jcoffey-dev
7d316f92db
Adds a self-hosted (Ollama, qwen2.5-coder) model provider abstraction with a pluggable opt-in cloud adapter, schema grounding, and a shared cost/safety guard every AI-suggested query is assessed against -- compiling to and executing through the same unchanged Phase 2 IR/ compiler and Phase 4 tenant scoping as a hand-written query, no parallel execution path. Track A (built into the query bar): inline ghost-text autocomplete, "Explain this query", "Fix this query" with a diff view, and a rule-based "Optimize" suggestion. Track B: natural-language-to-query translation, always a separate review step from execution, with `sentryctl query --nl` requiring explicit confirmation to run. Every accepted/dismissed translate-fix-optimize interaction is logged into the same append-only audit_log table Phase 4 built. Two real product bugs were found and fixed via live browser verification (a Svelte effect re-running on every keystroke that silently cancelled the ghost-text debounce; a ghost-text widget positioned at document offset 0 instead of the cursor), and a real costguard logic bug (unbounded-aggregation vs. raw-row) was caught by its own test suite. New integration tests wire a real Ollama client through the real HTTP handler against a mock server matching Ollama's wire contract (hack/mock-ollama), keeping model-quality verification out of CI as a disclosed, periodic human-run check instead. See /docs/phase-7-ai-design.md and /docs/phase-7-runbook.md.
101 lines
3.0 KiB
Go
101 lines
3.0 KiB
Go
package costguard
|
|
|
|
import (
|
|
"testing"
|
|
"time"
|
|
|
|
"github.com/sentry/sentry/api/internal/querylang/ir"
|
|
)
|
|
|
|
// A raw-row (non-aggregation) query with no time range and no explicit
|
|
// Limit still gets executor/sql.go's defaultRowLimit=100 safety net
|
|
// applied automatically -- so this is a Warn (a possibly-expensive scan
|
|
// to find those 100 rows), not a Reject (genuinely unbounded output),
|
|
// which only an unbounded *aggregation* actually is. See the case
|
|
// immediately below for that contrast.
|
|
func TestAssessNoTimeRangeNoLimitRawRowWarns(t *testing.T) {
|
|
plan := &ir.Plan{Filters: []ir.FilterPredicate{{Field: "service", Op: "=", Value: "api"}}}
|
|
got := Assess(plan)
|
|
if got.Level != LevelWarn {
|
|
t.Errorf("Level = %v, want warn (executor applies a default row limit even with no explicit Limit)", got.Level)
|
|
}
|
|
if len(got.Reasons) == 0 {
|
|
t.Error("expected at least one reason")
|
|
}
|
|
}
|
|
|
|
func TestAssessNoTimeRangeWithAggregationRejects(t *testing.T) {
|
|
plan := &ir.Plan{
|
|
TimeRange: &ir.TimeRange{},
|
|
Aggregation: &ir.Aggregation{Funcs: []ir.AggFunc{{Func: "count", Alias: "count"}}},
|
|
}
|
|
got := Assess(plan)
|
|
if got.Level != LevelReject {
|
|
t.Errorf("Level = %v, want reject for an unbounded aggregation", got.Level)
|
|
}
|
|
}
|
|
|
|
func TestAssessNoTimeRangeWithLimitWarns(t *testing.T) {
|
|
plan := &ir.Plan{
|
|
TimeRange: &ir.TimeRange{},
|
|
Limit: &ir.Limit{N: 100},
|
|
}
|
|
got := Assess(plan)
|
|
if got.Level != LevelWarn {
|
|
t.Errorf("Level = %v, want warn (limited, no aggregation)", got.Level)
|
|
}
|
|
}
|
|
|
|
func TestAssessBoundedTimeRangeIsOK(t *testing.T) {
|
|
now := time.Now()
|
|
plan := &ir.Plan{
|
|
TimeRange: &ir.TimeRange{From: now.Add(-1 * time.Hour), To: now},
|
|
Limit: &ir.Limit{N: 100},
|
|
}
|
|
got := Assess(plan)
|
|
if got.Level != LevelOK {
|
|
t.Errorf("Level = %v, want ok, reasons: %v", got.Level, got.Reasons)
|
|
}
|
|
}
|
|
|
|
func TestAssessVeryLargeTimeRangeWarns(t *testing.T) {
|
|
now := time.Now()
|
|
plan := &ir.Plan{
|
|
TimeRange: &ir.TimeRange{From: now.Add(-200 * 24 * time.Hour), To: now},
|
|
Limit: &ir.Limit{N: 100},
|
|
}
|
|
got := Assess(plan)
|
|
if got.Level != LevelWarn {
|
|
t.Errorf("Level = %v, want warn for a 200-day range", got.Level)
|
|
}
|
|
}
|
|
|
|
func TestAssessRawSQLWithTimestampFilterIsOK(t *testing.T) {
|
|
plan := &ir.Plan{RawSQL: "SELECT count(*) FROM logs WHERE timestamp > now() - INTERVAL 1 HOUR"}
|
|
got := Assess(plan)
|
|
if got.Level != LevelOK {
|
|
t.Errorf("Level = %v, want ok, reasons: %v", got.Level, got.Reasons)
|
|
}
|
|
}
|
|
|
|
func TestAssessRawSQLWithoutTimestampFilterWarns(t *testing.T) {
|
|
plan := &ir.Plan{RawSQL: "SELECT service, count(*) FROM logs GROUP BY service"}
|
|
got := Assess(plan)
|
|
if got.Level != LevelWarn {
|
|
t.Errorf("Level = %v, want warn for raw SQL with no detectable time filter", got.Level)
|
|
}
|
|
}
|
|
|
|
func TestSummaryEmptyForOK(t *testing.T) {
|
|
if s := Summary(Assessment{Level: LevelOK}); s != "" {
|
|
t.Errorf("Summary(OK) = %q, want empty", s)
|
|
}
|
|
}
|
|
|
|
func TestSummaryJoinsReasons(t *testing.T) {
|
|
a := Assessment{Level: LevelWarn, Reasons: []string{"a", "b"}}
|
|
if s := Summary(a); s != "a; b" {
|
|
t.Errorf("Summary = %q, want %q", s, "a; b")
|
|
}
|
|
}
|