Compare commits

..
Author SHA1 Message Date
eSlider 7db9e6b836 docs: record v1 detective epic and remaining gaps.
Tests / Test (push) Skipped
Tests / Release (semver) (push) Skipped
Tests / Test (pull_request) Failing after 6s
Tests / Release (semver) (pull_request) Skipped
Read path and MCP are in; write, hops, corpus, and CI eval are still open. Board is Gitea epic #16.
2026-08-14 10:22:36 +01:00
30 changed files with 108 additions and 742 deletions
+4 -6
View File
@@ -40,7 +40,7 @@ PLAN.md decisions + execution + open questions
docs/ published docs
skills/ in-project agent skills (vendored, no external links)
bin/ self-describing tools bin/{subject}/{method}.go (shebang)
bin/brain/ search.go serve.go index.go add.go get.go stats.go eval.go watch.go
bin/brain/ search.go serve.go index.go get.go stats.go eval.go watch.go
bin/chats/ sync.go import.go facts.go apply.go; libs in internal/chats
bin/mail/ sync.go import.go (index_mail → brain/index.go)
bin/markdown/ import.go (H2 leaf split; Python bin/md/import fallback)
@@ -74,9 +74,9 @@ bin/brain/index.go --rebuild # rebuil
`pdftotext -layout` fast path (~15ms); textless/scanned PDFs fall back to
docling (isolated subprocess — its native onnx can segfault the parent).
Conversion never touches the brain DB (crash safety).
- `index_mail` is a deprecation shim for `bin/brain/index.go --rebuild`. Bulk
rebuild still deletes `var/kb.lbug` and creates FTS/HNSW last. Single-leaf
write is `bin/brain/add.go` (safe while indexes exist; do not DROP INDEX).
- `index_mail` is a deprecation shim for `bin/brain/index.go --rebuild`. Ladybug
corrupts its WAL when brand-new leafs are bulk-inserted while FTS/vector
indexes exist; a fresh DB with indexes created last is the only safe path.
Keep conversion + indexing separate so a conversion crash can't leave the
DB mid-transaction.
@@ -89,8 +89,6 @@ bin/kb/search "query" [--repo X] # deprecated wrapper → bin/b
bin/brain/search.go "query" [--root facts|info] # deduction search → YAML
bin/brain/search.go "query" --no-web # local graph only
eval "$(bin/cgo/zig env)" # Zig cc + liblbug (not gcc)
bin/brain/add.go --text T --root facts --source "a.md x b.md" # incremental write
bin/brain/add.go --json # stdin leaf or {leafs:[...]}
bin/brain/get.go <id> [--body] [--json] # Go read; Python bin/kb/get CI fallback
bin/brain/stats.go [--json]
bin/brain/eval.go [--json] # recall@5; questions in internal/brain/rank
+10 -14
View File
@@ -31,9 +31,9 @@ detective method: **a fact needs ≥2 independent sources or it is
| D3 | web search | Go client `bin/web/search.go` (`internal/websearch`). SearXNG URL is config (`BRAIN_SEARCH_URL`). Optional Compose profile `searxng` (sanitized settings). Do not run a second copy on a host that already has one. Empty/`throttled` ≠ “nothing exists”. |
| D4 | embeddings | **model2vec** `minishlab/potion-multilingual-128M` instead of embeddinggemma. |
| D5 | parser | **mistune** for MD → leaf extraction (duckdb-md documented as future optional SQL/export layer, not v1). |
| D6 | graph engine | **LadybugDB**. Go is the service (`bin/brain/search.go`, `bin/brain/serve.go` in-process, `internal/brain`). Read path is Go + Zig CGO (D21). Python `bin/kb/{get,stats,eval}` is the CI fallback when Zig/libs are not fetched. Incremental write is Python `bin/kb/add` (`bin/brain/add.go`). Bulk rebuild stays `compose --profile index` until the Go write path is safe. |
| D6 | graph engine | **LadybugDB**. Go is the service (`bin/brain/search.go`, `bin/brain/serve.go` in-process, `internal/brain`). Read path is Go + Zig CGO (D21). Python `bin/kb/{get,stats,eval}` is the CI fallback when Zig/libs are not fetched. Index/write stays Python (`compose --profile index`) until the Go write path is safe. |
| D7 | db access | `db-yaml`/`psql-yq`-style, read-only, YAML out. OnlyOffice Postgres via SSH tunnel (`127.0.0.1:5433`). |
| D8 | evidence | detective method: ≥2 independent sources or `(not confirmed)`. 2-source auto-pair docker ps × compose × ssh-config × docs. |
| D8 | evidence | detective method: ≥2 independent sources or `(not confirmed)`. Auto-pair docker ps × compose × ssh-config × docs. |
| D9 | facts/goal model | Who / What / How / Where / When + evidence + confidence on every edge. |
| D10 | versioning | everything is a leaf with `sha256 + observed_at + source_rev`; `File-[:HAS_VERSION]->Commit-[:AUTHORED]->Person`. Stale = `source_rev` < git HEAD. |
| D11 | strong/weak | `root` column: `facts` (strong) vs `info` (weak). Answer is `confirmed` only from facts root. |
@@ -45,7 +45,7 @@ detective method: **a fact needs ≥2 independent sources or it is
| 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 (`REASONER_BASE_URL`). RAM: `Qwen/Qwen3.5-9B`. Quality: `prism-ml/Bonsai-27B-gguf` or `Qwen/Qwen3.6-27B`. No official Qwen3.6-9B. CPU bake-off: `bin/reasoner/bakeoff.go` + compose profile `reasoner` (`OLLAMA_NUM_GPU=0`, `:11435`). PicoClaw is compose profile `picoclaw`; tools are `search`/`get`/`audit`. Weights are not copied into the 2dph image. Agent lever/loop: [#15](https://git.produktor.io/eSlider/2dph/issues/15). |
| 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`. |
| D20 | agent API | OpenAPI + MCP are generated from the same `internal/httpapi.Ops` table as `bin/brain/serve.go` handlers. `GET /openapi.json`, `POST /mcp` (JSON-RPC tools/list + tools/call). Tool names match OpenAPI paths (`search`/`get`/`stats`/`audit`/`ingest`). |
| D20 | agent API | OpenAPI + MCP are generated from the same `internal/httpapi.Ops` table as `bin/brain/serve.go` handlers. `GET /openapi.json`, `POST /mcp` (JSON-RPC tools/list + tools/call). Tool names match OpenAPI paths (`search`/`get`/`stats`/`audit`). |
| D21 | CGO | Ladybug/tokenizers CGO is compiled with **Zig** (`bin/cgo/zcc``zig cc -target …-linux-gnu`), not gcc. `bin/cgo/zig` pins Zig 0.14.1 + liblbug 0.19.1 + libtokenizers 1.27.0. Compose `target: api` has no CPython; write/rebuild is profile `index`. |
## Architecture
@@ -57,10 +57,8 @@ detective method: **a fact needs ≥2 independent sources or it is
skills/ in-project skills (web-search, postgres, brain, picoclaw, diataxis-docs)
bin/
facts/extract.go audit.go crm.go # D14 shebang; Python implementation
kb/index Python bulk write (called by bin/brain/index.go)
kb/add Python incremental write (called by bin/brain/add.go)
kb/index Python write path (called by bin/brain/index.go)
brain/index.go rebuild FTS + HNSW (incl. --with-mail)
brain/add.go incremental leaf write (no rebuild)
brain/get.go stats.go eval.go # Go read (cgo); Python bin/kb/* CI fallback
brain/watch.go
brain/search.go deduction: facts → info → web-search
@@ -88,9 +86,7 @@ detective method: **a fact needs ≥2 independent sources or it is
Node tables: `Person, Service, Host, Container, Repo, File, Commit, Leaf`.
`Leaf(embedding FLOAT[N])` — FTS on `text`, HNSW vector index on `embedding`.
Edges: `RUNS / USES / FROM_FILE / HAS_VERSION / AUTHORED / ABOUT / ASSOCIATED / SIMILAR_0.85`.
`FROM_FILE` / `HAS_VERSION` / `AUTHORED`: `bin/brain/search.go --hop N` walks
them from each hit (1=File, 2=Commit, 3=Person). Rebuild writes
`Leaf-[:FROM_FILE]->File`; git import writes the rest.
`FROM_FILE` / `HAS_VERSION` exist in schema; search `--hop` does not walk them yet ([#17](https://git.produktor.io/eSlider/2dph/issues/17)).
Common props on every node/edge: `root`, `confidence`, `evidence[]`, `how`,
`where`, `when`, `source_rev`.
@@ -164,18 +160,18 @@ Feedback loop: every commit → PR → CI → green/gate → merge. Same discipl
## Gap to v1 (epic #16)
Read path + MCP are in. Incremental `brain/add` and `--hop` are in. Remaining:
facts+chats corpus on rebuild, and CI eval SoT. Board:
Read path + MCP are in. The detective brain is not closed until the graph is
**writable incrementally** and search can **walk** it. Board:
[epic #16](https://git.produktor.io/eSlider/2dph/issues/16),
milestone [v1 detective brain](https://git.produktor.io/eSlider/2dph/milestone/12).
Narrative: [docs/roadmap.md](docs/roadmap.md).
| Order | Issue | Gap |
|-------|-------|-----|
| 1 | [#14](https://git.produktor.io/eSlider/2dph/issues/14) | **in**`bin/brain/add.go` / `POST /ingest` write facts+info without deleting `kb.lbug`. Bulk corpus still `--rebuild`. Leftover Python (mail/facts) is not the living-graph blocker. |
| 2 | [#17](https://git.produktor.io/eSlider/2dph/issues/17) | **in** `--hop N` walks `FROM_FILE` `HAS_VERSION` `AUTHORED` (max 3). |
| 1 | [#14](https://git.produktor.io/eSlider/2dph/issues/14) | Write stays Python rebuild; `brain/add` / `POST /ingest` are hints. Ladybug 0.19 WAL corrupts if new leafs land while FTS/HNSW exist. |
| 2 | [#17](https://git.produktor.io/eSlider/2dph/issues/17) | `--hop` errors. `FROM_FILE` / `HAS_VERSION` are in schema; search does not walk them. |
| 3 | [#18](https://git.produktor.io/eSlider/2dph/issues/18) | Rebuild is mostly `info` (repo md + mail). `facts/extract` and chats are not a first-class index input. WhatsApp sync is a stub. |
| 4 | [#15](https://git.produktor.io/eSlider/2dph/issues/15) | **in** — lever/loop documented (`search``get``audit`). |
| 4 | [#15](https://git.produktor.io/eSlider/2dph/issues/15) | Lever = 2dph fact-check. Loop = PicoClaw/MCP `search``get``audit`. Specify in-repo, not only live config. |
| 5 | [#19](https://git.produktor.io/eSlider/2dph/issues/19) | GitHub CI recall still runs Python `bin/kb/eval`. |
Does **not** block epic close: [#6](https://git.produktor.io/eSlider/2dph/issues/6) OCR, OQ1, OQ3, OQ4.
+3 -5
View File
@@ -96,7 +96,7 @@ bin/brain/stats.go # index health
bin/brain/eval.go # recall@5 gate
```
`--hop N` walks File/Commit/Person from each hit (max 3). `bin/kb/search` is a deprecated wrapper around `bin/brain/search.go`.
`--hop` is not implemented (needs File/FROM_FILE edges); the flag errors instead of walking. `bin/kb/search` is a deprecated wrapper around `bin/brain/search.go`.
Git history is read with [go-git](https://github.com/go-git/go-git) (no git binary):
@@ -120,7 +120,6 @@ Mail is a first-class corpus (retrievable through the same search):
```bash
bin/mail/sync.go --source onlyoffice,gmail --workers 8 --out var/mail # raw sync (Go)
bin/mail/import.go --from-raw var/mail # JSON → markdown
bin/brain/add.go --text T --root facts --source "a.md x b.md"
bin/brain/index.go --rebuild # rebuild brain (incl. mail)
bin/brain/search.go "invoice from last week" # same search over mail leafs
```
@@ -129,9 +128,8 @@ bin/brain/search.go "invoice from last week" # same s
- **LadybugDB** — single `var/kb.lbug`, Cypher + HNSW + BM25, embedded.
Read tools (`get` / `stats` / `eval`) are Go + Zig CGO (`bin/cgo/zcc`).
Python fallbacks stay for CI until the runner fetches Zig. Incremental
write is `bin/brain/add.go` (Python `kblib.add_leafs`). Bulk rebuild is
Compose profile `index` (`bin/brain/index.go --rebuild`).
Python fallbacks stay for CI until the runner fetches Zig. Write is
Compose profile `index` (`bin/brain/index.go`).
- **model2vec** — `potion-multilingual-128M` (256-dim), CPU, no Ollama
runtime dependency.
- facts and info split by `root` but written in the same transaction.
-21
View File
@@ -1,21 +0,0 @@
//usr/bin/env go run -tags=brain_add "$0" "$@"; exit
//go:build brain_add
//
// bin/brain/add.go - incremental leaf write (Python kblib, no rebuild).
//
// ./bin/brain/add.go --text T --root facts --source "a.md x b.md"
// ./bin/brain/add.go --json
//
// D6: write stays Python. Does not delete var/kb.lbug.
// NOTE: never run `gofmt -w` on this file — it breaks the shebang.
package main
import (
"os"
"github.com/eSlider/2dph/internal/cmdbin"
)
func main() {
os.Exit(cmdbin.ExecFile("bin/kb/add", os.Args[1:]))
}
+2 -2
View File
@@ -7,8 +7,8 @@
// ./bin/brain/index.go --rebuild --with-mail
// ./bin/brain/index.go --dry-run --with-mail
//
// v1 write: bin/brain/add.go for one/few leafs (indexes may already exist).
// Bulk mail/corpus still --rebuild (fresh file, indexes last).
// v1 write is always a rebuild when mail is included (live FTS/HNSW + bulk
// insert corrupts Ladybug 0.19 WAL). `add` is v2.
// NOTE: never run `gofmt -w` on this file — it breaks the shebang.
package main
+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] [--hop N] [--json] [--no-web]
// ./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
//
-114
View File
@@ -1,114 +0,0 @@
#!/usr/bin/env python3
"""kb/add - incremental leaf write (no rebuild).
bin/kb/add --text T --root facts|info --source S
bin/kb/add --json # stdin: one object or {"leafs":[...]}
bin/kb/add --db PATH --json
Writes facts+info in one Ladybug transaction. Does not delete kb.lbug.
Embedding is used when provided; otherwise model2vec encodes the text.
"""
from __future__ import annotations
import json
import sys
from pathlib import Path
ROOT = Path(__file__).resolve().parents[2]
sys.path.insert(0, str(ROOT / "bin" / "tools"))
from kblib import ( # noqa: E402
EMBED_DIM,
add_leafs,
connect,
ensure_indexes,
init_schema,
)
def _as_leafs(payload: object) -> list[dict]:
if isinstance(payload, list):
return [dict(x) for x in payload]
if isinstance(payload, dict):
if "leafs" in payload:
return [dict(x) for x in payload["leafs"]]
return [dict(payload)]
raise ValueError("json must be an object, a list, or {leafs:[...]}")
def _embed_missing(leafs: list[dict]) -> None:
missing = [lf for lf in leafs if not lf.get("embedding")]
if not missing:
return
from model2vec import StaticModel
model = StaticModel.from_pretrained("minishlab/potion-multilingual-128M")
for lf in missing:
text = str(lf.get("text") or "")
vec = model.encode([text])[0].astype(float).tolist()
if len(vec) != EMBED_DIM:
vec = (vec + [0.0] * EMBED_DIM)[:EMBED_DIM]
lf["embedding"] = vec
def main(argv: list[str]) -> int:
import argparse
p = argparse.ArgumentParser(description="add leafs without rebuilding the brain")
p.add_argument("--db", default="", help="path to kb.lbug (default var/kb.lbug)")
p.add_argument("--json", action="store_true", help="read leaf JSON from stdin")
p.add_argument("--text", default="", help="leaf text")
p.add_argument("--root", default="info", choices=("facts", "info"))
p.add_argument("--source", default="")
p.add_argument("--confidence", default="confirmed")
p.add_argument("--source-rev", default="working-tree")
p.add_argument("--how", default="brain/add")
p.add_argument("--loc", default="")
p.add_argument("--type", default="reference", dest="type_")
args = p.parse_args(argv)
if args.json:
raw = sys.stdin.read()
if not raw.strip():
print("kb/add: empty stdin", file=sys.stderr)
return 2
leafs = _as_leafs(json.loads(raw))
else:
if not args.text or not args.source:
print("kb/add: --text and --source are required (or --json)", file=sys.stderr)
return 2
leafs = [{
"text": args.text,
"root": args.root,
"source": args.source,
"confidence": args.confidence,
"source_rev": args.source_rev,
"how": args.how,
"loc": args.loc or args.source,
"type": args.type_,
}]
for lf in leafs:
if not lf.get("text") or not lf.get("source"):
print("kb/add: each leaf needs text and source", file=sys.stderr)
return 2
_embed_missing(leafs)
from kblib import DB_PATH, VAR
dbpath = Path(args.db) if args.db else DB_PATH
dbpath.parent.mkdir(parents=True, exist_ok=True)
VAR.mkdir(exist_ok=True)
db, conn = connect(dbpath, read_only=False)
init_schema(conn)
ids = add_leafs(conn, leafs)
ensure_indexes(conn)
conn.close()
db.close()
print(json.dumps({"mode": "add", "ids": ids, "db": str(dbpath)}))
return 0
if __name__ == "__main__":
sys.exit(main(sys.argv[1:]))
+2 -3
View File
@@ -22,7 +22,7 @@ ROOT = Path(__file__).resolve().parents[2]
sys.path.insert(0, str(ROOT / "bin" / "tools"))
from kblib import ( # noqa: E402
connect, ensure_indexes, init_schema, upsert_leaf, link_from_file,
connect, ensure_indexes, init_schema, upsert_leaf,
open_readonly, stats,
)
from mdleaves import read_markdown, to_all, walk_markdown # noqa: E402
@@ -81,11 +81,10 @@ def index_leafs(conn, leafs: list[dict], embed_fn, limit: int) -> tuple[int, int
for lf in leafs[:limit] if limit else leafs:
query = f"{lf['heading']}\n\n{lf['text']}"
emb = embed_fn(lf["text"]) if lf["text"] else None
lid = upsert_leaf(conn, text=query, root="info", confidence="confirmed",
upsert_leaf(conn, text=query, root="info", confidence="confirmed",
source=lf["source"], source_rev="working-tree",
how="kb/index", loc=lf["source"], type_=lf.get("type", "reference"),
embedding=emb)
link_from_file(conn, lid, lf["source"], repo=str(lf.get("repo") or ""))
count += 1
return count, len(leafs)
+1 -92
View File
@@ -4,7 +4,7 @@ Single embedded graph `var/kb.lbug`. Two roots: facts (assertions backed by
>=2 independent sources) and info (narrative leafs). Hybrid retrieval: BM25
(FTS extension) + HNSW cosine (VECTOR extension) + Cypher graph hops.
All access is read-only unless `--rebuild` (kb/index) or `kb/add`.
All access is read-only unless `--rebuild` is passed to kb/index.
"""
from __future__ import annotations
@@ -118,97 +118,6 @@ def upsert_leaf(conn: ladybug.Connection, *, text: str, root: str, confidence: s
return lid
def add_leafs(conn: ladybug.Connection, leafs: list[dict]) -> list[str]:
"""Write facts+info leafs in one transaction. Safe while FTS/HNSW exist.
Each leaf dict: text, source, optional root/confidence/source_rev/how/loc/type/embedding.
Does not delete the database file. Measured on Ladybug 0.19: MERGE of new
ids (and updates) stays FTS+HNSW queryable; DROP INDEX is the fatal path.
"""
if not leafs:
return []
started = False
try:
conn.execute("BEGIN TRANSACTION")
started = True
except Exception:
started = False
ids: list[str] = []
try:
for lf in leafs:
ids.append(
upsert_leaf(
conn,
text=str(lf["text"]),
root=str(lf.get("root") or ROOT_INFO),
confidence=str(lf.get("confidence") or CONF_CONFIRMED),
source=str(lf["source"]),
source_rev=str(lf.get("source_rev") or "working-tree"),
how=str(lf.get("how") or "brain/add"),
loc=str(lf.get("loc") or lf.get("source") or ""),
type_=str(lf.get("type") or lf.get("type_") or "reference"),
embedding=lf.get("embedding"),
)
)
if started:
conn.execute("COMMIT")
except Exception:
if started:
try:
conn.execute("ROLLBACK")
except Exception:
pass
raise
return ids
def file_id(repo: str, path: str) -> str:
"""Stable File.id matching gitimport (`repo:path`)."""
return f"{repo}:{path}" if repo else path
def link_from_file(conn: ladybug.Connection, leaf_id: str, path: str,
repo: str = "", mtime: str = "") -> str:
"""MERGE File and Leaf-[:FROM_FILE]->File so --hop 1 can walk."""
fid = file_id(repo, path)
conn.execute(
"MERGE (f:File {id:$id}) SET f.path=$path, f.repo=$repo, f.mtime=$mtime",
parameters={"id": fid, "path": path, "repo": repo, "mtime": mtime},
)
conn.execute(
"MATCH (l:Leaf {id:$lid}), (f:File {id:$fid}) "
"MERGE (l)-[:FROM_FILE]->(f)",
parameters={"lid": leaf_id, "fid": fid},
)
return fid
HOP_STMTS = {
1: "MATCH (l:Leaf {id:$id})-[:FROM_FILE]->(f:File) RETURN f.id, f.path, 1",
2: ("MATCH (l:Leaf {id:$id})-[:FROM_FILE]->(f:File)-[:HAS_VERSION]->(c:Commit) "
"RETURN c.id, c.subject, 2"),
3: ("MATCH (l:Leaf {id:$id})-[:FROM_FILE]->(f:File)-[:HAS_VERSION]->(c:Commit)"
"-[:AUTHORED]->(p:Person) RETURN p.id, p.name, 3"),
}
HOP_LABELS = {1: "File", 2: "Commit", 3: "Person"}
def hop_walk(conn: ladybug.Connection, leaf_id: str, n: int) -> list[dict]:
"""Walk Leaf → File → Commit → Person up to n hops (max 3)."""
depth = min(max(int(n), 0), 3)
out: list[dict] = []
for d in range(1, depth + 1):
rows = conn.execute(HOP_STMTS[d], parameters={"id": leaf_id}).get_all()
for row in rows:
out.append({
"id": row[0],
"label": HOP_LABELS[d],
"name": row[1],
"depth": int(row[2]),
})
return out
def leaf_index_names(conn: ladybug.Connection) -> set[str]:
"""Return index names on the Leaf table (e.g. {'id', 'Leaf_vec', '_PK'})."""
rows = conn.execute("CALL SHOW_INDEXES() RETURN *").get_all()
+1 -12
View File
@@ -75,20 +75,9 @@ class BinLayoutTest(unittest.TestCase):
)
def test_brain_methods_are_shebangs(self) -> None:
for method in ("index.go", "add.go", "get.go", "stats.go", "eval.go", "watch.go"):
for method in ("index.go", "get.go", "stats.go", "eval.go", "watch.go"):
self._assert_shebang(f"bin/brain/{method}")
def test_brain_add_is_python_write_not_rebuild(self) -> None:
self._assert_shebang("bin/brain/add.go")
text = (ROOT / "bin" / "brain" / "add.go").read_text()
self.assertIn("cmdbin.ExecFile", text)
self.assertIn("bin/kb/add", text)
self.assertNotIn("--rebuild", text)
py = (ROOT / "bin" / "kb" / "add").read_text()
self.assertIn("add_leafs", py)
self.assertIn("--json", py)
self.assertNotIn("unlink", py.lower())
def test_brain_get_stats_eval_are_not_python_exec(self) -> None:
for method in ("get.go", "stats.go", "eval.go"):
text = (ROOT / "bin" / "brain" / method).read_text()
-69
View File
@@ -1,69 +0,0 @@
"""Incremental add writes leafs without deleting kb.lbug."""
from __future__ import annotations
import json
import os
import subprocess
import sys
import tempfile
import unittest
from pathlib import Path
ROOT = Path(__file__).resolve().parents[2]
class KbAddCLITest(unittest.TestCase):
def test_json_add_does_not_delete_db(self) -> None:
tmp = Path(tempfile.mkdtemp())
dbpath = tmp / "kb.lbug"
py = sys.executable
venv_py = ROOT / ".venv" / "bin" / "python"
if venv_py.is_file():
py = str(venv_py)
payload = {
"text": "cli zebra leaf",
"root": "info",
"source": "cli-test",
"confidence": "confirmed",
"how": "test",
"loc": str(tmp),
"type": "reference",
"embedding": [0.0] * 256,
}
payload["embedding"][0] = 0.3
proc = subprocess.run(
[py, str(ROOT / "bin" / "kb" / "add"), "--db", str(dbpath), "--json"],
cwd=ROOT,
input=json.dumps(payload),
capture_output=True,
text=True,
env=os.environ.copy(),
check=False,
)
self.assertEqual(proc.returncode, 0, proc.stderr)
self.assertTrue(dbpath.exists(), "add must create the db, not skip write")
out = json.loads(proc.stdout)
self.assertEqual(out.get("mode"), "add")
self.assertEqual(len(out.get("ids") or []), 1)
again = subprocess.run(
[py, str(ROOT / "bin" / "kb" / "add"), "--db", str(dbpath), "--json"],
cwd=ROOT,
input=json.dumps({
**payload,
"text": "second moose leaf",
"source": "cli-test-2",
}),
capture_output=True,
text=True,
env=os.environ.copy(),
check=False,
)
self.assertEqual(again.returncode, 0, again.stderr)
self.assertTrue(dbpath.exists())
second = json.loads(again.stdout)
self.assertEqual(len(second.get("ids") or []), 1)
self.assertNotEqual(out["ids"][0], second["ids"][0])
if __name__ == "__main__":
unittest.main()
-96
View File
@@ -71,69 +71,6 @@ class KblibTest(unittest.TestCase):
self.assertTrue(hits)
self.assertIn("Leaf_vec", kblib.leaf_index_names(self.conn))
def test_add_after_indexes_keeps_fts_queryable(self):
"""Incremental add after FTS+HNSW must find the new leaf on both indexes."""
kblib.upsert_leaf(self.conn, text="seed fox leaf", root="info",
confidence="confirmed", source="s", source_rev="r1",
how="test", loc="/tmp", type_="reference",
embedding=make_emb(0.1))
kblib.ensure_indexes(self.conn)
ids = kblib.add_leafs(self.conn, [{
"text": "added zebra after index",
"root": "facts",
"confidence": "confirmed",
"source": "a.md x b.md",
"source_rev": "r1",
"how": "test",
"loc": "/tmp",
"type": "fact",
"embedding": make_emb(0.9),
}])
self.assertEqual(len(ids), 1)
fts = kblib.query_fts(self.conn, "zebra", 5)
self.assertTrue(fts)
self.assertIn("zebra", fts[0]["text"])
self.assertEqual(fts[0]["root"], "facts")
vec = kblib.query_vector(self.conn, make_emb(0.9), 5)
self.assertTrue(any("zebra" in h["text"] for h in vec))
fox = kblib.query_fts(self.conn, "fox", 5)
self.assertTrue(fox)
self.assertIn("fox", fox[0]["text"])
def test_add_facts_and_info_one_transaction(self):
"""D12: facts and info land in the same transaction."""
kblib.ensure_indexes(self.conn)
ids = kblib.add_leafs(self.conn, [
{
"text": "tx fact leaf two-source",
"root": "facts",
"confidence": "confirmed",
"source": "compose.yml x docker ps",
"source_rev": "r1",
"how": "test",
"loc": "/tmp",
"type": "fact",
"embedding": make_emb(0.4),
},
{
"text": "tx info narrative",
"root": "info",
"confidence": "confirmed",
"source": "note.md",
"source_rev": "r1",
"how": "test",
"loc": "/tmp",
"type": "reference",
"embedding": make_emb(0.5),
},
])
self.assertEqual(len(ids), 2)
stats = kblib.stats(self.conn)
self.assertEqual(stats["by_root"].get("facts"), 1)
self.assertEqual(stats["by_root"].get("info"), 1)
self.assertTrue(kblib.query_fts(self.conn, "two-source", 5))
self.assertTrue(kblib.query_fts(self.conn, "narrative", 5))
def test_drop_vector_then_create_raises_clear_error(self):
"""DROP INDEX leaves ghost catalog; create_fts_and_vector must raise."""
kblib.upsert_leaf(self.conn, text="seed", root="info",
@@ -161,39 +98,6 @@ class KblibTest(unittest.TestCase):
self.assertEqual(stats["total"], 2)
self.assertEqual(stats["by_root"], {"facts": 1, "info": 1})
def test_hop_1_returns_file_hop_3_reaches_person(self):
"""--hop walks FROM_FILE / HAS_VERSION / AUTHORED (Gitea #17)."""
import gitimport
lid = kblib.upsert_leaf(
self.conn, text="readme hop fixture", root="info",
confidence="confirmed", source="README.md", source_rev="r1",
how="test", loc="README.md", type_="reference",
embedding=make_emb(0.3),
)
kblib.link_from_file(self.conn, lid, "README.md", repo="sample-repo")
gitimport.index_commits(self.conn, [gitimport.Commit(
sha="a1b2c3d",
author="Ada Lovelace",
email="ada@example.com",
date="2026-08-10T12:00:00Z",
subject="feat: first commit",
files=["README.md"],
)], "sample-repo")
hop1 = kblib.hop_walk(self.conn, lid, 1)
self.assertEqual(len(hop1), 1)
self.assertEqual(hop1[0]["label"], "File")
self.assertEqual(hop1[0]["name"], "README.md")
self.assertEqual(hop1[0]["depth"], 1)
hop3 = kblib.hop_walk(self.conn, lid, 3)
labels = {n["label"] for n in hop3}
self.assertIn("File", labels)
self.assertIn("Commit", labels)
self.assertIn("Person", labels)
person = [n for n in hop3 if n["label"] == "Person"][0]
self.assertEqual(person["name"], "Ada Lovelace")
self.assertEqual(person["depth"], 3)
if __name__ == "__main__":
unittest.main()
+11 -7
View File
@@ -1,6 +1,7 @@
"""Published docs must match live commands (Gitea SoT, brain/search)."""
"""Published docs must match live commands (Gitea SoT, brain/search, no fake --hop)."""
from __future__ import annotations
import re
import unittest
from pathlib import Path
@@ -138,21 +139,24 @@ class PublishedDocsTest(unittest.TestCase):
skill = (ROOT / "skills" / "brain" / "SKILL.md").read_text()
self.assertIn("`web` block", skill)
def test_docs_say_hop_walks_from_file(self) -> None:
def test_docs_do_not_claim_hop_walks(self) -> None:
paths = [
ROOT / "README.md",
ROOT / "docs" / "design.md",
ROOT / "skills" / "brain" / "SKILL.md",
ROOT / "skills" / "diataxis-docs" / "SKILL.md",
ROOT / "docs" / "runbook.md",
ROOT / "docs" / "README.md",
ROOT / "docs" / "roadmap.md",
]
# Command-style `--hop 1` / `--hop N` plus follow/walk = the old lie.
# Honest "not implemented" notes must not match.
lie = re.compile(r"--hop (?:N|1).*(?:follow|walk)", re.I | re.S)
for path in paths:
text = path.read_text()
self.assertIn("--hop", text, f"{path.relative_to(ROOT)} must document --hop")
self.assertNotIn(
"not implemented",
text.lower(),
f"{path.relative_to(ROOT)} still says hop is not implemented",
self.assertIsNone(
lie.search(text),
f"{path.relative_to(ROOT)} still claims --hop walks the graph",
)
def test_docs_are_portable_diataxis(self) -> None:
+3 -3
View File
@@ -27,9 +27,9 @@ Python write sidecar, **D14** `bin/{subject}/{method}.go`, **D15** Gitea origin,
**D17** assertion gate (facts → info → web), **D18** pluggable reasoner.
Search: `bin/brain/search.go "query"` (HTTP: `bin/brain/serve.go`
`/health` `/search` `/get` `/stats` `/audit` `/ingest`). `--hop N` walks
`FROM_FILE` → Commit → Person from each hit (max 3). Rebuild writes
File edges ([#17](https://git.produktor.io/eSlider/2dph/issues/17)).
`/health` `/search` `/get` `/stats` `/audit` `/ingest`). `--hop` is
not a walk; the flag errors. Schema has `FROM_FILE`; search does not
use it ([#17](https://git.produktor.io/eSlider/2dph/issues/17)).
Work board: [Gitea issues](https://git.produktor.io/eSlider/2dph/issues)
([epic #16](https://git.produktor.io/eSlider/2dph/issues/16)).
+6 -8
View File
@@ -34,9 +34,9 @@ bin/brain/search.go "question"
is not evidence of absence; `--no-web` / `--root` skip it)
```
`--hop N` walks `Leaf-[:FROM_FILE]->File-[:HAS_VERSION]->Commit-[:AUTHORED]->Person`
from each hit (1=File, 2=Commit, 3=Person). Rebuild writes FROM_FILE;
git import writes HAS_VERSION/AUTHORED ([#17](https://git.produktor.io/eSlider/2dph/issues/17)).
`--hop` is not implemented. `FROM_FILE` / `HAS_VERSION` exist in schema;
search does not walk them ([#17](https://git.produktor.io/eSlider/2dph/issues/17)).
The flag is an error; it is not a graph walk.
## Who / What / How / Where / When + evidence
@@ -80,16 +80,14 @@ Conflicting pairings (≥2 yes vs ≥2 no) = hypothesis (OQ1 → v2 resolution).
They do not exec Python. Control questions for recall@5 live in
`internal/brain/rank` so CI can test the table without libladybug.
Python `bin/kb/{get,stats,eval}` remain for GitHub Actions until the runner
fetches Zig + libs (`bin/cgo/zig`). Incremental write is `bin/kb/add`
(`bin/brain/add.go`). Bulk index/write is still `bin/kb/index`
fetches Zig + libs (`bin/cgo/zig`). Index/write is still `bin/kb/index`
(`docker compose --profile index`).
## Agent API (D20)
`bin/brain/serve.go` exposes the same `internal/httpapi.Ops` table as OpenAPI
(`GET /openapi.json`) and MCP (`POST /mcp` JSON-RPC `tools/list` +
`tools/call`). Tool names match paths: `search`, `get`, `stats`, `audit`,
`ingest` (add a leaf; omit body for the CLI hint).
`tools/call`). Tool names match paths: `search`, `get`, `stats`, `audit`.
Agents should use these endpoints instead of shebang CLIs.
## Reasoner (D18)
@@ -100,5 +98,5 @@ CPU sidecar: compose profile `reasoner` (`OLLAMA_NUM_GPU=0`,
`127.0.0.1:11435`). Bake-off: `bin/reasoner/bakeoff.go`. Weights stay out
of the 2dph image. See [docs/reasoner.md](reasoner.md).
Gap to v1 (hops, corpus, CI eval): [roadmap](roadmap.md),
Gap to v1 (write, hops, corpus, agent loop): [roadmap](roadmap.md),
[epic #16](https://git.produktor.io/eSlider/2dph/issues/16).
+17 -10
View File
@@ -23,11 +23,8 @@ Decisions: [PLAN.md](../PLAN.md).
Read path Go + Zig CGO (D21). HTTP + OpenAPI + MCP (D20). PicoClaw compose
profile + CPU reasoner (D18). Mail sync → import → rebuild. D14 shebangs.
Compose `api` (no CPython) / `index` (Python write). Issues #1#5, #7#13.
[#15](https://git.produktor.io/eSlider/2dph/issues/15) lever/loop.
[#14](https://git.produktor.io/eSlider/2dph/issues/14) `bin/brain/add.go` /
`POST /ingest` (Python `kblib.add_leafs`; no Go upsert port).
[#17](https://git.produktor.io/eSlider/2dph/issues/17) `--hop N` walks
FROM_FILE / HAS_VERSION / AUTHORED.
`POST /ingest` is a rebuild **hint**. `add` is not implemented.
## Blockers
@@ -37,15 +34,24 @@ question
├─ FTS + HNSW ← in
├─ facts / info roots ← in
├─ web (D17) ← in
├─ brain/add ACID ← in
├─ Cypher hop ← in
├─ Cypher hop ← #17 schema yes, search no
├─ brain/add ACID ← #14 rebuild only
└─ facts+chats corpus ← #18
```
1. **[#18](https://git.produktor.io/eSlider/2dph/issues/18) corpus** —
1. **[#14](https://git.produktor.io/eSlider/2dph/issues/14) write** —
`bin/brain/index.go --rebuild` (Python `kblib`). No incremental
`brain/add`. Watch/mail/git cannot become facts “now”.
2. **[#17](https://git.produktor.io/eSlider/2dph/issues/17) hops** —
`Leaf-[:FROM_FILE]->File-[:HAS_VERSION]->Commit-[:AUTHORED]->Person`
exists; `--hop` still errors. Without a walk, D9/D10 are paper.
3. **[#18](https://git.produktor.io/eSlider/2dph/issues/18) corpus** —
rebuild loads repo markdown + mail as `info`. `facts/extract` pairing
and `bin/chats` are not indexed. WhatsApp is a stub. PII stays in `var/`.
2. **[#19](https://git.produktor.io/eSlider/2dph/issues/19) CI eval** —
4. **[#15](https://git.produktor.io/eSlider/2dph/issues/15) lever/loop** —
2dph is the lever (`search``get``audit`). PicoClaw is the loop.
Document the contour in-repo; CPU turns need a large context window.
5. **[#19](https://git.produktor.io/eSlider/2dph/issues/19) CI eval** —
recall SoT should be `bin/brain/eval.go` via Zig, not Python `bin/kb/eval`.
## Not v1
@@ -55,6 +61,7 @@ contradiction resolution, OQ3 duckdb-md export, OQ4 YAML-first leafs.
## Close epic #16 when
- facts+info can be written without a full rebuild for every leaf
- `--hop` stops erroring and runs a Cypher path from search hits
- ops pairing + chat import land as leafs on rebuild
- MCP tool order is documented and still gated by tests
- CI recall SoT is `bin/brain/eval.go` via Zig
+3 -5
View File
@@ -43,12 +43,10 @@ That binds `127.0.0.1:8888`. JSON format must stay enabled.
## Index then search
Write path is `bin/brain/add.go` for a leaf (or `POST /ingest`). Bulk
corpus rebuild remains `bin/brain/index.go --rebuild` (Compose profile
`index`). Do not DROP INDEX on Ladybug 0.19.
Write path is Compose profile `index` (Python Ladybug rebuild) until
`brain/add` is v2. The operator command is `bin/brain/index.go`.
```bash
bin/brain/add.go --text "arc-1 runs Matrix" --root facts --source "compose.yml x docker ps"
bin/brain/index.go --rebuild
bin/brain/search.go "LadybugDB vector index" # facts → info → web (D17)
bin/brain/search.go "upstream flag" --no-web
@@ -56,7 +54,7 @@ bin/brain/get.go <id> --body
bin/brain/stats.go
```
`--hop N` walks File → Commit → Person from each hit. Empty web results are `throttled`, not absence.
`--hop` is not implemented. Empty web results are `throttled`, not absence.
Gap to v1: [roadmap](roadmap.md) / [epic #16](https://git.produktor.io/eSlider/2dph/issues/16).
Ladybug 0.19: never `DROP INDEX` FTS/VECTOR (ghost catalog). Fresh indexes =
+4 -16
View File
@@ -7,8 +7,6 @@ import (
"context"
"encoding/json"
"fmt"
"os/exec"
"path/filepath"
"github.com/eSlider/2dph/internal/brain/rank"
)
@@ -139,23 +137,13 @@ func (HTTP) Audit(context.Context) ([]byte, error) {
return json.Marshal(map[string]any{"status": "ok", "by_confidence": rows})
}
func (HTTP) Ingest(ctx context.Context, body []byte) ([]byte, error) {
if len(bytes.TrimSpace(body)) == 0 {
func (HTTP) Ingest(context.Context) ([]byte, error) {
return json.Marshal(map[string]any{
"mode": "add",
"command": "bin/brain/add.go",
"rebuild": "bin/brain/index.go --rebuild",
"mode": "rebuild",
"command": "bin/brain/index.go --rebuild",
"add": "v2",
})
}
cmd := exec.CommandContext(ctx, filepath.Join(repoRoot(), "bin", "kb", "add"), "--json")
cmd.Stdin = bytes.NewReader(body)
cmd.Dir = repoRoot()
out, err := cmd.Output()
if err != nil {
return nil, fmt.Errorf("add: %w", err)
}
return out, nil
}
func asInt(v any) int64 {
switch n := v.(type) {
+4 -11
View File
@@ -6,7 +6,7 @@ import (
"strings"
)
const Usage = `usage: bin/brain/search.go "query" [--root facts|info] [--repo REPO] [-n N] [--hop N] [--json] [--no-web]
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`
@@ -15,7 +15,6 @@ type Options struct {
Root string
Repo string
Limit int
Hop int
JSONOut bool
ListModel bool
NoWeb bool
@@ -23,6 +22,8 @@ type Options struct {
// ParseArgs reads flags. Unknown flags are an error: silently dropping them
// meant `--hop 1` vanished and its argument `1` was appended to the query.
// --hop is recognised so it cannot be swallowed; it is not implemented until
// File/FROM_FILE edges exist.
func ParseArgs(args []string) (Options, error) {
opt := Options{Limit: 20}
var queryArgs []string
@@ -51,15 +52,7 @@ func ParseArgs(args []string) (Options, error) {
}
opt.Limit = n
case "--hop":
i++
n, err := strconv.Atoi(args[i])
if err != nil || n < 1 {
return opt, fmt.Errorf("--hop must be a positive integer, got %q", args[i])
}
if n > 3 {
return opt, fmt.Errorf("--hop max is 3 (File → Commit → Person)")
}
opt.Hop = n
return opt, fmt.Errorf("--hop is not implemented yet (needs File/FROM_FILE edges)")
case "--json":
opt.JSONOut = true
case "--no-web":
-27
View File
@@ -7,30 +7,3 @@ const FTSStmt = "CALL QUERY_FTS_INDEX('Leaf', 'id', $q) " +
const VecStmt = "CALL QUERY_VECTOR_INDEX('Leaf', 'Leaf_vec', $q, $n) " +
"RETURN node.id, node.text, node.root, node.source, distance ORDER BY distance LIMIT $n"
// HopStmt is the Cypher walk from a search hit. Depth 1 = File, 2 = Commit, 3 = Person.
func HopStmt(depth int) string {
switch depth {
case 1:
return "MATCH (l:Leaf {id:$id})-[:FROM_FILE]->(f:File) RETURN f.id, f.path, 1"
case 2:
return "MATCH (l:Leaf {id:$id})-[:FROM_FILE]->(f:File)-[:HAS_VERSION]->(c:Commit) RETURN c.id, c.subject, 2"
case 3:
return "MATCH (l:Leaf {id:$id})-[:FROM_FILE]->(f:File)-[:HAS_VERSION]->(c:Commit)-[:AUTHORED]->(p:Person) RETURN p.id, p.name, 3"
default:
return ""
}
}
func HopLabel(depth int) string {
switch depth {
case 1:
return "File"
case 2:
return "Commit"
case 3:
return "Person"
default:
return ""
}
}
-8
View File
@@ -7,13 +7,6 @@ import (
"strings"
)
type HopNode struct {
ID string `json:"id"`
Label string `json:"label"`
Name string `json:"name"`
Depth int `json:"depth"`
}
// Hit is one search result, mirroring the python script's dict shape.
type Hit struct {
ID string `json:"id"`
@@ -22,7 +15,6 @@ type Hit struct {
Source string `json:"-"`
Score float64 `json:"score"`
Snippet string `json:"snippet,omitempty"`
Hops []HopNode `json:"hops,omitempty"`
}
// rrfK dampens the contribution of low ranks; same constant as kblib.py.
+7 -33
View File
@@ -91,41 +91,15 @@ func TestHybridKeepsVectorScoreForSharedHit(t *testing.T) {
}
// The old parser dropped unknown flags and appended their arguments to the
// query, so `search "q" --hop 1` searched for "q 1". --hop must stay a flag.
// query, so `search "q" --hop 1` searched for "q 1". --hop is not implemented
// here (needs File edges); it must still fail closed instead of changing q.
func TestParseHopIsNotSwallowedIntoTheQuery(t *testing.T) {
opt, err := ParseArgs([]string{"what runs on arc-2", "--hop", "1"})
if err != nil {
t.Fatalf("unexpected error: %v", err)
_, err := ParseArgs([]string{"what runs on arc-2", "--hop", "1"})
if err == nil {
t.Fatal("expected --hop to error (not implemented), not be swallowed")
}
if opt.Query != "what runs on arc-2" {
t.Fatalf("query swallowed hop arg: %q", opt.Query)
}
if opt.Hop != 1 {
t.Fatalf("hop = %d, want 1", opt.Hop)
}
}
func TestParseHopMaxIsThree(t *testing.T) {
if _, err := ParseArgs([]string{"q", "--hop", "4"}); err == nil {
t.Fatal("expected --hop 4 to error")
}
opt, err := ParseArgs([]string{"q", "--hop", "3"})
if err != nil || opt.Hop != 3 {
t.Fatalf("hop 3: %+v err=%v", opt, err)
}
}
func TestHopStmtWalksFromFile(t *testing.T) {
s := HopStmt(1)
if !strings.Contains(s, "FROM_FILE") || !strings.Contains(s, "File") {
t.Fatalf("hop 1 must walk FROM_FILE, got %q", s)
}
s3 := HopStmt(3)
if !strings.Contains(s3, "HAS_VERSION") || !strings.Contains(s3, "AUTHORED") || !strings.Contains(s3, "Person") {
t.Fatalf("hop 3 must reach Person, got %q", s3)
}
if HopLabel(1) != "File" || HopLabel(3) != "Person" {
t.Fatal("hop labels")
if !strings.Contains(err.Error(), "--hop") {
t.Fatalf("error should name --hop, got %v", err)
}
}
-58
View File
@@ -56,12 +56,6 @@ func runSearch(args []string) int {
fmt.Fprintf(os.Stderr, "search: %v\n", err)
return 1
}
if opt.Hop > 0 {
if err := attachHops(hits, opt.Hop); err != nil {
fmt.Fprintf(os.Stderr, "hop: %v\n", err)
return 1
}
}
results := hits
for i := range results {
@@ -114,44 +108,6 @@ func searchHits(query, root, repo string, limit int) ([]Hit, error) {
return rank.RankAndFilter(fts, vec, root, repo, limit), nil
}
func attachHops(hits []Hit, n int) error {
if conn == nil {
return fmt.Errorf("brain not open")
}
for i := range hits {
var hops []rank.HopNode
for d := 1; d <= n; d++ {
stmt, err := conn.Prepare(rank.HopStmt(d))
if err != nil {
return err
}
res, err := conn.Execute(stmt, map[string]any{"id": hits[i].ID})
stmt.Close()
if err != nil {
return err
}
for res.HasNext() {
row, err := res.Next()
if err != nil {
return err
}
vals, err := row.GetAsSlice()
if err != nil || len(vals) < 3 {
continue
}
hops = append(hops, rank.HopNode{
ID: fmt.Sprint(vals[0]),
Label: rank.HopLabel(d),
Name: fmt.Sprint(vals[1]),
Depth: int(asInt(vals[2])),
})
}
}
hits[i].Hops = hops
}
return nil
}
func b2i(err error) int {
if err != nil {
return 1
@@ -232,7 +188,6 @@ type jsonHit struct {
Root string `json:"root"`
Score float64 `json:"score"`
Snippet string `json:"snippet,omitempty"`
Hops []rank.HopNode `json:"hops,omitempty"`
}
func toJSONOut(hits []Hit, query, rootFilter string, web *rank.SecondSource) *jsonOut {
@@ -244,7 +199,6 @@ func toJSONOut(hits []Hit, query, rootFilter string, web *rank.SecondSource) *js
Root: h.Root,
Score: h.Score,
Snippet: h.Snippet,
Hops: h.Hops,
}
}
return &jsonOut{
@@ -268,18 +222,6 @@ func resultsToDicts(hits []Hit) []any {
if h.Snippet != "" {
d = append(d, KV{"snippet", h.Snippet})
}
if len(h.Hops) > 0 {
nodes := make([]any, len(h.Hops))
for j, n := range h.Hops {
nodes[j] = Dict{
{"id", n.ID},
{"label", n.Label},
{"name", n.Name},
{"depth", n.Depth},
}
}
d = append(d, KV{"hops", nodes})
}
out[i] = d
}
return out
+1 -9
View File
@@ -144,15 +144,7 @@ func (s *Server) mcpCall(r *http.Request, params json.RawMessage) (any, error) {
return nil, fmt.Errorf("cancelled")
}
defer s.release()
var payload []byte
text := strings.TrimSpace(fmt.Sprint(p.Arguments["text"]))
if text != "" && text != "<nil>" {
payload, err = json.Marshal(p.Arguments)
if err != nil {
return nil, err
}
}
body, err = s.api.Ingest(r.Context(), payload)
body, err = s.api.Ingest(r.Context())
default:
return nil, fmt.Errorf("unknown tool %s", p.Name)
}
+5 -43
View File
@@ -11,7 +11,6 @@ import (
"context"
"encoding/json"
"errors"
"io"
"log"
"net/http"
"os"
@@ -28,7 +27,7 @@ type API interface {
Get(ctx context.Context, id string, body bool) ([]byte, error)
Stats(ctx context.Context) ([]byte, error)
Audit(ctx context.Context) ([]byte, error)
Ingest(ctx context.Context, body []byte) ([]byte, error)
Ingest(ctx context.Context) ([]byte, error)
}
type Server struct {
@@ -60,7 +59,7 @@ func (s *Server) ServeHTTP(w http.ResponseWriter, r *http.Request) {
case PathAudit:
s.handleJSON(w, r, s.api.Audit)
case PathIngest:
s.handleIngest(w, r)
s.handleJSON(w, r, s.api.Ingest)
case PathOpenAPI:
s.handleOpenAPI(w, r)
case PathMCP:
@@ -117,24 +116,6 @@ func (s *Server) handleJSON(w http.ResponseWriter, r *http.Request, fn func(cont
writeAPI(w, body, err)
}
func (s *Server) handleIngest(w http.ResponseWriter, r *http.Request) {
var raw []byte
if r.Method == http.MethodPost {
b, err := io.ReadAll(io.LimitReader(r.Body, 1<<20))
if err != nil {
writeJSON(w, http.StatusBadRequest, map[string]any{"error": "read body"})
return
}
raw = b
}
if !s.acquire(w, r) {
return
}
defer s.release()
body, err := s.api.Ingest(r.Context(), raw)
writeAPI(w, body, err)
}
func (s *Server) tryAcquire(r *http.Request) bool {
return s.acquire(nopWriter{}, r)
}
@@ -210,31 +191,12 @@ func (ExecSearcher) Get(context.Context, string, bool) ([]byte, error) {
}
func (ExecSearcher) Stats(context.Context) ([]byte, error) { return nil, errUnimplemented }
func (ExecSearcher) Audit(context.Context) ([]byte, error) { return nil, errUnimplemented }
func (b ExecSearcher) Ingest(ctx context.Context, body []byte) ([]byte, error) {
if len(strings.TrimSpace(string(body))) == 0 {
func (ExecSearcher) Ingest(context.Context) ([]byte, error) {
return json.Marshal(map[string]any{
"mode": "add",
"command": "bin/brain/add.go",
"rebuild": "bin/brain/index.go --rebuild",
"mode": "rebuild",
"command": "bin/brain/index.go --rebuild",
})
}
root := os.Getenv("KB_ROOT")
if root == "" {
root = "."
}
cmd := exec.CommandContext(ctx, filepath.Join(root, "bin/kb/add"), "--json")
cmd.Stdin = strings.NewReader(string(body))
cmd.Dir = root
out, err := cmd.Output()
if err != nil {
var exitErr *exec.ExitError
if errors.As(err, &exitErr) {
return nil, errors.New("add failed: " + strings.TrimSpace(string(exitErr.Stderr)))
}
return nil, err
}
return out, nil
}
func defaultSearchCmd(root string) string {
if env := os.Getenv("KB_SEARCH_CMD"); env != "" {
+2 -27
View File
@@ -1,7 +1,6 @@
package httpapi
import (
"bytes"
"context"
"encoding/json"
"net/http"
@@ -65,11 +64,8 @@ func (f *fakeSearcher) Audit(context.Context) ([]byte, error) {
return []byte(`{"status":"ok"}`), nil
}
func (f *fakeSearcher) Ingest(_ context.Context, body []byte) ([]byte, error) {
if len(bytes.TrimSpace(body)) == 0 {
return []byte(`{"mode":"add","command":"bin/brain/add.go"}`), nil
}
return []byte(`{"mode":"add","ids":["fake-leaf"]}`), nil
func (f *fakeSearcher) Ingest(context.Context) ([]byte, error) {
return []byte(`{"mode":"rebuild","command":"bin/brain/index.go --rebuild"}`), nil
}
func (f *fakeSearcher) count() int {
@@ -197,27 +193,6 @@ func TestStatsAuditIngest(t *testing.T) {
}
}
func TestIngestIsAddNotRebuildHint(t *testing.T) {
h := NewServer(&fakeSearcher{}, 1)
code, body := get(t, h, "/ingest")
if code != http.StatusOK {
t.Fatalf("GET /ingest code = %d body=%s", code, body)
}
if strings.Contains(string(body), `"add":"v2"`) || strings.Contains(string(body), "write is v2") {
t.Fatalf("GET /ingest still a v2 hint: %s", body)
}
if !strings.Contains(string(body), "bin/brain/add.go") {
t.Fatalf("GET /ingest should name add.go: %s", body)
}
code, body = postJSON(t, h, "/ingest", `{"text":"hello","root":"info","source":"t"}`)
if code != http.StatusOK {
t.Fatalf("POST /ingest code = %d body=%s", code, body)
}
if !strings.Contains(string(body), "fake-leaf") {
t.Fatalf("POST /ingest should add: %s", body)
}
}
func TestHTTPPackageDoesNotExecPython(t *testing.T) {
raw, err := os.ReadFile("server.go")
if err != nil {
+1 -9
View File
@@ -47,15 +47,7 @@ var Ops = []Op{
},
{Path: PathStats, Method: "get", ID: "stats", Summary: "index health", MCP: true},
{Path: PathAudit, Method: "get", ID: "audit", Summary: "facts confidence histogram", MCP: true},
{
Path: PathIngest, Method: "post", ID: "ingest", Summary: "add a leaf without rebuild",
MCP: true,
Params: []Param{
{Name: "text", In: "query", Type: "string", Description: "leaf text (omit for CLI hint)"},
{Name: "root", In: "query", Type: "string", Description: "facts or info (default info)"},
{Name: "source", In: "query", Type: "string", Description: "evidence pointer; facts need two sources"},
},
},
{Path: PathIngest, Method: "get", ID: "ingest", Summary: "rebuild hint (write is v2)", MCP: true},
{Path: PathOpenAPI, Method: "get", ID: "openapi", Summary: "OpenAPI 3 document for this server"},
}
+1 -14
View File
@@ -38,24 +38,11 @@ func TestMCPToolsMatchOpenAPIPaths(t *testing.T) {
t.Fatalf("MCP tool %s has no OpenAPI path %s", tool.Name, path)
}
}
for _, need := range []string{"search", "get", "stats", "audit", "ingest"} {
for _, need := range []string{"search", "get", "stats", "audit"} {
if !names[need] {
t.Fatalf("MCP tools missing %s: %v", need, names)
}
}
var ingest MCPTool
for _, tool := range tools {
if tool.Name == "ingest" {
ingest = tool
break
}
}
if strings.Contains(ingest.Description, "v2") {
t.Fatalf("ingest still a v2 hint: %s", ingest.Description)
}
if !strings.Contains(ingest.Description, "add") {
t.Fatalf("ingest should describe add: %s", ingest.Description)
}
}
func TestOpenAPIHTTP(t *testing.T) {
+3 -3
View File
@@ -26,14 +26,14 @@ second independent source when local roots cannot confirm. An answer is
bin/brain/search.go "Matrix federation" # pointers + snippets, YAML
bin/brain/search.go "onlyoffice postgres" --root facts # restrict to confirmed
bin/brain/search.go "where is cs-lexicon" --json | yq '.[].ref'
bin/brain/add.go --text T --root facts --source "a.md x b.md"
bin/brain/get.go <id> --body # full chunk only when needed
bin/brain/stats.go # index health
bin/brain/eval.go # recall@5 >= 0.95 gate (Go; Python bin/kb/eval is CI fallback)
```
`bin/kb/search` is a deprecated wrapper. `--hop N` walks
`FROM_FILE` / `HAS_VERSION` / `AUTHORED` from each hit (1=File, 3=Person).
`bin/kb/search` is a deprecated wrapper. `--hop` errors (schema has
`FROM_FILE`; search does not walk it yet, [#17](https://git.produktor.io/eSlider/2dph/issues/17));
do not treat it as a graph walk.
## Rules
+1 -1
View File
@@ -8,4 +8,4 @@ Serve: `bin/brain/serve.go` (`GET /openapi.json`, `POST /mcp`).
- `get` — read one leaf by id
- `stats` — index health
- `audit` — facts confidence histogram
- `ingest`add a leaf without rebuild
- `ingest`rebuild hint (write is v2)