Files
oikos/internal/policy/command.go
dtoro 657e1a8be1
Some checks failed
ci / build-test (push) Has been cancelled
ci / docker-build (push) Has been cancelled
feat: assent window + compound read-only classification + continue-after-approval
Agent stopped after every approval step, forcing operator to type
'continue' 7× per deploy session. Root causes and fixes:

1. Compound read-only commands (e.g. 'systemctl status; journalctl')
   defaulted to config_mutation — now splits on ;/&&/||/| and classifies
   as read_only if all segments are inspection verbs. Added grep, wc,
   sort, uniq, cut, tr, dpkg -l, apt list, docker stats to allowlist.

2. curl|sh was classified destructive, forcing typed confirmation for
   legitimate installs (get.docker.com). Demoted to config_mutation —
   loose assent grants it, no typed phrase needed.

3. SOUL.md said 'STOP after queuing' — replaced with 'continue working
   on non-blocked steps'. Added assent window section instructing agent
   to carry out the full plan after approval.

4. Assent window: when operator approves a plan via chat assent, a
   30-minute window opens where config_mutation commands auto-run
   without re-approval. Agent writes expiry to autonomy_settings; MCP
   run tool checks it before gating. Destructive never auto-runs.

5. System note after approval now says 'CONTINUE executing the full
   plan — do not stop and wait for continue.'
2026-07-10 13:10:57 +02:00

172 lines
7.0 KiB
Go

package policy
import (
"regexp"
"strings"
)
// Risk class names, in escalation order (index = severity). A command's final
// risk class is the MAX of what the rules compute and what the caller
// declared — classification can only escalate, never de-escalate, mirroring
// the signal classifier's "policy can only lower autonomy, never raise it."
const (
RiskReadOnly = "read_only"
RiskReversibleLow = "reversible_low"
RiskConfigMutation = "config_mutation"
RiskDestructive = "destructive"
)
var riskOrder = map[string]int{
RiskReadOnly: 0,
RiskReversibleLow: 1,
RiskConfigMutation: 2,
RiskDestructive: 3,
}
func riskRank(r string) int {
if n, ok := riskOrder[r]; ok {
return n
}
return riskOrder[RiskConfigMutation] // unknown declared risk: assume the safer-to-gate default
}
// destructivePatterns match commands that must always be treated as
// destructive, regardless of what the caller declares. Irreversible,
// data-loss, or fleet-wide-impact operations. Matched against the raw
// command text, case-insensitive.
var destructivePatterns = []*regexp.Regexp{
regexp.MustCompile(`(?i)\brm\s+.*-[a-zA-Z]*r[a-zA-Z]*f|\brm\s+.*-[a-zA-Z]*f[a-zA-Z]*r`), // rm -rf / rm -fr (any flag order)
regexp.MustCompile(`(?i)\bdd\s+.*of=`),
regexp.MustCompile(`(?i)\bmkfs(\.\w+)?\b`),
regexp.MustCompile(`(?i)\bwipefs\b`),
regexp.MustCompile(`(?i)\bshred\b`),
regexp.MustCompile(`(?i)\bpct\s+destroy\b`),
regexp.MustCompile(`(?i)\bqm\s+destroy\b`),
regexp.MustCompile(`(?i)\bzpool\s+destroy\b`),
regexp.MustCompile(`(?i)\blvremove\b|\bvgremove\b|\bpvremove\b`),
regexp.MustCompile(`(?i)\bdrop\s+(table|database|schema)\b`),
regexp.MustCompile(`(?i)\btruncate\s+table\b`),
regexp.MustCompile(`(?i)>\s*/dev/(sd|nvme|vd|hd)`),
regexp.MustCompile(`(?i)\bshutdown\b|\breboot\b|\bhalt\b|\bpoweroff\b`),
regexp.MustCompile(`(?i)\bformat\b.*\b(disk|partition|volume)\b`),
regexp.MustCompile(`:\(\)\s*\{.*:\|:.*\}\s*;\s*:`), // fork bomb
regexp.MustCompile(`(?i)\bchmod\s+-R\s+000\b|\bchmod\s+000\s+/`),
regexp.MustCompile(`(?i)\biptables\s+-F\b|\bufw\s+disable\b`), // wipes firewall
// secret/credential exfiltration — reading private keys, shadow, or age
// keys is always destructive. (Piping a remote script into a shell via
// curl|sh was previously here too, but that pattern is common for
// legitimate installs — get.docker.com, convenience scripts — and
// demoting it to config_mutation means loose assent can grant it without
// a typed confirmation. The assent window covers the deploy case.)
regexp.MustCompile(`(?i)\bcat\s+.*(id_rsa|id_ed25519|\.pem|shadow|\.age)\b`),
}
// readOnlyLeadPattern matches the leading command word (after env-var
// prefixes and a leading sudo) against a small allowlist of verbs that are
// safe to auto-run unattended: they inspect state and cannot mutate it.
// Compound commands (&&, ;, |, $(), backticks) are excluded from this fast
// path below — only a single simple command can qualify.
var readOnlyLeadPattern = regexp.MustCompile(
`^(cat|less|head|tail|ls|stat|file|du|df|free|uptime|uname|hostname|whoami|id|ip|ss|netstat|ping|` +
`journalctl|dmesg|ps|top|htop|env|printenv|echo|which|whereis|` +
`grep|egrep|fgrep|rg|wc|sort|uniq|cut|tr|tee|` +
`dpkg\s+(-l|-s|--list|--status)\b|apt\s+(list|search|show)\b|` +
`systemctl\s+(status|is-active|is-enabled|is-failed|list-units)|` +
`docker\s+(ps|images|inspect|logs|version|info|stats)|` +
`pct\s+(status|config|list)|qm\s+(status|config|list)|pvesh\s+get|` +
`git\s+(status|log|diff|show|branch|remote)|` +
`curl\s+-.*-I\b|curl\s+.*--head\b)\b`)
// compoundSplitRe splits a command on shell chaining operators (;, &&, ||, |)
// so each segment can be individually classified. A piped or chained command
// where EVERY segment is a recognized read-only inspection verb is safe to
// auto-run — e.g. "systemctl status caddy; journalctl -u caddy -n 5" or
// "docker ps | grep caddy".
var compoundSplitRe = regexp.MustCompile(`\s*(?:&&|\|\||;|\|)\s*`)
// subshellRe matches command substitution ($() or backticks) that can hide
// arbitrary execution. A command using these never qualifies for the read-only
// fast path — the substituted content could do anything.
var subshellRe = regexp.MustCompile("\\$\\(|`")
// compoundOpPattern is retained for compatibility — matches any compound
// operator. (Previously used to block ALL compound commands from the read-only
// path; now the per-segment check is more precise.)
var compoundOpPattern = regexp.MustCompile("[;&|`]|\\$\\(")
// ClassifyCommand scores an arbitrary shell command for the general `run`
// primitive. It combines a rule-based verdict (destructive denylist first,
// then a read-only allowlist for simple inspection commands) with the
// caller's declared risk, and returns the more severe of the two — the
// classifier may only escalate, never de-escalate, so a model that
// under-declares risk (or an adversarial prompt) cannot talk its way past a
// genuinely dangerous command. Anything not matched by either rule defaults
// to config_mutation (escalate), per "when in doubt, escalate."
func ClassifyCommand(command, declaredRisk string) string {
computed := computeCommandRisk(command)
if declaredRisk == "" {
return computed // no declaration to escalate with; computed's own escalate-by-default already applies
}
declared := normalizeRisk(declaredRisk)
if riskRank(declared) > riskRank(computed) {
return declared
}
return computed
}
func normalizeRisk(r string) string {
if _, ok := riskOrder[r]; ok {
return r
}
return RiskConfigMutation
}
func computeCommandRisk(command string) string {
cmd := strings.TrimSpace(command)
if cmd == "" {
return RiskConfigMutation
}
for _, p := range destructivePatterns {
if p.MatchString(cmd) {
return RiskDestructive
}
}
// Subshell substitution ($(), backticks) can hide arbitrary execution —
// never auto-run, even if the visible verbs look read-only.
if !subshellRe.MatchString(cmd) {
if allSegmentsReadOnly(cmd) {
return RiskReadOnly
}
}
// Not obviously destructive, not a recognized read-only inspection —
// default to the gated tier rather than guessing it's safe.
return RiskConfigMutation
}
// allSegmentsReadOnly splits a compound command on chaining operators
// (;, &&, ||, |) and checks whether EVERY segment is a recognized read-only
// inspection verb. If so, the whole command is safe to auto-run. Any segment
// that isn't a recognized read-only verb disqualifies the whole command —
// the classifier errs toward gating, not guessing.
func allSegmentsReadOnly(cmd string) bool {
segments := compoundSplitRe.Split(cmd, -1)
for _, seg := range segments {
seg = strings.TrimSpace(seg)
if seg == "" {
continue
}
// Strip a leading sudo/env assignment so "sudo cat /x" still matches.
probe := seg
probe = regexp.MustCompile(`^sudo\s+`).ReplaceAllString(probe, "")
probe = regexp.MustCompile(`^(\w+=\S+\s+)+`).ReplaceAllString(probe, "")
probe = strings.TrimSpace(probe)
if !readOnlyLeadPattern.MatchString(probe) {
return false
}
}
return len(segments) > 0
}