Files
ARTEX/server/target_gate_scope_test.go
BaaRai 16ddfc7779 Hierarchical run budgets: min(child, parent) with forced wrap-up (off by default)
Per-level token/turn budgets: task -> intent (worker run) -> planner round
(counted inside the task). A child's effective budget is
min(own budget, parent's remaining above the wrap-up reserve). When the task
can no longer afford one worker, workers stop claiming intents and the task
settles through one forced wrap-up planner round (the existing settle
sequence, budget words instead of the timeout words).

Config: ARTEX_TASK_BUDGET_TOKENS, ARTEX_TASK_BUDGET_TURNS,
ARTEX_INTENT_BUDGET_TOKENS, ARTEX_INTENT_BUDGET_TURNS. 0 or unset = unlimited;
with all four unset nothing changes.
2026-11-12 17:27:28 +01:00

447 lines
16 KiB
Go

package server
import (
"context"
"iter"
"net/http/httptest"
"strings"
"sync/atomic"
"testing"
"time"
"github.com/Autumn-27/artex/agent"
"github.com/Autumn-27/artex/db"
"github.com/Autumn-27/artex/guard"
"github.com/Autumn-27/artex/intercept"
"github.com/Autumn-27/norma/llm"
)
// Target-gate wiring: every platform-owned session starts on a context that
// carries the approval scope of its task or conversation, and the planner and
// the main agent run with the task's target-only hooks. The gate is off, so
// none of this changes what a session does.
// innerHooksProbe is a programmable inner HookRunner that records what
// steerHooks hands it.
type innerHooksProbe struct {
block bool
msg string
updated []byte
pre, post int
tool string
input string
scoped bool
}
func (p *innerHooksProbe) PreToolUse(ctx context.Context, name string, input []byte) (bool, string, []byte) {
p.pre++
p.tool, p.input = name, string(input)
_, p.scoped = intercept.TargetScopeFromContext(ctx)
return p.block, p.msg, p.updated
}
func (p *innerHooksProbe) PostToolUse(context.Context, string, []byte, []byte, bool) { p.post++ }
func (p *innerHooksProbe) Stop(context.Context, []llm.Message) (bool, []string, string) {
return false, nil, ""
}
// The worker's hooks are the task Guard wrapped in steerHooks. The wrapper must
// hand the call, on the caller's context, to the inner hooks and return their
// decision unchanged — a block decided by the Guard must not be lost on the way.
func TestSteerHooksForwardInnerBlock(t *testing.T) {
ctx := intercept.WithTargetScope(context.Background(), intercept.TargetScope{TaskID: "7"})
noSteer := func() (string, bool) { return "", false }
input := []byte(`{"command":"curl https://app.example.com/"}`)
inner := &innerHooksProbe{block: true, msg: "inner refused"}
h := steerHooks{inner: inner, drain: noSteer, nudges: &atomic.Int64{}}
block, msg, updated := h.PreToolUse(ctx, "Bash", input)
if !block || msg != "inner refused" || updated != nil {
t.Fatalf("inner block not forwarded: block=%v msg=%q updated=%q", block, msg, updated)
}
if inner.pre != 1 || inner.tool != "Bash" || inner.input != string(input) || !inner.scoped {
t.Fatalf("inner hooks saw pre=%d tool=%q input=%q scoped=%v", inner.pre, inner.tool, inner.input, inner.scoped)
}
// An inner pass (with a rewritten input) is forwarded just the same.
inner = &innerHooksProbe{updated: []byte(`{"command":"true"}`)}
h = steerHooks{inner: inner, drain: noSteer, nudges: &atomic.Int64{}}
if block, msg, updated := h.PreToolUse(ctx, "Bash", input); block || msg != "" || string(updated) != `{"command":"true"}` {
t.Fatalf("inner pass not forwarded: block=%v msg=%q updated=%q", block, msg, updated)
}
h.PostToolUse(ctx, "Bash", input, []byte(`"ok"`), false)
if inner.post != 1 {
t.Fatalf("PostToolUse reached the inner hooks %d times, want 1", inner.post)
}
// A queued steer message is delivered first; the inner hooks are not asked.
inner = &innerHooksProbe{}
h = steerHooks{inner: inner, drain: func() (string, bool) { return "change course", true }, nudges: &atomic.Int64{}}
if block, msg, _ := h.PreToolUse(ctx, "Bash", input); !block || !strings.Contains(msg, "change course") || inner.pre != 0 {
t.Fatalf("steer message: block=%v msg=%q inner.pre=%d", block, msg, inner.pre)
}
}
// scopeProbe is the target scope a session's context carried.
type scopeProbe struct {
scope intercept.TargetScope
ok bool
}
// scopeProbeProvider is a model that lists its work dir (a read-only LS call) on
// its first turn and ends the run on the next, recording the target scope of the
// context it is called with. The harness calls the model and the tool hooks on
// the same session context.
type scopeProbeProvider struct {
seen chan scopeProbe
turn atomic.Int64
}
func newScopeProbeProvider() *scopeProbeProvider {
return &scopeProbeProvider{seen: make(chan scopeProbe, 16)}
}
func (p *scopeProbeProvider) Stream(ctx context.Context, _ llm.CompletionRequest) iter.Seq2[llm.StreamEvent, error] {
scope, ok := intercept.TargetScopeFromContext(ctx)
select {
case p.seen <- scopeProbe{scope, ok}:
default:
}
events := []llm.StreamEvent{{Type: llm.SETextDelta, Text: "done"}, {Type: llm.SEMessageDelta, StopReason: "end_turn"}}
if p.turn.Add(1) == 1 {
events = []llm.StreamEvent{
{Type: llm.SEToolUseStart, ToolID: "call-1", ToolName: "LS"},
{Type: llm.SEToolInputJSON, Text: `{}`},
{Type: llm.SEMessageDelta, StopReason: "tool_use"},
}
}
return func(yield func(llm.StreamEvent, error) bool) {
for _, event := range events {
if !yield(event, nil) {
return
}
}
}
}
func (p *scopeProbeProvider) Complete(ctx context.Context, req llm.CompletionRequest) (llm.Message, string, llm.Usage, error) {
return accumulateStreamForTest(ctx, p.Stream, req)
}
// first returns the scope of the first model call, failing if none arrives.
func (p *scopeProbeProvider) first(t *testing.T) scopeProbe {
t.Helper()
select {
case s := <-p.seen:
return s
case <-time.After(30 * time.Second):
t.Fatal("the session never called the model")
return scopeProbe{}
}
}
// targetScopeFixture is a manager, engine and server on the test database.
type targetScopeFixture struct {
m *Manager
e *Engine
s *Server
}
func newTargetScopeFixture(t *testing.T) *targetScopeFixture {
t.Helper()
skipWithoutDSN(t)
m, err := NewManager(t.TempDir(), "")
if err != nil {
t.Fatal(err)
}
ctx, cancel := context.WithCancel(context.Background())
e := NewEngine(m)
s := &Server{m: m, engine: e, ctx: ctx, chatBusy: map[string]bool{},
chatCancel: map[string]context.CancelCauseFunc{}, taskAgents: map[string]*taskAgentBundle{}}
t.Cleanup(func() {
cancel()
_ = m.Close()
})
return &targetScopeFixture{m: m, e: e, s: s}
}
// newTask creates a task with one open goal (so the planner loop plans).
func (f *targetScopeFixture) newTask(t *testing.T) *Task {
t.Helper()
created, err := f.m.CreateTaskWithOptions("target scope probe", "probe goal", db.TaskCreateOptions{})
if err != nil {
t.Fatal(err)
}
task, ok := f.m.Task(created.ID)
if !ok {
t.Fatal("task not found after creation")
}
if _, err := task.Store.AddGoal(map[string]any{"summary": "probe goal"}, "seed"); err != nil {
t.Fatal(err)
}
return task
}
// usePlanner makes the engine resolve every task to agents driven by p.
func (f *targetScopeFixture) usePlanner(p llm.Provider) {
planner := agent.NewPlanner(p, "test-model", f.m.dir, nil, 0, 3)
worker := agent.NewWorker(p, "test-model", f.m.dir, nil, 0, 3)
f.e.SetAuthoritativeAgentResolver(func(*Task) (*agent.Planner, *agent.Worker) { return planner, worker })
}
// waitUntil polls cond until it holds, failing after 30 seconds.
func waitUntil(t *testing.T, what string, cond func() bool) {
t.Helper()
deadline := time.Now().Add(30 * time.Second)
for !cond() {
if time.Now().After(deadline) {
t.Fatalf("timed out waiting for %s", what)
}
time.Sleep(10 * time.Millisecond)
}
}
// plannerLoopRound runs the planner loop until its first round has finished and
// returns the scope that round's session carried.
func (f *targetScopeFixture) plannerLoopRound(t *testing.T, task *Task) scopeProbe {
t.Helper()
probe := newScopeProbeProvider()
f.usePlanner(probe)
ctx, stop := context.WithCancel(context.Background())
done := make(chan struct{})
go func() {
defer close(done)
f.e.plannerLoop(ctx, task)
}()
task.Notify()
got := probe.first(t)
waitUntil(t, "the planning round to finish", func() bool { return f.e.inflightCount(task.ID) == 0 })
stop()
<-done
return got
}
// finalPlannerRound runs the task-timeout settlement round and returns the scope
// its session carried.
func (f *targetScopeFixture) finalPlannerRound(t *testing.T, task *Task) scopeProbe {
t.Helper()
probe := newScopeProbeProvider()
f.usePlanner(probe)
f.e.runFinalPlannerRound(context.Background(), task, false)
return probe.first(t)
}
func (f *targetScopeFixture) mainAgentTurn(t *testing.T, task *Task) scopeProbe {
t.Helper()
probe := newScopeProbeProvider()
f.s.cfgMu.Lock()
f.s.llmOn, f.s.llmProv = true, probe
f.s.cfgMu.Unlock()
f.s.taskAgentMu.Lock()
f.s.taskAgents[task.ID] = &taskAgentBundle{main: agent.NewMainAgent(probe, "test-model", f.m.dir, nil, 0, 3)}
f.s.taskAgentMu.Unlock()
rec := httptest.NewRecorder()
f.s.chat(rec, httptest.NewRequest("POST", "/api/chat?task="+task.ID, strings.NewReader(`{"message":"status?"}`)))
if rec.Code != 202 {
t.Fatalf("chat status = %d, want 202: %s", rec.Code, rec.Body.String())
}
got := probe.first(t)
waitUntil(t, "the main-agent turn to finish", func() bool {
f.s.chatMu.Lock()
defer f.s.chatMu.Unlock()
return !f.s.chatBusy[task.ID]
})
return got
}
func (f *targetScopeFixture) workerIntent(t *testing.T, task *Task) scopeProbe {
t.Helper()
probe := newScopeProbeProvider()
if _, err := task.Store.AddIntent(map[string]any{"summary": "scope probe"}, 1, nil, "planner"); err != nil {
t.Fatal(err)
}
intent, token := f.e.claimNext(task, "work#1")
if intent == nil {
t.Fatal("no intent claimed")
}
worker := agent.NewWorker(probe, "test-model", f.m.dir, nil, 0, 3)
f.e.runIntent(context.Background(), task, "work#1", worker, intent, token, "", "")
return probe.first(t)
}
func (f *targetScopeFixture) conversationTurn(t *testing.T) (scopeProbe, int64) {
t.Helper()
probe := newScopeProbeProvider()
conv, err := f.m.pg.CreateConversation("assistant", "target scope probe", nil)
if err != nil {
t.Fatal(err)
}
t.Cleanup(func() { _ = f.m.pg.DeleteConversation(conv.ID) })
f.s.cfgMu.Lock()
f.s.chatAgent = agent.NewChatAgent(probe, "test-model", f.m.dir, nil, 10000)
f.s.cfgMu.Unlock()
busyKey := f.s.convBusyKey(conv.ID)
ctx, cancel := f.s.conversationRunContext(conv.ID, busyKey)
f.s.runConversationTurn(ctx, cancel, conv, "hello", busyKey)
return probe.first(t), conv.ID
}
// auditedTools lists the tool names in a guard's audit ring.
func auditedTools(g *guard.Guard) []string {
var tools []string
for _, e := range g.Audit() {
tools = append(tools, e.Tool)
}
return tools
}
// The five session entry points — planner round, final planner round, main-agent
// turn, worker intent, conversation turn (chat and retester share it) — each run
// on a context carrying the scope the gate will decide on, with the gate off.
// The planner and the main agent hand their tool calls to Task.TargetGuard, the
// worker to Task.Guard. The target-only guard keeps no record, so the test puts
// a recording guard in its place.
func TestEveryAgentKindCarriesTargetScope(t *testing.T) {
f := newTargetScopeFixture(t)
taskSites := []struct {
name string
run func(*testing.T, *Task) scopeProbe
wait time.Duration
targetOnly bool // the session runs on Task.TargetGuard, not Task.Guard
}{
{"planner round", f.plannerLoopRound, intercept.DefaultTargetWaitBound, true},
{"final planner round", f.finalPlannerRound, 0, true},
{"main-agent turn", f.mainAgentTurn, intercept.DefaultTargetWaitBound, true},
{"worker intent", f.workerIntent, intercept.DefaultTargetWaitBound, false},
}
for _, site := range taskSites {
t.Run(site.name, func(t *testing.T) {
task := f.newTask(t)
recorder := guard.New()
task.TargetGuard = recorder
got := site.run(t, task)
onTarget, onMain := auditedTools(recorder), auditedTools(task.Guard)
if site.targetOnly && (len(onTarget) != 1 || onTarget[0] != "LS" || len(onMain) != 0) {
t.Fatalf("tool calls seen by TargetGuard=%v Guard=%v, want one LS on TargetGuard only", onTarget, onMain)
}
if !site.targetOnly && (len(onMain) != 1 || onMain[0] != "LS" || len(onTarget) != 0) {
t.Fatalf("tool calls seen by TargetGuard=%v Guard=%v, want one LS on Guard only", onTarget, onMain)
}
if !got.ok || got.scope.TaskID != task.ID || got.scope.ConversationID != 0 {
t.Fatalf("scope = %+v (present=%v), want task %s", got.scope, got.ok, task.ID)
}
if got.scope.WaitBound != site.wait {
t.Fatalf("wait bound = %v, want %v", got.scope.WaitBound, site.wait)
}
if got.scope.Enabled == nil || got.scope.Enabled() {
t.Fatal("the gate must be off: the task did not opt in")
}
if got.scope.Interceptor != f.m.interceptor {
t.Fatal("the scope does not carry the interceptor that owns the gate")
}
})
}
t.Run("conversation turn", func(t *testing.T) {
got, convID := f.conversationTurn(t)
if !got.ok || got.scope.ConversationID != convID || got.scope.TaskID != "" {
t.Fatalf("scope = %+v (present=%v), want conversation %d", got.scope, got.ok, convID)
}
if got.scope.WaitBound != intercept.DefaultTargetWaitBound {
t.Fatalf("wait bound = %v, want %v", got.scope.WaitBound, intercept.DefaultTargetWaitBound)
}
if got.scope.Enabled == nil || got.scope.Enabled() {
t.Fatal("the gate must be off: the conversation did not opt in")
}
if got.scope.Interceptor != f.m.interceptor {
t.Fatal("the scope does not carry the interceptor that owns the gate")
}
})
}
// The final settlement round runs on a context a pause cannot cancel and is
// meant to judge, not to explore: a gated call must never wait there. A regular
// round of the same task keeps the default bound.
func TestFinalPlannerRoundHasZeroWait(t *testing.T) {
f := newTargetScopeFixture(t)
task := f.newTask(t)
regular := f.plannerLoopRound(t, task)
final := f.finalPlannerRound(t, task)
if !regular.ok || !final.ok {
t.Fatalf("scope missing: regular=%v final=%v", regular.ok, final.ok)
}
if regular.scope.WaitBound <= 0 {
t.Fatalf("regular round wait bound = %v, want a positive bound", regular.scope.WaitBound)
}
if final.scope.WaitBound != 0 {
t.Fatalf("final round wait bound = %v, want 0", final.scope.WaitBound)
}
if final.scope.TaskID != task.ID {
t.Fatalf("final round scope task = %q, want %s", final.scope.TaskID, task.ID)
}
}
// With the gate off (the task default) the target-only hooks are a no-op: a call is
// allowed and nothing is written — no intercept row, no audit-ring entry. The
// control runs the same call through the task's full Guard, where a deny rule
// blocks it and logs a row, so the rule and the row count are known to be live.
func TestTargetGateSeamAllowsWithoutDBWrite(t *testing.T) {
f := newTargetScopeFixture(t)
task := f.newTask(t)
ic := f.m.interceptor
priorTools, err := ic.GetEnabledTools()
if err != nil {
t.Fatal(err)
}
t.Cleanup(func() { _ = ic.SetEnabledTools(priorTools) })
if err := ic.SetEnabledTools([]string{"Bash"}); err != nil {
t.Fatal(err)
}
const sentinel = "ARTEX_TARGET_SEAM_PROBE"
rule, err := f.m.pg.CreateInterceptRule("target seam probe", "tool_input", "string", sentinel, "deny", "", 1000000, true, false, 0, "deny")
if err != nil {
t.Fatal(err)
}
t.Cleanup(func() {
_ = f.m.pg.DeleteInterceptRule(rule.ID)
_, _ = f.m.pg.Exec(`DELETE FROM intercept_pending WHERE task_id=$1`, task.ID)
ic.Invalidate()
})
ic.Invalidate()
rows := func() int {
t.Helper()
var n int
if err := f.m.pg.QueryRow(`SELECT count(*) FROM intercept_pending WHERE task_id=$1`, task.ID).Scan(&n); err != nil {
t.Fatal(err)
}
return n
}
ctx := intercept.WithTaskContext(context.Background(), task.ID, "planner", nil)
ctx = intercept.WithTargetScope(ctx, task.targetScope(intercept.DefaultTargetWaitBound))
input := []byte(`{"command":"echo ` + sentinel + `"}`)
if block, _, _ := task.Guard.Hooks().PreToolUse(ctx, "Bash", input); !block {
t.Fatal("control: the full guard was expected to deny the call")
}
if n := rows(); n != 1 {
t.Fatalf("control: the full guard logged %d intercept rows, want 1", n)
}
ring := len(task.Guard.Audit())
block, msg, updated := task.TargetGuard.Hooks().PreToolUse(ctx, "Bash", input)
if block || msg != "" || updated != nil {
t.Fatalf("target-only hooks: block=%v msg=%q updated=%q, want the call allowed untouched", block, msg, updated)
}
task.TargetGuard.Hooks().PostToolUse(ctx, "Bash", input, []byte(`"ok"`), false)
if n := rows(); n != 1 {
t.Fatalf("target-only hooks changed the intercept rows: %d, want 1", n)
}
if n := len(task.TargetGuard.Audit()); n != 0 {
t.Fatalf("target-only guard wrote %d audit entries, want none", n)
}
if n := len(task.Guard.Audit()); n != ring {
t.Fatalf("the task's audit ring grew from %d to %d entries", ring, n)
}
}