Files
kyleandornith-1.5-35b-a3b 7e78de633f P5a: digests cite pages; sift_pdf_* metrics; sift fetch --pages/--grep; skill, unit and README
Digest systemPrompt gains a page-cite instruction and PromptVersion is 3.
Add the sift_pdf_* metric series (extract_total{outcome}, extract_seconds,
pages_total, pool_wait_seconds, cache_hits_total) to internal/metrics and wire
ObservePDF/ObservePDFWait/PDFCacheHit into internal/api/pdf.go. Refactor
cmd/sift/fetchcmd.go to a fetchOpts struct with parseFetchOpts and fetchBody,
adding --pages/--grep. Update skill/SKILL.md, set nix MemoryMax to 1G, and add a
PDF documents section to the README.

Co-Authored-By: ornith-1.5-35b-a3b <ornith-1.5-35b-a3b@llama.cpp.invalid>
2026-09-26 04:36:49 -07:00

50 lines
1.3 KiB
Go

package metrics
// P5a task 07: the sift_pdf_* series.
import (
"io"
"net/http/httptest"
"strings"
"testing"
"time"
)
type zeroSrc struct{}
func (zeroSrc) Snapshot() Snapshot { return Snapshot{} }
func TestPDFSeries(t *testing.T) {
s := New(zeroSrc{})
s.ObservePDF("ok", 1500*time.Millisecond, 212)
s.ObservePDF("ok", 200*time.Millisecond, 3)
s.ObservePDF("no_text", 50*time.Millisecond, 0)
s.ObservePDF("blocked: evil.example", time.Millisecond, 0) // raw text never becomes a label
s.ObservePDFWait(2 * time.Second)
s.PDFCacheHit()
s.PDFCacheHit()
req := httptest.NewRequest("GET", "/metrics", nil)
req.RemoteAddr, req.Host = "127.0.0.1:9", "127.0.0.1:8890"
rec := httptest.NewRecorder()
s.Handler().ServeHTTP(rec, req)
body, _ := io.ReadAll(rec.Body)
out := string(body)
for _, want := range []string{
`sift_pdf_extract_total{outcome="ok"} 2`,
`sift_pdf_extract_total{outcome="no_text"} 1`,
`sift_pdf_extract_total{outcome="other"} 1`,
`sift_pdf_pages_total 215`,
`sift_pdf_cache_hits_total 2`,
`sift_pdf_extract_seconds_count 4`,
`sift_pdf_pool_wait_seconds_count 1`,
} {
if !strings.Contains(out, want) {
t.Errorf("metrics lack %q", want)
}
}
if strings.Contains(out, "evil.example") {
t.Error("a raw outcome string leaked into a label")
}
}