Compare commits

...

4 Commits

Author SHA1 Message Date
claude 8a21478f36 mavweb: group the allowlist by capability domain (V-452) 2026-08-04 04:55:13 +04:00
claude 958d2a2fc8 tool: read a row as a dotted capability id (V-452)
scope.domain.action, the shape Hexis has always spoken, derived from the row
rather than stored — a derivation is one place to argue with, a column is
whatever the last person to enable the tool typed. The name stays the primary
key and nothing about lookup or execution changes: this is a way to read the
allowlist, not a second allowlist.

MatchCapability widens one way, so house.lock covers every action on the
locks and nothing narrower can claim a wider pattern.
2026-08-04 04:55:13 +04:00
claude 7db139b83e tool, mavend: cover the tiers end to end (V-449) 2026-08-04 04:50:56 +04:00
claude 0987dabfc4 tool: risk tiers decide the confirm, not one boolean (V-449)
The Destructive column was a mechanism with no policy behind it: nothing said
which acts are destructive, whether a confirmed act stays confirmed, or what a
new tool domain inherits, so each domain answered for itself.

Three tiers, derived from the row rather than stored, so the answer can be
argued with in one place instead of being whatever the last person to tick the
checkbox believed. Safe runs. Destructive costs a confirm turn, every time —
a confirmation binds one capability, one target and one argument list, and it
dies with the parked turn. Irreversible is refused: a confirm turn there would
be theatre, because the STT, the router and the fuzzy allowlist match are all
guesses and a spoken "да" checks none of them. She names the gap; the row
stays enabled.

An unrecognised dispatch shape inherits destructive, not safe. A domain argues
its way down to running freely, never up to being gated.
2026-08-04 04:50:56 +04:00
9 changed files with 625 additions and 9 deletions
+6
View File
@@ -51,6 +51,12 @@ func (h *reactiveHandler) actionAct(ctx context.Context, dec router.Decision) st
phrase := actPhrase(dec.Slots.Fn, dec.Slots.Args)
h.park(dec.Slots.Fn, dec.Slots.Args, phrase)
return "выполнить «" + phrase + "»? скажи «да» или «нет»."
case errors.Is(err, tool.ErrNeedsAuthedSurface):
// Irreversible (internal/tool/risk.go). A confirm turn would not
// help: everything that proposed this act — the STT, the router,
// the fuzzy allowlist match — is a guess, and a spoken "да" checks
// none of it. She names the gap instead.
return "это я из голоса не выполню — после него ничего не вернуть. запусти сам, если правда надо."
case errors.Is(err, tool.ErrNotEnabled):
return h.proposeGap(ctx, dec)
case errors.Is(err, tool.ErrNotConnected), errors.Is(err, mcp.ErrNotConnected), errors.Is(err, mcp.ErrNoServer):
+73
View File
@@ -0,0 +1,73 @@
package main
import (
"context"
"strings"
"testing"
"github.com/kami/maven/internal/router"
)
// The act path speaks each tier (Vikunja #449): a safe row runs, a destructive
// one costs a confirm turn, an irreversible one is refused with the reason.
func TestActPathSpeaksTheTiers(t *testing.T) {
h, st, _ := newClarifyHandler(t)
ctx := context.Background()
now := h.now()
for _, tc := range []struct {
name string
cmd []string
destructive bool
}{
{"status", []string{"true"}, false},
{"restart", []string{"true"}, true},
{"wipe", []string{"rm", "-rf"}, true},
} {
if _, err := st.ProposeTool(ctx, tc.name, "test", "homelab", now); err != nil {
t.Fatalf("propose %s: %v", tc.name, err)
}
if err := st.EnableTool(ctx, tc.name, tc.cmd, tc.destructive, "homelab", now); err != nil {
t.Fatalf("enable %s: %v", tc.name, err)
}
}
act := func(fn string) string {
return h.actionAct(ctx, router.Decision{
Intent: router.IntentAct,
Utterance: fn,
Slots: router.Slots{Fn: fn, HasFn: true},
})
}
if reply := act("status"); !strings.HasPrefix(reply, "готово") {
t.Errorf("safe act replied %q; want it to have run", reply)
}
if reply := act("restart"); !strings.Contains(reply, "скажи «да»") {
t.Errorf("destructive act replied %q; want a confirm turn", reply)
}
// Clear the confirm the destructive act parked, so what is pending after
// the irreversible one is only what the irreversible one parked.
h.mu.Lock()
h.pending = nil
h.mu.Unlock()
reply := act("wipe")
if strings.Contains(reply, "скажи «да»") {
t.Fatalf("irreversible act asked for a confirm: %q", reply)
}
if !strings.Contains(reply, "не вернуть") {
t.Errorf("irreversible act replied %q; want it to name the reason", reply)
}
// Nothing was parked, so a later "да" cannot pick it up.
h.mu.Lock()
pending := h.pending
h.mu.Unlock()
if pending != nil {
t.Errorf("an irreversible act parked %+v", pending)
}
// And it is still an enabled row — refusing to run it from voice is not
// the same as taking it off the allowlist.
if got, err := st.LookupTool(ctx, "wipe"); err != nil || got.Status != "enabled" {
t.Errorf("wipe is %+v, %v; want it still enabled", got, err)
}
}
+16 -7
View File
@@ -27,6 +27,7 @@ import (
"github.com/kami/maven/internal/ipc"
"github.com/kami/maven/internal/pattern"
"github.com/kami/maven/internal/tasks"
"github.com/kami/maven/internal/tool"
"github.com/kami/maven/internal/voice"
"github.com/kami/maven/internal/webauthn"
)
@@ -746,6 +747,8 @@ func handleDash(w http.ResponseWriter, r *http.Request, core ipc.CoreAPI) {
var toolsTmpl = template.Must(template.New("tools").Funcs(func() template.FuncMap {
m := shellFuncs()
m["join"] = strings.Join
m["capability"] = func(t ipc.Tool) string { return tool.CapabilityOf(t).String() }
m["risk"] = func(t ipc.Tool) string { return string(tool.RiskOf(t)) }
return m
}()).Parse(shellTopHTML + toolsHTML + shellBottomHTML))
@@ -756,9 +759,9 @@ const toolsHTML = `{{template "shellTop" "tools"}}
<section class=card>
<h2 class=card-title>proposed <span class=badge>{{len .Proposed}}</span></h2>
{{if .Proposed}}<p class=hint>maven drafted these from acts she couldn't run. Fill the command (argv, space-separated) and enable. A row in an <code>mcp:</code> scope came from an MCP server and already knows what it calls — check the command, then enable.</p>
<div class=scroll><table><tr><th>name</th><th>scope</th><th>from utterance</th><th>enable as</th></tr>
<div class=scroll><table><tr><th>name</th><th>capability</th><th>scope</th><th>from utterance</th><th>enable as</th></tr>
{{range .Proposed}}<tr>
<td><code>{{.Name}}</code></td><td><span class=badge>{{.Scope}}</span></td><td>{{.Utterance}}</td>
<td><code>{{.Name}}</code></td><td><code>{{capability .}}</code></td><td><span class=badge>{{.Scope}}</span></td><td>{{.Utterance}}</td>
<td><form method=post action=/tools>
<input type=hidden name=name value="{{.Name}}">
<input type=hidden name=scope value="{{.Scope}}">
@@ -779,14 +782,16 @@ const toolsHTML = `{{template "shellTop" "tools"}}
</section>
<section class=card>
<h2 class=card-title>enabled <span class=badge>{{len .Enabled}}</span></h2>
{{if .Enabled}}<div class=scroll><table><tr><th>name</th><th>scope</th><th>command</th><th></th><th></th></tr>
{{range .Enabled}}<tr><td><code>{{.Name}}</code></td><td><span class=badge>{{.Scope}}</span></td><td><code>{{join .Cmd " "}}</code></td>
<td>{{if .Destructive}}<span class=red>destructive</span>{{end}}</td>
{{if .Enabled}}<p class=hint>grouped by capability domain. The dotted id is <code>scope.domain.action</code> — the same shape Hexis speaks — and it is derived from the row, so it always describes what the command actually does.</p>
{{range .Groups}}<h3 class=card-title><code>{{.Prefix}}</code> <span class=badge>{{len .Tools}}</span></h3>
<div class=scroll><table><tr><th>capability</th><th>name</th><th>command</th><th>risk</th><th></th></tr>
{{range .Tools}}<tr><td><code>{{capability .}}</code></td><td><code>{{.Name}}</code></td><td><code>{{join .Cmd " "}}</code></td>
<td>{{$r := risk .}}{{if eq $r "irreversible"}}<span class=red>irreversible</span>{{else if eq $r "destructive"}}<span class=red>destructive</span>{{else}}<span class=badge>safe</span>{{end}}</td>
<td><form method=post action=/tools class=inline-form>
<input type=hidden name=name value="{{.Name}}">
<input type=hidden name=scope value="{{.Scope}}">
<input type=hidden name=action value=disable>
<button class=btn>disable</button></form></td></tr>{{end}}</table></div>
<button class=btn>disable</button></form></td></tr>{{end}}</table></div>{{end}}
{{else}}<div class=empty>
<svg class=icon width="20" height="20"><use href="/ethos-icons.svg#i-settings"/></svg>
<div>no tools enabled</div>
@@ -1459,12 +1464,16 @@ func handleTools(w http.ResponseWriter, r *http.Request, core ipc.CoreAPI, sessi
servers = nil
}
w.Header().Set("Content-Type", "text/html; charset=utf-8")
// Enabled rows are shown grouped by capability domain (Vikunja #452). A
// flat list stops answering "what can she do to the house" somewhere
// around fifteen rows, and that is the question this page exists for.
if err := toolsTmpl.Execute(w, struct {
Msg string
Proposed []ipc.Tool
Enabled []ipc.Tool
Groups []tool.CapabilityGroup
MCP []ipc.MCPServerStatus
}{msg, proposed, enabled, servers}); err != nil {
}{msg, proposed, enabled, tool.GroupByDomain(enabled), servers}); err != nil {
log.Printf("tools render: %v", err)
}
}
+51
View File
@@ -293,6 +293,57 @@ don't improvise.** Destructive ones still gate behind confirm.
Misroute correction is append-only and grows the router's examples with use —
same shape as `nudges.outcome` tuning cooldowns, no retrain.
#### Risk tiers, not one boolean
`Destructive` on a tool row is one bit set by whoever ticked the checkbox on
`/tools`. It is a mechanism, and it never said which acts are destructive,
whether a confirmed act stays confirmed, or what a new tool domain inherits.
`internal/tool/risk.go` is the policy (Vikunja #449). The tier is DERIVED from
the row, not stored, so it can be argued with in one place instead of being
whatever the last person to enable the tool believed.
| Tier | What it is | What it costs |
|---|---|---|
| `safe` | a read, or a change he can undo by saying the opposite | runs on first hearing |
| `destructive` | it changes something real and undoing it takes work | one confirm turn, every time |
| `irreversible` | the thing does not come back: a wipe, a format, a delete with no bin | voice may not authorise it at all |
Three rules fall out, and they are the part that was missing:
- **Which acts are destructive is not only the checkbox.** A house row always
is, because there is no read-only way to turn the heating off. A row whose
argv names one of the irreversible verbs always is, whatever the row says.
- **A confirmed act never stays confirmed.** At any tier. A confirmation binds
one capability, one target and one argument list, and it dies with the parked
turn (90s). "The same act again" is a new act. A sticky confirm is a standing
grant and nothing on the voice path may hold one.
- **A new domain inherits `destructive`, not `safe`.** A dispatch shape the
policy does not recognise gets the confirm turn. A domain argues its way down
to running freely; it never has to argue its way up to being gated.
#### Capability ids
A row is also read as a dotted capability id, `scope.domain.action` — the same
shape Hexis has always spoken, which made the local surface the odd one out
(Vikunja #452). `homelab.docker.restart`, `house.lock.unlock`,
`mcp_vikunja.vikunja.delete_task`.
Derived, not stored, for the reason the tier is: a derivation is one place to
argue with. The name is still the primary key and nothing about lookup or
execution changed — this is a way to READ the allowlist, not a second one.
`/tools` groups the enabled rows by `scope.domain` and prints the id and the
tier beside each, because a flat list stops answering "what can she do to the
house" somewhere around fifteen rows.
`MatchCapability` widens one way: `house` and `house.lock` both cover
`house.lock.unlock`, and nothing lets a narrower id claim a wider pattern.
The irreversible tier is refused rather than asked about, because a confirm
turn would be theatre: everything that proposed the act — an STT guess, a
router guess, a fuzzy allowlist match — is a guess, and a spoken "да" checks
none of it. She names the gap and he runs it himself. The row stays enabled;
refusing to run it from voice is not the same as taking it off the allowlist.
---
## Voice pipeline (STT / TTS)
+140
View File
@@ -0,0 +1,140 @@
package tool
import (
"sort"
"strings"
"github.com/kami/maven/internal/ipc"
"github.com/kami/maven/internal/mcp"
"github.com/kami/maven/internal/smarthome"
)
// Capability ids (Vikunja #452).
//
// A tool row is flat: one name, one scope, one enabled bit. Permission is
// therefore per name, and nothing groups. Hexis has spoken dotted capability
// ids since it existed, so the local surface was the odd one out — and the
// flat shape gets expensive around fifteen rows, when "what can she do to the
// house" stops being a question anyone can answer by reading a list.
//
// A capability id is scope.domain.action: homelab.docker.restart,
// house.lock.unlock, mcp_vikunja.vikunja.delete_task.
//
// DERIVED, not stored, for the same reason the risk tier is (risk.go): a
// derivation is one place to argue with, a column is whatever the last person
// to enable the row happened to type. The name stays the primary key and
// nothing about lookup or execution changes — this is a way to READ the
// allowlist, not a second allowlist.
type Capability struct {
Scope string
Domain string
Action string
}
// String renders the dotted id. An empty segment becomes "unknown" rather than
// collapsing, so an id always has three parts and a prefix match cannot
// accidentally widen.
func (c Capability) String() string {
return capSegment(c.Scope) + "." + capSegment(c.Domain) + "." + capSegment(c.Action)
}
func capSegment(s string) string {
s = strings.ToLower(strings.TrimSpace(s))
s = strings.ReplaceAll(s, ".", "_")
s = strings.ReplaceAll(s, " ", "_")
if s == "" {
return "unknown"
}
return s
}
// CapabilityOf derives the id of a tool row.
//
// The domain is the thing acted on and the action is what is done to it, read
// off whichever dispatch shape the row uses:
//
// - a house row: the Home Assistant entity domain and the service, so
// light.kitchen + turn_off becomes house.light.turn_off. Its scope is
// "house" whatever the row says, because the entity id is what decides
// what it touches.
// - an MCP row: the server handle and the remote tool name.
// - a process row: the program (path stripped) and its first subcommand, or
// the tool name when the argv carries no second word.
func CapabilityOf(t ipc.Tool) Capability {
if entityID, service, ok := smarthome.ParseCmd(t.Cmd); ok {
domain := entityID
if i := strings.Index(entityID, "."); i > 0 {
domain = entityID[:i]
}
return Capability{Scope: "house", Domain: domain, Action: service}
}
if server, remote, ok := mcp.ParseCmd(t.Cmd); ok {
return Capability{Scope: "mcp_" + server, Domain: server, Action: remote}
}
scope := t.Scope
if scope == "" {
scope = "homelab"
}
if len(t.Cmd) == 0 {
// A proposal has no argv yet. It still gets an id, because "what did
// she ask for" is exactly the question the proposed list answers.
return Capability{Scope: scope, Domain: "unknown", Action: t.Name}
}
program := t.Cmd[0]
if i := strings.LastIndex(program, "/"); i >= 0 {
program = program[i+1:]
}
action := t.Name
if len(t.Cmd) > 1 && !strings.HasPrefix(t.Cmd[1], "-") {
action = t.Cmd[1]
}
return Capability{Scope: scope, Domain: program, Action: action}
}
// MatchCapability reports whether an id matches a pattern. A pattern is a
// dotted id whose segments may be "*", and a pattern with fewer segments than
// the id matches every id under it: "house" and "house.*" both cover
// house.lock.unlock.
//
// Prefix widening is deliberate and one-directional. "house.lock" covers every
// action on the locks; nothing lets a narrower id claim a wider pattern.
func MatchCapability(pattern string, c Capability) bool {
want := strings.Split(strings.ToLower(strings.TrimSpace(pattern)), ".")
got := strings.Split(c.String(), ".")
if len(want) > len(got) {
return false
}
for i, w := range want {
if w == "*" || w == "" {
continue
}
if w != got[i] {
return false
}
}
return true
}
// GroupByDomain buckets rows by "scope.domain" and returns the buckets in a
// stable order, which is what makes the allowlist readable past the point
// where a flat list stops being.
func GroupByDomain(tools []ipc.Tool) []CapabilityGroup {
byKey := map[string][]ipc.Tool{}
for _, t := range tools {
c := CapabilityOf(t)
byKey[capSegment(c.Scope)+"."+capSegment(c.Domain)] = append(byKey[capSegment(c.Scope)+"."+capSegment(c.Domain)], t)
}
out := make([]CapabilityGroup, 0, len(byKey))
for k, v := range byKey {
sort.Slice(v, func(i, j int) bool { return v[i].Name < v[j].Name })
out = append(out, CapabilityGroup{Prefix: k, Tools: v})
}
sort.Slice(out, func(i, j int) bool { return out[i].Prefix < out[j].Prefix })
return out
}
// CapabilityGroup — one scope.domain and the rows under it.
type CapabilityGroup struct {
Prefix string
Tools []ipc.Tool
}
+92
View File
@@ -0,0 +1,92 @@
package tool
import (
"testing"
"github.com/kami/maven/internal/ipc"
)
func TestCapabilityOfDescribesTheRow(t *testing.T) {
cases := []struct {
name string
tool ipc.Tool
want string
}{
{
"a process with a subcommand",
ipc.Tool{Name: "restart", Scope: "homelab", Cmd: []string{"docker", "restart"}},
"homelab.docker.restart",
},
{
"a program with a path and a flag",
ipc.Tool{Name: "backup", Scope: "homelab", Cmd: []string{"/usr/local/bin/borg", "-v"}},
"homelab.borg.backup",
},
{
"the house",
ipc.Tool{Name: "unlock_front", Cmd: []string{"smarthome", "lock.front_door", "unlock"}},
"house.lock.unlock",
},
{
"an mcp tool",
ipc.Tool{Name: "vikunja_delete_task", Cmd: []string{"mcp", "vikunja", "delete_task"}},
"mcp_vikunja.vikunja.delete_task",
},
{
"a proposal with no command yet",
ipc.Tool{Name: "перезапусти", Scope: "homelab"},
"homelab.unknown.перезапусти",
},
}
for _, c := range cases {
if got := CapabilityOf(c.tool).String(); got != c.want {
t.Errorf("%s: %q; want %q", c.name, got, c.want)
}
}
}
// A dotted id always has three segments, so a prefix pattern cannot widen by
// accident onto a row whose scope happens to be empty.
func TestCapabilityStringAlwaysHasThreeSegments(t *testing.T) {
if got := (Capability{}).String(); got != "unknown.unknown.unknown" {
t.Errorf("empty capability = %q", got)
}
if got := (Capability{Scope: "home lab", Domain: "a.b", Action: "X"}).String(); got != "home_lab.a_b.x" {
t.Errorf("segments not folded: %q", got)
}
}
func TestMatchCapabilityWidensOneWay(t *testing.T) {
c := CapabilityOf(ipc.Tool{Name: "unlock_front", Cmd: []string{"smarthome", "lock.front_door", "unlock"}})
for _, p := range []string{"house", "house.lock", "house.lock.unlock", "house.*.unlock", "*.lock"} {
if !MatchCapability(p, c) {
t.Errorf("%q did not match %s", p, c)
}
}
for _, p := range []string{"homelab", "house.light", "house.lock.lock", "house.lock.unlock.now"} {
if MatchCapability(p, c) {
t.Errorf("%q matched %s", p, c)
}
}
}
func TestGroupByDomainIsStable(t *testing.T) {
tools := []ipc.Tool{
{Name: "restart", Scope: "homelab", Cmd: []string{"docker", "restart"}},
{Name: "unlock_front", Cmd: []string{"smarthome", "lock.front_door", "unlock"}},
{Name: "logs", Scope: "homelab", Cmd: []string{"docker", "logs"}},
}
groups := GroupByDomain(tools)
if len(groups) != 2 {
t.Fatalf("%d groups; want 2", len(groups))
}
if groups[0].Prefix != "homelab.docker" || len(groups[0].Tools) != 2 {
t.Errorf("first group %+v; want homelab.docker with 2 rows", groups[0])
}
if groups[0].Tools[0].Name != "logs" {
t.Errorf("rows not sorted: %+v", groups[0].Tools)
}
if groups[1].Prefix != "house.lock" {
t.Errorf("second group %q; want house.lock", groups[1].Prefix)
}
}
+145
View File
@@ -0,0 +1,145 @@
package tool
import (
"strings"
"github.com/kami/maven/internal/ipc"
"github.com/kami/maven/internal/mcp"
"github.com/kami/maven/internal/smarthome"
)
// Risk tiers (Vikunja #449).
//
// What existed before this file was a mechanism and no policy: one
// `Destructive` boolean per row, set by whoever ticked the checkbox on /tools.
// Nothing said which acts are destructive, whether a confirmed act stays
// confirmed, or what a new tool domain inherits — so every domain answered
// those questions for itself, and two of them answered differently.
//
// The tiers below are the policy. They are derived from the row, not stored:
// a derivation can be argued with and corrected in one place, while a column
// is whatever the last person to enable the tool believed.
//
// The three questions, answered once:
//
// - WHICH ACTS ARE DESTRUCTIVE. A house row always is, because there is no
// read-only way to turn the heating off. A row whose argv names one of the
// irreversible verbs always is, whatever the checkbox says. Everything else
// is what the row was enabled as.
// - DOES A CONFIRMED ACT STAY CONFIRMED. No. Never, at any tier. A
// confirmation binds one capability, one target and one argument list, and
// it expires with the parked turn (confirmTTL, 90s). "Same act again" is a
// new act and costs a new turn. A sticky confirm is a standing grant, and
// nothing on the voice path may hold one.
// - WHAT A NEW DOMAIN INHERITS. The default is TierDestructive, not
// TierSafe. A dispatch shape this file does not recognise gets the confirm
// turn — a new domain must argue its way DOWN to running freely, never up
// to needing a confirm.
type Risk string
const (
// TierSafe — a read, or a mutation the owner can undo by saying the
// opposite. Runs on first hearing.
TierSafe Risk = "safe"
// TierDestructive — it changes something real and undoing it takes work.
// One confirm turn, every time, never remembered.
TierDestructive Risk = "destructive"
// TierIrreversible — the thing it acts on does not come back: a wipe, a
// format, a delete with no bin behind it. A confirm turn is not enough,
// because the whole chain that proposed it — an STT guess, a router guess,
// a fuzzy allowlist match — has a spoken "да" as its only check. She names
// the gap and he runs it himself.
TierIrreversible Risk = "irreversible"
)
// Policy — what a tier requires of the act path.
//
// There is deliberately no "sticky for" field. Non-stickiness is the policy,
// and a knob that could turn it off would be the thing to argue with instead
// of the rule.
type Policy struct {
// Confirm — the act does not run on first hearing.
Confirm bool
// VoiceMayRun — a spoken confirmation is enough authority to run it.
VoiceMayRun bool
}
// PolicyFor returns the requirements of a tier. An unknown tier is treated as
// destructive, for the same reason the default derivation is.
func PolicyFor(r Risk) Policy {
switch r {
case TierSafe:
return Policy{Confirm: false, VoiceMayRun: true}
case TierIrreversible:
return Policy{Confirm: true, VoiceMayRun: false}
default:
return Policy{Confirm: true, VoiceMayRun: true}
}
}
// irreversibleVerbs — argv heads and subcommands that destroy the thing they
// name. Matched as whole argv elements, never as substrings: "rm" must not
// fire on "/usr/bin/rmdir-report" and "drop" must not fire on "dropbox".
//
// The list is short on purpose. It is not a sandbox and it does not try to be
// one — an enabled row can already run anything the daemon's user can run.
// What it is, is the set of words that mean "and then it is gone", so that the
// one act nobody can walk back is the one act a spoken "да" cannot authorise.
var irreversibleVerbs = map[string]bool{
"rm": true, "rmdir": true, "shred": true, "srm": true,
"mkfs": true, "fdisk": true, "parted": true, "wipefs": true,
"dd": true, "format": true,
"drop": true, "drop-database": true, "destroy": true, "purge": true,
"prune": true, "truncate": true,
}
// RiskOf derives the tier of an enabled tool row.
func RiskOf(t ipc.Tool) Risk {
if isIrreversible(t.Cmd) {
return TierIrreversible
}
// A house row is a physical change to the flat, and the confirm turn on it
// is structural rather than a column: /tools writes the checkbox straight
// through on enable, so unticking it once turned an unlock into a row that
// ran on first hearing. Nothing any surface writes removes the second turn
// from a physical device.
if _, _, ok := smarthome.ParseCmd(t.Cmd); ok {
return TierDestructive
}
// An MCP row is a call to somebody else's server. It is enabled with a
// fingerprint of what it declared at approval time (Vikunja #251), and the
// tier tracks the same flag every other row uses — the point of this branch
// is that it is NOT special-cased into running freely.
if _, _, ok := mcp.ParseCmd(t.Cmd); ok {
if t.Destructive {
return TierDestructive
}
return TierSafe
}
if t.Destructive {
return TierDestructive
}
if len(t.Cmd) == 0 {
// Not a shape this file knows how to read. The default is the confirm
// turn: a new domain argues its way down, not up.
return TierDestructive
}
return TierSafe
}
// isIrreversible reports whether any argv element is one of the verbs that
// destroys what it names. Every element, not just the head: "sudo rm" and
// "docker volume prune" both hide the verb behind a wrapper.
func isIrreversible(cmd []string) bool {
for _, arg := range cmd {
word := strings.ToLower(strings.TrimSpace(arg))
// Take the last path element, so /bin/rm reads as rm.
if i := strings.LastIndex(word, "/"); i >= 0 {
word = word[i+1:]
}
if irreversibleVerbs[word] {
return true
}
}
return false
}
+81
View File
@@ -0,0 +1,81 @@
package tool
import (
"context"
"errors"
"testing"
"github.com/kami/maven/internal/ipc"
)
func TestRiskOfReadsTheRow(t *testing.T) {
cases := []struct {
name string
tool ipc.Tool
want Risk
}{
{"a plain read", ipc.Tool{Cmd: []string{"systemctl", "status"}}, TierSafe},
{"the checkbox", ipc.Tool{Cmd: []string{"systemctl", "restart"}, Destructive: true}, TierDestructive},
{"a wipe", ipc.Tool{Cmd: []string{"rm", "-rf"}}, TierIrreversible},
{"a wipe behind a wrapper", ipc.Tool{Cmd: []string{"sudo", "/bin/rm"}}, TierIrreversible},
{"a prune behind a subcommand", ipc.Tool{Cmd: []string{"docker", "volume", "prune"}}, TierIrreversible},
{"the house", ipc.Tool{Cmd: []string{"smarthome", "light.kitchen", "turn_off"}}, TierDestructive},
{"the house with the box unticked", ipc.Tool{Cmd: []string{"smarthome", "lock.front", "unlock"}}, TierDestructive},
{"an mcp read", ipc.Tool{Cmd: []string{"mcp", "vikunja", "list_tasks"}}, TierSafe},
{"an mcp write", ipc.Tool{Cmd: []string{"mcp", "vikunja", "delete_task"}, Destructive: true}, TierDestructive},
{"a shape nobody wrote yet", ipc.Tool{}, TierDestructive},
}
for _, c := range cases {
if got := RiskOf(c.tool); got != c.want {
t.Errorf("%s: RiskOf = %q; want %q", c.name, got, c.want)
}
}
}
// The default is the confirm turn. A tier this file does not know is not a
// tier that runs freely.
func TestPolicyForDefaultsToConfirming(t *testing.T) {
for _, r := range []Risk{TierDestructive, Risk("whatever-lands-here-next")} {
p := PolicyFor(r)
if !p.Confirm || !p.VoiceMayRun {
t.Errorf("PolicyFor(%q) = %+v; want a confirm turn she may run", r, p)
}
}
if p := PolicyFor(TierSafe); p.Confirm || !p.VoiceMayRun {
t.Errorf("PolicyFor(safe) = %+v; want it to run", p)
}
if p := PolicyFor(TierIrreversible); !p.Confirm || p.VoiceMayRun {
t.Errorf("PolicyFor(irreversible) = %+v; want voice refused", p)
}
}
// An irreversible act is refused whether or not he said "да", because there is
// no second answer that changes what it would do.
func TestExecRefusesIrreversibleEvenConfirmed(t *testing.T) {
api := fakeAPI{tools: map[string]ipc.Tool{
"wipe": {Name: "wipe", Status: "enabled", Cmd: []string{"rm", "-rf"}, Destructive: true},
}}
e := NewExecutor(api, 0)
ran := false
e.run = func(context.Context, []string) (string, error) { ran = true; return "", nil }
for _, confirmed := range []bool{false, true} {
if _, err := e.Exec(context.Background(), "wipe", []string{"/data"}, confirmed); !errors.Is(err, ErrNeedsAuthedSurface) {
t.Errorf("confirmed=%v: %v; want ErrNeedsAuthedSurface", confirmed, err)
}
}
if ran {
t.Fatal("an irreversible act ran from the voice path")
}
}
// A row with no cmd at all is not a shape this file reads, and it must not
// slide through as safe.
func TestExecConfirmsAnUnreadableRow(t *testing.T) {
api := fakeAPI{tools: map[string]ipc.Tool{
"mystery": {Name: "mystery", Status: "enabled"},
}}
e := NewExecutor(api, 0)
if _, err := e.Exec(context.Background(), "mystery", nil, false); !errors.Is(err, ErrNeedsConfirm) {
t.Errorf("%v; want ErrNeedsConfirm", err)
}
}
+21 -2
View File
@@ -67,6 +67,12 @@ var (
// proposal, and drafting a new proposal for a tool that already exists and
// is enabled is a lie about what is wrong.
ErrNotConnected = errors.New("tool is enabled but its backend is not connected")
// ErrNeedsAuthedSurface — the row is enabled and the act is understood,
// and its tier is one a spoken "да" may not authorise (risk.go,
// TierIrreversible). Held apart from ErrNeedsConfirm because there is no
// confirm turn that would help: asking again would imply the second answer
// changes the outcome.
ErrNeedsAuthedSurface = errors.New("tool is irreversible and voice may not authorise it")
)
// MCPCaller is the seam for an act that is an MCP tool call rather than a
@@ -121,7 +127,12 @@ func (e *Executor) WithHome(h HomeCaller) *Executor {
// Exec looks up name in the store and runs Cmd+args as argv (no shell).
// confirmed=true is the second turn of a destructive act (the user said "да");
// it bypasses the ErrNeedsConfirm gate. Non-enabled ⇒ ErrNotEnabled; a
// destructive tool with confirmed=false ⇒ ErrNeedsConfirm.
// destructive tool with confirmed=false ⇒ ErrNeedsConfirm; an irreversible one
// ⇒ ErrNeedsAuthedSurface, confirmed or not.
//
// Exec IS the voice path. Nothing else calls it, which is why the tier check
// needs no surface argument: the authority it can offer a tool is a spoken
// "да", and TierIrreversible says that is not enough.
func (e *Executor) Exec(ctx context.Context, name string, args []string, confirmed bool) (string, error) {
t, err := e.api.LookupTool(ctx, name)
if errors.Is(err, ipc.ErrToolNotFound) {
@@ -133,7 +144,15 @@ func (e *Executor) Exec(ctx context.Context, name string, args []string, confirm
if t.Status != "enabled" {
return "", ErrNotEnabled
}
if t.Destructive && !confirmed {
// The tier decides, not the column (Vikunja #449). RiskOf reads the row and
// answers the three questions the boolean never did: which acts are
// destructive, whether a confirm sticks (it never does), and what an
// unrecognised shape inherits (the confirm turn).
policy := PolicyFor(RiskOf(t))
if !policy.VoiceMayRun {
return "", ErrNeedsAuthedSurface
}
if policy.Confirm && !confirmed {
return "", ErrNeedsConfirm
}
// An MCP row is a call to a configured server, not a process. Everything