Sprint 0-1: Python indexer, TS plugin scaffolding, and test suite

## What's new

**Python indexer (`python/obsidian_rag/`)** — full pipeline from scan to LanceDB:
- `config.py` — JSON config loader with cross-platform path resolution
- `security.py` — path traversal prevention, HTML stripping, sensitive content detection, dir allow/deny lists
- `chunker.py` — section-split for journal entries (date-named files), sliding-window for unstructured notes
- `embedder.py` — Ollama `/api/embeddings` client with batched requests and timeout/error handling
- `vector_store.py` — LanceDB schema, upsert (merge_insert), delete, search with filters, stats
- `indexer.py` — full/sync/reindex pipeline orchestrator with progress yields
- `cli.py` — `index | sync | reindex | status` CLI commands

**TypeScript plugin (`src/`)** — OpenClaw plugin scaffold:
- `utils/` — config loader, TypeScript types, response envelope factory, LanceDB client
- `services/` — health state machine (HEALTHY/DEGRADED/UNAVAILABLE), vault watcher with debounce/batching, indexer bridge (subprocess spawner)
- `tools/` — 4 tool stubs: search, index, status, memory_store (OpenClaw wiring pending)
- `index.ts` — plugin entry point with health probe + vault watcher startup

**Config** (`obsidian-rag/config.json`, `openclaw.plugin.json`):
- 627 files / 3764 chunks indexed in dev vault

**Tests: 76 passing**
- Python: 64 pytest tests (chunker, security, vector_store, config)
- TypeScript: 12 vitest tests (lancedb client, response envelope)

## Bugs fixed

- LanceDB `tags` column filter: `LIKE '%tag%'` → `list_contains(tags, 'tag')` (List<String> column)
- LanceDB JS `db.list_tables()` returns `ListTablesResponse` object, not plain array
- LanceDB JS result score field: `_score` → `_distance`
- TypeScript regex literal with unescaped `/` in path-resolve regex
- Python: `create_table_if_not_exists` identity check → name comparison

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-04-10 22:56:50 -04:00
parent 18ad47e100
commit 5c281165c7
40 changed files with 5814 additions and 59 deletions

130
src/services/health.ts Normal file
View File

@@ -0,0 +1,130 @@
/** Health state machine: HEALTHY / DEGRADED / UNAVAILABLE. */
import { existsSync, readFileSync } from "fs";
import { resolve } from "path";
import type { ObsidianRagConfig } from "../utils/config.js";
export type HealthState = "healthy" | "degraded" | "unavailable";
export interface HealthStatus {
state: HealthState;
ollama_up: boolean;
index_exists: boolean;
vault_exists: boolean;
total_docs: number;
total_chunks: number;
last_sync: string | null;
active_job: { id: string; mode: string; progress: number } | null;
}
export interface ProbeResult {
ollama_up: boolean;
index_exists: boolean;
vault_exists: boolean;
total_docs: number;
total_chunks: number;
last_sync: string | null;
}
const REPROBE_INTERVAL_MS = 30_000;
export function createHealthMachine(_config: ObsidianRagConfig) {
let currentState: HealthState = "unavailable";
let status: ProbeResult = {
ollama_up: false,
index_exists: false,
vault_exists: false,
total_docs: 0,
total_chunks: 0,
last_sync: null,
};
let activeJob: { id: string; mode: string; progress: number } | null = null;
let reprobeTimer: ReturnType<typeof setInterval> | null = null;
function transition(probe: ProbeResult): void {
status = probe;
const prev = currentState;
if (!probe.index_exists || !probe.vault_exists) {
currentState = "unavailable";
} else if (!probe.ollama_up) {
currentState = "degraded";
} else {
currentState = "healthy";
}
if (prev !== currentState) {
console.log(`[obsidian-rag] Health: ${prev}${currentState}`);
}
}
function get(): HealthStatus {
return { state: currentState, ...status, active_job: activeJob };
}
function setActiveJob(job: { id: string; mode: string; progress: number } | null): void {
activeJob = job;
}
function startReprobing(fn: () => Promise<ProbeResult>): void {
if (reprobeTimer) clearInterval(reprobeTimer);
reprobeTimer = setInterval(async () => {
const probe = await fn();
transition(probe);
}, REPROBE_INTERVAL_MS);
}
function stop(): void {
if (reprobeTimer) {
clearInterval(reprobeTimer);
reprobeTimer = null;
}
}
return { get, transition, setActiveJob, startReprobing, stop };
}
export async function probeAll(config: ObsidianRagConfig): Promise<ProbeResult> {
const { resolveVectorDbPath } = await import("../utils/lancedb.js");
const vaultPath = resolve(process.cwd(), config.vault_path);
const dbPath = resolveVectorDbPath(config);
const vaultExists = existsSync(vaultPath);
const indexExists = existsSync(String(dbPath));
const ollamaUp = await probeOllama(config.embedding.base_url);
let totalDocs = 0;
let totalChunks = 0;
let lastSync: string | null = null;
if (indexExists) {
try {
const syncPath = resolve(dbPath, "..", "sync-result.json");
if (existsSync(syncPath)) {
const data = JSON.parse(readFileSync(syncPath, "utf-8"));
lastSync = data.timestamp ?? null;
totalDocs = data.indexed_files ?? 0;
totalChunks = data.total_chunks ?? 0;
}
} catch {
// ignore
}
}
return {
ollama_up: ollamaUp,
index_exists: indexExists,
vault_exists: vaultExists,
total_docs: totalDocs,
total_chunks: totalChunks,
last_sync: lastSync,
};
}
async function probeOllama(baseUrl: string): Promise<boolean> {
try {
const res = await fetch(`${baseUrl}/api/tags`, { signal: AbortSignal.timeout(3000) });
return res.ok;
} catch {
return false;
}
}