mirror of
https://github.com/Sea-Haven-Industries/security-review.git
synced 2026-09-30 02:13:13 +00:00
feat: re-home cross-family reviewer CLI, retire Path B host artifacts (#5)
* feat: add router-less cross-family reviewer CLI (cross_review.py)
Re-homes the archived orchestrator repo's GPT-4.1 cross_reviewer as a
direct OpenAI SDK CLI: verbatim system prompt, same model id, ported
3-attempt exponential-backoff retry. Reads OPENAI_API_KEY from the
environment or the gitignored repo-root .env. Lazy openai import so
--help works without the package.
* feat: create machine-level suppressions dir on --global hook install
install-hooks.sh --global now mkdir -p's
${SH_SECURITY_SUPPRESSIONS_DIR:-~/.config/sea-haven/security-review} and
states the convention: machine-level <dir>/<repo-basename>/suppressions.json
is preferred over repo-local .security-review/suppressions.json, with
review.sh merging both when run without --suppressions.
* docs: describe sh-build-review as cross-family GPT-4.1 pass via cross_review.py
* chore: retire Path B VM host artifacts, repoint xmodel hook to cross_review.py
- delete systemd/ units and DEPLOY-R720.md (VM destroyed; recoverable
from git history)
- nightly_sweep.sh: retained for reference — header notes the VM-based
Path B sweep is retired; ENABLE_XMODEL_HOOK now calls this repo's
cross_review.py instead of the archived orchestrator's run.py
- sweep-targets.txt: drop the stale ~/orchestrator warning block
- README: document the Claude Code web cloud routines
(repo-scanner-nightly-sweep 08:00 ET, repo-checkers-plane1 07:30 ET,
ALARM-only to #repo-scanner) and add the cross_review.py section
* docs(iam): repoint cross-family review invocations to cross_review.py
* fix(ci): exclude canary corpus from ruff, add import smoke test
CI has been red repo-wide: the latest ruff wants to reformat the
intentionally-vulnerable canary fixtures (whose line numbers are keyed
in canary-meta/KEY.md), and pytest --collect-only exits 5 with zero
tests. Exclude canary/ via ruff.toml and add a root-level import smoke
test so collection is non-empty and imports cross_review.py.
This commit is contained in:
Adam Moussa
GitHub
parent
5408649943
commit
58aa07d8be
16 changed files with 226 additions and 371 deletions
144
DEPLOY-R720.md
144
DEPLOY-R720.md
|
|
@ -1,144 +0,0 @@
|
|||
# Phase 3 — Path B deployment (R720 VM)
|
||||
|
||||
Status: **host built; headless runner built + validated; two-tier auto-discovery nightly sweep built.**
|
||||
Pending: provision the read-only `GH_TOKEN` and run one live VM dry-run to validate the clone-mirror path
|
||||
end-to-end. **CI was removed by design** — the git hooks + this nightly sweep are the backstop. See memory
|
||||
`project-security-review-agent`.
|
||||
|
||||
Path B is the unattended backstop that shares one pure-code gate (`review.sh`) with the interactive Path A
|
||||
(`/sh-security-review`). This file is the operator runbook for the box that runs it.
|
||||
|
||||
## Host
|
||||
|
||||
- **Hypervisor:** R720 at `10.10.60.40` (Windows Server 2022, Hyper-V role).
|
||||
- **VM:** `sh-secrev`, always-on Ubuntu 24.04 (kernel 6.8), Gen2, 4GB / 2 vCPU / 40GB dynamic vhdx.
|
||||
- **Reach it:** `ssh -i ~/.ssh/r720_seahaven adam@10.10.60.120` (key-only, NOPASSWD sudo).
|
||||
|
||||
Operate on the VM, not from the Mac against the host by hand.
|
||||
|
||||
## What is installed on the VM
|
||||
|
||||
- **Deterministic scanners:** semgrep, gitleaks, checkov, pip-audit, cfn-lint. **Node 18** (`npm audit`).
|
||||
- **`claude` CLI** (Node) — the subscription-auth path for Path B.
|
||||
- **Python 3.12 venv** at `~/orchestrator/.venv` with `claude-agent-sdk`.
|
||||
- **Repo:** `~/orchestrator/` (rsync from the Mac, `.env` excluded — NOT a git clone). After editing the
|
||||
sweep locally, re-sync: `rsync -av --exclude .env --exclude .venv ~/Documents/repositories/orchestrator/ adam@10.10.60.120:orchestrator/`.
|
||||
- **Testbed corpus:** `~/security-review-testbed` (also rsync'd; includes the Node + .NET fixtures).
|
||||
- **No `gh` CLI required** — discovery uses the GitHub REST API via `curl`. `run_headless.py` is
|
||||
self-contained (detector/verifier prompts are inline), so the VM needs no `~/.claude` assets to run.
|
||||
|
||||
## Auth, billing, and the read-only GitHub token
|
||||
|
||||
### Claude (subscription OAuth)
|
||||
- Token from `claude setup-token`, stored in `~/secrev.env` as `CLAUDE_CODE_OAUTH_TOKEN` (mode 600, NOT in git).
|
||||
- The 2026-06-15 SDK-billing split was **deferred**, so automated SDK usage draws from the Max 20x
|
||||
subscription's normal usage limits — the same pool as interactive Claude Code. The two-tier sweep below
|
||||
is what keeps that draw bounded. See memory `reference-claude-subscription-billing`.
|
||||
- **CRITICAL:** a raw `ANTHROPIC_API_KEY` would silently win and meter to API rates — it must NOT be set on
|
||||
this host. `run_headless.py` pops it defensively and refuses to run without `CLAUDE_CODE_OAUTH_TOKEN`.
|
||||
|
||||
### GitHub (`GH_TOKEN`, read-only — REQUIRED for auto-discovery)
|
||||
The nightly sweep enumerates and clones org repos with a **fine-grained, read-only PAT**. Never give this
|
||||
always-on box a write-capable token.
|
||||
|
||||
1. github.com → Settings → Developer settings → **Fine-grained personal access tokens** → Generate new.
|
||||
2. **Resource owner:** Sea-Haven-Industries. **Repository access:** All repositories.
|
||||
3. **Permissions:** Repository → **Contents: Read-only**, **Metadata: Read-only** (auto). Nothing else.
|
||||
4. Set an expiry (e.g. 90 days; calendar a rotation). Generate and copy the `github_pat_...` value.
|
||||
5. On the VM, append it to `~/secrev.env` and lock the file down:
|
||||
```
|
||||
echo 'GH_TOKEN=github_pat_xxxxxxxx' >> ~/secrev.env && chmod 600 ~/secrev.env
|
||||
```
|
||||
6. Verify (should print repo names, not a 401):
|
||||
```
|
||||
set -a; . ~/secrev.env; set +a
|
||||
curl -fsS -H "Authorization: Bearer $GH_TOKEN" \
|
||||
"https://api.github.com/orgs/Sea-Haven-Industries/repos?per_page=3" | jq '.[].full_name'
|
||||
```
|
||||
|
||||
### Non-Claude provider keys
|
||||
The GPT-4.1 critical tiebreak (optional) uses keys in `~/orchestrator/.env` (mode 600, gitignored,
|
||||
auto-loaded by `run.py`). They bill to their own provider accounts — keep them out of `~/secrev.env`.
|
||||
|
||||
## The headless runner: `run_headless.py`
|
||||
|
||||
Runs the 6 fresh-context detectors + proof-or-kill verifier unattended via the Agent SDK; emits the
|
||||
finding-schema JSON that `review.sh --agent-findings` consumes. Read-only tools, hermetic
|
||||
(`setting_sources=[]`), fails toward over-reporting. CLI:
|
||||
|
||||
```
|
||||
CLAUDE_CODE_OAUTH_TOKEN=... python3 run_headless.py TARGET_DIR \
|
||||
[--scope "src infra web"] [--out findings.json] [--model claude-...] \
|
||||
[--detectors injection,authz,...] [--concurrency 3] [--max-turns 40] \
|
||||
[--detector-budget-usd 2.0] [--total-budget-usd 12.0]
|
||||
```
|
||||
When the total budget is exhausted the verifier is skipped and remaining candidates stay `unverified` —
|
||||
never silently dropped. Manual single-repo run:
|
||||
```
|
||||
cd ~/orchestrator
|
||||
set -a; . ~/secrev.env; set +a
|
||||
.venv/bin/python security-review/run_headless.py ~/security-review-testbed --out /tmp/agent.json
|
||||
security-review/review.sh --agent-findings /tmp/agent.json ~/security-review-testbed
|
||||
```
|
||||
|
||||
## Nightly two-tier, clean-clone auto-discovery sweep
|
||||
|
||||
`nightly_sweep.sh` needs **no per-repo wiring**. Each night it:
|
||||
|
||||
1. **Discovers** every non-archived Sea-Haven-Industries repo via the REST API (`curl` + `GH_TOKEN`) and
|
||||
**mirrors** each as a shallow clean clone (`git clone --depth=1`, default branch from the API
|
||||
`default_branch`) into `~/repo-mirrors`. The token is injected only for the fetch and scrubbed from the
|
||||
on-disk remote afterward. Clean clones contain no developer-local gitignored `.env`, so live secrets
|
||||
stay out of scope by construction.
|
||||
2. **Canary first:** scans `~/security-review-testbed` agentically (anti-complacency) — must block and meet
|
||||
the recall floor, else COMPLACENCY ALARM.
|
||||
3. **Tier 1 (every repo, $0 Claude):** `review.sh --scanners-only` over every mirror.
|
||||
4. **Tier 2 (bounded agentic):** `run_headless.py` over a deterministic round-robin rotation that fits
|
||||
`TOTAL_BUDGET_USD`, with a persistent cycle pointer (`~/sweep-reports/.rotation-state.json`) so every
|
||||
repo gets a deep pass within `MAX_CYCLE_NIGHTS`; a COVERAGE ALARM fires if it falls behind.
|
||||
|
||||
ALARM-only (a clean night posts nothing). Secret-shaped values are redacted from the Slack string; reports
|
||||
under `~/sweep-reports/<UTC-date>/` are mode 600.
|
||||
|
||||
### Config (env / systemd `Environment=`)
|
||||
`GH_ORG` (Sea-Haven-Industries) · `MIRROR_DIR` (~/repo-mirrors) · `TOTAL_BUDGET_USD` (120) ·
|
||||
`PER_TARGET_BUDGET_USD` (12) · `CANARY_FLOOR` (10) · `MAX_CYCLE_NIGHTS` (4) · `MAX_AGENTIC_PER_NIGHT`
|
||||
(0 = unlimited) · `CENTRAL_SKIP_FILE` (~/.secrev-skip.txt) · `ENABLE_XMODEL_HOOK` (0) ·
|
||||
`TARGETS` (manual override — scan explicit paths, no discovery).
|
||||
|
||||
### Skip a repo
|
||||
Commit a `.security-review-skip` at its root, **or** add its name to `~/.secrev-skip.txt`. Marker-skips are
|
||||
logged in the report (a sensitive repo cannot silently self-exclude).
|
||||
|
||||
### Manual dry-run (do this once after provisioning `GH_TOKEN`)
|
||||
```
|
||||
cd ~/orchestrator
|
||||
set -a; . ~/secrev.env; set +a
|
||||
./security-review/nightly_sweep.sh
|
||||
# Watch: discovery count, mirrors, canary block+recall, tier1 over all repos, tier2 rotation, clean exit.
|
||||
# Then re-tune CANARY_FLOOR to the reported recall, and confirm the ALARM path with a forced failure.
|
||||
```
|
||||
|
||||
### Install the timer
|
||||
```
|
||||
sudo cp security-review/systemd/sea-haven-secrev.{service,timer} /etc/systemd/system/
|
||||
sudo systemctl daemon-reload
|
||||
sudo systemctl enable --now sea-haven-secrev.timer # the timer drives it; do not enable the .service
|
||||
systemctl list-timers sea-haven-secrev.timer
|
||||
```
|
||||
Fires nightly ~02:00 local (`Persistent=true` catches missed runs). `TimeoutStartSec=21600` (6h) bounds a
|
||||
hang without killing a healthy long night; spend is capped by `TOTAL_BUDGET_USD`.
|
||||
|
||||
## Anti-complacency reinforcements
|
||||
- **Canary:** the testbed (now Python/IaC/React + Node + .NET planted vulns) is scanned every night; a
|
||||
recall drop or non-block is a COMPLACENCY ALARM.
|
||||
- **Coverage:** the rotation pointer + `MAX_CYCLE_NIGHTS` guarantee every repo gets a deep pass on a cadence,
|
||||
with a COVERAGE ALARM if it slips — no silent incomplete coverage.
|
||||
- **Two-model disagreement (optional):** `ENABLE_XMODEL_HOOK=1` re-checks confirmed criticals with GPT-4.1.
|
||||
|
||||
## Remaining (deferred by design)
|
||||
- **Persistent budget/telemetry ledger:** cross-run spend tracking beyond the per-run + nightly caps (optional).
|
||||
- **Phase 4 roster growth** (compliance/drift sweep, CVE agent, optional auto-fixer) — only per a real job.
|
||||
- **Phase 5 remediation:** harden findings as real repos surface them (payments-dashboard first).
|
||||
- **Confluence:** document `sh-secrev` as standing infrastructure (always-on VM holding a read-only org PAT,
|
||||
pulling all org repos nightly) in the IT host/LAN inventory.
|
||||
99
README.md
99
README.md
|
|
@ -16,16 +16,18 @@ See memory `project-security-review-agent` for the full design.
|
|||
- `skill/sh-security-review.md` — the interactive agentic detector/verifier prompt (Path A, Max-covered).
|
||||
`finding.schema.json` — the structured finding contract both paths emit. `install-hooks.sh --global`
|
||||
links these into `~/.claude/` (this repo is the source of truth).
|
||||
- `run_headless.py` — the Path B headless detector fan-out + proof-or-kill verifier (Claude Agent SDK,
|
||||
subscription OAuth). Self-contained: prompts are inline, so the VM needs no `~/.claude` assets to run it.
|
||||
- `nightly_sweep.sh` + `systemd/` — the unattended two-tier sweep on the `sh-secrev` VM (R720).
|
||||
- `run_headless.py` — the headless detector fan-out + proof-or-kill verifier (Claude Agent SDK,
|
||||
subscription OAuth). Self-contained: prompts are inline, so the host needs no `~/.claude` assets to run it.
|
||||
- `cross_review.py` — the mandatory cross-family GPT-4.1 reviewer CLI (see its section below).
|
||||
- `nightly_sweep.sh` — the retired VM-based two-tier sweep, retained for reference; the automated
|
||||
sweep now runs as Claude Code web cloud routines (see below).
|
||||
|
||||
## Triggers (one script, many entry points)
|
||||
- **On-demand (primary):** run `/sh-security-review` in a Claude Code session (Max-covered), have it
|
||||
write its schema JSON, then `review.sh --agent-findings out.json <repo>` to gate. Required before
|
||||
pushing payments/auth/IaC/input-handling changes (see the global CLAUDE.md security-review rule).
|
||||
- **Pre-commit / pre-push:** the global git hooks run deterministic scanners automatically.
|
||||
- **Nightly:** the VM sweep (Path B) is the unattended backstop.
|
||||
- **Scheduled:** the Claude Code web cloud routines are the unattended backstop (see below).
|
||||
|
||||
### Installing the hooks
|
||||
```
|
||||
|
|
@ -40,6 +42,11 @@ The global mode sets `git config --global core.hooksPath ~/.config/git/hooks`. S
|
|||
its own local `core.hooksPath` overrides the global hook — install per-repo there. See memory
|
||||
`reference_global_security_review_hook`.
|
||||
|
||||
- `--global` also creates the machine-level suppressions dir
|
||||
(`${SH_SECURITY_SUPPRESSIONS_DIR:-~/.config/sea-haven/security-review}`): the per-repo file
|
||||
`<dir>/<repo-basename>/suppressions.json` is preferred by the hooks over repo-local
|
||||
`.security-review/suppressions.json`, and `review.sh` merges both when run without `--suppressions`.
|
||||
|
||||
**Suppressing a false positive.** A written justification is required and is surfaced in the report.
|
||||
When no `--suppressions FILE` is passed, `review.sh` auto-resolves and **merges** suppressions from
|
||||
two locations (an explicit `--suppressions` still overrides both):
|
||||
|
|
@ -50,10 +57,10 @@ two locations (an explicit `--suppressions` still overrides both):
|
|||
2. **Repo-local:** `<repo>/.security-review/suppressions.json` (tracked; travels with the repo).
|
||||
|
||||
Both files' `.suppressions[]` are concatenated (machine-level first, so it wins any id collision).
|
||||
This means every entry point — the pre-push hook, the nightly sweep, on-demand/CI runs, and the
|
||||
This means every entry point — the pre-push hook, the scheduled sweeps, on-demand/CI runs, and the
|
||||
Open SWE daily-report automation — resolves suppressions identically. **Portability note:** hosts that
|
||||
cannot see the Mac's `~/.config` (the Open SWE automation, the R720 VM) get only the tracked repo-local
|
||||
file, so a suppression that must be honored off-Mac has to live repo-local. Fail-safe: if a file is
|
||||
cannot see the Mac's `~/.config` (the Open SWE automation, the cloud routines) get only the tracked
|
||||
repo-local file, so a suppression that must be honored off-Mac has to live repo-local. Fail-safe: if a file is
|
||||
present but unparseable, nothing is suppressed (the gate blocks).
|
||||
|
||||
> **⚠️ Trust model — automated scanners must target TRUSTED repos only.** The repo-local
|
||||
|
|
@ -87,63 +94,33 @@ brew install gitleaks # hardcoded secrets
|
|||
# cfn-lint via pip; Node.js provides npm audit
|
||||
```
|
||||
|
||||
## Scheduled execution — migrating from the VM to Claude Code web routines
|
||||
The unattended runs are moving off the `sh-secrev` VM into **Claude Code web scheduled routines** (which
|
||||
post ALARM-only to Slack `#repo-scanner`): one routine for the agentic two-tier sweep, and a second that
|
||||
runs the deterministic `checker_coordinator.sh` (the script owns the findings + ALARM decision; the
|
||||
routine relays its output verbatim, never re-judging). `nightly_sweep.sh` / `checker_coordinator.sh` and
|
||||
the `systemd/` units below remain the source of truth and the VM-deployment path; the VM timers are being
|
||||
retired once the routines are validated.
|
||||
## Scheduled execution — Claude Code web cloud routines
|
||||
The automated sweep runs as **Claude Code web cloud routines**, both **ALARM-only** to Slack
|
||||
`#repo-scanner` (a clean run posts nothing — see memory `feedback_cloudwatch_alarms`):
|
||||
|
||||
## Nightly sweep (Path B) — two-tier, clean-clone auto-discovery
|
||||
`nightly_sweep.sh` runs on the `sh-secrev` Ubuntu VM (R720) and needs **no per-repo wiring**. It:
|
||||
- **repo-scanner-nightly-sweep** — daily 08:00 ET: the agentic two-tier sweep (deterministic
|
||||
scanners over every repo, plus the bounded agentic detector/verifier rotation).
|
||||
- **repo-checkers-plane1** — daily 07:30 ET: the deterministic `checker_coordinator.sh` (the script
|
||||
owns the findings + ALARM decision; the routine relays its output verbatim, never re-judging).
|
||||
|
||||
1. **Discovers** every non-archived Sea-Haven-Industries repo via the GitHub REST API (`curl` + a
|
||||
read-only `GH_TOKEN`; no `gh` CLI dependency) and **mirrors** each as a shallow clean clone
|
||||
(`git clone --depth=1`, default branch from the API) into `~/repo-mirrors`. Scanning server-side
|
||||
clones — not developer working trees — structurally keeps local gitignored `.env` secrets out of scope.
|
||||
2. **Tier 1 (every repo, every night, $0 Claude):** `review.sh --scanners-only` over every mirror —
|
||||
complete deterministic baseline coverage.
|
||||
3. **Tier 2 (bounded agentic):** `run_headless.py` over a deterministic **round-robin rotation** that
|
||||
fits `TOTAL_BUDGET_USD`, with a persistent cycle pointer so every repo gets a deep pass within
|
||||
`MAX_CYCLE_NIGHTS`. This bounds the draw on the shared Max limits (a clean night never deep-scans all
|
||||
repos). A `COVERAGE ALARM` fires if the rotation falls behind.
|
||||
The VM-based Path B sweep is **retired** (the sweep VM was destroyed); its host artifacts (the
|
||||
`systemd/` units and the `DEPLOY-R720.md` runbook) are deleted — recover them from git history if
|
||||
ever needed. `nightly_sweep.sh` is retained in-repo as the reference implementation of the two-tier
|
||||
design: GitHub REST API auto-discovery into shallow clean clones, Tier 1 `review.sh --scanners-only`
|
||||
over every mirror, Tier 2 bounded agentic `run_headless.py` round-robin rotation, canary
|
||||
anti-complacency floor, budget ceilings, and secret redaction. Its optional `ENABLE_XMODEL_HOOK=1`
|
||||
critical tiebreak now calls this repo's `cross_review.py` (default off). Target scoping stays
|
||||
trusted-repos-only — see `sweep-targets.txt`.
|
||||
|
||||
It is **ALARM-only**: a clean night posts nothing. See memory `feedback_cloudwatch_alarms`.
|
||||
## cross_review.py — mandatory cross-family reviewer
|
||||
The GPT-4.1 cross-family reviewer CLI, re-homed here from the archived orchestrator repo as a
|
||||
router-less direct OpenAI SDK call. It is **mandatory** for IAM/policy and Lambda-handler-signature
|
||||
changes (per the global instructions), and is the reasoning backend for the `sh-plan-review`,
|
||||
`sh-security-audit`, and `sh-build-review` gates.
|
||||
|
||||
### Skip / override
|
||||
- A repo is skipped if it commits a `.security-review-skip` marker **or** is listed in the central skip
|
||||
file (`~/.secrev-skip.txt`, one repo name per line). Repos skipped via their own committed marker are
|
||||
**logged in the report** so a sensitive repo can't silently self-exclude.
|
||||
- `TARGETS="/path/a /path/b"` overrides discovery entirely (scan explicit paths, no cloning).
|
||||
- The canary corpus (`~/security-review-testbed`) is **always** scanned agentically first as the
|
||||
anti-complacency check — independent of the skip filter.
|
||||
|
||||
### Anti-complacency + guards
|
||||
- **Canary check:** the testbed MUST block AND surface ≥ `CANARY_FLOOR` (default 10) confirmed crit/high.
|
||||
Otherwise → COMPLACENCY ALARM. The corpus now includes Node + .NET fixtures (see the testbed key);
|
||||
re-tune the floor after the first VM canary run reports the expanded recall number.
|
||||
- **Budget ceiling:** `TOTAL_BUDGET_USD` (default 120 — full deep-pass coverage of every repo per night) caps aggregate agentic spend; `PER_TARGET_BUDGET_USD`
|
||||
(default 12) caps each repo; `MAX_AGENTIC_PER_NIGHT` (default 0 = unlimited) optionally caps wall-clock.
|
||||
With the SDK-billing split deferred (memory `reference-claude-subscription-billing`), spend draws from
|
||||
the Max subscription limits, so the two-tier design keeps full coverage cheap and bounds the agentic draw.
|
||||
- **Two-model hook (optional, off):** `ENABLE_XMODEL_HOOK=1` re-checks each confirmed CRITICAL with the
|
||||
orchestrator cross-family reviewer (GPT-4.1) and flags disagreement; skips gracefully, never fails the sweep.
|
||||
- **Redaction:** secret-shaped values are masked in the Slack ALARM string; on-disk reports are mode 600.
|
||||
|
||||
### Secrets / env (`~/secrev.env`, mode 600)
|
||||
- `CLAUDE_CODE_OAUTH_TOKEN` — required (`run_headless.py` pops `ANTHROPIC_API_KEY`).
|
||||
- `GH_TOKEN` — **read-only fine-grained PAT** scoped to the org (Contents + Metadata: read-only, nothing
|
||||
else) for discovery + cloning. Never give this unattended box a write-capable token.
|
||||
- `SLACK_WEBHOOK_URL` — alarms (plain incoming-webhook). `~/orchestrator/.env` → `OPENAI_API_KEY` (xmodel hook only).
|
||||
- Reports + per-target JSON land under `~/sweep-reports/<UTC-date>/`.
|
||||
|
||||
### Install the timer
|
||||
Units are in `systemd/`; full runbook is `DEPLOY-R720.md`. On the VM:
|
||||
```
|
||||
sudo cp systemd/sea-haven-secrev.{service,timer} /etc/systemd/system/
|
||||
sudo systemctl daemon-reload
|
||||
sudo systemctl enable --now sea-haven-secrev.timer # the timer drives it; do not enable the .service
|
||||
sudo systemctl start sea-haven-secrev.service # optional one-off smoke test
|
||||
python3 ~/Documents/repositories/seahaven/security-review/cross_review.py "<task>"
|
||||
```
|
||||
The timer fires nightly at ~02:00 local (`Persistent=true` catches missed runs after downtime).
|
||||
|
||||
Setup: `OPENAI_API_KEY` in the environment or in the repo-root `.env` (gitignored — never commit
|
||||
it); `pip install -r requirements.txt` provides the `openai` SDK.
|
||||
|
|
|
|||
139
cross_review.py
Executable file
139
cross_review.py
Executable file
|
|
@ -0,0 +1,139 @@
|
|||
#!/usr/bin/env python3
|
||||
"""cross_review.py — Sea Haven cross-family (GPT-4.1) review CLI.
|
||||
|
||||
Re-homed from the archived Sea-Haven-Industries/orchestrator repo's
|
||||
`cross_reviewer` agent. Router-less: one direct OpenAI SDK call, no langchain,
|
||||
no routing logic. This is the mandatory cross-family reviewer for IAM/policy
|
||||
and Lambda-handler-signature changes, and the reasoning backend for the
|
||||
sh-plan-review / sh-security-audit / sh-build-review gates.
|
||||
|
||||
Usage:
|
||||
python3 cross_review.py "Review this diff for breaking changes: <diff>"
|
||||
|
||||
Auth: reads OPENAI_API_KEY from the environment, falling back to the
|
||||
gitignored .env at the repo root. Never prints the key.
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import os
|
||||
import random
|
||||
import sys
|
||||
import time
|
||||
|
||||
# Model ID — single source of truth (ported from orchestrator/models.py).
|
||||
DEFAULT_MODEL = "gpt-4.1"
|
||||
TEMPERATURE = 0.2
|
||||
MAX_ATTEMPTS = 3
|
||||
|
||||
# System prompt ported verbatim from the orchestrator's cross_reviewer agent
|
||||
# (orchestrator/agents.py, CROSS_REVIEWER_PROMPT).
|
||||
CROSS_REVIEWER_PROMPT = """You are a cross-family code review agent. You provide an independent review perspective.
|
||||
Review the provided code for bugs, security issues, and improvements.
|
||||
Categorize findings as BLOCK, FIX, or NIT. Be concise.
|
||||
Focus on issues that might be missed by the primary development team."""
|
||||
|
||||
|
||||
def load_api_key() -> str:
|
||||
"""OPENAI_API_KEY from the environment, else hand-parsed from repo-root .env."""
|
||||
key = os.environ.get("OPENAI_API_KEY")
|
||||
if key:
|
||||
return key
|
||||
env_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), ".env")
|
||||
try:
|
||||
with open(env_path, encoding="utf-8") as f:
|
||||
for line in f:
|
||||
line = line.strip()
|
||||
if not line or line.startswith("#") or "=" not in line:
|
||||
continue
|
||||
name, _, value = line.partition("=")
|
||||
if name.strip() == "OPENAI_API_KEY":
|
||||
return value.strip().strip("'\"")
|
||||
except OSError:
|
||||
pass
|
||||
return ""
|
||||
|
||||
|
||||
def run_review(task: str, model: str, api_key: str) -> str:
|
||||
"""One review call with retries on transient API errors (3 attempts,
|
||||
exponential backoff with jitter — ported from orchestrator/models.py
|
||||
with_retries)."""
|
||||
# Lazy import so --help works without the openai package installed.
|
||||
import openai
|
||||
|
||||
retriable = (
|
||||
openai.APIConnectionError,
|
||||
openai.RateLimitError,
|
||||
openai.InternalServerError,
|
||||
)
|
||||
client = openai.OpenAI(api_key=api_key)
|
||||
for attempt in range(1, MAX_ATTEMPTS + 1):
|
||||
try:
|
||||
response = client.chat.completions.create(
|
||||
model=model,
|
||||
temperature=TEMPERATURE,
|
||||
messages=[
|
||||
{"role": "system", "content": CROSS_REVIEWER_PROMPT},
|
||||
{"role": "user", "content": task},
|
||||
],
|
||||
)
|
||||
content = response.choices[0].message.content
|
||||
if not content:
|
||||
raise RuntimeError("model returned an empty review")
|
||||
return content
|
||||
except retriable as exc:
|
||||
if attempt == MAX_ATTEMPTS:
|
||||
raise
|
||||
delay = (2 ** (attempt - 1)) + random.uniform(0, 1)
|
||||
print(
|
||||
f"cross_review: transient API error ({type(exc).__name__}), "
|
||||
f"retrying in {delay:.1f}s (attempt {attempt}/{MAX_ATTEMPTS})",
|
||||
file=sys.stderr,
|
||||
)
|
||||
time.sleep(delay)
|
||||
raise RuntimeError("unreachable")
|
||||
|
||||
|
||||
def main() -> int:
|
||||
parser = argparse.ArgumentParser(
|
||||
description=(
|
||||
"Cross-family GPT-4.1 review (direct OpenAI SDK, no router). "
|
||||
"Mandatory for IAM/policy and Lambda-handler-signature changes."
|
||||
)
|
||||
)
|
||||
parser.add_argument("task", help="review task: a diff, change description, or plan")
|
||||
parser.add_argument(
|
||||
"--model",
|
||||
default=DEFAULT_MODEL,
|
||||
help=f"OpenAI model id (default: {DEFAULT_MODEL})",
|
||||
)
|
||||
args = parser.parse_args()
|
||||
|
||||
api_key = load_api_key()
|
||||
if not api_key:
|
||||
print(
|
||||
"cross_review: OPENAI_API_KEY not set and not found in repo-root .env",
|
||||
file=sys.stderr,
|
||||
)
|
||||
return 2
|
||||
|
||||
try:
|
||||
review = run_review(args.task, args.model, api_key)
|
||||
except ImportError:
|
||||
print(
|
||||
"cross_review: the 'openai' package is not installed "
|
||||
"(pip install -r requirements.txt)",
|
||||
file=sys.stderr,
|
||||
)
|
||||
return 2
|
||||
except Exception as exc: # noqa: BLE001 — CLI boundary: report and exit nonzero
|
||||
print(
|
||||
f"cross_review: review failed: {type(exc).__name__}: {exc}", file=sys.stderr
|
||||
)
|
||||
return 1
|
||||
|
||||
print(review)
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
|
|
@ -177,6 +177,6 @@ snapshot-restore away from gone.
|
|||
## Process note
|
||||
|
||||
Per global instructions this IAM change ALSO requires the GPT-4.1 cross-family review run via
|
||||
`python3 ~/Documents/repositories/orchestrator/run.py "<diff/describe>"` (it is an IAM
|
||||
`python3 ~/Documents/repositories/seahaven/security-review/cross_review.py "<task>"` (it is an IAM
|
||||
role/policy + trust-anchor change). This packet is the input to that review; aws-posture is not
|
||||
built until the review is recorded.
|
||||
|
|
|
|||
|
|
@ -27,4 +27,5 @@ box**.
|
|||
| `step-ca-config-sketch.md` | Internal CA config + systemd-timer auto-renewal of the short-lived leaf. |
|
||||
|
||||
Per global instructions this IAM change also requires the GPT-4.1 cross-family review via
|
||||
`orchestrator/run.py`; this directory is that review's input.
|
||||
`python3 ~/Documents/repositories/seahaven/security-review/cross_review.py "<task>"`; this
|
||||
directory is that review's input.
|
||||
|
|
|
|||
|
|
@ -18,6 +18,7 @@ set -euo pipefail
|
|||
SRC="$(cd "$(dirname "$0")" && pwd)"
|
||||
GLOBAL_HOOKS="$HOME/.config/git/hooks"
|
||||
CLAUDE_DIR="$HOME/.claude"
|
||||
SUP_DIR="${SH_SECURITY_SUPPRESSIONS_DIR:-$HOME/.config/sea-haven/security-review}"
|
||||
|
||||
usage() { grep '^#' "$0" | sed 's/^# \{0,1\}//'; }
|
||||
|
||||
|
|
@ -40,6 +41,9 @@ case "${1:-}" in
|
|||
--global)
|
||||
echo "== Installing Sea Haven security-review hooks globally =="
|
||||
mkdir -p "$GLOBAL_HOOKS"
|
||||
mkdir -p "$SUP_DIR"
|
||||
echo " suppressions: machine-level per-repo file $SUP_DIR/<repo-basename>/suppressions.json is preferred by the hooks over repo-local .security-review/suppressions.json"
|
||||
echo " suppressions: review.sh merges both locations when run without --suppressions"
|
||||
|
||||
# Warn (don't clobber silently) if a different global hooksPath is already set.
|
||||
CURRENT="$(git config --global --get core.hooksPath || true)"
|
||||
|
|
|
|||
|
|
@ -1,5 +1,9 @@
|
|||
#!/usr/bin/env bash
|
||||
# nightly_sweep.sh — Sea Haven Path B nightly security sweep (R720 / sh-secrev VM).
|
||||
# nightly_sweep.sh — Sea Haven nightly security sweep (RETIRED — retained for reference).
|
||||
#
|
||||
# The VM-based Path B sweep is retired (the sweep VM was destroyed); the automated
|
||||
# sweep now runs as Claude Code web cloud routines (see README.md). This script is
|
||||
# kept as the reference implementation of the two-tier sweep design.
|
||||
#
|
||||
# TWO-TIER, CLEAN-CLONE AUTO-DISCOVERY (no per-repo wiring):
|
||||
# Discovery: enumerate ALL Sea-Haven-Industries org repos via the GitHub REST API
|
||||
|
|
@ -27,7 +31,7 @@
|
|||
#
|
||||
# Contract notes:
|
||||
# - run_headless.py REQUIRES CLAUDE_CODE_OAUTH_TOKEN and pops ANTHROPIC_API_KEY.
|
||||
# Source ~/secrev.env before invoking (the systemd unit does this via EnvironmentFile).
|
||||
# Source the sweep env file before invoking.
|
||||
# - review.sh re-derives the block decision (exit 1 = BLOCK). This script makes NO
|
||||
# block decision itself; it only reports.
|
||||
#
|
||||
|
|
@ -48,9 +52,9 @@
|
|||
# (default: 0 = unlimited, bounded only by TOTAL_BUDGET_USD)
|
||||
# REPORT_ROOT base dir for logs+JSON (default: ~/sweep-reports)
|
||||
# SLACK_WEBHOOK_URL incoming-webhook URL; if unset, alarms are logged only
|
||||
# ENABLE_XMODEL_HOOK 1 to run the cross-family critical tiebreak (default: 0)
|
||||
# ORCHESTRATOR_DIR orchestrator repo root (default: ~/orchestrator)
|
||||
# VENV_PY python in the SDK venv (default: ~/orchestrator/.venv/bin/python)
|
||||
# ENABLE_XMODEL_HOOK 1 to run the cross-family critical tiebreak via this repo's
|
||||
# cross_review.py (default: 0)
|
||||
# VENV_PY python interpreter (default: python3 on PATH)
|
||||
#
|
||||
# Exit: 0 = sweep completed (whether or not it alarmed); 2 = setup/usage error.
|
||||
set -euo pipefail
|
||||
|
|
@ -60,16 +64,16 @@ log() { echo "[nightly_sweep] $*" >&2; }
|
|||
die() { echo "[nightly_sweep] FATAL: $*" >&2; exit 2; }
|
||||
|
||||
# --- Shared substrate (discovery / mirror / budget / rotation / Slack / canary) -
|
||||
# Factored out so secrev and the R720 agent-team reuse one implementation, WITHOUT
|
||||
# changing any secrev behavior. The functions close over this script's globals by name
|
||||
# Factored out so the sweep and the checker coordinator reuse one implementation, WITHOUT
|
||||
# changing any sweep behavior. The functions close over this script's globals by name
|
||||
# (bash dynamic scoping); see lib/sweep_substrate.sh for the read/mutate contract.
|
||||
HERE="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
# shellcheck source=lib/sweep_substrate.sh
|
||||
. "$HERE/lib/sweep_substrate.sh"
|
||||
|
||||
# --- Config + defaults --------------------------------------------------------
|
||||
ORCHESTRATOR_DIR="${ORCHESTRATOR_DIR:-$HOME/orchestrator}"
|
||||
VENV_PY="${VENV_PY:-$ORCHESTRATOR_DIR/.venv/bin/python}"
|
||||
VENV_PY="${VENV_PY:-$(command -v python3)}"
|
||||
CROSS_REVIEW="$HERE/cross_review.py"
|
||||
RUN_HEADLESS="$HERE/run_headless.py"
|
||||
REVIEW_SH="$HERE/review.sh"
|
||||
GH_ORG="${GH_ORG:-Sea-Haven-Industries}"
|
||||
|
|
@ -90,7 +94,7 @@ command -v git >/dev/null || die "git is required"
|
|||
[ -x "$VENV_PY" ] || die "venv python not found/executable: $VENV_PY"
|
||||
[ -f "$RUN_HEADLESS" ] || die "run_headless.py not found: $RUN_HEADLESS"
|
||||
[ -x "$REVIEW_SH" ] || die "review.sh not found/executable: $REVIEW_SH"
|
||||
[ -n "${CLAUDE_CODE_OAUTH_TOKEN:-}" ] || die "CLAUDE_CODE_OAUTH_TOKEN not set (source ~/secrev.env)"
|
||||
[ -n "${CLAUDE_CODE_OAUTH_TOKEN:-}" ] || die "CLAUDE_CODE_OAUTH_TOKEN not set (source the sweep env file)"
|
||||
|
||||
UTC_DATE="$(date -u +%Y-%m-%d)"
|
||||
UTC_STAMP="$(date -u +%Y-%m-%dT%H:%M:%SZ)"
|
||||
|
|
@ -129,8 +133,8 @@ skip_reason() { # name dir
|
|||
xmodel_check_criticals() {
|
||||
local label="$1" result_json="$2"
|
||||
[ "$ENABLE_XMODEL_HOOK" = "1" ] || return 0
|
||||
[ -n "${OPENAI_API_KEY:-}" ] || { log " xmodel hook: OPENAI_API_KEY unset — skipping"; return 0; }
|
||||
"$VENV_PY" -c 'import langchain_openai' >/dev/null 2>&1 || { log " xmodel hook: deps missing — skipping"; return 0; }
|
||||
[ -f "$CROSS_REVIEW" ] || { log " xmodel hook: cross_review.py missing — skipping"; return 0; }
|
||||
"$VENV_PY" -c 'import openai' >/dev/null 2>&1 || { log " xmodel hook: openai package missing — skipping"; return 0; }
|
||||
local crits n; crits="$(jq -c '[.findings[]? | select(.status=="confirmed" and .severity=="critical")]' "$result_json" 2>/dev/null || echo '[]')"
|
||||
n="$(echo "$crits" | jq 'length')"; [ "${n:-0}" -gt 0 ] || return 0
|
||||
log " xmodel hook: re-checking $n confirmed critical(s) for $label"
|
||||
|
|
@ -138,11 +142,11 @@ xmodel_check_criticals() {
|
|||
while [ "$i" -lt "$n" ]; do
|
||||
local summary; summary="$(echo "$crits" | jq -r --argjson i "$i" '.[$i] | "\(.cwe // "n/a") \(.file):\(.line // 0) — \(.title // .id) :: \(.data_flow // "")"')"
|
||||
local verdict
|
||||
if verdict="$(cd "$ORCHESTRATOR_DIR" && "$VENV_PY" run.py "Independently assess whether this is a real exploitable vulnerability (yes/no) and why: $summary" 2>>"$REPORT_DIR/xmodel.log")"; then
|
||||
if verdict="$("$VENV_PY" "$CROSS_REVIEW" "Independently assess whether this is a real exploitable vulnerability (yes/no) and why: $summary" 2>>"$REPORT_DIR/xmodel.log")"; then
|
||||
if echo "$verdict" | grep -qiE '(^|[^a-z])no([^a-z]|$)|not (a |an )?(real |exploitable )?vuln'; then
|
||||
XMODEL_LINES+=( "DISAGREEMENT on $label critical: $summary (cross_reviewer says NOT a vuln)" )
|
||||
fi
|
||||
else log " xmodel hook: run.py failed for a critical (logged) — continuing"; fi
|
||||
else log " xmodel hook: cross_review.py failed for a critical (logged) — continuing"; fi
|
||||
i=$((i+1))
|
||||
done
|
||||
}
|
||||
|
|
@ -350,7 +354,7 @@ $ALARM_BODY
|
|||
|
||||
Coverage: tier1 scanners ${#SCANNABLE[@]} repos · tier2 agentic $AGENTIC_DONE this night ($REMAINING pending) · canary_ok=$CANARY_OK
|
||||
Spend: \$$TOTAL_SPEND (ceiling \$$TOTAL_BUDGET_USD)
|
||||
Reports + JSON: \`$REPORT_DIR\` (on sh-secrev VM)"
|
||||
Reports + JSON: \`$REPORT_DIR\`"
|
||||
SLACK_TEXT="$(echo "$SLACK_TEXT" | redact)"
|
||||
|
||||
log "ALARM conditions present — composing Slack post"
|
||||
|
|
|
|||
|
|
@ -1,5 +1,6 @@
|
|||
# Path B headless agentic runner (run_headless.py). Scanners (semgrep, gitleaks,
|
||||
# Headless agentic runner (run_headless.py). Scanners (semgrep, gitleaks,
|
||||
# checkov, cfn-lint, pip-audit) and npm are external binaries, installed separately
|
||||
# (see README). The optional cross-model hook (ENABLE_XMODEL_HOOK=1) additionally
|
||||
# needs langchain-openai, intentionally not pinned here since it is off by default.
|
||||
# (see README).
|
||||
claude-agent-sdk
|
||||
# Cross-family reviewer CLI (cross_review.py) — direct OpenAI SDK, no langchain.
|
||||
openai
|
||||
|
|
|
|||
4
ruff.toml
Normal file
4
ruff.toml
Normal file
|
|
@ -0,0 +1,4 @@
|
|||
# canary/ is the intentionally-vulnerable scanner-recall corpus: it must stay
|
||||
# byte-stable (canary-meta/KEY.md keys findings to its line numbers) and linting
|
||||
# deliberately-bad code is meaningless, so ruff skips it entirely.
|
||||
extend-exclude = ["canary"]
|
||||
|
|
@ -83,7 +83,7 @@ with file:line, the numbered data-flow trace, and the proof. List unverified and
|
|||
nothing is silently dropped. The reader reviews proofs, not raw code.
|
||||
|
||||
## Relationship to existing tooling
|
||||
- `sh-build-review` — single deep Fable pass over a change surface (depth, one reasoner).
|
||||
- `sh-build-review` — single deep cross-family pass (GPT-4.1 via `cross_review.py` in this repo) over a change surface (depth, one out-of-family reasoner).
|
||||
- `sh-security-review` — high-recall fan-out + proof-or-kill verifier (breadth + anti-complacency).
|
||||
- IAM/policy and Lambda-signature changes still require the mandatory cross-family review per global instructions; this does not replace it.
|
||||
|
||||
|
|
|
|||
|
|
@ -19,8 +19,5 @@
|
|||
# TODO (Phase 5): add the first real hardened repo here once it is cloned on the
|
||||
# VM (candidates: payments-dashboard / proposal-system / procurement-ingest).
|
||||
#
|
||||
# Deliberately EMPTY by default = canary-only nights. Do NOT scan ~/orchestrator:
|
||||
# it holds ~/orchestrator/.env with live provider API keys, which the agentic
|
||||
# detector could surface into sweep reports / Slack. Only add repos with no
|
||||
# Deliberately EMPTY by default = canary-only nights. Only add repos with no
|
||||
# plaintext secrets (or scrub/exclude secret files first).
|
||||
# ~/orchestrator
|
||||
|
|
|
|||
|
|
@ -1,52 +0,0 @@
|
|||
# sea-haven-checkers.service — Plane-1 nightly checker coordinator (sh-secrev VM, user adam).
|
||||
#
|
||||
# Runs security-review/checker_coordinator.sh: the read-only Plane-1 checkers
|
||||
# (compliance-drift, dependency-cve, doc-drift, plan-groomer) under ONE shared
|
||||
# budget ledger + versioned rotation/coverage, ALARM-only to Slack. Reuses the
|
||||
# secrev sweep's substrate ($MIRROR_DIR clones, budget discipline) — no re-clone.
|
||||
#
|
||||
# Install (on the VM, as root):
|
||||
# sudo cp sea-haven-checkers.service /etc/systemd/system/
|
||||
# sudo cp sea-haven-checkers.timer /etc/systemd/system/
|
||||
# sudo systemctl daemon-reload
|
||||
# sudo systemctl enable --now sea-haven-checkers.timer # the timer drives it
|
||||
# systemctl list-timers sea-haven-checkers.timer
|
||||
#
|
||||
# Secrets/config come from the EnvironmentFiles (leading '-' = optional):
|
||||
# ~/secrev.env -> CLAUDE_CODE_OAUTH_TOKEN, GH_TOKEN, SLACK_WEBHOOK_URL
|
||||
# ~/orchestrator/.env -> OPENAI/etc. (only if a checker shells the cross-model run.py)
|
||||
#
|
||||
# COORDINATOR_SKIP_ROLES excludes roles whose creds are NOT provisioned:
|
||||
# - aws-posture needs IAM Roles Anywhere / step-ca (not provisioned)
|
||||
# confluence-doc is ONLINE (2026-06-22): authenticates via the OAuth 2.0
|
||||
# client-credentials service account in ~/secrev.env (CONFLUENCE_BASE_URL +
|
||||
# CONFLUENCE_OAUTH_CLIENT_ID/_SECRET); PAGE_MAP_FILE points at the IT page-ID map
|
||||
# generated from the live space. Remove a name from the skip list once its
|
||||
# credential is provisioned to bring that checker online.
|
||||
|
||||
[Unit]
|
||||
Description=Sea Haven agent-team Plane-1 nightly checker coordinator
|
||||
After=network-online.target
|
||||
Wants=network-online.target
|
||||
|
||||
[Service]
|
||||
Type=oneshot
|
||||
User=adam
|
||||
WorkingDirectory=/home/adam/orchestrator/security-review
|
||||
EnvironmentFile=-/home/adam/secrev.env
|
||||
EnvironmentFile=-/home/adam/orchestrator/.env
|
||||
Environment=GH_ORG=Sea-Haven-Industries
|
||||
Environment=COORDINATOR_SKIP_ROLES=aws-posture
|
||||
# IT page-ID map for confluence-doc (generated from the live space; regenerate
|
||||
# periodically as pages change).
|
||||
Environment=PAGE_MAP_FILE=/home/adam/confluence-page-map.json
|
||||
# Tune the shared ceiling without editing the script (uncomment to override):
|
||||
# Environment=TOTAL_BUDGET_USD=120
|
||||
# Environment=MAX_CYCLE_NIGHTS=4
|
||||
ExecStart=/home/adam/orchestrator/security-review/checker_coordinator.sh
|
||||
# Bounded so a hung checker cannot run forever; spend is capped by TOTAL_BUDGET_USD.
|
||||
TimeoutStartSec=10800
|
||||
Nice=10
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
|
|
@ -1,20 +0,0 @@
|
|||
# sea-haven-checkers.timer — fires the Plane-1 checker coordinator nightly.
|
||||
#
|
||||
# 03:30 UTC — ~90 min after the sea-haven-secrev sweep (02:00) so the two do not
|
||||
# contend on $MIRROR_DIR or the shared Claude subscription pool at the same instant.
|
||||
# Persistent=true → if the VM was off, it runs at next boot. RandomizedDelaySec
|
||||
# spreads load off an exact-minute spike.
|
||||
#
|
||||
# Install: see the header of sea-haven-checkers.service.
|
||||
|
||||
[Unit]
|
||||
Description=Run the Sea Haven Plane-1 checker coordinator nightly (~03:30 UTC)
|
||||
|
||||
[Timer]
|
||||
OnCalendar=*-*-* 03:30:00
|
||||
Persistent=true
|
||||
RandomizedDelaySec=600
|
||||
Unit=sea-haven-checkers.service
|
||||
|
||||
[Install]
|
||||
WantedBy=timers.target
|
||||
|
|
@ -1,49 +0,0 @@
|
|||
# sea-haven-secrev.service — Path B nightly security sweep (sh-secrev VM, user adam).
|
||||
#
|
||||
# Install (on the VM, as root):
|
||||
# sudo cp sea-haven-secrev.service /etc/systemd/system/
|
||||
# sudo cp sea-haven-secrev.timer /etc/systemd/system/
|
||||
# sudo systemctl daemon-reload
|
||||
# sudo systemctl enable --now sea-haven-secrev.timer # timer drives the run; do NOT enable the .service
|
||||
# systemctl list-timers sea-haven-secrev.timer # confirm next run
|
||||
# sudo systemctl start sea-haven-secrev.service # optional: run once now to smoke-test
|
||||
# journalctl -u sea-haven-secrev.service -e # logs (also under ~/sweep-reports/<date>/)
|
||||
#
|
||||
# Secrets come from the EnvironmentFiles (the leading '-' = optional, no failure if absent):
|
||||
# ~/secrev.env -> CLAUDE_CODE_OAUTH_TOKEN (required by run_headless.py),
|
||||
# GH_TOKEN (read-only fine-grained PAT — REQUIRED for org auto-discovery),
|
||||
# SLACK_WEBHOOK_URL
|
||||
# ~/orchestrator/.env -> OPENAI_API_KEY etc. (only needed if ENABLE_XMODEL_HOOK=1)
|
||||
#
|
||||
# GH_TOKEN must be a fine-grained PAT scoped to the Sea-Haven-Industries org with READ-ONLY
|
||||
# Contents (and Metadata) permission — nothing else. It enumerates repos and clones them into
|
||||
# ~/repo-mirrors. Never give this unattended box a write-capable token.
|
||||
|
||||
[Unit]
|
||||
Description=Sea Haven Path B nightly security sweep
|
||||
After=network-online.target
|
||||
Wants=network-online.target
|
||||
|
||||
[Service]
|
||||
Type=oneshot
|
||||
User=adam
|
||||
WorkingDirectory=/home/adam/orchestrator
|
||||
EnvironmentFile=-/home/adam/secrev.env
|
||||
EnvironmentFile=-/home/adam/orchestrator/.env
|
||||
# Tune ceilings/targets here without editing the script (uncomment to override defaults):
|
||||
# Environment=TOTAL_BUDGET_USD=120
|
||||
# Environment=PER_TARGET_BUDGET_USD=12
|
||||
# Environment=CANARY_FLOOR=10
|
||||
# Environment=MAX_CYCLE_NIGHTS=4
|
||||
# Environment=MAX_AGENTIC_PER_NIGHT=0
|
||||
# Environment=GH_ORG=Sea-Haven-Industries
|
||||
# Environment=MIRROR_DIR=/home/adam/repo-mirrors
|
||||
# Environment=ENABLE_XMODEL_HOOK=0
|
||||
ExecStart=/home/adam/orchestrator/security-review/nightly_sweep.sh
|
||||
# Two-tier sweep (scanners over every repo + a budget-bounded agentic rotation) runs for hours;
|
||||
# 6h ceiling bounds a hang without killing a healthy long night. Spend is capped by TOTAL_BUDGET_USD.
|
||||
TimeoutStartSec=21600
|
||||
Nice=10
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
|
|
@ -1,20 +0,0 @@
|
|||
# sea-haven-secrev.timer — fires the nightly sweep at ~02:00 local, user adam.
|
||||
#
|
||||
# Install: see the header of sea-haven-secrev.service. In short:
|
||||
# sudo systemctl enable --now sea-haven-secrev.timer
|
||||
# systemctl list-timers sea-haven-secrev.timer
|
||||
#
|
||||
# Persistent=true → if the VM was off at 02:00, the sweep runs at next boot.
|
||||
# RandomizedDelaySec spreads load off an exact-minute spike.
|
||||
|
||||
[Unit]
|
||||
Description=Run the Sea Haven Path B security sweep nightly (~02:00)
|
||||
|
||||
[Timer]
|
||||
OnCalendar=*-*-* 02:00:00
|
||||
Persistent=true
|
||||
RandomizedDelaySec=600
|
||||
Unit=sea-haven-secrev.service
|
||||
|
||||
[Install]
|
||||
WantedBy=timers.target
|
||||
13
test_imports.py
Normal file
13
test_imports.py
Normal file
|
|
@ -0,0 +1,13 @@
|
|||
"""Import smoke test.
|
||||
|
||||
CI runs `pytest --collect-only` as an import check; collection imports this
|
||||
module, which imports the repo's Python entry points. No API calls are made
|
||||
(cross_review imports the openai SDK lazily, inside the call path).
|
||||
"""
|
||||
|
||||
import cross_review
|
||||
|
||||
|
||||
def test_cross_review_importable():
|
||||
assert cross_review.DEFAULT_MODEL == "gpt-4.1"
|
||||
assert "BLOCK" in cross_review.CROSS_REVIEWER_PROMPT
|
||||
Loading…
Add table
Reference in a new issue