Compare commits

..
Author SHA1 Message Date
eSlider 515088f4e1 feat: escalate brain search to web when facts cannot confirm
Tests / Test (push) Skipped
Tests / Release (semver) (push) Skipped
2026-08-13 20:23:07 +01:00
eSliderandGitHub 368a757612 feat: Go SearXNG client; throttled is not absence (#16)
Tests / Test (push) Failing after 4s
Tests / Release (semver) (push) Skipped
2026-08-13 19:53:31 +01:00
eSliderandGitHub a8675ac33b feat: read git history with go-git, not the git binary (#15)
Tests / Test (push) Failing after 5s
Tests / Release (semver) (push) Skipped
2026-08-13 18:07:56 +01:00
eSliderandGitHub de632ba6cc docs: delete agent-cost; rename kb-search skill to brain (#14)
Tests / Test (push) Failing after 5s
Tests / Release (semver) (push) Skipped
* docs: delete agent-cost; rename kb-search skill to brain.

bin/agents/cost does not exist. CI unittest now fails if a SKILL.md names a
missing bin/ path.

* test: gate SKILL.md bin/ paths; name the brain skill brain.

Follow-up to the agent-cost delete: unittest fails if a skill names a missing
tool. Frontmatter name is brain, not kb-search.
2026-08-13 17:55:41 +01:00
eSliderandGitHub 66c87842e2 feat: in-process HTTP search; /get /stats /audit /ingest. (#13)
Tests / Test (push) Failing after 5s
Tests / Release (semver) (push) Skipped
bin/brain/serve.go (ladybug tags) calls internal/brain instead of exec.
HTTP tests inject a fake API so CI stays cgo-free. ExecSearcher remains
the fallback when the binary is built without system_ladybug.
2026-08-13 17:52:15 +01:00
eSliderandGitHub 20b78a9a20 feat: brain/index.go shebang; mail import is not a brain write (D14). (#12)
Tests / Test (push) Failing after 5s
Tests / Release (semver) (push) Skipped
Commands live at bin/brain/{index,get,stats,eval,watch}.go and
bin/mail/import.go, bin/markdown/import.go, bin/postgres/query.go.
Python remains the Ladybug write worker. index_mail is a deprecation
shim that rebuilds via --with-mail.
2026-08-13 17:46:25 +01:00
eSliderandGitHub 5d4b3427a4 refactor: chats method shebangs; drop chats index (D14). (#11)
Tests / Test (push) Failing after 5s
Tests / Release (semver) (push) Skipped
Parsers and commands live in internal/chats. bin/chats/{sync,import,facts,apply}.go
are tagged shebang mains. Brain ingest is not a chats command.
2026-08-13 17:31:03 +01:00
eSliderandGitHub 1c7db6d499 docs: name bin/brain/search.go; --hop is not a graph walk. (#10)
Tests / Test (push) Failing after 6s
Tests / Release (semver) (push) Skipped
Published docs and skills still taught bin/kb/search --hop 1. Search lives
at bin/brain/search.go; --hop errors until File edges exist. A unittest
gates the SoT so the lie cannot return.
2026-08-13 17:23:40 +01:00
eSliderandGitHub 0786ddcb06 feat: bin/brain/serve.go; search backend is Go not Python (#9)
Tests / Test (push) Failing after 5s
Tests / Release (semver) (push) Skipped
* feat(brain): HTTP serve from bin/brain/serve.go, default Go search binary.

Move the HTTP package to internal/httpapi. Default backend is
var/bin/brain-search, not Python. bin/serve.go stays as a deprecation shim.

* feat(httpapi): default search backend is var/bin/brain-search.

bin/brain/serve.go is the command; bin/serve.go stays as a tagged
deprecation shim. Tests fail if the default path still names Python.
2026-08-13 14:32:21 +01:00
eSliderandGitHub eeb5b79cf2 refactor: one Go module; brain search in bin/brain + internal/brain. (#8)
Tests / Test (push) Failing after 5s
Tests / Release (semver) (push) Skipped
Collapse nested kbsearch/chats go.mod into the root module. Ranking stays
cgo-free under internal/brain/rank so CI does not need ladybug. bin/kb/search
is a deprecation wrapper that still sets CGO and builds the binary.
2026-08-13 14:26:54 +01:00
eSliderandGitHub 5990feb1f6 docs: point issues at Gitea origin (D15). (#7)
Tests / Test (push) Failing after 4s
Tests / Release (semver) (push) Skipped
GitHub stays the public clone for PRs and Actions. Work board is
https://git.produktor.io/eSlider/2dph/issues.
2026-08-13 14:11:00 +01:00
eSliderandGitHub d27a738fee feat(chats): parse LinkedIn MCP v4.22 inbox/conversation blobs. (#6)
Tests / Test (push) Failing after 29s
Tests / Release (semver) (push) Skipped
get_inbox/get_conversation return a sections+references envelope, not a
message list. Parser is covered by synthetic Alice/Bob fixtures; CI now
runs the nested bin/chats tests. Session check no longer launches Chromium.
2026-08-13 12:25:51 +01:00
eSliderandGitHub 669e184cf6 fix(kbsearch): rank FTS correctly, filter before -n, start the daemon. (#5)
Go search took worst BM25 hits (ORDER BY score), cut to -n before --root,
and never called ensureDaemon. Ranking and flag parsing move to a cgo-free
package so CI can fail those regressions without ladybug. --hop errors
instead of being swallowed into the query.
2026-08-13 12:19:26 +01:00
eSliderandGitHub ebc3f948c1 Add Gmail --query to mail/sync (default in:inbox) (#4)
* Add --query to Gmail mail/sync instead of always listing in:inbox.

Callers keep the search string; default remains in:inbox.

* Document Gmail --query on the mail/sync pipeline.

* test(mail): assert Gmail --query reaches ListIDs, not only the CLI flag.

ParseCLI coverage left a hole: an empty query still has to become in:inbox
and a custom q has to be the string the client lists with.
2026-08-13 12:19:22 +01:00
eSlider fe6a02024c feat(chats): LinkedIn source — MCP client via get_inbox + get_conversation
- LinkedInMCPSource: MCP JSON-RPC, как TelegramMCPSource
- sync linkedin --limit N: выгрузка сообщений из LinkedIn
- Проверка сессии: uvx mcp-server-linkedin --status
- Вывод инструкции если сессия истекла
- JSONL в var/chats/linkedin/<thread_id>/messages.jsonl
2026-08-13 00:10:42 +01:00
eSlider 4a065d9838 docs: add edelweiss to GitHub safety rules 2026-08-13 00:07:01 +01:00
eSlider e3c6ef5684 chore: remove edelweiss references from public repo 2026-08-13 00:06:49 +01:00
eSlider 98c14e23f1 docs: GitHub safety rules — no absolute paths, PII, secrets, curasoft 2026-08-13 00:02:09 +01:00
eSlider ff1716de40 fix: resolve plan.md conflict, remove remaining /mnt/ paths 2026-08-13 00:00:48 +01:00
eSlider fec5325c7a chore: clean absolute paths, curasoft refs, secrets from history
- bin/chats/: env-based paths, no /mnt/ /home/ hardcodes
- bin/edelweiss-pilot: remove curasoft, use DOCS_BASE env var
- bin/facts/crm: use KNOWLEDGE_MESH_SEED env var
- compose.edelweiss.yml: remove curasoft volumes, use DOCS_BASE
- docs/chat-import-plan.md: link to Gitea issue, no secrets
- bin/seed-edelweiss-facts.py: removed (curasoft-only)
2026-08-13 00:00:15 +01:00
eSlider 27d9521e7f bin/chats: Phase 1 MVP — Telegram sync/import/index/facts/apply
- bin/chats/ — nested Go module (как bin/kbsearch/)
  - sync telegram — MCP JSON-RPC клиент, 31 личный чат, 922 сообщения
  - import — конвертация JSONL → MD с YAML frontmatter
  - index — делегирует bin/kb/index --corpus (132 leafs в brain)
  - facts — regex extraction phone/email/linkedin с валидацией
    (исключены: даты, суммы, номера карт, инвойсы)
  - apply — oo CLI cross-check + dry-run
- Source interface для будущих WhatsApp/LinkedIn
- 4 system tests (import, facts, empty, roundtrip) — синтетические данные
- bin/chat — build+exec wrapper
- docs/chat-import-plan.md — прогресс, пути к env (без секретов)

Безопасность: var/ в gitignore, credentials в env, тесты без реальных данных.
2026-08-12 23:59:29 +01:00
eSlider a7cb8d4c76 docs: chat import pipeline plan — link to Gitea issue #1 2026-08-12 23:59:20 +01:00
eSliderandCursor 53cd00284d fix(kb): seed facts before CREATE indexes (FTS MERGE corruption)
Upsert under live FTS raises "document for node offset N is missing".
Add --skip-indexes; edelweiss-pilot index = write → seed → ensure_indexes.
Ship seed-edelweiss-facts.py (paired lexicon/OO/interview/QEMU facts).

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-12 16:09:02 +01:00
eSliderandCursor b73b4d4f97 fix(kb): stop DROP INDEX killing HNSW via Ladybug ghost catalog
Ladybug 0.19 DROP INDEX leaves `_0_Leaf_vec_UPPER` / `0_id_docs` in catalog so
CREATE fails while SHOW_INDEXES omits the index; create_fts_and_vector used to
swallow that. Never drop FTS/VECTOR; ensure_indexes after upserts; rebuild =
delete kb.lbug. Add compose.edelweiss.yml + regression tests.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-12 16:05:14 +01:00
eSlider 1d1f6a90ff Remove curasoft references, rename to detective method
- PLAN.md: replace 'curasoft-detective' with 'detective method'
- README.md: replace curasoft-detective link with plain reference
- test_websearch.py: fix test domain from ticket.curasoft.de to example.com
- Rewrote git history with git-filter-repo to remove all traces
2026-08-12 13:46:54 +01:00
eSlider f220bcd95a kbsearch: Go implementation with daemon model serving
- New nested module bin/kbsearch with Go implementation of bin/kb/search
- Embedding model (potion-multilingual-128M) served by localhost daemon
  so repeated CLI calls reuse the loaded model
- Bash launcher bin/kb/search builds binary on first run, caches to var/bin/
- Hybrid FTS + vector search (RRF k=60) matching Python kblib behavior
- YAML output via port of yamlout.py (ordered keys, same format)
- JSON output with proper field order
- All flags: --root, --repo, -n, --json, --list-model
- Root go.mod reverted to 1.25.0 (kbsearch is isolated nested module)
- CI passes: go test ./... and go vet ./... unaffected by kbsearch
2026-08-11 23:57:39 +01:00
eSlider 678a1d1dba feat(mail): full Gmail+OnlyOffice sync, import, and brain indexing
- bin/mail/sync.go: async Go sync engine (8 workers, paginated Gmail via
  API + OnlyOffice IMAP); Gmail attachments key off body.attachmentId, not
  MIME partId; ICS sidecars Latin-1->UTF-8 normalized (TestICSToMarkdownNormalizesLatin1)
- bin/mail/import: message.json -> markdown; PDFs via pdftotext -layout
  fast path with docling subprocess fallback for the ~5% textless files
- bin/mail/index_mail: fresh-rebuild indexer (repo corpus + mail) avoiding
  ladybug WAL corruption on bulk-insert into indexed DBs; split from import
- bin/kb/index: keep FTS/VECTOR indexes across incremental runs (drop+recreate
  leaves stale backing tables killing the vector index)
- docs: README/PLAN/AGENTS cover the mail pipeline

Result: 17,835 messages -> 28,918 info leafs, FTS+HNSW healthy.
2026-08-11 21:57:38 +01:00
eSlider 8781c0c3eb refactor(tools): bin/{subject}/{method} layout; Go serve+watch modules
Move serve/ (module) -> bin/server, tools/ -> bin/tools, replace bin/kb-watch
bash with bin/watch Go package; self-executing Go shebangs bin/serve.go and
bin/kb/watch.go; Docker + CI + git/import + docs repointed. Multi-stage image
builds static serve+watch binaries (no Go runtime in container).
2026-08-11 09:52:20 +01:00
eSlider d6b17e8819 feat(kb): CRM association proof via oo, fix ssh-tunnel self-ref + oo creds
- bin/facts/crm: prove person<->company/company<->project against ooCRM
  x corpus SoT (knowledge-mesh-seed.yaml), write 78 facts (root=facts)
- tools/crmfacts.py + test_crm_facts.py: parser under unit tests (26 pass)
- docs/crm-associations-proof.md: provable graph, mistakes, fixes
- oo merge 759->763 resolves duplicate GoldenRatio.Exchange legal entity
- bin/db/ssh-tunnel: "$0" self-check + accept-new/BatchMode ssh flags
- AGENTS.md: document bin/facts/crm
2026-08-10 23:22:34 +01:00
16 changed files with 473 additions and 16 deletions
+1
View File
@@ -81,6 +81,7 @@ bin/facts/audit ["self"|"facts"|"info"|"stale"] # 2-source + staleness gate
bin/facts/crm [--dry-run] # proof person↔company/company↔project (ooCRM × corpus SoT)
bin/kb/search "query" [--repo X] # deprecated wrapper → bin/brain/search.go
bin/brain/search.go "query" [--root facts|info] # deduction search → YAML
bin/brain/search.go "query" --no-web # local graph only
bin/brain/get.go <id> [--body]
bin/markdown/import.go [dir] # mistune leaves → YAML
bin/git/import.go [REPO] [--json] [--limit N] # go-git history → commit leafs
+1 -1
View File
@@ -40,7 +40,7 @@ detective method: **a fact needs ≥2 independent sources or it is
| D14 | tooling style | `bin/{subject}/{method}.go` shebang (e.g. `bin/brain/search.go`). Shared code in `internal/`. One root `go.mod` + `go.work`. No `bin/*/main.go`, no nested modules. |
| D15 | repo | Gitea [`eSlider/2dph`](https://git.produktor.io/eSlider/2dph) is origin + [issues](https://git.produktor.io/eSlider/2dph/issues). GitHub `eSlider/2dph` is the public clone (PRs + Actions CI). No direct `main` pushes. TDD → PR → CI green → merge. |
| D16 | contradictions | ≥2 yes vs ≥2 no → unrelated sources conflict → hypothesis → `(not confirmed)`. Resolution (authority, staleness adjudication) = **v2**, tracked as open question. |
| D17 | assertion gate | Fact-check every *claim* (facts → info → live sources → web), not every edit. Missing graph ≠ “does not exist”. |
| D17 | assertion gate | Fact-check every *claim* (facts → info → live → web), not every edit. `bin/brain/search.go` adds a `web` block when there is no facts hit (`throttled`/`skipped`/`refused` ≠ absence). `--root` and `--no-web` stay local. Missing graph ≠ “does not exist”. |
| D18 | reasoner | Pluggable OpenAI-compatible URL. RAM: Qwen3.5-9B. Quality: Bonsai-27B or Qwen3.6-27B. No official Qwen3.6-9B. |
| D19 | git history | [go-git](https://github.com/go-git/go-git) via `bin/git/import.go`. No subprocess of the git binary. Conversion prints commit leafs; brain write is `bin/brain/index.go`. |
+2 -1
View File
@@ -85,9 +85,10 @@ fact; conflicting sources or a single source → `hypothesis` → `(not confirme
## Deduction search
```bash
bin/brain/search.go "Matrix federation over HTTPS" # facts → info → web-search
bin/brain/search.go "Matrix federation over HTTPS" # facts → info → web
bin/brain/search.go "onlyoffice postgres" --root facts
bin/brain/search.go "where is cs-lexicon" --json | yq '.'
bin/brain/search.go "upstream flag" --no-web # local graph only
bin/brain/get.go <id> --body # full chunk on demand
bin/brain/stats.go # index health
bin/brain/eval.go # recall@5 gate
+1 -1
View File
@@ -3,7 +3,7 @@
//
// bin/brain/search.go - deduction search over the 2dph brain.
//
// ./bin/brain/search.go "query" [--root facts|info] [--repo P] [-n N] [--json]
// ./bin/brain/search.go "query" [--root facts|info] [--repo P] [-n N] [--json] [--no-web]
// ./bin/brain/search.go serve [port]
// ./bin/brain/search.go --list-model
//
+7
View File
@@ -59,6 +59,13 @@ class PublishedDocsTest(unittest.TestCase):
self.assertNotIn("password", settings.lower())
self.assertIn("json", settings)
def test_readme_search_escalates_web(self) -> None:
text = (ROOT / "README.md").read_text()
self.assertIn("--no-web", text)
self.assertIn("D17", (ROOT / "PLAN.md").read_text())
skill = (ROOT / "skills" / "brain" / "SKILL.md").read_text()
self.assertIn("`web` block", skill)
def test_docs_do_not_claim_hop_walks(self) -> None:
paths = [
ROOT / "README.md",
+33
View File
@@ -0,0 +1,33 @@
# CRM association proof (oo CLI ↔ corpus)
Proven with `oo` (eslider/go-onlyoffice) against the OnlyOffice portal
(`office.produktor.io`). Portal CRM is the SSOT for company ↔ person ↔
project associations; the corpus SoT (`eslider/cv/projects/knowledge-mesh-seed.yaml`)
is the second, independent source. Facts that can be backed by both are
written to the brain under `root=facts` by `bin/facts/crm`.
## What was verified
- Logical counts (portal MySQL): 1300 contacts = 897 persons + 404 companies,
198 projects, 998 deals, 939 project↔contact links.
- Every client company linked to a project has ≥1 person underneath.
- Every person `company_id` resolves to an existing company.
- Corpus org list (9) maps 1:1 onto CRM companies:
ProProdukt SL / produktor.io, Dyvenia, Immowelt AG, WhereGroup,
Keynote SIGOS, D2S/SYSTEMS, GRID, Pack und Cup, Markets Platform.
- 78 person↔company association facts written to the brain
(`how=crm-crosscheck`, `type=association`). Recall@5 in `bin/kb/eval` = 1.0.
## Mistakes found
| # | Mistake | Fix |
|---|---------|-----|
| 1 | Duplicate legal entity `GoldenRatio.Exchange` (contact 759) vs `Golden Ratio Exchange` (763); 3 deals (211, 287, 559) were linked to 759 | `oo contacts merge 759 763` — 763 kept, 759 removed, deal links re-pointed to 763 |
| 2 | `env/`-wide: OnlyOffice creds file used wrong UX (user `eslider`, password with `$2` suffix) making `oo` auth fail | `.env` fixed to `eslider@gmail.com` + clean password; `.env` stays gitignored |
## Gates after fix
- `uv run python -m unittest discover -s bin/tools -t .` → 26 tests OK
- `bin/facts/audit self` + `bin/facts/audit db` → ok
- `bin/kb/eval` → recall@5 = 1.0
- `go test ./...` (bin/server + bin/watch) → ok
+2 -1
View File
@@ -21,7 +21,8 @@ bin/brain/search.go "question"
1. facts root — confirmed answers only → return with evidence links
2. info root — supporting narrative → snippets, marked (not confirmed)
3. web-search — second independent source → upgrade hypothesis to confirmed
(`bin/web/search.go`; status `throttled` is not evidence of absence)
(`web` block from `bin/web/search.go` when no facts hit; status `throttled`
is not evidence of absence; `--no-web` / `--root` skip it)
```
`--hop` is not implemented yet (needs File/FROM_FILE edges). The flag is an
+7 -2
View File
@@ -7,6 +7,8 @@ import (
"context"
"encoding/json"
"fmt"
"github.com/eSlider/2dph/internal/brain/rank"
)
// Ready opens the Ladybug file for the life of the serve process.
@@ -17,7 +19,7 @@ func Ready() error {
// HTTP is the in-process API used by bin/brain/serve.go.
type HTTP struct{}
func (HTTP) Search(_ context.Context, query string, limit int) ([]byte, error) {
func (HTTP) Search(ctx context.Context, query string, limit int) ([]byte, error) {
hits, err := searchHits(query, "", "", limit)
if err != nil {
return nil, err
@@ -31,10 +33,13 @@ func (HTTP) Search(_ context.Context, query string, limit int) ([]byte, error) {
hits[i].Snippet = string(runes)
}
}
webOut := rank.Deduce(hits, query, "", false, func(q string) rank.SecondSource {
return lookupWeb(ctx, q)
})
var buf bytes.Buffer
enc := json.NewEncoder(&buf)
enc.SetEscapeHTML(false)
if err := enc.Encode(toJSONOut(hits, query, "")); err != nil {
if err := enc.Encode(toJSONOut(hits, query, "", webOut)); err != nil {
return nil, err
}
return buf.Bytes(), nil
+4 -1
View File
@@ -6,7 +6,7 @@ import (
"strings"
)
const Usage = `usage: bin/brain/search.go "query" [--root facts|info] [--repo REPO] [-n N] [--json]
const Usage = `usage: bin/brain/search.go "query" [--root facts|info] [--repo REPO] [-n N] [--json] [--no-web]
bin/brain/search.go serve [port]
bin/brain/search.go --list-model`
@@ -17,6 +17,7 @@ type Options struct {
Limit int
JSONOut bool
ListModel bool
NoWeb bool
}
// ParseArgs reads flags. Unknown flags are an error: silently dropping them
@@ -54,6 +55,8 @@ func ParseArgs(args []string) (Options, error) {
return opt, fmt.Errorf("--hop is not implemented yet (needs File/FROM_FILE edges)")
case "--json":
opt.JSONOut = true
case "--no-web":
opt.NoWeb = true
case "--list-model":
opt.ListModel = true
default:
+43
View File
@@ -0,0 +1,43 @@
package rank
// SecondSource is the web-search block on a deduction answer.
// Kept apart from graph hits so "ours" and "not ours" stay visible.
type SecondSource struct {
Status string `json:"status"`
Note string `json:"note,omitempty"`
Cached bool `json:"cached,omitempty"`
Results []SecondSourceHit `json:"results,omitempty"`
}
type SecondSourceHit struct {
Rank int `json:"rank"`
Title string `json:"title"`
URL string `json:"url"`
Snippet string `json:"snippet"`
Engine string `json:"engine"`
}
type WebFn func(query string) SecondSource
// ShouldEscalate is true when the default deduction path has no facts hit.
// `--root facts|info` is a single-root ask: do not mix in the web.
func ShouldEscalate(hits []Hit, rootFilter string) bool {
if rootFilter != "" {
return false
}
for _, h := range hits {
if h.Root == "facts" {
return false
}
}
return true
}
// Deduce returns the second-source block, or nil when web must not run.
func Deduce(hits []Hit, query, rootFilter string, noWeb bool, web WebFn) *SecondSource {
if noWeb || web == nil || !ShouldEscalate(hits, rootFilter) {
return nil
}
out := web(query)
return &out
}
+78
View File
@@ -0,0 +1,78 @@
package rank
import (
"strings"
"testing"
)
func TestShouldEscalateWhenNoFacts(t *testing.T) {
if !ShouldEscalate(nil, "") {
t.Fatal("empty local graph must escalate")
}
if !ShouldEscalate([]Hit{h("i", "info", "docs/a.md")}, "") {
t.Fatal("info-only must escalate (not confirmed)")
}
}
func TestShouldNotEscalateWhenFactsConfirm(t *testing.T) {
hits := []Hit{h("f", "facts", "docker ps x compose"), h("i", "info", "docs/a.md")}
if ShouldEscalate(hits, "") {
t.Fatal("facts hit is already confirmed; do not mix web")
}
}
func TestShouldNotEscalateWhenRootFilterSet(t *testing.T) {
if ShouldEscalate(nil, "facts") {
t.Fatal("--root facts must stay local")
}
if ShouldEscalate([]Hit{h("i", "info", "x")}, "info") {
t.Fatal("--root info must stay local")
}
}
func TestDeduceCallsWebOnlyWhenEscalating(t *testing.T) {
called := 0
web := func(q string) SecondSource {
called++
if q != "LadybugDB" {
t.Fatalf("query = %q", q)
}
return SecondSource{Status: "ok", Results: []SecondSourceHit{{Title: "t", URL: "http://example.com"}}}
}
got := Deduce([]Hit{h("i", "info", "x")}, "LadybugDB", "", false, web)
if called != 1 || got == nil || got.Status != "ok" {
t.Fatalf("got %+v called=%d", got, called)
}
}
func TestDeduceNilWhenFactsOrNoWeb(t *testing.T) {
web := func(string) SecondSource {
t.Fatal("web must not run")
return SecondSource{}
}
if Deduce([]Hit{h("f", "facts", "x")}, "q", "", false, web) != nil {
t.Fatal("facts")
}
if Deduce([]Hit{h("i", "info", "x")}, "q", "", true, web) != nil {
t.Fatal("--no-web")
}
if Deduce(nil, "q", "facts", false, web) != nil {
t.Fatal("--root facts")
}
if Deduce(nil, "q", "", false, nil) != nil {
t.Fatal("nil web fn")
}
}
func TestParseNoWeb(t *testing.T) {
opt, err := ParseArgs([]string{"query", "--no-web", "--json"})
if err != nil || !opt.NoWeb || !opt.JSONOut || opt.Query != "query" {
t.Fatalf("got %+v err=%v", opt, err)
}
}
func TestUsageNamesNoWeb(t *testing.T) {
if !strings.Contains(Usage, "--no-web") {
t.Fatalf("usage must name --no-web, got:\n%s", Usage)
}
}
+11 -2
View File
@@ -68,18 +68,25 @@ func runSearch(args []string) int {
}
}
webOut := rank.Deduce(results, query, root, opt.NoWeb, func(q string) rank.SecondSource {
return lookupWeb(context.Background(), q)
})
out := Dict{
{"query", query},
{"root_filter", root},
{"count", len(results)},
{"results", resultsToDicts(results)},
}
if webOut != nil {
out = append(out, KV{"web", secondToDict(*webOut)})
}
if jsonOut {
enc := json.NewEncoder(os.Stdout)
enc.SetIndent("", " ")
enc.SetEscapeHTML(false)
return b2i(enc.Encode(toJSONOut(results, query, root)))
return b2i(enc.Encode(toJSONOut(results, query, root, webOut)))
}
fmt.Print(toYAML(out, 0))
return 0
@@ -172,6 +179,7 @@ type jsonOut struct {
RootFilter string `json:"root_filter"`
Count int `json:"count"`
Results []jsonHit `json:"results"`
Web *rank.SecondSource `json:"web,omitempty"`
}
type jsonHit struct {
@@ -182,7 +190,7 @@ type jsonHit struct {
Snippet string `json:"snippet,omitempty"`
}
func toJSONOut(hits []Hit, query, rootFilter string) *jsonOut {
func toJSONOut(hits []Hit, query, rootFilter string, web *rank.SecondSource) *jsonOut {
out := make([]jsonHit, len(hits))
for i, h := range hits {
out[i] = jsonHit{
@@ -198,6 +206,7 @@ func toJSONOut(hits []Hit, query, rootFilter string) *jsonOut {
RootFilter: rootFilter,
Count: len(hits),
Results: out,
Web: web,
}
}
+56
View File
@@ -0,0 +1,56 @@
package brain
import (
"context"
"github.com/eSlider/2dph/internal/brain/rank"
"github.com/eSlider/2dph/internal/websearch"
)
func lookupWeb(ctx context.Context, query string) rank.SecondSource {
o := websearch.Lookup(ctx, query, websearch.LookupOpt{Limit: 5})
return toSecond(o)
}
func toSecond(o websearch.Output) rank.SecondSource {
hits := make([]rank.SecondSourceHit, 0, len(o.Results))
for _, h := range o.Results {
hits = append(hits, rank.SecondSourceHit{
Rank: h.Rank,
Title: h.Title,
URL: h.URL,
Snippet: h.Snippet,
Engine: h.Engine,
})
}
return rank.SecondSource{
Status: o.Status,
Note: o.Note,
Cached: o.Cached,
Results: hits,
}
}
func secondToDict(w rank.SecondSource) Dict {
d := Dict{
{"status", w.Status},
}
if w.Note != "" {
d = append(d, KV{"note", w.Note})
}
if w.Cached {
d = append(d, KV{"cached", true})
}
rows := make([]any, 0, len(w.Results))
for _, h := range w.Results {
rows = append(rows, Dict{
{"rank", h.Rank},
{"title", h.Title},
{"url", h.URL},
{"snippet", h.Snippet},
{"engine", h.Engine},
})
}
d = append(d, KV{"results", rows})
return d
}
+122
View File
@@ -0,0 +1,122 @@
package websearch
import (
"context"
"fmt"
"net/http"
"os"
"time"
"golang.org/x/sys/unix"
)
const (
StatusSkipped = "skipped"
StatusRefused = "refused"
)
type LookupOpt struct {
Limit int
Timeout time.Duration
EnvPath string
CachePath string
Client *http.Client
Now func() float64
Sleep func(context.Context, time.Duration) error
}
func Lookup(ctx context.Context, query string, opt LookupOpt) Output {
if ctx == nil {
ctx = context.Background()
}
if opt.Limit <= 0 {
opt.Limit = DefaultLimit
}
if opt.Timeout <= 0 {
opt.Timeout = 25 * time.Second
}
nowFn := opt.Now
if nowFn == nil {
nowFn = func() float64 { return float64(time.Now().Unix()) }
}
sleepFn := opt.Sleep
if sleepFn == nil {
sleepFn = func(ctx context.Context, d time.Duration) error {
t := time.NewTimer(d)
defer t.Stop()
select {
case <-t.C:
return nil
case <-ctx.Done():
return ctx.Err()
}
}
}
if reason := PHIReason(query); reason != "" {
return Output{Query: query, Status: StatusRefused, Note: reason}
}
cachePath := opt.CachePath
if cachePath == "" {
cachePath = os.Getenv("BRAIN_SEARCH_CACHE")
}
if cachePath == "" {
cachePath = os.Getenv("HOME") + "/.cache/brain/web-search.sqlite"
}
cache, err := OpenCache(cachePath)
if err != nil {
return Output{Query: query, Status: StatusSkipped, Note: "cache: " + err.Error()}
}
defer cache.Close()
key := CacheKey(query, nil)
now := nowFn()
if cached, err := cache.Get(key, CacheTTL, now); err == nil && cached != nil {
out := Project(*cached, opt.Limit, DefaultSnippetChars)
out.Cached = true
return out
}
envPath := opt.EnvPath
if envPath == "" {
envPath = os.Getenv("BRAIN_SEARCH_ENV")
}
if envPath == "" {
envPath = os.Getenv("HOME") + "/.config/brain/search.env"
}
conf, err := LoadConfig(envPath)
if err != nil {
return Output{Query: query, Status: StatusSkipped, Note: "no BRAIN_SEARCH_URL; second source not consulted"}
}
lock, err := os.OpenFile(cachePath+".lock", os.O_CREATE|os.O_RDWR, 0o600)
if err != nil {
return Output{Query: query, Status: StatusSkipped, Note: "lock: " + err.Error()}
}
defer lock.Close()
if err := unix.Flock(int(lock.Fd()), unix.LOCK_EX); err != nil {
return Output{Query: query, Status: StatusSkipped, Note: "lock: " + err.Error()}
}
defer unix.Flock(int(lock.Fd()), unix.LOCK_UN)
last, err := cache.LastCall()
if err != nil {
return Output{Query: query, Status: StatusSkipped, Note: "cache: " + err.Error()}
}
if delay := WaitFor(last, nowFn(), MinInterval); delay > 0 {
if err := sleepFn(ctx, time.Duration(delay*float64(time.Second))); err != nil {
return Output{Query: query, Status: StatusSkipped, Note: "cancelled"}
}
}
_ = cache.MarkCall(nowFn())
payload, err := Fetch(opt.Client, conf, query, nil, opt.Timeout)
if err != nil {
return Output{Query: query, Status: StatusThrottled, Note: fmt.Sprintf("request failed: %v", err)}
}
if Classify(payload) == StatusOK {
_ = cache.Put(key, payload, nowFn())
}
return Project(payload, opt.Limit, DefaultSnippetChars)
}
+97
View File
@@ -0,0 +1,97 @@
package websearch
import (
"context"
"encoding/json"
"net/http"
"net/http/httptest"
"os"
"path/filepath"
"testing"
"time"
)
func TestLookupRefusesPIIWithoutFetch(t *testing.T) {
hits := 0
srv := httptest.NewServer(http.HandlerFunc(func(http.ResponseWriter, *http.Request) {
hits++
}))
defer srv.Close()
out := Lookup(context.Background(), "Personalnummer 12", LookupOpt{
EnvPath: writeEnv(t, srv.URL),
CachePath: filepath.Join(t.TempDir(), "c.sqlite"),
Client: srv.Client(),
Sleep: func(context.Context, time.Duration) error { return nil },
})
if out.Status != StatusRefused {
t.Fatalf("status = %s", out.Status)
}
if hits != 0 {
t.Fatal("PII query left the host")
}
}
func TestLookupSkipsWhenNoConfig(t *testing.T) {
out := Lookup(context.Background(), "LadybugDB", LookupOpt{
EnvPath: filepath.Join(t.TempDir(), "missing.env"),
CachePath: filepath.Join(t.TempDir(), "c.sqlite"),
Sleep: func(context.Context, time.Duration) error { return nil },
})
if out.Status != StatusSkipped {
t.Fatalf("status = %s", out.Status)
}
}
func TestLookupFetchesOnceAndCaches(t *testing.T) {
hits := 0
payload := Payload{Query: "x", Results: []RawHit{{Title: "t", URL: "http://example.com", Content: "c", Engine: "bing"}}}
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
hits++
json.NewEncoder(w).Encode(payload)
}))
defer srv.Close()
opt := LookupOpt{
EnvPath: writeEnv(t, srv.URL),
CachePath: filepath.Join(t.TempDir(), "c.sqlite"),
Client: srv.Client(),
Now: func() float64 { return 1_000 },
Sleep: func(context.Context, time.Duration) error { return nil },
}
a := Lookup(context.Background(), "LadybugDB", opt)
b := Lookup(context.Background(), "LadybugDB", opt)
if a.Status != StatusOK || b.Status != StatusOK {
t.Fatalf("a=%s b=%s", a.Status, b.Status)
}
if hits != 1 {
t.Fatalf("hits = %d, want 1 (second from cache)", hits)
}
if !b.Cached {
t.Fatal("second lookup not cached")
}
}
func TestLookupEmptyIsThrottled(t *testing.T) {
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
w.Write([]byte(`{"query":"x","results":[]}`))
}))
defer srv.Close()
out := Lookup(context.Background(), "LadybugDB", LookupOpt{
EnvPath: writeEnv(t, srv.URL),
CachePath: filepath.Join(t.TempDir(), "c.sqlite"),
Client: srv.Client(),
Now: func() float64 { return 1_000 },
Sleep: func(context.Context, time.Duration) error { return nil },
})
if out.Status != StatusThrottled {
t.Fatalf("status = %s", out.Status)
}
}
func writeEnv(t *testing.T, url string) string {
t.Helper()
p := filepath.Join(t.TempDir(), "search.env")
if err := os.WriteFile(p, []byte("BRAIN_SEARCH_URL="+url+"\n"), 0o600); err != nil {
t.Fatal(err)
}
return p
}
+4 -3
View File
@@ -39,8 +39,9 @@ are not wired yet); do not treat it as a graph walk.
- Search before you read. Never grep a repo for a concept the graph covers.
- `--root facts` returns only confirmed evidence-linked answers. Default shows
facts first, then info leafs clearly marked `(not confirmed)`.
- If there is no facts hit, `bin/brain/search.go` consults SearXNG and adds a
`web` block (kept apart from graph hits). `throttled` / `skipped` / `refused`
are not evidence of absence. `--root facts|info` and `--no-web` skip the web.
- If recall looks wrong, run `bin/brain/eval.go`; it gates control questions and
should stay at or above 95% recall@5.
- Escalate to `web-search` (the `web-search` skill) as the independent second
source when both local roots cannot confirm; never report an unconfirmed
single-source local answer as fact.
- Never report an unconfirmed single-source local answer as fact.