p3: search API, pinned sources, cache, CLI

POST /v1/search and /v2/search fan in SearXNG, Brave LLM Context, and
Tavily from config-fixed endpoints. Public sources refuse private A
records; SearXNG is a loopback-only client, not the fetch guard.

Cache keys include caller class. Restricted callers search like the
fleet; logs omit query, hosts, URLs, and upstream errors. Degraded
results are not stored. Tavily sends search_depth=basic and drops
answer. Missing keys surface in /healthz.

Default-on sources stay off until the bake-off. Query harvest is not
in this commit.
This commit is contained in:
2026-09-23 12:17:51 -07:00
parent 3687636ed7
commit d7873403ff
27 changed files with 2361 additions and 21 deletions
+147
View File
@@ -0,0 +1,147 @@
package api
import (
"encoding/json"
"net/http"
"strings"
"git.wntrmute.dev/kyle/sift/internal/auth"
"git.wntrmute.dev/kyle/sift/internal/search"
)
type v1SearchReq struct {
Query string `json:"query"`
Question string `json:"question"`
K int `json:"k"`
Rerank *bool `json:"rerank"`
Digest bool `json:"digest"`
URL string `json:"url"`
Limit int `json:"limit"`
}
type v2SearchReq struct {
Query string `json:"query"`
Limit int `json:"limit"`
URL string `json:"url"`
Digest bool `json:"digest"`
}
func (s *Server) v1search(w http.ResponseWriter, r *http.Request) {
s.handleSearch(w, r, false)
}
func (s *Server) v2search(w http.ResponseWriter, r *http.Request) {
s.handleSearch(w, r, true)
}
func (s *Server) handleSearch(w http.ResponseWriter, r *http.Request, v2 bool) {
s.reqN.Add(1)
c := s.caller(w, r)
if c == nil {
return
}
dec := json.NewDecoder(r.Body)
query := ""
k := 0
doRerank := true
digest := false
if v2 {
var req v2SearchReq
if err := dec.Decode(&req); err != nil && err.Error() != "EOF" {
writeErr(w, 400, "invalid query", "")
return
}
query = req.Query
k = req.Limit
digest = req.Digest
_ = req.URL
} else {
var req v1SearchReq
if err := dec.Decode(&req); err != nil && err.Error() != "EOF" {
writeErr(w, 400, "invalid query", "")
return
}
query = req.Query
k = req.K
if k == 0 {
k = req.Limit
}
if req.Rerank != nil {
doRerank = *req.Rerank
}
digest = req.Digest
_ = req.URL
_ = req.Question
}
if msg := search.ValidateQuery(query); msg != "" {
writeErr(w, 400, msg, "")
return
}
defK := search.DefaultK
if v2 {
defK = search.DefaultV2K
}
k = search.ClampK(k, defK)
if s.Search == nil {
writeErr(w, 422, "no search results", "")
return
}
res := s.Search.Run(r.Context(), strings.TrimSpace(query), k, doRerank, c.Name, s.callerClass(c))
warns := append([]string(nil), res.Warnings...)
if digest {
warns = append(warns, "digest ignored")
}
if !res.Cached && len(res.SourcesOK) == 0 && len(res.Hits) == 0 {
writeErr(w, 422, "no search results", "")
return
}
s.logSearch(c, query, res)
if v2 {
web := make([]map[string]any, 0, len(res.Hits))
for i, h := range res.Hits {
web = append(web, map[string]any{
"url": h.URL,
"title": h.Title,
"description": h.Snippet,
"position": i + 1,
})
}
writeJSON(w, 200, map[string]any{"success": true, "data": map[string]any{"web": web}})
return
}
results := make([]map[string]any, 0, len(res.Hits))
for _, h := range res.Hits {
results = append(results, map[string]any{
"url": h.URL,
"title": h.Title,
"snippet": h.Snippet,
"score": h.Score,
"source": h.Source,
})
}
writeJSON(w, 200, map[string]any{
"results": results,
"warnings": warns,
"sizes": map[string]any{
"results": len(results),
"sources_ok": res.SourcesOK,
"sources_failed": res.SourcesFailed,
},
"timings": map[string]any{"search_ms": res.SearchMS, "rerank_ms": res.RerankMS},
"cached": res.Cached,
})
}
func (s *Server) logSearch(c *auth.Caller, query string, res search.RunResult) {
qLen := len([]rune(query))
cache := "miss"
if res.Cached {
cache = "hit"
}
src := strings.Join(res.Attempted, ",")
if s.restrictedLog(c) {
s.Log.Info("search", "caller", c.Name, "q_len", qLen, "sources", src, "n", len(res.Hits), "cache", cache)
return
}
s.Log.Info("search", "caller", c.Name, "q_len", qLen, "sources", src, "n", len(res.Hits), "cache", cache, "rerank_ms", res.RerankMS)
}