oikos/internal/policy/command.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|find|tree|locate|` +
		`dpkg\s+(-l|-s|--list|--status)\b|apt\s+(list|search|show)\b|` +
		`systemctl\s+(status|is-active|is-enabled|is-failed|list-units|list-unit-files|list-timers|show)\b|` +
		`timedatectl|hostnamectl|systemd-analyze|` +
		`docker\s+(ps|images|inspect|logs|version|info|stats)|` +
		`docker\s+compose\s+(logs|ps|top|config|images|port|cp)\b|` +
		`pct\s+(status|config|list)|qm\s+(status|config|list)|pvesh\s+get|` +
		`rclone\s+(ls|lsl|md5sum|check|cryptcheck)\b|` +
		`git\s+(status|log|diff|show|branch|remote))\b`)

// envAssignRe matches leading FOO=bar env-var assignments so they can be
// stripped before the read-only verb check.
var envAssignRe = regexp.MustCompile(`^(\w+=\S+\s+)+`)

// pctExecRe matches "pct exec <id> [--] <inner>" and captures <inner>. The
// id is a decimal digit string (Proxmox CT ids). The "--" separator is
// optional but recommended — without it, the rest of the line is the
// command passed to exec. Case-insensitive.
var pctExecRe = regexp.MustCompile(`(?i)^pct\s+exec\s+\d+\s+(?:--\s+)?(.+)$`)

// qmGuestExecRe matches "qm guest exec <id> [--] <inner>" similarly.
var qmGuestExecRe = regexp.MustCompile(`(?i)^qm\s+guest\s+exec\s+\d+\s+(?:--\s+)?(.+)$`)

// shellDashCRe matches "bash -c 'cmd'", "sh -c \"cmd\"" etc., capturing
// the quoted inner command. Handles single-quoted, double-quoted, and bare
// (unquoted) forms.
var shellDashCRe = regexp.MustCompile(`(?i)^(?:ba)?sh\s+-c\s+(?:"([^"]*)"|'([^']*)'|(\S+))\s*$`)

// curlLeadRe matches a curl command (the verb alone, at the segment start).
var curlLeadRe = regexp.MustCompile(`(?i)^curl\b`)

// curlMutateRe matches curl flags that indicate mutation (POST/PUT/DELETE
// method override, data payloads, form uploads, file uploads, file output).
// When any of these appears, the curl command is no longer read-only.
var curlMutateRe = regexp.MustCompile(`(?i)(?:^|\s)-X\s+(?:post|put|delete|patch|connect|trace)\b|(?:^|\s)-(?:d|F|T|o)\b|(?:^|\s)--(?:data[-a-z]*|request|form|upload-file|output)\b`)

// redirectOutRe matches shell output redirection to a file (> or >> followed
// by a path), but excludes the file-descriptor merge form `>&<digit>` (e.g.
// `2>&1`) which only rearranges streams and writes nothing to disk. RE2 has
// no lookahead, so we encode the exclusion by requiring the post-`>` char to
// be neither `&` nor whitespace.
var redirectOutRe = regexp.MustCompile(`(^|[^-])>>?\s*[^&\s]`)

// 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
	}

	// Unwrap known wrappers (pct exec <id> --, qm guest exec <id> --,
	// bash -c '…', sh -c '…', sudo, env assignments) so the classifier
	// scores the *actual* command, not the wrapper. Without this, every
	// `pct exec 132 systemctl status rclone-backup.timer` escalates to
	// config_mutation even though the inner command is read-only inspection.
	// See plans/2026-07-20-session-review-ten-sessions.md P0.1 — three
	// sessions bounced off the classifier because read-only `pct exec` and
	// `curl` were gated as config_mutation.
	inner := unwrapCommand(cmd)

	for _, p := range destructivePatterns {
		// Match on both the raw and unwrapped forms so that
		// `pct exec 121 -- rm -rf /` is still destructive even if the
		// unwrapping somehow hid it.
		if p.MatchString(inner) || 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(inner) {
		if allSegmentsReadOnly(inner) {
			return RiskReadOnly
		}
	}

	// Not obviously destructive, not a recognized read-only inspection —
	// default to the gated tier rather than guessing it's safe.
	return RiskConfigMutation
}

// unwrapCommand peels known command wrappers to expose the inner command
// for classification. It repeatedly strips:
//   - leading sudo
//   - leading FOO=bar env-var assignments
//   - `pct exec <id> [--] <inner>` → <inner>
//   - `qm guest exec <id> [--] <inner>` → <inner>
//   - `bash -c 'cmd'` / `sh -c "cmd"` → <cmd>
//
// When no wrapper is detected, the input is returned unchanged. The peel
// is iterative so "sudo pct exec 121 -- bash -c 'echo hi'" reduces to
// "echo hi" after a few passes. Compound commands (containing ;, &&, ||,
// |) are returned unchanged — they need per-segment classification, which
// the caller handles.
func unwrapCommand(cmd string) string {
	probe := strings.TrimSpace(cmd)
	// A compound command cannot be unwrapped as a whole — the inner
	// command of "pct exec 121 -- foo; rm -rf /" depends on which side of
	// the ";" you're on. The caller splits compounds before classifying
	// each segment, and each segment is unwrapped independently. Bail out
	// here so we don't unwrap "pct exec 121 -- foo" and lose the rest.
	if compoundOpPattern.MatchString(probe) {
		return probe
	}
	for i := 0; i < 8; i++ { // bounded unwrap depth
		next := peelOneWrapper(probe)
		if next == probe {
			return probe
		}
		probe = strings.TrimSpace(next)
	}
	return probe
}

// peelOneWrapper applies one peel step. Returns the input unchanged if no
// wrapper matched.
func peelOneWrapper(probe string) string {
	// sudo prefix
	if stripped := strings.TrimPrefix(probe, "sudo "); stripped != probe {
		return strings.TrimSpace(stripped)
	}
	// Env assignments: FOO=bar BAZ=qux <cmd>
	if envAssignRe.MatchString(probe) {
		return envAssignRe.ReplaceAllString(probe, "")
	}
	// pct exec <id> [--] <inner>
	if m := pctExecRe.FindStringSubmatch(probe); m != nil {
		return m[1]
	}
	// qm guest exec <id> [--] <inner>
	if m := qmGuestExecRe.FindStringSubmatch(probe); m != nil {
		return m[1]
	}
	// bash -c 'cmd' / sh -c "cmd" / sh -c cmd
	if m := shellDashCRe.FindStringSubmatch(probe); m != nil {
		// m[1] is the double-quoted form, m[2] is single-quoted, m[3] is bare.
		for _, g := range m[1:] {
			if g != "" {
				return g
			}
		}
	}
	return probe
}

// 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
		}
		// Unwrap wrappers per-segment too — "pct exec 121 -- systemctl
		// status caddy; pct exec 122 -- journalctl -u caddy" should reduce
		// to two read-only segments after unwrapping each.
		seg = unwrapCommand(seg)
		// Strip a leading sudo/env assignment so "sudo cat /x" still matches.
		probe := seg
		probe = strings.TrimPrefix(probe, "sudo ")
		probe = envAssignRe.ReplaceAllString(probe, "")
		probe = strings.TrimSpace(probe)
		// curl is handled by a dedicated check because GET (the default) is
		// read-only but POST/data/upload flags are not. The general
		// readOnlyLeadPattern can't distinguish these.
		if curlLeadRe.MatchString(probe) {
			if !curlIsReadOnly(probe) {
				return false
			}
			continue
		}
		// Any output redirection makes a verb non-read-only even if the
		// verb itself is (e.g. "curl url > /etc/passwd").
		if redirectOutRe.MatchString(probe) {
			return false
		}
		if !readOnlyLeadPattern.MatchString(probe) {
			return false
		}
	}
	return len(segments) > 0
}

// curlIsReadOnly returns true if a curl command performs a GET (or HEAD)
// without data/upload/output flags. POST/PUT/DELETE method overrides, -d/--data
// payloads, -F/--form uploads, -T/--upload-file transfers, and -o/--output
// file writes all disqualify the read-only path.
func curlIsReadOnly(curlCmd string) bool {
	if !curlLeadRe.MatchString(curlCmd) {
		return false
	}
	if curlMutateRe.MatchString(curlCmd) {
		return false
	}
	if redirectOutRe.MatchString(curlCmd) {
		return false
	}
	return true
}