mirror of
https://github.com/norandom/OpenUltraSAST.git
synced 2026-10-16 19:59:26 +00:00
chore(index): remove the unused vector index, the ousast index subcommand and the [embeddings] section
Legacy inventory 2, item R1. The vector half of index.py (VectorIndex, VectorRecord, RetrievalHit, RetrievalPackage, the EmbeddingClient protocol, index_reuse_key, build/write/read/query_vector_index, build_retrieval_package and their helpers) had no importer in src; `ousast index` wrote index/chunks.json that nothing read, and was the only reader of `[embeddings]`. index.py keeps CodeChunk and chunk_text_namespace, which skills.py imports; chunk_file/build_code_chunks go with their only caller. `[embeddings] model` and `[embeddings] store` join RETIRED_KEYS (RetiredConfigError naming the reason), the same way the [variants] keys were retired; OPENROUTER_EMBEDDING_MODEL is no longer read, so the README and .env.example drop it (`ousast learn memory embed --model` names the model). test_index.py now tests the chunker only; test_config.py covers the two retired keys and no longer asserts the removed field. The module audit record is regenerated (counts unchanged: 151 modules, 0 orphaned; the index module's importer list shrinks to skills). RELEASE_NOTES Unreleased carries the line. Co-Authored-By: Claude Fable 5.1 <[email protected]> Claude-Session: https://claude.ai/code/session_01EmM1j46qgKMh3zqD1QMwEo
This commit is contained in:
Marius Ciepluch
co-authored by
Claude Fable 5.1
Claude Fable 5.1
parent
69b5e0efcc
commit
e1db7e1920
@@ -43,7 +43,6 @@ from .gate import FALSE_POSITIVE_CEILING, RECALL_FLOOR
|
||||
from .harness import HarnessRuntime, HarnessTraceWriter, write_harness_config
|
||||
from .hunter import run_hunter_pool, write_hunter_trajectories
|
||||
from .improve import RoundOutcome, run_improvement
|
||||
from .index import build_code_chunks
|
||||
from .learn.cli import add_commands as add_learn_commands
|
||||
from .learn.cli import run as run_learn
|
||||
from .mapping import analyze_entry_points, attach_reachability_hints, ingest_sarif, write_entry_points, write_static_hints
|
||||
@@ -173,11 +172,6 @@ def _main(argv: list[str] | None) -> int:
|
||||
scan.add_argument("--config", type=Path, default=Path("openultrasast.toml"))
|
||||
scan.add_argument("--fail-on", choices=("never", "findings", "verified", "worth-fixing"), default="never")
|
||||
|
||||
index = subparsers.add_parser("index", help="chunk a local repository for embedding index construction")
|
||||
index.add_argument("path", type=Path)
|
||||
index.add_argument("--config", type=Path, default=Path("openultrasast.toml"))
|
||||
index.add_argument("--chunk-lines", type=int, default=80)
|
||||
|
||||
benchmark = subparsers.add_parser("benchmark", help="run a benchmark manifest and write scoreboard artifacts")
|
||||
benchmark.add_argument("manifest", type=Path)
|
||||
benchmark.add_argument("--mode", choices=("quick", "standard", "deep"), default="quick")
|
||||
@@ -426,8 +420,6 @@ def _main(argv: list[str] | None) -> int:
|
||||
return delivery.exit_code
|
||||
if args.command == "scan":
|
||||
return _scan(args.path, args.config, args.mode, args.fail_on)
|
||||
if args.command == "index":
|
||||
return _index(args.path, args.config, args.chunk_lines)
|
||||
if args.command == "benchmark":
|
||||
return _benchmark(args.manifest, args.config, args.mode)
|
||||
if args.command == "improve":
|
||||
@@ -1564,30 +1556,5 @@ def _model_candidates(args: argparse.Namespace) -> int:
|
||||
return 0
|
||||
|
||||
|
||||
def _index(path: Path, config_path: Path, chunk_lines: int) -> int:
|
||||
if not path.exists() or not path.is_dir():
|
||||
raise SystemExit(f"index path is not a directory: {path}")
|
||||
config = load_config(config_path if config_path.exists() else None)
|
||||
run = create_scan_run(path, config)
|
||||
snapshot, targets = preprocess_repository(run.target, run.root / "preprocess" / "file_targets.json")
|
||||
chunks = build_code_chunks(run.target, targets, max_lines=chunk_lines)
|
||||
payload = {
|
||||
"store": config.embeddings.store or "json-local",
|
||||
"embedding_model": config.embeddings.model,
|
||||
"repo_root": snapshot.root,
|
||||
"repo_commit": snapshot.commit,
|
||||
"chunk_count": len(chunks),
|
||||
"chunks": [chunk.__dict__ for chunk in chunks],
|
||||
}
|
||||
path_out = run.root / "index" / "chunks.json"
|
||||
path_out.parent.mkdir(parents=True, exist_ok=True)
|
||||
path_out.write_text(json.dumps(payload, indent=2, sort_keys=True) + "\n")
|
||||
print(f"scan_id={run.scan_id}")
|
||||
print(f"run_dir={run.root}")
|
||||
print(f"chunks={len(chunks)}")
|
||||
print(f"index_artifact={path_out}")
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
|
||||
@@ -10,8 +10,6 @@ from typing import Literal
|
||||
|
||||
from openultrasast.contracts import Contract
|
||||
|
||||
DEFAULT_VECTOR_STORE = "json-local"
|
||||
|
||||
# Retirement notes (harnessx-removal Req 1.3, 3.3). A key that asked for a retired LLM capability fails and names
|
||||
# the replacement, never a silent downgrade; the old budget section only warns. Every line below that names the
|
||||
# removed plane carries its retirement date, which the reference-search test holds the rest of the tree to.
|
||||
@@ -26,6 +24,10 @@ _UNREAD_ON = "retired 2026-10-02 because nothing ever read it"
|
||||
_UNREAD_DYNAMIC = "no dynamic or deep tier exists; deep mode will define its own keys when it is built"
|
||||
_UNREAD_EVIDENCE = "evidence tiers come from the program model's ladder (model/ladder.py), not from configuration"
|
||||
_UNREAD_VARIANTS = "the structural variant search it configured was deleted with semantic/variants.py"
|
||||
_UNREAD_EMBEDDINGS = (
|
||||
"the json-local vector index it configured and `ousast index` were deleted; the decision engine embeds through "
|
||||
"`ousast learn memory embed --model` (learn/embeddings.py)"
|
||||
)
|
||||
RETIRED_KEYS: dict[tuple[str, str], str] = {
|
||||
("models", "verifier"): f"{_RETIRED_ON}: LLM verification runs on the plane (`verify` + `agree`, {_PLANE_RUN})",
|
||||
("fusion", "panel_model"): f"{_RETIRED_ON}: {_RETIRED_PANELS}",
|
||||
@@ -38,6 +40,8 @@ RETIRED_KEYS: dict[tuple[str, str], str] = {
|
||||
("evidence", "minimum_patch"): f"{_UNREAD_ON}: {_UNREAD_EVIDENCE}",
|
||||
("variants", "enabled"): f"{_UNREAD_ON}: {_UNREAD_VARIANTS}",
|
||||
("variants", "max_mechanisms"): f"{_UNREAD_ON}: {_UNREAD_VARIANTS}",
|
||||
("embeddings", "model"): f"{_UNREAD_ON}: {_UNREAD_EMBEDDINGS}",
|
||||
("embeddings", "store"): f"{_UNREAD_ON}: {_UNREAD_EMBEDDINGS}",
|
||||
}
|
||||
RETIRED_SECTION = "harnessx" # retired 2026-09-30: loads with one warning and is otherwise ignored (Req 3.3)
|
||||
RETIRED_SECTION_WARNING = (
|
||||
@@ -94,12 +98,6 @@ class ModelConfig:
|
||||
thinking: bool = False
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class EmbeddingConfig:
|
||||
model: str | None = None
|
||||
store: str = DEFAULT_VECTOR_STORE
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class SandboxConfig:
|
||||
network: bool = False
|
||||
@@ -205,7 +203,6 @@ class PushConfig(Contract):
|
||||
@dataclass(frozen=True)
|
||||
class ResolvedConfig:
|
||||
models: ModelConfig = ModelConfig()
|
||||
embeddings: EmbeddingConfig = EmbeddingConfig()
|
||||
sandbox: SandboxConfig = SandboxConfig()
|
||||
static_analysis: StaticAnalysisConfig = StaticAnalysisConfig()
|
||||
score: ScoreConfig = ScoreConfig()
|
||||
@@ -231,7 +228,6 @@ def load_config(config_path: Path | None = None, *, dotenv: bool = True) -> Reso
|
||||
|
||||
return ResolvedConfig(
|
||||
models=_load_models(data.get("models", {})),
|
||||
embeddings=_load_embeddings(data.get("embeddings", {})),
|
||||
sandbox=_load_sandbox(data.get("sandbox", {})),
|
||||
static_analysis=_load_static_analysis(data.get("static_analysis", {})),
|
||||
score=_load_score(data.get("score", {})),
|
||||
@@ -277,14 +273,6 @@ def _load_models(value: object) -> ModelConfig:
|
||||
)
|
||||
|
||||
|
||||
def _load_embeddings(value: object) -> EmbeddingConfig:
|
||||
data = _section(value)
|
||||
return EmbeddingConfig(
|
||||
model=_string(data.get("model")) or _string(os.environ.get("OPENROUTER_EMBEDDING_MODEL")),
|
||||
store=_string(data.get("store")) or DEFAULT_VECTOR_STORE,
|
||||
)
|
||||
|
||||
|
||||
def _load_sandbox(value: object) -> SandboxConfig:
|
||||
data = _section(value)
|
||||
return SandboxConfig(
|
||||
|
||||
+8
-207
@@ -1,13 +1,14 @@
|
||||
"""Text chunking for the skill router (`skills.py`).
|
||||
|
||||
The vector index that once lived beside the chunker (`VectorIndex`, `build_vector_index`, `query_vector_index`,
|
||||
`build_retrieval_package`) and the `ousast index` subcommand that fed it were removed on 2026-10-02: nothing ever
|
||||
read the `chunks.json` they wrote. The decision engine's embeddings live in `learn/embeddings.py`.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import hashlib
|
||||
import json
|
||||
import math
|
||||
from dataclasses import asdict, dataclass
|
||||
from pathlib import Path
|
||||
from typing import Protocol
|
||||
|
||||
from .preprocess import FileTarget, RepoSnapshot
|
||||
from dataclasses import dataclass
|
||||
|
||||
VALID_NAMESPACES = {"repo_code", "docs", "static_findings", "mechanisms", "skills", "traces"}
|
||||
|
||||
@@ -24,82 +25,6 @@ class CodeChunk:
|
||||
metadata: dict[str, str | int | bool]
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class VectorRecord:
|
||||
chunk: CodeChunk
|
||||
embedding: list[float]
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class VectorIndex:
|
||||
store: str
|
||||
embedding_model: str
|
||||
repo_root: str
|
||||
repo_commit: str | None
|
||||
records: list[VectorRecord]
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class RetrievalHit:
|
||||
score: float
|
||||
chunk: CodeChunk
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class RetrievalPackage:
|
||||
role: str
|
||||
hits: list[RetrievalHit]
|
||||
text: str
|
||||
truncated: bool
|
||||
|
||||
|
||||
class EmbeddingClient(Protocol):
|
||||
def embed(self, *, model: str, inputs: list[str], timeout_seconds: int = 60) -> list[list[float]]:
|
||||
raise NotImplementedError
|
||||
|
||||
|
||||
def chunk_file(root: Path, target: FileTarget, *, max_lines: int = 80) -> list[CodeChunk]:
|
||||
if max_lines < 1:
|
||||
raise ValueError("max_lines must be at least 1")
|
||||
text = (root / target.path).read_text(errors="ignore")
|
||||
lines = text.splitlines()
|
||||
chunks: list[CodeChunk] = []
|
||||
for start in range(0, len(lines), max_lines):
|
||||
chunk_lines = lines[start : start + max_lines]
|
||||
if not any(line.strip() for line in chunk_lines):
|
||||
continue
|
||||
start_line = start + 1
|
||||
end_line = start + len(chunk_lines)
|
||||
chunk_text = "\n".join(chunk_lines)
|
||||
chunks.append(
|
||||
CodeChunk(
|
||||
chunk_id=_chunk_id(target.path, start_line, end_line, chunk_text),
|
||||
namespace="repo_code",
|
||||
path=target.path,
|
||||
language=target.language,
|
||||
start_line=start_line,
|
||||
end_line=end_line,
|
||||
text=chunk_text,
|
||||
metadata={
|
||||
"path": target.path,
|
||||
"language": target.language,
|
||||
"start_line": start_line,
|
||||
"end_line": end_line,
|
||||
"has_fuzz_entry_point": target.has_fuzz_entry_point,
|
||||
"tags": ",".join(target.tags),
|
||||
},
|
||||
)
|
||||
)
|
||||
return chunks
|
||||
|
||||
|
||||
def build_code_chunks(root: Path, targets: list[FileTarget], *, max_lines: int = 80) -> list[CodeChunk]:
|
||||
chunks: list[CodeChunk] = []
|
||||
for target in targets:
|
||||
chunks.extend(chunk_file(root, target, max_lines=max_lines))
|
||||
return chunks
|
||||
|
||||
|
||||
def chunk_text_namespace(
|
||||
*,
|
||||
namespace: str,
|
||||
@@ -144,130 +69,6 @@ def chunk_text_namespace(
|
||||
return chunks
|
||||
|
||||
|
||||
def index_reuse_key(snapshot: RepoSnapshot, embedding_model: str) -> str:
|
||||
source = {
|
||||
"root": snapshot.root,
|
||||
"commit": snapshot.commit,
|
||||
"file_count": snapshot.file_count,
|
||||
"languages": snapshot.languages,
|
||||
"embedding_model": embedding_model,
|
||||
}
|
||||
return hashlib.sha256(json.dumps(source, sort_keys=True).encode()).hexdigest()[:24]
|
||||
|
||||
|
||||
def build_vector_index(
|
||||
*,
|
||||
snapshot: RepoSnapshot,
|
||||
chunks: list[CodeChunk],
|
||||
embedding_model: str,
|
||||
client: EmbeddingClient,
|
||||
store: str = "json-local",
|
||||
batch_size: int = 32,
|
||||
) -> VectorIndex:
|
||||
if batch_size < 1:
|
||||
raise ValueError("batch_size must be at least 1")
|
||||
records: list[VectorRecord] = []
|
||||
for start in range(0, len(chunks), batch_size):
|
||||
batch = chunks[start : start + batch_size]
|
||||
vectors = client.embed(model=embedding_model, inputs=[chunk.text for chunk in batch])
|
||||
if len(vectors) != len(batch):
|
||||
raise ValueError("embedding response count did not match chunk count")
|
||||
records.extend(VectorRecord(chunk=chunk, embedding=vector) for chunk, vector in zip(batch, vectors, strict=True))
|
||||
return VectorIndex(
|
||||
store=store,
|
||||
embedding_model=embedding_model,
|
||||
repo_root=snapshot.root,
|
||||
repo_commit=snapshot.commit,
|
||||
records=records,
|
||||
)
|
||||
|
||||
|
||||
def write_vector_index(index: VectorIndex, path: Path) -> None:
|
||||
path.parent.mkdir(parents=True, exist_ok=True)
|
||||
path.write_text(json.dumps(_index_to_payload(index), indent=2, sort_keys=True) + "\n")
|
||||
|
||||
|
||||
def read_vector_index(path: Path) -> VectorIndex:
|
||||
payload = json.loads(path.read_text())
|
||||
return VectorIndex(
|
||||
store=str(payload["store"]),
|
||||
embedding_model=str(payload["embedding_model"]),
|
||||
repo_root=str(payload["repo_root"]),
|
||||
repo_commit=payload.get("repo_commit"),
|
||||
records=[
|
||||
VectorRecord(
|
||||
chunk=CodeChunk(**item["chunk"]),
|
||||
embedding=[float(value) for value in item["embedding"]],
|
||||
)
|
||||
for item in payload.get("records", [])
|
||||
],
|
||||
)
|
||||
|
||||
|
||||
def query_vector_index(
|
||||
index: VectorIndex,
|
||||
query_embedding: list[float],
|
||||
*,
|
||||
metadata_filter: dict[str, str | int | bool] | None = None,
|
||||
limit: int = 5,
|
||||
) -> list[tuple[float, CodeChunk]]:
|
||||
matches: list[tuple[float, CodeChunk]] = []
|
||||
for record in index.records:
|
||||
if metadata_filter and not _metadata_matches(record.chunk.metadata, metadata_filter):
|
||||
continue
|
||||
matches.append((_cosine_similarity(query_embedding, record.embedding), record.chunk))
|
||||
return sorted(matches, key=lambda item: item[0], reverse=True)[:limit]
|
||||
|
||||
|
||||
def build_retrieval_package(
|
||||
*,
|
||||
role: str,
|
||||
index: VectorIndex,
|
||||
query_embedding: list[float],
|
||||
metadata_filter: dict[str, str | int | bool] | None = None,
|
||||
limit: int = 5,
|
||||
max_chars: int = 4000,
|
||||
) -> RetrievalPackage:
|
||||
hits: list[RetrievalHit] = []
|
||||
parts: list[str] = []
|
||||
total = 0
|
||||
truncated = False
|
||||
for score, chunk in query_vector_index(index, query_embedding, metadata_filter=metadata_filter, limit=limit):
|
||||
block = f"[{chunk.namespace}] {chunk.path}:{chunk.start_line}-{chunk.end_line}\n{chunk.text}"
|
||||
if total + len(block) > max_chars:
|
||||
truncated = True
|
||||
break
|
||||
hits.append(RetrievalHit(score=score, chunk=chunk))
|
||||
parts.append(block)
|
||||
total += len(block)
|
||||
return RetrievalPackage(role=role, hits=hits, text="\n\n".join(parts), truncated=truncated)
|
||||
|
||||
|
||||
def _index_to_payload(index: VectorIndex) -> dict[str, object]:
|
||||
return {
|
||||
"store": index.store,
|
||||
"embedding_model": index.embedding_model,
|
||||
"repo_root": index.repo_root,
|
||||
"repo_commit": index.repo_commit,
|
||||
"records": [{"chunk": asdict(record.chunk), "embedding": record.embedding} for record in index.records],
|
||||
}
|
||||
|
||||
|
||||
def _metadata_matches(metadata: dict[str, str | int | bool], expected: dict[str, str | int | bool]) -> bool:
|
||||
return all(metadata.get(key) == value for key, value in expected.items())
|
||||
|
||||
|
||||
def _cosine_similarity(left: list[float], right: list[float]) -> float:
|
||||
if len(left) != len(right):
|
||||
return 0.0
|
||||
numerator = sum(a * b for a, b in zip(left, right, strict=True))
|
||||
left_norm = math.sqrt(sum(a * a for a in left))
|
||||
right_norm = math.sqrt(sum(b * b for b in right))
|
||||
if left_norm == 0 or right_norm == 0:
|
||||
return 0.0
|
||||
return numerator / (left_norm * right_norm)
|
||||
|
||||
|
||||
def _chunk_id(path: str, start_line: int, end_line: int, text: str) -> str:
|
||||
digest = hashlib.sha256(f"{path}:{start_line}:{end_line}:{text}".encode()).hexdigest()[:16]
|
||||
return f"{path}:{start_line}-{end_line}:{digest}"
|
||||
|
||||
Reference in New Issue
Block a user