d82cef46b4
executus CI / test (push) Failing after 1m4s
Security (all 3 models — HIGH): audit OnTool persisted raw tool args + results verbatim for the very tools the OnStep narration-redaction flags as secret (mcp_call/email_send/http_*) — the args/results are what CARRY the secret, so they landed in skill_run_logs unredacted. Factored the predicate into isSecretTool() (single source of truth) and OnTool now emits args_redacted/result_redacted (+ lengths) for secret tools. Test asserts no secret reaches the log. (persona) webhook_ip_allowlist entries are now CIDR/IP-validated at load (malformed dropped + warned) instead of accepted raw. Contract correctness (glm-5.2 + deepseek) — audit Memory now honors its documented Storage contract: ListChildrenByParent/ListFinishedRunsBefore return oldest-first; WalkParentChain returns root-first and honors MaxParentChainDepth; ListRunsFiltered clamps limit (<=0 or >500 -> 50); ListFinishedRunsBefore with limit<=0 returns none; an explicit RunFilter.Status (incl. "dry_run") matches regardless of IncludeDryRun; LastRunBySkills counts only status=="ok" unless includeFailed. (PurgeOlderThan's FinishedAt key is the SAFE behavior — in-flight runs retained — so the doc was aligned to it, not the impl.) Error-handling: appendLog now uses a bounded context (auditAppendTimeout=3s) so a hung backend can't block the run goroutine on the hot path; Sink.StartRun logs its (still best-effort) failure instead of swallowing it; budget Memory.Get uses RLock (RWMutex); budget package doc fixed (was skillexec's); Check uses the budgetWindow constant, not a duplicated literal. Triaged false-positive: NewNoOpBudget returning BudgetTracker is assignable to run.Budget (identical method sets) — no change needed. Core go.sum still free of host/DB deps. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
170 lines
6.2 KiB
Go
170 lines
6.2 KiB
Go
// Package budget gates and meters per-caller resource use over a rolling
|
|
// 7-day window (run.Ports.Budget). DBBudget is the durable tracker; NoOpBudget
|
|
// disables metering; the BudgetStorage seam backs it (Memory / contrib SQLite).
|
|
// loop (gitea.stevedudenhoeffer.com/steve/majordomo/agent).
|
|
//
|
|
// Why: a Skill is data; the executor turns data into a running agent
|
|
// (resolve model, build toolbox, start audit, run the agent loop,
|
|
// finish audit, deliver).
|
|
package budget
|
|
|
|
import (
|
|
"context"
|
|
"errors"
|
|
"fmt"
|
|
"log/slog"
|
|
"time"
|
|
)
|
|
|
|
// BudgetTracker enforces per-user GPU budgets in v2. v1 ships
|
|
// NoOpBudget which always allows. The interface exists now so the v2
|
|
// migration is a single line in the executor.
|
|
//
|
|
// Why interface now: the executor's Check/Commit calls would need to
|
|
// be added in v2 anyway; doing it now means v2 only swaps NoOp for
|
|
// DBBudget without touching call sites.
|
|
type BudgetTracker interface {
|
|
// Check reports whether the caller has remaining budget. Returns
|
|
// nil for "yes" or an error describing the exhaustion.
|
|
Check(ctx context.Context, callerID string) error
|
|
|
|
// Commit records that the caller spent runtimeSeconds of budget on
|
|
// this run. Called after the agent completes (success or error).
|
|
Commit(ctx context.Context, callerID string, runtimeSeconds float64)
|
|
}
|
|
|
|
// NoOpBudget always allows and never records. v1 default.
|
|
type NoOpBudget struct{}
|
|
|
|
// NewNoOpBudget constructs the no-op tracker.
|
|
func NewNoOpBudget() BudgetTracker { return NoOpBudget{} }
|
|
|
|
// Check always returns nil.
|
|
func (NoOpBudget) Check(_ context.Context, _ string) error { return nil }
|
|
|
|
// Commit is a no-op.
|
|
func (NoOpBudget) Commit(_ context.Context, _ string, _ float64) {}
|
|
|
|
// ErrBudgetExceeded is returned by DBBudget.Check when the caller's
|
|
// 7-day rolling window has hit the convar-configured cap.
|
|
//
|
|
// Why a sentinel: callers (executor, audit writer) need to distinguish
|
|
// budget rejection from generic errors so they can record
|
|
// status="budget_exceeded" instead of "error" and skip user-visible
|
|
// delivery side-effects.
|
|
var ErrBudgetExceeded = errors.New("weekly skill budget exceeded")
|
|
|
|
// BudgetNotifier is the optional callback DBBudget invokes when a
|
|
// Check rejects a caller. Production wires a Discord-DM hook so the
|
|
// user knows why their skill failed; tests inject a recorder.
|
|
//
|
|
// nil is allowed and is silently skipped.
|
|
type BudgetNotifier func(ctx context.Context, userID string, secondsUsed, cap float64)
|
|
|
|
// DBBudget enforces per-user weekly GPU budgets via the BudgetStorage
|
|
// interface. The "weekly" cap is a rolling 7-day window — see
|
|
// SkillBudget for the rollover semantics.
|
|
//
|
|
// Why a closure for the limit instead of an int field: the cap comes
|
|
// from a runtime convar. Reading it on every Check means a `.convar
|
|
// set skills.user_budget_seconds_per_week 7200` takes effect on the
|
|
// next call without restarting the bot or rewiring the executor.
|
|
type DBBudget struct {
|
|
storage BudgetStorage
|
|
// weeklyLimit returns the current cap in seconds. Reads convar at
|
|
// every Check so a runtime convar bump takes effect on the next
|
|
// call.
|
|
weeklyLimit func() float64
|
|
|
|
// notify is called when a Check rejects a caller. Optional —
|
|
// production wires a Discord-DM hook so the user knows why their
|
|
// skill failed. nil-safe.
|
|
notify BudgetNotifier
|
|
|
|
// now is the time source. Test injects a fake clock; production
|
|
// uses time.Now.
|
|
now func() time.Time
|
|
}
|
|
|
|
// NewDBBudget constructs a DBBudget. now may be nil — defaults to
|
|
// time.Now.
|
|
//
|
|
// Why time injection: budget rollover is time-sensitive; tests need to
|
|
// fast-forward past the 7-day boundary deterministically. now=nil
|
|
// means production callers (mort.go) don't have to think about it.
|
|
//
|
|
// Test: pass a closure that returns a fixed instant; assert rollover
|
|
// only happens when (now - WindowStart) >= 7 days.
|
|
func NewDBBudget(storage BudgetStorage, weeklyLimit func() float64, notify BudgetNotifier, now func() time.Time) *DBBudget {
|
|
if now == nil {
|
|
now = time.Now
|
|
}
|
|
return &DBBudget{
|
|
storage: storage,
|
|
weeklyLimit: weeklyLimit,
|
|
notify: notify,
|
|
now: now,
|
|
}
|
|
}
|
|
|
|
// Check returns ErrBudgetExceeded if the caller has spent at least
|
|
// weeklyLimit seconds in the current rolling 7-day window.
|
|
//
|
|
// Why anonymous callerID="" is unbudgeted: scheduler-driven and
|
|
// system-initiated runs don't have a Discord user to bill; charging
|
|
// "system" would conflate them with a real user. The scheduler sets
|
|
// CallerID to the skill owner where applicable, so cron-loop
|
|
// abusiveness still consumes the owner's budget.
|
|
//
|
|
// Why cap<=0 means "disabled": operator wants a runtime kill-switch.
|
|
// Setting the convar to "0" turns enforcement off without restart.
|
|
//
|
|
// Test: Get returns nil → Check returns nil; Get returns row with
|
|
// SecondsUsed >= cap → Check returns ErrBudgetExceeded and notify is
|
|
// invoked; window expired (>=7d) → Check returns nil regardless of
|
|
// SecondsUsed.
|
|
func (b *DBBudget) Check(ctx context.Context, callerID string) error {
|
|
if callerID == "" {
|
|
return nil
|
|
}
|
|
bud, err := b.storage.Get(ctx, callerID)
|
|
if err != nil {
|
|
return fmt.Errorf("budget: %w", err)
|
|
}
|
|
if bud != nil {
|
|
if b.now().Sub(bud.WindowStart) < budgetWindow {
|
|
cap := b.weeklyLimit()
|
|
if cap > 0 && bud.SecondsUsed >= cap {
|
|
if b.notify != nil {
|
|
b.notify(ctx, callerID, bud.SecondsUsed, cap)
|
|
}
|
|
return ErrBudgetExceeded
|
|
}
|
|
}
|
|
}
|
|
return nil
|
|
}
|
|
|
|
// Commit records the run's runtime against the caller's budget.
|
|
// Failures are logged but never returned — budget accounting must
|
|
// not break user-visible execution.
|
|
//
|
|
// Why callerID="" is a no-op: matches Check's anonymous-caller
|
|
// shortcut; system runs don't get billed.
|
|
//
|
|
// Why runtimeSeconds<=0 is a no-op: a run that errored before
|
|
// resolving a model has wallSecs near 0 in floating-point terms but
|
|
// can also be exactly 0 (synthetic test fixtures). Skipping avoids
|
|
// spurious 0-runs rows from short-lived failures.
|
|
//
|
|
// Test: Commit(50) → Get reports SecondsUsed=50; storage failure
|
|
// surfaces only as a slog.Warn (no panic, no return).
|
|
func (b *DBBudget) Commit(ctx context.Context, callerID string, runtimeSeconds float64) {
|
|
if callerID == "" || runtimeSeconds <= 0 {
|
|
return
|
|
}
|
|
if err := b.storage.Add(ctx, callerID, runtimeSeconds, b.now()); err != nil {
|
|
slog.Warn("skills budget: commit failed", "user", callerID, "error", err)
|
|
}
|
|
}
|