
text.append(content, style="dim")
|
||||
|
||||
@@ -1,12 +1,11 @@
|
||||
from functools import cache
|
||||
from typing import Any, ClassVar
|
||||
|
||||
from pygments.lexers import PythonLexer
|
||||
from pygments.styles import get_style_by_name
|
||||
from rich.text import Text
|
||||
from textual.widgets import Static
|
||||
|
||||
from strix.report.writer import parse_fenced_code, resolve_lexer
|
||||
|
||||
from .base_renderer import BaseToolRenderer
|
||||
from .registry import register_tool_renderer
|
||||
|
||||
@@ -62,8 +61,8 @@ class CreateVulnerabilityReportRenderer(BaseToolRenderer):
|
||||
return None
|
||||
|
||||
@classmethod
|
||||
def _highlight_code(cls, code: str, language: str | None) -> Text:
|
||||
lexer = resolve_lexer(language, code)
|
||||
def _highlight_python(cls, code: str) -> Text:
|
||||
lexer = PythonLexer()
|
||||
text = Text()
|
||||
|
||||
for token_type, token_value in lexer.get_tokens(code):
|
||||
@@ -235,11 +234,10 @@ class CreateVulnerabilityReportRenderer(BaseToolRenderer):
|
||||
text.append(poc_description)
|
||||
|
||||
if poc_script_code:
|
||||
poc_language, poc_code = parse_fenced_code(poc_script_code)
|
||||
text.append("\n\n")
|
||||
text.append("PoC Code", style=FIELD_STYLE)
|
||||
text.append("\n")
|
||||
text.append_text(cls._highlight_code(poc_code, poc_language))
|
||||
text.append_text(cls._highlight_python(poc_script_code))
|
||||
|
||||
if remediation_steps:
|
||||
text.append("\n\n")
|
||||
@@ -431,117 +429,3 @@ class CreateDependencyReportRenderer(BaseToolRenderer):
|
||||
|
||||
css_classes = cls.get_css_classes("completed")
|
||||
return Static(padded, classes=css_classes)
|
||||
|
||||
|
||||
_LIST_SEVERITY_COLORS = {
|
||||
"critical": "#dc2626",
|
||||
"high": "#ea580c",
|
||||
"medium": "#d97706",
|
||||
"low": "#65a30d",
|
||||
"info": "#0284c7",
|
||||
"none": "#6b7280",
|
||||
}
|
||||
|
||||
|
||||
def _severity_style(severity: Any) -> str:
|
||||
return _LIST_SEVERITY_COLORS.get(str(severity or "").lower(), "#d97706")
|
||||
|
||||
|
||||
def _author_label(report: dict[str, Any]) -> str:
|
||||
if report.get("by_you"):
|
||||
return "you"
|
||||
agent_name = report.get("agent_name")
|
||||
return str(agent_name).strip() if agent_name else ""
|
||||
|
||||
|
||||
@register_tool_renderer
|
||||
class ListReportsRenderer(BaseToolRenderer):
|
||||
tool_name: ClassVar[str] = "list_reports"
|
||||
css_classes: ClassVar[list[str]] = ["tool-call", "reporting-tool"]
|
||||
|
||||
@classmethod
|
||||
def render(cls, tool_data: dict[str, Any]) -> Static:
|
||||
result = _coerce_dict(tool_data.get("result"))
|
||||
|
||||
text = Text()
|
||||
text.append("◆ ", style="#ef4444")
|
||||
text.append("reports", style="dim")
|
||||
|
||||
if isinstance(tool_data.get("result"), str) and str(tool_data["result"]).strip():
|
||||
text.append("\n ")
|
||||
text.append(str(tool_data["result"]).strip(), style="dim")
|
||||
elif result.get("success"):
|
||||
total = result.get("total_count", 0)
|
||||
reports = _coerce_list_of_dicts(result.get("reports"))
|
||||
counts = _coerce_dict(result.get("severity_counts"))
|
||||
|
||||
text.append(f" ({total})", style="dim")
|
||||
for sev, count in counts.items():
|
||||
text.append(" ")
|
||||
text.append(f"{sev} {count}", style=_severity_style(sev))
|
||||
|
||||
if not reports:
|
||||
text.append("\n ")
|
||||
text.append("No reports filed yet", style="dim")
|
||||
else:
|
||||
for report in reports:
|
||||
rid = str(report.get("id", "")).strip()
|
||||
title = str(report.get("title", "")).strip() or "(untitled)"
|
||||
severity = str(report.get("severity", "")).strip()
|
||||
text.append("\n - ")
|
||||
if severity:
|
||||
text.append(severity.upper(), style=f"bold {_severity_style(severity)}")
|
||||
text.append(" ")
|
||||
if rid:
|
||||
text.append(f"{rid} ", style="dim")
|
||||
text.append(title)
|
||||
author = _author_label(report)
|
||||
if author:
|
||||
text.append(f" ({author})", style="dim")
|
||||
else:
|
||||
text.append("\n ")
|
||||
text.append("Loading...", style="dim")
|
||||
|
||||
css_classes = cls.get_css_classes("completed")
|
||||
return Static(text, classes=css_classes)
|
||||
|
||||
|
||||
@register_tool_renderer
|
||||
class GetReportRenderer(BaseToolRenderer):
|
||||
tool_name: ClassVar[str] = "get_report"
|
||||
css_classes: ClassVar[list[str]] = ["tool-call", "reporting-tool"]
|
||||
|
||||
@classmethod
|
||||
def render(cls, tool_data: dict[str, Any]) -> Static:
|
||||
result = _coerce_dict(tool_data.get("result"))
|
||||
|
||||
text = Text()
|
||||
text.append("◆ ", style="#ef4444")
|
||||
text.append("report read", style="dim")
|
||||
|
||||
report = _coerce_dict(result.get("report")) if result.get("success") else {}
|
||||
if report:
|
||||
rid = str(report.get("id", "")).strip()
|
||||
title = str(report.get("title", "")).strip() or "(untitled)"
|
||||
severity = str(report.get("severity", "")).strip()
|
||||
text.append("\n ")
|
||||
if severity:
|
||||
text.append(severity.upper(), style=f"bold {_severity_style(severity)}")
|
||||
text.append(" ")
|
||||
if rid:
|
||||
text.append(f"{rid} ", style="dim")
|
||||
text.append(title)
|
||||
author = _author_label(report)
|
||||
if author:
|
||||
text.append(f" ({author})", style="dim")
|
||||
target = str(report.get("target", "")).strip()
|
||||
if target:
|
||||
text.append("\n ")
|
||||
text.append(target, style="dim")
|
||||
else:
|
||||
text.append("\n ")
|
||||
detail = result.get("error") if result.get("success") is False else None
|
||||
text.append(str(detail) if detail else "Loading...", style="dim")
|
||||
|
||||
css_classes = cls.get_css_classes("completed")
|
||||
return Static(text, classes=css_classes)
|
||||
|
||||
@@ -1,35 +0,0 @@
|
||||
from typing import Any, ClassVar
|
||||
|
||||
from rich.text import Text
|
||||
from textual.widgets import Static
|
||||
|
||||
from .agent_message_renderer import AgentMessageRenderer
|
||||
from .base_renderer import BaseToolRenderer
|
||||
from .registry import register_tool_renderer
|
||||
|
||||
|
||||
@register_tool_renderer
|
||||
class RespondToUserRenderer(BaseToolRenderer):
|
||||
"""Render a reply as the agent's own prose, not as a tool call.
|
||||
|
||||
``respond_to_user`` carries the message the user is meant to read, so it
|
||||
gets the same markdown treatment as a plain assistant turn.
|
||||
"""
|
||||
|
||||
tool_name: ClassVar[str] = "respond_to_user"
|
||||
css_classes: ClassVar[list[str]] = ["tool-call", "respond-tool"]
|
||||
|
||||
@classmethod
|
||||
def render(cls, tool_data: dict[str, Any]) -> Static:
|
||||
args = tool_data.get("args", {})
|
||||
message = args.get("message", "")
|
||||
|
||||
text = Text()
|
||||
if message:
|
||||
text.append_text(AgentMessageRenderer.render_simple(message))
|
||||
text.append("\n\n")
|
||||
text.append("○ ", style="#6b7280")
|
||||
text.append("waiting for your reply", style="dim")
|
||||
|
||||
css_classes = cls.get_css_classes(tool_data.get("status", "unknown"))
|
||||
return Static(text, classes=css_classes)
|
||||
@@ -1,395 +0,0 @@
|
||||
"""Update notifications and self-update for the strix CLI.
|
||||
|
||||
Follows the pattern used by tools like gh, uv, and pip: a background,
|
||||
rate-limited (once per 24h) check against the release source, a cached
|
||||
result in ``~/.strix``, a non-intrusive notice with the upgrade command
|
||||
for the detected install method, and a ``strix --update`` self-update
|
||||
path for the standalone binary install.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import hashlib
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import platform
|
||||
import shutil
|
||||
import stat
|
||||
import subprocess
|
||||
import sys
|
||||
import tarfile
|
||||
import tempfile
|
||||
import threading
|
||||
import time
|
||||
import zipfile
|
||||
from pathlib import Path
|
||||
from typing import cast
|
||||
|
||||
import requests
|
||||
from rich.console import Console
|
||||
from rich.prompt import Prompt
|
||||
|
||||
from strix.telemetry._common import get_version
|
||||
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
GITHUB_REPO = "usestrix/strix"
|
||||
PYPI_PACKAGE = "strix-agent"
|
||||
CHECK_INTERVAL_SECONDS = 24 * 60 * 60
|
||||
REQUEST_TIMEOUT_SECONDS = 5
|
||||
|
||||
_CACHE_PATH = Path.home() / ".strix" / "update-check.json"
|
||||
|
||||
_background_thread: threading.Thread | None = None
|
||||
|
||||
|
||||
def _is_disabled() -> bool:
|
||||
return bool(os.environ.get("STRIX_NO_UPDATE_CHECK")) or any(
|
||||
os.environ.get(key)
|
||||
for key in ("CI", "GITHUB_ACTIONS", "GITLAB_CI", "JENKINS_URL", "BUILDKITE", "CIRCLECI")
|
||||
)
|
||||
|
||||
|
||||
def is_binary_install() -> bool:
|
||||
return bool(getattr(sys, "frozen", False))
|
||||
|
||||
|
||||
def get_install_method() -> str:
|
||||
if is_binary_install():
|
||||
return "binary"
|
||||
prefix = str(Path(sys.prefix)).replace("\\", "/")
|
||||
if "/pipx/" in prefix or prefix.endswith("/pipx"):
|
||||
return "pipx"
|
||||
if "/uv/tools/" in prefix:
|
||||
return "uv"
|
||||
return "pip"
|
||||
|
||||
|
||||
def get_upgrade_command(method: str | None = None) -> str:
|
||||
method = method or get_install_method()
|
||||
commands = {
|
||||
"binary": "strix --update",
|
||||
"pipx": "pipx upgrade strix-agent",
|
||||
"uv": "uv tool upgrade strix-agent",
|
||||
"pip": "pip install --upgrade strix-agent",
|
||||
}
|
||||
return commands[method]
|
||||
|
||||
|
||||
def _parse_version(value: str) -> tuple[int, ...] | None:
|
||||
parts = value.strip().lstrip("v").split(".")
|
||||
try:
|
||||
return tuple(int(part) for part in parts)
|
||||
except ValueError:
|
||||
return None
|
||||
|
||||
|
||||
def _is_newer(latest: str, current: str) -> bool:
|
||||
latest_parts = _parse_version(latest)
|
||||
current_parts = _parse_version(current)
|
||||
if latest_parts is None or current_parts is None:
|
||||
return False
|
||||
return latest_parts > current_parts
|
||||
|
||||
|
||||
def _fetch_latest_version() -> str | None:
|
||||
try:
|
||||
if is_binary_install():
|
||||
response = requests.get(
|
||||
f"https://api.github.com/repos/{GITHUB_REPO}/releases/latest",
|
||||
timeout=REQUEST_TIMEOUT_SECONDS,
|
||||
)
|
||||
response.raise_for_status()
|
||||
tag = response.json().get("tag_name", "")
|
||||
return tag.lstrip("v") or None
|
||||
response = requests.get(
|
||||
f"https://pypi.org/pypi/{PYPI_PACKAGE}/json",
|
||||
timeout=REQUEST_TIMEOUT_SECONDS,
|
||||
)
|
||||
response.raise_for_status()
|
||||
version = response.json().get("info", {}).get("version")
|
||||
return str(version) if version else None
|
||||
except Exception: # noqa: BLE001
|
||||
logger.debug("update check failed", exc_info=True)
|
||||
return None
|
||||
|
||||
|
||||
def _fetch_asset_digest(version: str, filename: str) -> str | None:
|
||||
"""Return the expected sha256 (hex) for a release asset, if the API provides one."""
|
||||
try:
|
||||
response = requests.get(
|
||||
f"https://api.github.com/repos/{GITHUB_REPO}/releases/tags/v{version}",
|
||||
timeout=REQUEST_TIMEOUT_SECONDS,
|
||||
)
|
||||
response.raise_for_status()
|
||||
for asset in response.json().get("assets", []):
|
||||
if asset.get("name") == filename:
|
||||
digest = asset.get("digest") or ""
|
||||
if digest.startswith("sha256:"):
|
||||
return digest.removeprefix("sha256:")
|
||||
except Exception: # noqa: BLE001
|
||||
logger.debug("release asset digest lookup failed", exc_info=True)
|
||||
return None
|
||||
|
||||
|
||||
def _sha256_file(path: Path) -> str:
|
||||
digest = hashlib.sha256()
|
||||
with path.open("rb") as f:
|
||||
for chunk in iter(lambda: f.read(1 << 20), b""):
|
||||
digest.update(chunk)
|
||||
return digest.hexdigest()
|
||||
|
||||
|
||||
def _read_cache() -> dict[str, object]:
|
||||
try:
|
||||
with _CACHE_PATH.open(encoding="utf-8") as f:
|
||||
data = json.load(f)
|
||||
if isinstance(data, dict):
|
||||
return cast("dict[str, object]", data)
|
||||
except Exception: # noqa: BLE001, S110
|
||||
pass # nosec B110
|
||||
return {}
|
||||
|
||||
|
||||
def _write_cache(**fields: object) -> None:
|
||||
try:
|
||||
cache = _read_cache()
|
||||
cache.update(fields)
|
||||
_CACHE_PATH.parent.mkdir(parents=True, exist_ok=True)
|
||||
_CACHE_PATH.write_text(json.dumps(cache), encoding="utf-8")
|
||||
except Exception: # noqa: BLE001, S110
|
||||
pass # nosec B110
|
||||
|
||||
|
||||
def skip_version(version: str) -> None:
|
||||
"""Remember not to prompt again for this version (newer releases still notify)."""
|
||||
_write_cache(skipped_version=version)
|
||||
|
||||
|
||||
def _refresh_cache() -> None:
|
||||
latest = _fetch_latest_version()
|
||||
if latest:
|
||||
_write_cache(latest_version=latest, checked_at=time.time())
|
||||
|
||||
|
||||
def start_background_check() -> None:
|
||||
"""Refresh the cached latest-version info in a daemon thread (at most once per 24h)."""
|
||||
global _background_thread # noqa: PLW0603
|
||||
if _is_disabled():
|
||||
return
|
||||
cache = _read_cache()
|
||||
checked_at = cache.get("checked_at")
|
||||
if isinstance(checked_at, int | float) and time.time() - checked_at < CHECK_INTERVAL_SECONDS:
|
||||
return
|
||||
_background_thread = threading.Thread(target=_refresh_cache, daemon=True)
|
||||
_background_thread.start()
|
||||
|
||||
|
||||
def get_available_update(*, respect_skip: bool = True) -> str | None:
|
||||
"""Return the newer version from the cache, or None if up to date / unknown."""
|
||||
if _is_disabled():
|
||||
return None
|
||||
if _background_thread is not None:
|
||||
_background_thread.join(timeout=0.2)
|
||||
cache = _read_cache()
|
||||
latest = cache.get("latest_version")
|
||||
current = get_version()
|
||||
if not isinstance(latest, str) or current == "unknown" or not _is_newer(latest, current):
|
||||
return None
|
||||
if respect_skip and cache.get("skipped_version") == latest:
|
||||
return None
|
||||
return latest
|
||||
|
||||
|
||||
def notify_update(console: Console) -> None:
|
||||
latest = get_available_update()
|
||||
if not latest:
|
||||
return
|
||||
console.print(
|
||||
f"[#eab308]A new version of strix is available:[/] "
|
||||
f"[dim]{get_version()}[/] [dim]→[/] [bold #22c55e]{latest}[/]"
|
||||
f" [dim]·[/] [#60a5fa]{get_upgrade_command()}[/]"
|
||||
)
|
||||
console.print()
|
||||
|
||||
|
||||
def run_package_upgrade(console: Console, method: str) -> bool:
|
||||
"""Upgrade a package-manager install by running its upgrade command."""
|
||||
command = get_upgrade_command(method).split()
|
||||
console.print(f"[dim]Running[/] [#60a5fa]{' '.join(command)}[/]")
|
||||
try:
|
||||
result = subprocess.run(command, check=False) # noqa: S603
|
||||
except OSError as e:
|
||||
console.print(f"[bold red]Update failed:[/] {e}")
|
||||
return False
|
||||
if result.returncode != 0:
|
||||
console.print(
|
||||
f"[bold red]Update failed[/] [dim](exit code {result.returncode}).[/] "
|
||||
f"Run it manually: [#60a5fa]{get_upgrade_command(method)}[/]"
|
||||
)
|
||||
return False
|
||||
console.print("[#22c55e]✓ strix updated — restart the scan to use the new version[/]")
|
||||
return True
|
||||
|
||||
|
||||
def prompt_update_if_available(console: Console) -> bool:
|
||||
"""Offer an interactive update before a scan starts.
|
||||
|
||||
Returns True if strix was updated (caller should re-exec / exit).
|
||||
"""
|
||||
latest = get_available_update()
|
||||
if not latest or not sys.stdin.isatty() or not sys.stdout.isatty():
|
||||
return False
|
||||
console.print()
|
||||
console.print(
|
||||
f"[#eab308]A new version of strix is available:[/] "
|
||||
f"[dim]{get_version()}[/] [dim]→[/] [bold #22c55e]{latest}[/]"
|
||||
)
|
||||
console.print(
|
||||
"[dim] y — update now n — not now (ask again next run) s — skip this version[/]"
|
||||
)
|
||||
choice = Prompt.ask("Update strix?", choices=["y", "n", "s"], default="n")
|
||||
console.print()
|
||||
if choice == "s":
|
||||
skip_version(latest)
|
||||
return False
|
||||
if choice != "y":
|
||||
return False
|
||||
method = get_install_method()
|
||||
if method == "binary":
|
||||
return self_update(console, version=latest)
|
||||
return run_package_upgrade(console, method)
|
||||
|
||||
|
||||
def _release_target() -> str | None:
|
||||
raw_os = platform.system().lower()
|
||||
os_name = {"darwin": "macos", "linux": "linux", "windows": "windows"}.get(raw_os)
|
||||
arch = platform.machine().lower()
|
||||
arch = {"aarch64": "arm64", "amd64": "x86_64"}.get(arch, arch)
|
||||
if os_name is None:
|
||||
return None
|
||||
target = f"{os_name}-{arch}"
|
||||
supported = {
|
||||
"linux-x86_64",
|
||||
"linux-arm64",
|
||||
"macos-x86_64",
|
||||
"macos-arm64",
|
||||
"windows-x86_64",
|
||||
}
|
||||
return target if target in supported else None
|
||||
|
||||
|
||||
def _download_and_replace(version: str, target: str, console: Console) -> bool:
|
||||
is_windows = target.startswith("windows")
|
||||
archive_ext = ".zip" if is_windows else ".tar.gz"
|
||||
filename = f"strix-{version}-{target}{archive_ext}"
|
||||
url = f"https://github.com/{GITHUB_REPO}/releases/download/v{version}/{filename}"
|
||||
binary_name = f"strix-{version}-{target}" + (".exe" if is_windows else "")
|
||||
current_exe = Path(sys.executable).resolve()
|
||||
|
||||
with tempfile.TemporaryDirectory() as tmp:
|
||||
tmp_dir = Path(tmp)
|
||||
archive_path = tmp_dir / filename
|
||||
console.print(f"[dim]Downloading[/] {url}")
|
||||
with requests.get( # nosec B113
|
||||
url,
|
||||
stream=True,
|
||||
timeout=REQUEST_TIMEOUT_SECONDS * 12,
|
||||
) as response:
|
||||
response.raise_for_status()
|
||||
with archive_path.open("wb") as f:
|
||||
for chunk in response.iter_content(chunk_size=1 << 20):
|
||||
f.write(chunk)
|
||||
|
||||
expected_digest = _fetch_asset_digest(version, filename)
|
||||
if expected_digest:
|
||||
actual_digest = _sha256_file(archive_path)
|
||||
if actual_digest != expected_digest:
|
||||
raise RuntimeError(
|
||||
f"checksum mismatch for {filename}: "
|
||||
f"expected sha256 {expected_digest}, got {actual_digest}"
|
||||
)
|
||||
else:
|
||||
console.print("[dim yellow]No published checksum available; skipping verification[/]")
|
||||
|
||||
if is_windows:
|
||||
with zipfile.ZipFile(archive_path) as zf:
|
||||
zf.extract(binary_name, tmp_dir)
|
||||
else:
|
||||
with tarfile.open(archive_path, "r:gz") as tf:
|
||||
tf.extract(binary_name, tmp_dir, filter="data")
|
||||
|
||||
new_binary = tmp_dir / binary_name
|
||||
new_binary.chmod(new_binary.stat().st_mode | stat.S_IXUSR | stat.S_IXGRP | stat.S_IXOTH)
|
||||
|
||||
staged = current_exe.with_name(current_exe.name + ".new")
|
||||
try:
|
||||
shutil.copy2(new_binary, staged)
|
||||
if is_windows:
|
||||
# Windows can't replace a running executable in place; move it aside first.
|
||||
old = current_exe.with_name(current_exe.name + ".old")
|
||||
old.unlink(missing_ok=True)
|
||||
current_exe.rename(old)
|
||||
try:
|
||||
staged.replace(current_exe)
|
||||
except Exception:
|
||||
old.rename(current_exe)
|
||||
raise
|
||||
else:
|
||||
staged.replace(current_exe)
|
||||
except Exception:
|
||||
staged.unlink(missing_ok=True)
|
||||
raise
|
||||
return True
|
||||
|
||||
|
||||
def self_update(console: Console | None = None, version: str | None = None) -> bool:
|
||||
"""Replace the running standalone binary with the latest release.
|
||||
|
||||
Returns True on success. For package-manager installs this only
|
||||
prints the right upgrade command and returns False.
|
||||
"""
|
||||
console = console or Console()
|
||||
|
||||
if not is_binary_install():
|
||||
method = get_install_method()
|
||||
console.print(
|
||||
f"[#eab308]This strix was installed via {method};[/] "
|
||||
f"upgrade it with: [#60a5fa]{get_upgrade_command(method)}[/]"
|
||||
)
|
||||
return False
|
||||
|
||||
latest = version or _fetch_latest_version()
|
||||
if not latest:
|
||||
console.print("[bold red]Could not determine the latest strix version.[/]")
|
||||
return False
|
||||
|
||||
current = get_version()
|
||||
if current != "unknown" and not _is_newer(latest, current):
|
||||
console.print(f"[#22c55e]strix {current} is already the latest version.[/]")
|
||||
return True
|
||||
|
||||
target = _release_target()
|
||||
if not target:
|
||||
console.print(
|
||||
f"[bold red]No prebuilt binary for this platform "
|
||||
f"({platform.system()}/{platform.machine()}).[/]"
|
||||
)
|
||||
return False
|
||||
|
||||
try:
|
||||
_download_and_replace(latest, target, console)
|
||||
except Exception as e: # noqa: BLE001
|
||||
logger.debug("self-update failed", exc_info=True)
|
||||
console.print(f"[bold red]Update failed:[/] {e}")
|
||||
console.print(
|
||||
"[dim]You can reinstall manually with:[/] "
|
||||
"[#60a5fa]curl -sSL https://strix.ai/install | bash[/]"
|
||||
)
|
||||
return False
|
||||
|
||||
_write_cache(latest_version=latest, checked_at=time.time())
|
||||
console.print(f"[#22c55e]✓ Updated strix to {latest}[/]")
|
||||
return True
|
||||
+106
-145
@@ -11,10 +11,11 @@ import tempfile
|
||||
from dataclasses import dataclass, field
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
from urllib.error import HTTPError, URLError
|
||||
from urllib.parse import urlparse
|
||||
from urllib.request import Request, urlopen
|
||||
|
||||
import docker
|
||||
import requests
|
||||
from docker.errors import DockerException, ImageNotFound
|
||||
from rich.console import Console
|
||||
from rich.panel import Panel
|
||||
@@ -252,20 +253,6 @@ def _llm_usage(report_state: Any) -> dict[str, Any]:
|
||||
return usage if isinstance(usage, dict) else {}
|
||||
|
||||
|
||||
def _is_subscription(report_state: Any) -> bool:
|
||||
"""Whether this run uses a model subscription (no metered cost).
|
||||
|
||||
Prefers the run record so it's correct for hydrated/resumed runs; falls back
|
||||
to current settings.
|
||||
"""
|
||||
record = getattr(report_state, "run_record", None)
|
||||
if isinstance(record, dict) and record.get("auth_mode"):
|
||||
return record.get("auth_mode") == "subscription"
|
||||
from strix.config import codex
|
||||
|
||||
return codex.auth_mode(load_settings().llm.model) == "subscription"
|
||||
|
||||
|
||||
def _int_stat(usage: dict[str, Any], key: str) -> int:
|
||||
try:
|
||||
return max(0, int(usage.get(key) or 0))
|
||||
@@ -290,27 +277,17 @@ def _detail_value(usage: dict[str, Any], detail_key: str, value_key: str) -> int
|
||||
return _int_stat(details, value_key)
|
||||
|
||||
|
||||
def has_model_response(report_state: Any) -> bool:
|
||||
usage = _llm_usage(report_state)
|
||||
return bool(usage) and _int_stat(usage, "requests") > 0
|
||||
|
||||
|
||||
def _build_llm_usage_stats(
|
||||
stats_text: Text,
|
||||
report_state: Any,
|
||||
*,
|
||||
live: bool = False,
|
||||
) -> None:
|
||||
subscription = _is_subscription(report_state)
|
||||
usage = _llm_usage(report_state)
|
||||
if not usage or _int_stat(usage, "requests") <= 0:
|
||||
stats_text.append("\n")
|
||||
stats_text.append("Cost ", style="dim")
|
||||
if subscription:
|
||||
stats_text.append("$0.00 ", style="#22c55e")
|
||||
stats_text.append("(subscription) ", style="dim")
|
||||
else:
|
||||
stats_text.append("$0.0000 ", style="#fbbf24")
|
||||
stats_text.append("$0.0000 ", style="#fbbf24")
|
||||
stats_text.append("· ", style="dim white")
|
||||
stats_text.append("Tokens ", style="dim")
|
||||
stats_text.append("0", style="white")
|
||||
@@ -335,12 +312,7 @@ def _build_llm_usage_stats(
|
||||
stats_text.append("Output Tokens ", style="dim")
|
||||
stats_text.append(format_token_count(output_tokens), style="white")
|
||||
|
||||
if subscription:
|
||||
stats_text.append(" · ", style="dim white")
|
||||
stats_text.append("Cost ", style="dim")
|
||||
stats_text.append("$0.00", style="#22c55e")
|
||||
stats_text.append(" (subscription)", style="dim")
|
||||
elif live or cost > 0:
|
||||
if live or cost > 0:
|
||||
stats_text.append(" · ", style="dim white")
|
||||
stats_text.append("Cost ", style="dim")
|
||||
stats_text.append(f"${cost:.4f}", style="#fbbf24")
|
||||
@@ -365,9 +337,6 @@ def build_live_stats_text(report_state: Any) -> Text:
|
||||
model = load_settings().llm.model or "unknown"
|
||||
stats_text.append("Model ", style="dim")
|
||||
stats_text.append(str(model), style="white")
|
||||
if _is_subscription(report_state):
|
||||
stats_text.append(" · ", style="dim white")
|
||||
stats_text.append("ChatGPT subscription", style="#22c55e")
|
||||
stats_text.append("\n")
|
||||
|
||||
vuln_count = len(report_state.vulnerability_reports)
|
||||
@@ -410,10 +379,6 @@ def build_tui_stats_text(report_state: Any) -> Text:
|
||||
|
||||
model = load_settings().llm.model or "unknown"
|
||||
stats_text.append(str(model), style="white")
|
||||
subscription = _is_subscription(report_state)
|
||||
if subscription:
|
||||
stats_text.append("\n")
|
||||
stats_text.append("ChatGPT subscription", style="#22c55e")
|
||||
|
||||
usage = _llm_usage(report_state)
|
||||
if usage and _int_stat(usage, "total_tokens") > 0:
|
||||
@@ -423,10 +388,7 @@ def build_tui_stats_text(report_state: Any) -> Text:
|
||||
style="white",
|
||||
)
|
||||
cost = _float_stat(usage, "cost")
|
||||
if subscription:
|
||||
stats_text.append(" · ", style="white")
|
||||
stats_text.append("$0.00", style="white")
|
||||
elif cost > 0:
|
||||
if cost > 0:
|
||||
stats_text.append(" · ", style="white")
|
||||
stats_text.append(f"${cost:.2f}", style="white")
|
||||
|
||||
@@ -1092,12 +1054,13 @@ def resolve_diff_scope_context(
|
||||
def _is_http_git_repo(url: str) -> bool:
|
||||
check_url = f"{url.rstrip('/')}/info/refs?service=git-upload-pack"
|
||||
try:
|
||||
resp = requests.get(check_url, headers={"User-Agent": "git/strix"}, timeout=10)
|
||||
except (requests.RequestException, ValueError):
|
||||
req = Request(check_url, headers={"User-Agent": "git/strix"}) # noqa: S310
|
||||
with urlopen(req, timeout=10) as resp: # noqa: S310 # nosec B310
|
||||
return "x-git-upload-pack-advertisement" in resp.headers.get("Content-Type", "")
|
||||
except HTTPError as e:
|
||||
return e.code == 401
|
||||
except (URLError, OSError, ValueError):
|
||||
return False
|
||||
if resp.status_code >= 400:
|
||||
return resp.status_code == 401
|
||||
return "x-git-upload-pack-advertisement" in resp.headers.get("Content-Type", "")
|
||||
|
||||
|
||||
def infer_target_type(target: str) -> tuple[str, dict[str, str]]: # noqa: PLR0911
|
||||
@@ -1136,7 +1099,6 @@ def infer_target_type(target: str) -> tuple[str, dict[str, str]]: # noqa: PLR09
|
||||
try:
|
||||
if path.exists():
|
||||
if path.is_dir():
|
||||
check_mountable_dir(path)
|
||||
return "local_code", {"target_path": str(path.resolve())}
|
||||
raise ValueError(f"Path exists but is not a directory: {target}")
|
||||
except (OSError, RuntimeError) as e:
|
||||
@@ -1185,7 +1147,9 @@ def read_target_list_file(path_str: str) -> list[str]:
|
||||
if (target := line.strip()) and not target.startswith("#")
|
||||
]
|
||||
except UnicodeDecodeError as e:
|
||||
raise ValueError(f"Target list file '{path_str}' must be valid UTF-8 text: {e!s}") from e
|
||||
raise ValueError(
|
||||
f"Target list file '{path_str}' must be valid UTF-8 text: {e!s}"
|
||||
) from e
|
||||
except OSError as e:
|
||||
raise ValueError(f"Failed to read target list file '{path_str}': {e!s}") from e
|
||||
|
||||
@@ -1265,7 +1229,7 @@ def collect_local_sources(targets_info: list[dict[str, Any]]) -> list[dict[str,
|
||||
{
|
||||
"source_path": details["target_path"],
|
||||
"workspace_subdir": workspace_subdir,
|
||||
"protect_metadata": True,
|
||||
"mount": bool(details.get("mount", False)),
|
||||
}
|
||||
)
|
||||
|
||||
@@ -1274,126 +1238,123 @@ def collect_local_sources(targets_info: list[dict[str, Any]]) -> list[dict[str,
|
||||
{
|
||||
"source_path": details["cloned_repo_path"],
|
||||
"workspace_subdir": workspace_subdir,
|
||||
"protect_metadata": False,
|
||||
"mount": False,
|
||||
}
|
||||
)
|
||||
|
||||
return local_sources
|
||||
|
||||
|
||||
# Refused along with everything under them.
|
||||
_FORBIDDEN_MOUNT_TREES = frozenset(
|
||||
{
|
||||
"/bin",
|
||||
"/sbin",
|
||||
"/usr",
|
||||
"/etc",
|
||||
"/lib",
|
||||
"/lib64",
|
||||
"/nix/store",
|
||||
"/run/current-system/sw",
|
||||
"/Applications",
|
||||
"/Library",
|
||||
"/System",
|
||||
"/dev",
|
||||
"/boot",
|
||||
"/proc",
|
||||
"/sys",
|
||||
}
|
||||
)
|
||||
def directory_size_bytes(path: Path) -> int:
|
||||
"""Total size in bytes of regular files under ``path`` (symlinks not followed).
|
||||
|
||||
# Refused themselves, but they hold projects too, so their contents are fine.
|
||||
_FORBIDDEN_MOUNT_ROOTS = frozenset(
|
||||
{
|
||||
"/",
|
||||
"/private",
|
||||
"/var",
|
||||
"/opt",
|
||||
"/home",
|
||||
"/root",
|
||||
"/srv",
|
||||
"/Users",
|
||||
"/Volumes",
|
||||
}
|
||||
)
|
||||
Best-effort: files that disappear or can't be stat'd mid-walk are skipped.
|
||||
Used as a cheap (stat-only) pre-flight to estimate the cost of streaming a
|
||||
local target into the sandbox before we actually try to copy it.
|
||||
|
||||
_FORBIDDEN_WINDOWS_TREE_NAMES = frozenset(
|
||||
{"windows", "program files", "program files (x86)", "programdata"}
|
||||
)
|
||||
Directories that can't be listed (e.g. permission denied) are logged and
|
||||
skipped rather than silently dropped — so an under-count is at least
|
||||
visible — but the returned total then excludes their contents.
|
||||
"""
|
||||
|
||||
_FORBIDDEN_MOUNT_DIR_NAMES = frozenset(
|
||||
{
|
||||
".ssh",
|
||||
".tsh",
|
||||
".brev",
|
||||
".gnupg",
|
||||
".aws",
|
||||
".azure",
|
||||
".kube",
|
||||
".docker",
|
||||
".config",
|
||||
".npm",
|
||||
".pki",
|
||||
".terraform.d",
|
||||
}
|
||||
)
|
||||
def _on_walk_error(error: OSError) -> None:
|
||||
logger.warning("Could not read %s while measuring size: %s", error.filename, error)
|
||||
|
||||
total = 0
|
||||
for root, _dirs, files in os.walk(path, followlinks=False, onerror=_on_walk_error):
|
||||
for name in files:
|
||||
file_path = os.path.join(root, name) # noqa: PTH118
|
||||
try:
|
||||
if os.path.islink(file_path): # noqa: PTH114
|
||||
continue
|
||||
total += os.path.getsize(file_path) # noqa: PTH202
|
||||
except OSError:
|
||||
continue
|
||||
return total
|
||||
|
||||
|
||||
def _is_within(path: Path, ancestor: Path) -> bool:
|
||||
ancestor_parts = [part.casefold() for part in ancestor.parts]
|
||||
path_parts = [part.casefold() for part in path.parts]
|
||||
return path_parts[: len(ancestor_parts)] == ancestor_parts
|
||||
def find_oversized_local_targets(
|
||||
targets_info: list[dict[str, Any]], max_bytes: int
|
||||
) -> list[tuple[str, int]]:
|
||||
"""Return ``(path, size_bytes)`` for non-mounted local targets over ``max_bytes``.
|
||||
|
||||
Mounted targets are bind-mounted rather than copied, so their size is
|
||||
irrelevant and they are excluded. A ``max_bytes`` of zero or less disables
|
||||
the check entirely (returns no targets).
|
||||
"""
|
||||
if max_bytes <= 0:
|
||||
return []
|
||||
oversized: list[tuple[str, int]] = []
|
||||
for target in targets_info:
|
||||
if target.get("type") != "local_code":
|
||||
continue
|
||||
details = target.get("details") or {}
|
||||
if details.get("mount"):
|
||||
continue
|
||||
target_path = details.get("target_path")
|
||||
if not target_path:
|
||||
continue
|
||||
size = directory_size_bytes(Path(target_path))
|
||||
if size > max_bytes:
|
||||
oversized.append((target_path, size))
|
||||
return oversized
|
||||
|
||||
|
||||
def check_mountable_dir(path: Path) -> None:
|
||||
resolved = path.resolve()
|
||||
if not resolved.is_dir():
|
||||
raise ValueError(f"'{path}' is not an existing directory.")
|
||||
def build_mount_targets_info(mount_paths: list[str]) -> list[dict[str, Any]]:
|
||||
"""Build ``targets_info`` entries for ``--mount`` directories.
|
||||
|
||||
# Both the literal and the resolved form: macOS reaches /etc through the
|
||||
# /private/etc symlink, and only the resolved path is compared below.
|
||||
exact = {str(Path(root)).casefold() for root in _FORBIDDEN_MOUNT_ROOTS}
|
||||
exact |= {str(Path(root).resolve()).casefold() for root in _FORBIDDEN_MOUNT_ROOTS}
|
||||
exact.add(str(Path.home().resolve()).casefold())
|
||||
tree_roots = set(_FORBIDDEN_MOUNT_TREES)
|
||||
if os.name == "nt":
|
||||
drive = Path(resolved.anchor)
|
||||
tree_roots |= {str(drive / name) for name in _FORBIDDEN_WINDOWS_TREE_NAMES}
|
||||
exact.add(str(drive / "Users").casefold())
|
||||
trees = [Path(root) for root in tree_roots] + [Path(root).resolve() for root in tree_roots]
|
||||
if (
|
||||
str(resolved).casefold() in exact
|
||||
or resolved.parent == resolved
|
||||
or any(_is_within(resolved, tree) for tree in trees)
|
||||
):
|
||||
raise ValueError(
|
||||
f"Refusing to mount '{resolved}' into the sandbox: it is a system "
|
||||
"or home directory, not a codebase. Point the target at the "
|
||||
"project directory you want tested."
|
||||
)
|
||||
|
||||
credential = next(
|
||||
(part for part in resolved.parts if part.casefold() in _FORBIDDEN_MOUNT_DIR_NAMES), None
|
||||
)
|
||||
if credential is not None:
|
||||
raise ValueError(
|
||||
f"Refusing to mount '{resolved}' into the sandbox: '{credential}' "
|
||||
"holds credentials, not code."
|
||||
Each path must be an existing local directory; it is bind-mounted into the
|
||||
sandbox (read-only) instead of being copied file-by-file. Raises
|
||||
``ValueError`` for an empty path, or one that does not exist or is not a
|
||||
directory.
|
||||
"""
|
||||
targets_info: list[dict[str, Any]] = []
|
||||
for raw in mount_paths:
|
||||
if not raw or not raw.strip():
|
||||
raise ValueError("--mount path must not be empty.")
|
||||
path = Path(raw).expanduser()
|
||||
try:
|
||||
resolved = path.resolve()
|
||||
is_dir = resolved.is_dir()
|
||||
except (OSError, RuntimeError) as e:
|
||||
raise ValueError(f"Invalid mount path '{raw}': {e!s}") from e
|
||||
if not is_dir:
|
||||
raise ValueError(
|
||||
f"Mount path '{raw}' is not an existing directory. "
|
||||
"--mount requires a path to a local directory."
|
||||
)
|
||||
targets_info.append(
|
||||
{
|
||||
"type": "local_code",
|
||||
"details": {"target_path": str(resolved), "mount": True},
|
||||
"original": str(resolved),
|
||||
}
|
||||
)
|
||||
return targets_info
|
||||
|
||||
|
||||
def dedupe_local_targets(targets_info: list[dict[str, Any]]) -> list[dict[str, Any]]:
|
||||
"""Collapse local_code targets that resolve to the same path.
|
||||
|
||||
When a directory is supplied both as a copied ``--target`` and via
|
||||
``--mount`` (or as duplicate values of either), keep one entry and prefer
|
||||
the bind-mounted one — so the same tree is never both streamed in and
|
||||
mounted. Order is preserved; non-local targets pass through untouched.
|
||||
"""
|
||||
result: list[dict[str, Any]] = []
|
||||
seen_paths: set[str] = set()
|
||||
index_by_path: dict[str, int] = {}
|
||||
for target in targets_info:
|
||||
details = target.get("details") or {}
|
||||
path = details.get("target_path")
|
||||
if target.get("type") != "local_code" or not path:
|
||||
result.append(target)
|
||||
continue
|
||||
if path not in seen_paths:
|
||||
seen_paths.add(path)
|
||||
existing = index_by_path.get(path)
|
||||
if existing is None:
|
||||
index_by_path[path] = len(result)
|
||||
result.append(target)
|
||||
elif details.get("mount") and not (result[existing].get("details") or {}).get("mount"):
|
||||
result[existing] = target # bind mount supersedes the copied entry
|
||||
return result
|
||||
|
||||
|
||||
|
||||
-121
@@ -1,121 +0,0 @@
|
||||
"use client";
|
||||
|
||||
import type { ToolRendererProps } from "@/types/events";
|
||||
import { TruncatedText } from "./ToolCard";
|
||||
import Markdown from "./Markdown";
|
||||
|
||||
const SEVERITY_COLORS: Record<string, string> = {
|
||||
critical: "text-red-400", high: "text-orange-400", medium: "text-yellow-400",
|
||||
low: "text-blue-400", info: "text-cyan-400", none: "text-[#888]",
|
||||
};
|
||||
|
||||
interface ReportEntry {
|
||||
id?: string;
|
||||
title?: string;
|
||||
severity?: string;
|
||||
cvss?: number;
|
||||
cve?: string;
|
||||
cwe?: string;
|
||||
target?: string;
|
||||
endpoint?: string;
|
||||
method?: string;
|
||||
description_preview?: string;
|
||||
description?: string;
|
||||
agent_name?: string;
|
||||
by_you?: boolean;
|
||||
}
|
||||
|
||||
function authorTag(r: ReportEntry) {
|
||||
if (!r.agent_name && !r.by_you) return null;
|
||||
const label = r.by_you ? "you" : r.agent_name;
|
||||
return <span className="text-[#666] text-xs ml-1.5">({label})</span>;
|
||||
}
|
||||
|
||||
function sevBadge(severity: string | undefined) {
|
||||
const sev = String(severity ?? "").toLowerCase();
|
||||
const color = SEVERITY_COLORS[sev] ?? "text-yellow-400";
|
||||
return <span className={`font-semibold text-[13px] ${color}`}>{sev.toUpperCase() || "—"}</span>;
|
||||
}
|
||||
|
||||
export default function ReportListRenderer({ toolName, result }: ToolRendererProps) {
|
||||
const res = result as Record<string, unknown> | null;
|
||||
const ok = res != null && typeof res === "object" && res.success === true;
|
||||
|
||||
if (toolName === "get_report") {
|
||||
const report = ok ? (res.report as ReportEntry | undefined) : undefined;
|
||||
return (
|
||||
<div>
|
||||
<span className="text-red-400/80 font-semibold text-sm">report</span>
|
||||
{report ? (
|
||||
<div className="mt-1.5 space-y-2">
|
||||
<div className="flex items-center gap-2 flex-wrap">
|
||||
{sevBadge(report.severity)}
|
||||
{report.cvss != null && <span className="text-[#888] text-[13px]">CVSS {report.cvss}</span>}
|
||||
{report.id && <span className="text-[#555] font-mono text-[13px]">{report.id}</span>}
|
||||
{report.cve && <span className="text-[#888] font-mono text-[13px]">{report.cve}</span>}
|
||||
{report.cwe && <span className="text-[#888] font-mono text-[13px]">{report.cwe}</span>}
|
||||
{(report.agent_name || report.by_you) && (
|
||||
<span className="text-[#666] text-[13px]">{report.by_you ? "you" : report.agent_name}</span>
|
||||
)}
|
||||
</div>
|
||||
{report.title && <div className="text-[15px] text-white/80 font-semibold">{report.title}</div>}
|
||||
{(report.target || report.endpoint) && (
|
||||
<div className="text-[13px] text-[#888] font-mono">
|
||||
{report.target}{report.endpoint ? ` ${report.method ?? ""} ${report.endpoint}` : ""}
|
||||
</div>
|
||||
)}
|
||||
{report.description && <TruncatedText text={report.description} maxLines={20} />}
|
||||
</div>
|
||||
) : (
|
||||
<div className="mt-1 text-[#555] text-xs">
|
||||
{(res && typeof res === "object" && (res.error as string)) || "Report not found"}
|
||||
</div>
|
||||
)}
|
||||
</div>
|
||||
);
|
||||
}
|
||||
|
||||
// list_reports
|
||||
const rawReports = ok ? res.reports : null;
|
||||
const reports: ReportEntry[] = Array.isArray(rawReports) ? (rawReports as ReportEntry[]) : [];
|
||||
const total = ok && typeof res.total_count === "number" ? (res.total_count as number) : reports.length;
|
||||
const counts = ok && res.severity_counts && typeof res.severity_counts === "object"
|
||||
? (res.severity_counts as Record<string, number>)
|
||||
: {};
|
||||
const countEntries = Object.entries(counts);
|
||||
|
||||
return (
|
||||
<div>
|
||||
<div className="flex items-center gap-2 flex-wrap">
|
||||
<span className="text-red-400/80 font-semibold text-sm">reports</span>
|
||||
<span className="text-[#555] text-[13px]">({total})</span>
|
||||
{countEntries.map(([sev, n]) => (
|
||||
<span key={sev} className="text-[13px]">
|
||||
{sevBadge(sev)}<span className="text-[#888] ml-0.5">{n}</span>
|
||||
</span>
|
||||
))}
|
||||
</div>
|
||||
{reports.length > 0 ? (
|
||||
<div className="mt-1.5 space-y-1">
|
||||
{reports.map((r, i) => (
|
||||
<div key={r.id ?? i} className="text-[13px]">
|
||||
<span className="text-[#555] mr-1">-</span>
|
||||
{sevBadge(r.severity)}
|
||||
{r.id && <span className="text-[#555] font-mono ml-1.5">{r.id}</span>}
|
||||
<span className="text-[#999] ml-1.5">{r.title ?? "(untitled)"}</span>
|
||||
{authorTag(r)}
|
||||
{(r.target || r.endpoint) && (
|
||||
<div className="ml-3 text-[#666] font-mono text-xs">
|
||||
{r.target}{r.endpoint ? ` ${r.method ?? ""} ${r.endpoint}` : ""}
|
||||
</div>
|
||||
)}
|
||||
{r.description_preview && (
|
||||
<div className="ml-3"><Markdown text={r.description_preview} /></div>
|
||||
)}
|
||||
</div>
|
||||
))}
|
||||
</div>
|
||||
) : <div className="mt-1 text-[#555] text-xs">No reports filed yet</div>}
|
||||
</div>
|
||||
);
|
||||
}
|
||||
-20
@@ -1,20 +0,0 @@
|
||||
"use client";
|
||||
|
||||
import type { ToolRendererProps } from "@/types/events";
|
||||
import Markdown from "./Markdown";
|
||||
|
||||
/**
|
||||
* `respond_to_user` carries the message the user is meant to read, so it renders
|
||||
* as the agent's own prose rather than as a tool call.
|
||||
*/
|
||||
export default function RespondRenderer({ args }: ToolRendererProps) {
|
||||
const message = (args.message as string) ?? "";
|
||||
if (!message) return null;
|
||||
|
||||
return (
|
||||
<div>
|
||||
<Markdown text={message} />
|
||||
<div className="mt-1.5 text-[#888] text-[13px]">waiting for your reply</div>
|
||||
</div>
|
||||
);
|
||||
}
|
||||
@@ -1,27 +0,0 @@
|
||||
export interface ParsedFencedCode {
|
||||
language?: string;
|
||||
code: string;
|
||||
}
|
||||
|
||||
const FENCE_RE = /^```([^\n`]*)\r?\n([\s\S]*?)\r?\n?```$/;
|
||||
|
||||
/**
|
||||
* Agent-generated `poc_script_code` is stored wrapped in a markdown code fence
|
||||
* that carries the language, e.g.
|
||||
*
|
||||
* ```python
|
||||
* import requests
|
||||
* ```
|
||||
*
|
||||
* Renderers that show the value as bare code must not display the fence lines
|
||||
* literally. This extracts the inner code and the fence's language tag. Returns
|
||||
* the input unchanged (no language) when it isn't fenced.
|
||||
*/
|
||||
export function parseFencedCode(raw: string | null | undefined): ParsedFencedCode {
|
||||
if (!raw) return { code: "" };
|
||||
const match = FENCE_RE.exec(raw.trim());
|
||||
if (!match) return { code: raw };
|
||||
const info = match[1].trim();
|
||||
const language = info ? info.split(/\s+/)[0] : undefined;
|
||||
return { language: language || undefined, code: match[2] };
|
||||
}
|
||||
@@ -1,32 +0,0 @@
|
||||
import hljs from "highlight.js/lib/common";
|
||||
import http from "highlight.js/lib/languages/http";
|
||||
import nginx from "highlight.js/lib/languages/nginx";
|
||||
import apache from "highlight.js/lib/languages/apache";
|
||||
import dockerfile from "highlight.js/lib/languages/dockerfile";
|
||||
import properties from "highlight.js/lib/languages/properties";
|
||||
|
||||
hljs.registerLanguage("http", http);
|
||||
hljs.registerLanguage("nginx", nginx);
|
||||
hljs.registerLanguage("apache", apache);
|
||||
hljs.registerLanguage("dockerfile", dockerfile);
|
||||
hljs.registerLanguage("properties", properties);
|
||||
|
||||
/**
|
||||
* Highlight code, preferring an explicit language when it's recognized,
|
||||
* otherwise auto-detecting. Falls back to Python when auto-detection is
|
||||
* inconclusive, since legacy (unfenced) PoC scripts are Python.
|
||||
*/
|
||||
export function highlightCode(code: string, language?: string | null): string {
|
||||
try {
|
||||
if (language && hljs.getLanguage(language)) {
|
||||
return hljs.highlight(code, { language, ignoreIllegals: true }).value;
|
||||
}
|
||||
const auto = hljs.highlightAuto(code);
|
||||
if (auto.language) return auto.value;
|
||||
return hljs.highlight(code, { language: "python", ignoreIllegals: true }).value;
|
||||
} catch {
|
||||
return hljs.highlight(code, { language: "python", ignoreIllegals: true }).value;
|
||||
}
|
||||
}
|
||||
|
||||
export default hljs;
|
||||
File diff suppressed because one or more lines are too long
@@ -1 +0,0 @@
|
||||
"""LLM-facing context management: model-aware budgets and history compaction."""
|
||||
@@ -1,386 +0,0 @@
|
||||
"""Provider-agnostic conversation compaction.
|
||||
|
||||
When an agent's session grows past the model's usable context window, older
|
||||
turns are summarised into a single checkpoint while the most recent turns are
|
||||
kept verbatim. This runs for every LiteLLM provider (not just OpenAI), keeps a
|
||||
security-focused structured summary, and preserves tool-call/tool-result
|
||||
pairing so the trimmed history is still valid provider input.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
from typing import TYPE_CHECKING, Any
|
||||
|
||||
from agents.model_settings import ModelSettings
|
||||
from agents.models.interface import ModelTracing
|
||||
from litellm.exceptions import BadRequestError, ContextWindowExceededError
|
||||
from openai.types.responses import ResponseOutputMessage, ResponseOutputText
|
||||
|
||||
from strix.config import load_settings
|
||||
from strix.config.models import StrixProvider
|
||||
from strix.core.inputs import make_model_settings
|
||||
from strix.core.sessions import replace_session_items, session_write_lock
|
||||
from strix.llm.context_budget import context_window, count_tokens, output_limit
|
||||
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from agents.items import ModelResponse
|
||||
from agents.memory import Session
|
||||
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
_CHECKPOINT_TAG = "<conversation-checkpoint>"
|
||||
_TOOL_OUTPUT_MAX_CHARS = 2_000
|
||||
_MIN_ITEMS_TO_COMPACT = 6
|
||||
_HEAD_TRUNCATED_MARKER = "\n\n[... older conversation omitted to fit the summary request ...]\n\n"
|
||||
|
||||
|
||||
# Providers that don't type overflow errors (OpenRouter maps every 400 to a
|
||||
# plain BadRequestError) leave only the message to go on, so we match it the way
|
||||
# LiteLLM's own checker does — but with rate-limit exclusions first, so a
|
||||
# throttling 429 is never mistaken for an overflow and sent into compaction.
|
||||
_OVERFLOW_EXCLUSIONS = (
|
||||
"rate limit",
|
||||
"too many requests",
|
||||
"throttling",
|
||||
"service unavailable",
|
||||
"quota",
|
||||
)
|
||||
_OVERFLOW_MARKERS = (
|
||||
"context length",
|
||||
"context window",
|
||||
"context_length_exceeded",
|
||||
"prompt is too long",
|
||||
"input is too long",
|
||||
"input length",
|
||||
"maximum prompt length",
|
||||
"reduce the length of the messages",
|
||||
"too many tokens",
|
||||
"token limit exceeded",
|
||||
"request entity too large",
|
||||
)
|
||||
|
||||
|
||||
def is_context_overflow(exc: BaseException) -> bool:
|
||||
"""Whether ``exc`` is a model context-window-overflow error.
|
||||
|
||||
LiteLLM types most providers' overflow as ContextWindowExceededError, but its
|
||||
OpenRouter branch raises a plain BadRequestError, so for that we fall back to
|
||||
matching the provider message.
|
||||
"""
|
||||
if isinstance(exc, ContextWindowExceededError):
|
||||
return True
|
||||
if isinstance(exc, BadRequestError):
|
||||
msg = str(exc).lower()
|
||||
if any(x in msg for x in _OVERFLOW_EXCLUSIONS):
|
||||
return False
|
||||
return any(x in msg for x in _OVERFLOW_MARKERS)
|
||||
return False
|
||||
|
||||
|
||||
_SUMMARY_INSTRUCTIONS = """\
|
||||
You are compacting the earlier part of an autonomous security-testing agent's \
|
||||
conversation so it fits the model context window. Produce a dense, factual \
|
||||
record that lets the agent continue with no loss of important state.
|
||||
|
||||
This is a security engagement: dropped findings mean lost vulnerabilities. Be \
|
||||
EXHAUSTIVE, not concise. Enumerate every distinct item as its own bullet — \
|
||||
never merge, deduplicate, generalise, or omit distinct findings, credentials, \
|
||||
or dead ends, even if they seem minor or repetitive. If the source mentions \
|
||||
five vulnerabilities, list five. Copy exact values verbatim: URLs, endpoints, \
|
||||
file paths, parameters, payloads, credentials, tokens, keys, hashes, cracked \
|
||||
passwords, software versions, and error messages — never paraphrase or \
|
||||
placeholder them. Do not invent anything and do not describe this compaction \
|
||||
process.
|
||||
|
||||
Return Markdown with exactly these sections:
|
||||
|
||||
## Objective
|
||||
The overall goal and target scope.
|
||||
|
||||
## Vulnerabilities & Findings
|
||||
One bullet per DISTINCT vulnerability or finding (SQLi, XSS, SSRF, auth bypass, \
|
||||
misconfig, etc.). For each: type, exact location (URL/endpoint/param/file), the \
|
||||
verbatim payload or proof, confirmation status, and impact. List them all.
|
||||
|
||||
## Credentials & Secrets
|
||||
One bullet per credential, secret, API key, token, hash, or cracked password, \
|
||||
copied verbatim with where it applies. Write "(none)" only if truly none.
|
||||
|
||||
## System & Recon Details
|
||||
Architecture, tech stack, versions, discovered endpoints/paths/params, and \
|
||||
other weak points worth keeping.
|
||||
|
||||
## Work State
|
||||
- Completed: what has been verified or finished.
|
||||
- Active: what is in progress right now.
|
||||
- Blocked: anything stuck and why.
|
||||
|
||||
## Failed Attempts & Dead Ends
|
||||
One bullet per approach already tried that did not work (including WAF blocks, \
|
||||
filtered inputs, non-exploitable leads) so they are not repeated. Write \
|
||||
"(none)" only if truly none.
|
||||
|
||||
## Next Move
|
||||
The concrete next step(s) the agent intended to take.
|
||||
|
||||
## Relevant Files
|
||||
Files/notes/reports created or modified and their purpose."""
|
||||
|
||||
|
||||
def _content_text(content: Any) -> str:
|
||||
if isinstance(content, str):
|
||||
return content
|
||||
if isinstance(content, list):
|
||||
parts: list[str] = []
|
||||
for block in content:
|
||||
if not isinstance(block, dict):
|
||||
continue
|
||||
text = block.get("text")
|
||||
if isinstance(text, str):
|
||||
parts.append(text)
|
||||
elif block.get("type") in {"input_image", "image_url", "output_image"}:
|
||||
parts.append("[image]")
|
||||
return "\n".join(parts)
|
||||
return ""
|
||||
|
||||
|
||||
def _truncate(text: str, limit: int) -> str:
|
||||
return text if len(text) <= limit else f"{text[:limit]}\n[truncated]"
|
||||
|
||||
|
||||
def _serialize_item(item: Any) -> str:
|
||||
if not isinstance(item, dict):
|
||||
return str(item)
|
||||
item_type = item.get("type")
|
||||
role = item.get("role")
|
||||
if item_type == "function_call":
|
||||
args = _truncate(str(item.get("arguments", "")), _TOOL_OUTPUT_MAX_CHARS)
|
||||
return f"[tool_call {item.get('name', '?')}] {args}"
|
||||
if item_type == "function_call_output":
|
||||
output = item.get("output")
|
||||
text = output if isinstance(output, str) else _content_text(output)
|
||||
return f"[tool_result] {_truncate(text, _TOOL_OUTPUT_MAX_CHARS)}"
|
||||
if item_type == "reasoning":
|
||||
return ""
|
||||
if role or item_type == "message":
|
||||
return f"[{role or 'assistant'}] {_content_text(item.get('content'))}".strip()
|
||||
return ""
|
||||
|
||||
|
||||
def _serialize_items(items: list[Any]) -> str:
|
||||
return "\n".join(s for s in (_serialize_item(item) for item in items) if s)
|
||||
|
||||
|
||||
def _is_tool_call(item: Any) -> bool:
|
||||
return isinstance(item, dict) and item.get("type") == "function_call"
|
||||
|
||||
|
||||
def _is_tool_output(item: Any) -> bool:
|
||||
return isinstance(item, dict) and item.get("type") == "function_call_output"
|
||||
|
||||
|
||||
def _open_calls_at(items: list[Any]) -> list[int]:
|
||||
"""Prefix count of tool calls still awaiting their result at each index;
|
||||
a split is only safe where this is zero."""
|
||||
balance = [0] * (len(items) + 1)
|
||||
for i, item in enumerate(items):
|
||||
delta = 1 if _is_tool_call(item) else -1 if _is_tool_output(item) else 0
|
||||
balance[i + 1] = max(0, balance[i] + delta)
|
||||
return balance
|
||||
|
||||
|
||||
def _select_split(model: str, items: list[Any], keep_tokens: int) -> int:
|
||||
"""Index where the kept-verbatim recent tail begins: walk newest→oldest to
|
||||
``keep_tokens``, then snap to a point with no tool call left open."""
|
||||
total = 0
|
||||
split = len(items)
|
||||
for i in range(len(items) - 1, -1, -1):
|
||||
total += count_tokens(model, _serialize_item(items[i]))
|
||||
if total > keep_tokens:
|
||||
break
|
||||
split = i
|
||||
open_calls = _open_calls_at(items)
|
||||
while split > 0 and open_calls[split] != 0:
|
||||
split -= 1
|
||||
return split
|
||||
|
||||
|
||||
def _previous_summary(head: list[Any]) -> str | None:
|
||||
for item in head:
|
||||
if isinstance(item, dict) and item.get("role") == "user":
|
||||
text = _content_text(item.get("content"))
|
||||
if text.startswith(_CHECKPOINT_TAG):
|
||||
return text
|
||||
return None
|
||||
|
||||
|
||||
def _fit_to_tokens(model: str, text: str, max_tokens: int) -> str:
|
||||
"""Head+tail-truncate ``text`` to ``max_tokens``, keeping start and end."""
|
||||
if count_tokens(model, text) <= max_tokens:
|
||||
return text
|
||||
# Rough char budget (~4x tokens), then tighten by real token count.
|
||||
budget_chars = max_tokens * 4
|
||||
head_chars = budget_chars // 2
|
||||
tail_chars = budget_chars - head_chars
|
||||
candidate = text[:head_chars] + _HEAD_TRUNCATED_MARKER + text[len(text) - tail_chars :]
|
||||
while count_tokens(model, candidate) > max_tokens and (head_chars > 0 or tail_chars > 0):
|
||||
head_chars = int(head_chars * 0.8)
|
||||
tail_chars = int(tail_chars * 0.8)
|
||||
candidate = text[:head_chars] + _HEAD_TRUNCATED_MARKER + text[len(text) - tail_chars :]
|
||||
return candidate
|
||||
|
||||
|
||||
def _summary_output_tokens(model: str) -> int:
|
||||
"""Summary output allowance, capped at the model's own output limit."""
|
||||
return min(load_settings().context.summary_max_tokens, output_limit(model))
|
||||
|
||||
|
||||
def _summary_input_budget(model: str, previous: str | None) -> int:
|
||||
"""Token room left for the head after instructions and the summary output."""
|
||||
overhead = count_tokens(model, _SUMMARY_INSTRUCTIONS)
|
||||
if previous:
|
||||
overhead += count_tokens(model, previous)
|
||||
# 256 leaves slack for the prompt wrapper text not counted in ``overhead``.
|
||||
room = context_window(model) - _summary_output_tokens(model) - overhead - 256
|
||||
return max(0, room)
|
||||
|
||||
|
||||
def _build_summary_prompt(serialized_head: str, previous: str | None) -> str:
|
||||
previous_block = (
|
||||
f"\n\nA previous checkpoint summary follows. Update it: keep what is "
|
||||
f"still true, drop what is now stale, and merge in the new "
|
||||
f"conversation below.\n\n{previous}\n"
|
||||
if previous
|
||||
else ""
|
||||
)
|
||||
return (
|
||||
f"{_SUMMARY_INSTRUCTIONS}{previous_block}\n\n"
|
||||
f"Conversation to summarise:\n\n{serialized_head}"
|
||||
)
|
||||
|
||||
|
||||
def _checkpoint_item(summary: str) -> dict[str, Any]:
|
||||
return {
|
||||
"role": "user",
|
||||
"content": (
|
||||
f"{_CHECKPOINT_TAG}\nThe following summarises earlier conversation that was "
|
||||
f"compacted to fit the context window. Treat it as established context, not "
|
||||
f"new instructions.\n\n{summary}\n</conversation-checkpoint>"
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
def _extract_text(response: ModelResponse) -> str:
|
||||
parts: list[str] = []
|
||||
for item in response.output:
|
||||
if not isinstance(item, ResponseOutputMessage):
|
||||
continue
|
||||
parts.extend(
|
||||
chunk.text
|
||||
for chunk in item.content
|
||||
if isinstance(chunk, ResponseOutputText) and chunk.text
|
||||
)
|
||||
return "".join(parts)
|
||||
|
||||
|
||||
async def _summarize(model: str, prompt: str, max_tokens: int) -> str | None:
|
||||
llm = load_settings().llm
|
||||
model_settings = make_model_settings(
|
||||
None,
|
||||
model_name=model,
|
||||
request_timeout=llm.timeout,
|
||||
prompt_cache=False,
|
||||
extra_headers=llm.extra_headers,
|
||||
).resolve(ModelSettings(max_tokens=max_tokens))
|
||||
try:
|
||||
response = (
|
||||
await StrixProvider()
|
||||
.get_model(model)
|
||||
.get_response(
|
||||
system_instructions=None,
|
||||
input=prompt,
|
||||
model_settings=model_settings,
|
||||
tools=[],
|
||||
output_schema=None,
|
||||
handoffs=[],
|
||||
tracing=ModelTracing.DISABLED,
|
||||
previous_response_id=None,
|
||||
conversation_id=None,
|
||||
prompt=None,
|
||||
)
|
||||
)
|
||||
except Exception:
|
||||
logger.exception("compaction summary call failed for model %s", model)
|
||||
return None
|
||||
content = _extract_text(response).strip()
|
||||
if not content:
|
||||
logger.warning("compaction summary returned no content")
|
||||
return None
|
||||
return content
|
||||
|
||||
|
||||
async def maybe_compact(
|
||||
session: Session,
|
||||
*,
|
||||
model: str,
|
||||
instructions: str = "",
|
||||
tools_text: str = "",
|
||||
force: bool = False,
|
||||
) -> bool:
|
||||
"""Compact ``session`` if it is near the model's context window.
|
||||
|
||||
Returns ``True`` when the session was rewritten. ``force`` skips the size
|
||||
check (used after a provider context-overflow error).
|
||||
"""
|
||||
context = load_settings().context
|
||||
if not context.auto_compact and not force:
|
||||
return False
|
||||
|
||||
async with session_write_lock(session):
|
||||
items = list(await session.get_items())
|
||||
if len(items) < _MIN_ITEMS_TO_COMPACT:
|
||||
return False
|
||||
|
||||
window = context_window(model)
|
||||
reserve = max(context.compact_buffer_tokens, output_limit(model))
|
||||
budget = max(context.keep_tokens, window - reserve)
|
||||
used = count_tokens(model, "\n".join((instructions, tools_text, _serialize_items(items))))
|
||||
if not force and used <= budget:
|
||||
return False
|
||||
|
||||
split = _select_split(model, items, context.keep_tokens)
|
||||
head, recent = items[:split], items[split:]
|
||||
previous = _previous_summary(head)
|
||||
input_budget = _summary_input_budget(model, previous)
|
||||
if not head or input_budget <= 0:
|
||||
# Nothing to summarise, or no room for even the summary request itself.
|
||||
if head:
|
||||
logger.warning(
|
||||
"skipping compaction for %s: no room to summarise within its context window", model
|
||||
)
|
||||
return False
|
||||
|
||||
serialized_head = _fit_to_tokens(model, _serialize_items(head), input_budget)
|
||||
summary = await _summarize(
|
||||
model,
|
||||
_build_summary_prompt(serialized_head, previous),
|
||||
_summary_output_tokens(model),
|
||||
)
|
||||
if summary is None:
|
||||
return False
|
||||
|
||||
new_items = [_checkpoint_item(summary), *recent]
|
||||
rewritten = await replace_session_items(session, new_items, expected_len=len(items))
|
||||
if rewritten:
|
||||
logger.info(
|
||||
"compacted %s: %d items (~%d tok) -> %d items (summary + %d recent)",
|
||||
model,
|
||||
len(items),
|
||||
used,
|
||||
len(new_items),
|
||||
len(recent),
|
||||
)
|
||||
return rewritten
|
||||
@@ -1,87 +0,0 @@
|
||||
"""Model-aware token budgets, resolved from LiteLLM model metadata with a
|
||||
large configurable fallback for models LiteLLM doesn't map.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
from functools import lru_cache
|
||||
from typing import Any
|
||||
|
||||
import litellm
|
||||
|
||||
from strix.config import load_settings
|
||||
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# LiteLLM keys models without the routing prefix users type (``openai/``,
|
||||
# ``litellm/``, ``ollama/`` ...). Strip a leading provider segment on lookup.
|
||||
_STRIPPABLE_PREFIXES = (
|
||||
"openai/",
|
||||
"chatgpt/",
|
||||
"litellm/",
|
||||
"any-llm/",
|
||||
"ollama/",
|
||||
"ollama_chat/",
|
||||
)
|
||||
|
||||
_DEFAULT_OUTPUT_TOKENS = 8_192
|
||||
|
||||
|
||||
def _lookup_key(model: str) -> str:
|
||||
for prefix in _STRIPPABLE_PREFIXES:
|
||||
if model.startswith(prefix):
|
||||
return model[len(prefix) :]
|
||||
return model
|
||||
|
||||
|
||||
def _safe_get_model_info(model: str) -> dict[str, Any] | None:
|
||||
try:
|
||||
return dict(litellm.get_model_info(model))
|
||||
except Exception: # noqa: BLE001 - unmapped models raise; caller falls back.
|
||||
return None
|
||||
|
||||
|
||||
@lru_cache(maxsize=128)
|
||||
def _model_info(model: str) -> dict[str, int]:
|
||||
lookup_key = _lookup_key(model)
|
||||
# Provider-qualified ChatGPT lookups may start a synchronous device-login
|
||||
# poll. LiteLLM keys the metadata by the underlying model slug.
|
||||
candidates = (lookup_key,) if model.startswith("chatgpt/") else (model, lookup_key)
|
||||
for candidate in candidates:
|
||||
info = _safe_get_model_info(candidate)
|
||||
if info is not None:
|
||||
return {
|
||||
"max_input_tokens": int(
|
||||
info.get("max_input_tokens") or info.get("max_tokens") or 0
|
||||
),
|
||||
"max_output_tokens": int(info.get("max_output_tokens") or 0),
|
||||
}
|
||||
logger.debug("No LiteLLM model info for %r; using configured fallbacks", model)
|
||||
return {"max_input_tokens": 0, "max_output_tokens": 0}
|
||||
|
||||
|
||||
def context_window(model: str) -> int:
|
||||
"""Input token capacity for ``model`` (configured fallback when unmapped)."""
|
||||
resolved = _model_info(model)["max_input_tokens"]
|
||||
return resolved or load_settings().context.fallback_context_tokens
|
||||
|
||||
|
||||
def output_limit(model: str) -> int:
|
||||
"""Max output tokens for ``model`` (a conservative default when unmapped)."""
|
||||
return _model_info(model)["max_output_tokens"] or _DEFAULT_OUTPUT_TOKENS
|
||||
|
||||
|
||||
def count_tokens(model: str, text: str) -> int:
|
||||
"""Token count for ``text`` under ``model``.
|
||||
|
||||
Falls back to UTF-8 byte length (a guaranteed upper bound) when LiteLLM
|
||||
can't count, so budget checks stay conservative.
|
||||
"""
|
||||
if not text:
|
||||
return 0
|
||||
try:
|
||||
return int(litellm.token_counter(model=_lookup_key(model), text=text))
|
||||
except Exception: # noqa: BLE001 - tokenizer may be unavailable for some models.
|
||||
return len(text.encode("utf-8"))
|
||||
+9
-48
@@ -13,62 +13,20 @@ from openai.types.responses import ResponseOutputMessage
|
||||
|
||||
from strix.config import load_settings
|
||||
from strix.config.models import (
|
||||
DEFAULT_MODEL_RETRY,
|
||||
StrixProvider,
|
||||
configure_sdk_model_defaults,
|
||||
request_timeout_extra_args,
|
||||
)
|
||||
from strix.core.inputs import make_model_settings
|
||||
from strix.report.state import get_global_report_state
|
||||
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from agents.items import ModelResponse
|
||||
|
||||
from strix.config.settings import DedupeSettings
|
||||
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def _dedupe_extra_args(dedupe: DedupeSettings) -> dict[str, str]:
|
||||
"""Per-call credential + endpoint for the dedupe model.
|
||||
|
||||
Provider env vars and the global base URL are process-wide, so a
|
||||
shared-provider dedupe key or a distinct dedupe endpoint can't be installed
|
||||
globally without clobbering (or being clobbered by) the main model's
|
||||
config. Passing them per call keeps the two apart. Only applies when a
|
||||
dedicated dedupe model is configured.
|
||||
"""
|
||||
if not dedupe.model:
|
||||
return {}
|
||||
extra: dict[str, str] = {}
|
||||
if dedupe.api_key and dedupe.api_key.strip():
|
||||
extra["api_key"] = dedupe.api_key.strip()
|
||||
if dedupe.api_base and dedupe.api_base.strip():
|
||||
extra["api_base"] = dedupe.api_base.strip()
|
||||
return extra
|
||||
|
||||
|
||||
def _dedupe_model_settings(
|
||||
dedupe: DedupeSettings, model_name: str, request_timeout: float | None
|
||||
) -> ModelSettings:
|
||||
llm = load_settings().llm
|
||||
settings = make_model_settings(
|
||||
dedupe.reasoning_effort,
|
||||
model_name=model_name,
|
||||
force_required_tool_choice=False,
|
||||
request_timeout=request_timeout,
|
||||
# The main model's headers apply only when dedupe falls back to the main
|
||||
# model; a dedicated dedupe model may route to another provider, which
|
||||
# must never receive the main endpoint's credentials. A dedicated model
|
||||
# gets its own DEDUPE_LLM_EXTRA_HEADERS instead.
|
||||
extra_headers=dedupe.extra_headers if dedupe.model else llm.extra_headers,
|
||||
)
|
||||
extra = _dedupe_extra_args(dedupe)
|
||||
if extra:
|
||||
settings = settings.resolve(ModelSettings(extra_args=extra))
|
||||
return settings
|
||||
|
||||
|
||||
DEDUPE_SYSTEM_PROMPT = """You are an expert vulnerability report deduplication judge.
|
||||
Your task is to determine if a candidate vulnerability report describes the SAME vulnerability
|
||||
as any existing report.
|
||||
@@ -328,14 +286,13 @@ async def check_duplicate(
|
||||
|
||||
try:
|
||||
settings = load_settings()
|
||||
dedupe = settings.dedupe
|
||||
model_name = (dedupe.model or "").strip() or settings.llm.model
|
||||
model_name = settings.llm.model
|
||||
if not model_name:
|
||||
return {
|
||||
"is_duplicate": False,
|
||||
"duplicate_id": "",
|
||||
"confidence": 0.0,
|
||||
"reason": "No LLM model configured; skipping dedupe check",
|
||||
"reason": "STRIX_LLM not configured; skipping dedupe check",
|
||||
}
|
||||
|
||||
candidate_cleaned = _prepare_report_for_comparison(candidate)
|
||||
@@ -354,7 +311,11 @@ async def check_duplicate(
|
||||
response = await model.get_response(
|
||||
system_instructions=DEDUPE_SYSTEM_PROMPT,
|
||||
input=user_msg,
|
||||
model_settings=_dedupe_model_settings(dedupe, resolved_model, settings.llm.timeout),
|
||||
model_settings=ModelSettings(
|
||||
retry=DEFAULT_MODEL_RETRY,
|
||||
include_usage=True,
|
||||
extra_args=request_timeout_extra_args(settings.llm.timeout),
|
||||
),
|
||||
tools=[],
|
||||
output_schema=None,
|
||||
handoffs=[],
|
||||
|
||||
@@ -1,7 +1,6 @@
|
||||
import json
|
||||
import logging
|
||||
import subprocess
|
||||
import threading
|
||||
from collections.abc import Callable
|
||||
from datetime import UTC, datetime
|
||||
from importlib.metadata import PackageNotFoundError, version
|
||||
@@ -11,8 +10,6 @@ from uuid import uuid4
|
||||
|
||||
from agents.usage import Usage
|
||||
|
||||
from strix.config import codex
|
||||
from strix.config.loader import load_settings
|
||||
from strix.core.paths import run_dir_for
|
||||
from strix.report.sarif import write_sarif
|
||||
from strix.report.usage import LLMUsageLedger
|
||||
@@ -96,8 +93,6 @@ def get_global_report_state() -> Optional["ReportState"]:
|
||||
def set_global_report_state(report_state: "ReportState") -> None:
|
||||
global _global_report_state # noqa: PLW0603
|
||||
_global_report_state = report_state
|
||||
# New run: drop any streamed-cost entries a prior run left unconsumed.
|
||||
streamed_openrouter_costs.clear()
|
||||
|
||||
|
||||
class ReportState:
|
||||
@@ -122,15 +117,12 @@ class ReportState:
|
||||
self.scan_results: dict[str, Any] | None = None
|
||||
self.scan_config: dict[str, Any] | None = None
|
||||
self._llm_usage = LLMUsageLedger()
|
||||
auth_mode = codex.auth_mode(load_settings().llm.model)
|
||||
self._llm_usage.zero_cost = auth_mode == "subscription"
|
||||
self.run_record: dict[str, Any] = {
|
||||
"run_id": self.run_id,
|
||||
"run_name": self.run_name,
|
||||
"start_time": self.start_time,
|
||||
"end_time": None,
|
||||
"status": "running",
|
||||
"auth_mode": auth_mode,
|
||||
"targets_info": [],
|
||||
"llm_usage": self._build_llm_usage_record(),
|
||||
}
|
||||
@@ -510,72 +502,6 @@ class ReportState:
|
||||
self._sync_llm_usage_record()
|
||||
|
||||
|
||||
def openrouter_stream_cost(usage: Any) -> float | None:
|
||||
"""Total OpenRouter-reported cost from a raw stream ``usage`` block, or None.
|
||||
|
||||
Non-BYOK responses bill everything to ``usage.cost``. BYOK responses put the
|
||||
OpenRouter fee in ``usage.cost`` (often 0) and the provider charge in
|
||||
``usage.cost_details.upstream_inference_cost``, so BYOK totals sum the two.
|
||||
"""
|
||||
if not isinstance(usage, dict):
|
||||
return None
|
||||
total = 0.0
|
||||
cost = usage.get("cost")
|
||||
if isinstance(cost, int | float) and cost > 0:
|
||||
total += float(cost)
|
||||
if bool(usage.get("is_byok")):
|
||||
details = usage.get("cost_details")
|
||||
upstream = details.get("upstream_inference_cost") if isinstance(details, dict) else None
|
||||
if isinstance(upstream, int | float) and upstream > 0:
|
||||
total += float(upstream)
|
||||
return total if total > 0 else None
|
||||
|
||||
|
||||
def _response_id(completion_response: Any) -> str | None:
|
||||
response_id = getattr(completion_response, "id", None)
|
||||
if response_id is None and isinstance(completion_response, dict):
|
||||
response_id = cast("dict[str, Any]", completion_response).get("id")
|
||||
return response_id if isinstance(response_id, str) and response_id else None
|
||||
|
||||
|
||||
class StreamedOpenRouterCosts:
|
||||
"""Correlates OpenRouter's per-stream cost from the parser to the cost callback.
|
||||
|
||||
LiteLLM rebuilds streamed responses from token-only chunks and drops the
|
||||
``usage.cost`` OpenRouter reports in its final stream chunk (its non-streamed
|
||||
path preserves it; streaming snapshots hidden params at stream start). Every
|
||||
scan streams, so the OpenRouter streaming handler (see strix.config.models)
|
||||
records the cost here keyed by response id, and the callback takes it back out
|
||||
for the matching rebuilt response. Entries are removed on read; ``clear()``
|
||||
runs per scan so nothing accumulates across runs.
|
||||
"""
|
||||
|
||||
def __init__(self) -> None:
|
||||
self._costs: dict[str, float] = {}
|
||||
self._lock = threading.Lock()
|
||||
|
||||
def remember(self, response_id: Any, usage: Any) -> None:
|
||||
cost = openrouter_stream_cost(usage)
|
||||
if cost is None or not (isinstance(response_id, str) and response_id):
|
||||
return
|
||||
with self._lock:
|
||||
self._costs[response_id] = cost
|
||||
|
||||
def take(self, completion_response: Any) -> float | None:
|
||||
response_id = _response_id(completion_response)
|
||||
if response_id is None:
|
||||
return None
|
||||
with self._lock:
|
||||
return self._costs.pop(response_id, None)
|
||||
|
||||
def clear(self) -> None:
|
||||
with self._lock:
|
||||
self._costs.clear()
|
||||
|
||||
|
||||
streamed_openrouter_costs = StreamedOpenRouterCosts()
|
||||
|
||||
|
||||
def litellm_cost_callback(
|
||||
kwargs: Any,
|
||||
completion_response: Any,
|
||||
@@ -610,11 +536,6 @@ def litellm_cost_callback(
|
||||
if cost is None:
|
||||
cost = _usage_reported_cost(completion_response)
|
||||
|
||||
# Recover the exact OpenRouter cost the streaming handler stashed for this
|
||||
# response — LiteLLM drops it from streamed usage, so nothing above sees it.
|
||||
if cost is None:
|
||||
cost = streamed_openrouter_costs.take(completion_response)
|
||||
|
||||
if cost is None:
|
||||
cost = _estimate_response_cost(kwargs, completion_response)
|
||||
|
||||
|
||||
@@ -19,9 +19,6 @@ class LLMUsageLedger:
|
||||
self._agent_usage: dict[str, Usage] = {}
|
||||
self._agent_metadata: dict[str, dict[str, str]] = {}
|
||||
self._total_cost = 0.0
|
||||
# When True, tokens are still tracked but cost stays $0 — the run is on a
|
||||
# model subscription, so there is no metered per-token charge to report.
|
||||
self.zero_cost = False
|
||||
|
||||
def record(
|
||||
self,
|
||||
@@ -44,7 +41,7 @@ class LLMUsageLedger:
|
||||
if model:
|
||||
metadata["model"] = model
|
||||
|
||||
if not self.zero_cost and not _is_litellm_routed(model):
|
||||
if not _is_litellm_routed(model):
|
||||
estimated = _estimate_litellm_cost(usage, model)
|
||||
if estimated:
|
||||
self._total_cost += estimated
|
||||
@@ -52,8 +49,6 @@ class LLMUsageLedger:
|
||||
return True
|
||||
|
||||
def record_observed_cost(self, cost: float) -> None:
|
||||
if self.zero_cost:
|
||||
return
|
||||
if isinstance(cost, int | float) and cost > 0:
|
||||
self._total_cost += float(cost)
|
||||
|
||||
|
||||
+6
-65
@@ -10,27 +10,19 @@ import re
|
||||
import tempfile
|
||||
from datetime import UTC, datetime
|
||||
from pathlib import Path
|
||||
from typing import TYPE_CHECKING, Any, cast
|
||||
|
||||
from pygments.lexers import PythonLexer, get_lexer_by_name, guess_lexer
|
||||
from pygments.lexers.special import TextLexer
|
||||
from pygments.util import ClassNotFound
|
||||
from typing import Any
|
||||
|
||||
from strix.core.paths import run_record_path
|
||||
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from pygments.lexer import Lexer
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
_SEVERITY_ORDER = {"critical": 0, "high": 1, "medium": 2, "low": 3, "info": 4}
|
||||
|
||||
_FENCE_RE = re.compile(r"^```([^\n`]*)\r?\n(.*?)\r?\n?```$", re.DOTALL)
|
||||
_BACKTICK_RUN = re.compile(r"`+")
|
||||
|
||||
|
||||
def safe_fence(content: str) -> str:
|
||||
def _safe_fence(content: str) -> str:
|
||||
"""Return a backtick fence that ``content`` cannot break out of.
|
||||
|
||||
Per CommonMark a fenced code block is closed only by a run of backticks at
|
||||
@@ -43,56 +35,6 @@ def safe_fence(content: str) -> str:
|
||||
return "`" * max(3, longest + 1)
|
||||
|
||||
|
||||
def parse_fenced_code(raw: str) -> tuple[str | None, str]:
|
||||
"""Split an optionally fenced code string into ``(language, code)``.
|
||||
|
||||
Agent-generated code fields (e.g. ``poc_script_code``) are stored wrapped in
|
||||
a markdown fence carrying the language, like ``` ```python\n...\n``` ```.
|
||||
Return the fence's language tag and the inner code, or ``(None, raw)`` when
|
||||
the value isn't fenced.
|
||||
"""
|
||||
match = _FENCE_RE.match(raw.strip())
|
||||
if not match:
|
||||
return None, raw
|
||||
info = match.group(1).strip()
|
||||
language = info.split()[0] if info else None
|
||||
return (language or None), match.group(2)
|
||||
|
||||
|
||||
def resolve_lexer(language: str | None, code: str) -> Lexer:
|
||||
"""Pick a pygments lexer for ``code``.
|
||||
|
||||
Prefer the explicit fence ``language`` when it names a known lexer, otherwise
|
||||
auto-detect from the source. Fall back to Python when detection is
|
||||
inconclusive, since legacy (unfenced) PoC scripts are Python.
|
||||
"""
|
||||
if language:
|
||||
try:
|
||||
return get_lexer_by_name(language)
|
||||
except ClassNotFound:
|
||||
pass
|
||||
try:
|
||||
lexer = guess_lexer(code)
|
||||
except ClassNotFound:
|
||||
return cast("Lexer", PythonLexer())
|
||||
# ``guess_lexer`` returns the plain-text lexer when it can't detect anything.
|
||||
if isinstance(lexer, TextLexer):
|
||||
return cast("Lexer", PythonLexer())
|
||||
return lexer
|
||||
|
||||
|
||||
def guess_language_name(code: str) -> str:
|
||||
"""Return a markdown fence tag for ``code``, defaulting to ``python`` when
|
||||
auto-detection is inconclusive."""
|
||||
try:
|
||||
lexer = guess_lexer(code)
|
||||
except ClassNotFound:
|
||||
return "python"
|
||||
if isinstance(lexer, TextLexer) or not lexer.aliases:
|
||||
return "python"
|
||||
return str(lexer.aliases[0])
|
||||
|
||||
|
||||
def read_run_record(run_dir: Path) -> dict[str, Any]:
|
||||
path = run_record_path(run_dir)
|
||||
if not path.exists():
|
||||
@@ -245,10 +187,9 @@ def render_vulnerability_md(report: dict[str, Any]) -> str: # noqa: PLR0912, PL
|
||||
lines.append(str(report["poc_description"]))
|
||||
lines.append("")
|
||||
if report.get("poc_script_code"):
|
||||
language, code = parse_fenced_code(str(report["poc_script_code"]))
|
||||
fence_lang = language or guess_language_name(code)
|
||||
fence = safe_fence(code)
|
||||
lines.append(f"{fence}{fence_lang}")
|
||||
code = str(report["poc_script_code"])
|
||||
fence = _safe_fence(code)
|
||||
lines.append(fence)
|
||||
lines.append(code)
|
||||
lines.append(fence)
|
||||
lines.append("")
|
||||
@@ -268,7 +209,7 @@ def render_vulnerability_md(report: dict[str, Any]) -> str: # noqa: PLR0912, PL
|
||||
lines.append(f" {loc['label']}")
|
||||
if loc.get("snippet"):
|
||||
snippet = str(loc["snippet"])
|
||||
fence = safe_fence(snippet)
|
||||
fence = _safe_fence(snippet)
|
||||
lines.append(f" {fence}")
|
||||
lines.extend(f" {ln}" for ln in snippet.splitlines())
|
||||
lines.append(f" {fence}")
|
||||
|
||||
+13
-25
@@ -31,11 +31,16 @@ async def _docker_backend(
|
||||
``docker`` lazily so deployments that target a non-Docker
|
||||
backend don't need the docker-py library installed.
|
||||
|
||||
``session.start()`` is what materializes the manifest into the running
|
||||
container — the SDK's ``client.create()`` only builds the inner session
|
||||
object without applying it. ``async with session:`` would call it too, but
|
||||
Strix manages session lifetime explicitly via ``client.delete()`` so we
|
||||
trigger ``start()`` ourselves.
|
||||
``session.start()`` is what materializes the manifest entries
|
||||
(LocalDir copies and manifest-declared volume/FUSE mounts) into the
|
||||
running container — the SDK's ``client.create()`` only builds the inner
|
||||
session object without applying the manifest. ``async with session:``
|
||||
would call it too, but Strix manages session lifetime explicitly via
|
||||
``client.delete()`` so we trigger ``start()`` ourselves.
|
||||
|
||||
``bind_mounts`` are host directories (e.g. large repos passed via
|
||||
``--mount``) bind-mounted read-only; unlike manifest entries they are
|
||||
applied by Docker at container-create time, not by ``start()``.
|
||||
"""
|
||||
import docker
|
||||
from agents.sandbox.sandboxes.docker import DockerSandboxClientOptions
|
||||
@@ -54,8 +59,6 @@ _BACKENDS: dict[str, SandboxBackend] = {
|
||||
"docker": _docker_backend,
|
||||
}
|
||||
|
||||
_BIND_MOUNT_BACKENDS: set[str] = {"docker"}
|
||||
|
||||
|
||||
def get_backend(name: str) -> SandboxBackend:
|
||||
"""Return the backend factory for ``name`` or raise.
|
||||
@@ -75,30 +78,15 @@ def get_backend(name: str) -> SandboxBackend:
|
||||
return backend
|
||||
|
||||
|
||||
def register_backend(
|
||||
name: str,
|
||||
backend: SandboxBackend,
|
||||
*,
|
||||
supports_bind_mounts: bool = False,
|
||||
) -> None:
|
||||
def register_backend(name: str, backend: SandboxBackend) -> None:
|
||||
"""Register a custom backend under ``name``.
|
||||
|
||||
Intended for downstream users who ship their own runtime — register
|
||||
before any ``session_manager.create_or_reuse`` call. Re-registering
|
||||
an existing name overwrites the prior entry. ``supports_bind_mounts``
|
||||
defaults to False: a remote runtime cannot see the caller's filesystem, so
|
||||
it is handed local sources as manifest entries to upload instead.
|
||||
an existing name overwrites the prior entry.
|
||||
"""
|
||||
_BACKENDS[name] = backend
|
||||
if supports_bind_mounts:
|
||||
_BIND_MOUNT_BACKENDS.add(name)
|
||||
else:
|
||||
_BIND_MOUNT_BACKENDS.discard(name)
|
||||
logger.info("Registered sandbox backend: %s (bind mounts: %s)", name, supports_bind_mounts)
|
||||
|
||||
|
||||
def backend_supports_bind_mounts(name: str) -> bool:
|
||||
return name in _BIND_MOUNT_BACKENDS
|
||||
logger.info("Registered sandbox backend: %s", name)
|
||||
|
||||
|
||||
def supported_backends() -> list[str]:
|
||||
|
||||
@@ -110,19 +110,6 @@ def _apply_log_limits(create_kwargs: dict[str, Any]) -> None:
|
||||
)
|
||||
|
||||
|
||||
def _apply_run_labels(create_kwargs: dict[str, Any]) -> None:
|
||||
run_id = os.getenv("STRIX_RUN_ID")
|
||||
if not run_id:
|
||||
return
|
||||
labels = create_kwargs.setdefault("labels", {})
|
||||
if not isinstance(labels, dict):
|
||||
return
|
||||
labels["strix-run-id"] = run_id
|
||||
run_type = os.getenv("STRIX_RUN_TYPE")
|
||||
if run_type:
|
||||
labels["strix-run-type"] = run_type
|
||||
|
||||
|
||||
class StrixDockerSandboxSession(DockerSandboxSession):
|
||||
sandbox_network: str = ""
|
||||
|
||||
@@ -235,20 +222,19 @@ class StrixDockerSandboxClient(DockerSandboxClient):
|
||||
_apply_sandbox_network(create_kwargs)
|
||||
_apply_resource_limits(create_kwargs)
|
||||
_apply_log_limits(create_kwargs)
|
||||
_apply_run_labels(create_kwargs)
|
||||
|
||||
# Strix injection: local source trees, sorted shallowest-first so a
|
||||
# nested spec lands on top of the tree it covers.
|
||||
bind_mounts = self.strix_bind_mounts or ()
|
||||
# Strix injection: host bind mounts (e.g. large repos passed via --mount)
|
||||
# that bypass the SDK's file-by-file LocalDir copy.
|
||||
bind_mounts = getattr(self, "strix_bind_mounts", ())
|
||||
if bind_mounts:
|
||||
mounts = create_kwargs.setdefault("mounts", [])
|
||||
for spec in sorted(bind_mounts, key=lambda s: str(s["target"]).count("/")):
|
||||
for spec in bind_mounts:
|
||||
mounts.append(
|
||||
DockerSDKMount(
|
||||
target=spec["target"],
|
||||
source=spec["source"],
|
||||
type="bind",
|
||||
read_only=spec.get("read_only", False),
|
||||
read_only=spec.get("read_only", True),
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
@@ -0,0 +1,120 @@
|
||||
"""Symlink-safe staging for ``LocalDir`` manifest uploads.
|
||||
|
||||
The sandbox SDK's ``LocalDir`` walker refuses to copy symlinks at all — it
|
||||
raises ``LocalDirReadError(reason="symlink_not_supported")`` on the first one
|
||||
as a path-escape / TOCTOU safeguard. Real source trees (especially JS/TS
|
||||
monorepos with workspace or shared-config links) routinely commit symlinks, so
|
||||
handing such a tree straight to ``LocalDir`` aborts the upload before the agent
|
||||
even starts.
|
||||
|
||||
:func:`stage_symlink_safe_dir` returns a path that is always safe to hand to
|
||||
``LocalDir``:
|
||||
|
||||
* a tree with no symlinks is used as-is (no copy);
|
||||
* otherwise the tree is copied into a temp directory with symlinks resolved:
|
||||
|
||||
- a link whose target stays inside the tree is *dereferenced* (its target
|
||||
content is materialized in place), so the agent still sees the file;
|
||||
- a link that escapes the tree, dangles, or forms a cycle is *dropped* and
|
||||
never followed. Refusing to follow out-of-tree links preserves the walker's
|
||||
path-escape safety and keeps host/out-of-tree content from leaking into the
|
||||
(hostile) sandbox.
|
||||
|
||||
Regular files are hard-linked when possible (falling back to a copy across
|
||||
devices), so the staged tree adds negligible disk for the non-symlink bulk.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import os
|
||||
import shutil
|
||||
import tempfile
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
_STAGING_PREFIX = "strix-localdir-"
|
||||
|
||||
|
||||
def _is_within(target: Path, root: Path) -> bool:
|
||||
"""Return whether ``target`` is ``root`` itself or nested under it."""
|
||||
if target == root:
|
||||
return True
|
||||
try:
|
||||
target.relative_to(root)
|
||||
except ValueError:
|
||||
return False
|
||||
return True
|
||||
|
||||
|
||||
def tree_has_symlink(root: Path) -> bool:
|
||||
"""Return whether ``root`` contains any symlink (file or directory)."""
|
||||
for dirpath, dirnames, filenames in os.walk(root, followlinks=False):
|
||||
base = Path(dirpath)
|
||||
for name in (*dirnames, *filenames):
|
||||
if (base / name).is_symlink():
|
||||
return True
|
||||
return False
|
||||
|
||||
|
||||
def _link_or_copy(src: Path, dst: Path) -> None:
|
||||
"""Hard-link ``src`` to ``dst``, falling back to a content copy."""
|
||||
try:
|
||||
os.link(src, dst)
|
||||
except OSError:
|
||||
shutil.copy2(src, dst, follow_symlinks=True)
|
||||
|
||||
|
||||
def _stage_dir(src: Path, dst: Path, root: Path, seen: frozenset[Path]) -> None:
|
||||
dst.mkdir(parents=True, exist_ok=True)
|
||||
for entry in os.scandir(src):
|
||||
entry_path = Path(entry.path)
|
||||
dest_path = dst / entry.name
|
||||
|
||||
if entry.is_symlink():
|
||||
target = Path(os.path.realpath(entry_path))
|
||||
if not _is_within(target, root):
|
||||
logger.warning("staging: dropping out-of-tree symlink %s -> %s", entry_path, target)
|
||||
continue
|
||||
if not target.exists():
|
||||
logger.warning("staging: dropping dangling symlink %s", entry_path)
|
||||
continue
|
||||
if target in seen:
|
||||
logger.warning("staging: dropping cyclic symlink %s -> %s", entry_path, target)
|
||||
continue
|
||||
if target.is_dir():
|
||||
_stage_dir(target, dest_path, root, seen | {target})
|
||||
else:
|
||||
_link_or_copy(target, dest_path)
|
||||
elif entry.is_dir(follow_symlinks=False):
|
||||
_stage_dir(entry_path, dest_path, root, seen)
|
||||
elif entry.is_file(follow_symlinks=False):
|
||||
_link_or_copy(entry_path, dest_path)
|
||||
else:
|
||||
# Sockets, FIFOs, devices — not part of a source tree; skip.
|
||||
logger.debug("staging: skipping non-regular entry %s", entry_path)
|
||||
|
||||
|
||||
def stage_symlink_safe_dir(src_root: Path) -> tuple[Path, Path | None]:
|
||||
"""Return ``(upload_path, staged_temp)`` for uploading ``src_root``.
|
||||
|
||||
``upload_path`` is safe to hand to ``LocalDir``. When the tree contains no
|
||||
symlinks it is ``src_root`` itself and ``staged_temp`` is ``None``.
|
||||
Otherwise a symlink-safe copy is materialized in a temp directory and both
|
||||
returned values point at it; the caller owns removing ``staged_temp`` once
|
||||
the upload completes.
|
||||
"""
|
||||
root = src_root.resolve()
|
||||
if not tree_has_symlink(root):
|
||||
return root, None
|
||||
|
||||
staged = Path(tempfile.mkdtemp(prefix=_STAGING_PREFIX))
|
||||
try:
|
||||
_stage_dir(root, staged, root, frozenset({root}))
|
||||
except OSError:
|
||||
shutil.rmtree(staged, ignore_errors=True)
|
||||
raise
|
||||
logger.info("staging: materialized symlink-safe copy of %s at %s", root, staged)
|
||||
return staged, staged
|
||||
@@ -3,21 +3,17 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import os
|
||||
import sys
|
||||
import shutil
|
||||
from pathlib import Path
|
||||
from typing import TYPE_CHECKING, Any
|
||||
from typing import Any
|
||||
|
||||
from agents.sandbox.entries import BaseEntry, LocalDir
|
||||
from agents.sandbox.manifest import Environment, Manifest
|
||||
|
||||
from strix.config import load_settings
|
||||
from strix.runtime.backends import backend_supports_bind_mounts, get_backend
|
||||
from strix.runtime.backends import get_backend
|
||||
from strix.runtime.caido_bootstrap import bootstrap_caido
|
||||
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from strix.runtime.status import StatusSink
|
||||
from strix.runtime.local_dir_staging import stage_symlink_safe_dir
|
||||
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
@@ -32,72 +28,43 @@ _SESSION_CACHE: dict[str, dict[str, Any]] = {}
|
||||
# Manifest root inside the container; entry keys hang off this path.
|
||||
_WORKSPACE_ROOT = "/workspace"
|
||||
|
||||
_PROTECTED_METADATA_NAMES = (".git", ".agents", ".codex")
|
||||
|
||||
def build_session_entries(
|
||||
local_sources: list[dict[str, Any]],
|
||||
) -> tuple[dict[str | Path, BaseEntry], list[dict[str, Any]], list[Path]]:
|
||||
"""Split local sources into copied manifest entries and host bind mounts.
|
||||
|
||||
def _host_identity_env() -> dict[str, str]:
|
||||
if sys.platform != "linux":
|
||||
return {}
|
||||
return {"STRIX_HOST_UID": str(os.getuid()), "STRIX_HOST_GID": str(os.getgid())}
|
||||
|
||||
|
||||
def build_bind_mounts(local_sources: list[dict[str, Any]]) -> list[dict[str, Any]]:
|
||||
Sources flagged ``mount`` are bind-mounted read-only at
|
||||
``/workspace/<workspace_subdir>`` (not added to the manifest, so the SDK
|
||||
does not stream them in file-by-file). Every other source becomes a
|
||||
``LocalDir`` entry copied into the container as before. Trees containing
|
||||
symlinks (which the SDK's ``LocalDir`` walker refuses outright) are first
|
||||
staged into a symlink-safe temp copy; those temp dirs are returned so the
|
||||
caller can remove them once the upload completes.
|
||||
"""
|
||||
entries: dict[str | Path, BaseEntry] = {}
|
||||
bind_mounts: list[dict[str, Any]] = []
|
||||
staged_dirs: list[Path] = []
|
||||
for src in local_sources:
|
||||
ws_subdir = src.get("workspace_subdir") or ""
|
||||
host_path = src.get("source_path") or ""
|
||||
if not ws_subdir or not host_path:
|
||||
continue
|
||||
resolved = Path(host_path).expanduser().resolve()
|
||||
target = f"{_WORKSPACE_ROOT}/{ws_subdir}"
|
||||
bind_mounts.append({"source": str(resolved), "target": target, "read_only": False})
|
||||
if src.get("protect_metadata"):
|
||||
bind_mounts.extend(_metadata_mounts(resolved, target))
|
||||
return bind_mounts
|
||||
|
||||
|
||||
def build_manifest_entries(local_sources: list[dict[str, Any]]) -> dict[str | Path, BaseEntry]:
|
||||
entries: dict[str | Path, BaseEntry] = {}
|
||||
for src in local_sources:
|
||||
ws_subdir = src.get("workspace_subdir") or ""
|
||||
host_path = src.get("source_path") or ""
|
||||
if not ws_subdir or not host_path:
|
||||
continue
|
||||
entries[ws_subdir] = LocalDir(src=Path(host_path).expanduser().resolve())
|
||||
return entries
|
||||
|
||||
|
||||
def _metadata_mounts(tree: Path, target: str) -> list[dict[str, Any]]:
|
||||
mounts: list[dict[str, Any]] = []
|
||||
for name in _PROTECTED_METADATA_NAMES:
|
||||
metadata = tree / name
|
||||
if not metadata.is_dir() and not metadata.is_file():
|
||||
continue
|
||||
if not metadata.resolve().is_relative_to(tree):
|
||||
continue
|
||||
mounts.append({"source": str(metadata), "target": f"{target}/{name}", "read_only": True})
|
||||
gitdir = _gitdir_from_pointer(metadata) if metadata.is_file() else None
|
||||
if gitdir is not None and gitdir.exists() and gitdir.is_relative_to(tree):
|
||||
relative = gitdir.relative_to(tree).as_posix()
|
||||
mounts.append(
|
||||
{"source": str(gitdir), "target": f"{target}/{relative}", "read_only": True}
|
||||
if src.get("mount"):
|
||||
bind_mounts.append(
|
||||
{
|
||||
"source": str(resolved),
|
||||
"target": f"{_WORKSPACE_ROOT}/{ws_subdir}",
|
||||
"read_only": True,
|
||||
}
|
||||
)
|
||||
return mounts
|
||||
|
||||
|
||||
def _gitdir_from_pointer(git_file: Path) -> Path | None:
|
||||
try:
|
||||
content = git_file.read_text(encoding="utf-8", errors="replace")
|
||||
except OSError:
|
||||
return None
|
||||
for line in content.splitlines():
|
||||
prefix, _, value = line.partition(":")
|
||||
if prefix.strip() == "gitdir" and value.strip():
|
||||
candidate = Path(value.strip()).expanduser()
|
||||
if not candidate.is_absolute():
|
||||
candidate = git_file.parent / candidate
|
||||
return candidate.resolve()
|
||||
return None
|
||||
else:
|
||||
upload_path, staged = stage_symlink_safe_dir(resolved)
|
||||
if staged is not None:
|
||||
staged_dirs.append(staged)
|
||||
entries[ws_subdir] = LocalDir(src=upload_path)
|
||||
return entries, bind_mounts, staged_dirs
|
||||
|
||||
|
||||
async def create_or_reuse(
|
||||
@@ -105,32 +72,19 @@ async def create_or_reuse(
|
||||
*,
|
||||
image: str,
|
||||
local_sources: list[dict[str, Any]],
|
||||
status_sink: StatusSink | None = None,
|
||||
) -> dict[str, Any]:
|
||||
"""Return the existing session bundle for ``scan_id`` or create a new one.
|
||||
|
||||
Each ``local_sources`` entry exposes its host ``source_path`` at
|
||||
``/workspace/<workspace_subdir>`` inside the container.
|
||||
``/workspace/<workspace_subdir>`` inside the container — copied in, or
|
||||
bind-mounted read-only when the entry is flagged ``mount``.
|
||||
"""
|
||||
|
||||
def report(phase: str) -> None:
|
||||
if status_sink is not None:
|
||||
status_sink(phase)
|
||||
|
||||
cached = _SESSION_CACHE.get(scan_id)
|
||||
if cached is not None:
|
||||
logger.info("Reusing existing sandbox session for scan %s", scan_id)
|
||||
return cached
|
||||
|
||||
backend_name = load_settings().runtime.backend
|
||||
backend = get_backend(backend_name)
|
||||
|
||||
if backend_supports_bind_mounts(backend_name):
|
||||
bind_mounts = build_bind_mounts(local_sources)
|
||||
entries: dict[str | Path, BaseEntry] = {}
|
||||
else:
|
||||
bind_mounts = []
|
||||
entries = build_manifest_entries(local_sources)
|
||||
entries, bind_mounts, staged_dirs = build_session_entries(local_sources)
|
||||
|
||||
# Caido runs as an in-container sidecar; HTTP(S) traffic from any
|
||||
# process started via ``session.exec`` (the SDK's Shell tool, etc.)
|
||||
@@ -144,7 +98,6 @@ async def create_or_reuse(
|
||||
value={
|
||||
"PYTHONUNBUFFERED": "1",
|
||||
"HOST_GATEWAY": "host.docker.internal",
|
||||
**_host_identity_env(),
|
||||
"http_proxy": container_caido_url,
|
||||
"https_proxy": container_caido_url,
|
||||
"ALL_PROXY": container_caido_url,
|
||||
@@ -153,21 +106,26 @@ async def create_or_reuse(
|
||||
),
|
||||
)
|
||||
|
||||
backend_name = load_settings().runtime.backend
|
||||
backend = get_backend(backend_name)
|
||||
|
||||
logger.info(
|
||||
"Creating sandbox session for scan %s (backend=%s, image=%s)",
|
||||
scan_id,
|
||||
backend_name,
|
||||
image,
|
||||
)
|
||||
report("Starting sandbox container")
|
||||
client, session = await backend(
|
||||
image=image,
|
||||
manifest=manifest,
|
||||
exposed_ports=(_CONTAINER_CAIDO_PORT,),
|
||||
bind_mounts=bind_mounts,
|
||||
)
|
||||
try:
|
||||
client, session = await backend(
|
||||
image=image,
|
||||
manifest=manifest,
|
||||
exposed_ports=(_CONTAINER_CAIDO_PORT,),
|
||||
bind_mounts=bind_mounts,
|
||||
)
|
||||
finally:
|
||||
for staged in staged_dirs:
|
||||
shutil.rmtree(staged, ignore_errors=True)
|
||||
|
||||
report("Setting up the proxy")
|
||||
caido_endpoint = await session.resolve_exposed_port(_CONTAINER_CAIDO_PORT)
|
||||
scheme = "https" if caido_endpoint.tls else "http"
|
||||
host_caido_url = f"{scheme}://{caido_endpoint.host}:{caido_endpoint.port}"
|
||||
|
||||
@@ -1,8 +0,0 @@
|
||||
"""Startup phase reporting."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from collections.abc import Callable
|
||||
|
||||
|
||||
StatusSink = Callable[[str], None]
|
||||
@@ -54,17 +54,18 @@ CT logs record nearly every publicly-trusted certificate. Query by domain (match
|
||||
|
||||
## Recommended Tooling
|
||||
|
||||
These tools are available in the sandbox and are pipeline-friendly with JSON output:
|
||||
Prefer the projectdiscovery suite (already available in the sandbox and pipeline-friendly with JSON output):
|
||||
|
||||
- **`subfinder`** — passive subdomain aggregation across many sources incl. CT: `subfinder -d example.com -all -recursive -silent -oJ -o subs.jsonl`
|
||||
- **`httpx`** — live probing plus cert/SAN grab in one pass: `httpx -l hosts.txt -tls-grab -json` (see methodology).
|
||||
- **`tlsx`** — TLS/cert data at scale; grab SANs and issuer/org to pivot: `tlsx -l hosts.txt -san -cn -tls-version -json -o tls.jsonl`
|
||||
- **`uncover`** — query Shodan/Censys/Fofa/Quake/crt.sh engines from one CLI: `uncover -q 'ssl:"Example Inc"' -e shodan,censys,fofa -json`
|
||||
- **`asnmap`** — org/domain/ASN → CIDR ranges: `asnmap -d example.com -json` / `asnmap -org "Example Inc"`
|
||||
- **`mapcidr`** — expand/aggregate CIDRs into host lists for probing: `mapcidr -cidr 192.0.2.0/24 -o hosts.txt`
|
||||
- **`dnsx`** — fast resolution, PTR, and wildcard filtering: `dnsx -l names.txt -a -aaaa -cname -ptr -resp -json -o dns.jsonl`
|
||||
- **`httpx`** — live probing + cert grab in one pass (see methodology).
|
||||
- **`naabu`** — port sweep for non-HTTP services: `naabu -list hosts.txt -top-ports 100 -verify -silent`
|
||||
- **`curl` + `jq`** — direct **crt.sh** JSON queries for CT (no key needed) and other index APIs.
|
||||
- **`openssl s_client`** — active read of a live host's cert to extract SANs/CN.
|
||||
- **`dig`** / **`nslookup`** — forward/reverse (PTR) resolution and CNAME chains.
|
||||
- **`whois`** — ASN/netblock lookups (e.g. `whois -h whois.cymru.com`).
|
||||
|
||||
Cross-source results — CT + passive DNS + `subfinder` together beat any single source. If you need a tool that is not installed, install it into the sandbox at runtime.
|
||||
Also useful: **`amass`** (`amass intel`/`enum` for ASN, cert, and passive sources), **`cero`** (bulk SAN extraction from IPs/ranges), and direct **crt.sh** JSON queries when no keys are configured. Cross-source results — CT + passive DNS + `subfinder` together beat any single source.
|
||||
|
||||
## Key Techniques
|
||||
|
||||
@@ -74,7 +75,7 @@ Every new name, PTR result, CNAME target, and cert SAN becomes a fresh seed. Loo
|
||||
|
||||
### Cert-Fingerprint Pivoting
|
||||
|
||||
Search Censys/Shodan by a cert's `fingerprint_sha256` to find every other host presenting the same certificate — the strongest cross-asset link for tying acquisitions and shadow infra to the target.
|
||||
Search Censys/Shodan (or `uncover`) by a cert's `fingerprint_sha256` to find every other host presenting the same certificate — the strongest cross-asset link for tying acquisitions and shadow infra to the target.
|
||||
|
||||
### Naming-Convention Inference
|
||||
|
||||
@@ -82,11 +83,11 @@ Wildcard SANs and observed hostnames expose the org's naming scheme; generate ta
|
||||
|
||||
### IP-First Discovery
|
||||
|
||||
For ASN-owned ranges, sweep IPs directly with `naabu`/`httpx` and read served certs (`httpx -tls-grab`, or `openssl s_client`) to find services that have no DNS name at all.
|
||||
For ASN-owned ranges, sweep IPs directly with `naabu`/`httpx` and read served certs (`tlsx`) to find services that have no DNS name at all.
|
||||
|
||||
## Advanced Techniques
|
||||
|
||||
- **Active SAN harvesting** across whole ranges with `httpx -tls-grab` (or `openssl s_client`) recovers internal hostnames never logged to public CT.
|
||||
- **Active SAN harvesting** across whole ranges with `tlsx`/`cero` recovers internal hostnames never logged to public CT.
|
||||
- **Favicon and response hashing** (`httpx -favicon`, hash pivots in Shodan) clusters instances of the same app across unrelated hostnames.
|
||||
- **Vhost differentials**: probe a single IP with multiple `Host:` values to unmask co-located apps behind one address.
|
||||
- **Historical CT/DNS diffing** highlights recently issued certs and newly appearing hosts — high-signal for fresh or misconfigured deployments.
|
||||
@@ -107,11 +108,11 @@ For ASN-owned ranges, sweep IPs directly with `naabu`/`httpx` and read served ce
|
||||
## Testing Methodology
|
||||
|
||||
1. **Seed** - domains, org/legal names, known IPs, email domains, code-host org
|
||||
2. **Certificate transparency** - pull all logged certs per seed domain and org name (crt.sh, Censys/Shodan)
|
||||
3. **SAN/CN extraction** - parse every Subject CN and SAN with `httpx -tls-grab` (or `openssl s_client`); each new name is a new seed
|
||||
4. **Passive DNS** - resolve forward and reverse with `dig`; harvest historical records
|
||||
5. **ASN/IP mapping** - `whois` the netblock/ASN to expand owned ranges, then sweep for live hosts
|
||||
6. **Active TLS pivot** - `httpx -tls-grab` on live IPs/ports to grab SANs missing from public CT
|
||||
2. **Certificate transparency** - pull all logged certs per seed domain and org name (crt.sh, `uncover`)
|
||||
3. **SAN/CN extraction** - parse every Subject CN and SAN with `tlsx`; each new name is a new seed
|
||||
4. **Passive DNS** - resolve forward and reverse with `dnsx`; harvest historical records
|
||||
5. **ASN/IP mapping** - `asnmap` → `mapcidr` to expand owned ranges, then sweep for live hosts
|
||||
6. **Active TLS pivot** - `tlsx`/`cero` on live IPs/ports to grab SANs missing from public CT
|
||||
7. **Consolidate & probe** - dedupe, `httpx` probe, classify, and route to specialists
|
||||
|
||||
## Validation
|
||||
@@ -138,13 +139,13 @@ For ASN-owned ranges, sweep IPs directly with `naabu`/`httpx` and read served ce
|
||||
## Pro Tips
|
||||
|
||||
1. Loop the pipeline — every SAN, PTR, and CNAME target is a new seed until the set converges.
|
||||
2. crt.sh is the cheapest high-yield source (no key); Censys/Shodan add cert-fingerprint and vhost pivoting when keys exist.
|
||||
3. Always cert-grab live hosts with `httpx -tls-grab` (or `openssl s_client`) — active SANs catch internal hostnames never sent to public CT.
|
||||
2. crt.sh is the cheapest high-yield source (no key); Censys/Shodan via `uncover` add cert-fingerprint and vhost pivoting when keys exist.
|
||||
3. Always cert-grab live hosts with `tlsx` — active SANs catch internal hostnames never sent to public CT.
|
||||
4. Internal-looking SANs (`*.internal`, `*.svc.cluster.local`, staging names) are the highest-signal leads.
|
||||
5. Wildcard SANs reveal naming conventions — seed targeted guesses instead of blind brute force.
|
||||
6. Cluster by function, not product name, so the workflow generalizes to any exposed service.
|
||||
7. Keep JSON output throughout so stages chain cleanly (`subfinder` → `dig` → `httpx` → `naabu`).
|
||||
7. Keep JSON output throughout so stages chain cleanly (`subfinder` → `dnsx` → `httpx` → `naabu`).
|
||||
|
||||
## Summary
|
||||
|
||||
Broad passive discovery — CT + TLS SAN pivoting + passive DNS + ASN/IP mapping, looped until convergence — finds the assets brute force misses, especially internal-named and forgotten services leaked through certificates. Build the inventory with `subfinder`, `httpx`, `naabu`, and CT/DNS/cert queries, probe and classify it generically, then route each interesting asset to the specialist skill for its class.
|
||||
Broad passive discovery — CT + TLS SAN pivoting + passive DNS + ASN/IP mapping, looped until convergence — finds the assets brute force misses, especially internal-named and forgotten services leaked through certificates. Build the inventory with the projectdiscovery suite, probe and classify it generically, then route each interesting asset to the specialist skill for its class.
|
||||
|
||||
@@ -152,7 +152,7 @@ TLS clues: certificate CN/SAN referencing provider default host instead of the c
|
||||
|
||||
## Pro Tips
|
||||
|
||||
1. Build a pipeline: enumerate (subfinder) → resolve (dig) → probe (httpx) → fingerprint (nuclei/custom) → verify claims
|
||||
1. Build a pipeline: enumerate (subfinder/amass) → resolve (dnsx) → probe (httpx) → fingerprint (nuclei/custom) → verify claims
|
||||
2. Maintain a current fingerprint corpus; provider messages change frequently
|
||||
3. Prefer minimal PoCs: static "ownership proof" page and, where allowed, DV cert issuance
|
||||
4. Monitor CT for unexpected certs on your subdomains
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
name: weak-password-detection
|
||||
description: Weak password detection, credential stuffing, and brute-force testing using common passwords, system-generated credentials, and HTTP fuzzing / NSE brute-force tooling
|
||||
description: Weak password detection, credential stuffing, and brute-force testing using common passwords, system-generated credentials, and tooling like Hydra
|
||||
---
|
||||
|
||||
# Weak Password Detection / Credential Brute-Force
|
||||
@@ -98,7 +98,7 @@ Weak or default credentials remain one of the most prevalent and high-impact vul
|
||||
- Season + year patterns: `Summer2025!`, `Winter2026@`
|
||||
- Keyboard walks and leet speak variations
|
||||
- Previously breached passwords for the target domain
|
||||
- Scrape the target site to build a content-derived wordlist (e.g. a small custom Python crawler that harvests unique words)
|
||||
- Cewl: `cewl -d 3 -m 5 -w custom.txt https://target.com` to generate from website content
|
||||
|
||||
### Credential Stuffing Workflows
|
||||
|
||||
@@ -123,25 +123,37 @@ Weak or default credentials remain one of the most prevalent and high-impact vul
|
||||
|
||||
### Service-Level Brute-Force
|
||||
|
||||
- HTTP login endpoints: `ffuf` or custom scripts (see Tooling)
|
||||
- SSH/FTP/SMB/Telnet and other services: `nmap` NSE `*-brute` scripts, e.g. `nmap -p 22 --script ssh-brute --script-args userdb=users.txt,passdb=passwords.txt target.com`
|
||||
- Databases (MySQL, PostgreSQL, MongoDB, Redis): weak/default credentials via the matching NSE brute script (`mysql-brute`, `pgsql-brute`, `mongodb-brute`, `redis-brute`) or a custom client script
|
||||
- Any protocol lacking a ready script: custom Python
|
||||
- SSH: `hydra -l admin -P passwords.txt ssh://target.com`
|
||||
- FTP: `hydra -L users.txt -P passwords.txt ftp://target.com`
|
||||
- RDP: `hydra -l administrator -P passwords.txt rdp://target.com`
|
||||
- SMB: `hydra -L users.txt -P passwords.txt smb://target.com`
|
||||
- Database: MySQL, PostgreSQL, MongoDB, Redis with weak credentials
|
||||
- API endpoints: `ffuf` or custom scripts for HTTP-based brute-force
|
||||
|
||||
## Tooling
|
||||
|
||||
### ffuf (primary for web logins)
|
||||
### Hydra (Primary Tool)
|
||||
|
||||
- HTTP POST form brute-force:
|
||||
`hydra -l admin -P /usr/share/wordlists/rockyou.txt target.com http-post-form "/login:username=^USER^&password=^PASS^:Invalid credentials"`
|
||||
- Basic Auth:
|
||||
`hydra -L users.txt -P passwords.txt target.com http-get -s 8080 /admin`
|
||||
- SSH:
|
||||
`hydra -l root -P passwords.txt -t 4 ssh://target.com`
|
||||
- FTP:
|
||||
`hydra -L users.txt -P passwords.txt ftp://target.com`
|
||||
- Custom headers and cookies:
|
||||
`hydra ... http-post-form "/api/login:json={\"user\":\"^USER^\",\"pass\":\"^PASS^\"}:F=401"`
|
||||
|
||||
### ffuf (HTTP Fuzzing)
|
||||
|
||||
- Login brute-force with multiple users and passwords:
|
||||
`ffuf -w users.txt:USER -w passwords.txt:PASS -u https://target.com/login -X POST -d "username=USER&password=PASS" -fr "Invalid"`
|
||||
- JSON body / custom headers via `-H` and a JSON `-d` payload
|
||||
- Filter by response size, status code, or regex to identify successes
|
||||
|
||||
### nmap NSE (service brute-force)
|
||||
### Patator (Versatile Brute-Force)
|
||||
|
||||
- `*-brute` scripts cover many non-HTTP services:
|
||||
`nmap -p 22 --script ssh-brute --script-args userdb=users.txt,passdb=passwords.txt target.com`
|
||||
- Available scripts include `ssh-brute`, `ftp-brute`, `smb-brute`, `telnet-brute`, `mysql-brute`, `pgsql-brute`, `mongodb-brute`, `redis-brute`, `http-brute`, `http-form-brute`.
|
||||
- `patator http_fuzz url=https://target.com/login method=POST body='username=FILE0&password=FILE1' 0=user.txt 1=pass.txt -x ignore:fgrep='Invalid'`
|
||||
|
||||
### Custom Python Scripts
|
||||
|
||||
@@ -151,10 +163,10 @@ Weak or default credentials remain one of the most prevalent and high-impact vul
|
||||
|
||||
### Wordlists
|
||||
|
||||
No password wordlists ship in the sandbox by default — download what you need into `/home/pentester/tools/wordlists` at runtime:
|
||||
- Common passwords (e.g. `rockyou.txt`) from its upstream source
|
||||
- SecLists `Passwords/` and `Passwords/Default-Credentials/` (vendor defaults) from https://github.com/danielmiessler/SecLists
|
||||
- Custom lists from target-specific scraping
|
||||
- `/usr/share/wordlists/rockyou.txt` (common passwords)
|
||||
- `/usr/share/seclists/Passwords/` (organized by category)
|
||||
- `/usr/share/seclists/Passwords/Default-Credentials/` (vendor defaults)
|
||||
- Custom lists from Cewl, CeWL, or target-specific scraping
|
||||
- Breach compilation subsets filtered by target relevance
|
||||
|
||||
## Validation
|
||||
@@ -192,7 +204,7 @@ No password wordlists ship in the sandbox by default — download what you need
|
||||
6. Check for concurrent session limits; successful logins may kick out legitimate users
|
||||
7. GraphQL batching can test multiple credentials in a single request, bypassing per-request limits
|
||||
8. Document the password policy and recommend minimum standards (length, complexity, breach checking)
|
||||
9. For web logins prefer `ffuf`; for other services use `nmap` NSE `*-brute` scripts or custom scripts with equivalent logic
|
||||
9. When Hydra is unavailable, use ffuf or custom scripts with equivalent logic
|
||||
10. Combine with MFA testing: weak passwords plus missing MFA is a critical finding
|
||||
|
||||
## Summary
|
||||
|
||||
@@ -15,7 +15,7 @@ We collect only very **basic** usage data including:
|
||||
**Session Errors:** Duration and error types (not messages or stack traces)\
|
||||
**System Context:** OS type, architecture, Strix version\
|
||||
**Scan Context:** Scan mode (quick/standard/deep), scan type (whitebox/blackbox)\
|
||||
**Model Usage:** Which LLM model is being used and whether it runs via an API key or a model subscription (not prompts or responses)\
|
||||
**Model Usage:** Which LLM model is being used (not prompts or responses)\
|
||||
**Feature Usage:** Which built-in skills are loaded\
|
||||
**Aggregate Metrics:** Vulnerability counts by severity and weakness category (CWE)
|
||||
|
||||
|
||||
@@ -5,7 +5,6 @@ from __future__ import annotations
|
||||
import contextlib
|
||||
import logging
|
||||
import os
|
||||
import sys
|
||||
import warnings
|
||||
from contextvars import ContextVar
|
||||
from pathlib import Path # noqa: TC003 used at runtime by ``setup_scan_logging``
|
||||
@@ -79,10 +78,11 @@ class _StdoutQuietFilter(logging.Filter):
|
||||
|
||||
def configure_dependency_logging() -> None:
|
||||
"""Quiet dependency logging/warnings that obscure Strix scan logs."""
|
||||
litellm = sys.modules.get("litellm")
|
||||
if litellm is not None:
|
||||
with contextlib.suppress(Exception):
|
||||
litellm._logging._disable_debugging()
|
||||
with contextlib.suppress(Exception):
|
||||
import litellm
|
||||
|
||||
litellm_logging = litellm._logging
|
||||
litellm_logging._disable_debugging() # type: ignore[no-untyped-call]
|
||||
|
||||
logging.getLogger("asyncio").setLevel(logging.CRITICAL)
|
||||
logging.getLogger("asyncio").propagate = False
|
||||
|
||||
@@ -1,9 +1,9 @@
|
||||
import json
|
||||
import logging
|
||||
import urllib.request
|
||||
from datetime import datetime
|
||||
from typing import TYPE_CHECKING, Any
|
||||
|
||||
import requests
|
||||
|
||||
from strix.config import load_settings
|
||||
from strix.telemetry._common import (
|
||||
SESSION_ID,
|
||||
@@ -37,7 +37,13 @@ def _send(event: str, properties: dict[str, Any]) -> bool:
|
||||
"distinct_id": SESSION_ID,
|
||||
"properties": properties,
|
||||
}
|
||||
requests.post(f"{_POSTHOG_HOST}/capture/", json=payload, timeout=10)
|
||||
req = urllib.request.Request( # noqa: S310
|
||||
f"{_POSTHOG_HOST}/capture/",
|
||||
data=json.dumps(payload).encode(),
|
||||
headers={"Content-Type": "application/json"},
|
||||
)
|
||||
with urllib.request.urlopen(req, timeout=10): # noqa: S310 # nosec B310
|
||||
pass
|
||||
except Exception: # noqa: BLE001
|
||||
logger.debug("posthog send failed for event %s", event, exc_info=True)
|
||||
return False
|
||||
@@ -52,14 +58,12 @@ def start(
|
||||
is_whitebox: bool,
|
||||
interactive: bool,
|
||||
has_instructions: bool,
|
||||
auth_mode: str | None = None,
|
||||
) -> None:
|
||||
_send(
|
||||
"scan_started",
|
||||
{
|
||||
**base_props(),
|
||||
"model": model or "unknown",
|
||||
"auth_mode": auth_mode or "api_key",
|
||||
"scan_mode": scan_mode or "unknown",
|
||||
"scan_type": "whitebox" if is_whitebox else "blackbox",
|
||||
"interactive": interactive,
|
||||
@@ -129,7 +133,6 @@ def end(report_state: "ReportState", exit_reason: str = "completed") -> None:
|
||||
"scan_ended",
|
||||
{
|
||||
**base_props(),
|
||||
"auth_mode": report_state.run_record.get("auth_mode") or "api_key",
|
||||
"exit_reason": report_state.scan_ended_exit_reason,
|
||||
"duration_seconds": round(duration),
|
||||
"vulnerabilities_total": len(report_state.vulnerability_reports),
|
||||
|
||||
@@ -2,11 +2,10 @@ from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import urllib.parse
|
||||
import urllib.request
|
||||
from datetime import datetime
|
||||
from typing import TYPE_CHECKING, Any
|
||||
|
||||
import requests
|
||||
|
||||
from strix.config import load_settings
|
||||
from strix.telemetry._common import (
|
||||
SESSION_ID,
|
||||
@@ -43,7 +42,9 @@ def _send(event: str, properties: dict[str, Any]) -> bool:
|
||||
url = f"{_SCARF_ENDPOINT}{path}"
|
||||
if query:
|
||||
url = f"{url}?{query}"
|
||||
requests.post(url, timeout=10)
|
||||
req = urllib.request.Request(url, method="POST") # noqa: S310
|
||||
with urllib.request.urlopen(req, timeout=10): # noqa: S310 # nosec B310
|
||||
pass
|
||||
except Exception: # noqa: BLE001
|
||||
logger.debug("scarf send failed for event %s", event, exc_info=True)
|
||||
return False
|
||||
@@ -58,7 +59,6 @@ def start(
|
||||
is_whitebox: bool,
|
||||
interactive: bool,
|
||||
has_instructions: bool,
|
||||
auth_mode: str | None = None,
|
||||
) -> None:
|
||||
_send(
|
||||
"scan_started",
|
||||
@@ -66,7 +66,6 @@ def start(
|
||||
**base_props(),
|
||||
"session": SESSION_ID,
|
||||
"model": model or "unknown",
|
||||
"auth_mode": auth_mode or "api_key",
|
||||
"scan_mode": scan_mode or "unknown",
|
||||
"scan_type": "whitebox" if is_whitebox else "blackbox",
|
||||
"interactive": interactive,
|
||||
@@ -141,7 +140,6 @@ def end(report_state: ReportState, exit_reason: str = "completed") -> None:
|
||||
{
|
||||
**base_props(),
|
||||
"session": SESSION_ID,
|
||||
"auth_mode": report_state.run_record.get("auth_mode") or "api_key",
|
||||
"exit_reason": report_state.scan_ended_exit_reason,
|
||||
"duration_seconds": round(duration),
|
||||
"vulnerabilities_total": len(report_state.vulnerability_reports),
|
||||
|
||||
@@ -13,7 +13,6 @@ from typing import Any, Literal, get_args
|
||||
from agents import RunContextWrapper, function_tool
|
||||
|
||||
from strix.core.agents import Status, coordinator_from_context
|
||||
from strix.core.execution import notify_parent_on_terminal
|
||||
from strix.skills import validate_requested_skills
|
||||
|
||||
|
||||
@@ -88,7 +87,7 @@ async def view_agent_graph(ctx: RunContextWrapper) -> str:
|
||||
default=str,
|
||||
)
|
||||
|
||||
parent_of, statuses, names, _ = await coordinator.graph_snapshot()
|
||||
parent_of, statuses, names = await coordinator.graph_snapshot()
|
||||
|
||||
lines: list[str] = []
|
||||
|
||||
@@ -219,43 +218,25 @@ def _session_items_payload(items: list[Any]) -> list[dict[str, Any]]:
|
||||
return payload
|
||||
|
||||
|
||||
_WAIT_DEFAULT_TIMEOUT_S = 300
|
||||
# Enforced by the SDK around the whole tool call, so it caps an oversized
|
||||
# ``timeout_seconds`` the model asks for. One second of headroom lets the
|
||||
# tool's own timeout fire first and return a clean result.
|
||||
_WAIT_HARD_CEILING_S = _WAIT_DEFAULT_TIMEOUT_S + 1
|
||||
|
||||
|
||||
@function_tool(timeout=_WAIT_HARD_CEILING_S)
|
||||
async def wait_for_agents( # noqa: PLR0911
|
||||
@function_tool(timeout=601)
|
||||
async def wait_for_message( # noqa: PLR0911
|
||||
ctx: RunContextWrapper,
|
||||
reason: str = "Waiting for messages from other agents",
|
||||
timeout_seconds: int = _WAIT_DEFAULT_TIMEOUT_S,
|
||||
timeout_seconds: int = 600,
|
||||
) -> str:
|
||||
"""Pause until another AGENT messages you (or the timeout elapses).
|
||||
"""Pause this agent until a message lands in its inbox (or timeout).
|
||||
|
||||
Use when you have nothing useful to do until a child or peer
|
||||
responds — typically after spawning subagents and you want their
|
||||
completion reports. You resume the instant any message arrives, so
|
||||
size ``timeout_seconds`` to the work you're awaiting.
|
||||
|
||||
**This tool is only for waiting on other agents.** Two things it is
|
||||
NOT for:
|
||||
|
||||
- **Talking to the user.** Use ``respond_to_user``, which delivers
|
||||
your message and hands control back in one call.
|
||||
- **Waiting for a long-running command.** This tool does not watch
|
||||
processes at all — it sleeps until a *message* arrives, so it
|
||||
burns the full timeout even if your command finished a second
|
||||
later. Poll the process instead: ``exec_command`` returns a
|
||||
session/process id, and ``write_stdin`` with ``chars=""`` returns
|
||||
as soon as there is new output or the process exits.
|
||||
Use when you have nothing useful to do until a child/peer responds
|
||||
— typically after spawning subagents and you want to wait for
|
||||
their completion reports. The agent automatically resumes when any
|
||||
message arrives, so pick a ``timeout_seconds`` proportional to the
|
||||
work you're awaiting.
|
||||
|
||||
**Critical caveats:**
|
||||
|
||||
- **Never** call this if you have no agents left to hear from —
|
||||
that just strands you until the timeout. Call ``finish_scan``
|
||||
(root) or ``agent_finish`` (subagent) instead.
|
||||
- **Never** call this if you finished your own task and have **no**
|
||||
child agents running — that's a permanent stall. Call
|
||||
``finish_scan`` (root) or ``agent_finish`` (subagent) instead.
|
||||
- If you're waiting on an agent that **isn't your child**, message
|
||||
it first asking it to ping you when done — otherwise it has no
|
||||
reason to send to your inbox and you'll wait the full timeout.
|
||||
@@ -266,8 +247,7 @@ async def wait_for_agents( # noqa: PLR0911
|
||||
reason: One-line note shown in graph snapshots while you're
|
||||
waiting (helps a human or sibling agent debug who's stuck
|
||||
on what).
|
||||
timeout_seconds: Max seconds to wait (default 300, and values above
|
||||
that are cut short by a hard ceiling). This is only
|
||||
timeout_seconds: Max seconds to wait (default 600). This is only
|
||||
a cap — the tool returns the INSTANT a message arrives, so a
|
||||
larger value never makes you wait longer when the reply does
|
||||
come. Right-size it to what you're waiting on: a short wait
|
||||
@@ -277,7 +257,9 @@ async def wait_for_agents( # noqa: PLR0911
|
||||
bites when the expected message never arrives — so an oversized
|
||||
timeout on a trivial wait just strands you idle until it
|
||||
elapses. On timeout the tool returns and you decide whether to
|
||||
keep working or wait again.
|
||||
keep working or wait again. (Applies to autonomous multi-agent
|
||||
runs; in interactive/chat sessions the agent instead parks until
|
||||
a message arrives and this cap is not enforced.)
|
||||
"""
|
||||
inner = _ctx(ctx)
|
||||
coordinator = coordinator_from_context(inner)
|
||||
@@ -320,7 +302,7 @@ async def wait_for_agents( # noqa: PLR0911
|
||||
)
|
||||
|
||||
if interactive:
|
||||
await coordinator.park_waiting(me, wait_kind="agents")
|
||||
await coordinator.park_waiting(me)
|
||||
return json.dumps(
|
||||
{
|
||||
"success": True,
|
||||
@@ -332,7 +314,7 @@ async def wait_for_agents( # noqa: PLR0911
|
||||
default=str,
|
||||
)
|
||||
|
||||
await coordinator.park_waiting(me, wait_kind="agents")
|
||||
await coordinator.park_waiting(me)
|
||||
try:
|
||||
await asyncio.wait_for(coordinator.wait_for_message(me), timeout_seconds)
|
||||
except TimeoutError:
|
||||
@@ -391,7 +373,7 @@ async def create_agent(
|
||||
|
||||
Decompose complex pentests by handing focused subtasks to dedicated
|
||||
children. The child runs asynchronously — the parent continues
|
||||
immediately and can ``wait_for_agents`` later (or just keep
|
||||
immediately and can ``wait_for_message`` later (or just keep
|
||||
working in parallel). When the child calls ``agent_finish``, its
|
||||
completion report lands in the parent's inbox.
|
||||
|
||||
@@ -559,7 +541,7 @@ async def agent_finish(
|
||||
)
|
||||
|
||||
parent_notified = False
|
||||
if report_to_parent and await coordinator.claim_parent_notice(me):
|
||||
if report_to_parent:
|
||||
async with coordinator._lock:
|
||||
agent_name = coordinator.names.get(me, me)
|
||||
report = _render_completion_report(
|
||||
@@ -583,11 +565,6 @@ async def agent_finish(
|
||||
)
|
||||
parent_notified = True
|
||||
|
||||
await coordinator.set_status(me, "completed")
|
||||
if not parent_notified:
|
||||
# Silence here would leave a parent waiting on a report that is never coming.
|
||||
await notify_parent_on_terminal(coordinator, me, "completed")
|
||||
|
||||
logger.info(
|
||||
"agent_finish: %s success=%s findings=%d parent_notified=%s",
|
||||
me,
|
||||
@@ -595,6 +572,7 @@ async def agent_finish(
|
||||
len(findings or []),
|
||||
parent_notified,
|
||||
)
|
||||
await coordinator.set_status(me, "completed")
|
||||
|
||||
return json.dumps(
|
||||
{
|
||||
@@ -657,7 +635,7 @@ async def stop_agent(
|
||||
ensure_ascii=False,
|
||||
default=str,
|
||||
)
|
||||
_, statuses, _, _ = await coordinator.graph_snapshot()
|
||||
_, statuses, _ = await coordinator.graph_snapshot()
|
||||
if target_agent_id not in statuses:
|
||||
return json.dumps(
|
||||
{"success": False, "error": f"Unknown agent_id: {target_agent_id}"},
|
||||
@@ -685,16 +663,9 @@ async def stop_agent(
|
||||
)
|
||||
|
||||
if cascade:
|
||||
stopped = await coordinator.cancel_descendants_graceful(target_agent_id)
|
||||
await coordinator.cancel_descendants_graceful(target_agent_id)
|
||||
else:
|
||||
await coordinator.request_stop(target_agent_id)
|
||||
stopped = [target_agent_id]
|
||||
|
||||
# The stopper knows what it just did; anyone else waiting on those agents does not.
|
||||
async with coordinator._lock:
|
||||
orphaned = [aid for aid in stopped if coordinator.parent_of.get(aid) not in (None, me)]
|
||||
for aid in orphaned:
|
||||
await notify_parent_on_terminal(coordinator, aid, "stopped")
|
||||
|
||||
logger.info(
|
||||
"stop_agent: target=%s cascade=%s reason=%r",
|
||||
|
||||
@@ -101,7 +101,7 @@ async def finish_scan(
|
||||
execution stops. There is no draft mode and no second chance: never
|
||||
submit placeholder, provisional, or "checking if done" text in any
|
||||
field, and never call ``finish_scan`` to poll whether subagents are
|
||||
done (use ``view_agent_graph`` / ``wait_for_agents`` for that).
|
||||
done (use ``view_agent_graph`` / ``wait_for_message`` for that).
|
||||
Call it exactly ONCE, only when every field holds genuine, finished
|
||||
assessment prose.
|
||||
|
||||
@@ -111,21 +111,17 @@ async def finish_scan(
|
||||
summary. If ANY agent is in ``running`` / ``waiting`` state,
|
||||
you MUST NOT call ``finish_scan`` yet —
|
||||
wrap them up first via ``send_message_to_agent`` (ask them to
|
||||
finish), ``wait_for_agents`` (block until their report
|
||||
finish), ``wait_for_message`` (block until their report
|
||||
arrives), or ``stop_agent`` (graceful cancel). Only ``completed``
|
||||
/ ``crashed`` / ``stopped`` agents are safe to leave behind.
|
||||
Calling ``finish_scan`` while children are alive orphans their
|
||||
work and produces an incomplete report.
|
||||
2. It's a good idea to call ``list_reports`` before finishing to
|
||||
review every finding filed in this scan (use ``get_report`` for
|
||||
full detail on any of them) so your ``executive_summary`` /
|
||||
``technical_analysis`` are grounded in what was actually reported
|
||||
— don't invent or omit findings. All vulnerabilities you found are
|
||||
filed via ``create_vulnerability_report`` — or, for known-CVE
|
||||
dependency findings, ``create_dependency_report`` (un-reported
|
||||
findings are not tracked and not credited). A dependency CVE
|
||||
already filed via ``create_dependency_report`` counts as reported;
|
||||
it does NOT need re-filing here and does NOT block finishing.
|
||||
2. All vulnerabilities you found are filed via
|
||||
``create_vulnerability_report`` — or, for known-CVE dependency
|
||||
findings, ``create_dependency_report`` (un-reported findings are
|
||||
not tracked and not credited). A dependency CVE already filed via
|
||||
``create_dependency_report`` counts as reported; it does NOT need
|
||||
re-filing here and does NOT block finishing.
|
||||
3. Don't double-report — one report per distinct vulnerability.
|
||||
4. **Attack-chaining gate.** Do NOT finish until you have genuinely
|
||||
considered chaining the confirmed findings into higher-impact,
|
||||
@@ -253,8 +249,6 @@ async def finish_scan(
|
||||
parent_id = inner.get("parent_id")
|
||||
if coordinator is not None and parent_id is None and me is not None:
|
||||
active_agents = await coordinator.active_agents_except(me)
|
||||
if active_agents and coordinator.reserve_stopped:
|
||||
active_agents = []
|
||||
else:
|
||||
active_agents = []
|
||||
|
||||
|
||||
@@ -27,21 +27,6 @@ _NOTE_ID_GENERATION_ATTEMPTS = 1024
|
||||
_notes_path: Path | None = None
|
||||
|
||||
|
||||
def _caller_identity(ctx: RunContextWrapper) -> tuple[str | None, str | None]:
|
||||
"""Return the (agent_id, agent_name) of the agent invoking this tool."""
|
||||
inner = ctx.context if isinstance(ctx.context, dict) else {}
|
||||
raw_agent_id = inner.get("agent_id")
|
||||
agent_id = raw_agent_id if isinstance(raw_agent_id, str) else None
|
||||
agent_name: str | None = None
|
||||
coordinator = inner.get("coordinator")
|
||||
if agent_id is not None and coordinator is not None:
|
||||
names = getattr(coordinator, "names", {})
|
||||
if isinstance(names, dict):
|
||||
raw_agent_name = names.get(agent_id)
|
||||
agent_name = raw_agent_name if isinstance(raw_agent_name, str) else None
|
||||
return agent_id, agent_name
|
||||
|
||||
|
||||
def _generate_note_id() -> str | None:
|
||||
for _ in range(_NOTE_ID_GENERATION_ATTEMPTS):
|
||||
note_id = uuid.uuid4().hex[:6]
|
||||
@@ -132,26 +117,10 @@ def _filter_notes(
|
||||
return filtered
|
||||
|
||||
|
||||
def _mark_authorship(
|
||||
entry: dict[str, Any], note: dict[str, Any], caller_agent_id: str | None
|
||||
) -> dict[str, Any]:
|
||||
"""Attach the note's author and flag whether the caller wrote it."""
|
||||
agent_name = note.get("agent_name")
|
||||
if agent_name:
|
||||
entry["agent_name"] = agent_name
|
||||
agent_id = note.get("agent_id")
|
||||
if agent_id:
|
||||
entry["agent_id"] = agent_id
|
||||
if caller_agent_id is not None and agent_id == caller_agent_id:
|
||||
entry["by_you"] = True
|
||||
return entry
|
||||
|
||||
|
||||
def _to_note_listing_entry(
|
||||
note: dict[str, Any],
|
||||
*,
|
||||
include_content: bool = False,
|
||||
caller_agent_id: str | None = None,
|
||||
) -> dict[str, Any]:
|
||||
entry = {
|
||||
"note_id": note.get("note_id"),
|
||||
@@ -169,7 +138,7 @@ def _to_note_listing_entry(
|
||||
entry["content_preview"] = f"{content[:_DEFAULT_CONTENT_PREVIEW_CHARS].rstrip()}..."
|
||||
else:
|
||||
entry["content_preview"] = content
|
||||
return _mark_authorship(entry, note, caller_agent_id)
|
||||
return entry
|
||||
|
||||
|
||||
def _create_note_impl(
|
||||
@@ -177,8 +146,6 @@ def _create_note_impl(
|
||||
content: str,
|
||||
category: str = "general",
|
||||
tags: list[str] | None = None,
|
||||
agent_id: str | None = None,
|
||||
agent_name: str | None = None,
|
||||
) -> dict[str, Any]:
|
||||
with _notes_lock:
|
||||
try:
|
||||
@@ -212,10 +179,6 @@ def _create_note_impl(
|
||||
"created_at": timestamp,
|
||||
"updated_at": timestamp,
|
||||
}
|
||||
if agent_id:
|
||||
note["agent_id"] = agent_id
|
||||
if agent_name:
|
||||
note["agent_name"] = agent_name
|
||||
_notes_storage[note_id] = note
|
||||
except (ValueError, TypeError) as e:
|
||||
return {"success": False, "error": f"Failed to create note: {e}", "note_id": None}
|
||||
@@ -234,17 +197,11 @@ def _list_notes_impl(
|
||||
tags: list[str] | None = None,
|
||||
search: str | None = None,
|
||||
include_content: bool = False,
|
||||
caller_agent_id: str | None = None,
|
||||
) -> dict[str, Any]:
|
||||
with _notes_lock:
|
||||
try:
|
||||
filtered = _filter_notes(category=category, tags=tags, search_query=search)
|
||||
notes = [
|
||||
_to_note_listing_entry(
|
||||
n, include_content=include_content, caller_agent_id=caller_agent_id
|
||||
)
|
||||
for n in filtered
|
||||
]
|
||||
notes = [_to_note_listing_entry(n, include_content=include_content) for n in filtered]
|
||||
except (ValueError, TypeError) as e:
|
||||
return {
|
||||
"success": False,
|
||||
@@ -261,7 +218,7 @@ def _list_notes_impl(
|
||||
}
|
||||
|
||||
|
||||
def _get_note_impl(note_id: str, caller_agent_id: str | None = None) -> dict[str, Any]:
|
||||
def _get_note_impl(note_id: str) -> dict[str, Any]:
|
||||
with _notes_lock:
|
||||
try:
|
||||
if not note_id or not note_id.strip():
|
||||
@@ -275,7 +232,6 @@ def _get_note_impl(note_id: str, caller_agent_id: str | None = None) -> dict[str
|
||||
}
|
||||
note_with_id = note.copy()
|
||||
note_with_id["note_id"] = note_id
|
||||
_mark_authorship(note_with_id, note, caller_agent_id)
|
||||
except (ValueError, TypeError) as e:
|
||||
return {"success": False, "error": f"Failed to get note: {e}", "note": None}
|
||||
else:
|
||||
@@ -348,9 +304,7 @@ async def create_note(
|
||||
|
||||
Notes are visible to every agent in the same scan for the lifetime
|
||||
of the run; they live in-memory only and are cleared when the
|
||||
process exits. Each note records the agent that wrote it, so
|
||||
``list_notes`` / ``get_note`` show the author (``agent_name``) and
|
||||
flag your own notes with ``by_you``.
|
||||
process exits.
|
||||
|
||||
For actionable tasks, use ``todo`` instead — notes are for capturing
|
||||
information, todos are for tracking work.
|
||||
@@ -375,11 +329,8 @@ async def create_note(
|
||||
category: One of the categories above. Default ``"general"``.
|
||||
tags: Optional free-form tags.
|
||||
"""
|
||||
agent_id, agent_name = _caller_identity(ctx)
|
||||
return json.dumps(
|
||||
await asyncio.to_thread(
|
||||
_create_note_impl, title, content, category, tags, agent_id, agent_name
|
||||
),
|
||||
await asyncio.to_thread(_create_note_impl, title, content, category, tags),
|
||||
ensure_ascii=False,
|
||||
default=str,
|
||||
)
|
||||
@@ -404,9 +355,6 @@ async def list_notes(
|
||||
when you need to scan many notes; expensive in tokens for large
|
||||
notes.
|
||||
|
||||
Each entry also carries the author (``agent_name``) and, for notes
|
||||
you wrote yourself, ``by_you: true``.
|
||||
|
||||
Args:
|
||||
category: Filter by category.
|
||||
tags: Filter to notes that have any of these tags.
|
||||
@@ -414,7 +362,6 @@ async def list_notes(
|
||||
include_content: When False (default) entries have a preview;
|
||||
when True the full ``content`` is included.
|
||||
"""
|
||||
caller_agent_id, _ = _caller_identity(ctx)
|
||||
return json.dumps(
|
||||
await asyncio.to_thread(
|
||||
_list_notes_impl,
|
||||
@@ -422,7 +369,6 @@ async def list_notes(
|
||||
tags=tags,
|
||||
search=search,
|
||||
include_content=include_content,
|
||||
caller_agent_id=caller_agent_id,
|
||||
),
|
||||
ensure_ascii=False,
|
||||
default=str,
|
||||
@@ -436,11 +382,8 @@ async def get_note(ctx: RunContextWrapper, note_id: str) -> str:
|
||||
Args:
|
||||
note_id: Note id from ``create_note`` or a ``list_notes`` entry.
|
||||
"""
|
||||
caller_agent_id, _ = _caller_identity(ctx)
|
||||
return json.dumps(
|
||||
await asyncio.to_thread(_get_note_impl, note_id, caller_agent_id),
|
||||
ensure_ascii=False,
|
||||
default=str,
|
||||
await asyncio.to_thread(_get_note_impl, note_id), ensure_ascii=False, default=str
|
||||
)
|
||||
|
||||
|
||||
|
||||
@@ -1,166 +0,0 @@
|
||||
"""Bound oversized tool results before they enter agent history.
|
||||
|
||||
Oversized results are spilled into the sandbox at
|
||||
``/workspace/.strix/tool-output/<id>.txt``; the agent sees a head + tail slice
|
||||
plus the path and reads the rest back with its own file tools. The spill writer
|
||||
is injected by the runner via :func:`configure_spill_writer`.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import uuid
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from collections.abc import Awaitable, Callable
|
||||
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
_TRUNCATION_NOTICE = "[... {lines} lines ({bytes} bytes) truncated ...]"
|
||||
_WORKSPACE_SPILL_NOTICE = (
|
||||
"[... {lines} lines ({bytes} bytes) truncated — full output saved to {path} "
|
||||
"in the sandbox; read it with exec_command (e.g. `sed -n`, `grep`, `cat`) ...]"
|
||||
)
|
||||
|
||||
WORKSPACE_SPILL_DIR = "/workspace/.strix/tool-output"
|
||||
|
||||
# Longest possible workspace path, used only to reserve notice bytes.
|
||||
_SAMPLE_WORKSPACE_PATH = f"{WORKSPACE_SPILL_DIR}/{'0' * 32}.txt"
|
||||
|
||||
if TYPE_CHECKING:
|
||||
SpillWriter = Callable[[str, str], Awaitable[str | None]]
|
||||
|
||||
_spill: dict[str, SpillWriter] = {}
|
||||
|
||||
|
||||
def configure_spill_writer(writer: SpillWriter | None) -> None:
|
||||
"""Install (or clear) the sandbox-workspace spill writer."""
|
||||
if writer is None:
|
||||
_spill.pop("writer", None)
|
||||
else:
|
||||
_spill["writer"] = writer
|
||||
|
||||
|
||||
def _byte_len(text: str) -> int:
|
||||
return len(text.encode("utf-8"))
|
||||
|
||||
|
||||
def _take_prefix(text: str, max_bytes: int) -> str:
|
||||
budget = 0
|
||||
out: list[str] = []
|
||||
for char in text:
|
||||
size = len(char.encode("utf-8"))
|
||||
if budget + size > max_bytes:
|
||||
break
|
||||
out.append(char)
|
||||
budget += size
|
||||
return "".join(out)
|
||||
|
||||
|
||||
def _take_suffix(text: str, max_bytes: int) -> str:
|
||||
budget = 0
|
||||
out: list[str] = []
|
||||
for char in reversed(text):
|
||||
size = len(char.encode("utf-8"))
|
||||
if budget + size > max_bytes:
|
||||
break
|
||||
out.append(char)
|
||||
budget += size
|
||||
out.reverse()
|
||||
return "".join(out)
|
||||
|
||||
|
||||
def _head_tail(
|
||||
text: str,
|
||||
max_lines: int,
|
||||
max_bytes: int,
|
||||
*,
|
||||
notice_templates: tuple[str, ...] = (_TRUNCATION_NOTICE,),
|
||||
) -> tuple[str, str, int, int] | None:
|
||||
"""Head/tail slices plus dropped line/byte counts, or ``None`` if small.
|
||||
|
||||
``max_bytes`` bounds the entire joined result; the largest of
|
||||
``notice_templates`` (plus separators) is reserved before slicing.
|
||||
"""
|
||||
lines = text.split("\n")
|
||||
total_bytes = _byte_len(text)
|
||||
if len(lines) <= max_lines and total_bytes <= max_bytes:
|
||||
return None
|
||||
|
||||
# Reserve using the largest counts/path; ``+ 4`` covers the two "\n\n".
|
||||
notice_overhead = (
|
||||
max(
|
||||
_byte_len(
|
||||
template.format(
|
||||
lines=len(lines),
|
||||
bytes=total_bytes,
|
||||
path=_SAMPLE_WORKSPACE_PATH,
|
||||
)
|
||||
)
|
||||
for template in notice_templates
|
||||
)
|
||||
+ 4
|
||||
)
|
||||
byte_budget = max(2, max_bytes - notice_overhead)
|
||||
|
||||
head_lines = max(1, max_lines // 2)
|
||||
tail_lines = max_lines - head_lines
|
||||
head = "\n".join(lines[:head_lines])
|
||||
tail = "\n".join(lines[len(lines) - tail_lines :]) if tail_lines > 0 else ""
|
||||
|
||||
half_bytes = max(1, byte_budget // 2)
|
||||
if _byte_len(head) > half_bytes:
|
||||
head = _take_prefix(head, half_bytes)
|
||||
if tail and _byte_len(tail) > half_bytes:
|
||||
tail = _take_suffix(tail, half_bytes)
|
||||
|
||||
# Count from the final slices; the byte pass may have dropped whole lines.
|
||||
kept_lines = len(head.split("\n")) + (len(tail.split("\n")) if tail else 0)
|
||||
dropped_lines = max(0, len(lines) - kept_lines)
|
||||
dropped_bytes = max(0, total_bytes - _byte_len(head) - _byte_len(tail))
|
||||
return head, tail, dropped_lines, dropped_bytes
|
||||
|
||||
|
||||
def _join(head: str, tail: str, notice: str) -> str:
|
||||
return f"{head}\n\n{notice}\n\n{tail}" if tail else f"{head}\n\n{notice}"
|
||||
|
||||
|
||||
def bound_text(text: str, *, max_lines: int, max_bytes: int) -> str:
|
||||
"""Return ``text`` unchanged when small, else a head+tail preview.
|
||||
|
||||
Nothing is persisted; use :func:`bound_and_store` to keep the full output.
|
||||
"""
|
||||
parts = _head_tail(text, max_lines, max_bytes)
|
||||
if parts is None:
|
||||
return text
|
||||
head, tail, dropped_lines, dropped_bytes = parts
|
||||
return _join(head, tail, _TRUNCATION_NOTICE.format(lines=dropped_lines, bytes=dropped_bytes))
|
||||
|
||||
|
||||
async def bound_and_store(text: str, *, max_lines: int, max_bytes: int) -> str:
|
||||
"""Like :func:`bound_text`, but spill the full output into the sandbox and
|
||||
point the agent at its path. Degrades to a plain preview if the spill fails.
|
||||
"""
|
||||
parts = _head_tail(
|
||||
text,
|
||||
max_lines,
|
||||
max_bytes,
|
||||
notice_templates=(_WORKSPACE_SPILL_NOTICE, _TRUNCATION_NOTICE),
|
||||
)
|
||||
if parts is None:
|
||||
return text
|
||||
head, tail, dropped_lines, dropped_bytes = parts
|
||||
|
||||
writer = _spill.get("writer")
|
||||
if writer is not None:
|
||||
path = await writer(uuid.uuid4().hex, text)
|
||||
if path is not None:
|
||||
notice = _WORKSPACE_SPILL_NOTICE.format(
|
||||
lines=dropped_lines, bytes=dropped_bytes, path=path
|
||||
)
|
||||
return _join(head, tail, notice)
|
||||
|
||||
return _join(head, tail, _TRUNCATION_NOTICE.format(lines=dropped_lines, bytes=dropped_bytes))
|
||||
+21
-309
@@ -1,13 +1,7 @@
|
||||
"""Reporting tools — file vuln findings (with dedup + CVSS) and read them back.
|
||||
|
||||
``create_vulnerability_report`` / ``create_dependency_report`` file findings;
|
||||
``list_reports`` / ``get_report`` let any agent (notably the root orchestrator)
|
||||
review what's been filed so far across the whole scan.
|
||||
"""
|
||||
"""``create_vulnerability_report`` — file a vuln finding with dedup + CVSS."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import json
|
||||
import logging
|
||||
import re
|
||||
@@ -324,21 +318,6 @@ async def _do_create( # noqa: PLR0912
|
||||
}
|
||||
|
||||
|
||||
def _caller_identity(ctx: RunContextWrapper) -> tuple[str | None, str | None]:
|
||||
"""Return the (agent_id, agent_name) of the agent invoking this tool."""
|
||||
inner = ctx.context if isinstance(ctx.context, dict) else {}
|
||||
raw_agent_id = inner.get("agent_id")
|
||||
agent_id = raw_agent_id if isinstance(raw_agent_id, str) else None
|
||||
agent_name: str | None = None
|
||||
coordinator = inner.get("coordinator")
|
||||
if agent_id is not None and coordinator is not None:
|
||||
names = getattr(coordinator, "names", {})
|
||||
if isinstance(names, dict):
|
||||
raw_agent_name = names.get(agent_id)
|
||||
agent_name = raw_agent_name if isinstance(raw_agent_name, str) else None
|
||||
return agent_id, agent_name
|
||||
|
||||
|
||||
@function_tool(timeout=180, strict_mode=False)
|
||||
async def create_vulnerability_report(
|
||||
ctx: RunContextWrapper,
|
||||
@@ -625,7 +604,16 @@ async def create_vulnerability_report(
|
||||
template engine's auto-escaping over string interpolation.
|
||||
fix_effort: "low"
|
||||
"""
|
||||
agent_id, agent_name = _caller_identity(ctx)
|
||||
inner = ctx.context if isinstance(ctx.context, dict) else {}
|
||||
raw_agent_id = inner.get("agent_id")
|
||||
agent_id = raw_agent_id if isinstance(raw_agent_id, str) else None
|
||||
agent_name = None
|
||||
coordinator = inner.get("coordinator")
|
||||
if agent_id is not None and coordinator is not None:
|
||||
names = getattr(coordinator, "names", {})
|
||||
if isinstance(names, dict):
|
||||
raw_agent_name = names.get(agent_id)
|
||||
agent_name = raw_agent_name if isinstance(raw_agent_name, str) else None
|
||||
|
||||
result = await _do_create(
|
||||
title=title,
|
||||
@@ -930,7 +918,16 @@ async def create_dependency_report(
|
||||
fix_effort: One of ``trivial`` / ``low`` / ``medium`` / ``high``
|
||||
(dependency upgrades are usually ``trivial``/``low``).
|
||||
"""
|
||||
agent_id, agent_name = _caller_identity(ctx)
|
||||
inner = ctx.context if isinstance(ctx.context, dict) else {}
|
||||
raw_agent_id = inner.get("agent_id")
|
||||
agent_id = raw_agent_id if isinstance(raw_agent_id, str) else None
|
||||
agent_name = None
|
||||
coordinator = inner.get("coordinator")
|
||||
if agent_id is not None and coordinator is not None:
|
||||
names = getattr(coordinator, "names", {})
|
||||
if isinstance(names, dict):
|
||||
raw_agent_name = names.get(agent_id)
|
||||
agent_name = raw_agent_name if isinstance(raw_agent_name, str) else None
|
||||
|
||||
result = await _do_create_dependency(
|
||||
title=title,
|
||||
@@ -952,288 +949,3 @@ async def create_dependency_report(
|
||||
agent_name=agent_name,
|
||||
)
|
||||
return json.dumps(result, ensure_ascii=False, default=str)
|
||||
|
||||
|
||||
_SEVERITY_ORDER = {
|
||||
"critical": 0,
|
||||
"high": 1,
|
||||
"medium": 2,
|
||||
"low": 3,
|
||||
"info": 4,
|
||||
"none": 5,
|
||||
}
|
||||
_VALID_SEVERITIES = frozenset(_SEVERITY_ORDER)
|
||||
_VALID_FINDING_CLASSES = frozenset({"dynamic", "dependency_cve"})
|
||||
_REPORT_DESCRIPTION_PREVIEW_CHARS = 280
|
||||
|
||||
# Compact, listing-safe fields — no full bodies / PoC code / evidence.
|
||||
_REPORT_SUMMARY_FIELDS = (
|
||||
"id",
|
||||
"title",
|
||||
"severity",
|
||||
"cvss",
|
||||
"finding_class",
|
||||
"cve",
|
||||
"cwe",
|
||||
"target",
|
||||
"endpoint",
|
||||
"method",
|
||||
"fix_effort",
|
||||
"agent_name",
|
||||
"timestamp",
|
||||
)
|
||||
|
||||
|
||||
def _report_severity_rank(report: dict[str, Any]) -> int:
|
||||
return _SEVERITY_ORDER.get(str(report.get("severity", "")).lower(), 99)
|
||||
|
||||
|
||||
def _report_matches_filters(
|
||||
report: dict[str, Any],
|
||||
*,
|
||||
severity: str | None,
|
||||
finding_class: str | None,
|
||||
target: str | None,
|
||||
search: str | None,
|
||||
) -> bool:
|
||||
if severity and str(report.get("severity", "")).lower() != severity:
|
||||
return False
|
||||
if finding_class and str(report.get("finding_class", "dynamic")).lower() != finding_class:
|
||||
return False
|
||||
if target:
|
||||
target_lower = target.lower()
|
||||
haystack = f"{report.get('target', '')} {report.get('endpoint', '')}".lower()
|
||||
if target_lower not in haystack:
|
||||
return False
|
||||
if search:
|
||||
search_lower = search.lower()
|
||||
title_match = search_lower in str(report.get("title", "")).lower()
|
||||
desc_match = search_lower in str(report.get("description", "")).lower()
|
||||
if not (title_match or desc_match):
|
||||
return False
|
||||
return True
|
||||
|
||||
|
||||
def _mark_authorship(
|
||||
entry: dict[str, Any], report: dict[str, Any], caller_agent_id: str | None
|
||||
) -> dict[str, Any]:
|
||||
"""Flag whether ``report`` was filed by the agent making this call."""
|
||||
if caller_agent_id is not None and report.get("agent_id") == caller_agent_id:
|
||||
entry["by_you"] = True
|
||||
return entry
|
||||
|
||||
|
||||
def _to_report_summary_entry(
|
||||
report: dict[str, Any], caller_agent_id: str | None = None
|
||||
) -> dict[str, Any]:
|
||||
entry = {
|
||||
field: report[field] for field in _REPORT_SUMMARY_FIELDS if report.get(field) is not None
|
||||
}
|
||||
description = str(report.get("description", "")).strip()
|
||||
if description:
|
||||
if len(description) > _REPORT_DESCRIPTION_PREVIEW_CHARS:
|
||||
entry["description_preview"] = (
|
||||
f"{description[:_REPORT_DESCRIPTION_PREVIEW_CHARS].rstrip()}..."
|
||||
)
|
||||
else:
|
||||
entry["description_preview"] = description
|
||||
return _mark_authorship(entry, report, caller_agent_id)
|
||||
|
||||
|
||||
def _severity_counts(reports: list[dict[str, Any]]) -> dict[str, int]:
|
||||
counts: dict[str, int] = {}
|
||||
for report in reports:
|
||||
sev = str(report.get("severity", "")).lower() or "none"
|
||||
counts[sev] = counts.get(sev, 0) + 1
|
||||
return {sev: counts[sev] for sev in _SEVERITY_ORDER if sev in counts}
|
||||
|
||||
|
||||
async def _run_report_reader(fn: Any, *args: Any, **kwargs: Any) -> dict[str, Any]:
|
||||
try:
|
||||
return await asyncio.to_thread(fn, *args, **kwargs)
|
||||
except (ImportError, AttributeError) as e:
|
||||
logger.exception("report reader failed")
|
||||
return {"success": False, "error": f"Failed to read reports: {e!s}"}
|
||||
|
||||
|
||||
def _do_list_reports(
|
||||
*,
|
||||
severity: str | None,
|
||||
finding_class: str | None,
|
||||
target: str | None,
|
||||
search: str | None,
|
||||
include_details: bool,
|
||||
caller_agent_id: str | None = None,
|
||||
) -> dict[str, Any]:
|
||||
errors: list[str] = []
|
||||
severity = (severity or "").strip().lower() or None
|
||||
if severity and severity not in _VALID_SEVERITIES:
|
||||
errors.append(
|
||||
f"Invalid severity: {severity!r}. Must be one of: {sorted(_VALID_SEVERITIES)}"
|
||||
)
|
||||
finding_class = (finding_class or "").strip().lower() or None
|
||||
if finding_class and finding_class not in _VALID_FINDING_CLASSES:
|
||||
errors.append(
|
||||
f"Invalid finding_class: {finding_class!r}. "
|
||||
f"Must be one of: {sorted(_VALID_FINDING_CLASSES)}"
|
||||
)
|
||||
if errors:
|
||||
return {"success": False, "error": "Validation failed", "errors": errors}
|
||||
|
||||
from strix.report.state import get_global_report_state
|
||||
|
||||
report_state = get_global_report_state()
|
||||
if report_state is None:
|
||||
return {
|
||||
"success": True,
|
||||
"reports": [],
|
||||
"filtered_count": 0,
|
||||
"total_count": 0,
|
||||
"severity_counts": {},
|
||||
"warning": "Report state unavailable - no reports have been filed yet",
|
||||
}
|
||||
|
||||
all_reports = report_state.get_existing_vulnerabilities()
|
||||
matched = [
|
||||
r
|
||||
for r in all_reports
|
||||
if _report_matches_filters(
|
||||
r,
|
||||
severity=severity,
|
||||
finding_class=finding_class,
|
||||
target=(target or "").strip() or None,
|
||||
search=(search or "").strip() or None,
|
||||
)
|
||||
]
|
||||
matched.sort(key=lambda r: (_report_severity_rank(r), str(r.get("id", ""))))
|
||||
|
||||
reports = [
|
||||
_mark_authorship(dict(r), r, caller_agent_id)
|
||||
if include_details
|
||||
else _to_report_summary_entry(r, caller_agent_id)
|
||||
for r in matched
|
||||
]
|
||||
return {
|
||||
"success": True,
|
||||
"reports": reports,
|
||||
"filtered_count": len(reports),
|
||||
"total_count": len(all_reports),
|
||||
"severity_counts": _severity_counts(all_reports),
|
||||
}
|
||||
|
||||
|
||||
def _do_get_report(report_id: str, caller_agent_id: str | None = None) -> dict[str, Any]:
|
||||
report_id = (report_id or "").strip()
|
||||
if not report_id:
|
||||
return {"success": False, "error": "report_id cannot be empty", "report": None}
|
||||
|
||||
from strix.report.state import get_global_report_state
|
||||
|
||||
report_state = get_global_report_state()
|
||||
if report_state is None:
|
||||
return {
|
||||
"success": False,
|
||||
"error": "Report state unavailable - no reports have been filed yet",
|
||||
"report": None,
|
||||
}
|
||||
|
||||
for report in report_state.get_existing_vulnerabilities():
|
||||
if report.get("id") == report_id:
|
||||
return {
|
||||
"success": True,
|
||||
"report": _mark_authorship(dict(report), report, caller_agent_id),
|
||||
}
|
||||
return {
|
||||
"success": False,
|
||||
"error": f"Report with id '{report_id}' not found",
|
||||
"report": None,
|
||||
}
|
||||
|
||||
|
||||
@function_tool(timeout=30)
|
||||
async def list_reports(
|
||||
ctx: RunContextWrapper,
|
||||
severity: str | None = None,
|
||||
finding_class: str | None = None,
|
||||
target: str | None = None,
|
||||
search: str | None = None,
|
||||
include_details: bool = False,
|
||||
) -> str:
|
||||
"""List vulnerability reports filed so far in this scan — metadata-first.
|
||||
|
||||
**For the orchestrator / root agent.** This is an orchestration tool
|
||||
for tracking scan-wide coverage and assembling the final report — leaf
|
||||
/ specialist agents do their own testing and file findings; they should
|
||||
NOT call this. If you are a subagent, ignore it and focus on your task.
|
||||
|
||||
Reports are shared across **every** agent in the scan, so this returns
|
||||
findings filed by any agent (root or child), not just your own. As the
|
||||
root agent, use it to track progress, avoid dispatching work on
|
||||
already-covered ground, reason about attack-chaining across confirmed
|
||||
findings, and build the ``finish_scan`` executive summary.
|
||||
|
||||
By default each entry is compact: ``id``, ``title``, ``severity``,
|
||||
``cvss``, ``finding_class``, ``cve`` / ``cwe``, ``target`` /
|
||||
``endpoint``, ``fix_effort``, ``agent_name`` (who filed it), ``timestamp``,
|
||||
plus a 280-char ``description_preview``. Entries you filed yourself are
|
||||
flagged ``by_you: true``. The response also carries
|
||||
``total_count`` and ``severity_counts`` (counts per severity across all
|
||||
reports, ignoring filters). Set ``include_details=True`` for full report
|
||||
bodies (PoC, evidence, remediation, code_locations) — token-expensive;
|
||||
prefer ``get_report`` to drill into a single finding.
|
||||
|
||||
Filters compose (all must match): ``severity`` and ``finding_class``
|
||||
match exactly, ``target`` is a substring match against target/endpoint,
|
||||
and ``search`` is a substring match against title/description. Results
|
||||
are ordered by severity (critical -> info), then report id.
|
||||
|
||||
This is read-only — it never files or dedupes anything.
|
||||
|
||||
Args:
|
||||
severity: Filter to one of ``critical`` / ``high`` / ``medium`` /
|
||||
``low`` / ``info`` / ``none``.
|
||||
finding_class: Filter to ``dynamic`` (PoC-backed) or
|
||||
``dependency_cve`` (known-CVE supply-chain).
|
||||
target: Substring match against a report's target / endpoint.
|
||||
search: Substring match against title and description.
|
||||
include_details: When False (default) entries are compact; when
|
||||
True full report bodies are returned.
|
||||
"""
|
||||
caller_agent_id, _ = _caller_identity(ctx)
|
||||
return json.dumps(
|
||||
await _run_report_reader(
|
||||
_do_list_reports,
|
||||
severity=severity,
|
||||
finding_class=finding_class,
|
||||
target=target,
|
||||
search=search,
|
||||
include_details=include_details,
|
||||
caller_agent_id=caller_agent_id,
|
||||
),
|
||||
ensure_ascii=False,
|
||||
default=str,
|
||||
)
|
||||
|
||||
|
||||
@function_tool(timeout=30)
|
||||
async def get_report(ctx: RunContextWrapper, report_id: str) -> str:
|
||||
"""Fetch one vulnerability report by its id (e.g. ``vuln-0001``).
|
||||
|
||||
Returns the full report body — description, impact, technical analysis,
|
||||
PoC, evidence, remediation, CVSS breakdown, and any ``code_locations``.
|
||||
Use ``list_reports`` first to find ids; this is the cheap way to read a
|
||||
single finding in full without pulling every body.
|
||||
|
||||
Read-only.
|
||||
|
||||
Args:
|
||||
report_id: Report id from ``list_reports`` or a
|
||||
``create_vulnerability_report`` / ``create_dependency_report``
|
||||
response (format ``vuln-NNNN``).
|
||||
"""
|
||||
caller_agent_id, _ = _caller_identity(ctx)
|
||||
return json.dumps(
|
||||
await _run_report_reader(_do_get_report, report_id, caller_agent_id),
|
||||
ensure_ascii=False,
|
||||
default=str,
|
||||
)
|
||||
|
||||
@@ -1,6 +0,0 @@
|
||||
"""User-facing reply tool for interactive sessions."""
|
||||
|
||||
from strix.tools.respond.tool import respond_to_user
|
||||
|
||||
|
||||
__all__ = ["respond_to_user"]
|
||||
@@ -1,110 +0,0 @@
|
||||
"""``respond_to_user`` — deliver a reply and hand control back to the user."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
from typing import Any
|
||||
|
||||
from agents import RunContextWrapper, function_tool
|
||||
|
||||
from strix.core.agents import coordinator_from_context
|
||||
|
||||
|
||||
def _ctx(ctx: RunContextWrapper) -> dict[str, Any]:
|
||||
return ctx.context if isinstance(ctx.context, dict) else {}
|
||||
|
||||
|
||||
@function_tool
|
||||
async def respond_to_user(ctx: RunContextWrapper, message: str) -> str:
|
||||
"""Answer the user and hand control back to them.
|
||||
|
||||
This is the ONLY way to yield to the user. Delivering the message and
|
||||
yielding are the same call on purpose: there is no way to answer and
|
||||
then forget to stop, and no way to stop without having answered.
|
||||
|
||||
Call it when you have something for the user and nothing to do until
|
||||
they reply — you answered their question, you need a decision or a
|
||||
credential only they can give, or you finished a chunk of work and
|
||||
want direction. You resume exactly where you left off when they
|
||||
reply, with everything you have done so far intact.
|
||||
|
||||
Do NOT call it to narrate progress or to think out loud. Plain text
|
||||
is still shown to the user as you work, so say whatever you like
|
||||
mid-task without stopping; ``respond_to_user`` is specifically the
|
||||
act of *waiting* for them. Every call costs the user their attention.
|
||||
|
||||
Not for these:
|
||||
|
||||
- **Waiting on another agent** (a child's report, a peer's reply) —
|
||||
use ``wait_for_agents``.
|
||||
- **Ending the engagement** — use ``finish_scan`` (root) or
|
||||
``agent_finish`` (subagent). Those are terminal; this is a pause.
|
||||
|
||||
Args:
|
||||
message: What to say to the user. Self-contained: they may not
|
||||
have followed the tool calls that led here. Lead with the
|
||||
answer or the decision you need, and if you are blocked, say
|
||||
exactly what you need from them.
|
||||
"""
|
||||
inner = _ctx(ctx)
|
||||
coordinator = coordinator_from_context(inner)
|
||||
me = inner.get("agent_id")
|
||||
interactive = bool(inner.get("interactive", False))
|
||||
|
||||
if coordinator is None or me is None:
|
||||
return json.dumps(
|
||||
{"success": False, "error": "Agent coordinator or agent_id missing in context"},
|
||||
ensure_ascii=False,
|
||||
default=str,
|
||||
)
|
||||
|
||||
if not interactive:
|
||||
return json.dumps(
|
||||
{
|
||||
"success": False,
|
||||
"error": (
|
||||
"No user is attached to an autonomous run. Keep working, and call "
|
||||
"finish_scan (root) or agent_finish (subagent) when the task is done."
|
||||
),
|
||||
},
|
||||
ensure_ascii=False,
|
||||
default=str,
|
||||
)
|
||||
|
||||
async with coordinator._lock:
|
||||
stopped = coordinator.statuses.get(me) == "stopped"
|
||||
if stopped:
|
||||
return json.dumps(
|
||||
{"success": True, "wait_outcome": "stopped", "message": message},
|
||||
ensure_ascii=False,
|
||||
default=str,
|
||||
)
|
||||
|
||||
# A message that arrived while this turn was running is the user already
|
||||
# talking: take it now instead of parking for one they have sent.
|
||||
pending, _ = await coordinator.consume_pending(me)
|
||||
if pending > 0:
|
||||
await coordinator.mark_running(me)
|
||||
return json.dumps(
|
||||
{
|
||||
"success": True,
|
||||
"wait_outcome": "message_arrived",
|
||||
"pending_messages": pending,
|
||||
"message": message,
|
||||
"note": "Your reply was delivered; the user had already sent a new message.",
|
||||
},
|
||||
ensure_ascii=False,
|
||||
default=str,
|
||||
)
|
||||
|
||||
await coordinator.park_waiting(me, wait_kind="user")
|
||||
return json.dumps(
|
||||
{
|
||||
"success": True,
|
||||
"wait_outcome": "waiting",
|
||||
"message": message,
|
||||
"note": "Reply delivered; parked until the user responds.",
|
||||
},
|
||||
ensure_ascii=False,
|
||||
default=str,
|
||||
)
|
||||
@@ -6,7 +6,7 @@ directly from the run's on-disk files. No cloud dependency, no file picker.
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from strix.interface.viewer.server import serve
|
||||
from strix.viewer.server import serve
|
||||
|
||||
|
||||
__all__ = ["serve"]
|
||||
@@ -15,12 +15,12 @@ import base64
|
||||
import contextlib
|
||||
import json
|
||||
import logging
|
||||
import urllib.error
|
||||
import urllib.request
|
||||
from datetime import UTC, datetime
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
import requests
|
||||
|
||||
from strix.config.loader import load_settings
|
||||
|
||||
|
||||
@@ -147,17 +147,21 @@ def _post_json(path: str, payload: dict[str, Any], *, timeout: int) -> tuple[int
|
||||
map, not raised.
|
||||
"""
|
||||
url = f"{_app_url()}{path}"
|
||||
body = json.dumps(payload).encode("utf-8")
|
||||
request = urllib.request.Request( # noqa: S310 - fixed https relay URL
|
||||
url,
|
||||
data=body,
|
||||
headers={"Content-Type": "application/json", "Accept": "application/json"},
|
||||
method="POST",
|
||||
)
|
||||
try:
|
||||
response = requests.post(
|
||||
url,
|
||||
json=payload,
|
||||
headers={"Accept": "application/json"},
|
||||
timeout=timeout,
|
||||
)
|
||||
except requests.RequestException as exc:
|
||||
with urllib.request.urlopen(request, timeout=timeout) as response: # noqa: S310
|
||||
return response.status, _parse_body(response.read())
|
||||
except urllib.error.HTTPError as exc:
|
||||
return exc.code, _parse_body(exc.read())
|
||||
except (urllib.error.URLError, TimeoutError, OSError) as exc:
|
||||
logger.warning("relay request to %s failed: %s", path, exc)
|
||||
raise RelayError("unavailable") from exc
|
||||
return response.status_code, _parse_body(response.content)
|
||||
|
||||
|
||||
def _parse_body(raw: bytes) -> dict[str, Any]:
|
||||
@@ -16,8 +16,8 @@ from strix.core.paths import (
|
||||
run_record_path,
|
||||
runs_base_dir,
|
||||
)
|
||||
from strix.interface.viewer.server import authorized_url, bundle_is_built, serve
|
||||
from strix.interface.viewer.transcript import read_run_summary
|
||||
from strix.viewer.server import authorized_url, bundle_is_built, serve
|
||||
from strix.viewer.transcript import read_run_summary
|
||||
|
||||
|
||||
if TYPE_CHECKING:
|
||||
@@ -58,7 +58,7 @@ def run_view(argv: list[str]) -> None:
|
||||
if not bundle_is_built():
|
||||
console.print(
|
||||
"[bold red]Viewer UI is not built.[/]\n"
|
||||
"Build it with: [cyan]cd strix/interface/viewer/frontend && npm ci && npm run build[/]"
|
||||
"Build it with: [cyan]cd strix/viewer/frontend && npm ci && npm run build[/]"
|
||||
)
|
||||
raise SystemExit(1)
|
||||
|
||||
Generated
+9
@@ -63,6 +63,7 @@
|
||||
"integrity": "sha512-RgHBCvtjbOK2gXSNBNIkNoEc9qoVEtau3hj8gEqKQuL3HZAibKarWFEI3Lfm6EYKkLalOh8eSrj9b+ch9H/VBA==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"peer": true,
|
||||
"dependencies": {
|
||||
"@babel/code-frame": "^7.29.7",
|
||||
"@babel/generator": "^7.29.7",
|
||||
@@ -1604,6 +1605,7 @@
|
||||
"resolved": "https://registry.npmjs.org/@types/react/-/react-19.2.17.tgz",
|
||||
"integrity": "sha512-MXfmqaVPEVgkBT/aY0aGCkRWWtByiYQXo3xdQ8r5RzuFrPiRn8Gar2tQdXSUQ2GKV3bkXckek89V8wQBY2Q/Aw==",
|
||||
"license": "MIT",
|
||||
"peer": true,
|
||||
"dependencies": {
|
||||
"csstype": "^3.2.2"
|
||||
}
|
||||
@@ -1614,6 +1616,7 @@
|
||||
"integrity": "sha512-jp2L/eY6fn+KgVVQAOqYItbF0VY/YApe5Mz2F0aykSO8gx31bYCZyvSeYxCHKvzHG5eZjc+zyaS5BrBWya2+kQ==",
|
||||
"devOptional": true,
|
||||
"license": "MIT",
|
||||
"peer": true,
|
||||
"peerDependencies": {
|
||||
"@types/react": "^19.2.0"
|
||||
}
|
||||
@@ -1736,6 +1739,7 @@
|
||||
}
|
||||
],
|
||||
"license": "MIT",
|
||||
"peer": true,
|
||||
"dependencies": {
|
||||
"baseline-browser-mapping": "^2.10.42",
|
||||
"caniuse-lite": "^1.0.30001803",
|
||||
@@ -1916,6 +1920,7 @@
|
||||
"resolved": "https://registry.npmjs.org/d3-selection/-/d3-selection-3.0.0.tgz",
|
||||
"integrity": "sha512-fmTRWbNMmsmWq6xJV8D19U/gw/bwrHfNXxrIN+HfZgnzqTHp9jOmKMhsTUjXOJnZOdZY9Q28y4yebKzqDKlxlQ==",
|
||||
"license": "ISC",
|
||||
"peer": true,
|
||||
"engines": {
|
||||
"node": ">=12"
|
||||
}
|
||||
@@ -3566,6 +3571,7 @@
|
||||
"integrity": "sha512-RvwwcruNjI1ncT5xRakeyS9Lf8lcItv34KD+aif+VH9kduAyfYBipGh12274xtenIPZ119/R9BdTBa8gAwSh0A==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"peer": true,
|
||||
"engines": {
|
||||
"node": ">=12"
|
||||
},
|
||||
@@ -3617,6 +3623,7 @@
|
||||
"resolved": "https://registry.npmjs.org/react/-/react-19.2.7.tgz",
|
||||
"integrity": "sha512-HNe9WslTbXmFK8o8cmwgAeJFSBvt1bPdHCVKtaaV+WlAN36mpT4hcRpwbf3fY56ar2oIXzsBpOAiIRHAdY0OlQ==",
|
||||
"license": "MIT",
|
||||
"peer": true,
|
||||
"engines": {
|
||||
"node": ">=0.10.0"
|
||||
}
|
||||
@@ -3626,6 +3633,7 @@
|
||||
"resolved": "https://registry.npmjs.org/react-dom/-/react-dom-19.2.7.tgz",
|
||||
"integrity": "sha512-t0BRVXvbiE/o20Hfw669rLbMCDWtYZLvmJigy2f0MxsXF+71pxhR3xOkspmsO8h3ZlNzyibAmtCa3l4lYKk6gQ==",
|
||||
"license": "MIT",
|
||||
"peer": true,
|
||||
"dependencies": {
|
||||
"scheduler": "^0.27.0"
|
||||
},
|
||||
@@ -4101,6 +4109,7 @@
|
||||
"integrity": "sha512-NTKlcQjlAK7MlQoyb6LgaqHc8sso/pVyUJYWMws3jg21uTJw/LddqIFPcPqP6PzpgbIcZyKI85sFE4HBrQDA8A==",
|
||||
"dev": true,
|
||||
"license": "MIT",
|
||||
"peer": true,
|
||||
"dependencies": {
|
||||
"esbuild": "^0.25.0",
|
||||
"fdir": "^6.4.4",
|
||||
|
Before Width: | Height: | Size: 3.7 KiB After Width: | Height: | Size: 3.7 KiB |
+1
-18
@@ -100,7 +100,6 @@ export function RunDetails({
|
||||
const reasoning = num(rec(arr(usage.output_tokens_details)[0]).reasoning_tokens);
|
||||
const totalTokens = num(usage.total_tokens);
|
||||
const cost = num(usage.cost);
|
||||
const subscription = str(raw.auth_mode) === "subscription";
|
||||
|
||||
const sub = (n: number, word: string) => (
|
||||
<span className="text-[#666]"> ({formatNumber(n)} {word})</span>
|
||||
@@ -176,15 +175,6 @@ export function RunDetails({
|
||||
{hasUsage ? (
|
||||
<dl className="space-y-2.5 tabular-nums">
|
||||
<Field label="Model">{models.length ? models.join(", ") : "n/a"}</Field>
|
||||
{subscription && (
|
||||
<Field label="Provider">
|
||||
<span className="inline-flex items-center gap-1.5">
|
||||
<span className="rounded-full border border-[#22c55e]/40 bg-[#22c55e]/10 px-2 py-0.5 text-[11px] text-[#22c55e]">
|
||||
ChatGPT subscription
|
||||
</span>
|
||||
</span>
|
||||
</Field>
|
||||
)}
|
||||
<Field label="Run time">{fmtDuration(durationSeconds)}</Field>
|
||||
{requests != null && <Field label="Requests">{formatNumber(requests)}</Field>}
|
||||
{inputTokens != null && (
|
||||
@@ -200,14 +190,7 @@ export function RunDetails({
|
||||
</Field>
|
||||
)}
|
||||
{totalTokens != null && <Field label="Total tokens">{formatNumber(totalTokens)}</Field>}
|
||||
{subscription ? (
|
||||
<Field label="Cost">
|
||||
<span className="text-[#22c55e]">$0.00</span>
|
||||
<span className="text-[#666]"> (subscription)</span>
|
||||
</Field>
|
||||
) : (
|
||||
cost != null && <Field label="Cost">${cost.toFixed(2)}</Field>
|
||||
)}
|
||||
{cost != null && <Field label="Cost">${cost.toFixed(2)}</Field>}
|
||||
{agents.length > 0 && <Field label="Agents">{formatNumber(agents.length)}</Field>}
|
||||
</dl>
|
||||
) : (
|
||||
+1
-1
@@ -54,7 +54,7 @@ export default function AgentCommsRenderer({ toolName, args }: ToolRendererProps
|
||||
);
|
||||
}
|
||||
|
||||
if (toolName === "wait_for_agents") {
|
||||
if (toolName === "wait_for_message") {
|
||||
const reason = (args.reason as string) ?? "";
|
||||
return (
|
||||
<div className="flex items-center gap-2">
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user