Compare commits
15 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 uncle6me-web
|
a5e4caf5cb | ||
|
uncle6me-web
|
e69d6bbc03 | ||
|
uncle6me-web
|
b302c03ea8 | ||
|
uncle6me-web
|
c497ec418e | ||
|
uncle6me-web
|
6985bf4850 | ||
|
uncle6me-web
|
8e10f1d83e | ||
|
uncle6me-web
|
3eb8b31f2b | ||
|
uncle6me-web
|
8cee9c9f76 | ||
|
uncle6me-web
|
7e3ca4c1a1 | ||
|
uncle6me-web
|
af3edff856 | ||
|
uncle6me-web
|
c5d696556e | ||
|
uncle6me-web
|
5919c6b90f | ||
|
uncle6me-web
|
37e13fc9bf | ||
|
uncle6me-web
|
674e1b4fa2 | ||
|
uncle6me-web
|
1d6dde4a01 |
@@ -1,7 +1,12 @@
|
||||
var __defProp = Object.defineProperty;
|
||||
var __getOwnPropNames = Object.getOwnPropertyNames;
|
||||
var __esm = (fn, res) => function __init() {
|
||||
return fn && (res = (0, fn[__getOwnPropNames(fn)[0]])(fn = 0)), res;
|
||||
var __esm = (fn, res, err2) => function __init() {
|
||||
if (err2) throw err2[0];
|
||||
try {
|
||||
return fn && (res = (0, fn[__getOwnPropNames(fn)[0]])(fn = 0)), res;
|
||||
} catch (e) {
|
||||
throw err2 = [e], e;
|
||||
}
|
||||
};
|
||||
var __export = (target, all) => {
|
||||
for (var name in all)
|
||||
@@ -102,7 +107,7 @@ function applyBaseRuntimeOptions(runtime, options) {
|
||||
function applyModuleEvalRuntimeOptions(runtime, options) {
|
||||
options.moduleLoader && runtime.setModuleLoader(options.moduleLoader), options.shouldInterrupt && runtime.setInterruptHandler(options.shouldInterrupt), options.memoryLimitBytes !== void 0 && runtime.setMemoryLimit(options.memoryLimitBytes), options.maxStackSizeBytes !== void 0 && runtime.setMaxStackSize(options.maxStackSizeBytes);
|
||||
}
|
||||
var __defProp2, __export2, QTS_DEBUG, errors_exports, QuickJSUnwrapError, QuickJSWrongOwner, QuickJSUseAfterFree, QuickJSNotImplemented, QuickJSAsyncifyError, QuickJSAsyncifySuspended, QuickJSMemoryLeakDetected, QuickJSEmscriptenModuleError, QuickJSUnknownIntrinsic, QuickJSPromisePending, QuickJSEmptyGetOwnPropertyNames, AwaitYield, UsingDisposable, SymbolDispose, prototypeAsAny, Lifetime, StaticLifetime, WeakLifetime, Scope, AbstractDisposableResult, DisposableSuccess, DisposableFail, DisposableResult, QuickJSDeferredPromise, ModuleMemory, UnstableSymbol, DefaultIntrinsics, QuickJSIterator, ContextMemory, QuickJSContext, QuickJSRuntime, QuickJSEmscriptenModuleCallbacks, QuickJSModuleCallbacks, QuickJSWASMModule;
|
||||
var __defProp2, __export2, QTS_DEBUG, errors_exports, QuickJSUnwrapError, QuickJSWrongOwner, QuickJSUseAfterFree, QuickJSNotImplemented, QuickJSAsyncifyError, QuickJSAsyncifySuspended, QuickJSMemoryLeakDetected, QuickJSEmscriptenModuleError, QuickJSUnknownIntrinsic, QuickJSPromisePending, QuickJSEmptyGetOwnPropertyNames, AwaitYield, UsingDisposable, SymbolDispose, prototypeAsAny, Lifetime, StaticLifetime, WeakLifetime, Scope, AbstractDisposableResult, DisposableSuccess, DisposableFail, DisposableResult, QuickJSDeferredPromise, ModuleMemory, DefaultIntrinsics, QuickJSIterator, ContextMemory, QuickJSContext, QuickJSRuntime, QuickJSEmscriptenModuleCallbacks, QuickJSModuleCallbacks, QuickJSWASMModule;
|
||||
var init_chunk_JTKJZQYV = __esm({
|
||||
"registry/components/code/node_modules/quickjs-emscripten-core/dist/chunk-JTKJZQYV.mjs"() {
|
||||
init_dist();
|
||||
@@ -190,7 +195,7 @@ var init_chunk_JTKJZQYV = __esm({
|
||||
return this.dispose();
|
||||
}
|
||||
};
|
||||
SymbolDispose = Symbol.dispose ?? Symbol.for("Symbol.dispose");
|
||||
SymbolDispose = Symbol.dispose ?? /* @__PURE__ */ Symbol.for("Symbol.dispose");
|
||||
prototypeAsAny = UsingDisposable.prototype;
|
||||
prototypeAsAny[SymbolDispose] || (prototypeAsAny[SymbolDispose] = function() {
|
||||
return this.dispose();
|
||||
@@ -409,7 +414,6 @@ Lifetime used`) : new QuickJSUseAfterFree("Lifetime not alive");
|
||||
return this.module._free(ptr), str;
|
||||
}
|
||||
};
|
||||
UnstableSymbol = Symbol("Unstable");
|
||||
DefaultIntrinsics = Object.freeze({ BaseObjects: true, Date: true, Eval: true, StringNormalize: true, RegExp: true, JSON: true, Proxy: true, MapSet: true, TypedArrays: true, Promise: true });
|
||||
QuickJSIterator = class extends UsingDisposable {
|
||||
constructor(handle, context) {
|
||||
@@ -773,7 +777,7 @@ ${cause.stack}Host: ${hostStack}`), Object.assign(exception, rest), exception;
|
||||
}
|
||||
return result.value;
|
||||
}
|
||||
[Symbol.for("nodejs.util.inspect.custom")]() {
|
||||
[/* @__PURE__ */ Symbol.for("nodejs.util.inspect.custom")]() {
|
||||
return this.alive ? `${this.constructor.name} { ctx: ${this.ctx.value} rt: ${this.rt.value} }` : `${this.constructor.name} { disposed }`;
|
||||
}
|
||||
getFunction(fn_id) {
|
||||
@@ -909,7 +913,7 @@ ${cause.stack}Host: ${hostStack}`), Object.assign(exception, rest), exception;
|
||||
debugLog(...msg) {
|
||||
this._debugMode && console.log("quickjs-emscripten:", ...msg);
|
||||
}
|
||||
[Symbol.for("nodejs.util.inspect.custom")]() {
|
||||
[/* @__PURE__ */ Symbol.for("nodejs.util.inspect.custom")]() {
|
||||
return this.alive ? `${this.constructor.name} { rt: ${this.rt.value} }` : `${this.constructor.name} { disposed }`;
|
||||
}
|
||||
getSystemContext() {
|
||||
@@ -1339,10 +1343,10 @@ async function QuickJSRaw(moduleArg = {}) {
|
||||
x ? (0 === h && (h = ra()), g[m] = x(e[m])) : g[m] = e[m];
|
||||
}
|
||||
b = a(...g);
|
||||
return b = function(k) {
|
||||
return b = (function(k) {
|
||||
0 !== h && sa(h);
|
||||
return "string" === d ? R(k) : "boolean" === d ? !!k : k;
|
||||
}(b);
|
||||
})(b);
|
||||
};
|
||||
c.wasmMemory ? r = c.wasmMemory : r = new WebAssembly.Memory({ initial: (c.INITIAL_MEMORY || 16777216) / 65536, maximum: 32768 });
|
||||
K();
|
||||
@@ -1464,7 +1468,7 @@ async function QuickJSRaw(moduleArg = {}) {
|
||||
}, t: function(a, d) {
|
||||
c.callbacks.freeHostRef(void 0, a, d);
|
||||
} }, Z;
|
||||
Z = await async function() {
|
||||
Z = await (async function() {
|
||||
function a(b) {
|
||||
b = Z = b.exports;
|
||||
c._malloc = b.v;
|
||||
@@ -1551,7 +1555,7 @@ async function QuickJSRaw(moduleArg = {}) {
|
||||
});
|
||||
M ??= c.locateFile ? c.locateFile ? c.locateFile("emscripten-module.wasm", u) : u + "emscripten-module.wasm" : new URL("emscripten-module.wasm", import.meta.url).href;
|
||||
return a((await ea(d)).instance);
|
||||
}();
|
||||
})();
|
||||
(function() {
|
||||
function a() {
|
||||
c.calledRun = true;
|
||||
@@ -3034,7 +3038,7 @@ var Hono = class _Hono {
|
||||
var emptyParam = [];
|
||||
function match(method, path) {
|
||||
const matchers = this.buildAllMatchers();
|
||||
const match2 = (method2, path2) => {
|
||||
const match2 = ((method2, path2) => {
|
||||
const matcher = matchers[method2] || matchers[METHOD_NAME_ALL];
|
||||
const staticMatch = matcher[2][path2];
|
||||
if (staticMatch) {
|
||||
@@ -3046,7 +3050,7 @@ function match(method, path) {
|
||||
}
|
||||
const index = match3.indexOf("", 1);
|
||||
return [matcher[1][index], match3];
|
||||
};
|
||||
});
|
||||
this.match = match2;
|
||||
return match2(method, path);
|
||||
}
|
||||
@@ -4008,7 +4012,7 @@ app.post("/", async (c) => {
|
||||
);
|
||||
}
|
||||
});
|
||||
var code_default = app;
|
||||
var index_default = app;
|
||||
export {
|
||||
code_default as default
|
||||
index_default as default
|
||||
};
|
||||
|
||||
@@ -1,7 +1,12 @@
|
||||
var __defProp = Object.defineProperty;
|
||||
var __getOwnPropNames = Object.getOwnPropertyNames;
|
||||
var __esm = (fn, res) => function __init() {
|
||||
return fn && (res = (0, fn[__getOwnPropNames(fn)[0]])(fn = 0)), res;
|
||||
var __esm = (fn, res, err) => function __init() {
|
||||
if (err) throw err[0];
|
||||
try {
|
||||
return fn && (res = (0, fn[__getOwnPropNames(fn)[0]])(fn = 0)), res;
|
||||
} catch (e) {
|
||||
throw err = [e], e;
|
||||
}
|
||||
};
|
||||
var __export = (target, all) => {
|
||||
for (var name in all)
|
||||
@@ -1501,7 +1506,7 @@ var init_hono_base = __esm({
|
||||
// cypher-executor/node_modules/.pnpm/hono@4.12.10/node_modules/hono/dist/router/reg-exp-router/matcher.js
|
||||
function match(method, path) {
|
||||
const matchers = this.buildAllMatchers();
|
||||
const match2 = (method2, path2) => {
|
||||
const match2 = ((method2, path2) => {
|
||||
const matcher = matchers[method2] || matchers[METHOD_NAME_ALL];
|
||||
const staticMatch = matcher[2][path2];
|
||||
if (staticMatch) {
|
||||
@@ -1513,7 +1518,7 @@ function match(method, path) {
|
||||
}
|
||||
const index = match3.indexOf("", 1);
|
||||
return [matcher[1][index], match3];
|
||||
};
|
||||
});
|
||||
this.match = match2;
|
||||
return match2(method, path);
|
||||
}
|
||||
@@ -3022,7 +3027,7 @@ async function readBodyOnce(res) {
|
||||
return text;
|
||||
}
|
||||
}
|
||||
var WASM_HTTP_RUNNER_IDS, LOGIC_BINDING_MAP;
|
||||
var WASM_HTTP_RUNNER_IDS, LOGIC_BINDING_MAP, RUNTIME_NATIVE_COMPONENT_IDS;
|
||||
var init_component_loader = __esm({
|
||||
"cypher-executor/src/lib/component-loader.ts"() {
|
||||
"use strict";
|
||||
@@ -3065,6 +3070,12 @@ var init_component_loader = __esm({
|
||||
// ai_transform_compile / ai_transform_run 已刪除（2026-05-29）：
|
||||
// Arcrun 是 AI 呼叫的工具，工作流不該內嵌 AI 節點回頭呼叫 AI（n8n 才需要，因它沒大腦）。
|
||||
};
|
||||
RUNTIME_NATIVE_COMPONENT_IDS = /* @__PURE__ */ new Set([
|
||||
"trigger_workflow",
|
||||
...BUILTIN_COMPONENTS.keys(),
|
||||
...Object.keys(LOGIC_BINDING_MAP),
|
||||
...WASM_HTTP_RUNNER_IDS
|
||||
]);
|
||||
}
|
||||
});
|
||||
|
||||
@@ -3201,6 +3212,20 @@ var init_kbdb_proxy = __esm({
|
||||
const res = await fetch(`${base}/records/${encodeURIComponent(c.req.param("recordId"))}`, { headers });
|
||||
return new Response(res.body, { status: res.status, headers: { "Content-Type": "application/json" } });
|
||||
});
|
||||
kbdbProxyRouter.patch("/kbdb/records/:recordId", async (c) => {
|
||||
if (!tenant(c)) return c.json(NEED_KEY, 401);
|
||||
const body = await c.req.json().catch(() => null);
|
||||
if (!body || typeof body.values !== "object" || body.values === null) {
|
||||
return c.json({ error: "values \u5FC5\u586B\uFF08{slot\u540D: \u5167\u5BB9}\uFF09" }, 400);
|
||||
}
|
||||
const { base, headers } = kbdbBase(c.env);
|
||||
const res = await fetch(`${base}/records/${encodeURIComponent(c.req.param("recordId"))}`, {
|
||||
method: "PATCH",
|
||||
headers,
|
||||
body: JSON.stringify({ values: body.values })
|
||||
});
|
||||
return new Response(res.body, { status: res.status, headers: { "Content-Type": "application/json" } });
|
||||
});
|
||||
kbdbProxyRouter.get("/kbdb/search", async (c) => {
|
||||
const owner = tenant(c);
|
||||
if (!owner) return c.json(NEED_KEY, 401);
|
||||
@@ -7355,7 +7380,7 @@ var init_lib = __esm({
|
||||
...processCreateParams(params)
|
||||
});
|
||||
};
|
||||
BRAND = Symbol("zod_brand");
|
||||
BRAND = /* @__PURE__ */ Symbol("zod_brand");
|
||||
ZodBranded = class extends ZodType {
|
||||
_parse(input) {
|
||||
const { ctx } = this._processInputParams(input);
|
||||
@@ -7529,14 +7554,14 @@ var init_lib = __esm({
|
||||
onumber = () => numberType().optional();
|
||||
oboolean = () => booleanType().optional();
|
||||
coerce = {
|
||||
string: (arg) => ZodString.create({ ...arg, coerce: true }),
|
||||
number: (arg) => ZodNumber.create({ ...arg, coerce: true }),
|
||||
boolean: (arg) => ZodBoolean.create({
|
||||
string: ((arg) => ZodString.create({ ...arg, coerce: true })),
|
||||
number: ((arg) => ZodNumber.create({ ...arg, coerce: true })),
|
||||
boolean: ((arg) => ZodBoolean.create({
|
||||
...arg,
|
||||
coerce: true
|
||||
}),
|
||||
bigint: (arg) => ZodBigInt.create({ ...arg, coerce: true }),
|
||||
date: (arg) => ZodDate.create({ ...arg, coerce: true })
|
||||
})),
|
||||
bigint: ((arg) => ZodBigInt.create({ ...arg, coerce: true })),
|
||||
date: ((arg) => ZodDate.create({ ...arg, coerce: true }))
|
||||
};
|
||||
NEVER = INVALID;
|
||||
z = /* @__PURE__ */ Object.freeze({
|
||||
@@ -7757,6 +7782,7 @@ var init_recipe_loader = __esm({
|
||||
super(message);
|
||||
this.recipe = recipe;
|
||||
}
|
||||
recipe;
|
||||
};
|
||||
}
|
||||
});
|
||||
@@ -8763,7 +8789,7 @@ function recordRecipeStats(env, recipeKeys, ok, at, ctx) {
|
||||
)
|
||||
).then(() => void 0);
|
||||
if (ctx?.waitUntil) ctx.waitUntil(promise);
|
||||
else ;
|
||||
else void promise;
|
||||
}
|
||||
function generateToken() {
|
||||
const tokenBytes = crypto.getRandomValues(new Uint8Array(16));
|
||||
@@ -8805,7 +8831,7 @@ async function executeWebhookGraph(env, graph, triggerContext, token, apiKey, ct
|
||||
result.trace
|
||||
);
|
||||
if (ctx?.waitUntil) ctx.waitUntil(statsPromise);
|
||||
else ;
|
||||
else void statsPromise;
|
||||
}
|
||||
return { success: true, data: result.data, duration_ms };
|
||||
} catch (err) {
|
||||
@@ -8829,7 +8855,7 @@ async function executeWebhookGraph(env, graph, triggerContext, token, apiKey, ct
|
||||
err.trace
|
||||
);
|
||||
if (ctx?.waitUntil) ctx.waitUntil(statsPromise);
|
||||
else ;
|
||||
else void statsPromise;
|
||||
}
|
||||
if (err instanceof ExecutionError) {
|
||||
const traceFormatted = err.trace.map((s) => ({
|
||||
@@ -9294,6 +9320,7 @@ function extractTarget(input) {
|
||||
return typeof raw2 === "string" ? raw2 : JSON.stringify(raw2);
|
||||
}
|
||||
async function writeExecutionVerdict(env, workflowId, nodes, verdict, durationMs, message, input, apiKey) {
|
||||
void nodes;
|
||||
try {
|
||||
const { base, headers } = kbdbBase(env);
|
||||
await fetch(`${base}/execution-log/record`, {
|
||||
@@ -9485,6 +9512,16 @@ async function searchNodes(parsed, config, env, mode = "discover", target) {
|
||||
nodeResults[nodeName] = { status: "found", componentId, type: role };
|
||||
continue;
|
||||
}
|
||||
if (wantComponents && RUNTIME_NATIVE_COMPONENT_IDS.has(componentId)) {
|
||||
nodeResults[nodeName] = {
|
||||
status: "found",
|
||||
componentId,
|
||||
type: role,
|
||||
source: "builtin",
|
||||
branch_hint: branchHintFor(componentId)
|
||||
};
|
||||
continue;
|
||||
}
|
||||
if (catalog.status === "unreachable") {
|
||||
nodeResults[nodeName] = { status: "unknown", componentId, type: role };
|
||||
continue;
|
||||
@@ -15257,10 +15294,10 @@ app.route("/", consoleAuthRouter);
|
||||
app.route("/", consoleDashboardRouter);
|
||||
app.route("/", portalRouter);
|
||||
app.route("/", portalDataRouter);
|
||||
var src_default = {
|
||||
var index_default = {
|
||||
fetch: app.fetch,
|
||||
scheduled: handleScheduled
|
||||
};
|
||||
export {
|
||||
src_default as default
|
||||
index_default as default
|
||||
};
|
||||
|
||||
@@ -1427,7 +1427,7 @@ var Hono = class _Hono {
|
||||
var emptyParam = [];
|
||||
function match(method, path) {
|
||||
const matchers = this.buildAllMatchers();
|
||||
const match2 = (method2, path2) => {
|
||||
const match2 = ((method2, path2) => {
|
||||
const matcher = matchers[method2] || matchers[METHOD_NAME_ALL];
|
||||
const staticMatch = matcher[2][path2];
|
||||
if (staticMatch) {
|
||||
@@ -1439,7 +1439,7 @@ function match(method, path) {
|
||||
}
|
||||
const index = match3.indexOf("", 1);
|
||||
return [matcher[1][index], match3];
|
||||
};
|
||||
});
|
||||
this.match = match2;
|
||||
return match2(method, path);
|
||||
}
|
||||
@@ -2522,7 +2522,7 @@ app.post("/", async (c) => {
|
||||
);
|
||||
}
|
||||
});
|
||||
var src_default = app;
|
||||
var index_default = app;
|
||||
async function runWasm(input) {
|
||||
const hostFunctions = {
|
||||
http_request: async (url, method, headersJson, body) => {
|
||||
@@ -2568,5 +2568,5 @@ async function runWasm(input) {
|
||||
return JSON.parse(stdout);
|
||||
}
|
||||
export {
|
||||
src_default as default
|
||||
index_default as default
|
||||
};
|
||||
|
||||
@@ -1444,7 +1444,7 @@ var Hono = class _Hono {
|
||||
var emptyParam = [];
|
||||
function match(method, path) {
|
||||
const matchers = this.buildAllMatchers();
|
||||
const match2 = (method2, path2) => {
|
||||
const match2 = ((method2, path2) => {
|
||||
const matcher = matchers[method2] || matchers[METHOD_NAME_ALL];
|
||||
const staticMatch = matcher[2][path2];
|
||||
if (staticMatch) {
|
||||
@@ -1456,7 +1456,7 @@ function match(method, path) {
|
||||
}
|
||||
const index = match3.indexOf("", 1);
|
||||
return [matcher[1][index], match3];
|
||||
};
|
||||
});
|
||||
this.match = match2;
|
||||
return match2(method, path);
|
||||
}
|
||||
@@ -2189,11 +2189,18 @@ async function deprecateEntriesByLibrary(db, ownerId, library) {
|
||||
var MAX_LIKE_Q_BYTES = 48;
|
||||
var MAX_LIKE_TERMS = 6;
|
||||
var utf8Len = (s) => new TextEncoder().encode(s).length;
|
||||
var LIKE_ESCAPE = "\\";
|
||||
var CONTENT_LIKE = `content LIKE ? ESCAPE '${LIKE_ESCAPE}'`;
|
||||
function escapeLikeLiteral(s) {
|
||||
return s.replace(/[\\%_]/g, (ch) => LIKE_ESCAPE + ch);
|
||||
}
|
||||
var likeBytes = (s) => utf8Len(escapeLikeLiteral(s));
|
||||
var likePattern = (s) => `%${escapeLikeLiteral(s)}%`;
|
||||
function chunkByBytes(s, maxBytes) {
|
||||
const out = [];
|
||||
let cur = "";
|
||||
for (const ch of s) {
|
||||
if (utf8Len(cur + ch) > maxBytes) {
|
||||
if (likeBytes(cur + ch) > maxBytes) {
|
||||
if (cur) out.push(cur);
|
||||
cur = ch;
|
||||
} else {
|
||||
@@ -2204,8 +2211,8 @@ function chunkByBytes(s, maxBytes) {
|
||||
return out;
|
||||
}
|
||||
function buildContentLike(q) {
|
||||
if (utf8Len(q) <= MAX_LIKE_Q_BYTES) {
|
||||
return { conds: ["content LIKE ?"], params: [`%${q}%`], split: false };
|
||||
if (likeBytes(q) <= MAX_LIKE_Q_BYTES) {
|
||||
return { conds: [CONTENT_LIKE], params: [likePattern(q)], split: false };
|
||||
}
|
||||
const terms = [];
|
||||
for (const word of q.split(/\s+/).filter(Boolean)) {
|
||||
@@ -2217,8 +2224,8 @@ function buildContentLike(q) {
|
||||
}
|
||||
if (terms.length === 0) terms.push(chunkByBytes(q, MAX_LIKE_Q_BYTES)[0] ?? "");
|
||||
return {
|
||||
conds: terms.map(() => "content LIKE ?"),
|
||||
params: terms.map((t) => `%${t}%`),
|
||||
conds: terms.map(() => CONTENT_LIKE),
|
||||
params: terms.map(likePattern),
|
||||
split: true
|
||||
};
|
||||
}
|
||||
@@ -2335,7 +2342,7 @@ function buildSearchScore(q) {
|
||||
if (terms.length === 0) {
|
||||
const m = buildContentLike(trimmed);
|
||||
return {
|
||||
scoreExpr: m.conds.map(() => "CASE WHEN content LIKE ? THEN 1 ELSE 0 END").join(" + "),
|
||||
scoreExpr: m.conds.map(() => `CASE WHEN ${CONTENT_LIKE} THEN 1 ELSE 0 END`).join(" + "),
|
||||
scoreParams: m.params,
|
||||
terms: [],
|
||||
legacyShape: true
|
||||
@@ -2344,14 +2351,14 @@ function buildSearchScore(q) {
|
||||
const parts = [];
|
||||
const params = [];
|
||||
for (const { term, weight } of terms) {
|
||||
parts.push(`CASE WHEN content LIKE ? THEN ${weight} ELSE 0 END`);
|
||||
params.push(`%${term}%`);
|
||||
parts.push(`CASE WHEN ${CONTENT_LIKE} THEN ${weight} ELSE 0 END`);
|
||||
params.push(likePattern(term));
|
||||
}
|
||||
const single = terms.length === 1 && terms[0].term === trimmed;
|
||||
if (!single && utf8Len(trimmed) <= MAX_LIKE_Q_BYTES) {
|
||||
if (!single && likeBytes(trimmed) <= MAX_LIKE_Q_BYTES) {
|
||||
const bonus = terms.reduce((s, t) => s + t.weight, 0);
|
||||
parts.push(`CASE WHEN content LIKE ? THEN ${bonus} ELSE 0 END`);
|
||||
params.push(`%${trimmed}%`);
|
||||
parts.push(`CASE WHEN ${CONTENT_LIKE} THEN ${bonus} ELSE 0 END`);
|
||||
params.push(likePattern(trimmed));
|
||||
}
|
||||
return { scoreExpr: parts.join(" + "), scoreParams: params, terms, legacyShape: single };
|
||||
}
|
||||
@@ -2408,6 +2415,57 @@ async function searchEntries(db, q, owner_id, entry_type, limit = 50, library, s
|
||||
return applyRelativeCut(res.results ?? []);
|
||||
}
|
||||
|
||||
// kbdb/src/actions/maintenance-quota.ts
|
||||
var DEFAULT_MAINTENANCE_DAILY_WRITE_LIMIT = 2e4;
|
||||
function maintenanceDailyLimit(env) {
|
||||
const raw2 = env.KBDB_MAINTENANCE_DAILY_WRITE_LIMIT;
|
||||
const n = raw2 ? parseInt(raw2, 10) : NaN;
|
||||
return Number.isFinite(n) && n > 0 ? n : DEFAULT_MAINTENANCE_DAILY_WRITE_LIMIT;
|
||||
}
|
||||
function utcDay() {
|
||||
return (/* @__PURE__ */ new Date()).toISOString().slice(0, 10);
|
||||
}
|
||||
function maintenanceUsageId() {
|
||||
return `kbdb-maintenance-usage:${utcDay()}`;
|
||||
}
|
||||
async function getMaintenanceUsageToday(db) {
|
||||
const row = await db.prepare("SELECT metadata_json FROM entries WHERE id = ?").bind(maintenanceUsageId()).first();
|
||||
if (!row) return 0;
|
||||
try {
|
||||
const parsed = row.metadata_json ? JSON.parse(row.metadata_json) : {};
|
||||
return Number(parsed.writes) || 0;
|
||||
} catch {
|
||||
return 0;
|
||||
}
|
||||
}
|
||||
async function addMaintenanceUsage(db, by) {
|
||||
if (by <= 0) return;
|
||||
const id = maintenanceUsageId();
|
||||
const existing = await db.prepare("SELECT metadata_json FROM entries WHERE id = ?").bind(id).first();
|
||||
let prev = 0;
|
||||
if (existing) {
|
||||
try {
|
||||
const parsed = existing.metadata_json ? JSON.parse(existing.metadata_json) : {};
|
||||
prev = Number(parsed.writes) || 0;
|
||||
} catch {
|
||||
prev = 0;
|
||||
}
|
||||
await db.prepare("UPDATE entries SET metadata_json = ?, updated_at = unixepoch() WHERE id = ?").bind(JSON.stringify({ day: utcDay(), writes: prev + by }), id).run();
|
||||
} else {
|
||||
await db.prepare(`INSERT INTO entries (id, entry_type, metadata_json) VALUES (?, 'kbdb_maintenance_usage', ?)`).bind(id, JSON.stringify({ day: utcDay(), writes: by })).run();
|
||||
}
|
||||
}
|
||||
async function maintenanceBudgetToday(env, db) {
|
||||
const limit = maintenanceDailyLimit(env);
|
||||
let used = 0;
|
||||
try {
|
||||
used = await getMaintenanceUsageToday(db);
|
||||
} catch {
|
||||
used = 0;
|
||||
}
|
||||
return { limit, used, remaining: Math.max(0, limit - used) };
|
||||
}
|
||||
|
||||
// kbdb/src/embed.ts
|
||||
var DEFAULT_EMBED_MODEL = "@cf/baai/bge-m3";
|
||||
var MIN_SCORE_ABS_FLOOR = 0.45;
|
||||
@@ -2449,7 +2507,7 @@ async function embedOnWrite(env, entry) {
|
||||
}
|
||||
}
|
||||
]);
|
||||
await env.DB.prepare("UPDATE entries SET is_embedded = 1 WHERE id = ?").bind(entry.id).run();
|
||||
await env.DB.prepare("UPDATE entries SET is_embedded = 1, content_hash = ? WHERE id = ?").bind(embedModel(env), entry.id).run();
|
||||
return true;
|
||||
}
|
||||
function isEmbeddable(entry) {
|
||||
@@ -2476,12 +2534,47 @@ function parseMeta(json) {
|
||||
}
|
||||
}
|
||||
var BACKFILL_PREDICATE = "is_embedded = 0 AND content IS NOT NULL AND content <> '' AND json_extract(metadata_json, '$.embed') = 1";
|
||||
async function backfillEmbeddings(env, opts = {}) {
|
||||
if (!embedEnabled(env)) return { enabled: false, processed: 0, skipped: 0, remaining: 0, scanned: 0 };
|
||||
const limit = Math.min(Math.max(opts.limit ?? 25, 1), 100);
|
||||
const offset = Math.max(opts.offset ?? 0, 0);
|
||||
const basePredicate = opts.reindex ? "content IS NOT NULL AND content <> '' AND json_extract(metadata_json, '$.embed') = 1" : BACKFILL_PREDICATE;
|
||||
const conds = [basePredicate, "COALESCE(json_extract(metadata_json, '$.status'), '') != 'deprecated'"];
|
||||
var DEFAULT_BACKFILL_DAILY_LIMIT = 1800;
|
||||
function backfillDailyLimit(env) {
|
||||
const raw2 = env.EMBED_BACKFILL_DAILY_LIMIT;
|
||||
const n = raw2 ? parseInt(raw2, 10) : NaN;
|
||||
return Number.isFinite(n) && n > 0 ? n : DEFAULT_BACKFILL_DAILY_LIMIT;
|
||||
}
|
||||
function utcDay2() {
|
||||
return (/* @__PURE__ */ new Date()).toISOString().slice(0, 10);
|
||||
}
|
||||
function backfillUsageId() {
|
||||
return `embed-backfill-usage:${utcDay2()}`;
|
||||
}
|
||||
async function getBackfillUsageToday(db) {
|
||||
const row = await db.prepare("SELECT metadata_json FROM entries WHERE id = ?").bind(backfillUsageId()).first();
|
||||
if (!row) return 0;
|
||||
try {
|
||||
const parsed = row.metadata_json ? JSON.parse(row.metadata_json) : {};
|
||||
return Number(parsed.embedded) || 0;
|
||||
} catch {
|
||||
return 0;
|
||||
}
|
||||
}
|
||||
async function addBackfillUsage(db, by) {
|
||||
if (by <= 0) return;
|
||||
const id = backfillUsageId();
|
||||
const existing = await db.prepare("SELECT metadata_json FROM entries WHERE id = ?").bind(id).first();
|
||||
let prev = 0;
|
||||
if (existing) {
|
||||
try {
|
||||
const parsed = existing.metadata_json ? JSON.parse(existing.metadata_json) : {};
|
||||
prev = Number(parsed.embedded) || 0;
|
||||
} catch {
|
||||
prev = 0;
|
||||
}
|
||||
await db.prepare("UPDATE entries SET metadata_json = ?, updated_at = unixepoch() WHERE id = ?").bind(JSON.stringify({ day: utcDay2(), embedded: prev + by }), id).run();
|
||||
} else {
|
||||
await db.prepare(`INSERT INTO entries (id, entry_type, metadata_json) VALUES (?, 'embed_backfill_usage', ?)`).bind(id, JSON.stringify({ day: utcDay2(), embedded: by })).run();
|
||||
}
|
||||
}
|
||||
function selectionCriteriaPredicate(opts) {
|
||||
const conds = [];
|
||||
const params = [];
|
||||
if (opts.owner_id) {
|
||||
conds.push("owner_id = ?");
|
||||
@@ -2491,12 +2584,55 @@ async function backfillEmbeddings(env, opts = {}) {
|
||||
conds.push("json_extract(metadata_json, '$.source') = ?");
|
||||
params.push(opts.source);
|
||||
}
|
||||
if (opts.library) {
|
||||
conds.push("COALESCE(NULLIF(json_extract(metadata_json, '$.library'), ''), 'general') = ?");
|
||||
params.push(opts.library);
|
||||
}
|
||||
if (typeof opts.since === "number") {
|
||||
conds.push("created_at >= ?");
|
||||
params.push(opts.since);
|
||||
}
|
||||
if (typeof opts.until === "number") {
|
||||
conds.push("created_at < ?");
|
||||
params.push(opts.until);
|
||||
}
|
||||
return { conds, params };
|
||||
}
|
||||
async function backfillEmbeddings(env, opts = {}) {
|
||||
if (!embedEnabled(env)) {
|
||||
return {
|
||||
enabled: false,
|
||||
processed: 0,
|
||||
skipped: 0,
|
||||
remaining: 0,
|
||||
scanned: 0,
|
||||
quota_limit: 0,
|
||||
quota_used_today: 0,
|
||||
quota_exceeded: false
|
||||
};
|
||||
}
|
||||
const limit = Math.min(Math.max(opts.limit ?? 25, 1), 100);
|
||||
const offset = Math.max(opts.offset ?? 0, 0);
|
||||
const basePredicate = opts.reindex ? "content IS NOT NULL AND content <> '' AND json_extract(metadata_json, '$.embed') = 1" : BACKFILL_PREDICATE;
|
||||
const sel = selectionCriteriaPredicate(opts);
|
||||
const conds = [basePredicate, "COALESCE(json_extract(metadata_json, '$.status'), '') != 'deprecated'", ...sel.conds];
|
||||
const params = [...sel.params];
|
||||
const where = conds.join(" AND ");
|
||||
const res = await env.DB.prepare(`SELECT * FROM entries WHERE ${where} ORDER BY created_at ASC LIMIT ? OFFSET ?`).bind(...params, limit, offset).all();
|
||||
const res = await env.DB.prepare(`SELECT * FROM entries WHERE ${where} ORDER BY created_at DESC LIMIT ? OFFSET ?`).bind(...params, limit, offset).all();
|
||||
const rows = res.results ?? [];
|
||||
const scanned = rows.length;
|
||||
const dailyCap = backfillDailyLimit(env);
|
||||
let usedToday = 0;
|
||||
try {
|
||||
usedToday = await getBackfillUsageToday(env.DB);
|
||||
} catch {
|
||||
usedToday = 0;
|
||||
}
|
||||
const remainingQuota = Math.max(0, dailyCap - usedToday);
|
||||
let processed = 0;
|
||||
const embeddable = rows.filter((e) => (e.content ?? "").trim().length > 0);
|
||||
const candidates = rows.filter((e) => (e.content ?? "").trim().length > 0);
|
||||
const embeddable = candidates.slice(0, remainingQuota);
|
||||
const quotaExceeded = candidates.length > embeddable.length;
|
||||
if (embeddable.length > 0 && env.AI && env.VECTORIZE) {
|
||||
const texts = embeddable.map((e) => (e.content ?? "").trim());
|
||||
const out = await env.AI.run(embedModel(env), { text: texts });
|
||||
@@ -2516,14 +2652,27 @@ async function backfillEmbeddings(env, opts = {}) {
|
||||
await env.VECTORIZE.upsert(vectors);
|
||||
const ids = vectors.map((v) => v.id);
|
||||
const placeholders = ids.map(() => "?").join(",");
|
||||
await env.DB.prepare(`UPDATE entries SET is_embedded = 1 WHERE id IN (${placeholders})`).bind(...ids).run();
|
||||
await env.DB.prepare(`UPDATE entries SET is_embedded = 1, content_hash = ? WHERE id IN (${placeholders})`).bind(embedModel(env), ...ids).run();
|
||||
processed = vectors.length;
|
||||
try {
|
||||
await addBackfillUsage(env.DB, processed);
|
||||
} catch {
|
||||
}
|
||||
}
|
||||
}
|
||||
const remRow = await env.DB.prepare(`SELECT COUNT(*) as c FROM entries WHERE ${where}`).bind(...params).first();
|
||||
const totalMatching = remRow?.c ?? 0;
|
||||
const remaining = opts.reindex ? Math.max(0, totalMatching - (offset + scanned)) : totalMatching;
|
||||
return { enabled: true, processed, skipped: scanned - processed, remaining, scanned };
|
||||
return {
|
||||
enabled: true,
|
||||
processed,
|
||||
skipped: scanned - processed,
|
||||
remaining,
|
||||
scanned,
|
||||
quota_limit: dailyCap,
|
||||
quota_used_today: usedToday + processed,
|
||||
quota_exceeded: quotaExceeded
|
||||
};
|
||||
}
|
||||
async function backfillStatus(env, opts = {}) {
|
||||
const conds = [];
|
||||
@@ -2541,6 +2690,74 @@ async function backfillStatus(env, opts = {}) {
|
||||
const embeddedRow = await env.DB.prepare(`SELECT COUNT(*) as c FROM entries WHERE is_embedded = 1 AND json_extract(metadata_json, '$.embed') = 1${extra}`).bind(...params).first();
|
||||
return { enabled: embedEnabled(env), pending: pendingRow?.c ?? 0, embedded: embeddedRow?.c ?? 0 };
|
||||
}
|
||||
async function reconcileEmbedGeneration(env, opts = {}) {
|
||||
if (!embedEnabled(env)) {
|
||||
return {
|
||||
enabled: false,
|
||||
checked: 0,
|
||||
confirmed_current: 0,
|
||||
reset_to_pending: 0,
|
||||
remaining: 0,
|
||||
scanned: 0,
|
||||
quota_limit: 0,
|
||||
quota_used_today: 0,
|
||||
quota_exceeded: false
|
||||
};
|
||||
}
|
||||
const limit = Math.min(Math.max(opts.limit ?? 50, 1), 200);
|
||||
const currentModel = embedModel(env);
|
||||
const sel = selectionCriteriaPredicate(opts);
|
||||
const conds = [
|
||||
"is_embedded = 1",
|
||||
"(content_hash IS NULL OR content_hash != ?)",
|
||||
"COALESCE(json_extract(metadata_json, '$.status'), '') != 'deprecated'",
|
||||
...sel.conds
|
||||
];
|
||||
const params = [currentModel, ...sel.params];
|
||||
const where = conds.join(" AND ");
|
||||
const res = await env.DB.prepare(`SELECT id FROM entries WHERE ${where} ORDER BY created_at DESC LIMIT ?`).bind(...params, limit).all();
|
||||
const scannedIds = (res.results ?? []).map((r) => r.id);
|
||||
const scanned = scannedIds.length;
|
||||
const budget = await maintenanceBudgetToday(env, env.DB);
|
||||
const ids = scannedIds.slice(0, budget.remaining);
|
||||
const quotaExceeded = scanned > ids.length;
|
||||
const checked = ids.length;
|
||||
let confirmed_current = 0;
|
||||
let reset_to_pending = 0;
|
||||
if (ids.length > 0 && env.VECTORIZE) {
|
||||
const found = await env.VECTORIZE.getByIds(ids);
|
||||
const foundIds = new Set(found.map((v) => v.id));
|
||||
const presentIds = ids.filter((id) => foundIds.has(id));
|
||||
const missingIds = ids.filter((id) => !foundIds.has(id));
|
||||
if (presentIds.length > 0) {
|
||||
const ph = presentIds.map(() => "?").join(",");
|
||||
await env.DB.prepare(`UPDATE entries SET content_hash = ? WHERE id IN (${ph})`).bind(currentModel, ...presentIds).run();
|
||||
confirmed_current = presentIds.length;
|
||||
}
|
||||
if (missingIds.length > 0) {
|
||||
const ph = missingIds.map(() => "?").join(",");
|
||||
await env.DB.prepare(`UPDATE entries SET is_embedded = 0, content_hash = NULL WHERE id IN (${ph})`).bind(...missingIds).run();
|
||||
reset_to_pending = missingIds.length;
|
||||
}
|
||||
}
|
||||
const remRow = await env.DB.prepare(`SELECT COUNT(*) as c FROM entries WHERE ${where}`).bind(...params).first();
|
||||
const written = confirmed_current + reset_to_pending;
|
||||
try {
|
||||
await addMaintenanceUsage(env.DB, written);
|
||||
} catch {
|
||||
}
|
||||
return {
|
||||
enabled: true,
|
||||
checked,
|
||||
confirmed_current,
|
||||
reset_to_pending,
|
||||
remaining: remRow?.c ?? 0,
|
||||
scanned,
|
||||
quota_limit: budget.limit,
|
||||
quota_used_today: budget.used + written,
|
||||
quota_exceeded: quotaExceeded
|
||||
};
|
||||
}
|
||||
async function embedSelfTest(env, opts = {}) {
|
||||
if (!embedEnabled(env)) {
|
||||
return { enabled: false, tested: false, passed: null, note: "embed \u6A21\u7D44\u672A\u958B\uFF08\u7F3A Vectorize/AI binding\uFF09\uFF0C\u8A9E\u7FA9\u641C\u5C0B\u9019\u689D\u8DEF\u76EE\u524D\u4E0D\u5B58\u5728" };
|
||||
@@ -2647,6 +2864,90 @@ async function migrateLegacyCredentialsForOwner(db, ownerId) {
|
||||
return (after?.n ?? 0) - (before?.n ?? 0);
|
||||
}
|
||||
|
||||
// kbdb/src/actions/library-backfill.ts
|
||||
var MAX_PAGE_NAMES = 300;
|
||||
var HARD_LIMIT_CAP = 500;
|
||||
function criteriaPredicate(c) {
|
||||
const conds = [
|
||||
"(json_extract(metadata_json, '$.library') IS NULL OR json_extract(metadata_json, '$.library') = '')"
|
||||
];
|
||||
const params = [];
|
||||
if (c.owner_id) {
|
||||
conds.push("owner_id = ?");
|
||||
params.push(c.owner_id);
|
||||
}
|
||||
if (c.entry_type) {
|
||||
conds.push("entry_type = ?");
|
||||
params.push(c.entry_type);
|
||||
}
|
||||
if (c.page_names && c.page_names.length > 0) {
|
||||
const names = c.page_names.slice(0, MAX_PAGE_NAMES);
|
||||
conds.push(`page_name IN (${names.map(() => "?").join(",")})`);
|
||||
params.push(...names);
|
||||
}
|
||||
if (c.source_prefix) {
|
||||
conds.push("json_extract(metadata_json, '$.source') LIKE ? || '%'");
|
||||
params.push(c.source_prefix);
|
||||
}
|
||||
if (c.page_name_prefix) {
|
||||
conds.push("page_name LIKE ? || '%'");
|
||||
params.push(c.page_name_prefix);
|
||||
}
|
||||
if (typeof c.since === "number") {
|
||||
conds.push("created_at >= ?");
|
||||
params.push(c.since);
|
||||
}
|
||||
if (typeof c.until === "number") {
|
||||
conds.push("created_at < ?");
|
||||
params.push(c.until);
|
||||
}
|
||||
return { conds, params };
|
||||
}
|
||||
async function backfillEntryLibraryTags(db, env, opts) {
|
||||
const library = (opts.library ?? "").trim();
|
||||
if (!library) throw new Error("library required");
|
||||
const ownerId = (opts.owner_id ?? "").trim();
|
||||
if (!ownerId) throw new Error("owner_id required\uFF08\u6A19\u5EAB\u662F\u8DE8\u5927\u91CF\u65E2\u6709\u8CC7\u6599\u7684\u6279\u6B21\u5BEB\u5165\uFF0C\u4E0D\u51C6\u7121\u79DF\u6236\u7BC4\u570D\u5730\u6383\u5168\u5EAB\u2014\u20142026-08-11 leo \u76F4\u4EE4\uFF09");
|
||||
const limit = Math.min(Math.max(opts.limit ?? 100, 1), HARD_LIMIT_CAP);
|
||||
const sel = criteriaPredicate({ ...opts, owner_id: ownerId });
|
||||
const where = sel.conds.join(" AND ");
|
||||
const params = sel.params;
|
||||
const res = await db.prepare(`SELECT id FROM entries WHERE ${where} ORDER BY created_at ASC LIMIT ?`).bind(...params, limit).all();
|
||||
const scannedIds = (res.results ?? []).map((r) => r.id);
|
||||
const scanned = scannedIds.length;
|
||||
const budget = await maintenanceBudgetToday(env, db);
|
||||
const ids = scannedIds.slice(0, budget.remaining);
|
||||
const quotaExceeded = scanned > ids.length;
|
||||
let tagged = 0;
|
||||
if (ids.length > 0) {
|
||||
const ph = ids.map(() => "?").join(",");
|
||||
await db.prepare(
|
||||
`UPDATE entries SET metadata_json = json_set(COALESCE(metadata_json, '{}'), '$.library', ?), updated_at = unixepoch() WHERE id IN (${ph})`
|
||||
).bind(library, ...ids).run();
|
||||
tagged = ids.length;
|
||||
}
|
||||
try {
|
||||
await addMaintenanceUsage(db, tagged);
|
||||
} catch {
|
||||
}
|
||||
const remRow = await db.prepare(`SELECT COUNT(*) as c FROM entries WHERE ${where}`).bind(...params).first();
|
||||
return {
|
||||
library,
|
||||
scanned,
|
||||
tagged,
|
||||
remaining: remRow?.c ?? 0,
|
||||
quota_limit: budget.limit,
|
||||
quota_used_today: budget.used + tagged,
|
||||
quota_exceeded: quotaExceeded
|
||||
};
|
||||
}
|
||||
async function libraryBackfillStatus(db, opts = {}) {
|
||||
const sel = criteriaPredicate(opts);
|
||||
const where = sel.conds.join(" AND ");
|
||||
const row = await db.prepare(`SELECT COUNT(*) as c FROM entries WHERE ${where}`).bind(...sel.params).first();
|
||||
return { pending: row?.c ?? 0 };
|
||||
}
|
||||
|
||||
// kbdb/src/routes/entries.ts
|
||||
var entryRoutes = new Hono2();
|
||||
function fireAndForget(c, p) {
|
||||
@@ -2873,6 +3174,39 @@ entryRoutes.patch("/deprecate-by-library", async (c) => {
|
||||
}
|
||||
return c.json({ success: true, deprecated_count: count, vectors_deleted });
|
||||
});
|
||||
entryRoutes.post("/backfill-library", async (c) => {
|
||||
const body = await c.req.json().catch(() => ({}));
|
||||
const library = String(body.library ?? "").trim();
|
||||
const ownerId = String(body.owner_id ?? "").trim();
|
||||
if (!library || !ownerId) return c.json({ success: false, error: "library \u8207 owner_id \u5FC5\u586B" }, 400);
|
||||
try {
|
||||
const result = await backfillEntryLibraryTags(c.env.DB, c.env, {
|
||||
library,
|
||||
owner_id: ownerId,
|
||||
entry_type: body.entry_type || void 0,
|
||||
page_names: Array.isArray(body.page_names) && body.page_names.length > 0 ? body.page_names : void 0,
|
||||
source_prefix: body.source_prefix || void 0,
|
||||
page_name_prefix: body.page_name_prefix || void 0,
|
||||
since: body.since !== void 0 ? Number(body.since) : void 0,
|
||||
until: body.until !== void 0 ? Number(body.until) : void 0,
|
||||
limit: body.limit !== void 0 ? Number(body.limit) : void 0
|
||||
});
|
||||
return c.json({ success: true, ...result });
|
||||
} catch (e) {
|
||||
return c.json({ success: false, error: e instanceof Error ? e.message : String(e) }, 400);
|
||||
}
|
||||
});
|
||||
entryRoutes.get("/backfill-library/status", async (c) => {
|
||||
const status = await libraryBackfillStatus(c.env.DB, {
|
||||
owner_id: c.req.query("owner_id") || void 0,
|
||||
entry_type: c.req.query("entry_type") || void 0,
|
||||
source_prefix: c.req.query("source_prefix") || void 0,
|
||||
page_name_prefix: c.req.query("page_name_prefix") || void 0,
|
||||
since: c.req.query("since") ? Number(c.req.query("since")) : void 0,
|
||||
until: c.req.query("until") ? Number(c.req.query("until")) : void 0
|
||||
});
|
||||
return c.json({ success: true, ...status });
|
||||
});
|
||||
entryRoutes.patch("/:id", async (c) => {
|
||||
const body = await c.req.json().catch(() => ({}));
|
||||
const entry = await updateEntry(c.env.DB, c.req.param("id"), body);
|
||||
@@ -3192,6 +3526,9 @@ embedRoutes.post("/backfill", async (c) => {
|
||||
limit: body.limit !== void 0 ? Number(body.limit) : void 0,
|
||||
owner_id: body.owner_id || void 0,
|
||||
source: body.source || void 0,
|
||||
library: body.library || void 0,
|
||||
since: body.since !== void 0 ? Number(body.since) : void 0,
|
||||
until: body.until !== void 0 ? Number(body.until) : void 0,
|
||||
// reindex（Arcrun#11）：重推既有向量讓事後建立的 Vectorize metadata index 收錄（見 embed.ts）。
|
||||
reindex: body.reindex === true,
|
||||
offset: body.offset !== void 0 ? Number(body.offset) : void 0
|
||||
@@ -3205,6 +3542,23 @@ embedRoutes.get("/backfill/status", async (c) => {
|
||||
});
|
||||
return c.json({ success: true, ...status });
|
||||
});
|
||||
embedRoutes.post("/reconcile", async (c) => {
|
||||
if (!embedEnabled(c.env)) {
|
||||
return c.json(
|
||||
{ success: false, error: "embed module not enabled (need VECTORIZE + AI bindings)", capability_hint: OFF_HINT },
|
||||
409
|
||||
);
|
||||
}
|
||||
const body = await c.req.json().catch(() => ({}));
|
||||
const result = await reconcileEmbedGeneration(c.env, {
|
||||
limit: body.limit !== void 0 ? Number(body.limit) : void 0,
|
||||
owner_id: body.owner_id || void 0,
|
||||
library: body.library || void 0,
|
||||
since: body.since !== void 0 ? Number(body.since) : void 0,
|
||||
until: body.until !== void 0 ? Number(body.until) : void 0
|
||||
});
|
||||
return c.json({ success: true, ...result });
|
||||
});
|
||||
embedRoutes.get("/selftest", async (c) => {
|
||||
const result = await embedSelfTest(c.env, { owner_id: c.req.query("owner_id") || void 0 });
|
||||
return c.json({ success: true, ...result });
|
||||
@@ -3402,14 +3756,18 @@ async function recomputeLibraryMap(db, input) {
|
||||
async function liveTripletCountsByLibrary(db, tripletTemplateId, owner_id) {
|
||||
const params = owner_id ? [tripletTemplateId, owner_id] : [tripletTemplateId];
|
||||
const res = await db.prepare(
|
||||
// kbdb-sql-ok：牆內本體（kbdb/src/actions/），checkout 開在巢狀 worktree matrix/arcrun/.worktree-fix-87/（避免打斷另一 session 佔用中的 matrix/arcrun 主 checkout），hook 逐字比對 matrix/arcrun/kbdb/src/ 吃不到中間多出的 worktree 目錄層，非繞牆
|
||||
`SELECT COALESCE(NULLIF(lib_e.content, ''), 'general') AS library, COUNT(*) AS n
|
||||
FROM (
|
||||
SELECT DISTINCT ev.record_id
|
||||
SELECT ev.record_id AS rid,
|
||||
MAX(CASE WHEN ev.slot_name = 'status' THEN e.content END) AS status
|
||||
FROM entry_values ev JOIN entries e ON ev.entry_id = e.id
|
||||
WHERE ev.template_id = ?${owner_id ? " AND e.owner_id = ?" : ""}
|
||||
GROUP BY ev.record_id
|
||||
) AS tr
|
||||
LEFT JOIN entry_values lev ON lev.record_id = tr.record_id AND lev.slot_name = 'library'
|
||||
LEFT JOIN entry_values lev ON lev.record_id = tr.rid AND lev.slot_name = 'library'
|
||||
LEFT JOIN entries lib_e ON lib_e.id = lev.entry_id
|
||||
WHERE COALESCE(tr.status, 'active') = 'active'
|
||||
GROUP BY COALESCE(NULLIF(lib_e.content, ''), 'general')`
|
||||
).bind(...params).all();
|
||||
const m = /* @__PURE__ */ new Map();
|
||||
@@ -3558,7 +3916,7 @@ function dailyLimit(env) {
|
||||
const n = raw2 ? parseInt(raw2, 10) : NaN;
|
||||
return Number.isFinite(n) && n > 0 ? n : DEFAULT_DAILY_LIMIT;
|
||||
}
|
||||
function utcDay() {
|
||||
function utcDay3() {
|
||||
return (/* @__PURE__ */ new Date()).toISOString().slice(0, 10);
|
||||
}
|
||||
function truncate(s, max) {
|
||||
@@ -3566,7 +3924,7 @@ function truncate(s, max) {
|
||||
return s.slice(0, Math.max(0, max - 1)) + "\u2026";
|
||||
}
|
||||
async function checkUsage(db, limit) {
|
||||
const id = `exlog-usage:${utcDay()}`;
|
||||
const id = `exlog-usage:${utcDay3()}`;
|
||||
const existing = await db.prepare("SELECT metadata_json FROM entries WHERE id = ?").bind(id).first();
|
||||
let count;
|
||||
if (existing) {
|
||||
@@ -3578,10 +3936,10 @@ async function checkUsage(db, limit) {
|
||||
prevWrites = 0;
|
||||
}
|
||||
count = prevWrites + 1;
|
||||
await db.prepare("UPDATE entries SET metadata_json = ?, updated_at = unixepoch() WHERE id = ?").bind(JSON.stringify({ day: utcDay(), writes: count }), id).run();
|
||||
await db.prepare("UPDATE entries SET metadata_json = ?, updated_at = unixepoch() WHERE id = ?").bind(JSON.stringify({ day: utcDay3(), writes: count }), id).run();
|
||||
} else {
|
||||
count = 1;
|
||||
await db.prepare(`INSERT INTO entries (id, entry_type, metadata_json) VALUES (?, 'execution_log_usage', ?)`).bind(id, JSON.stringify({ day: utcDay(), writes: count })).run();
|
||||
await db.prepare(`INSERT INTO entries (id, entry_type, metadata_json) VALUES (?, 'execution_log_usage', ?)`).bind(id, JSON.stringify({ day: utcDay3(), writes: count })).run();
|
||||
}
|
||||
if (count > limit) return "skip";
|
||||
if (count > limit * DEGRADE_RATIO) return "log_failure_only";
|
||||
@@ -3797,7 +4155,7 @@ app.route("/recipe-stats", recipeStatRoutes);
|
||||
app.route("/execution-log", executionLogRoutes);
|
||||
app.route("/embed", embedRoutes);
|
||||
app.route("/map", mapRoutes);
|
||||
var src_default = app;
|
||||
var index_default = app;
|
||||
export {
|
||||
src_default as default
|
||||
index_default as default
|
||||
};
|
||||
|
||||
@@ -5,7 +5,11 @@ var __getOwnPropNames = Object.getOwnPropertyNames;
|
||||
var __getProtoOf = Object.getPrototypeOf;
|
||||
var __hasOwnProp = Object.prototype.hasOwnProperty;
|
||||
var __commonJS = (cb, mod) => function __require() {
|
||||
return mod || (0, cb[__getOwnPropNames(cb)[0]])((mod = { exports: {} }).exports, mod), mod.exports;
|
||||
try {
|
||||
return mod || (0, cb[__getOwnPropNames(cb)[0]])((mod = { exports: {} }).exports, mod), mod.exports;
|
||||
} catch (e) {
|
||||
throw mod = 0, e;
|
||||
}
|
||||
};
|
||||
var __export = (target, all) => {
|
||||
for (var name in all)
|
||||
@@ -8223,7 +8227,7 @@ var Hono = class _Hono {
|
||||
var emptyParam = [];
|
||||
function match(method, path) {
|
||||
const matchers = this.buildAllMatchers();
|
||||
const match2 = (method2, path2) => {
|
||||
const match2 = ((method2, path2) => {
|
||||
const matcher = matchers[method2] || matchers[METHOD_NAME_ALL];
|
||||
const staticMatch = matcher[2][path2];
|
||||
if (staticMatch) {
|
||||
@@ -8235,7 +8239,7 @@ function match(method, path) {
|
||||
}
|
||||
const index = match3.indexOf("", 1);
|
||||
return [matcher[1][index], match3];
|
||||
};
|
||||
});
|
||||
this.match = match2;
|
||||
return match2(method, path);
|
||||
}
|
||||
@@ -12954,7 +12958,7 @@ ZodNaN.create = (params) => {
|
||||
...processCreateParams(params)
|
||||
});
|
||||
};
|
||||
var BRAND = Symbol("zod_brand");
|
||||
var BRAND = /* @__PURE__ */ Symbol("zod_brand");
|
||||
var ZodBranded = class extends ZodType {
|
||||
_parse(input) {
|
||||
const { ctx } = this._processInputParams(input);
|
||||
@@ -13156,14 +13160,14 @@ var ostring = () => stringType().optional();
|
||||
var onumber = () => numberType().optional();
|
||||
var oboolean = () => booleanType().optional();
|
||||
var coerce = {
|
||||
string: (arg) => ZodString.create({ ...arg, coerce: true }),
|
||||
number: (arg) => ZodNumber.create({ ...arg, coerce: true }),
|
||||
boolean: (arg) => ZodBoolean.create({
|
||||
string: ((arg) => ZodString.create({ ...arg, coerce: true })),
|
||||
number: ((arg) => ZodNumber.create({ ...arg, coerce: true })),
|
||||
boolean: ((arg) => ZodBoolean.create({
|
||||
...arg,
|
||||
coerce: true
|
||||
}),
|
||||
bigint: (arg) => ZodBigInt.create({ ...arg, coerce: true }),
|
||||
date: (arg) => ZodDate.create({ ...arg, coerce: true })
|
||||
})),
|
||||
bigint: ((arg) => ZodBigInt.create({ ...arg, coerce: true })),
|
||||
date: ((arg) => ZodDate.create({ ...arg, coerce: true }))
|
||||
};
|
||||
var NEVER = INVALID;
|
||||
|
||||
@@ -13214,7 +13218,6 @@ function $constructor(name, initializer3, params) {
|
||||
Object.defineProperty(_, "name", { value: name });
|
||||
return _;
|
||||
}
|
||||
var $brand = Symbol("zod_brand");
|
||||
var $ZodAsyncError = class extends Error {
|
||||
constructor() {
|
||||
super(`Encountered Promise during synchronous parse. Use .parseAsync() instead.`);
|
||||
@@ -15718,8 +15721,6 @@ function en_default2() {
|
||||
}
|
||||
|
||||
// mcp/node_modules/.pnpm/zod@3.25.76/node_modules/zod/v4/core/registries.js
|
||||
var $output = Symbol("ZodOutput");
|
||||
var $input = Symbol("ZodInput");
|
||||
var $ZodRegistry = class {
|
||||
constructor() {
|
||||
this._map = /* @__PURE__ */ new Map();
|
||||
@@ -16997,10 +16998,10 @@ var ZodMiniType = /* @__PURE__ */ $constructor("ZodMiniType", (inst, def) => {
|
||||
};
|
||||
inst.clone = (_def, params) => clone(inst, _def, params);
|
||||
inst.brand = () => inst;
|
||||
inst.register = (reg, meta) => {
|
||||
inst.register = ((reg, meta) => {
|
||||
reg.add(inst, meta);
|
||||
return inst;
|
||||
};
|
||||
});
|
||||
});
|
||||
var ZodMiniObject = /* @__PURE__ */ $constructor("ZodMiniObject", (inst, def) => {
|
||||
$ZodObject.init(inst, def);
|
||||
@@ -17263,10 +17264,10 @@ var ZodType2 = /* @__PURE__ */ $constructor("ZodType", (inst, def) => {
|
||||
};
|
||||
inst.clone = (def2, params) => clone(inst, def2, params);
|
||||
inst.brand = () => inst;
|
||||
inst.register = (reg, meta) => {
|
||||
inst.register = ((reg, meta) => {
|
||||
reg.add(inst, meta);
|
||||
return inst;
|
||||
};
|
||||
});
|
||||
inst.parse = (data, params) => parse2(inst, data, params, { callee: inst.parse });
|
||||
inst.safeParse = (data, params) => safeParse3(inst, data, params);
|
||||
inst.parseAsync = async (data, params) => parseAsync2(inst, data, params, { callee: inst.parseAsync });
|
||||
@@ -19238,11 +19239,13 @@ function assertCompleteRequestPrompt(request) {
|
||||
if (request.params.ref.type !== "ref/prompt") {
|
||||
throw new TypeError(`Expected CompleteRequestPrompt, but got ${request.params.ref.type}`);
|
||||
}
|
||||
void request;
|
||||
}
|
||||
function assertCompleteRequestResourceTemplate(request) {
|
||||
if (request.params.ref.type !== "ref/resource") {
|
||||
throw new TypeError(`Expected CompleteRequestResourceTemplate, but got ${request.params.ref.type}`);
|
||||
}
|
||||
void request;
|
||||
}
|
||||
var CompleteResultSchema = ResultSchema.extend({
|
||||
completion: looseObject({
|
||||
@@ -19395,7 +19398,7 @@ function isTerminal(status) {
|
||||
}
|
||||
|
||||
// mcp/node_modules/.pnpm/zod-to-json-schema@3.25.2_zod@3.25.76/node_modules/zod-to-json-schema/dist/esm/Options.js
|
||||
var ignoreOverride = Symbol("Let zodToJsonSchema decide on which parser to use");
|
||||
var ignoreOverride = /* @__PURE__ */ Symbol("Let zodToJsonSchema decide on which parser to use");
|
||||
var defaultOptions = {
|
||||
name: void 0,
|
||||
$refStrategy: "root",
|
||||
@@ -22371,7 +22374,7 @@ var Server = class extends Protocol {
|
||||
};
|
||||
|
||||
// mcp/node_modules/.pnpm/@modelcontextprotocol+sdk@1.29.0_zod@3.25.76/node_modules/@modelcontextprotocol/sdk/dist/esm/server/completable.js
|
||||
var COMPLETABLE_SYMBOL = Symbol.for("mcp.completable");
|
||||
var COMPLETABLE_SYMBOL = /* @__PURE__ */ Symbol.for("mcp.completable");
|
||||
function isCompletable(schema4) {
|
||||
return !!schema4 && typeof schema4 === "object" && COMPLETABLE_SYMBOL in schema4;
|
||||
}
|
||||
@@ -24686,13 +24689,13 @@ function registerAllIntrospectionTools(server, env) {
|
||||
}
|
||||
|
||||
// mcp/node_modules/.pnpm/yaml@2.9.0/node_modules/yaml/browser/dist/nodes/identity.js
|
||||
var ALIAS = Symbol.for("yaml.alias");
|
||||
var DOC = Symbol.for("yaml.document");
|
||||
var MAP = Symbol.for("yaml.map");
|
||||
var PAIR = Symbol.for("yaml.pair");
|
||||
var SCALAR = Symbol.for("yaml.scalar");
|
||||
var SEQ = Symbol.for("yaml.seq");
|
||||
var NODE_TYPE = Symbol.for("yaml.node.type");
|
||||
var ALIAS = /* @__PURE__ */ Symbol.for("yaml.alias");
|
||||
var DOC = /* @__PURE__ */ Symbol.for("yaml.document");
|
||||
var MAP = /* @__PURE__ */ Symbol.for("yaml.map");
|
||||
var PAIR = /* @__PURE__ */ Symbol.for("yaml.pair");
|
||||
var SCALAR = /* @__PURE__ */ Symbol.for("yaml.scalar");
|
||||
var SEQ = /* @__PURE__ */ Symbol.for("yaml.seq");
|
||||
var NODE_TYPE = /* @__PURE__ */ Symbol.for("yaml.node.type");
|
||||
var isAlias = (node) => !!node && typeof node === "object" && node[NODE_TYPE] === ALIAS;
|
||||
var isDocument = (node) => !!node && typeof node === "object" && node[NODE_TYPE] === DOC;
|
||||
var isMap = (node) => !!node && typeof node === "object" && node[NODE_TYPE] === MAP;
|
||||
@@ -24722,9 +24725,9 @@ function isNode(node) {
|
||||
var hasAnchor = (node) => (isScalar(node) || isCollection(node)) && !!node.anchor;
|
||||
|
||||
// mcp/node_modules/.pnpm/yaml@2.9.0/node_modules/yaml/browser/dist/visit.js
|
||||
var BREAK = Symbol("break visit");
|
||||
var SKIP = Symbol("skip children");
|
||||
var REMOVE = Symbol("remove node");
|
||||
var BREAK = /* @__PURE__ */ Symbol("break visit");
|
||||
var SKIP = /* @__PURE__ */ Symbol("skip children");
|
||||
var REMOVE = /* @__PURE__ */ Symbol("remove node");
|
||||
function visit(node, visitor) {
|
||||
const visitor_ = initVisitor(visitor);
|
||||
if (isDocument(node)) {
|
||||
@@ -29317,9 +29320,9 @@ ${end.comment}` : end.comment;
|
||||
};
|
||||
|
||||
// mcp/node_modules/.pnpm/yaml@2.9.0/node_modules/yaml/browser/dist/parse/cst-visit.js
|
||||
var BREAK2 = Symbol("break visit");
|
||||
var SKIP2 = Symbol("skip children");
|
||||
var REMOVE2 = Symbol("remove item");
|
||||
var BREAK2 = /* @__PURE__ */ Symbol("break visit");
|
||||
var SKIP2 = /* @__PURE__ */ Symbol("skip children");
|
||||
var REMOVE2 = /* @__PURE__ */ Symbol("remove item");
|
||||
function visit2(cst, visitor) {
|
||||
if ("type" in cst && cst.type === "document")
|
||||
cst = { start: cst.start, value: cst.value };
|
||||
@@ -33389,7 +33392,7 @@ app.post("/", partnerAuthMiddleware, async (c) => {
|
||||
const partnerToken = c.get("partner_token");
|
||||
return handleMcpRequest(c.req.raw, c.env, orgNamespace, partnerToken);
|
||||
});
|
||||
var src_default = _app;
|
||||
var index_default = _app;
|
||||
export {
|
||||
src_default as default
|
||||
index_default as default
|
||||
};
|
||||
|
||||
@@ -1,18 +1,18 @@
|
||||
{
|
||||
"schema": 1,
|
||||
"built_for": "arcrun-tier2-worker-artifacts",
|
||||
"generated_at": "2026-08-11T05:33:37.988Z",
|
||||
"repo_head": "d8bbf2241bd6b117d76fb27d9e386ecfb0ffe8f7",
|
||||
"generated_at": "2026-08-12T04:21:48.581Z",
|
||||
"repo_head": "b302c03ea8076bcfe82bbcebb1523dcec2d1e830",
|
||||
"repo_dirty": false,
|
||||
"workers": [
|
||||
{
|
||||
"name": "arcrun-cypher-executor",
|
||||
"source_dir": "cypher-executor",
|
||||
"source_commit": "797e7f751cc42cb1f5d9e2e187f18cf51eb981a1",
|
||||
"source_commit": "525faaf5d01e156a9b8f90808607bead92f40165",
|
||||
"main_module": "worker.mjs",
|
||||
"main_file": "arcrun-cypher-executor/worker.mjs",
|
||||
"js_bytes": 568855,
|
||||
"content_sha256": "66e2a6341854e8b2de0567a46282b94669e73b95d152b05b17b0f8b58e257fec",
|
||||
"js_bytes": 570290,
|
||||
"content_sha256": "49d59597c01b5264875e0295c86c7bb2212bf54d3c5858cd4a167752370fa716",
|
||||
"modules": [],
|
||||
"compat_date": "2025-02-19",
|
||||
"compat_flags": [
|
||||
@@ -58,11 +58,11 @@
|
||||
{
|
||||
"name": "arcrun-kbdb",
|
||||
"source_dir": "kbdb",
|
||||
"source_commit": "a7e23badf2a771be779a861e69e7efa6e8141dfe",
|
||||
"source_commit": "c497ec418eba6cd94b1d5872671c51fd5812c11c",
|
||||
"main_module": "worker.mjs",
|
||||
"main_file": "arcrun-kbdb/worker.mjs",
|
||||
"js_bytes": 135910,
|
||||
"content_sha256": "5e5a7a030f4fd1f5549ace6791c3827b6497b0bfdd9add46af041af47c472905",
|
||||
"js_bytes": 149533,
|
||||
"content_sha256": "ffb8d43467d0cefbd7545fdc0d347f2b965e3c3de20b3315eed7613f20266891",
|
||||
"modules": [],
|
||||
"compat_date": "2025-02-19",
|
||||
"compat_flags": [
|
||||
@@ -90,8 +90,8 @@
|
||||
"source_commit": "1e85dfb49b0e8d81c0854781d93ee4e6a300c7b3",
|
||||
"main_module": "worker.mjs",
|
||||
"main_file": "arcrun-http-request/worker.mjs",
|
||||
"js_bytes": 80073,
|
||||
"content_sha256": "9a9dcb71879a7bdfd9fec1bd94eb9742e12cb63733d822ce63eeb1be30008d15",
|
||||
"js_bytes": 80079,
|
||||
"content_sha256": "cdd97364f277587cbade69e09bb40812c68f26a1e8bc9aa632c65b1b962b0b85",
|
||||
"modules": [
|
||||
{
|
||||
"name": "component.wasm",
|
||||
@@ -122,8 +122,8 @@
|
||||
"source_commit": "621cb8d948d61be6202063fd02effb3f538437fe",
|
||||
"main_module": "worker.mjs",
|
||||
"main_file": "arcrun-code/worker.mjs",
|
||||
"js_bytes": 153671,
|
||||
"content_sha256": "285a7406ec694ae47dccfaf48517f712c74d207a1689dffa15c39f1555b45be5",
|
||||
"js_bytes": 153758,
|
||||
"content_sha256": "751634a3fc9a99cc2da662026818d754c48f031d10bff3b3be2d3a8ee2311bd6",
|
||||
"modules": [
|
||||
{
|
||||
"name": "quickjs.wasm",
|
||||
@@ -151,8 +151,8 @@
|
||||
"source_commit": "035e8b255b0dcbd4238707f7d2ac8ccf9ee1ba72",
|
||||
"main_module": "worker.mjs",
|
||||
"main_file": "arcrun-mcp/worker.mjs",
|
||||
"js_bytes": 1165130,
|
||||
"content_sha256": "be15033f32e605f03f69bd10cd87782dafa34dbafeee2ce367bd7361a062a291",
|
||||
"js_bytes": 1165388,
|
||||
"content_sha256": "c5ff10f9b9d5a77217be343af12d2be3ee8f9792d3e1e091e48e5e6c8d24ca9d",
|
||||
"modules": [],
|
||||
"compat_date": "2024-11-27",
|
||||
"compat_flags": [
|
||||
|
||||
@@ -277,9 +277,12 @@ function taipeiMonthDay(ms) { var d = new Date(ms + TAIPEI_OFFSET_MS); return {
|
||||
} else {
|
||||
rows.push(sysRow('語意嵌入', '狀態讀不到', 'off'));
|
||||
}
|
||||
rows.push(sys.graph && sys.graph.ok
|
||||
? sysRow('知識圖譜', '● 正常・三元組 ' + (sys.graph.triplets == null ? '?' : sys.graph.triplets), 'ok')
|
||||
: sysRow('知識圖譜', '● 打不通', 'bad'));
|
||||
// Arcrun#100：「服務活著嗎」與「庫裡有幾條」拆兩列。混一列時，圖服務打不通會把
|
||||
// 「其實有 1854 條」整個吞掉，畫面看起來就像知識庫是空的。數字讀不到寫「讀不到」，不寫 0。
|
||||
var gOk = !!(sys.graph && sys.graph.ok);
|
||||
var tri = sys.graph && sys.graph.triplets != null ? sys.graph.triplets : null;
|
||||
rows.push(sysRow('知識圖譜服務', gOk ? '● 正常' : '● 打不通', gOk ? 'ok' : 'bad'));
|
||||
rows.push(sysRow('三元組（關聯）', tri == null ? '讀不到' : tri.toLocaleString() + ' 條', tri == null ? 'off' : ''));
|
||||
rows.push(sysRow('工作流', sys.workflow_total == null ? '讀不到' : sys.workflow_total + ' 條', sys.workflow_total == null ? 'off' : ''));
|
||||
// 精耕層 wiki 卡（leo 2026-07-07 裁：14-E 遺產總數 deprecated 不再顯示，只顯示真的新的；
|
||||
// 三元組/已嵌入 已各有一列）
|
||||
|
||||
@@ -934,14 +934,15 @@ function taipeiMonthDay(ms) { var d = new Date(ms + TAIPEI_OFFSET_MS); return {
|
||||
fetch(API_BASE + '/console/kb-scale-data')
|
||||
.then(function (r) { return r.ok ? r.json() : null; })
|
||||
.then(function (d) {
|
||||
if (!d) return;
|
||||
var n = function (v) { return v == null ? '？' : v.toLocaleString(); };
|
||||
// #100：讀不到就明說讀不到（原本靜默 return，會把上一輪的舊數字留在畫面上）
|
||||
if (!d) { $('se-scale').textContent = '精耕層 讀不到（規模統計讀取失敗，不影響搜尋）'; return; }
|
||||
var n = function (v) { return v == null ? '讀不到' : v.toLocaleString(); };
|
||||
var parts = ['wiki 卡 ' + n(d.wiki_card_total), '三元組 ' + n(d.triplets_total), '已嵌入 ' + n(d.embedded)];
|
||||
var latest = d.wiki_card_latest_ago_minutes;
|
||||
$('se-scale').textContent = '精耕層 ' + parts.join('・') +
|
||||
(latest != null && latest >= 0 ? '・最近寫入 ' + ckAge(latest) : '');
|
||||
})
|
||||
.catch(function () { /* 規模感拿不到不擋搜尋 */ });
|
||||
.catch(function () { $('se-scale').textContent = '精耕層 讀不到（規模統計讀取失敗，不影響搜尋）'; });
|
||||
}
|
||||
$('se-sem').addEventListener('click', function () {
|
||||
S.semantic = !S.semantic;
|
||||
@@ -1504,7 +1505,7 @@ function taipeiMonthDay(ms) { var d = new Date(ms + TAIPEI_OFFSET_MS); return {
|
||||
]).then(function (rs) {
|
||||
var svc = rs[0].status === 'fulfilled' ? rs[0].value : {};
|
||||
var kb = rs[1].status === 'fulfilled' ? rs[1].value : null;
|
||||
var n = function (v) { return v == null ? '？' : v.toLocaleString(); };
|
||||
var n = function (v) { return v == null ? '讀不到' : v.toLocaleString(); };
|
||||
var rows = '';
|
||||
rows += '<div class="kvline"><span class="muted">服務</span><span class="mono" style="font-size:14px">' + esc(svc.service || 'arcrun-cypher-executor') + '</span></div>';
|
||||
rows += '<div class="kvline"><span class="muted">版本</span><span class="mono" style="color:var(--amber)">' + esc(svc.version || '—') + '</span></div>';
|
||||
|
||||
@@ -1486,7 +1486,14 @@ function taipeiMonthDay(ms) { var d = new Date(ms + TAIPEI_OFFSET_MS); return {
|
||||
$('se-q').value = name;
|
||||
doGraphSearch(name);
|
||||
}
|
||||
// 讀不到就明說「讀不到」——標題列**絕不**留著 0 或舊數字（Arcrun#100：leo 看到
|
||||
// 「0 個實體・0 條關聯」以為要去上傳文件，其實庫裡有 1854 條，只是這支讀失敗了）。
|
||||
function mapUnavailable(html) {
|
||||
$('map-meta').textContent = '讀不到';
|
||||
$('map-box').innerHTML = '<div class="err" style="padding:30px 10px">' + html + '</div>';
|
||||
}
|
||||
function loadMap() {
|
||||
$('map-meta').textContent = '';
|
||||
$('map-box').innerHTML = '<div class="muted" style="padding:30px 10px">載入總圖中…</div>';
|
||||
$('map-md-link').innerHTML = SOURCE_WEB_BASE
|
||||
? '：<a href="' + esc(SOURCE_WEB_BASE + '/system-dev/wiki/00-MAP.md') + '" target="_blank" rel="noopener" style="color:var(--amber)">00-MAP.md ↗</a>'
|
||||
@@ -1495,14 +1502,31 @@ function taipeiMonthDay(ms) { var d = new Date(ms + TAIPEI_OFFSET_MS); return {
|
||||
.then(function (r) { return safeJson(r).then(function (d) { return { ok: r.ok, status: r.status, d: d }; }); })
|
||||
.then(function (x) {
|
||||
if (guard401(x.status)) return;
|
||||
if (!x.ok) { $('map-box').innerHTML = '<div class="err">' + esc(x.d.error || ('總圖載入失敗（HTTP ' + x.status + '）')) + '</div>'; return; }
|
||||
var nodes = x.d.nodes || [];
|
||||
var edges = x.d.edges || [];
|
||||
$('map-meta').textContent = nodes.length + ' 個實體・' + edges.length + ' 條關聯' + (x.d.truncated ? '・已達上限截斷' : '');
|
||||
if (!x.ok) { mapUnavailable(esc(x.d.error || ('總圖載入失敗（HTTP ' + x.status + '）'))); return; }
|
||||
// Arcrun#100：「0」只准在後端確認過真的是 0 的時候出現。
|
||||
// 形狀不對 → 讀不到（不是空庫）；nodes 為空但 empty_confirmed 不成立 → 讀不到。
|
||||
if (!Array.isArray(x.d.nodes) || !Array.isArray(x.d.edges)) {
|
||||
mapUnavailable('總圖回應格式不對——沒有拿到關聯資料。這不代表知識庫是空的。');
|
||||
return;
|
||||
}
|
||||
var nodes = x.d.nodes, edges = x.d.edges;
|
||||
var total = typeof x.d.triplets_total === 'number' ? x.d.triplets_total : null;
|
||||
if (!nodes.length && x.d.empty_confirmed !== true) {
|
||||
mapUnavailable(x.d.empty_reason === 'scope_mismatch'
|
||||
? '讀不到你這個帳號的關聯資料——知識庫裡有三元組'
|
||||
+ (total ? '（本帳號範圍算到 ' + total.toLocaleString() + ' 條）' : '')
|
||||
+ '，但這張圖一條都抽不出來。<br>'
|
||||
+ '<b>這不是「還沒有關聯」，不用去上傳文件</b>；比較像資料的歸屬範圍對不上，請通知管理員。'
|
||||
: '讀不到知識庫的關聯資料，無法確認庫裡有沒有關聯。<br>'
|
||||
+ '<b>這不是「還沒有關聯」，不用去上傳文件</b>——是這次讀取失敗，請稍後重整或通知管理員。');
|
||||
return;
|
||||
}
|
||||
$('map-meta').textContent = nodes.length + ' 個實體・' + edges.length + ' 條關聯'
|
||||
+ (total !== null && x.d.truncated ? '（全庫共 ' + total.toLocaleString() + ' 條，已達單次上限）' : x.d.truncated ? '・已達上限截斷' : '');
|
||||
if (!nodes.length) { $('map-box').innerHTML = '<div class="muted" style="padding:30px 10px">知識庫還沒有任何關聯——上傳文件後 AI 會自動織網。</div>'; return; }
|
||||
renderMap(nodes, edges);
|
||||
})
|
||||
.catch(function (e) { $('map-box').innerHTML = '<div class="err">請求失敗：' + esc(friendlyErr(e)) + '</div>'; });
|
||||
.catch(function (e) { mapUnavailable('請求失敗：' + esc(friendlyErr(e))); });
|
||||
}
|
||||
function renderMap(nodes, edges) {
|
||||
var N = nodes.length;
|
||||
|
||||
@@ -48,7 +48,7 @@
|
||||
*/
|
||||
import { Hono } from 'hono';
|
||||
import type { Bindings } from '../types';
|
||||
import { kbdbBase, graphBase } from './kbdb-proxy';
|
||||
import { kbdbBase, graphBase, graphHeaders } from './kbdb-proxy';
|
||||
import { validateConsoleSession } from './console-auth';
|
||||
import {
|
||||
type KbdbEntry,
|
||||
@@ -104,6 +104,31 @@ async function fetchJson<T>(url: string, headers?: Record<string, string>): Prom
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* 本租戶三元組的**真實總數**（null = 讀不到，畫面要顯示「讀不到」而非 0）。
|
||||
*
|
||||
* 🔴 Arcrun#100：不可以拿 graph-plugin `/triplets/stats` 的 `total` 當數量。
|
||||
* 那支的 `total` 是**分頁長度**不是 COUNT——它走 `/records/by-template/triplet`（KBDB 端
|
||||
* `searchByTemplate` 預設 limit=100、硬上限 500）且不帶 owner 過濾，所以 1854 條的庫
|
||||
* 只會回 100。修好 401 之後若還讀它，畫面會從「0」變成「100」——一樣是假的。
|
||||
* 真相源＝KBDB `/records/triplet-stats`（真 SQL COUNT(*)、依 owner_id 過濾、無上限），
|
||||
* 回 `{ success, stats: [{ library, triplet_count }] }`，加總即全庫條數。
|
||||
*/
|
||||
async function fetchTripletTotal(env: Bindings, tenant: string): Promise<number | null> {
|
||||
const { base, headers } = kbdbBase(env);
|
||||
const data = await fetchJson<{ stats?: { triplet_count?: unknown }[] }>(
|
||||
`${base}/records/triplet-stats?owner_id=${encodeURIComponent(tenant)}`,
|
||||
headers,
|
||||
);
|
||||
if (!data || !Array.isArray(data.stats)) return null;
|
||||
let total = 0;
|
||||
for (const row of data.stats) {
|
||||
if (typeof row?.triplet_count !== 'number') return null; // 形狀不對 → 誠實回讀不到，不半信半疑加總
|
||||
total += row.triplet_count;
|
||||
}
|
||||
return total;
|
||||
}
|
||||
|
||||
/** KBDB entries 符合條件的總數（limit=1 只拿 total 欄，不搬資料）。null = 讀不到。 */
|
||||
async function fetchEntryTotal(env: Bindings, filters: Record<string, string>): Promise<number | null> {
|
||||
const { base, headers } = kbdbBase(env);
|
||||
@@ -254,6 +279,7 @@ consoleDashboardRouter.get('/console/dashboard-data', async (c) => {
|
||||
kbdbHealth,
|
||||
embedStatus,
|
||||
graphStats,
|
||||
tripletTotal,
|
||||
entriesTotal,
|
||||
wikiCardTotal,
|
||||
workflowTotal,
|
||||
@@ -265,7 +291,13 @@ consoleDashboardRouter.get('/console/dashboard-data', async (c) => {
|
||||
cachedGiteaSprint(c.env, now, (p) => c.executionCtx.waitUntil(p)),
|
||||
fetchJson<{ ok?: boolean }>(`${kbdbUrl}/health`, kbdbHeaders),
|
||||
fetchJson<{ enabled?: boolean; pending?: number; embedded?: number }>(`${kbdbUrl}/embed/backfill/status`, kbdbHeaders),
|
||||
fetchJson<{ total?: number; recent?: { today?: number; this_week?: number } }>(`${graphUrl}/triplets/stats`),
|
||||
// graph-plugin 只拿來判「圖服務活著沒」（燈號）——數字不從這裡拿，見 fetchTripletTotal。
|
||||
// headers 一定要帶：plugin 的 /triplets 前綴掛 Bearer 閘，漏帶＝永遠 401＝永遠假紅燈（#100）。
|
||||
fetchJson<{ total?: number; recent?: { today?: number; this_week?: number } }>(
|
||||
`${graphUrl}/triplets/stats`,
|
||||
graphHeaders(c.env),
|
||||
),
|
||||
fetchTripletTotal(c.env, tenant),
|
||||
// owner_id 一律鎖本租戶：原本不帶 owner 會混到別租戶（實測 459,137 vs leo 的 458,732）
|
||||
fetchEntryTotal(c.env, { owner_id: tenant }),
|
||||
fetchEntryTotal(c.env, { entry_type: 'wiki_card', owner_id: tenant }),
|
||||
@@ -400,13 +432,14 @@ consoleDashboardRouter.get('/console/dashboard-data', async (c) => {
|
||||
embed: embedStatus
|
||||
? { enabled: embedStatus.enabled === true, embedded: embedStatus.embedded ?? null, pending: embedStatus.pending ?? null }
|
||||
: null,
|
||||
graph: graphStats ? { ok: true, triplets: graphStats.total ?? null } : { ok: false, triplets: null },
|
||||
// ok = plugin 通不通（graphStats 讀得到就是通）；triplets = KBDB 真 COUNT（與 plugin 分頁長度無關）
|
||||
graph: { ok: graphStats !== null, triplets: tripletTotal },
|
||||
workflow_total: workflowTotal,
|
||||
},
|
||||
kb: {
|
||||
entries_total: entriesTotal,
|
||||
wiki_card_total: wikiCardTotal,
|
||||
triplets_total: graphStats?.total ?? null,
|
||||
triplets_total: tripletTotal,
|
||||
},
|
||||
generated_at: new Date(now).toISOString(),
|
||||
});
|
||||
@@ -420,15 +453,15 @@ consoleDashboardRouter.get('/console/dashboard-data', async (c) => {
|
||||
consoleDashboardRouter.get('/console/kb-scale-data', async (c) => {
|
||||
const tenant = c.env.CONSOLE_TENANT || 'leo';
|
||||
const { base, headers } = kbdbBase(c.env);
|
||||
const graphUrl = graphBase(c.env);
|
||||
const now = Date.now();
|
||||
const [wikiCards, graphStats, embedStatus] = await Promise.all([
|
||||
const [wikiCards, tripletTotal, embedStatus] = await Promise.all([
|
||||
// limit=1 順手拿最新一筆 created_at（list 為 created_at DESC）＝「最近寫入時間」
|
||||
fetchJson<{ total?: number; entries?: { created_at?: string | number }[] }>(
|
||||
`${base}/entries?${new URLSearchParams({ owner_id: tenant, entry_type: 'wiki_card', limit: '1' }).toString()}`,
|
||||
headers,
|
||||
),
|
||||
fetchJson<{ total?: number }>(`${graphUrl}/triplets/stats`),
|
||||
// #100：三元組數改讀 KBDB 真 COUNT，不再讀 graph-plugin 的分頁長度（見 fetchTripletTotal 註）
|
||||
fetchTripletTotal(c.env, tenant),
|
||||
fetchJson<{ enabled?: boolean; embedded?: number; pending?: number }>(`${base}/embed/backfill/status`, headers),
|
||||
]);
|
||||
const latestMs = parseCreatedAtMs(wikiCards?.entries?.[0]?.created_at ?? null);
|
||||
@@ -436,7 +469,7 @@ consoleDashboardRouter.get('/console/kb-scale-data', async (c) => {
|
||||
return c.json({
|
||||
wiki_card_total: typeof wikiCards?.total === 'number' ? wikiCards.total : null,
|
||||
wiki_card_latest_ago_minutes: latestMs === null ? -1 : agoMinutes(now, latestMs),
|
||||
triplets_total: typeof graphStats?.total === 'number' ? graphStats.total : null,
|
||||
triplets_total: tripletTotal,
|
||||
embedded: embedStatus?.embedded ?? null,
|
||||
embed_enabled: embedStatus ? embedStatus.enabled === true : null,
|
||||
generated_at: new Date(now).toISOString(),
|
||||
|
||||
@@ -223,13 +223,27 @@ export function graphBase(env: Bindings): string {
|
||||
return `https://kbdb-graph-plugin.${env.WORKER_SUBDOMAIN}.workers.dev`;
|
||||
}
|
||||
|
||||
/**
|
||||
* kbdb-graph-plugin 的 internal headers。**打 plugin 一律用這支，不要各自手拼**（Arcrun#100）。
|
||||
*
|
||||
* plugin 端（kbdb-graph-plugin/src/index.ts）對 `/triplets` `/graph` `/search` `/entities`
|
||||
* 四個前綴掛了 Bearer 閘：設了 KBDB_INTERNAL_TOKEN 就必須帶，否則一律 401。
|
||||
* 原本三處手拼（本檔 neighbors、portal-data neighbors、console-dashboard 兩支 stats），
|
||||
* 前兩處帶了、後兩處漏了 → `/triplets/stats` 永遠 401 → 前端「三元組 0」。
|
||||
* 收斂成一支函式＝新的呼叫點不可能再漏（漂移的根，不是那兩行本身）。
|
||||
*/
|
||||
export function graphHeaders(env: Bindings): Record<string, string> {
|
||||
const headers: Record<string, string> = {};
|
||||
if (env.KBDB_INTERNAL_TOKEN) headers['Authorization'] = `Bearer ${env.KBDB_INTERNAL_TOKEN}`;
|
||||
return headers;
|
||||
}
|
||||
|
||||
// GET /kbdb/graph/neighbors/:name — 查某節點（entity/卡片名）的鄰居 + 邊。
|
||||
// 查無 triplet 資料時 plugin 回空陣列——前端據此顯示「尚無關聯資料」（誠實，不編造關聯）。
|
||||
kbdbProxyRouter.get('/kbdb/graph/neighbors/:name', async (c) => {
|
||||
if (!tenant(c)) return c.json(NEED_KEY, 401);
|
||||
const base = graphBase(c.env);
|
||||
const headers: Record<string, string> = {};
|
||||
if (c.env.KBDB_INTERNAL_TOKEN) headers['Authorization'] = `Bearer ${c.env.KBDB_INTERNAL_TOKEN}`;
|
||||
const headers = graphHeaders(c.env);
|
||||
try {
|
||||
const res = await fetch(`${base}/graph/neighbors/${encodeURIComponent(c.req.param('name'))}`, { headers });
|
||||
return new Response(res.body, { status: res.status, headers: { 'Content-Type': 'application/json' } });
|
||||
|
||||
@@ -24,7 +24,7 @@ import { Hono } from 'hono';
|
||||
import type { Context } from 'hono';
|
||||
import type { Bindings } from '../types';
|
||||
import { kbdbFetch, run, requirePortalUser, parseLibraries, portalTenant, hasGraphAccess, workflowsVisible, uploadEnabled, buildDiagnostics } from './portal';
|
||||
import { graphBase } from './kbdb-proxy';
|
||||
import { graphBase, graphHeaders } from './kbdb-proxy';
|
||||
import { executeWebhookGraph } from '../actions/webhook-handlers';
|
||||
|
||||
export const portalDataRouter = new Hono<{ Bindings: Bindings }>();
|
||||
@@ -186,6 +186,45 @@ export function findBestNodeMatch(searchTerm: string, nodeNames: string[]): stri
|
||||
return hits.reduce((a, b) => a.length <= b.length ? a : b);
|
||||
}
|
||||
|
||||
/**
|
||||
* 三元組條數（KBDB `/records/triplet-stats` 真 SQL COUNT）。owner 傳 '' ＝不限租戶（KBDB 端
|
||||
* `?1 = '' OR e.owner_id = ?1`）。null＝讀不到——caller 據此不敢宣稱 0。
|
||||
*/
|
||||
async function tripletCount(env: Bindings, owner: string): Promise<number | null> {
|
||||
try {
|
||||
const res = await kbdbFetch(env, `/records/triplet-stats?owner_id=${encodeURIComponent(owner)}`);
|
||||
if (!res.ok) return null;
|
||||
const body = (await res.json().catch(() => null)) as { stats?: { triplet_count?: unknown }[] } | null;
|
||||
if (!body || !Array.isArray(body.stats)) return null;
|
||||
let total = 0;
|
||||
for (const row of body.stats) {
|
||||
if (typeof row?.triplet_count !== 'number') return null;
|
||||
total += row.triplet_count;
|
||||
}
|
||||
return total;
|
||||
} catch {
|
||||
return null;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* 三元組普查（Arcrun#100）——回答總圖那句「知識庫還沒有任何關聯」到底能不能講。
|
||||
*
|
||||
* leo 的原則（已寫在 portal.ts §②.5 daemon diagnostics）：**「不要讓『查不到』和『沒有』
|
||||
* 長得一樣」**。t161 前科：手補的 record owner_id 存成 None ⇒ 全量查得到、按 owner_id 過濾
|
||||
* 的畫面永遠空——比真的沒資料更難查。所以本租戶數為 0 時**再花一次查詢換一條路徑**
|
||||
* （同一支端點但不帶 owner），問「這個庫到底有沒有三元組」：
|
||||
* owned>0 → 有資料
|
||||
* owned=0 且 any=0 → 真的空（此時、也只有此時，畫面才准印 0）
|
||||
* owned=0 但 any>0 → owner_id / 範圍對不上，不是空庫 → 畫面說讀不到
|
||||
* owned=null → 讀不到 → 畫面說讀不到
|
||||
*/
|
||||
async function tripletCensus(env: Bindings, tenant: string): Promise<{ owned: number | null; any: number | null }> {
|
||||
const owned = await tripletCount(env, tenant);
|
||||
if (owned !== 0) return { owned, any: null }; // 非 0（含 null）不必多問一次
|
||||
return { owned, any: await tripletCount(env, '') };
|
||||
}
|
||||
|
||||
/** 從 KBDB triplet records 找最佳比對節點名（t96 plugin fuzzy fallback 用）。 */
|
||||
async function fuzzyFindNode(env: Bindings, tenant: string, searchTerm: string): Promise<string | null> {
|
||||
try {
|
||||
@@ -343,8 +382,7 @@ portalDataRouter.get('/portal/data/graph/neighbors/:name', (c) =>
|
||||
|
||||
// ② plugin fallback（Mira/leo21c 相容）
|
||||
const base = graphBase(c.env);
|
||||
const headers: Record<string, string> = {};
|
||||
if (c.env.KBDB_INTERNAL_TOKEN) headers['Authorization'] = `Bearer ${c.env.KBDB_INTERNAL_TOKEN}`;
|
||||
const headers = graphHeaders(c.env);
|
||||
try {
|
||||
const res = await fetch(`${base}/graph/neighbors/${encodeURIComponent(nodeName)}`, { headers });
|
||||
if (!res.ok) {
|
||||
@@ -383,14 +421,23 @@ portalDataRouter.get('/portal/data/graph/overview', (c) =>
|
||||
return c.json({ error: '無知識圖譜檢視權限' }, 403);
|
||||
}
|
||||
const tenant = portalTenant(c.env);
|
||||
const res = await kbdbFetch(c.env, `/records/by-template/triplet?owner_id=${encodeURIComponent(tenant)}`);
|
||||
const [res, census] = await Promise.all([
|
||||
kbdbFetch(c.env, `/records/by-template/triplet?owner_id=${encodeURIComponent(tenant)}&limit=500`),
|
||||
tripletCensus(c.env, tenant),
|
||||
]);
|
||||
const tripletsTotal = census.owned;
|
||||
if (!res.ok) {
|
||||
return new Response(res.body, { status: res.status, headers: { 'Content-Type': 'application/json' } });
|
||||
}
|
||||
const body = (await res.json().catch(() => null)) as
|
||||
| { records?: { values?: Record<string, unknown> }[] }
|
||||
| null;
|
||||
const records = body && Array.isArray(body.records) ? body.records : [];
|
||||
// #100：形狀不對 ≠ 沒有資料。原本 `: []` 會把「讀不出來」變成一張空圖，
|
||||
// 前端照著印「0 個實體・0 條關聯」——那是畫面在說謊。讀不出來就誠實 502。
|
||||
if (!body || !Array.isArray(body.records)) {
|
||||
return c.json({ error: '三元組讀取失敗：KBDB 回應不是預期的 records 清單' }, 502);
|
||||
}
|
||||
const records = body.records;
|
||||
const EDGE_CAP = 500;
|
||||
const seen = new Set<string>();
|
||||
const edges: { subject: string; predicate: string; object: string }[] = [];
|
||||
@@ -413,7 +460,28 @@ portalDataRouter.get('/portal/data/graph/overview', (c) =>
|
||||
degree.set(o, (degree.get(o) ?? 0) + 1);
|
||||
}
|
||||
const nodes = [...degree.entries()].map(([name, d]) => ({ name, degree: d }));
|
||||
return c.json({ nodes, edges, node_count: nodes.length, edge_count: edges.length, truncated });
|
||||
// #100：一張空圖有三種成因，前端必須分得出來（判準留在 server，不留給前端猜）——
|
||||
// confirmed_empty ：本租戶真的一條都沒有，全庫也沒有 → 才准印「0 個實體・0 條關聯」
|
||||
// scope_mismatch ：全庫有、本租戶查不到 → owner_id/範圍對不上，不是空庫（t161 前科）
|
||||
// unreadable ：連條數都讀不到 → 只能說讀不到
|
||||
let emptyReason: 'confirmed_empty' | 'scope_mismatch' | 'unreadable' | null = null;
|
||||
if (nodes.length === 0) {
|
||||
if (census.owned === null) emptyReason = 'unreadable';
|
||||
else if (census.owned > 0) emptyReason = 'scope_mismatch'; // 有條數卻抽不出邊
|
||||
else if (census.any === null) emptyReason = 'unreadable';
|
||||
else emptyReason = census.any > 0 ? 'scope_mismatch' : 'confirmed_empty';
|
||||
}
|
||||
return c.json({
|
||||
nodes,
|
||||
edges,
|
||||
node_count: nodes.length,
|
||||
edge_count: edges.length,
|
||||
// 取到的 record 已達 KBDB 單頁上限 → 這張圖只是全庫的一部分，別讓 meta 看起來像全部
|
||||
truncated: truncated || records.length >= 500,
|
||||
triplets_total: tripletsTotal,
|
||||
empty_confirmed: nodes.length > 0 || emptyReason === 'confirmed_empty',
|
||||
empty_reason: emptyReason,
|
||||
});
|
||||
}),
|
||||
);
|
||||
|
||||
|
||||
@@ -0,0 +1,147 @@
|
||||
/**
|
||||
* Arcrun#100 — 「畫面上的 0，只准在真的是 0 的時候出現」
|
||||
*
|
||||
* 病灶（leo 實遇）：總圖頁寫「0 個實體・0 條關聯／知識庫還沒有任何關聯——上傳文件後 AI 會
|
||||
* 自動織網」，而他庫裡有 1854 條三元組。那句話會叫他去做一件不需要做的事。
|
||||
*
|
||||
* 本檔釘住三件事：
|
||||
* ① kbdb-graph-plugin 的 `/triplets` 前綴掛 Bearer 閘，cypher 打它**一定要帶 token**
|
||||
* （console-dashboard 兩支 stats 原本漏帶 → 永遠 401）。
|
||||
* ② 三元組數量的真相源＝KBDB `/records/triplet-stats`（真 SQL COUNT、依 owner 過濾），
|
||||
* **不是** plugin `/triplets/stats` 的 `total`——那是分頁長度（KBDB 端上限 100/500），
|
||||
* 1854 條的庫只會回 100。只修 401 不換來源＝把「0」換成「100」，一樣是假的。
|
||||
* ③ 讀不到一律 null / 502 / empty_confirmed=false，**絕不退化成 0**。
|
||||
*
|
||||
* KBDB／graph-plugin 都打 fetchMock 假 host（wrangler.test.toml KBDB_BASE_URL=https://kbdb.test、
|
||||
* KBDB_GRAPH_URL=https://graph.test）＋disableNetConnect——絕不外連。
|
||||
*/
|
||||
import { SELF, env, fetchMock } from 'cloudflare:test';
|
||||
import { beforeAll, afterEach, describe, it, expect } from 'vitest';
|
||||
import { graphHeaders, graphBase } from '../src/routes/kbdb-proxy';
|
||||
import type { Bindings } from '../src/types';
|
||||
|
||||
const KBDB = 'https://kbdb.test';
|
||||
const GRAPH = 'https://graph.test';
|
||||
const TENANT = 'leo'; // wrangler.test.toml CONSOLE_TENANT
|
||||
|
||||
beforeAll(() => {
|
||||
fetchMock.activate();
|
||||
fetchMock.disableNetConnect();
|
||||
});
|
||||
afterEach(() => fetchMock.assertNoPendingInterceptors());
|
||||
|
||||
/** KBDB `/records/triplet-stats` — 真 COUNT 的形狀：{ success, stats: [{library, triplet_count}] } */
|
||||
function mockTripletStats(rows: { library: string; triplet_count: number }[] | null, status = 200) {
|
||||
fetchMock
|
||||
.get(KBDB)
|
||||
.intercept({ path: (p: string) => p.startsWith('/records/triplet-stats'), method: 'GET' })
|
||||
.reply(status, rows === null ? { success: false, error: 'boom' } : { success: true, stats: rows });
|
||||
}
|
||||
|
||||
// ═══════════════ 1. graphHeaders：打 plugin 的 header 只有一份 ═══════════════
|
||||
|
||||
describe('graphHeaders（#100 漂移的根：三處手拼 → 一支函式）', () => {
|
||||
it('有 KBDB_INTERNAL_TOKEN → 帶 Bearer（plugin 的 /triplets /graph /search /entities 全靠它）', () => {
|
||||
expect(graphHeaders({ KBDB_INTERNAL_TOKEN: 'tok-abc' } as unknown as Bindings)).toEqual({
|
||||
Authorization: 'Bearer tok-abc',
|
||||
});
|
||||
});
|
||||
|
||||
it('沒設 token → 空 headers（plugin 未設 secret 時本來就開放，不硬塞空 Bearer）', () => {
|
||||
expect(graphHeaders({} as unknown as Bindings)).toEqual({});
|
||||
});
|
||||
|
||||
it('graphBase 仍照舊（KBDB_GRAPH_URL 優先、去尾斜線）', () => {
|
||||
expect(graphBase({ KBDB_GRAPH_URL: 'https://graph.test/' } as unknown as Bindings)).toBe('https://graph.test');
|
||||
});
|
||||
});
|
||||
|
||||
// ═══════════════ 2. /console/kb-scale-data：數字對得上庫裡真正的數量 ═══════════════
|
||||
|
||||
describe('GET /console/kb-scale-data — 三元組數＝KBDB 真 COUNT', () => {
|
||||
it('庫裡 1854 條（跨三個庫）→ triplets_total 回 1854，不是 plugin 的分頁長度 100', async () => {
|
||||
mockTripletStats([
|
||||
{ library: 'general', triplet_count: 1200 },
|
||||
{ library: 'finance', triplet_count: 600 },
|
||||
{ library: 'ops', triplet_count: 54 },
|
||||
]);
|
||||
const res = await SELF.fetch('http://localhost/console/kb-scale-data');
|
||||
expect(res.status).toBe(200);
|
||||
const d = (await res.json()) as { triplets_total: number | null };
|
||||
expect(d.triplets_total).toBe(1854);
|
||||
});
|
||||
|
||||
it('反向：triplet-stats 讀不到（500）→ triplets_total = null，**不是 0**', async () => {
|
||||
mockTripletStats(null, 500);
|
||||
const res = await SELF.fetch('http://localhost/console/kb-scale-data');
|
||||
expect(res.status).toBe(200);
|
||||
const d = (await res.json()) as { triplets_total: number | null };
|
||||
expect(d.triplets_total).toBeNull();
|
||||
expect(d.triplets_total).not.toBe(0); // 這一行就是 #100 的整個重點
|
||||
});
|
||||
|
||||
it('反向：回應形狀不對（stats 不是陣列）→ null，不半信半疑當 0', async () => {
|
||||
fetchMock
|
||||
.get(KBDB)
|
||||
.intercept({ path: (p: string) => p.startsWith('/records/triplet-stats'), method: 'GET' })
|
||||
.reply(200, { success: true, stats: 'oops' });
|
||||
const res = await SELF.fetch('http://localhost/console/kb-scale-data');
|
||||
const d = (await res.json()) as { triplets_total: number | null };
|
||||
expect(d.triplets_total).toBeNull();
|
||||
});
|
||||
|
||||
it('真的是 0（庫存在但沒有任何三元組）→ 誠實回 0（0 只在這種時候出現）', async () => {
|
||||
mockTripletStats([]);
|
||||
const res = await SELF.fetch('http://localhost/console/kb-scale-data');
|
||||
const d = (await res.json()) as { triplets_total: number | null };
|
||||
expect(d.triplets_total).toBe(0);
|
||||
});
|
||||
|
||||
it('kb-scale-data 不再打 graph-plugin（沒有 plugin interceptor 也能拿到數字）', async () => {
|
||||
mockTripletStats([{ library: 'general', triplet_count: 7 }]);
|
||||
const res = await SELF.fetch('http://localhost/console/kb-scale-data');
|
||||
const d = (await res.json()) as { triplets_total: number | null };
|
||||
expect(d.triplets_total).toBe(7); // 打 GRAPH 的話 disableNetConnect 會讓它變 null
|
||||
});
|
||||
});
|
||||
|
||||
// ═══════════════ 3. /console/dashboard-data：燈號問 plugin、數字問 KBDB ═══════════════
|
||||
|
||||
describe('GET /console/dashboard-data — 圖服務健康 vs 三元組數量是兩件事', () => {
|
||||
it('打 plugin /triplets/stats **有帶 Bearer** → graph.ok=true；數量仍取 KBDB 真 COUNT', async () => {
|
||||
// headers matcher：漏帶 Authorization 就配不到這個 interceptor → 請求失敗 → graph.ok=false
|
||||
fetchMock
|
||||
.get(GRAPH)
|
||||
.intercept({
|
||||
path: (p: string) => p.startsWith('/triplets/stats'),
|
||||
method: 'GET',
|
||||
headers: { authorization: `Bearer ${env.KBDB_INTERNAL_TOKEN}` },
|
||||
})
|
||||
.reply(200, { total: 100 }); // plugin 的分頁長度，故意與真值不同
|
||||
mockTripletStats([{ library: 'general', triplet_count: 1854 }]);
|
||||
const res = await SELF.fetch('http://localhost/console/dashboard-data');
|
||||
expect(res.status).toBe(200);
|
||||
const d = (await res.json()) as {
|
||||
system: { graph: { ok: boolean; triplets: number | null } };
|
||||
kb: { triplets_total: number | null };
|
||||
};
|
||||
expect(d.system.graph.ok).toBe(true); // 帶了 token 才會是 true（#100 迴歸閘）
|
||||
expect(d.system.graph.triplets).toBe(1854); // 不是 plugin 的 100
|
||||
expect(d.kb.triplets_total).toBe(1854);
|
||||
});
|
||||
|
||||
it('反向：plugin 打不通 → graph.ok=false，但三元組數照樣是真的（不被服務狀態吞掉）', async () => {
|
||||
mockTripletStats([{ library: 'general', triplet_count: 1854 }]);
|
||||
const res = await SELF.fetch('http://localhost/console/dashboard-data');
|
||||
const d = (await res.json()) as { system: { graph: { ok: boolean; triplets: number | null } } };
|
||||
expect(d.system.graph.ok).toBe(false);
|
||||
expect(d.system.graph.triplets).toBe(1854);
|
||||
});
|
||||
|
||||
it('反向：兩邊都讀不到 → ok=false + triplets=null（不是 0）', async () => {
|
||||
const res = await SELF.fetch('http://localhost/console/dashboard-data');
|
||||
const d = (await res.json()) as { system: { graph: { ok: boolean; triplets: number | null } } };
|
||||
expect(d.system.graph.ok).toBe(false);
|
||||
expect(d.system.graph.triplets).toBeNull();
|
||||
});
|
||||
});
|
||||
@@ -942,3 +942,91 @@ describe('GET /portal/daemon/diagnostics（t213 daemon 版）', () => {
|
||||
expect(JSON.stringify(body.notes)).not.toContain('截圖');
|
||||
});
|
||||
});
|
||||
|
||||
// ═══ Arcrun#100: 總圖的「0」只准在真的是 0 的時候出現 ═══
|
||||
|
||||
describe('GET /portal/data/graph/overview（#100 空圖三態）', () => {
|
||||
/** KBDB `/records/triplet-stats`：帶 owner 與不帶 owner 是兩條不同路徑，分別攔。 */
|
||||
function mockCount(scoped: number | null, global?: number | null) {
|
||||
fetchMock
|
||||
.get(KBDB)
|
||||
.intercept({ path: (p: string) => p.startsWith(`/records/triplet-stats?owner_id=${TENANT}`), method: 'GET' })
|
||||
.reply(scoped === null ? 500 : 200, scoped === null ? { error: 'boom' } : { success: true, stats: [{ library: 'general', triplet_count: scoped }] });
|
||||
if (global !== undefined) {
|
||||
fetchMock
|
||||
.get(KBDB)
|
||||
.intercept({ path: (p: string) => p === '/records/triplet-stats?owner_id=', method: 'GET' })
|
||||
.reply(global === null ? 500 : 200, global === null ? { error: 'boom' } : { success: true, stats: [{ library: 'general', triplet_count: global }] });
|
||||
}
|
||||
}
|
||||
function mockTriplets(body: object, status = 200) {
|
||||
fetchMock
|
||||
.get(KBDB)
|
||||
.intercept({ path: (p: string) => p.startsWith('/records/by-template/triplet'), method: 'GET' })
|
||||
.reply(status, body);
|
||||
}
|
||||
async function overview(token: string) {
|
||||
await seedSession(token, `rec_${token}`);
|
||||
mockGetRecord(`rec_${token}`, userValues({ libraries: '["*"]', role: 'admin' }));
|
||||
return get('/portal/data/graph/overview', { Authorization: `Bearer ${token}` });
|
||||
}
|
||||
|
||||
it('有資料 → 照常回圖，並附上全庫真實條數', async () => {
|
||||
mockTriplets({ success: true, records: [{ values: { subject: 'A', predicate: '連到', object: 'B' } }] });
|
||||
mockCount(1854);
|
||||
const res = await overview('tok-ov1');
|
||||
expect(res.status).toBe(200);
|
||||
const d = (await res.json()) as { node_count: number; triplets_total: number; empty_confirmed: boolean };
|
||||
expect(d.node_count).toBe(2);
|
||||
expect(d.triplets_total).toBe(1854);
|
||||
expect(d.empty_confirmed).toBe(true);
|
||||
});
|
||||
|
||||
it('真的空（本租戶 0、全庫也 0）→ empty_confirmed=true，畫面才准印 0', async () => {
|
||||
mockTriplets({ success: true, records: [] });
|
||||
mockCount(0, 0);
|
||||
const res = await overview('tok-ov2');
|
||||
const d = (await res.json()) as { node_count: number; empty_confirmed: boolean; empty_reason: string };
|
||||
expect(d.node_count).toBe(0);
|
||||
expect(d.empty_confirmed).toBe(true);
|
||||
expect(d.empty_reason).toBe('confirmed_empty');
|
||||
});
|
||||
|
||||
it('🔴 反向：本租戶查到 0、全庫卻有 1854（t161 owner_id 對不上）→ 不准說空，回 scope_mismatch', async () => {
|
||||
mockTriplets({ success: true, records: [] });
|
||||
mockCount(0, 1854);
|
||||
const res = await overview('tok-ov3');
|
||||
const d = (await res.json()) as { empty_confirmed: boolean; empty_reason: string };
|
||||
expect(d.empty_confirmed).toBe(false);
|
||||
expect(d.empty_reason).toBe('scope_mismatch');
|
||||
});
|
||||
|
||||
it('🔴 反向：條數讀不到 → unreadable（不是 confirmed_empty，畫面顯示「讀不到」）', async () => {
|
||||
mockTriplets({ success: true, records: [] });
|
||||
mockCount(null);
|
||||
const res = await overview('tok-ov4');
|
||||
const d = (await res.json()) as { empty_confirmed: boolean; empty_reason: string; triplets_total: number | null };
|
||||
expect(d.empty_confirmed).toBe(false);
|
||||
expect(d.empty_reason).toBe('unreadable');
|
||||
expect(d.triplets_total).toBeNull();
|
||||
});
|
||||
|
||||
it('🔴 反向：有條數卻一條邊都抽不出來 → scope_mismatch，不是空庫', async () => {
|
||||
mockTriplets({ success: true, records: [{ values: { subject: '', object: '' } }] });
|
||||
mockCount(1854);
|
||||
const res = await overview('tok-ov5');
|
||||
const d = (await res.json()) as { node_count: number; empty_confirmed: boolean; empty_reason: string };
|
||||
expect(d.node_count).toBe(0);
|
||||
expect(d.empty_reason).toBe('scope_mismatch');
|
||||
expect(d.empty_confirmed).toBe(false);
|
||||
});
|
||||
|
||||
it('🔴 反向：KBDB 回應形狀不對（沒有 records 陣列）→ 502，不再回一張空圖', async () => {
|
||||
mockTriplets({ success: true, items: [] }); // 欄位名不對＝讀不出來
|
||||
mockCount(1854);
|
||||
const res = await overview('tok-ov6');
|
||||
expect(res.status).toBe(502);
|
||||
const d = (await res.json()) as { error: string };
|
||||
expect(d.error).toContain('三元組讀取失敗');
|
||||
});
|
||||
});
|
||||
|
||||
@@ -49,6 +49,10 @@ KBDB_BASE_URL = "https://kbdb.test"
|
||||
CONSOLE_TENANT = "leo"
|
||||
# portal-auth P3：graph 粗閘放行後的轉發目標也指假 host（fetchMock 攔截，絕不外連）
|
||||
KBDB_GRAPH_URL = "https://graph.test"
|
||||
# Arcrun#100：kbdb-graph-plugin 對 /triplets /graph /search /entities 掛 Bearer 閘。測試環境要有
|
||||
# 這把（明顯的假字串、非真實金鑰）才驗得出「cypher 打 plugin 有沒有帶 token」——原本兩支
|
||||
# /triplets/stats 漏帶 → 永遠 401 → 前端「三元組 0」。真實部署仍走 wrangler secret put。
|
||||
KBDB_INTERNAL_TOKEN = "test-fake-not-a-real-token" # credential-ok：測試假值，同上方 CF_SECRETS_API_TOKEN 慣例
|
||||
# D61（ADR D61 / Leo/arcrun-rag#55）：認證儲存（lib/portal-auth-store.ts）走 CF Workers
|
||||
# Scripts secrets 管理 API（https://api.cloudflare.com/...），authStoreWritable() 只看這兩項
|
||||
# 存不存在。測試環境預設就緒（比照真實已裝妥的實例），值是明顯的假字串、非真實金鑰；實際的
|
||||
|
||||
@@ -216,12 +216,63 @@ const MAX_LIKE_TERMS = 6;
|
||||
|
||||
const utf8Len = (s: string): number => new TextEncoder().encode(s).length;
|
||||
|
||||
/** 依 UTF-8 byte 上限切片，不切壞多位元組字元。 */
|
||||
// ── 使用者打的 `%` 與 `_` 是「要找的字」，不是萬用字元（Arcrun#94）────────────────
|
||||
//
|
||||
// 病徵：搜尋框打 `100%` 或 `owner_id`，回來一堆跟那些字無關的東西。
|
||||
// SQLite LIKE 只有兩個萬用字元——`%`（任意長度）與 `_`（任意一個字元），而且
|
||||
// **沒有預設跳脫字元**（不寫 ESCAPE 就沒有任何辦法表示「字面上的 %」）。
|
||||
// 我們把使用者輸入直接內插成 `'%' + q + '%'` ⇒ 他打的符號被當成 pattern 語法：
|
||||
// `100%` → `%100%%` → 「100」開頭後面接什麼都算 ⇒ 撈回一堆不相干的
|
||||
// `owner_id` → `%owner_id%` → `_` 匹配任一字元 ⇒ `ownerXid`、`owner-id` 也中
|
||||
// `%`／`_` 單打 → `%%%`／`%_%` → **整個庫都回來**（`_` 只要有一個字元就中）
|
||||
//
|
||||
// 這是舊病，不是 08-10 斷詞（47c6aae→本檔上一段）引進的：pattern 一直都是這樣拼的。
|
||||
// 之前關鍵字搜尋幾乎恆為 0 命中（整串比對），這個洞被那個洞蓋住，看不出來；
|
||||
// 斷詞讓搜尋真的會回東西之後它才浮出來。**斷詞那段一個字都沒動。**
|
||||
//
|
||||
// 修法：三個字元都跳脫，並在每個 LIKE 後面掛 `ESCAPE '\'`。
|
||||
//
|
||||
// 為什麼**跳脫字元本身（`\`）也要跳脫**（邊界問題的答案，不是順手多做）：
|
||||
// 一旦宣告了 ESCAPE，`\` 在 pattern 裡就變成有意義的字元，於是「使用者打的 `\`」
|
||||
// 同樣會被誤讀——而且是更糟的一種，因為它會**把後面那個字吃掉**：
|
||||
// 使用者打 `100\%` → 不跳脫 `\` ⇒ pattern `%100\%%` ⇒ `\%`＝字面 %
|
||||
// ⇒ 實際找的是 `100%`，**跟他打的字不一樣**
|
||||
// 使用者打 `C:\` → pattern `%C:\%` ⇒ 尾巴 `\%`＝字面 %
|
||||
// ⇒ 找的是 `C:%`，而真正的 `C:\` 反而找不到
|
||||
// ⇒ 三個字元是一組的：宣告 ESCAPE 卻不跳脫 `\` 等於用新的漏洞換掉舊的。
|
||||
// （SQLite 對「`\` 後面接其他字元」是寬容的——照字面匹配下一個字、不報錯——
|
||||
// 所以不跳脫不會炸，只會靜靜地找錯東西，正是最難發現的那種。）
|
||||
//
|
||||
// 為什麼**只有這三個**：SQLite 的 LIKE 萬用字元就只有 `%` 和 `_`（`[...]`、`?`、`*`
|
||||
// 是別的方言／GLOB 的東西，LIKE 不吃），加上自己宣告的跳脫字元 `\`，就這三個。
|
||||
// 不多跳脫其他字元——跳脫沒有語法意義的字元只會白白吃掉 pattern 的 byte 預算。
|
||||
//
|
||||
// 🔴 與 50 bytes 上限的交互作用（不能只加跳脫就收工）：跳脫會**變長**（`%`→`\%`），
|
||||
// 所以所有 byte 預算改用「跳脫後」的長度算（likeBytes），否則使用者打一串 `%`
|
||||
// 會讓 pattern 膨脹回 50 bytes 以上 ⇒ 退回 2026-08-03 那個 500。
|
||||
// 不含這三個字元的查詢，likeBytes ≡ utf8Len ⇒ **既有查詢的行為逐字不變**。
|
||||
const LIKE_ESCAPE = '\\';
|
||||
/** 每個 `content LIKE ?` 都要帶著它的 ESCAPE 宣告，否則跳脫過的 pattern 反而被當字面。 */
|
||||
const CONTENT_LIKE = `content LIKE ? ESCAPE '${LIKE_ESCAPE}'`;
|
||||
|
||||
/** 把使用者輸入當「字面字串」送進 LIKE（純函式，單測用 export）。 */
|
||||
export function escapeLikeLiteral(s: string): string {
|
||||
// 一次掃描、每個字元各自替換 ⇒ 不會發生「先換 % 再換 \ 把剛加的跳脫又跳脫一次」。
|
||||
return s.replace(/[\\%_]/g, (ch) => LIKE_ESCAPE + ch);
|
||||
}
|
||||
|
||||
/** 這段文字**跳脫後**佔的 byte 數（＝它在 LIKE pattern 裡真正佔的長度）。 */
|
||||
const likeBytes = (s: string): number => utf8Len(escapeLikeLiteral(s));
|
||||
|
||||
/** 子字串比對用的 pattern：只有頭尾那兩個 `%` 是萬用字元，中間全是字面。 */
|
||||
const likePattern = (s: string): string => `%${escapeLikeLiteral(s)}%`;
|
||||
|
||||
/** 依 UTF-8 byte 上限切片，不切壞多位元組字元。上限算的是**跳脫後**的長度。 */
|
||||
function chunkByBytes(s: string, maxBytes: number): string[] {
|
||||
const out: string[] = [];
|
||||
let cur = '';
|
||||
for (const ch of s) {
|
||||
if (utf8Len(cur + ch) > maxBytes) {
|
||||
if (likeBytes(cur + ch) > maxBytes) {
|
||||
if (cur) out.push(cur);
|
||||
cur = ch;
|
||||
} else {
|
||||
@@ -237,8 +288,8 @@ function chunkByBytes(s: string, maxBytes: number): string[] {
|
||||
* 回 `split=false` 代表走的是與舊版逐字相同的單一 LIKE。
|
||||
*/
|
||||
export function buildContentLike(q: string): { conds: string[]; params: string[]; split: boolean } {
|
||||
if (utf8Len(q) <= MAX_LIKE_Q_BYTES) {
|
||||
return { conds: ['content LIKE ?'], params: [`%${q}%`], split: false };
|
||||
if (likeBytes(q) <= MAX_LIKE_Q_BYTES) {
|
||||
return { conds: [CONTENT_LIKE], params: [likePattern(q)], split: false };
|
||||
}
|
||||
const terms: string[] = [];
|
||||
for (const word of q.split(/\s+/).filter(Boolean)) {
|
||||
@@ -251,8 +302,8 @@ export function buildContentLike(q: string): { conds: string[]; params: string[]
|
||||
// 理論上不會空（q 非空才進得來），但空陣列會產出 `WHERE` 沒有條件 ⇒ 保底退回單一截斷 LIKE
|
||||
if (terms.length === 0) terms.push(chunkByBytes(q, MAX_LIKE_Q_BYTES)[0] ?? '');
|
||||
return {
|
||||
conds: terms.map(() => 'content LIKE ?'),
|
||||
params: terms.map((t) => `%${t}%`),
|
||||
conds: terms.map(() => CONTENT_LIKE),
|
||||
params: terms.map(likePattern),
|
||||
split: true,
|
||||
};
|
||||
}
|
||||
@@ -428,7 +479,7 @@ export function buildSearchScore(q: string): SearchScorePlan {
|
||||
if (terms.length === 0) {
|
||||
const m = buildContentLike(trimmed);
|
||||
return {
|
||||
scoreExpr: m.conds.map(() => 'CASE WHEN content LIKE ? THEN 1 ELSE 0 END').join(' + '),
|
||||
scoreExpr: m.conds.map(() => `CASE WHEN ${CONTENT_LIKE} THEN 1 ELSE 0 END`).join(' + '),
|
||||
scoreParams: m.params,
|
||||
terms: [],
|
||||
legacyShape: true,
|
||||
@@ -438,16 +489,16 @@ export function buildSearchScore(q: string): SearchScorePlan {
|
||||
const parts: string[] = [];
|
||||
const params: string[] = [];
|
||||
for (const { term, weight } of terms) {
|
||||
parts.push(`CASE WHEN content LIKE ? THEN ${weight} ELSE 0 END`);
|
||||
params.push(`%${term}%`);
|
||||
parts.push(`CASE WHEN ${CONTENT_LIKE} THEN ${weight} ELSE 0 END`);
|
||||
params.push(likePattern(term));
|
||||
}
|
||||
|
||||
// 單詞查詢：整句 == 那個詞 ⇒ 不重複加一次 LIKE。送出的 SQL 與舊版一模一樣（成本也一樣）。
|
||||
const single = terms.length === 1 && terms[0].term === trimmed;
|
||||
if (!single && utf8Len(trimmed) <= MAX_LIKE_Q_BYTES) {
|
||||
if (!single && likeBytes(trimmed) <= MAX_LIKE_Q_BYTES) {
|
||||
const bonus = terms.reduce((s, t) => s + t.weight, 0);
|
||||
parts.push(`CASE WHEN content LIKE ? THEN ${bonus} ELSE 0 END`);
|
||||
params.push(`%${trimmed}%`);
|
||||
parts.push(`CASE WHEN ${CONTENT_LIKE} THEN ${bonus} ELSE 0 END`);
|
||||
params.push(likePattern(trimmed));
|
||||
}
|
||||
|
||||
return { scoreExpr: parts.join(' + '), scoreParams: params, terms, legacyShape: single };
|
||||
@@ -512,7 +563,9 @@ export function isDeprecatedEntry(entry: { metadata_json?: string | null }): boo
|
||||
// includeDeprecated（daemon-beta t24）：預設 false＝濾掉 status=deprecated 的下架內容。
|
||||
// 保留 true 選項給管理面查殘留（審計/驗證下架有沒有真的生效）用，正常搜尋路徑不帶。
|
||||
// 加在參數最尾端，既有 positional caller（source 之後）一個都不用改。
|
||||
// 2026-08-10（本次）：q 改走 buildSearchScore——**斷詞 + 覆蓋率排序**，取代整串 LIKE。
|
||||
// 2026-08-12（Arcrun#94）：q 裡的 `%` `_` `\` 一律當字面字元（escapeLikeLiteral ＋ ESCAPE 宣告）
|
||||
// ——使用者打什麼字就照那些字找。舊病，見上面 LIKE_ESCAPE 那段。
|
||||
// 2026-08-10：q 改走 buildSearchScore——**斷詞 + 覆蓋率排序**，取代整串 LIKE。
|
||||
// 回傳的 entry 多一個 match_score 欄（加欄不改形，同 semantic 路徑的 score 慣例；
|
||||
// 既有 caller 不解析多的欄位，不受影響）。詳細理由見上面那段長註解。
|
||||
export async function searchEntries(
|
||||
|
||||
@@ -0,0 +1,168 @@
|
||||
// 標庫 backfill（Arcrun#85 二次裁決，2026-08-11；相關票 Arcrun#87「藏書地圖是空的」）。
|
||||
//
|
||||
// 背景：leo 把向量化優先序講成一句話後又補一刀：「它是兩件事？其實是一件——沒有庫就
|
||||
// 剩一個，但你把庫標好以後，原來的判定要修改對吧」。⇒ 判定標準（embed.ts 的
|
||||
// SelectionCriteria）必須從第一天就同時容納時間與庫，本檔提供「庫」這一半真正的資料。
|
||||
//
|
||||
// base 的 write path 早就支援（`createEntry` 的 `metadata_json.$.library`，t52：「庫由
|
||||
// ingest 蓋章決定」）——既有的搜尋／embed／deprecate-by-library 全都讀這個欄位，
|
||||
// **缺的不是機制，是既有資料沒被蓋章**（library-map.ts 檔頭 2026-07-19 對 prod 核實：
|
||||
// 既有 entries 的 metadata.library 是空的）。「源頭寫入就貼標」是呼叫端（ingest）的事，
|
||||
// base 這裡管不到、也不該猜（base 對內容語意無知的既有原則）；triplet 的實際寫入更是
|
||||
// 在另一個 repo（見 kbdb/src/index.ts 檔頭「triplet (separate repo)」）。
|
||||
//
|
||||
// 這個模組只做「補存量」那一半，且刻意設計成呼叫端驅動：
|
||||
// - base 不猜「這筆該屬於哪個庫」——那是語意判斷。呼叫端給一個 target library 值
|
||||
// ＋一組篩選條件，base 只負責把符合條件、目前未標記的 entries 安全、節流地蓋上這個值。
|
||||
// - 篩選條件有兩種精度（2026-08-11 leo 定案的做法後補上）：
|
||||
// ① 精準比對 `page_names`（IN 清單）——leo 定的正解：「有 2 份原稿，在 gitea 和我的
|
||||
// Mac……去 gitea 把每個庫有哪些的卡名列出，跑來遍歷應該就搞定了」。呼叫端（daemon／
|
||||
// #87）從 Gitea repo 列出卡名，逐批把「這些卡名屬於庫 X」精準地寫進來，不必猜。
|
||||
// ② `source_prefix`／`page_name_prefix` 前綴 fallback（同 library-map.ts
|
||||
// recomputeLibraryMap 的 source_prefix 精神，只是這裡是寫入不是聚合）——沒有精準
|
||||
// 清單時的過渡手段，精度不如①，兩者可並用（AND）縮小範圍。
|
||||
// - 冪等：已標記的 entries 不會再入選（WHERE 帶「library 為空」）。
|
||||
//
|
||||
// D69 節流：與 reconcileEmbedGeneration（embed.ts）共用 maintenance-quota.ts 的同一顆
|
||||
// 每日 D1 寫入計數器——兩者都是「多筆 D1 row write、不打 AI」的背景維護操作，不共用
|
||||
// 計數器的話，補存量時會把世代核對的閘繞過去（leo 2026-08-11 二次裁決原話：「每日上限
|
||||
// 這件事不只管向量化，也要管補標，否則做標庫時就會把補算的閘繞過去」）。
|
||||
import type { Bindings } from '../types';
|
||||
import { maintenanceBudgetToday, addMaintenanceUsage } from './maintenance-quota';
|
||||
|
||||
// IN 清單長度上限（避開 D1/SQLite bound-parameter 上限；一次點名這麼多張卡已經很夠用，
|
||||
// 呼叫端清單更長就自然分批呼叫，跟 limit 分頁是同一種節奏）。
|
||||
const MAX_PAGE_NAMES = 300;
|
||||
|
||||
export interface LibraryBackfillCriteria {
|
||||
owner_id?: string;
|
||||
entry_type?: string;
|
||||
page_names?: string[]; // 精準比對 page_name（IN 清單）——leo 定案的正解：從 Gitea repo
|
||||
// 列出卡名，逐批精準點名「這些卡名屬於庫 X」（見檔頭說明①）。
|
||||
source_prefix?: string; // metadata_json.$.source LIKE prefix%（過渡 fallback，見檔頭②）
|
||||
page_name_prefix?: string; // page_name LIKE prefix%（過渡 fallback，見檔頭②）
|
||||
since?: number; // created_at >= since（unix seconds）
|
||||
until?: number; // created_at < until（unix seconds）
|
||||
}
|
||||
|
||||
export interface LibraryBackfillResult {
|
||||
library: string;
|
||||
scanned: number; // 本批掃到的候選筆數（受 limit 限制，額度截斷前）。
|
||||
tagged: number; // 本次真的寫入 metadata_json.$.library 的筆數。
|
||||
remaining: number; // 本次之後仍待補標（符合條件、仍未標記）的筆數，不受額度影響。
|
||||
quota_limit: number; // 今日「背景維護 D1 寫入」額度上限（與 reconcile 共用）。
|
||||
quota_used_today: number; // 本次呼叫後，今日累積已消耗的背景維護寫入額度。
|
||||
quota_exceeded: boolean; // 本批是否因額度不足被截斷。
|
||||
}
|
||||
|
||||
// 單次呼叫候選上限（避開 subrequest/CPU/timeout；一批只有 1 次 SELECT + 1 次 UPDATE，
|
||||
// 比 reconcile 多一次 Vectorize 呼叫的成本低，故上限可以放寬一些）。
|
||||
const HARD_LIMIT_CAP = 500;
|
||||
|
||||
function criteriaPredicate(c: LibraryBackfillCriteria): { conds: string[]; params: unknown[] } {
|
||||
// 冪等的核心：只選「目前沒有 library 值」的候選，已標記過的（含標成 'general' 的）不會再入選。
|
||||
const conds: string[] = [
|
||||
"(json_extract(metadata_json, '$.library') IS NULL OR json_extract(metadata_json, '$.library') = '')",
|
||||
];
|
||||
const params: unknown[] = [];
|
||||
if (c.owner_id) { conds.push('owner_id = ?'); params.push(c.owner_id); }
|
||||
if (c.entry_type) { conds.push('entry_type = ?'); params.push(c.entry_type); }
|
||||
if (c.page_names && c.page_names.length > 0) {
|
||||
const names = c.page_names.slice(0, MAX_PAGE_NAMES);
|
||||
conds.push(`page_name IN (${names.map(() => '?').join(',')})`);
|
||||
params.push(...names);
|
||||
}
|
||||
if (c.source_prefix) { conds.push("json_extract(metadata_json, '$.source') LIKE ? || '%'"); params.push(c.source_prefix); }
|
||||
if (c.page_name_prefix) { conds.push("page_name LIKE ? || '%'"); params.push(c.page_name_prefix); }
|
||||
if (typeof c.since === 'number') { conds.push('created_at >= ?'); params.push(c.since); }
|
||||
if (typeof c.until === 'number') { conds.push('created_at < ?'); params.push(c.until); }
|
||||
return { conds, params };
|
||||
}
|
||||
|
||||
/**
|
||||
* 對「符合條件、目前未標記 library」的既有 entries 批次蓋上 target library 值。
|
||||
* 冪等 + 分批（單次 limit 上限）+ budget（與 reconcile 共用每日 D1 寫入額度，見檔頭）。
|
||||
* 呼叫端（ingest / Arcrun#87）決定「這批是誰、該貼哪個庫」，本函式只負責安全、節流地
|
||||
* 把值寫進去——base 不猜語意，也因此不假裝「這樣就把 #87 做完了」（mindset §7）。
|
||||
*
|
||||
* `owner_id` 刻意設成**必填**（不同於 LibraryBackfillCriteria 其餘欄位皆選填）：
|
||||
* 2026-08-11 leo 在票上點出「補標補在錯的 owner 底下等於白做」（實查發現卡片實際掛在
|
||||
* `owner_id=bfezv28v`，換成 `owner_id='leo'` 查卻是空的——兩個候選 owner 已經在互相打架）。
|
||||
* 跟既有的 `deprecateEntriesByLibrary`（同樣是「依 library 批次改一大片既有資料」的操作）
|
||||
* 同一個防線：不給不知道自己在改誰的資料的呼叫端一個「忘記帶 owner_id 就變成跨租戶全庫掃」
|
||||
* 的後門，逼呼叫端明確想清楚「這批是哪個 owner」再動手。
|
||||
*/
|
||||
export async function backfillEntryLibraryTags(
|
||||
db: D1Database,
|
||||
env: Pick<Bindings, 'KBDB_MAINTENANCE_DAILY_WRITE_LIMIT'>,
|
||||
opts: { library: string; owner_id: string; limit?: number } & Omit<LibraryBackfillCriteria, 'owner_id'>,
|
||||
): Promise<LibraryBackfillResult> {
|
||||
const library = (opts.library ?? '').trim();
|
||||
if (!library) throw new Error('library required');
|
||||
const ownerId = (opts.owner_id ?? '').trim();
|
||||
if (!ownerId) throw new Error('owner_id required（標庫是跨大量既有資料的批次寫入，不准無租戶範圍地掃全庫——2026-08-11 leo 直令）');
|
||||
const limit = Math.min(Math.max(opts.limit ?? 100, 1), HARD_LIMIT_CAP);
|
||||
|
||||
const sel = criteriaPredicate({ ...opts, owner_id: ownerId });
|
||||
const where = sel.conds.join(' AND ');
|
||||
const params = sel.params;
|
||||
|
||||
const res = await db
|
||||
.prepare(`SELECT id FROM entries WHERE ${where} ORDER BY created_at ASC LIMIT ?`)
|
||||
.bind(...params, limit)
|
||||
.all<{ id: string }>();
|
||||
const scannedIds = (res.results ?? []).map((r) => r.id);
|
||||
const scanned = scannedIds.length;
|
||||
|
||||
// D69：額度截斷——每個候選最多 1 次 D1 write，與 reconcile 共用同一顆計數器。
|
||||
const budget = await maintenanceBudgetToday(env, db);
|
||||
const ids = scannedIds.slice(0, budget.remaining);
|
||||
const quotaExceeded = scanned > ids.length;
|
||||
|
||||
let tagged = 0;
|
||||
if (ids.length > 0) {
|
||||
const ph = ids.map(() => '?').join(',');
|
||||
await db
|
||||
.prepare(
|
||||
`UPDATE entries SET metadata_json = json_set(COALESCE(metadata_json, '{}'), '$.library', ?), updated_at = unixepoch() WHERE id IN (${ph})`,
|
||||
)
|
||||
.bind(library, ...ids)
|
||||
.run();
|
||||
tagged = ids.length;
|
||||
}
|
||||
|
||||
try {
|
||||
await addMaintenanceUsage(db, tagged);
|
||||
} catch {
|
||||
// fail-open：額度計數寫入失敗不影響已經完成的標庫寫入（精神同 embed.ts 的做法）。
|
||||
}
|
||||
|
||||
const remRow = await db
|
||||
.prepare(`SELECT COUNT(*) as c FROM entries WHERE ${where}`)
|
||||
.bind(...params)
|
||||
.first<{ c: number }>();
|
||||
|
||||
return {
|
||||
library,
|
||||
scanned,
|
||||
tagged,
|
||||
remaining: remRow?.c ?? 0,
|
||||
quota_limit: budget.limit,
|
||||
quota_used_today: budget.used + tagged,
|
||||
quota_exceeded: quotaExceeded,
|
||||
};
|
||||
}
|
||||
|
||||
/** 待補標統計（回報用）：符合條件、目前未標記 library 的筆數。 */
|
||||
export async function libraryBackfillStatus(
|
||||
db: D1Database,
|
||||
opts: LibraryBackfillCriteria = {},
|
||||
): Promise<{ pending: number }> {
|
||||
const sel = criteriaPredicate(opts);
|
||||
const where = sel.conds.join(' AND ');
|
||||
const row = await db
|
||||
.prepare(`SELECT COUNT(*) as c FROM entries WHERE ${where}`)
|
||||
.bind(...sel.params)
|
||||
.first<{ c: number }>();
|
||||
return { pending: row?.c ?? 0 };
|
||||
}
|
||||
@@ -330,6 +330,15 @@ type LibraryNameSet = Set<string>;
|
||||
|
||||
// 這個 owner 底下、依 triplet 自身 'library' slot 分組的即時三元組數（缺 library slot 值的舊
|
||||
// triplet 歸 'general'）——與 GET /records/triplet-stats（t142）同一套分組語意，兩處數字對得上。
|
||||
//
|
||||
// 2026-08-11 修根因（Arcrun#87，動工前量測 comment 第四節）：這裡原本完全不過濾 status，
|
||||
// 而 recomputeLibraryMap（上方 withLib）只算 COALESCE(status,'active')='active'。兩邊判準不
|
||||
// 一致，只要有一筆 superseded triplet，這裡的即時計數就會跟重算後的快取對不上，
|
||||
// ensureFreshLibraryMaps 判定 stale，每次讀地圖都觸發重算，每次都新建一筆 library_map
|
||||
// record（superseded 舊的），無止盡寫 D1，且加劇 recomputeLibraryMap 本身非原子 supersede
|
||||
// 的競態（另一個已知病，wiki 08-10 條目）。實測：間隔數秒連讀兩次地圖、中間無任何寫入動作，
|
||||
// updated_at 仍前進。修法：這裡的 status 判準改成與 recomputeLibraryMap 逐字一致，兩邊算出
|
||||
// 的計數才會在資料未變動時相等，stale 判定回歸「真的有資料變動才 stale」。
|
||||
async function liveTripletCountsByLibrary(
|
||||
db: D1Database,
|
||||
tripletTemplateId: string,
|
||||
@@ -337,15 +346,18 @@ async function liveTripletCountsByLibrary(
|
||||
): Promise<LibraryCountMap> {
|
||||
const params: unknown[] = owner_id ? [tripletTemplateId, owner_id] : [tripletTemplateId];
|
||||
const res = await db
|
||||
.prepare(
|
||||
.prepare( // kbdb-sql-ok：牆內本體（kbdb/src/actions/），checkout 開在巢狀 worktree matrix/arcrun/.worktree-fix-87/（避免打斷另一 session 佔用中的 matrix/arcrun 主 checkout），hook 逐字比對 matrix/arcrun/kbdb/src/ 吃不到中間多出的 worktree 目錄層，非繞牆
|
||||
`SELECT COALESCE(NULLIF(lib_e.content, ''), 'general') AS library, COUNT(*) AS n
|
||||
FROM (
|
||||
SELECT DISTINCT ev.record_id
|
||||
SELECT ev.record_id AS rid,
|
||||
MAX(CASE WHEN ev.slot_name = 'status' THEN e.content END) AS status
|
||||
FROM entry_values ev JOIN entries e ON ev.entry_id = e.id
|
||||
WHERE ev.template_id = ?${owner_id ? ' AND e.owner_id = ?' : ''}
|
||||
GROUP BY ev.record_id
|
||||
) AS tr
|
||||
LEFT JOIN entry_values lev ON lev.record_id = tr.record_id AND lev.slot_name = 'library'
|
||||
LEFT JOIN entry_values lev ON lev.record_id = tr.rid AND lev.slot_name = 'library'
|
||||
LEFT JOIN entries lib_e ON lib_e.id = lev.entry_id
|
||||
WHERE COALESCE(tr.status, 'active') = 'active'
|
||||
GROUP BY COALESCE(NULLIF(lib_e.content, ''), 'general')`,
|
||||
)
|
||||
.bind(...params)
|
||||
|
||||
@@ -0,0 +1,106 @@
|
||||
// 背景維護寫入的共用 D1 每日額度（Arcrun#85 D69，2026-08-11）。
|
||||
//
|
||||
// 為什麼需要這個模組（不是每個 caller 各自算）：
|
||||
// D68 已經替「補算向量」的 Workers AI 呼叫量設了每日軟上限（embed.ts
|
||||
// DEFAULT_BACKFILL_DAILY_LIMIT），但 leo 逐行複核後指出還有一個沒堵的洞——
|
||||
// 世代核對（reconcileEmbedGeneration）**不打 AI，卻一樣逐筆寫 D1**（補標 content_hash
|
||||
// 或重置 is_embedded），47 萬筆候選 ≈ 4.7 倍 D1 免費層 100,000 rows written/日，而它
|
||||
// 當時零保護。2026-08-11 leo 補了第二刀：**標庫（library backfill）也是同一種操作**
|
||||
// ——多筆 D1 row write、不打 AI——若各自設一顆獨立計數器，做標庫時會把 reconcile
|
||||
// 的閘繞過去（兩者加起來還是可能燒穿同一顆 D1）。
|
||||
// ⇒ 兩者必須共用同一顆「今天 D1 背景維護寫入還剩多少」計數器，這裡就是那顆計數器。
|
||||
//
|
||||
// 儲存精神完全比照 execution-log.ts checkUsage／embed.ts getBackfillUsageToday：單一
|
||||
// entries 列/日（entry_type='kbdb_maintenance_usage'），upsert，不新增表（D38）。
|
||||
//
|
||||
// 額度怎麼選（不是拍腦袋，比照 execution-log.ts DEFAULT_DAILY_LIMIT 的既有算法）：
|
||||
// D1 免費層 100,000 rows written/日。execution_log 自設 20%（20,000）留給知識卡；
|
||||
// 本模組管的是「背景維護」（reconcile + 標庫 backfill，兩者都是低優先、非使用者
|
||||
// 當下等待的操作），同樣自設 20%（20,000/日）——不是硬性 Cloudflare 限制，是不讓
|
||||
// 背景維護把當天寫入額度和知識卡片的正常寫入／execution_log 搶光的自我節制，
|
||||
// 可用 env.KBDB_MAINTENANCE_DAILY_WRITE_LIMIT 覆寫。
|
||||
import type { Bindings } from '../types';
|
||||
|
||||
export const DEFAULT_MAINTENANCE_DAILY_WRITE_LIMIT = 20000;
|
||||
|
||||
export function maintenanceDailyLimit(env: Pick<Bindings, 'KBDB_MAINTENANCE_DAILY_WRITE_LIMIT'>): number {
|
||||
const raw = env.KBDB_MAINTENANCE_DAILY_WRITE_LIMIT;
|
||||
const n = raw ? parseInt(raw, 10) : NaN;
|
||||
return Number.isFinite(n) && n > 0 ? n : DEFAULT_MAINTENANCE_DAILY_WRITE_LIMIT;
|
||||
}
|
||||
|
||||
function utcDay(): string {
|
||||
return new Date().toISOString().slice(0, 10);
|
||||
}
|
||||
|
||||
/** 額度計數器 entries id（單一列/日；不分租戶——D1 rows-written 額度是實例級，非租戶級）。 */
|
||||
function maintenanceUsageId(): string {
|
||||
return `kbdb-maintenance-usage:${utcDay()}`;
|
||||
}
|
||||
|
||||
/**
|
||||
* 今天背景維護寫入已消耗的筆數。讀取失敗（含壞資料）誠實視為 0（caller 決定是否 fail-open，
|
||||
* 精神同 embed.ts getBackfillUsageToday）。
|
||||
*/
|
||||
export async function getMaintenanceUsageToday(db: D1Database): Promise<number> {
|
||||
const row = await db
|
||||
.prepare('SELECT metadata_json FROM entries WHERE id = ?')
|
||||
.bind(maintenanceUsageId())
|
||||
.first<{ metadata_json: string | null }>();
|
||||
if (!row) return 0;
|
||||
try {
|
||||
const parsed = row.metadata_json ? (JSON.parse(row.metadata_json) as { writes?: number }) : {};
|
||||
return Number(parsed.writes) || 0;
|
||||
} catch {
|
||||
return 0;
|
||||
}
|
||||
}
|
||||
|
||||
/** 今天背景維護額度用量 +by（upsert：讀現有列 → +by → UPDATE，不存在則 INSERT，冪等日切）。 */
|
||||
export async function addMaintenanceUsage(db: D1Database, by: number): Promise<void> {
|
||||
if (by <= 0) return;
|
||||
const id = maintenanceUsageId();
|
||||
const existing = await db
|
||||
.prepare('SELECT metadata_json FROM entries WHERE id = ?')
|
||||
.bind(id)
|
||||
.first<{ metadata_json: string | null }>();
|
||||
let prev = 0;
|
||||
if (existing) {
|
||||
try {
|
||||
const parsed = existing.metadata_json ? (JSON.parse(existing.metadata_json) as { writes?: number }) : {};
|
||||
prev = Number(parsed.writes) || 0;
|
||||
} catch {
|
||||
prev = 0;
|
||||
}
|
||||
await db
|
||||
.prepare('UPDATE entries SET metadata_json = ?, updated_at = unixepoch() WHERE id = ?')
|
||||
.bind(JSON.stringify({ day: utcDay(), writes: prev + by }), id)
|
||||
.run();
|
||||
} else {
|
||||
await db
|
||||
.prepare(`INSERT INTO entries (id, entry_type, metadata_json) VALUES (?, 'kbdb_maintenance_usage', ?)`)
|
||||
.bind(id, JSON.stringify({ day: utcDay(), writes: by }))
|
||||
.run();
|
||||
}
|
||||
}
|
||||
|
||||
export interface MaintenanceBudget {
|
||||
limit: number;
|
||||
used: number;
|
||||
remaining: number;
|
||||
}
|
||||
|
||||
/** 今天還剩多少背景維護 D1 寫入額度（reconcile／標庫 backfill 呼叫前先問這個）。 */
|
||||
export async function maintenanceBudgetToday(
|
||||
env: Pick<Bindings, 'KBDB_MAINTENANCE_DAILY_WRITE_LIMIT'>,
|
||||
db: D1Database,
|
||||
): Promise<MaintenanceBudget> {
|
||||
const limit = maintenanceDailyLimit(env);
|
||||
let used = 0;
|
||||
try {
|
||||
used = await getMaintenanceUsageToday(db);
|
||||
} catch {
|
||||
used = 0; // fail-open：計數器本身故障（含 D1 額度打滿）不該連背景維護都做不了
|
||||
}
|
||||
return { limit, used, remaining: Math.max(0, limit - used) };
|
||||
}
|
||||
+305
-13
@@ -12,6 +12,7 @@
|
||||
// base 只認這個通用旗標 → base 維持對內容語意無知。
|
||||
|
||||
import type { Bindings, Entry } from './types';
|
||||
import { maintenanceBudgetToday, addMaintenanceUsage } from './actions/maintenance-quota';
|
||||
|
||||
// ── 嵌入模型（Arcrun#59：模型應可配置＋index 版本化，支援換代重刷）────────────────
|
||||
//
|
||||
@@ -132,7 +133,12 @@ export async function embedOnWrite(env: Bindings, entry: Entry): Promise<boolean
|
||||
},
|
||||
]);
|
||||
// 標記 bookkeeping（既有欄，base 不讀、僅供「已 embed」可查）。不動表結構。
|
||||
await env.DB.prepare('UPDATE entries SET is_embedded = 1 WHERE id = ?').bind(entry.id).run();
|
||||
// content_hash 順手蓋成「這次嵌入用的模型」（世代戳記，見下方 reconcileEmbedGeneration 的
|
||||
// 說明）——這裡是「新寫的立刻算」的路徑，寫入當下 model 必為現行 model，不會有世代落差。
|
||||
await env.DB
|
||||
.prepare('UPDATE entries SET is_embedded = 1, content_hash = ? WHERE id = ?')
|
||||
.bind(embedModel(env), entry.id)
|
||||
.run();
|
||||
return true;
|
||||
}
|
||||
|
||||
@@ -173,12 +179,134 @@ function parseMeta(json: string | null): Record<string, unknown> | null {
|
||||
const BACKFILL_PREDICATE =
|
||||
"is_embedded = 0 AND content IS NOT NULL AND content <> '' AND json_extract(metadata_json, '$.embed') = 1";
|
||||
|
||||
// ── 每日額度上限（D68，2026-08-11：leo「補算向量照時間新到舊、且每天有額度上限」）─────────
|
||||
//
|
||||
// backfill 與「寫入即嵌」「萃取」共用同一份 Workers AI 每日免費 10,000 neurons（UTC 午夜重置，
|
||||
// 見頂層 wiki ops-facts.md「萃取與向量化吃同一份 Workers AI 額度」）。backfill 是背景低優先
|
||||
// 動作，不該把當天額度燒光讓萃取／今天的新寫入整天卡死（embedOnWrite 不受此上限——「新寫的
|
||||
// 立刻算」是 D68 三條之一，不能被 backfill 的節制連坐）。自設「軟上限」，非 Cloudflare 硬限制，
|
||||
// 可用 env.EMBED_BACKFILL_DAILY_LIMIT 覆寫（精神比照 execution-log.ts 的 DEFAULT_DAILY_LIMIT）。
|
||||
//
|
||||
// 預設值怎麼選（不是拍腦袋，2026-08-11 查證 Cloudflare 官方定價後回推）：
|
||||
// bge-m3 定價：1,075 neurons / 1,000,000 input tokens（無輸出 token 成本，embedding 只有輸入）。
|
||||
// 保守估計每筆中文知識卡片 ~800 tokens（寧可高估——CJK tokenizer 密度通常高於英文，
|
||||
// 高估 token 數 ⇒ 算出的「每日可嵌筆數」偏保守，不會撞真的 CF 額度）：
|
||||
// 800 tokens × 1,075 / 1,000,000 ≈ 0.86 neurons/entry
|
||||
// backfill 分到日配額 20%（比照 execution-log.ts「自我節制、留大部分給主流程」的既有慣例）：
|
||||
// 10,000 × 20% = 2,000 neurons/日
|
||||
// 2,000 ÷ 0.86 ≈ 2,325 entries/日，再打八折留緩衝（token 估計誤差／其他背景消耗）：
|
||||
// 2,325 × 0.8 ≈ 1,860 → 取整數 1,800。
|
||||
const DEFAULT_BACKFILL_DAILY_LIMIT = 1800;
|
||||
|
||||
function backfillDailyLimit(env: Pick<Bindings, 'EMBED_BACKFILL_DAILY_LIMIT'>): number {
|
||||
const raw = env.EMBED_BACKFILL_DAILY_LIMIT;
|
||||
const n = raw ? parseInt(raw, 10) : NaN;
|
||||
return Number.isFinite(n) && n > 0 ? n : DEFAULT_BACKFILL_DAILY_LIMIT;
|
||||
}
|
||||
|
||||
function utcDay(): string {
|
||||
return new Date().toISOString().slice(0, 10);
|
||||
}
|
||||
|
||||
/** 額度計數器 entries id（單一列/日，UTC 日期字串，換日自然歸零；不分租戶——Workers AI 額度是帳號級）。 */
|
||||
function backfillUsageId(): string {
|
||||
return `embed-backfill-usage:${utcDay()}`;
|
||||
}
|
||||
|
||||
/**
|
||||
* 今天 backfill 已消耗的筆數。儲存精神完全比照 execution-log.ts 的 checkUsage：單一 entries 列/日
|
||||
* （entry_type='embed_backfill_usage'，計數包進 metadata_json），不新增表。
|
||||
* 讀取失敗（含壞資料）誠實視為 0（caller 決定是否 fail-open）。
|
||||
*/
|
||||
async function getBackfillUsageToday(db: D1Database): Promise<number> {
|
||||
const row = await db
|
||||
.prepare('SELECT metadata_json FROM entries WHERE id = ?')
|
||||
.bind(backfillUsageId())
|
||||
.first<{ metadata_json: string | null }>();
|
||||
if (!row) return 0;
|
||||
try {
|
||||
const parsed = row.metadata_json ? (JSON.parse(row.metadata_json) as { embedded?: number }) : {};
|
||||
return Number(parsed.embedded) || 0;
|
||||
} catch {
|
||||
return 0; // 壞資料誠實視為 0，不讓損毀的計數器卡死額度機制
|
||||
}
|
||||
}
|
||||
|
||||
/** 今天 backfill 額度用量 +by（upsert：讀現有列 → +by → UPDATE，不存在則 INSERT，冪等日切）。 */
|
||||
async function addBackfillUsage(db: D1Database, by: number): Promise<void> {
|
||||
if (by <= 0) return;
|
||||
const id = backfillUsageId();
|
||||
const existing = await db
|
||||
.prepare('SELECT metadata_json FROM entries WHERE id = ?')
|
||||
.bind(id)
|
||||
.first<{ metadata_json: string | null }>();
|
||||
let prev = 0;
|
||||
if (existing) {
|
||||
try {
|
||||
const parsed = existing.metadata_json ? (JSON.parse(existing.metadata_json) as { embedded?: number }) : {};
|
||||
prev = Number(parsed.embedded) || 0;
|
||||
} catch {
|
||||
prev = 0;
|
||||
}
|
||||
await db
|
||||
.prepare('UPDATE entries SET metadata_json = ?, updated_at = unixepoch() WHERE id = ?')
|
||||
.bind(JSON.stringify({ day: utcDay(), embedded: prev + by }), id)
|
||||
.run();
|
||||
} else {
|
||||
await db
|
||||
.prepare(`INSERT INTO entries (id, entry_type, metadata_json) VALUES (?, 'embed_backfill_usage', ?)`)
|
||||
.bind(id, JSON.stringify({ day: utcDay(), embedded: by }))
|
||||
.run();
|
||||
}
|
||||
}
|
||||
|
||||
// ── 「挑哪一批」可以從外面指定（Arcrun#85，2026-08-11 leo 二度裁決）───────────────
|
||||
//
|
||||
// leo 的優先序不是「一律新到舊」的單一佇列，是**分層**：今天寫的立刻／這週在跑的先跑／
|
||||
// 有查詢紀錄的庫優先／半年前的慢慢跑。分層要能實作，前提是「這次補哪一批」要能從外面
|
||||
// （工作流）指定，不能只靠資料層自己決定的固定排序——策略要住在 leo 打得開的地方
|
||||
// （工作流頁），不是焊死在這裡看不見也改不動。
|
||||
//
|
||||
// 這裡不預先幫 caller 決定「四層怎麼切」（那是策略，屬於呼叫端/工作流，見 Arcrun#85
|
||||
// D70 段落的意圖草案），只提供**同一套篩選形狀**讓任何一層都能表達：
|
||||
// - since／until：時間窗（unix seconds，created_at 半開區間 [since, until)）——時間分層
|
||||
// （①今天／②本週／④半年前）都是同一個 since/until 參數，差別只在呼叫端傳的值。
|
||||
// - library：依 metadata_json.$.library 過濾——一旦資料身上有庫這個資訊（Arcrun#87），
|
||||
// 「有查詢紀錄的庫優先」這層可以直接用同一個參數，不必再改介面形狀。
|
||||
// 三個操作（backfillEmbeddings／reconcileEmbedGeneration／backfillEntryLibraryTags，
|
||||
// 見 actions/library-backfill.ts）共用這個形狀，這就是「判定標準只有一份」的意思——
|
||||
// 不是先做時間、之後為了庫再回頭改介面。
|
||||
export interface SelectionCriteria {
|
||||
owner_id?: string;
|
||||
source?: string;
|
||||
library?: string; // 精確比對 metadata_json.$.library（未標記的舊資料一律歸 'general'，同 embedOnWrite 慣例）
|
||||
since?: number; // created_at >= since（unix seconds）
|
||||
until?: number; // created_at < until（unix seconds）
|
||||
}
|
||||
|
||||
function selectionCriteriaPredicate(opts: SelectionCriteria): { conds: string[]; params: unknown[] } {
|
||||
const conds: string[] = [];
|
||||
const params: unknown[] = [];
|
||||
if (opts.owner_id) { conds.push('owner_id = ?'); params.push(opts.owner_id); }
|
||||
if (opts.source) { conds.push("json_extract(metadata_json, '$.source') = ?"); params.push(opts.source); }
|
||||
if (opts.library) {
|
||||
conds.push("COALESCE(NULLIF(json_extract(metadata_json, '$.library'), ''), 'general') = ?");
|
||||
params.push(opts.library);
|
||||
}
|
||||
if (typeof opts.since === 'number') { conds.push('created_at >= ?'); params.push(opts.since); }
|
||||
if (typeof opts.until === 'number') { conds.push('created_at < ?'); params.push(opts.until); }
|
||||
return { conds, params };
|
||||
}
|
||||
|
||||
export interface BackfillResult {
|
||||
enabled: boolean; // 模組是否開（false → 什麼都沒做，caller 該誠實回錯，不假裝）。
|
||||
processed: number; // 本次真的嵌進 Vectorize 並標 is_embedded=1 的筆數。
|
||||
skipped: number; // 掃到但沒嵌（例如 embedText 回 null）的筆數。
|
||||
remaining: number; // 本次之後仍待補嵌的筆數（可重複呼叫直到 0）。
|
||||
skipped: number; // 掃到但沒嵌（例如 embedText 回 null，或本批被額度擋下）的筆數。
|
||||
remaining: number; // 本次之後仍待補嵌的筆數（可重複呼叫直到 0，與額度無關——單純候選總量）。
|
||||
scanned: number; // 本批掃出的候選筆數（受 limit 限制）。
|
||||
quota_limit: number; // 今日 backfill 額度上限（env.EMBED_BACKFILL_DAILY_LIMIT 或預設值）。
|
||||
quota_used_today: number; // 本次呼叫後，今日累積已消耗的 backfill 額度。
|
||||
quota_exceeded: boolean; // 本批是否因額度不足被截斷（true＝還有可嵌的候選但今天不再打 AI，等明天/調高上限）。
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -193,9 +321,14 @@ export interface BackfillResult {
|
||||
*/
|
||||
export async function backfillEmbeddings(
|
||||
env: Bindings,
|
||||
opts: { limit?: number; owner_id?: string; source?: string; reindex?: boolean; offset?: number } = {},
|
||||
opts: SelectionCriteria & { limit?: number; reindex?: boolean; offset?: number } = {},
|
||||
): Promise<BackfillResult> {
|
||||
if (!embedEnabled(env)) return { enabled: false, processed: 0, skipped: 0, remaining: 0, scanned: 0 };
|
||||
if (!embedEnabled(env)) {
|
||||
return {
|
||||
enabled: false, processed: 0, skipped: 0, remaining: 0, scanned: 0,
|
||||
quota_limit: 0, quota_used_today: 0, quota_exceeded: false,
|
||||
};
|
||||
}
|
||||
const limit = Math.min(Math.max(opts.limit ?? 25, 1), 100);
|
||||
const offset = Math.max(opts.offset ?? 0, 0);
|
||||
|
||||
@@ -210,21 +343,39 @@ export async function backfillEmbeddings(
|
||||
// 🔴 2026-08-05：**已下架的一律不嵌**（leo：「理論上它的向量也要刪掉，就不會有殘影了吧？」）。
|
||||
// 沒有這條，下架時清掉的向量會在下一次 backfill 又被嵌回來 ⇒ 殘影復活，
|
||||
// 而且 `reindex=true` 那條路更嚴重（它連 is_embedded=1 的都重推）。
|
||||
const conds = [basePredicate, "COALESCE(json_extract(metadata_json, '$.status'), '') != 'deprecated'"];
|
||||
const params: unknown[] = [];
|
||||
if (opts.owner_id) { conds.push('owner_id = ?'); params.push(opts.owner_id); }
|
||||
if (opts.source) { conds.push("json_extract(metadata_json, '$.source') = ?"); params.push(opts.source); }
|
||||
// 「挑哪一批」（Arcrun#85）：owner_id/source/library/since/until 全部走同一套
|
||||
// selectionCriteriaPredicate，讓呼叫端（工作流）能表達時間分層與庫分層，不必等
|
||||
// base 幫忙決定；本函式不預設任何一層，caller 傳什麼就篩什麼。
|
||||
const sel = selectionCriteriaPredicate(opts);
|
||||
const conds = [basePredicate, "COALESCE(json_extract(metadata_json, '$.status'), '') != 'deprecated'", ...sel.conds];
|
||||
const params: unknown[] = [...sel.params];
|
||||
const where = conds.join(' AND ');
|
||||
|
||||
// D68：由新到舊——最可能被查到的最先補回來（見檔頭 DEFAULT_BACKFILL_DAILY_LIMIT 段的決策脈絡）。
|
||||
const res = await env.DB
|
||||
.prepare(`SELECT * FROM entries WHERE ${where} ORDER BY created_at ASC LIMIT ? OFFSET ?`)
|
||||
.prepare(`SELECT * FROM entries WHERE ${where} ORDER BY created_at DESC LIMIT ? OFFSET ?`)
|
||||
.bind(...params, limit, offset)
|
||||
.all<Entry>();
|
||||
const rows = res.results ?? [];
|
||||
const scanned = rows.length;
|
||||
|
||||
// D68：每日額度上限。額度是「這次呼叫要不要打 AI」的唯一守門——reindex 一樣要打 AI.run，
|
||||
// 同樣受限（不因為是 reindex 就例外，會打 Workers AI 的動作都算）。
|
||||
const dailyCap = backfillDailyLimit(env);
|
||||
let usedToday = 0;
|
||||
try {
|
||||
usedToday = await getBackfillUsageToday(env.DB);
|
||||
} catch {
|
||||
usedToday = 0; // fail-open：計數器本身故障（含 D1 額度打滿）不該連 backfill 都不做
|
||||
}
|
||||
const remainingQuota = Math.max(0, dailyCap - usedToday);
|
||||
|
||||
let processed = 0;
|
||||
const embeddable = rows.filter((e) => (e.content ?? '').trim().length > 0);
|
||||
const candidates = rows.filter((e) => (e.content ?? '').trim().length > 0);
|
||||
// 額度截斷：candidates 已按 created_at DESC 排序，取前 remainingQuota 筆＝優先保留最新的。
|
||||
const embeddable = candidates.slice(0, remainingQuota);
|
||||
const quotaExceeded = candidates.length > embeddable.length;
|
||||
|
||||
if (embeddable.length > 0 && env.AI && env.VECTORIZE) {
|
||||
const texts = embeddable.map((e) => (e.content ?? '').trim());
|
||||
const out = (await env.AI.run(embedModel(env), { text: texts })) as { data: number[][] };
|
||||
@@ -246,8 +397,18 @@ export async function backfillEmbeddings(
|
||||
await env.VECTORIZE.upsert(vectors);
|
||||
const ids = vectors.map((v) => v.id);
|
||||
const placeholders = ids.map(() => '?').join(',');
|
||||
await env.DB.prepare(`UPDATE entries SET is_embedded = 1 WHERE id IN (${placeholders})`).bind(...ids).run();
|
||||
// content_hash 順手蓋成現行模型（世代戳記，見 reconcileEmbedGeneration）。
|
||||
await env.DB
|
||||
.prepare(`UPDATE entries SET is_embedded = 1, content_hash = ? WHERE id IN (${placeholders})`)
|
||||
.bind(embedModel(env), ...ids)
|
||||
.run();
|
||||
processed = vectors.length;
|
||||
try {
|
||||
await addBackfillUsage(env.DB, processed);
|
||||
} catch {
|
||||
// fail-open：額度計數寫入失敗不影響已經完成的嵌入（別讓 bookkeeping 故障吞掉已做的工）；
|
||||
// 代價是下次呼叫可能少算一點用量——比「明明做了卻沒生效」安全（誠實限制，mindset §7）。
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -259,7 +420,16 @@ export async function backfillEmbeddings(
|
||||
// 非 reindex：predicate 含 is_embedded=0，處理後該筆變 1 → COUNT 自然遞減（重呼直到 0）。
|
||||
// reindex：predicate 不含 is_embedded，COUNT 恆等於總數 → 改用 offset 分頁計 remaining（否則永不終止）。
|
||||
const remaining = opts.reindex ? Math.max(0, totalMatching - (offset + scanned)) : totalMatching;
|
||||
return { enabled: true, processed, skipped: scanned - processed, remaining, scanned };
|
||||
return {
|
||||
enabled: true,
|
||||
processed,
|
||||
skipped: scanned - processed,
|
||||
remaining,
|
||||
scanned,
|
||||
quota_limit: dailyCap,
|
||||
quota_used_today: usedToday + processed,
|
||||
quota_exceeded: quotaExceeded,
|
||||
};
|
||||
}
|
||||
|
||||
/** 補嵌進度統計（回報用；模組未開仍可查 pending 數，誠實標 enabled:false）。 */
|
||||
@@ -283,6 +453,128 @@ export async function backfillStatus(
|
||||
return { enabled: embedEnabled(env), pending: pendingRow?.c ?? 0, embedded: embeddedRow?.c ?? 0 };
|
||||
}
|
||||
|
||||
export interface ReconcileResult {
|
||||
enabled: boolean;
|
||||
checked: number; // 本批「真的核對＋寫回」的筆數（受下方 D1 額度截斷後的量）。
|
||||
confirmed_current: number; // 核對後確認已在現行 Vectorize index：只補標 content_hash，未打 AI。
|
||||
reset_to_pending: number; // 核對後確認不在現行 index：重置 is_embedded=0，回到正常 backfill 佇列。
|
||||
remaining: number; // 本次之後仍待核對的筆數（不受額度影響，可重複呼叫直到 0）。
|
||||
scanned: number; // 本批掃到的候選筆數（受 limit 限制，額度截斷前）。
|
||||
quota_limit: number; // 今日「背景維護 D1 寫入」額度上限（與標庫 backfill 共用，見 maintenance-quota.ts）。
|
||||
quota_used_today: number; // 本次呼叫後，今日累積已消耗的背景維護寫入額度。
|
||||
quota_exceeded: boolean; // 本批是否因額度不足被截斷（true＝還有候選但今天不再寫 D1，等明天/調高上限）。
|
||||
}
|
||||
|
||||
/**
|
||||
* 世代核對（Generation reconciliation，D68 配套修復，2026-08-11）。
|
||||
*
|
||||
* 背景：`is_embedded=1` 只代表「曾經對某個 Vectorize index 嵌過」，不保證是**現行**的
|
||||
* index/模型（見檔頭 2026-08-03 換代註解：換模型必須換 index，舊向量收不進新 index、也刪不掉）。
|
||||
* 從備份整批灌回的資料尤其會帶著對**已退役索引**（例：768 維 `arcrun-kbdb-embed`）的
|
||||
* `is_embedded=1`——現行 backfill 的預設路徑（只補 `is_embedded=0`）永遠不會碰它們，
|
||||
* 語意搜尋對現行（1024 維 `arcrun-kbdb-embed-m3`）索引而言永遠搜不到那批東西，畫面不會說壞掉。
|
||||
*
|
||||
* 做法：不猜（`is_embedded` 本身此刻不可信），直接問現行 Vectorize index「這些 id 真的在你這嗎」
|
||||
* （`env.VECTORIZE.getByIds`，ground truth，而非比對 content_hash 字串本身——後者在這次修復
|
||||
* 之前從未被寫過，所有既有 is_embedded=1 的列 content_hash 皆為 NULL，無法只憑字串判斷「哪些是
|
||||
* 這次修復前的正常資料、哪些是真正的舊世代殘留」，必須問 Vectorize 本身）：
|
||||
* - 真的在現行 index → 只是這次修復之前的正常資料，沒補寫過 content_hash。補標記，不重打 AI
|
||||
* （不浪費額度在已經正確的資料上）。
|
||||
* - 不在現行 index → 對現行 index 而言等於沒嵌過，重置 is_embedded=0、清空 content_hash，
|
||||
* 交回正常 backfill 佇列（下一輪照樣受「新到舊」排序＋每日額度上限保護，不特別優待）。
|
||||
*
|
||||
* 不消耗 Workers AI 額度：零 AI.run，只有一次 D1 掃描 + 一次 Vectorize.getByIds + D1 寫回。
|
||||
*
|
||||
* D69（Arcrun#85，2026-08-11 leo 逐行複核找到的破口）：**這一步雖不打 AI，但逐筆寫 D1**——
|
||||
* 每個候選最多消耗一次 row write（補標 content_hash 或重置 is_embedded，兩條路互斥、恰好一次），
|
||||
* 47 萬筆候選 ≈ 4.7 倍 D1 100,000 rows written/日免費額度。與標庫 backfill（同樣是多筆 D1
|
||||
* write、不打 AI）共用 `actions/maintenance-quota.ts` 的同一顆每日計數器——不共用的話，
|
||||
* 補標庫時會把這裡的閘繞過去（反之亦然）。額度用完 → 誠實截斷候選，不再寫 D1，等明天。
|
||||
*
|
||||
* 「挑哪一批」：owner_id/library/since/until 走 SelectionCriteria（同 backfillEmbeddings／
|
||||
* backfillEntryLibraryTags 共用的篩選形狀），讓時間分層／庫分層能從外面指定。
|
||||
*/
|
||||
export async function reconcileEmbedGeneration(
|
||||
env: Bindings,
|
||||
opts: Pick<SelectionCriteria, 'owner_id' | 'library' | 'since' | 'until'> & { limit?: number } = {},
|
||||
): Promise<ReconcileResult> {
|
||||
if (!embedEnabled(env)) {
|
||||
return {
|
||||
enabled: false, checked: 0, confirmed_current: 0, reset_to_pending: 0, remaining: 0,
|
||||
scanned: 0, quota_limit: 0, quota_used_today: 0, quota_exceeded: false,
|
||||
};
|
||||
}
|
||||
const limit = Math.min(Math.max(opts.limit ?? 50, 1), 200);
|
||||
const currentModel = embedModel(env);
|
||||
|
||||
const sel = selectionCriteriaPredicate(opts);
|
||||
const conds = [
|
||||
'is_embedded = 1',
|
||||
'(content_hash IS NULL OR content_hash != ?)',
|
||||
"COALESCE(json_extract(metadata_json, '$.status'), '') != 'deprecated'",
|
||||
...sel.conds,
|
||||
];
|
||||
const params: unknown[] = [currentModel, ...sel.params];
|
||||
const where = conds.join(' AND ');
|
||||
|
||||
const res = await env.DB
|
||||
.prepare(`SELECT id FROM entries WHERE ${where} ORDER BY created_at DESC LIMIT ?`)
|
||||
.bind(...params, limit)
|
||||
.all<{ id: string }>();
|
||||
const scannedIds = (res.results ?? []).map((r) => r.id);
|
||||
const scanned = scannedIds.length;
|
||||
|
||||
// D69：額度截斷——每個候選最多 1 次 D1 write，直接照剩餘額度砍候選清單長度。
|
||||
const budget = await maintenanceBudgetToday(env, env.DB);
|
||||
const ids = scannedIds.slice(0, budget.remaining);
|
||||
const quotaExceeded = scanned > ids.length;
|
||||
const checked = ids.length;
|
||||
|
||||
let confirmed_current = 0;
|
||||
let reset_to_pending = 0;
|
||||
if (ids.length > 0 && env.VECTORIZE) {
|
||||
const found = await env.VECTORIZE.getByIds(ids);
|
||||
const foundIds = new Set(found.map((v) => v.id));
|
||||
const presentIds = ids.filter((id) => foundIds.has(id));
|
||||
const missingIds = ids.filter((id) => !foundIds.has(id));
|
||||
|
||||
if (presentIds.length > 0) {
|
||||
const ph = presentIds.map(() => '?').join(',');
|
||||
await env.DB
|
||||
.prepare(`UPDATE entries SET content_hash = ? WHERE id IN (${ph})`)
|
||||
.bind(currentModel, ...presentIds)
|
||||
.run();
|
||||
confirmed_current = presentIds.length;
|
||||
}
|
||||
if (missingIds.length > 0) {
|
||||
const ph = missingIds.map(() => '?').join(',');
|
||||
await env.DB
|
||||
.prepare(`UPDATE entries SET is_embedded = 0, content_hash = NULL WHERE id IN (${ph})`)
|
||||
.bind(...missingIds)
|
||||
.run();
|
||||
reset_to_pending = missingIds.length;
|
||||
}
|
||||
}
|
||||
|
||||
const remRow = await env.DB
|
||||
.prepare(`SELECT COUNT(*) as c FROM entries WHERE ${where}`)
|
||||
.bind(...params)
|
||||
.first<{ c: number }>();
|
||||
|
||||
const written = confirmed_current + reset_to_pending;
|
||||
try {
|
||||
await addMaintenanceUsage(env.DB, written);
|
||||
} catch {
|
||||
// fail-open：額度計數寫入失敗不影響已經完成的核對寫入（精神同 backfillEmbeddings 的
|
||||
// addBackfillUsage 失敗處理——寧可下次呼叫少算一點用量，也不讓計數故障吞掉已做的工）。
|
||||
}
|
||||
|
||||
return {
|
||||
enabled: true, checked, confirmed_current, reset_to_pending, remaining: remRow?.c ?? 0,
|
||||
scanned, quota_limit: budget.limit, quota_used_today: budget.used + written, quota_exceeded: quotaExceeded,
|
||||
};
|
||||
}
|
||||
|
||||
export interface SelfTestResult {
|
||||
enabled: boolean; // embed 模組是否開（binding 都在）
|
||||
tested: boolean; // 是否真的跑了一次自我查詢（false＝連測都測不了，非失敗）
|
||||
|
||||
@@ -8,7 +8,7 @@
|
||||
// base 對內容語意無知：只認通用 metadata.embed===true 旗標，不知 triplet/wiki（解耦）。
|
||||
import { Hono } from 'hono';
|
||||
import type { Bindings } from '../types';
|
||||
import { embedEnabled, backfillEmbeddings, backfillStatus, embedSelfTest } from '../embed';
|
||||
import { embedEnabled, backfillEmbeddings, backfillStatus, embedSelfTest, reconcileEmbedGeneration } from '../embed';
|
||||
|
||||
export const embedRoutes = new Hono<{ Bindings: Bindings }>();
|
||||
|
||||
@@ -16,11 +16,14 @@ const OFF_HINT =
|
||||
'語義補嵌需先開 embed 模組（Vectorize+AI binding）。叫 CC「幫我開語義查詢」（設 kbdb_embed:true + redeploy 注入 binding）後再呼叫本端點。';
|
||||
|
||||
// POST /embed/backfill — batch-embed existing embeddable entries with is_embedded=0.
|
||||
// body（皆選填）：{ limit?:1-100（預設25）, owner_id?, source?, reindex?, offset? }。
|
||||
// body（皆選填）：{ limit?:1-100（預設25）, owner_id?, source?, library?, since?, until?, reindex?, offset? }。
|
||||
// 冪等：重跑不會重複嵌（已 is_embedded=1 的不再入選；upsert 同 id 冪等）。
|
||||
// 分批：單次最多 limit 筆；回傳 remaining>0 表示還有 → 重複呼叫直到 remaining=0。
|
||||
// reindex:true（Arcrun#11）：改重推「所有 embeddable」既有向量（含 is_embedded=1），
|
||||
// 讓事後建立的 Vectorize metadata index 收錄它們（否則帶過濾語意查詢回 0）；配 offset 分頁。
|
||||
// library／since／until（Arcrun#85，2026-08-11）：「挑哪一批」從外面指定——時間分層
|
||||
// （今天/本週/半年前）與庫分層（有查詢紀錄的庫優先）共用同一套 SelectionCriteria，
|
||||
// 由呼叫端（工作流）決定這次要補的是哪一批，不是資料層焊死單一排序（見 embed.ts 檔頭說明）。
|
||||
// 模組未開 → 409 + capability_hint（不假綠）。
|
||||
embedRoutes.post('/backfill', async (c) => {
|
||||
if (!embedEnabled(c.env)) {
|
||||
@@ -33,6 +36,9 @@ embedRoutes.post('/backfill', async (c) => {
|
||||
limit?: number | string;
|
||||
owner_id?: string;
|
||||
source?: string;
|
||||
library?: string;
|
||||
since?: number | string;
|
||||
until?: number | string;
|
||||
reindex?: boolean;
|
||||
offset?: number | string;
|
||||
};
|
||||
@@ -40,6 +46,9 @@ embedRoutes.post('/backfill', async (c) => {
|
||||
limit: body.limit !== undefined ? Number(body.limit) : undefined,
|
||||
owner_id: body.owner_id || undefined,
|
||||
source: body.source || undefined,
|
||||
library: body.library || undefined,
|
||||
since: body.since !== undefined ? Number(body.since) : undefined,
|
||||
until: body.until !== undefined ? Number(body.until) : undefined,
|
||||
// reindex（Arcrun#11）：重推既有向量讓事後建立的 Vectorize metadata index 收錄（見 embed.ts）。
|
||||
reindex: body.reindex === true,
|
||||
offset: body.offset !== undefined ? Number(body.offset) : undefined,
|
||||
@@ -56,6 +65,38 @@ embedRoutes.get('/backfill/status', async (c) => {
|
||||
return c.json({ success: true, ...status });
|
||||
});
|
||||
|
||||
// POST /embed/reconcile — 世代核對（D68 配套修復，2026-08-11；D69 額度節流同日補上）：
|
||||
// 對「is_embedded=1 但 content_hash 非現行模型」的候選，問現行 Vectorize index 是否真的收錄；
|
||||
// 真的在 → 補標 content_hash（不打 AI）；不在 → 重置 is_embedded=0，回到正常 /embed/backfill 佇列。
|
||||
// 解「從備份整批灌回、帶著對已退役索引的 is_embedded=1，永遠不被 backfill 碰到」這個坑。
|
||||
// body（皆選填）：{ limit?:1-200（預設50）, owner_id?, library?, since?, until? }。重複呼叫直到 remaining=0。
|
||||
// D69：每筆候選最多消耗一次 D1 row write，與 POST /entries/backfill-library 共用同一顆每日
|
||||
// 「背景維護 D1 寫入」額度（見 actions/maintenance-quota.ts）——額度用完會誠實回
|
||||
// quota_exceeded:true 並停手，不會把當天 D1 免費額度燒穿（2026-08-11 leo 逐行複核找到的破口）。
|
||||
embedRoutes.post('/reconcile', async (c) => {
|
||||
if (!embedEnabled(c.env)) {
|
||||
return c.json(
|
||||
{ success: false, error: 'embed module not enabled (need VECTORIZE + AI bindings)', capability_hint: OFF_HINT },
|
||||
409,
|
||||
);
|
||||
}
|
||||
const body = (await c.req.json().catch(() => ({}))) as {
|
||||
limit?: number | string;
|
||||
owner_id?: string;
|
||||
library?: string;
|
||||
since?: number | string;
|
||||
until?: number | string;
|
||||
};
|
||||
const result = await reconcileEmbedGeneration(c.env, {
|
||||
limit: body.limit !== undefined ? Number(body.limit) : undefined,
|
||||
owner_id: body.owner_id || undefined,
|
||||
library: body.library || undefined,
|
||||
since: body.since !== undefined ? Number(body.since) : undefined,
|
||||
until: body.until !== undefined ? Number(body.until) : undefined,
|
||||
});
|
||||
return c.json({ success: true, ...result });
|
||||
});
|
||||
|
||||
// GET /embed/selftest?owner_id= — 語義自我檢查（檢修孔，2026-08-07）：
|
||||
// 挑一筆已嵌入的卡片，拿它自己的內容查自己，只回布林診斷（不回卡片內容、不回 entry id）。
|
||||
// 計數（backfill/status）看不出「嵌了但查不到」這種故障模式（Arcrun#11 撞過的真實案例），
|
||||
|
||||
@@ -23,6 +23,7 @@ import {
|
||||
EmbedQueryFailedError,
|
||||
} from '../embed';
|
||||
import { migrateLegacyCredentialsForOwner } from '../actions/credential-legacy-migration';
|
||||
import { backfillEntryLibraryTags, libraryBackfillStatus } from '../actions/library-backfill';
|
||||
|
||||
export const entryRoutes = new Hono<{ Bindings: Bindings }>();
|
||||
|
||||
@@ -367,6 +368,64 @@ entryRoutes.patch('/deprecate-by-library', async (c) => {
|
||||
return c.json({ success: true, deprecated_count: count, vectors_deleted });
|
||||
});
|
||||
|
||||
// POST /entries/backfill-library — 標庫補存量（Arcrun#85 二次裁決／相關票 Arcrun#87，2026-08-11）。
|
||||
// body（必填 library + owner_id）：{ library, owner_id, page_names?（string[]，精準比對，
|
||||
// leo 定案的正解——見 actions/library-backfill.ts 檔頭「拿原稿遍歷」）, entry_type?,
|
||||
// source_prefix?, page_name_prefix?（後兩者為過渡 fallback，精度不如 page_names）,
|
||||
// since?, until?, limit?(1-500，預設100) }。
|
||||
// 冪等：只選「目前未標記 library」的候選；分批：單次 limit 上限，remaining>0 → 重複呼叫直到 0。
|
||||
// budget：與 /embed/reconcile 共用同一顆每日 D1 寫入額度（見 actions/maintenance-quota.ts）——
|
||||
// 兩者都是「多筆 D1 write、不打 AI」的背景維護操作，不共用額度的話補存量會把世代核對的閘繞過去。
|
||||
// base 對內容語意無知：不猜「這批該貼哪個庫」，呼叫端（ingest／#87）決定 library 與篩選條件；
|
||||
// owner_id 必填（同 /entries/deprecate-by-library 的既有防線——批次改一大片既有資料不准無租戶範圍地掃）。
|
||||
// 此路由必須在 '/:id' 之前註冊，否則 'backfill-library' 會被當成 id 參數。
|
||||
entryRoutes.post('/backfill-library', async (c) => {
|
||||
const body = (await c.req.json().catch(() => ({}))) as {
|
||||
library?: string;
|
||||
owner_id?: string;
|
||||
entry_type?: string;
|
||||
page_names?: string[];
|
||||
source_prefix?: string;
|
||||
page_name_prefix?: string;
|
||||
since?: number | string;
|
||||
until?: number | string;
|
||||
limit?: number | string;
|
||||
};
|
||||
const library = String(body.library ?? '').trim();
|
||||
const ownerId = String(body.owner_id ?? '').trim();
|
||||
if (!library || !ownerId) return c.json({ success: false, error: 'library 與 owner_id 必填' }, 400);
|
||||
try {
|
||||
const result = await backfillEntryLibraryTags(c.env.DB, c.env, {
|
||||
library,
|
||||
owner_id: ownerId,
|
||||
entry_type: body.entry_type || undefined,
|
||||
page_names: Array.isArray(body.page_names) && body.page_names.length > 0 ? body.page_names : undefined,
|
||||
source_prefix: body.source_prefix || undefined,
|
||||
page_name_prefix: body.page_name_prefix || undefined,
|
||||
since: body.since !== undefined ? Number(body.since) : undefined,
|
||||
until: body.until !== undefined ? Number(body.until) : undefined,
|
||||
limit: body.limit !== undefined ? Number(body.limit) : undefined,
|
||||
});
|
||||
return c.json({ success: true, ...result });
|
||||
} catch (e) {
|
||||
return c.json({ success: false, error: e instanceof Error ? e.message : String(e) }, 400);
|
||||
}
|
||||
});
|
||||
|
||||
// GET /entries/backfill-library/status?owner_id=&entry_type=&source_prefix=&page_name_prefix=&since=&until=
|
||||
// — 符合條件、目前未標記 library 的筆數（backfill 前後都能查，判斷還剩多少）。
|
||||
entryRoutes.get('/backfill-library/status', async (c) => {
|
||||
const status = await libraryBackfillStatus(c.env.DB, {
|
||||
owner_id: c.req.query('owner_id') || undefined,
|
||||
entry_type: c.req.query('entry_type') || undefined,
|
||||
source_prefix: c.req.query('source_prefix') || undefined,
|
||||
page_name_prefix: c.req.query('page_name_prefix') || undefined,
|
||||
since: c.req.query('since') ? Number(c.req.query('since')) : undefined,
|
||||
until: c.req.query('until') ? Number(c.req.query('until')) : undefined,
|
||||
});
|
||||
return c.json({ success: true, ...status });
|
||||
});
|
||||
|
||||
// PATCH /entries/:id
|
||||
entryRoutes.patch('/:id', async (c) => {
|
||||
const body = await c.req.json().catch(() => ({}));
|
||||
|
||||
+15
-1
@@ -24,6 +24,18 @@ export type Bindings = {
|
||||
// kbdb/src/actions/execution-log.ts DEFAULT_DAILY_LIMIT 說明）。未設 → 20000
|
||||
// （D1 100,000 rows written/日的 20%，留 80% 給知識卡 entries）。
|
||||
EXECUTION_LOG_DAILY_WRITE_LIMIT?: string;
|
||||
// embed backfill 每日軟上限（D68，2026-08-11：補算向量照時間新到舊、且每天有額度上限）。
|
||||
// backfill 與「寫入即嵌」「萃取」共用同一份 Workers AI 每日 10,000 免費 neurons（見頂層
|
||||
// wiki ops-facts.md）；backfill 是背景低優先動作，自設軟上限不把當天額度燒光。未設 → 見
|
||||
// kbdb/src/embed.ts DEFAULT_BACKFILL_DAILY_LIMIT 說明（含選值算式，非拍腦袋）。
|
||||
EMBED_BACKFILL_DAILY_LIMIT?: string;
|
||||
// 背景維護寫入（reconcile 世代核對 + 標庫 backfill）共用的 D1 每日寫入軟上限
|
||||
// （Arcrun#85 D69 修法，2026-08-11：兩者都是「多筆 D1 row write、不打 AI」的操作，
|
||||
// 各自不設防都會單獨燒穿 D1 100,000 rows/日免費額度——reconcile 47 萬筆 candidate
|
||||
// ≈ 4.7 倍全日額度，已在票上實測；標庫 backfill 同樣是逐筆 D1 write，若各管各的，
|
||||
// 補標庫時會把 reconcile 的閘繞過去。兩者共用同一顆「今天還剩多少」計數器。
|
||||
// 未設 → 見 kbdb/src/actions/maintenance-quota.ts DEFAULT_MAINTENANCE_DAILY_WRITE_LIMIT。
|
||||
KBDB_MAINTENANCE_DAILY_WRITE_LIMIT?: string;
|
||||
};
|
||||
|
||||
export type EntryType =
|
||||
@@ -35,7 +47,9 @@ export type EntryType =
|
||||
| 'workflow'
|
||||
| 'recipe_stat'
|
||||
| 'execution_log'
|
||||
| 'execution_log_usage';
|
||||
| 'execution_log_usage'
|
||||
| 'embed_backfill_usage'
|
||||
| 'kbdb_maintenance_usage';
|
||||
|
||||
export interface Entry {
|
||||
id: string;
|
||||
|
||||
+410
-108
@@ -1,130 +1,196 @@
|
||||
// embed backfill — D68（2026-08-11 leo 拍板：補算向量照時間新到舊、且每天有額度上限）測試。
|
||||
//
|
||||
// 測試策略比照 execution-log.test.ts／library-map.test.ts：真 SQLite（node:sqlite）套
|
||||
// migrations/0001_base.sql 原檔，比手刻假 DB 更硬——驗的是真實 SQL 語意（ORDER BY／WHERE／
|
||||
// JSON 函式），不是「以為 SQL 長這樣」。AI／VECTORIZE 仍是輕量假物件（Cloudflare binding，
|
||||
// 不是 SQL，沒有真 runtime 可套）。
|
||||
//
|
||||
// 覆蓋 D68 三條 + is_embedded 世代旗標坑，四項都要有實測輸出：
|
||||
// 1. 由新到舊：造 created_at 跨時間的候選，證明先被處理的是最新那幾筆
|
||||
// 2. 每日額度上限真的擋：cap 設小，跑到撞上限，證明它停手不再打 AI（不是繼續打）
|
||||
// 3. 帶著舊世代旗標（is_embedded=1 但對應已退役索引）的列補得回來
|
||||
// 4. 現有 idempotent／batching／reindex 行為不因本次改動而壞掉
|
||||
//
|
||||
// 本檔在 kbdb/tests/（牆外，非 kbdb/src|migrations），依 D38 kbdb-api-wall-guard 規則，
|
||||
// 所有直接對 SQLite 治具下 SQL 的行都集中在下面幾個 helper（每行標 kbdb-sql-ok 留痕）——
|
||||
// 這是**測試治具本身**（node:sqlite→D1 shim，模擬 D1 binding），不是牆外業務邏輯繞過 API。
|
||||
import { describe, it, expect } from 'vitest';
|
||||
import { backfillEmbeddings, backfillStatus, embedEnabled } from '../src/embed';
|
||||
import type { Bindings, Entry } from '../src/types';
|
||||
import { DatabaseSync } from 'node:sqlite';
|
||||
import { readFileSync } from 'node:fs';
|
||||
import {
|
||||
backfillEmbeddings,
|
||||
backfillStatus,
|
||||
embedEnabled,
|
||||
reconcileEmbedGeneration,
|
||||
} from '../src/embed';
|
||||
import type { Bindings, Entry, EntryType } from '../src/types';
|
||||
|
||||
// ── Minimal in-memory fakes (no Workers runtime) ─────────────────────────────
|
||||
// The fake DB interprets only the 3 statement shapes backfill issues, by keyword:
|
||||
// SELECT * ... LIMIT ? OFFSET ? → candidate rows (embeddable & non-empty content;
|
||||
// +is_embedded=0 for normal backfill, any for reindex)
|
||||
// UPDATE ... IN (...) → flip is_embedded=1 for the bound ids
|
||||
// SELECT COUNT(*) → count of matching candidates
|
||||
// embeddable = metadata.embed===true & non-empty content（reindex predicate）。
|
||||
function isEmbeddable(e: Entry): boolean {
|
||||
if (!e.content || e.content.trim() === '') return false;
|
||||
try {
|
||||
const m = JSON.parse(e.metadata_json ?? 'null');
|
||||
return m?.embed === true;
|
||||
} catch {
|
||||
return false;
|
||||
}
|
||||
}
|
||||
// normal backfill 額外要求 is_embedded=0（漏網補嵌）。
|
||||
function isCandidate(e: Entry): boolean {
|
||||
return e.is_embedded === 0 && isEmbeddable(e);
|
||||
}
|
||||
const CURRENT_MODEL = '@cf/baai/bge-m3'; // embed.ts DEFAULT_EMBED_MODEL（未 export，測試按文件字面核對）
|
||||
|
||||
function makeFakeDB(store: Entry[]) {
|
||||
const prepare = (sql: string) => {
|
||||
// reindex predicate 不含 "is_embedded = 0" → 依 SQL 判斷該用哪個 filter（對齊 embed.ts）。
|
||||
const pred = /is_embedded = 0/.test(sql) ? isCandidate : isEmbeddable;
|
||||
let bound: unknown[] = [];
|
||||
const stmt = {
|
||||
bind(...args: unknown[]) { bound = args; return stmt; },
|
||||
async all<T>() {
|
||||
// SELECT * ... LIMIT ? OFFSET ? (bound tail = [..., limit, offset])
|
||||
const offset = Number(bound[bound.length - 1]);
|
||||
const limit = Number(bound[bound.length - 2]);
|
||||
const results = store.filter(pred).slice(offset, offset + limit) as unknown as T[];
|
||||
return { results };
|
||||
},
|
||||
async first<T>() {
|
||||
// SELECT COUNT(*) as c ...
|
||||
const c = store.filter(pred).length;
|
||||
return { c } as unknown as T;
|
||||
},
|
||||
// ── node:sqlite → D1 介面最小 adapter（同 execution-log.test.ts／library-map.test.ts 手法）──
|
||||
function makeSqliteD1(): D1Database {
|
||||
const raw = new DatabaseSync(':memory:');
|
||||
raw.exec(readFileSync(new URL('../migrations/0001_base.sql', import.meta.url), 'utf8')); // kbdb-sql-ok：測試治具（node:sqlite→D1 shim）套 migration 原檔
|
||||
function stmt(sql: string, params: unknown[]) {
|
||||
const s = {
|
||||
bind(...args: unknown[]) { return stmt(sql, args); },
|
||||
async all<T>() { return { results: raw.prepare(sql).all(...params) as T[] }; }, // kbdb-sql-ok：測試治具（node:sqlite→D1 shim）
|
||||
async first<T>() { return (raw.prepare(sql).get(...params) ?? null) as T | null; }, // kbdb-sql-ok：測試治具（node:sqlite→D1 shim）
|
||||
async run() {
|
||||
// UPDATE entries SET is_embedded = 1 WHERE id IN (...) → bound = ids
|
||||
const ids = new Set(bound.map(String));
|
||||
for (const e of store) if (ids.has(e.id)) e.is_embedded = 1;
|
||||
return { success: true };
|
||||
const r = raw.prepare(sql).run(...params); // kbdb-sql-ok：測試治具（node:sqlite→D1 shim），非牆外業務邏輯繞過 API
|
||||
return { success: true, meta: { changes: r.changes } };
|
||||
},
|
||||
};
|
||||
return stmt;
|
||||
};
|
||||
return { prepare } as unknown as D1Database;
|
||||
return s;
|
||||
}
|
||||
return { prepare: (sql: string) => stmt(sql, []) } as unknown as D1Database;
|
||||
}
|
||||
|
||||
function mkEntry(id: string, content: string | null, embed: boolean, is_embedded = 0): Entry {
|
||||
return {
|
||||
id, content, entry_type: 'workflow', owner_id: 'leo', parent_id: null, page_name: null,
|
||||
refs_json: '[]', tags_json: '[]', task_status: null, content_hash: null, is_embedded,
|
||||
confidence: null, metadata_json: JSON.stringify({ embed }), created_at: 1, updated_at: 1,
|
||||
};
|
||||
// ── 測試專用資料存取 helper：把所有直接下 SQL 的呼叫收斂到這裡（每行標記留痕）──────────
|
||||
function insertEntry(db: D1Database, e: Partial<Entry> & { id: string; created_at: number }): void {
|
||||
const sql = `INSERT INTO entries (id, content, entry_type, owner_id, content_hash, is_embedded, metadata_json, created_at, updated_at)
|
||||
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)`;
|
||||
db.prepare(sql).bind( // kbdb-sql-ok：測試治具（node:sqlite→D1 shim）灌測試資料
|
||||
e.id,
|
||||
e.content === undefined ? 'x' : e.content, // 區分「沒提供」(undefined→預設'x') 與「顯式 null」(保留 null)
|
||||
|
||||
(e.entry_type ?? 'workflow') as EntryType,
|
||||
e.owner_id ?? 'leo',
|
||||
e.content_hash ?? null,
|
||||
e.is_embedded ?? 0,
|
||||
e.metadata_json ?? JSON.stringify({ embed: true }),
|
||||
e.created_at,
|
||||
e.created_at,
|
||||
).run();
|
||||
}
|
||||
|
||||
function makeEnv(store: Entry[], withBindings: boolean): Bindings {
|
||||
async function getRow(db: D1Database, id: string): Promise<{ id: string; is_embedded: number; content_hash: string | null } | null> {
|
||||
return db.prepare('SELECT id, is_embedded, content_hash FROM entries WHERE id = ?').bind(id).first(); // kbdb-sql-ok：測試治具讀回斷言用
|
||||
}
|
||||
|
||||
async function listAllRows(db: D1Database): Promise<{ id: string; is_embedded: number; content_hash: string | null }[]> {
|
||||
const res = await db.prepare('SELECT id, is_embedded, content_hash FROM entries').all<{ id: string; is_embedded: number; content_hash: string | null }>(); // kbdb-sql-ok：測試治具讀回斷言用
|
||||
return res.results;
|
||||
}
|
||||
|
||||
async function listEmbeddedIds(db: D1Database): Promise<string[]> {
|
||||
const res = await db.prepare("SELECT id FROM entries WHERE is_embedded = 1").all<{ id: string }>(); // kbdb-sql-ok：測試治具讀回斷言用
|
||||
return res.results.map((r) => r.id);
|
||||
}
|
||||
|
||||
async function countUsageRows(db: D1Database): Promise<{ id: string; entry_type: string }[]> {
|
||||
const res = await db.prepare("SELECT id, entry_type FROM entries WHERE entry_type = 'embed_backfill_usage'").all<{ id: string; entry_type: string }>(); // kbdb-sql-ok：測試治具驗證「不新增表、單列 upsert」
|
||||
return res.results;
|
||||
}
|
||||
|
||||
function makeEnv(db: D1Database, opts: { withBindings?: boolean; dailyLimit?: string; maintenanceLimit?: string } = {}): Bindings {
|
||||
const withBindings = opts.withBindings ?? true;
|
||||
const upserts: { id: string }[] = [];
|
||||
const aiCalls: string[][] = [];
|
||||
const getByIdsCalls: string[][] = [];
|
||||
const vectorizeStore = new Set<string>(); // ids "present" in the current (fake) Vectorize index
|
||||
const env = {
|
||||
DB: makeFakeDB(store),
|
||||
DB: db,
|
||||
ENVIRONMENT: 'test',
|
||||
EMBED_BACKFILL_DAILY_LIMIT: opts.dailyLimit,
|
||||
KBDB_MAINTENANCE_DAILY_WRITE_LIMIT: opts.maintenanceLimit,
|
||||
...(withBindings
|
||||
? {
|
||||
AI: { async run(_m: string, i: { text: string[] }) { aiCalls.push(i.text); return { data: i.text.map(() => [0.1, 0.2, 0.3]) }; } },
|
||||
VECTORIZE: { async upsert(v: { id: string }[]) { upserts.push(...v); return { count: v.length }; } },
|
||||
AI: {
|
||||
async run(_m: string, i: { text: string[] }) {
|
||||
aiCalls.push(i.text);
|
||||
return { data: i.text.map(() => [0.1, 0.2, 0.3]) };
|
||||
},
|
||||
},
|
||||
VECTORIZE: {
|
||||
async upsert(v: { id: string }[]) {
|
||||
upserts.push(...v);
|
||||
for (const x of v) vectorizeStore.add(x.id);
|
||||
return { count: v.length };
|
||||
},
|
||||
async getByIds(ids: string[]) {
|
||||
getByIdsCalls.push(ids);
|
||||
return ids.filter((id) => vectorizeStore.has(id)).map((id) => ({ id, values: [0.1] }));
|
||||
},
|
||||
},
|
||||
}
|
||||
: {}),
|
||||
} as unknown as Bindings;
|
||||
(env as unknown as { __upserts: unknown[]; __ai: unknown[] }).__upserts = upserts;
|
||||
(env as unknown as { __upserts: unknown[]; __ai: unknown[] }).__ai = aiCalls;
|
||||
const bag = env as unknown as {
|
||||
__upserts: unknown[]; __ai: unknown[]; __getByIds: unknown[];
|
||||
__seedVectorized: (ids: string[]) => void;
|
||||
};
|
||||
bag.__upserts = upserts;
|
||||
bag.__ai = aiCalls;
|
||||
bag.__getByIds = getByIdsCalls;
|
||||
bag.__seedVectorized = (ids: string[]) => { for (const id of ids) vectorizeStore.add(id); };
|
||||
return env;
|
||||
}
|
||||
|
||||
describe('backfillEmbeddings', () => {
|
||||
it('module off → enabled:false, no-op (誠實不假綠)', async () => {
|
||||
const store = [mkEntry('e1', 'hello', true)];
|
||||
const env = makeEnv(store, false);
|
||||
function aiCallsOf(env: Bindings): string[][] {
|
||||
return (env as unknown as { __ai: string[][] }).__ai;
|
||||
}
|
||||
function upsertsOf(env: Bindings): { id: string }[] {
|
||||
return (env as unknown as { __upserts: { id: string }[] }).__upserts;
|
||||
}
|
||||
function seedVectorized(env: Bindings, ids: string[]): void {
|
||||
(env as unknown as { __seedVectorized: (ids: string[]) => void }).__seedVectorized(ids);
|
||||
}
|
||||
|
||||
describe('backfillEmbeddings — 模組未開', () => {
|
||||
it('誠實不假綠：no-op，含新增的 quota 欄位', async () => {
|
||||
const db = makeSqliteD1();
|
||||
insertEntry(db, { id: 'e1', created_at: 1 });
|
||||
const env = makeEnv(db, { withBindings: false });
|
||||
expect(embedEnabled(env)).toBe(false);
|
||||
const r = await backfillEmbeddings(env);
|
||||
expect(r).toEqual({ enabled: false, processed: 0, skipped: 0, remaining: 0, scanned: 0 });
|
||||
expect(store[0].is_embedded).toBe(0); // untouched
|
||||
expect(r).toEqual({
|
||||
enabled: false, processed: 0, skipped: 0, remaining: 0, scanned: 0,
|
||||
quota_limit: 0, quota_used_today: 0, quota_exceeded: false,
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
it('embeds embeddable+is_embedded=0 entries, marks is_embedded=1, batches AI+upsert', async () => {
|
||||
const store = [
|
||||
mkEntry('e1', 'doorbell workflow', true),
|
||||
mkEntry('e2', 'notify workflow', true),
|
||||
mkEntry('e3', 'not tagged', false), // embed:false → not a candidate
|
||||
mkEntry('e4', 'already done', true, 1), // is_embedded=1 → not a candidate
|
||||
mkEntry('e5', ' ', true), // empty content → not embeddable
|
||||
];
|
||||
const env = makeEnv(store, true);
|
||||
describe('backfillEmbeddings — 基本行為（沿用既有覆蓋，改動後仍要綠）', () => {
|
||||
it('embeds embeddable+is_embedded=0 entries, marks is_embedded=1 + content_hash，批次 AI+upsert', async () => {
|
||||
const db = makeSqliteD1();
|
||||
insertEntry(db, { id: 'e1', content: 'doorbell workflow', created_at: 1 });
|
||||
insertEntry(db, { id: 'e2', content: 'notify workflow', created_at: 2 });
|
||||
insertEntry(db, { id: 'e3', content: 'not tagged', created_at: 3, metadata_json: JSON.stringify({ embed: false }) });
|
||||
insertEntry(db, { id: 'e4', content: 'already done', created_at: 4, is_embedded: 1 });
|
||||
insertEntry(db, { id: 'e5', content: null, created_at: 5 }); // NULL content → 排除，非本次改動範圍的既有行為
|
||||
const env = makeEnv(db);
|
||||
const r = await backfillEmbeddings(env, { limit: 100 });
|
||||
expect(r.enabled).toBe(true);
|
||||
expect(r.processed).toBe(2); // only e1,e2
|
||||
expect(r.remaining).toBe(0); // nothing left embeddable
|
||||
expect(store.find((e) => e.id === 'e1')!.is_embedded).toBe(1);
|
||||
expect(store.find((e) => e.id === 'e2')!.is_embedded).toBe(1);
|
||||
expect(store.find((e) => e.id === 'e3')!.is_embedded).toBe(0);
|
||||
const upserts = (env as unknown as { __upserts: { id: string }[] }).__upserts;
|
||||
expect(upserts.map((u) => u.id).sort()).toEqual(['e1', 'e2']);
|
||||
const ai = (env as unknown as { __ai: string[][] }).__ai;
|
||||
expect(ai.length).toBe(1); // single batched AI.run for the whole batch
|
||||
expect(ai[0].length).toBe(2);
|
||||
expect(r.processed).toBe(2); // only e1, e2
|
||||
expect(r.remaining).toBe(0);
|
||||
const rows = await listAllRows(db);
|
||||
const byId = Object.fromEntries(rows.map((x) => [x.id, x]));
|
||||
expect(byId.e1.is_embedded).toBe(1);
|
||||
expect(byId.e1.content_hash).toBe(CURRENT_MODEL); // 世代戳記有寫
|
||||
expect(byId.e2.is_embedded).toBe(1);
|
||||
expect(byId.e3.is_embedded).toBe(0);
|
||||
expect(upsertsOf(env).map((u) => u.id).sort()).toEqual(['e1', 'e2']);
|
||||
expect(aiCallsOf(env).length).toBe(1);
|
||||
expect(aiCallsOf(env)[0].length).toBe(2);
|
||||
});
|
||||
|
||||
it('idempotent: re-run after all embedded processes nothing', async () => {
|
||||
const store = [mkEntry('e1', 'x', true)];
|
||||
const env = makeEnv(store, true);
|
||||
it('idempotent：全部嵌完後重跑不再處理', async () => {
|
||||
const db = makeSqliteD1();
|
||||
insertEntry(db, { id: 'e1', content: 'x', created_at: 1 });
|
||||
const env = makeEnv(db, { dailyLimit: '100' });
|
||||
await backfillEmbeddings(env);
|
||||
const r2 = await backfillEmbeddings(env);
|
||||
expect(r2.processed).toBe(0);
|
||||
expect(r2.remaining).toBe(0);
|
||||
});
|
||||
|
||||
it('batches via limit → remaining reported so caller can loop to zero', async () => {
|
||||
const store = [mkEntry('a', 'x', true), mkEntry('b', 'y', true), mkEntry('c', 'z', true)];
|
||||
const env = makeEnv(store, true);
|
||||
it('batches via limit → remaining 讓 caller 可重複呼叫到 0', async () => {
|
||||
const db = makeSqliteD1();
|
||||
insertEntry(db, { id: 'a', content: 'x', created_at: 1 });
|
||||
insertEntry(db, { id: 'b', content: 'y', created_at: 2 });
|
||||
insertEntry(db, { id: 'c', content: 'z', created_at: 3 });
|
||||
const env = makeEnv(db, { dailyLimit: '100' });
|
||||
const r1 = await backfillEmbeddings(env, { limit: 2 });
|
||||
expect(r1.processed).toBe(2);
|
||||
expect(r1.remaining).toBe(1);
|
||||
@@ -133,34 +199,270 @@ describe('backfillEmbeddings', () => {
|
||||
expect(r2.remaining).toBe(0);
|
||||
});
|
||||
|
||||
it('reindex: 重推所有 embeddable（含 is_embedded=1），offset 分頁到 remaining=0（Arcrun#11）', async () => {
|
||||
// 三筆皆已 is_embedded=1（既有向量）：正常 backfill 不會碰（pending=0），reindex 要全部重推
|
||||
// 讓事後建立的 Vectorize metadata index 收錄。
|
||||
const store = [
|
||||
mkEntry('a', 'x', true, 1), mkEntry('b', 'y', true, 1), mkEntry('c', 'z', true, 1),
|
||||
];
|
||||
const env = makeEnv(store, true);
|
||||
// 正常 backfill：沒有 is_embedded=0 → 什麼都不做（證明「不重推就補不到」）。
|
||||
it('reindex：重推所有 embeddable（含 is_embedded=1），offset 分頁到 remaining=0（Arcrun#11）', async () => {
|
||||
const db = makeSqliteD1();
|
||||
insertEntry(db, { id: 'a', content: 'x', created_at: 1, is_embedded: 1 });
|
||||
insertEntry(db, { id: 'b', content: 'y', created_at: 2, is_embedded: 1 });
|
||||
insertEntry(db, { id: 'c', content: 'z', created_at: 3, is_embedded: 1 });
|
||||
const env = makeEnv(db, { dailyLimit: '100' });
|
||||
const normal = await backfillEmbeddings(env, { limit: 100 });
|
||||
expect(normal.processed).toBe(0);
|
||||
// reindex 分頁：第一批 2 筆、remaining=1；第二批 1 筆、remaining=0。
|
||||
expect(normal.processed).toBe(0); // 沒有 is_embedded=0 → 什麼都不做
|
||||
const r1 = await backfillEmbeddings(env, { reindex: true, limit: 2, offset: 0 });
|
||||
expect(r1.processed).toBe(2);
|
||||
expect(r1.remaining).toBe(1);
|
||||
const r2 = await backfillEmbeddings(env, { reindex: true, limit: 2, offset: 2 });
|
||||
expect(r2.processed).toBe(1);
|
||||
expect(r2.remaining).toBe(0);
|
||||
const upserts = (env as unknown as { __upserts: { id: string }[] }).__upserts;
|
||||
expect(upserts.map((u) => u.id).sort()).toEqual(['a', 'b', 'c']);
|
||||
expect(upsertsOf(env).map((u) => u.id).sort()).toEqual(['a', 'b', 'c']);
|
||||
});
|
||||
|
||||
it('status reports pending/embedded counts', async () => {
|
||||
const store = [mkEntry('e1', 'x', true), mkEntry('e2', 'y', true, 1)];
|
||||
const env = makeEnv(store, true);
|
||||
it('status 回報 pending/embedded 計數', async () => {
|
||||
const db = makeSqliteD1();
|
||||
insertEntry(db, { id: 'e1', content: 'x', created_at: 1 });
|
||||
insertEntry(db, { id: 'e2', content: 'y', created_at: 2, is_embedded: 1 });
|
||||
const env = makeEnv(db);
|
||||
const s = await backfillStatus(env);
|
||||
// fake first() returns candidate count for pending; embedded query also runs through
|
||||
// the same COUNT fake, so this asserts the call path works (enabled:true).
|
||||
expect(s.enabled).toBe(true);
|
||||
expect(typeof s.pending).toBe('number');
|
||||
});
|
||||
});
|
||||
|
||||
describe('D68①：由新到舊排序（實測，不是推論）', () => {
|
||||
it('候選跨時間分佈時，先被嵌入的是 created_at 最新的那幾筆', async () => {
|
||||
const db = makeSqliteD1();
|
||||
// 刻意亂序插入，證明排序看的是 created_at 不是插入順序 / id 字母序
|
||||
insertEntry(db, { id: 'old-2024', content: 'half year ago', created_at: 1_000 });
|
||||
insertEntry(db, { id: 'today', content: 'written today', created_at: 100_000 });
|
||||
insertEntry(db, { id: 'mid-2025', content: 'a few months ago', created_at: 50_000 });
|
||||
const env = makeEnv(db, { dailyLimit: '100' });
|
||||
// limit=1：一次只能處理一筆，若排序正確，該筆必須是 'today'（created_at 最大）
|
||||
const r = await backfillEmbeddings(env, { limit: 1 });
|
||||
expect(r.processed).toBe(1);
|
||||
const embedded = await listEmbeddedIds(db);
|
||||
expect(embedded).toEqual(['today']);
|
||||
expect(aiCallsOf(env)[0]).toEqual(['written today']);
|
||||
});
|
||||
});
|
||||
|
||||
describe('D68②：每日額度上限真的擋（把上限設小，跑到撞上限）', () => {
|
||||
it('額度耗盡後停手，不再繼續打 AI；未耗盡的仍優先保留最新的（額度截斷 + 排序疊加）', async () => {
|
||||
const db = makeSqliteD1();
|
||||
insertEntry(db, { id: 'e-oldest', content: 'c1', created_at: 1 });
|
||||
insertEntry(db, { id: 'e-old', content: 'c2', created_at: 2 });
|
||||
insertEntry(db, { id: 'e-new', content: 'c3', created_at: 3 });
|
||||
insertEntry(db, { id: 'e-newest', content: 'c4', created_at: 4 });
|
||||
const env = makeEnv(db, { dailyLimit: '2' }); // 上限設得比候選數（4）小
|
||||
const r = await backfillEmbeddings(env, { limit: 100 });
|
||||
|
||||
// 停手，不是繼續打：AI 只被叫過一次，且只帶 2 筆文字（不是全部 4 筆）
|
||||
expect(aiCallsOf(env).length).toBe(1);
|
||||
expect(aiCallsOf(env)[0].length).toBe(2);
|
||||
expect(r.processed).toBe(2);
|
||||
expect(r.quota_limit).toBe(2);
|
||||
expect(r.quota_used_today).toBe(2);
|
||||
expect(r.quota_exceeded).toBe(true); // 還有候選但今天不再打 AI
|
||||
|
||||
// 被留下處理的兩筆是最新的（e-newest, e-new），不是隨機或最舊的
|
||||
const embedded = await listEmbeddedIds(db);
|
||||
expect(embedded.sort()).toEqual(['e-new', 'e-newest']);
|
||||
|
||||
// 再跑一次（同一天）：額度已用完，processed=0，AI 呼叫次數仍是 1（沒有再打）
|
||||
const r2 = await backfillEmbeddings(env, { limit: 100 });
|
||||
expect(r2.processed).toBe(0);
|
||||
expect(r2.quota_exceeded).toBe(true);
|
||||
expect(aiCallsOf(env).length).toBe(1); // 沒有新增呼叫
|
||||
});
|
||||
|
||||
it('額度上限被拿掉時本測試會變紅（反向驗證：測試真的在測東西，不是恆真）', async () => {
|
||||
const db = makeSqliteD1();
|
||||
for (let i = 1; i <= 5; i++) insertEntry(db, { id: `e${i}`, content: `c${i}`, created_at: i });
|
||||
// 不設 dailyLimit（用預設 1800，遠大於 5）→ 全部應被處理，模擬「上限被拿掉」的行為
|
||||
const env = makeEnv(db);
|
||||
const r = await backfillEmbeddings(env, { limit: 100 });
|
||||
expect(r.processed).toBe(5);
|
||||
expect(r.quota_exceeded).toBe(false);
|
||||
// 對照組：把上限設到比候選數小，行為必須不同（證明上一組「額度=2」的測試不是巧合）
|
||||
const db2 = makeSqliteD1();
|
||||
for (let i = 1; i <= 5; i++) insertEntry(db2, { id: `e${i}`, content: `c${i}`, created_at: i });
|
||||
const env2 = makeEnv(db2, { dailyLimit: '2' });
|
||||
const r2 = await backfillEmbeddings(env2, { limit: 100 });
|
||||
expect(r2.processed).toBe(2);
|
||||
expect(r2.processed).not.toBe(r.processed); // 有 cap vs 沒 cap 必須不同，否則 cap 沒在起作用
|
||||
});
|
||||
|
||||
it('額度計數跨呼叫累加，換日字串變動即歸零（不新增表，entries 單列 upsert）', async () => {
|
||||
const db = makeSqliteD1();
|
||||
insertEntry(db, { id: 'e1', content: 'c1', created_at: 1 });
|
||||
insertEntry(db, { id: 'e2', content: 'c2', created_at: 2 });
|
||||
const env = makeEnv(db, { dailyLimit: '10' });
|
||||
const r1 = await backfillEmbeddings(env, { limit: 1 });
|
||||
expect(r1.quota_used_today).toBe(1);
|
||||
const r2 = await backfillEmbeddings(env, { limit: 1 });
|
||||
expect(r2.quota_used_today).toBe(2); // 累加，不是每次重算成當批數
|
||||
// 驗證只有一列計數器，且落在既有三表（entries），沒有新表
|
||||
const usageRows = await countUsageRows(db);
|
||||
expect(usageRows.length).toBe(1);
|
||||
expect(usageRows[0].id).toMatch(/^embed-backfill-usage:\d{4}-\d{2}-\d{2}$/);
|
||||
});
|
||||
});
|
||||
|
||||
describe('D68③：leo21c 資料還原情境——is_embedded=1 但對應已退役索引的列補得回來', () => {
|
||||
it('reconcile：確認在現行 index 的只補 content_hash，不打 AI', async () => {
|
||||
const db = makeSqliteD1();
|
||||
// 模擬「這次修復之前」就已經正確嵌入現行 index 的資料：is_embedded=1、content_hash 從未寫過（NULL）
|
||||
insertEntry(db, { id: 'ok-legacy', content: 'x', created_at: 1, is_embedded: 1, content_hash: null });
|
||||
const env = makeEnv(db);
|
||||
seedVectorized(env, ['ok-legacy']); // 現行 index 真的有它
|
||||
|
||||
const r = await reconcileEmbedGeneration(env, { limit: 100 });
|
||||
expect(r.checked).toBe(1);
|
||||
expect(r.confirmed_current).toBe(1);
|
||||
expect(r.reset_to_pending).toBe(0);
|
||||
expect(aiCallsOf(env).length).toBe(0); // 沒有打 AI
|
||||
|
||||
const row = await getRow(db, 'ok-legacy');
|
||||
expect(row!.is_embedded).toBe(1); // 沒被誤重置
|
||||
expect(row!.content_hash).toBe(CURRENT_MODEL); // 補標記
|
||||
});
|
||||
|
||||
it('reconcile 揪出真正對舊索引的殘留 → 重置回 pending → 正常 backfill 真的把它補回來（端到端）', async () => {
|
||||
const db = makeSqliteD1();
|
||||
// leo21c 情境：從備份整批灌回，is_embedded=1 但這是對已退役 768 維索引說的；
|
||||
// 現行（1024 維）Vectorize index 裡沒有這個向量（不呼叫 seedVectorized）。
|
||||
insertEntry(db, { id: 'restored-stale', content: '從備份還原的舊卡片', created_at: 999, is_embedded: 1, content_hash: null });
|
||||
const env = makeEnv(db);
|
||||
|
||||
// step 1：reconcile 應該發現它不在現行 index，重置成 pending
|
||||
const r1 = await reconcileEmbedGeneration(env, { limit: 100 });
|
||||
expect(r1.checked).toBe(1);
|
||||
expect(r1.confirmed_current).toBe(0);
|
||||
expect(r1.reset_to_pending).toBe(1);
|
||||
const midRow = await getRow(db, 'restored-stale');
|
||||
expect(midRow!.is_embedded).toBe(0);
|
||||
expect(midRow!.content_hash).toBe(null);
|
||||
expect(r1.remaining).toBe(0); // 處理完，沒有更多待核對的了
|
||||
|
||||
// step 2：正常 backfill 現在會撿到它（因為 is_embedded=0 了），真的打 AI 補回來
|
||||
const r2 = await backfillEmbeddings(env, { limit: 100 });
|
||||
expect(r2.processed).toBe(1);
|
||||
expect(aiCallsOf(env).length).toBe(1);
|
||||
expect(aiCallsOf(env)[0]).toEqual(['從備份還原的舊卡片']);
|
||||
|
||||
const finalRow = await getRow(db, 'restored-stale');
|
||||
expect(finalRow!.is_embedded).toBe(1); // 補回來了
|
||||
expect(finalRow!.content_hash).toBe(CURRENT_MODEL); // 蓋上現行世代戳記，下次 reconcile 不會再選到它
|
||||
});
|
||||
|
||||
it('已經是現行世代（content_hash 等於現行模型）的列不會被 reconcile 重複選中', async () => {
|
||||
const db = makeSqliteD1();
|
||||
insertEntry(db, { id: 'fresh', content: 'x', created_at: 1, is_embedded: 1, content_hash: CURRENT_MODEL });
|
||||
const env = makeEnv(db);
|
||||
const r = await reconcileEmbedGeneration(env, { limit: 100 });
|
||||
expect(r.checked).toBe(0);
|
||||
expect(r.remaining).toBe(0);
|
||||
});
|
||||
|
||||
it('模組未開 → 誠實回 enabled:false，不假裝', async () => {
|
||||
const db = makeSqliteD1();
|
||||
insertEntry(db, { id: 'e1', content: 'x', created_at: 1, is_embedded: 1 });
|
||||
const env = makeEnv(db, { withBindings: false });
|
||||
const r = await reconcileEmbedGeneration(env);
|
||||
expect(r).toEqual({
|
||||
enabled: false, checked: 0, confirmed_current: 0, reset_to_pending: 0, remaining: 0,
|
||||
scanned: 0, quota_limit: 0, quota_used_today: 0, quota_exceeded: false,
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
describe('Arcrun#85 D69：reconcile 的 D1 寫入額度（與標庫 backfill 共用的計數器）', () => {
|
||||
it('額度耗盡後 reconcile 停手：不再寫 D1，quota_exceeded=true', async () => {
|
||||
const db = makeSqliteD1();
|
||||
insertEntry(db, { id: 'r1', content: 'c1', created_at: 1, is_embedded: 1, content_hash: null });
|
||||
insertEntry(db, { id: 'r2', content: 'c2', created_at: 2, is_embedded: 1, content_hash: null });
|
||||
insertEntry(db, { id: 'r3', content: 'c3', created_at: 3, is_embedded: 1, content_hash: null });
|
||||
const env = makeEnv(db, { maintenanceLimit: '2' }); // 上限比候選數（3）小
|
||||
seedVectorized(env, ['r1', 'r2', 'r3']); // 全在現行 index（confirmed_current 路徑，仍是 D1 write）
|
||||
|
||||
const r = await reconcileEmbedGeneration(env, { limit: 100 });
|
||||
expect(r.scanned).toBe(3); // 掃到 3 筆候選
|
||||
expect(r.checked).toBe(2); // 但只處理了額度允許的 2 筆
|
||||
expect(r.confirmed_current).toBe(2);
|
||||
expect(r.quota_limit).toBe(2);
|
||||
expect(r.quota_used_today).toBe(2);
|
||||
expect(r.quota_exceeded).toBe(true);
|
||||
|
||||
// 只有 2 筆真的被寫回 content_hash（最新的兩筆，ORDER BY created_at DESC）
|
||||
const rows = await listAllRows(db);
|
||||
const byId = Object.fromEntries(rows.map((x) => [x.id, x]));
|
||||
expect(byId.r3.content_hash).toBe(CURRENT_MODEL);
|
||||
expect(byId.r2.content_hash).toBe(CURRENT_MODEL);
|
||||
expect(byId.r1.content_hash).toBe(null); // 額度用完，沒輪到它
|
||||
|
||||
// 再跑一次（同一天）：額度已用完，checked=0
|
||||
const r2 = await reconcileEmbedGeneration(env, { limit: 100 });
|
||||
expect(r2.checked).toBe(0);
|
||||
expect(r2.quota_exceeded).toBe(true);
|
||||
});
|
||||
|
||||
it('額度上限被拿掉時本測試會變紅（反向驗證，同 D68② 手法）', async () => {
|
||||
const db = makeSqliteD1();
|
||||
for (let i = 1; i <= 5; i++) insertEntry(db, { id: `r${i}`, content: `c${i}`, created_at: i, is_embedded: 1, content_hash: null });
|
||||
const env = makeEnv(db); // 不設 maintenanceLimit → 用預設 20000，遠大於 5，全部應被處理
|
||||
seedVectorized(env, ['r1', 'r2', 'r3', 'r4', 'r5']);
|
||||
const r = await reconcileEmbedGeneration(env, { limit: 100 });
|
||||
expect(r.checked).toBe(5);
|
||||
expect(r.quota_exceeded).toBe(false);
|
||||
|
||||
const db2 = makeSqliteD1();
|
||||
for (let i = 1; i <= 5; i++) insertEntry(db2, { id: `r${i}`, content: `c${i}`, created_at: i, is_embedded: 1, content_hash: null });
|
||||
const env2 = makeEnv(db2, { maintenanceLimit: '2' });
|
||||
seedVectorized(env2, ['r1', 'r2', 'r3', 'r4', 'r5']);
|
||||
const r2 = await reconcileEmbedGeneration(env2, { limit: 100 });
|
||||
expect(r2.checked).toBe(2);
|
||||
expect(r2.checked).not.toBe(r.checked); // 有 cap vs 沒 cap 必須不同，否則 cap 沒在作用
|
||||
});
|
||||
});
|
||||
|
||||
describe('Arcrun#85：「挑哪一批」可以從外面指定（SelectionCriteria：since/until/library）', () => {
|
||||
it('backfillEmbeddings 帶 since/until 只補時間窗內的候選', async () => {
|
||||
const db = makeSqliteD1();
|
||||
insertEntry(db, { id: 'too-old', content: 'x', created_at: 100 });
|
||||
insertEntry(db, { id: 'in-window-1', content: 'y', created_at: 500 });
|
||||
insertEntry(db, { id: 'in-window-2', content: 'z', created_at: 800 });
|
||||
insertEntry(db, { id: 'too-new', content: 'w', created_at: 1500 });
|
||||
const env = makeEnv(db, { dailyLimit: '100' });
|
||||
const r = await backfillEmbeddings(env, { limit: 100, since: 400, until: 1000 });
|
||||
expect(r.processed).toBe(2);
|
||||
expect((await listEmbeddedIds(db)).sort()).toEqual(['in-window-1', 'in-window-2']);
|
||||
});
|
||||
|
||||
it('backfillEmbeddings 帶 library 只補該庫的候選（未標記歸 general）', async () => {
|
||||
const db = makeSqliteD1();
|
||||
insertEntry(db, { id: 'finance-1', content: 'x', created_at: 1, metadata_json: JSON.stringify({ embed: true, library: 'finance' }) });
|
||||
insertEntry(db, { id: 'hr-1', content: 'y', created_at: 2, metadata_json: JSON.stringify({ embed: true, library: 'hr' }) });
|
||||
insertEntry(db, { id: 'untagged', content: 'z', created_at: 3 }); // 無 library → general
|
||||
const env = makeEnv(db, { dailyLimit: '100' });
|
||||
const r = await backfillEmbeddings(env, { limit: 100, library: 'finance' });
|
||||
expect(r.processed).toBe(1);
|
||||
expect(await listEmbeddedIds(db)).toEqual(['finance-1']);
|
||||
|
||||
const r2 = await backfillEmbeddings(env, { limit: 100, library: 'general' });
|
||||
expect(r2.processed).toBe(1);
|
||||
expect((await listEmbeddedIds(db)).sort()).toEqual(['finance-1', 'untagged']);
|
||||
});
|
||||
|
||||
it('reconcile 帶 since/until/library 同樣受篩選（同一套 SelectionCriteria，非獨立實作）', async () => {
|
||||
const db = makeSqliteD1();
|
||||
insertEntry(db, { id: 'old', content: 'x', created_at: 1, is_embedded: 1, content_hash: null, metadata_json: JSON.stringify({ embed: true, library: 'finance' }) });
|
||||
insertEntry(db, { id: 'new', content: 'y', created_at: 100, is_embedded: 1, content_hash: null, metadata_json: JSON.stringify({ embed: true, library: 'finance' }) });
|
||||
insertEntry(db, { id: 'other-lib', content: 'z', created_at: 100, is_embedded: 1, content_hash: null, metadata_json: JSON.stringify({ embed: true, library: 'hr' }) });
|
||||
const env = makeEnv(db);
|
||||
seedVectorized(env, ['old', 'new', 'other-lib']);
|
||||
const r = await reconcileEmbedGeneration(env, { limit: 100, library: 'finance', since: 50 });
|
||||
expect(r.checked).toBe(1);
|
||||
const row = await getRow(db, 'new');
|
||||
expect(row!.content_hash).toBe(CURRENT_MODEL);
|
||||
const oldRow = await getRow(db, 'old');
|
||||
expect(oldRow!.content_hash).toBe(null); // 在時間窗外，沒被動到
|
||||
});
|
||||
});
|
||||
|
||||
@@ -0,0 +1,230 @@
|
||||
// 標庫 backfill（Arcrun#85 二次裁決，2026-08-11）測試。
|
||||
//
|
||||
// 測試策略比照 embed-backfill.test.ts：真 SQLite（node:sqlite）套 migrations/0001_base.sql
|
||||
// 原檔，驗真實 SQL 語意（json_set／WHERE／LIMIT），不是「以為 SQL 長這樣」。
|
||||
//
|
||||
// 覆蓋：
|
||||
// 1. 只補「符合條件、目前未標記 library」的候選；已標記的不動（冪等）
|
||||
// 2. owner_id 必填（缺了要拋錯，防「補錯 owner 等於白做」——2026-08-11 leo 直令）
|
||||
// 3. source_prefix／page_name_prefix／since／until 篩選條件真的在篩
|
||||
// 4. 與 reconcileEmbedGeneration 共用同一顆每日 D1 寫入額度（D69 的核心訴求：
|
||||
// 補標不能把世代核對的閘繞過去，反之亦然）
|
||||
//
|
||||
// 本檔在 kbdb/tests/（牆外），依 D38 kbdb-api-wall-guard 規則，直接對 SQLite 治具下 SQL
|
||||
// 的行集中在 helper（測試治具本身，非牆外業務邏輯繞過 API，每行標 kbdb-sql-ok 留痕）。
|
||||
import { describe, it, expect } from 'vitest';
|
||||
import { DatabaseSync } from 'node:sqlite';
|
||||
import { readFileSync } from 'node:fs';
|
||||
import { backfillEntryLibraryTags, libraryBackfillStatus } from '../src/actions/library-backfill';
|
||||
import { reconcileEmbedGeneration } from '../src/embed';
|
||||
import type { Bindings, Entry, EntryType } from '../src/types';
|
||||
|
||||
// ── node:sqlite → D1 介面最小 adapter（同 embed-backfill.test.ts 手法）──────────────
|
||||
function makeSqliteD1(): D1Database {
|
||||
const raw = new DatabaseSync(':memory:');
|
||||
raw.exec(readFileSync(new URL('../migrations/0001_base.sql', import.meta.url), 'utf8')); // kbdb-sql-ok：測試治具（node:sqlite→D1 shim）套 migration 原檔
|
||||
function stmt(sql: string, params: unknown[]) {
|
||||
const s = {
|
||||
bind(...args: unknown[]) { return stmt(sql, args); },
|
||||
async all<T>() { return { results: raw.prepare(sql).all(...params) as T[] }; }, // kbdb-sql-ok：測試治具（node:sqlite→D1 shim）
|
||||
async first<T>() { return (raw.prepare(sql).get(...params) ?? null) as T | null; }, // kbdb-sql-ok：測試治具（node:sqlite→D1 shim）
|
||||
async run() {
|
||||
const r = raw.prepare(sql).run(...params); // kbdb-sql-ok：測試治具（node:sqlite→D1 shim），非牆外業務邏輯繞過 API
|
||||
return { success: true, meta: { changes: r.changes } };
|
||||
},
|
||||
};
|
||||
return s;
|
||||
}
|
||||
return { prepare: (sql: string) => stmt(sql, []) } as unknown as D1Database;
|
||||
}
|
||||
|
||||
function insertEntry(db: D1Database, e: Partial<Entry> & { id: string; created_at: number }): void {
|
||||
const sql = `INSERT INTO entries (id, content, entry_type, owner_id, content_hash, is_embedded, metadata_json, page_name, created_at, updated_at)
|
||||
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)`;
|
||||
db.prepare(sql).bind( // kbdb-sql-ok：測試治具（node:sqlite→D1 shim）灌測試資料
|
||||
e.id,
|
||||
e.content === undefined ? 'x' : e.content,
|
||||
(e.entry_type ?? 'block') as EntryType,
|
||||
e.owner_id ?? 'bfezv28v',
|
||||
e.content_hash ?? null,
|
||||
e.is_embedded ?? 0,
|
||||
e.metadata_json === undefined ? null : e.metadata_json,
|
||||
e.page_name ?? null,
|
||||
e.created_at,
|
||||
e.created_at,
|
||||
).run();
|
||||
}
|
||||
|
||||
async function getLibrary(db: D1Database, id: string): Promise<string | null> {
|
||||
const row = await db.prepare("SELECT json_extract(metadata_json, '$.library') AS library FROM entries WHERE id = ?").bind(id).first<{ library: string | null }>(); // kbdb-sql-ok：測試治具讀回斷言用
|
||||
return row?.library ?? null;
|
||||
}
|
||||
|
||||
function makeEnv(db: D1Database, opts: { maintenanceLimit?: string } = {}): Bindings {
|
||||
return {
|
||||
DB: db,
|
||||
ENVIRONMENT: 'test',
|
||||
KBDB_MAINTENANCE_DAILY_WRITE_LIMIT: opts.maintenanceLimit,
|
||||
} as unknown as Bindings;
|
||||
}
|
||||
|
||||
describe('backfillEntryLibraryTags — 基本行為', () => {
|
||||
it('只標記符合條件、目前未標記 library 的候選；已標記的不動', async () => {
|
||||
const db = makeSqliteD1();
|
||||
insertEntry(db, { id: 'a', created_at: 1 }); // 無 metadata_json → 未標記
|
||||
insertEntry(db, { id: 'b', created_at: 2, metadata_json: JSON.stringify({}) }); // 有 metadata_json 但無 library
|
||||
insertEntry(db, { id: 'c', created_at: 3, metadata_json: JSON.stringify({ library: 'hr' }) }); // 已標記，不該被動
|
||||
const env = makeEnv(db);
|
||||
const r = await backfillEntryLibraryTags(db, env, { library: 'finance', owner_id: 'bfezv28v' });
|
||||
expect(r.tagged).toBe(2);
|
||||
expect(r.remaining).toBe(0);
|
||||
expect(await getLibrary(db, 'a')).toBe('finance');
|
||||
expect(await getLibrary(db, 'b')).toBe('finance');
|
||||
expect(await getLibrary(db, 'c')).toBe('hr'); // 未被覆寫
|
||||
});
|
||||
|
||||
it('冪等：全部標記完後重跑不再處理', async () => {
|
||||
const db = makeSqliteD1();
|
||||
insertEntry(db, { id: 'a', created_at: 1 });
|
||||
const env = makeEnv(db);
|
||||
await backfillEntryLibraryTags(db, env, { library: 'finance', owner_id: 'bfezv28v' });
|
||||
const r2 = await backfillEntryLibraryTags(db, env, { library: 'finance', owner_id: 'bfezv28v' });
|
||||
expect(r2.tagged).toBe(0);
|
||||
expect(r2.remaining).toBe(0);
|
||||
});
|
||||
|
||||
it('owner_id 缺了要拋錯（防補錯 owner 等於白做，2026-08-11 leo 直令）', async () => {
|
||||
const db = makeSqliteD1();
|
||||
insertEntry(db, { id: 'a', created_at: 1 });
|
||||
const env = makeEnv(db);
|
||||
await expect(
|
||||
backfillEntryLibraryTags(db, env, { library: 'finance', owner_id: '' }),
|
||||
).rejects.toThrow(/owner_id/);
|
||||
});
|
||||
|
||||
it('library 缺了要拋錯', async () => {
|
||||
const db = makeSqliteD1();
|
||||
const env = makeEnv(db);
|
||||
await expect(
|
||||
backfillEntryLibraryTags(db, env, { library: '', owner_id: 'bfezv28v' }),
|
||||
).rejects.toThrow(/library/);
|
||||
});
|
||||
|
||||
it('owner_id 篩選：只動指定租戶的資料，其他租戶不受影響（跨租戶隔離）', async () => {
|
||||
const db = makeSqliteD1();
|
||||
insertEntry(db, { id: 'mine', created_at: 1, owner_id: 'bfezv28v' });
|
||||
insertEntry(db, { id: 'theirs', created_at: 2, owner_id: 'someone-else' });
|
||||
const env = makeEnv(db);
|
||||
const r = await backfillEntryLibraryTags(db, env, { library: 'finance', owner_id: 'bfezv28v' });
|
||||
expect(r.tagged).toBe(1);
|
||||
expect(await getLibrary(db, 'mine')).toBe('finance');
|
||||
expect(await getLibrary(db, 'theirs')).toBe(null); // 別的租戶完全沒被動到
|
||||
});
|
||||
|
||||
it('source_prefix／page_name_prefix／since／until 篩選真的在篩', async () => {
|
||||
const db = makeSqliteD1();
|
||||
insertEntry(db, { id: 'match-source', created_at: 500, metadata_json: JSON.stringify({ source: 'gitea://Leo/kb/foo.md' }) });
|
||||
insertEntry(db, { id: 'other-source', created_at: 500, metadata_json: JSON.stringify({ source: 'gitea://Leo/other/bar.md' }) });
|
||||
const r1 = await backfillEntryLibraryTags(db, makeEnv(db), {
|
||||
library: 'kb', owner_id: 'bfezv28v', source_prefix: 'gitea://Leo/kb/',
|
||||
});
|
||||
expect(r1.tagged).toBe(1);
|
||||
expect(await getLibrary(db, 'match-source')).toBe('kb');
|
||||
expect(await getLibrary(db, 'other-source')).toBe(null);
|
||||
|
||||
const db2 = makeSqliteD1();
|
||||
insertEntry(db2, { id: 'in-window', created_at: 500, page_name: 'wiki/foo' });
|
||||
insertEntry(db2, { id: 'out-window', created_at: 5000, page_name: 'wiki/bar' });
|
||||
const r2 = await backfillEntryLibraryTags(db2, makeEnv(db2), {
|
||||
library: 'wiki', owner_id: 'bfezv28v', page_name_prefix: 'wiki/', since: 0, until: 1000,
|
||||
});
|
||||
expect(r2.tagged).toBe(1);
|
||||
expect(await getLibrary(db2, 'in-window')).toBe('wiki');
|
||||
expect(await getLibrary(db2, 'out-window')).toBe(null);
|
||||
});
|
||||
|
||||
it('page_names 精準比對（leo 定案的正解：拿 Gitea 原稿卡名逐批遍歷點名）', async () => {
|
||||
const db = makeSqliteD1();
|
||||
insertEntry(db, { id: 'a', created_at: 1, page_name: 'card-alpha' });
|
||||
insertEntry(db, { id: 'b', created_at: 2, page_name: 'card-beta' });
|
||||
insertEntry(db, { id: 'c', created_at: 3, page_name: 'card-gamma' }); // 不在點名清單內
|
||||
const r = await backfillEntryLibraryTags(db, makeEnv(db), {
|
||||
library: 'kb', owner_id: 'bfezv28v', page_names: ['card-alpha', 'card-beta'],
|
||||
});
|
||||
expect(r.tagged).toBe(2);
|
||||
expect(await getLibrary(db, 'a')).toBe('kb');
|
||||
expect(await getLibrary(db, 'b')).toBe('kb');
|
||||
expect(await getLibrary(db, 'c')).toBe(null); // 沒被點名，不動
|
||||
});
|
||||
|
||||
it('libraryBackfillStatus 回報待補標筆數', async () => {
|
||||
const db = makeSqliteD1();
|
||||
insertEntry(db, { id: 'a', created_at: 1 });
|
||||
insertEntry(db, { id: 'b', created_at: 2, metadata_json: JSON.stringify({ library: 'hr' }) });
|
||||
const s = await libraryBackfillStatus(db, { owner_id: 'bfezv28v' });
|
||||
expect(s.pending).toBe(1); // 只有 'a' 未標記
|
||||
});
|
||||
});
|
||||
|
||||
describe('Arcrun#85 D69：標庫 backfill 與 reconcile 共用同一顆 D1 每日寫入額度', () => {
|
||||
it('reconcile 先消耗額度 → 標庫 backfill 看到的剩餘額度真的變少', async () => {
|
||||
const db = makeSqliteD1();
|
||||
// reconcile 的候選：is_embedded=1 且 content_hash 非現行世代
|
||||
// library 已標記（'hr'）→ 不會被下面的標庫 backfill 選中，讓兩種候選池互不重疊，
|
||||
// 才能單純驗證「額度共用」本身，不被「標庫候選也吃到 reconcile 資料」干擾。
|
||||
insertEntry(db, { id: 'reconcile-1', created_at: 1, is_embedded: 1, content_hash: null, metadata_json: JSON.stringify({ embed: true, library: 'hr' }) });
|
||||
insertEntry(db, { id: 'reconcile-2', created_at: 2, is_embedded: 1, content_hash: null, metadata_json: JSON.stringify({ embed: true, library: 'hr' }) });
|
||||
// 標庫的候選：未標記 library
|
||||
insertEntry(db, { id: 'tag-1', created_at: 3 });
|
||||
insertEntry(db, { id: 'tag-2', created_at: 4 });
|
||||
insertEntry(db, { id: 'tag-3', created_at: 5 });
|
||||
|
||||
const maintenanceLimit = '3'; // 5 個候選（2 reconcile + 3 tag），額度只夠 3 個
|
||||
const reconcileEnv = {
|
||||
DB: db, ENVIRONMENT: 'test', KBDB_MAINTENANCE_DAILY_WRITE_LIMIT: maintenanceLimit,
|
||||
AI: { async run() { return { data: [] }; } },
|
||||
VECTORIZE: {
|
||||
async getByIds(ids: string[]) { return ids.map((id) => ({ id, values: [0.1] })); }, // 全部視為現行 index 已有
|
||||
async upsert() { return { count: 0 }; },
|
||||
},
|
||||
} as unknown as Bindings;
|
||||
|
||||
// 先跑 reconcile：吃掉 2 筆額度（3 - 2 = 1 剩）
|
||||
const rc = await reconcileEmbedGeneration(reconcileEnv, { limit: 100 });
|
||||
expect(rc.checked).toBe(2);
|
||||
expect(rc.quota_used_today).toBe(2);
|
||||
|
||||
// 標庫 backfill 用同一顆 DB／同一個每日上限：只剩 1 筆額度可用，即使候選有 3 筆
|
||||
const tagEnv = makeEnv(db, { maintenanceLimit });
|
||||
const tagResult = await backfillEntryLibraryTags(db, tagEnv, { library: 'general', owner_id: 'bfezv28v' });
|
||||
expect(tagResult.scanned).toBe(3); // 3 筆候選都掃到了
|
||||
expect(tagResult.tagged).toBe(1); // 但只剩 1 筆額度，只標了 1 筆
|
||||
expect(tagResult.quota_exceeded).toBe(true);
|
||||
expect(tagResult.quota_used_today).toBe(3); // 2（reconcile）+ 1（本次）＝ 3，額度用滿
|
||||
});
|
||||
|
||||
it('反過來也一樣：標庫 backfill 先消耗額度 → reconcile 看到的剩餘額度真的變少', async () => {
|
||||
const db = makeSqliteD1();
|
||||
insertEntry(db, { id: 'tag-1', created_at: 1 });
|
||||
insertEntry(db, { id: 'tag-2', created_at: 2 });
|
||||
insertEntry(db, { id: 'reconcile-1', created_at: 3, is_embedded: 1, content_hash: null, metadata_json: JSON.stringify({ embed: true }) });
|
||||
|
||||
const maintenanceLimit = '2';
|
||||
const tagEnv = makeEnv(db, { maintenanceLimit });
|
||||
const tagResult = await backfillEntryLibraryTags(db, tagEnv, { library: 'general', owner_id: 'bfezv28v' });
|
||||
expect(tagResult.tagged).toBe(2); // 額度剛好夠標完兩筆
|
||||
|
||||
const reconcileEnv = {
|
||||
DB: db, ENVIRONMENT: 'test', KBDB_MAINTENANCE_DAILY_WRITE_LIMIT: maintenanceLimit,
|
||||
AI: { async run() { return { data: [] }; } },
|
||||
VECTORIZE: {
|
||||
async getByIds(ids: string[]) { return ids.map((id) => ({ id, values: [0.1] })); },
|
||||
async upsert() { return { count: 0 }; },
|
||||
},
|
||||
} as unknown as Bindings;
|
||||
const rc = await reconcileEmbedGeneration(reconcileEnv, { limit: 100 });
|
||||
expect(rc.scanned).toBe(1); // 有 1 筆候選
|
||||
expect(rc.checked).toBe(0); // 但額度已被標庫 backfill 用光，reconcile 一筆都動不了
|
||||
expect(rc.quota_exceeded).toBe(true);
|
||||
});
|
||||
});
|
||||
@@ -16,7 +16,7 @@ import {
|
||||
ensureFreshLibraryMaps,
|
||||
LIBRARY_MAP_SLOTS,
|
||||
} from '../src/actions/library-map';
|
||||
import { createTemplate, createRecord, getRecord, getTemplate } from '../src/actions/record-crud';
|
||||
import { createTemplate, createRecord, getRecord, getTemplate, searchByTemplate } from '../src/actions/record-crud';
|
||||
import { createEntry } from '../src/actions/entry-crud';
|
||||
import type { Bindings } from '../src/types';
|
||||
|
||||
@@ -292,6 +292,39 @@ describe('M3 收尾 — 即時新鮮度（ensureFreshLibraryMaps，讀端自動
|
||||
expect(secondBody.libraries.find((l) => l.library === 'kb')!.triplet_count).toBe(2);
|
||||
});
|
||||
|
||||
it('Arcrun#87 迴歸：superseded triplet 存在時，連讀兩次地圖不會再次觸發重算（不再無止盡寫入）', async () => {
|
||||
// 重現票上的根因：liveTripletCountsByLibrary 原本不濾 status，recomputeLibraryMap 只算
|
||||
// active——只要庫裡混了 superseded triplet，兩邊算出來的數字永遠對不上，
|
||||
// ensureFreshLibraryMaps 就永遠判定 stale，每次讀地圖都重算、每次都新建一筆 record。
|
||||
const db = makeSqliteD1();
|
||||
await seedTripletTemplate(db);
|
||||
await ensureTripletLibrarySlot(db, 'triplet');
|
||||
await seedTriplet(db, { s: 'A', p: '連結至', o: 'B', library: 'kb' }); // active
|
||||
await seedTriplet(db, { s: 'A', p: '連結至', o: 'C', library: 'kb', status: 'superseded' }); // 已淘汰
|
||||
|
||||
const { app, env } = makeApp(db);
|
||||
|
||||
// 第一次讀：資料是新的（從沒 recompute 過），觸發一次重算是正常的。
|
||||
const first = await app.request('/map', {}, env);
|
||||
const firstBody = (await first.json()) as { libraries: { library: string; triplet_count: number }[] };
|
||||
expect(firstBody.libraries.find((l) => l.library === 'kb')!.triplet_count).toBe(1); // 只算 active 那筆
|
||||
|
||||
const countAfterFirst = (await searchByTemplate(db, 'library_map')).length;
|
||||
|
||||
// 第二次讀：中間沒有任何寫入動作。修好之前，這裡會再次判定 stale 並多新建一筆 record。
|
||||
const second = await app.request('/map', {}, env);
|
||||
const secondBody = (await second.json()) as { libraries: { library: string; triplet_count: number }[] };
|
||||
expect(secondBody.libraries.find((l) => l.library === 'kb')!.triplet_count).toBe(1);
|
||||
|
||||
const countAfterSecond = (await searchByTemplate(db, 'library_map')).length;
|
||||
expect(countAfterSecond).toBe(countAfterFirst); // 沒有新增任何 library_map record
|
||||
|
||||
// 第三次也一樣，多讀幾次確認不是巧合。
|
||||
await app.request('/map', {}, env);
|
||||
const countAfterThird = (await searchByTemplate(db, 'library_map')).length;
|
||||
expect(countAfterThird).toBe(countAfterFirst);
|
||||
});
|
||||
|
||||
it('narrative 不會被自動重算靜默洗掉：先人工帶 narrative，之後的自動重算要保留它', async () => {
|
||||
const db = makeSqliteD1();
|
||||
await seedTripletTemplate(db);
|
||||
|
||||
@@ -0,0 +1,253 @@
|
||||
// 搜尋框裡的 `%` 與 `_` 是「要找的字」，不是萬用字元 —— Arcrun#94（2026-08-12）
|
||||
//
|
||||
// 病徵（leo 回報）：搜尋框打 `%` 或 `_`，搜出來一堆跟他打的字**無關**的東西。
|
||||
// 根因：pattern 一直是 `'%' + 使用者輸入 + '%'` 直接內插，而 SQLite 的 LIKE 有兩個
|
||||
// 萬用字元 `%`／`_` 且**沒有預設跳脫字元** ⇒ 使用者打的符號被當成 pattern 語法。
|
||||
//
|
||||
// 舊病，不是 08-10 斷詞（search-tokenize.test.ts）引進的：pattern 從來就是這樣拼的。
|
||||
// 之前關鍵字搜尋幾乎恆為 0 命中，這個洞被那個洞蓋住；斷詞讓搜尋真的會回東西之後才浮出來。
|
||||
//
|
||||
// 測試策略：**用真 SQLite 跑真的 SQL**（node:sqlite，與 library-map／embed-backfill 同款 adapter）。
|
||||
// 只驗 SQL 形狀不算數——「% 被當成萬用字元」這件事，只有真的跑一次 LIKE 才看得見。
|
||||
// 每組驗收都同時跑「舊寫法」與「現行寫法」，讓前後對照直接長在測試裡（legacyPattern）。
|
||||
//
|
||||
// 註：直接對 SQLite 治具下 SQL 的行集中在下面的 helper（測試治具本身，非牆外業務邏輯繞過
|
||||
// API），每行標 kbdb-sql-ok 留痕——與 embed-backfill／library-backfill 等既有測試同慣例。
|
||||
import { describe, it, expect } from 'vitest';
|
||||
import { DatabaseSync } from 'node:sqlite';
|
||||
import { readFileSync } from 'node:fs';
|
||||
import {
|
||||
escapeLikeLiteral,
|
||||
buildContentLike,
|
||||
buildSearchScore,
|
||||
searchEntries,
|
||||
createEntry,
|
||||
} from '../src/actions/entry-crud';
|
||||
|
||||
// ── node:sqlite → D1 最小 adapter ────────────────────────────────────────────
|
||||
function makeSqliteD1(): D1Database {
|
||||
const raw = new DatabaseSync(':memory:'); // kbdb-sql-ok：記憶體測試替身，非真 KBDB D1
|
||||
raw.exec(readFileSync(new URL('../migrations/0001_base.sql', import.meta.url), 'utf8')); // kbdb-sql-ok：測試治具套 migration 原檔
|
||||
function stmt(sql: string, params: unknown[]) {
|
||||
return {
|
||||
bind(...args: unknown[]) { return stmt(sql, args); },
|
||||
async all<T>() { return { results: raw.prepare(sql).all(...(params as never[])) as T[] }; }, // kbdb-sql-ok：測試治具（node:sqlite→D1 shim）
|
||||
async first<T>() { return (raw.prepare(sql).get(...(params as never[])) ?? null) as T | null; }, // kbdb-sql-ok：測試治具（node:sqlite→D1 shim）
|
||||
async run() { raw.prepare(sql).run(...(params as never[])); return { success: true }; }, // kbdb-sql-ok：測試治具（node:sqlite→D1 shim）
|
||||
};
|
||||
}
|
||||
return { prepare: (sql: string) => stmt(sql, []) } as unknown as D1Database;
|
||||
}
|
||||
|
||||
/** 舊寫法（本次修掉的那個）：使用者輸入直接內插、LIKE 不帶 ESCAPE。前後對照用。 */
|
||||
const legacyPattern = (q: string) => `%${q}%`;
|
||||
|
||||
/** 對真 SQLite 跑一次 `content LIKE ?`，回命中的 content（要不要帶 ESCAPE 可選）。 */
|
||||
async function likeHits(db: D1Database, pattern: string, escape: boolean): Promise<string[]> {
|
||||
const pred = escape ? "content LIKE ? ESCAPE '\\'" : 'content LIKE ?';
|
||||
const res = await db
|
||||
.prepare(`SELECT content FROM entries WHERE ${pred} ORDER BY id`) // kbdb-sql-ok：測試治具讀回斷言用
|
||||
.bind(pattern)
|
||||
.all<{ content: string }>();
|
||||
return (res.results ?? []).map((x) => x.content);
|
||||
}
|
||||
|
||||
/** 把 searchEntries 送出的 SQL 側錄下來（不改行為，只是中間插一層）。 */
|
||||
function sqlSpy(db: D1Database): { spy: D1Database; sqls: string[] } {
|
||||
const sqls: string[] = [];
|
||||
const spy = {
|
||||
prepare: (sql: string) => { sqls.push(sql); return db.prepare(sql); }, // kbdb-sql-ok：測試治具側錄，轉呼叫同一顆治具 DB
|
||||
} as unknown as D1Database;
|
||||
return { spy, sqls };
|
||||
}
|
||||
|
||||
const bytes = (s: string) => new TextEncoder().encode(s).length;
|
||||
const MAX_PATTERN = 50; // D1 LIKE pattern 硬上限（承 2026-08-03 的 500 修復）
|
||||
|
||||
// 一組刻意設計的語料：每一筆都用來分辨「字面命中」與「萬用字元誤中」。
|
||||
const CORPUS = [
|
||||
'毛利率 100% 達成', // 含字面 %
|
||||
'共有 100 個待辦項目', // 含 100 但不含 %，`%100%%` 會誤中它
|
||||
'owner_id 是租戶隔離的欄位', // 含字面 _
|
||||
'ownerXid 是打錯的欄位名', // `_` 當萬用字元才會中
|
||||
'路徑 C:\\_temp 底下', // 含字面「反斜線＋底線」（跳脫字元本身 ＋ 萬用字元）
|
||||
'路徑 C:\\Xtemp 底下', // 反斜線後接任一字元——`_` 漏成萬用字元才會中
|
||||
'完全無關的一筆內容', // 對照組：什麼都不該中
|
||||
];
|
||||
|
||||
async function seeded(): Promise<D1Database> {
|
||||
const db = makeSqliteD1();
|
||||
for (const [i, content] of CORPUS.entries()) {
|
||||
await createEntry(db, { id: `e${i}`, content, entry_type: 'block', owner_id: 'leo' });
|
||||
}
|
||||
return db;
|
||||
}
|
||||
|
||||
describe('① 前後對照：使用者打什麼字，就照那些字找', () => {
|
||||
it('`100%`：舊寫法把 % 當萬用字元、連「100 個待辦」都撈回來；現行只回真的含 100% 的', async () => {
|
||||
const db = await seeded();
|
||||
const before = await likeHits(db, legacyPattern('100%'), false);
|
||||
const after = await likeHits(db, buildContentLike('100%').params[0], true);
|
||||
|
||||
expect(before).toEqual(['毛利率 100% 達成', '共有 100 個待辦項目']); // ← 病徵：多了不相干的
|
||||
expect(after).toEqual(['毛利率 100% 達成']); // ← 只有真的含「100%」的
|
||||
});
|
||||
|
||||
it('`owner_id`：舊寫法 _ 匹配任一字元、把 ownerXid 也撈回來；現行只回字面相符的', async () => {
|
||||
const db = await seeded();
|
||||
expect(await likeHits(db, legacyPattern('owner_id'), false)).toEqual([
|
||||
'owner_id 是租戶隔離的欄位',
|
||||
'ownerXid 是打錯的欄位名', // ← 病徵
|
||||
]);
|
||||
expect(await likeHits(db, buildContentLike('owner_id').params[0], true)).toEqual([
|
||||
'owner_id 是租戶隔離的欄位',
|
||||
]);
|
||||
});
|
||||
|
||||
it('只打一個 `%` 或 `_`：舊寫法把**整個庫**倒回來（leo 回報的那個畫面）', async () => {
|
||||
const db = await seeded();
|
||||
// `%%%` 匹配任何字串；`%_%` 只要有一個字元就中 ⇒ 兩者都等於「全庫」
|
||||
expect(await likeHits(db, legacyPattern('%'), false)).toHaveLength(CORPUS.length);
|
||||
expect(await likeHits(db, legacyPattern('_'), false)).toHaveLength(CORPUS.length);
|
||||
|
||||
// 現行：只回真的含那個字元的（`_` 有兩筆——欄位名那筆與路徑那筆，兩筆都是字面命中）
|
||||
expect(await likeHits(db, buildContentLike('%').params[0], true)).toEqual(['毛利率 100% 達成']);
|
||||
expect(await likeHits(db, buildContentLike('_').params[0], true)).toEqual([
|
||||
'owner_id 是租戶隔離的欄位',
|
||||
'路徑 C:\\_temp 底下',
|
||||
]);
|
||||
});
|
||||
|
||||
it('走完整搜尋路徑（searchEntries，含斷詞與算分）結果一致——不是只有底層函式對', async () => {
|
||||
const db = await seeded();
|
||||
expect((await searchEntries(db, '100%', 'leo')).map((e) => e.content)).toEqual(['毛利率 100% 達成']);
|
||||
expect((await searchEntries(db, 'owner_id', 'leo')).map((e) => e.content)).toEqual([
|
||||
'owner_id 是租戶隔離的欄位',
|
||||
]);
|
||||
// 單打一個符號：以前是全庫，現在是「真的含那個字的那一筆」
|
||||
expect((await searchEntries(db, '%', 'leo')).map((e) => e.content)).toEqual(['毛利率 100% 達成']);
|
||||
expect((await searchEntries(db, '_', 'leo')).map((e) => e.content).sort()).toEqual(
|
||||
['owner_id 是租戶隔離的欄位', '路徑 C:\\_temp 底下'].sort(),
|
||||
);
|
||||
});
|
||||
});
|
||||
|
||||
describe('② 邊界：跳脫字元本身（`\\`）也必須跳脫', () => {
|
||||
// 為什麼這組必須存在：宣告了 ESCAPE 之後，`\` 就變成 pattern 裡有意義的字元。
|
||||
// 只跳脫 % 和 _、不跳脫 `\`，等於用新的漏洞換掉舊的——而且更難發現，因為它
|
||||
// **不會報錯**，只會靜靜地把後面那個字吃掉、去找一個使用者沒打過的字串。
|
||||
const halfDone = (q: string) => `%${q.replace(/[%_]/g, (c) => '\\' + c)}%`; // 只跳脫 %/_ 的假想修法
|
||||
|
||||
it('打 `C:\\`：不跳脫反斜線的話尾巴變成「字面 %」，反而找不到任何真正含 `C:\\` 的內容', async () => {
|
||||
const db = await seeded();
|
||||
// pattern `%C:\%` ⇒ 尾巴的 `\%` 被讀成「字面的 %」⇒ 實際去找 `C:%`，庫裡沒有 ⇒ 全漏
|
||||
expect(await likeHits(db, halfDone('C:\\'), true)).toEqual([]);
|
||||
expect(await likeHits(db, buildContentLike('C:\\').params[0], true)).toEqual([
|
||||
'路徑 C:\\_temp 底下',
|
||||
'路徑 C:\\Xtemp 底下',
|
||||
]);
|
||||
});
|
||||
|
||||
it('打 `C:\\_temp`：反斜線沒跳脫 ⇒ 它把 `_` 的跳脫吃掉，萬用字元漏回來、撈到不相干的', async () => {
|
||||
const db = await seeded();
|
||||
// `%C:\\_temp%`：`\\` 先被讀成「字面 \」，後面那個 `_` 就變回萬用字元 ⇒ C:\Xtemp 也中
|
||||
expect(await likeHits(db, halfDone('C:\\_temp'), true)).toEqual([
|
||||
'路徑 C:\\_temp 底下',
|
||||
'路徑 C:\\Xtemp 底下', // ← 使用者沒打過這個字
|
||||
]);
|
||||
expect(await likeHits(db, buildContentLike('C:\\_temp').params[0], true)).toEqual([
|
||||
'路徑 C:\\_temp 底下',
|
||||
]);
|
||||
});
|
||||
|
||||
it('打 `100\\%`：三個都不跳脫 ⇒ `\\%` 被讀成「字面 %」⇒ 去找 `100%`，跟他打的不一樣', async () => {
|
||||
const db = await seeded();
|
||||
// 原始寫法（一個都不跳脫）＝ pattern `%100\%%`：`\%`＝字面 %、尾巴那個 `%`＝萬用字元
|
||||
expect(await likeHits(db, legacyPattern('100\\%'), true)).toEqual(['毛利率 100% 達成']); // ← 找錯東西
|
||||
// 正解：庫裡沒有字面的 `100\%` ⇒ 就該零命中，而不是拿別的東西充數
|
||||
expect(await likeHits(db, buildContentLike('100\\%').params[0], true)).toEqual([]);
|
||||
});
|
||||
|
||||
it('escapeLikeLiteral 只碰這三個字元，且不會把自己剛加的跳脫再跳脫一次', () => {
|
||||
expect(escapeLikeLiteral('100%')).toBe('100\\%');
|
||||
expect(escapeLikeLiteral('owner_id')).toBe('owner\\_id');
|
||||
expect(escapeLikeLiteral('C:\\')).toBe('C:\\\\');
|
||||
expect(escapeLikeLiteral('%_\\')).toBe('\\%\\_\\\\'); // 三個各自跳脫一次，不是兩次
|
||||
// LIKE 沒有 [] ? * 這些萬用字元（那是 GLOB／別的方言）⇒ 不該白白吃掉 byte 預算
|
||||
expect(escapeLikeLiteral('a[b]?c*d 中文')).toBe('a[b]?c*d 中文');
|
||||
});
|
||||
});
|
||||
|
||||
describe('③ 每個 LIKE 都要帶 ESCAPE 宣告，否則跳脫過的 pattern 反而被當字面', () => {
|
||||
it('buildContentLike／buildSearchScore 產生的謂詞都含 ESCAPE', () => {
|
||||
for (const c of buildContentLike('100%').conds) expect(c).toContain("ESCAPE '\\'");
|
||||
for (const c of buildContentLike('a'.repeat(200)).conds) expect(c).toContain("ESCAPE '\\'");
|
||||
expect(buildSearchScore('Gemini 逃生口').scoreExpr).toContain("ESCAPE '\\'");
|
||||
expect(buildSearchScore('。。。').scoreExpr).toContain("ESCAPE '\\'"); // 一個詞都拆不出來的退路
|
||||
});
|
||||
|
||||
it('沒有任何 `content LIKE ?` 是裸的（漏掉一個就等於那條路沒修）', async () => {
|
||||
const { spy, sqls } = sqlSpy(await seeded());
|
||||
for (const q of ['100%', 'Gemini 逃生口', '。。。', 'a'.repeat(200)]) await searchEntries(spy, q, 'leo');
|
||||
expect(sqls.length).toBeGreaterThan(0);
|
||||
for (const sql of sqls) expect(sql.match(/content LIKE \?(?! ESCAPE)/g) ?? []).toHaveLength(0);
|
||||
});
|
||||
|
||||
it('ESCAPE 宣告本身是合法 SQL（D1＝SQLite；真的跑得起來，不是形狀對而已）', async () => {
|
||||
const db = await seeded();
|
||||
await expect(likeHits(db, '%100\\%%', true)).resolves.toEqual(['毛利率 100% 達成']);
|
||||
});
|
||||
});
|
||||
|
||||
describe('④ 不退化：不含 % _ \\ 的查詢，行為與修改前逐字相同', () => {
|
||||
it('pattern 一個字都沒變（跳脫對這些字串是恆等變換）', () => {
|
||||
for (const q of ['語意檢索', 'arcrun', 'Gemini 逃生口', '為什麼今天額度用完']) {
|
||||
expect(escapeLikeLiteral(q)).toBe(q);
|
||||
}
|
||||
expect(buildContentLike('語意檢索').params).toEqual(['%語意檢索%']);
|
||||
expect(buildSearchScore('arcrun').scoreParams).toEqual(['%arcrun%']);
|
||||
expect(buildSearchScore('語意檢索').legacyShape).toBe(true); // 最熱路徑仍是單一 LIKE
|
||||
});
|
||||
|
||||
it('斷詞（08-10，Arcrun#84 已判定留下）沒被動到：問句照樣拆得開', () => {
|
||||
expect(buildSearchScore('Gemini 逃生口').scoreParams).toEqual(
|
||||
expect.arrayContaining(['%Gemini%', '%逃生口%']),
|
||||
);
|
||||
});
|
||||
});
|
||||
|
||||
describe('⑤ 跳脫會變長 ⇒ byte 預算要用「跳脫後」的長度算，否則退回 2026-08-03 那個 500', () => {
|
||||
it('滿是 % 的長查詢，每個 pattern 仍在 D1 的 50 bytes 上限內', () => {
|
||||
const qs = [
|
||||
'%'.repeat(200), // 每個字元跳脫後變 2 bytes
|
||||
'_'.repeat(60),
|
||||
'\\'.repeat(60),
|
||||
`${'%'.repeat(30)}中文${'_'.repeat(30)}`,
|
||||
'a'.repeat(24) + '%'.repeat(24), // 卡在舊上限附近的混合
|
||||
];
|
||||
for (const q of qs) {
|
||||
for (const p of buildContentLike(q).params) expect(bytes(p)).toBeLessThanOrEqual(MAX_PATTERN);
|
||||
const plan = buildSearchScore(q);
|
||||
expect(plan.scoreParams.length).toBeGreaterThan(0); // 永不空條件（空條件＝WHERE 塌掉）
|
||||
for (const p of plan.scoreParams) expect(bytes(p)).toBeLessThanOrEqual(MAX_PATTERN);
|
||||
}
|
||||
});
|
||||
|
||||
it('48 個 `%`（跳脫前剛好在舊上限內）不會產生 98 bytes 的 pattern', () => {
|
||||
const q = '%'.repeat(48);
|
||||
expect(bytes(q)).toBe(48); // 用舊的算法看，它「在上限內」
|
||||
const m = buildContentLike(q);
|
||||
expect(m.split).toBe(true); // 用跳脫後的長度看，它必須被拆開
|
||||
for (const p of m.params) expect(bytes(p)).toBeLessThanOrEqual(MAX_PATTERN);
|
||||
});
|
||||
|
||||
it('拆片段仍切在字元邊界上，不會把跳脫序列切成半個', async () => {
|
||||
const db = await seeded();
|
||||
for (const p of buildContentLike(`${'%'.repeat(40)}中文${'_'.repeat(40)}`).params) {
|
||||
expect(p).not.toContain('\uFFFD');
|
||||
// 切壞的跳脫序列（尾巴是落單的 `\`）會讓 SQLite 把後面的 `%` 讀成字面 ⇒ 語意錯掉
|
||||
expect(/(^|[^\\])(\\\\)*\\%$/.test(p)).toBe(false);
|
||||
await expect(likeHits(db, p, true)).resolves.toBeDefined(); // 真的送得進 SQLite
|
||||
}
|
||||
});
|
||||
});
|
||||
@@ -16,12 +16,16 @@ import { buildContentLike, searchEntries } from '../src/actions/entry-crud';
|
||||
|
||||
const bytes = (s: string) => new TextEncoder().encode(s).length;
|
||||
const MAX_PATTERN = 50; // D1 上限
|
||||
// 謂詞字串在 Arcrun#94 多了 ESCAPE 宣告（`content LIKE ? ESCAPE '\'`）。這裡跟著改的是
|
||||
// **比對用的常數**，不是放寬檢查——底下仍然逐字相等比對，只是比的是現在正確的那個字串。
|
||||
// pattern 本身（'%語意檢索%'）一個字都沒變：那句話裡沒有 % _ \，跳脫後與原文相同。
|
||||
const LIKE_PRED = "content LIKE ? ESCAPE '\\'";
|
||||
|
||||
describe('buildContentLike：不得產生超過 D1 上限的 LIKE pattern', () => {
|
||||
it('短查詢（≤48 bytes）＝與舊版逐字相同的單一 LIKE', () => {
|
||||
const m = buildContentLike('語意檢索');
|
||||
expect(m.split).toBe(false);
|
||||
expect(m.conds).toEqual(['content LIKE ?']);
|
||||
expect(m.conds).toEqual([LIKE_PRED]);
|
||||
expect(m.params).toEqual(['%語意檢索%']);
|
||||
});
|
||||
|
||||
@@ -43,7 +47,7 @@ describe('buildContentLike：不得產生超過 D1 上限的 LIKE pattern', () =
|
||||
const m = buildContentLike('語意檢索 排名 選頁 雜訊 出處 門檻 正規化 三元組 知識庫');
|
||||
expect(m.split).toBe(true);
|
||||
expect(m.conds.length).toBeGreaterThan(1);
|
||||
expect(m.conds.every((c) => c === 'content LIKE ?')).toBe(true);
|
||||
expect(m.conds.every((c) => c === LIKE_PRED)).toBe(true);
|
||||
expect(m.params).toContain('%語意檢索%');
|
||||
expect(m.conds.length).toBeLessThanOrEqual(6); // 詞數上限
|
||||
});
|
||||
|
||||
@@ -0,0 +1,64 @@
|
||||
# 卡在人類閘前的產物（`Arcrun#89` / `#90` / `#91`）
|
||||
|
||||
> **為什麼這個資料夾存在**：這三樣東西都做完並實測過了，但落地的最後一步是
|
||||
> **終端機裡等人親手打字的互動閘**，AI 打不進去。
|
||||
> 2026-08-11 它們原本只存在於某個 session 的暫存目錄——**那種目錄一關就沒了**。
|
||||
> 先搶進版控，等人有空時再落地。
|
||||
|
||||
---
|
||||
|
||||
## 一、兩份 recipe（`#89`／`#90`）
|
||||
|
||||
`recipes/gitea_put_file.yaml` — 把檔案寫回 Gitea repo。**出貨線有 7 站等它。**
|
||||
`recipes/cf_worker_deploy_simple.yaml` — 部署單檔 Worker（classic 格式）。
|
||||
|
||||
**落地指令**（一份跑一次）：
|
||||
|
||||
```
|
||||
acr recipe push pending-human-gate/recipes/gitea_put_file.yaml
|
||||
```
|
||||
|
||||
跑的時候會停下來要你**親手輸入資源名確認**——那是「把資源變成可被外部呼叫」的暴露同意閘，
|
||||
不是卡住，是設計如此。
|
||||
|
||||
⚠️ **`cf_worker_deploy_simple.yaml` 先別急著推**：`#90` 查出一件結構性的事——
|
||||
recipe 引擎的 body 一律 JSON，而 Cloudflare 上傳 Worker 的 API 要的是原始 JS 或 multipart。
|
||||
⇒ **classic 版只適用於沒有 bindings 的簡單情形**。而實查安裝器那站有 9 把 KV ＋ 一顆 D1，
|
||||
**classic 版幫不上它**。詳見 `Leo/Arcrun#90`。
|
||||
|
||||
### 金鑰（D36）
|
||||
|
||||
兩份 recipe 都只寫名字（`gitea_token`／`cf_api_token`），真身由 credential 中心在執行前回填。
|
||||
對應的 auth-recipe **已經註冊在 leo21c 上**，可以直接查證：
|
||||
|
||||
```
|
||||
curl -s https://arcrun-cypher-executor.leo21c.workers.dev/auth-recipes/gitea
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 二、`hash` 零件（`#91`）
|
||||
|
||||
`hash-component/` — sha256／sha1／md5，hex／base64。出貨線的版本號機制與成品指紋核對都要它。
|
||||
|
||||
**已實測**（tinygo 編出來、wasmtime 真跑，三種演算法都跟系統原生指令**逐位元一致**）。
|
||||
`.wasm` 是 1.3 MB 編譯產物，**沒有進版控**——要驗自己重編：
|
||||
|
||||
```
|
||||
cd pending-human-gate/hash-component && tinygo build -target=wasi -o /tmp/hash.wasm main.go
|
||||
echo '{"algorithm":"sha256","input":"hello"}' | wasmtime /tmp/hash.wasm
|
||||
printf 'hello' | shasum -a 256 # 兩者應該一致
|
||||
```
|
||||
|
||||
**落地要走零件投稿流程**（D27／D28）：`docs/component-pr-review-standard.md` 的 checklist
|
||||
＋ 人在終端機互動跑 `scripts/component-arm.sh`。
|
||||
🔴 `registry/components/` 底下有機械閘（`component-guard.sh`）擋著 AI 直接寫入——**那是刻意的**，
|
||||
所以這份放在 `pending-human-gate/`，不是放在它最終該去的位置。
|
||||
|
||||
---
|
||||
|
||||
## 落地之後
|
||||
|
||||
三樣都上去之後，`Arcrun#89`／`#91` 才能從 **◐ 半通** 變 **✅**——
|
||||
而判準是**貼一次真實的執行輸出**（recipe 對某個測試檔案回 2xx、零件在真端點上跑出正確雜湊），
|
||||
不是「推上去了」。
|
||||
@@ -0,0 +1,74 @@
|
||||
canonical_id: "hash"
|
||||
display_name: "計算雜湊"
|
||||
category: "logic"
|
||||
version: "v1"
|
||||
wasi_target: "preview1"
|
||||
stability: "floating"
|
||||
runtime_compat:
|
||||
- "cf-workers"
|
||||
- "workerd"
|
||||
- "wazero"
|
||||
constraints:
|
||||
max_size_kb: 2048
|
||||
max_cold_start_ms: 50
|
||||
no_network_syscall: true
|
||||
no_filesystem_syscall: true
|
||||
io_model: "stdin_stdout_json"
|
||||
input_schema:
|
||||
type: object
|
||||
required: [input]
|
||||
properties:
|
||||
algorithm:
|
||||
type: string
|
||||
enum: [sha256, sha1, md5]
|
||||
description: 雜湊演算法，預設 sha256
|
||||
input:
|
||||
type: string
|
||||
description: 要算雜湊的內容
|
||||
encoding:
|
||||
type: string
|
||||
enum: [hex, base64]
|
||||
description: 輸出編碼，預設 hex
|
||||
output_schema:
|
||||
type: object
|
||||
properties:
|
||||
success:
|
||||
type: boolean
|
||||
data:
|
||||
type: object
|
||||
properties:
|
||||
result:
|
||||
type: string
|
||||
algorithm:
|
||||
type: string
|
||||
encoding:
|
||||
type: string
|
||||
gherkin_tests:
|
||||
- scenario: "sha256 hex（預設）"
|
||||
given: '{"algorithm":"sha256","input":"hello"}'
|
||||
then_contains: '"result":"2cf24dba5fb0a30e26e83b2ac5b9e29e1b161e5c1fa7425e73043362938b9824"'
|
||||
- scenario: "sha1"
|
||||
given: '{"algorithm":"sha1","input":"hello"}'
|
||||
then_contains: '"result":"aaf4c61ddcc5e8a2dabede0f3b482cd9aea9434d"'
|
||||
- scenario: "md5"
|
||||
given: '{"algorithm":"md5","input":"hello"}'
|
||||
then_contains: '"result":"5d41402abc4b2a76b9719d911017c592"'
|
||||
- scenario: "base64 編碼"
|
||||
given: '{"algorithm":"sha256","input":"hello","encoding":"base64"}'
|
||||
then_contains: '"result":"LPJNul+wow4m6DsqxbninhsWHlwfp0JecwQzYpOLmCQ="'
|
||||
- scenario: "預設 algorithm=sha256"
|
||||
given: '{"input":"hello"}'
|
||||
then_contains: '"algorithm":"sha256"'
|
||||
- scenario: "不支援的 algorithm"
|
||||
given: '{"algorithm":"crc32","input":"hello"}'
|
||||
then_contains: '{"success":false'
|
||||
tags: [builtin, logic, hash, checksum, versioning]
|
||||
description: >-
|
||||
計算內容雜湊（sha256/sha1/md5，輸出 hex 或 base64）。純計算，無網路/檔案 syscall。
|
||||
用途：出貨線版本號機制（Leo/Arcrun#91）——內容一變雜湊必變，是「改了東西版本沒動」在結構上
|
||||
不可能發生的機制來源；build 站核對官方成品指紋也用它。
|
||||
config_example: |
|
||||
compute_hash: # 節點名稱（可自訂）
|
||||
algorithm: "sha256" # 演算法（選填，預設 sha256），可選值：sha256/sha1/md5
|
||||
input: "{{ctx.bundle_content}}" # 要算雜湊的內容（必填）
|
||||
encoding: "hex" # 輸出編碼（選填，預設 hex），可選值：hex/base64
|
||||
@@ -0,0 +1,89 @@
|
||||
// hash — 計算內容雜湊（純計算，無網路/檔案 syscall）
|
||||
// 支援: sha256, sha1, md5；輸出編碼: hex（預設）, base64
|
||||
// 用途：出貨線版本號機制（Leo/Arcrun#91）——內容一變雜湊必變，
|
||||
// 是「改了東西版本沒動」在結構上不可能發生的機制來源。
|
||||
//
|
||||
//go:build tinygo
|
||||
|
||||
package main
|
||||
|
||||
import (
|
||||
"crypto/md5"
|
||||
"crypto/sha1"
|
||||
"crypto/sha256"
|
||||
"encoding/base64"
|
||||
"encoding/hex"
|
||||
"encoding/json"
|
||||
"io"
|
||||
"os"
|
||||
)
|
||||
|
||||
type Input struct {
|
||||
Algorithm string `json:"algorithm"` // sha256（預設）| sha1 | md5
|
||||
Input string `json:"input"`
|
||||
Encoding string `json:"encoding"` // hex（預設）| base64
|
||||
}
|
||||
|
||||
func main() {
|
||||
raw, err := io.ReadAll(os.Stdin)
|
||||
if err != nil {
|
||||
writeError("failed to read stdin: " + err.Error())
|
||||
return
|
||||
}
|
||||
var in Input
|
||||
if err := json.Unmarshal(raw, &in); err != nil {
|
||||
writeError("invalid input JSON: " + err.Error())
|
||||
return
|
||||
}
|
||||
|
||||
algorithm := in.Algorithm
|
||||
if algorithm == "" {
|
||||
algorithm = "sha256"
|
||||
}
|
||||
encoding := in.Encoding
|
||||
if encoding == "" {
|
||||
encoding = "hex"
|
||||
}
|
||||
|
||||
var sum []byte
|
||||
switch algorithm {
|
||||
case "sha256":
|
||||
h := sha256.Sum256([]byte(in.Input))
|
||||
sum = h[:]
|
||||
case "sha1":
|
||||
h := sha1.Sum([]byte(in.Input))
|
||||
sum = h[:]
|
||||
case "md5":
|
||||
h := md5.Sum([]byte(in.Input))
|
||||
sum = h[:]
|
||||
default:
|
||||
writeError("不支援的 algorithm: " + algorithm + "（支援 sha256/sha1/md5）")
|
||||
return
|
||||
}
|
||||
|
||||
var result string
|
||||
switch encoding {
|
||||
case "hex":
|
||||
result = hex.EncodeToString(sum)
|
||||
case "base64":
|
||||
result = base64.StdEncoding.EncodeToString(sum)
|
||||
default:
|
||||
writeError("不支援的 encoding: " + encoding + "（支援 hex/base64）")
|
||||
return
|
||||
}
|
||||
|
||||
out, _ := json.Marshal(map[string]interface{}{
|
||||
"success": true,
|
||||
"data": map[string]interface{}{
|
||||
"result": result,
|
||||
"algorithm": algorithm,
|
||||
"encoding": encoding,
|
||||
},
|
||||
})
|
||||
os.Stdout.Write(out)
|
||||
}
|
||||
|
||||
func writeError(msg string) {
|
||||
out, _ := json.Marshal(map[string]interface{}{"success": false, "error": msg})
|
||||
os.Stdout.Write(out)
|
||||
}
|
||||
@@ -0,0 +1,11 @@
|
||||
name = "arcrun-hash"
|
||||
main = "src/index.ts"
|
||||
compatibility_date = "2025-02-19"
|
||||
workers_dev = true
|
||||
|
||||
[vars]
|
||||
COMPONENT_ID = "hash"
|
||||
|
||||
[[routes]]
|
||||
pattern = "hash.arcrun.dev/*"
|
||||
zone_name = "arcrun.dev"
|
||||
@@ -0,0 +1,21 @@
|
||||
canonical_id: cf_worker_deploy_simple
|
||||
display_name: Cloudflare Worker Deploy (single-file, classic format)
|
||||
description: >-
|
||||
PUT /accounts/{account_id}/workers/scripts/{script_name} 部署單檔 Worker（CF 「classic Service
|
||||
Worker」格式，非 ES module）。_path 帶 /{account_id}/workers/scripts/{script_name}。
|
||||
auth: cloudflare_workers static_key（Bearer token）。
|
||||
⚠️ 已知限制（誠實記錄，非隱藏債）：這個 recipe 走 arcrun 的「recipe body 一律 JSON.stringify」
|
||||
引擎行為（cypher-executor/src/lib/component-loader.ts makeRecipeRunner），CF 這支 API 卻要求
|
||||
body 是「原始 JS 原始碼」或（現代 ES module + bindings 情境）multipart/form-data——兩者都不是
|
||||
JSON。純 recipe 模型在這支 API 上天生對不上，這不是可以在 recipe schema 裡修的事。
|
||||
正解＝07-thin-shell §3.5 自力救濟階梯「第三方 API 缺能力→ workflow/code-node 補丁」：
|
||||
用 http_request 零件直接打（body 走它的原生 string 模式，不透過本 recipe wrapper），
|
||||
header 用 {{credential.cf_api_token}} 直接內插（D36 credential 模板，不必經過 recipe/auth_service
|
||||
間接層）；若目標 Worker 需要 bindings/compatibility_flags（現代 ES module 格式常態），
|
||||
上游加一個 code 節點組出 multipart/form-data body（純資料編碼，非業務邏輯，合法局部整形）。
|
||||
本 recipe 保留給「目標帳號仍接受 classic 格式」的簡單場景；不保證覆蓋所有部署情境。
|
||||
endpoint: https://api.cloudflare.com/client/v4/accounts{{_path}}
|
||||
method: PUT
|
||||
auth_service: cloudflare_workers
|
||||
headers:
|
||||
Content-Type: application/javascript
|
||||
@@ -0,0 +1,11 @@
|
||||
canonical_id: gitea_put_file
|
||||
display_name: Gitea Put File (Create/Update)
|
||||
description: >-
|
||||
Gitea PUT /repos/{owner}/{repo}/contents/{filepath} 建立或更新檔案並產生 commit。
|
||||
_path 帶完整路徑（例 /Leo/arcrun-rag-bundles/contents/manifest.json，filepath 各段需 URL-encode）。
|
||||
body 帶 {message, content(base64), branch, sha(更新既有檔案時必填，取自前一次 GET 的 content.sha；
|
||||
新建檔案時不帶)}。auth: gitea static_key，header Authorization: token <TOKEN>（D36：定義只留
|
||||
{{credential.*}} 名字，真身由 credential 中心於執行前回填，非本 recipe 職責）。
|
||||
endpoint: https://git.uncle6.me/api/v1/repos{{_path}}
|
||||
method: PUT
|
||||
auth_service: gitea
|
||||
@@ -44,3 +44,34 @@ leo 否決②——「**藏書地圖就是 arcrun 的最重要功能，讓 AI
|
||||
不報錯。`mcp/tests/unit/tools/kbdb-map.test.ts` 新增 1 案釘住舊謊言不再出現（18/18 全綠）。
|
||||
tsc 兩包乾淨。實測：`yuga3bse` 租戶（從未 backfill 過、真實 triplet 資料橫跨 5 個庫）改前
|
||||
`kbdb_get_map` 回 `{libraries:[],count:0}`——改動待部署後需重新實測驗證非空。
|
||||
|
||||
### M3 止血（2026-08-11，Arcrun#87，總管交辦「動工前的量測」comment 第四節）
|
||||
|
||||
**08-08 那次改法本身留了一個判準缺口，這次補上**：`ensureFreshLibraryMaps` 比對
|
||||
「即時三元組數」（`liveTripletCountsByLibrary`）與「快取的地圖數」（`recomputeLibraryMap`
|
||||
算出來寫進去的），但兩邊的 status 過濾不一致——`recomputeLibraryMap` 只算
|
||||
`COALESCE(status,'active')='active'`，`liveTripletCountsByLibrary` 完全不濾 status。
|
||||
只要一個庫裡混了任何一筆 superseded/deprecated triplet，兩邊數字就永遠對不上，
|
||||
`ensureFreshLibraryMaps` 就永遠判定 stale ⇒ **每次讀地圖都觸發重算，每次都新建一筆
|
||||
library_map record（superseded 舊的），無止盡寫 D1**——且加劇 `recomputeLibraryMap`
|
||||
本身非原子 supersede 的既有競態（更高重算頻率 = 更高並發重算機率），是 `kb` 庫
|
||||
全部 44 筆被標 superseded、`notes` 庫兩筆同時 active（`arcrun-rag#50`）這兩個症狀的
|
||||
共同根因之一。
|
||||
|
||||
**修法**：`liveTripletCountsByLibrary`（`kbdb/src/actions/library-map.ts`）的 SQL 改成
|
||||
先 pivot 出每筆 triplet record 的 status，再套用與 `recomputeLibraryMap` 逐字一致的
|
||||
`COALESCE(status,'active')='active'` 過濾，兩邊判準對齊後，資料未變動時兩個計數必然相等，
|
||||
stale 判定回歸「真的有資料變動才 stale」。
|
||||
|
||||
**驗證**：新增迴歸案「Arcrun#87 迴歸：superseded triplet 存在時，連讀兩次地圖不會再次
|
||||
觸發重算」（`kbdb/tests/library-map.test.ts`，19/19 全綠）；反向驗證過——把同一顆測試跑在
|
||||
修前的舊 SQL 上會失敗（`library_map` record 數 2 vs 期望 1），證明測試真的釘住這個 bug、
|
||||
不是空氣測試。另外用 leo21c MCP 連線（`bfezv28v`）連讀兩次 `kbdb_get_map()`（無中間寫入）
|
||||
獨立重現修前症狀：`general` 庫 `updated_at` 從 `1786457080` 前進到 `1786457114`。
|
||||
|
||||
**尚待**：改動只在分支 `fix/library-map-recompute-loop-87-v3`（未 push、未部署 leo21c）；
|
||||
既有 100 筆 library_map 殘骸（`kb` 44 筆 superseded／`general` 41／`notes` 2）未清——
|
||||
清除需要一個目前不存在的 DELETE 通道（cypher-executor 的 `/kbdb/records/:id` proxy 只有
|
||||
GET/POST/PATCH，無 DELETE；kbdb base 自己雖有 `DELETE /records/:recordId` 但走 leo21c
|
||||
需要 `KBDB_INTERNAL_TOKEN`，非 CC 可持有的機密）——待總管部署本修法＋視情況補一支
|
||||
DELETE proxy 後再清。
|
||||
|
||||
Reference in New Issue
Block a user