Compare commits
13 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 uncle6me-web
|
45a546a686 | ||
|
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
|
525faaf5d0 |
@@ -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": [
|
||||
|
||||
+23
-40
@@ -10,7 +10,6 @@ import chalk from 'chalk';
|
||||
import { saveConfig, type ArcrunConfig } from '../lib/config.js';
|
||||
import { CfAccountClient } from '../lib/cf-api.js';
|
||||
import {
|
||||
REQUIRED_KV_NAMESPACES,
|
||||
downloadAndDeploy,
|
||||
type DeployContext,
|
||||
} from '../lib/deploy.js';
|
||||
@@ -135,7 +134,7 @@ async function initStandard(rl: ReturnType<typeof createInterface>): Promise<voi
|
||||
|
||||
/**
|
||||
* Self-hosted installer：用戶只提供 CF Account ID + API Token，其餘自動。
|
||||
* 驗 token → 建 KV（冪等，數量見 REQUIRED_KV_NAMESPACES）→ 查 subdomain → 下載 release 部署 Worker
|
||||
* 驗 token → 查 subdomain → 下載部署物 → 解析資源（沿用既有／必要才新建）→ 部署 Worker
|
||||
* → seed auth+api recipe → 寫 config → 印手動 secret 提示。
|
||||
* SDD：.agents/specs/arcrun/sdk-and-website/self-hosted-init.md
|
||||
*/
|
||||
@@ -185,41 +184,13 @@ async function initSelfHosted(
|
||||
process.exit(1);
|
||||
}
|
||||
|
||||
// 2. 建 KV namespace（冪等）
|
||||
// 2. KV / D1 / Vectorize 不在這裡預先建（Arcrun#97）。
|
||||
// 舊版在這一步「照名字 ensure」一輪再往下傳，acr update 沿用同一段程式碼
|
||||
// ⇒ 對一台安裝器裝出來的實例（資源名字不同）等於每次更新都重建一整套空的綁上去。
|
||||
// 現在資源解析統一在 downloadAndDeploy 內：**先看已部署的 worker 綁著什麼**，
|
||||
// 對得上就沿用、確定沒人綁過才建、說不準就停手。init 走 mode:'init'（允許從零建起）。
|
||||
// 不建 R2：R2 是 dead storage（registry-canon Phase 1.5），且 CF R2 首次啟用強制綁信用卡，
|
||||
// 違背 arcrun「開源免費自架，Workers + KV 免費額度即可運行」核心理念（壓測 2026-06-04 #3）。
|
||||
const kvNamespaceIds: Record<string, string> = {};
|
||||
try {
|
||||
const existing = await cf.listKvNamespaces();
|
||||
for (const title of REQUIRED_KV_NAMESPACES) {
|
||||
process.stdout.write(chalk.gray(` → KV ${title}...`));
|
||||
const id = await cf.ensureKvNamespace(title, existing);
|
||||
kvNamespaceIds[title] = id;
|
||||
console.log(chalk.green(' ✓'));
|
||||
}
|
||||
} catch (e) {
|
||||
console.log(chalk.yellow(`\n ✗ 建立資源失敗：${e instanceof Error ? e.message : e}\n`));
|
||||
process.exit(1);
|
||||
}
|
||||
|
||||
// 2.5 build D1 for KBDB Base (atomic universal table). Free on Workers Free, no credit card
|
||||
// (kbdb-base SDD Q4). idempotent: reuse if exists.
|
||||
let d1DatabaseId = '';
|
||||
try {
|
||||
process.stdout.write(chalk.gray(' → D1 arcrun-kbdb...'));
|
||||
d1DatabaseId = await cf.ensureD1Database('arcrun-kbdb');
|
||||
console.log(chalk.green(' ✓'));
|
||||
} catch (e) {
|
||||
const em = e instanceof Error ? e.message : String(e);
|
||||
console.log(chalk.yellow(`\n ⚠ D1 build failed (${em})`));
|
||||
if (/auth/i.test(em)) {
|
||||
// 最常見根因：CF token 沒勾 D1 權限（KV/Worker 建得起來但 D1 報 Authentication error）。
|
||||
console.log(chalk.yellow(' 多半是 CF token 缺 D1 權限 → 去 token 補勾「Account / D1 / Edit」'));
|
||||
console.log(chalk.gray(' 重產 token 填回 .env 後跑 acr update。D1 存 workflow/recipe，沒它後續會受限。'));
|
||||
} else {
|
||||
console.log(chalk.gray(' KBDB Base 暫不可用，可 acr update 重試。'));
|
||||
}
|
||||
}
|
||||
|
||||
// 3. 查 workers.dev subdomain（cypher-executor WORKER_SUBDOMAIN 用）
|
||||
let workerSubdomain = '';
|
||||
@@ -245,8 +216,20 @@ async function initSelfHosted(
|
||||
console.log(chalk.gray('\n → 下載部署物 + 部署 Worker（從 GitHub 拉預編譯 wasm，用你的 CF token 部署）...'));
|
||||
// selfHosted: true → deploy 注入 MULTI_TENANT="false"（mcp-account-source §5.5，修 MCP 401）。
|
||||
// init.ts 這條本就是 --self-hosted 分支（config.mode 稍後寫 'self-hosted'）。
|
||||
const deployCtx: DeployContext = { accountId, apiToken: cfApiToken, workerSubdomain, kvNamespaceIds, d1DatabaseId, selfHosted: true, kbdbEmbed };
|
||||
const deploy = await downloadAndDeploy(deployCtx);
|
||||
const deployCtx: DeployContext = { accountId, apiToken: cfApiToken, workerSubdomain, selfHosted: true, kbdbEmbed };
|
||||
const deploy = await downloadAndDeploy(deployCtx, 'main', { mode: 'init', api: cf });
|
||||
|
||||
// 資源解析喊停（例：這台其實已經裝過、但某顆綁著的資源不見了）→ 什麼都沒建、什麼都沒部。
|
||||
if (deploy.blocked) {
|
||||
console.log(chalk.yellow('\n ⚠ 安裝沒有進行，你的 Cloudflare 帳號維持原樣。\n'));
|
||||
console.log(' ' + deploy.message.split('\n').join('\n '));
|
||||
console.log('');
|
||||
process.exit(1);
|
||||
}
|
||||
|
||||
// 實際用上的資源（沿用既有的，或這次新建的）——寫 config / 驗收都以這份為準，不再自己查名字。
|
||||
const kvNamespaceIds = deployCtx.kvNamespaceIds ?? {};
|
||||
const d1DatabaseId = deployCtx.d1DatabaseId ?? '';
|
||||
const cypherUrl = deploy.cypherExecutorUrl
|
||||
?? (workerSubdomain ? `https://arcrun-cypher-executor.${workerSubdomain}.workers.dev` : '');
|
||||
// self-hosted 自己的 MCP worker URL（mcp-account-source §3：.mcp.json 指自己，不 fallback 官方）。
|
||||
@@ -290,8 +273,8 @@ async function initSelfHosted(
|
||||
// + 給一鍵補裝指令（不靜默印灰字）。假綠零容忍（mindset §7）：看實際狀態，非看 config 寫了沒。
|
||||
const verify = await verifyInstall({
|
||||
cf,
|
||||
requiredKv: REQUIRED_KV_NAMESPACES,
|
||||
expectD1Name: d1DatabaseId ? 'arcrun-kbdb' : undefined,
|
||||
kvNamespaceIds,
|
||||
d1DatabaseId: d1DatabaseId || undefined,
|
||||
cypherUrl,
|
||||
});
|
||||
printPreflight('安裝驗收（裝完檢查）', verify.items);
|
||||
@@ -301,7 +284,7 @@ async function initSelfHosted(
|
||||
}
|
||||
|
||||
// 結果回報（誠實：部分失敗時明說，不假綠 — mindset §7）
|
||||
console.log(chalk.green(`\n ✓ Cloudflare 資源就緒（${REQUIRED_KV_NAMESPACES.length} KV，免費額度即可，無需綁卡）`));
|
||||
console.log(chalk.green(`\n ✓ Cloudflare 資源就緒（${Object.keys(kvNamespaceIds).length} KV，免費額度即可，無需綁卡）`));
|
||||
console.log(chalk.green(' ✓ 設定寫入 ~/.arcrun/config.yaml'));
|
||||
console.log(chalk.green(' ✓ 建立 credentials.yaml'));
|
||||
|
||||
|
||||
+17
-36
@@ -14,11 +14,9 @@
|
||||
|
||||
import chalk from 'chalk';
|
||||
import { loadConfig } from '../lib/config.js';
|
||||
import { CfAccountClient } from '../lib/cf-api.js';
|
||||
import {
|
||||
wranglerAvailable,
|
||||
downloadAndDeploy,
|
||||
REQUIRED_KV_NAMESPACES,
|
||||
type DeployContext,
|
||||
} from '../lib/deploy.js';
|
||||
|
||||
@@ -44,43 +42,15 @@ export async function cmdUpdate(opts: { force?: boolean } = {}): Promise<void> {
|
||||
|
||||
console.log(chalk.bold('\n acr update — 拉新 release 並重新部署\n'));
|
||||
|
||||
// 重新解析「全部」KV namespace id（冪等：已存在則重用），不只 config 存的兩個。
|
||||
// 壓測 §4.1.3：舊版 update 只注入 WEBHOOKS+CREDENTIALS_KV，其餘 6 個注入成空字串 →
|
||||
// 重部署反而可能弄壞需要 RECIPES/EXEC_CONTEXT/... 的 worker。改為與 init 同樣全建妥。
|
||||
const cf = new CfAccountClient(config.cloudflare_account_id, config.cf_api_token);
|
||||
const kvNamespaceIds: Record<string, string> = {};
|
||||
try {
|
||||
const existing = await cf.listKvNamespaces();
|
||||
for (const title of REQUIRED_KV_NAMESPACES) {
|
||||
kvNamespaceIds[title] = await cf.ensureKvNamespace(title, existing);
|
||||
}
|
||||
} catch (e) {
|
||||
console.log(chalk.yellow(`\n ✗ 解析 KV namespace 失敗：${e instanceof Error ? e.message : e}\n`));
|
||||
process.exit(1);
|
||||
}
|
||||
|
||||
// D1（KBDB Base）冪等補建——之前只在 init 建，update 漏了，導致「init 時 D1 失敗（如 token 缺權限）
|
||||
// → 補好權限後沒有任何指令會補建 D1」（壓測 2026-06-09：D1 一直建不起來的真根因）。
|
||||
// update 既是「冪等重部署」就該與 init 一致把 D1 也 ensure 上。
|
||||
let d1DatabaseId = '';
|
||||
try {
|
||||
process.stdout.write(chalk.gray(' → D1 arcrun-kbdb（冪等）...'));
|
||||
d1DatabaseId = await cf.ensureD1Database('arcrun-kbdb');
|
||||
console.log(chalk.green(' ✓'));
|
||||
} catch (e) {
|
||||
const em = e instanceof Error ? e.message : String(e);
|
||||
console.log(chalk.yellow(` ⚠ ${em}`));
|
||||
if (/auth/i.test(em)) {
|
||||
console.log(chalk.yellow(' CF token 缺 D1 權限 → 補勾「Account / D1 / Edit」重產 token 填回 .env 再 acr update'));
|
||||
}
|
||||
}
|
||||
|
||||
// 🔴 Arcrun#97：這裡**曾經**先「照名字 ensure」一輪 KV + D1 再往下傳。
|
||||
// binding 名（WEBHOOKS）被當成 CF 上的資源標題去找，安裝器建的資源不叫那個名字
|
||||
// ⇒ 每次都對不上 ⇒ 每次都新建一顆空的綁上去 ⇒ 使用者的工作流／登入／子庫從畫面上消失。
|
||||
// 現在資源解析整段搬進 downloadAndDeploy：先讀「你已部署的 worker 現在綁著什麼」再決定，
|
||||
// 而且是**下載完、看得到這版要哪些 binding 之後**才決定，不再由這裡預先造一批。
|
||||
const ctx: DeployContext = {
|
||||
accountId: config.cloudflare_account_id,
|
||||
apiToken: config.cf_api_token,
|
||||
workerSubdomain: extractSubdomain(config.cypher_executor_url),
|
||||
kvNamespaceIds,
|
||||
d1DatabaseId: d1DatabaseId || undefined,
|
||||
// self-hosted → 注入 MULTI_TENANT="false"（mcp-account-source §5.5，修 acr update 部署的 MCP 401）。
|
||||
// config 源頭：init 寫 multi_tenant:false + mode:'self-hosted'。acr update 只在 self-hosted 跑。
|
||||
selfHosted: config.mode === 'self-hosted' || config.multi_tenant === false,
|
||||
@@ -93,7 +63,18 @@ export async function cmdUpdate(opts: { force?: boolean } = {}): Promise<void> {
|
||||
kbdbEmbed: config.kbdb_embed !== false,
|
||||
};
|
||||
|
||||
const result = await downloadAndDeploy(ctx, 'main', { force: opts.force });
|
||||
// mode:'update' → 資源解析在「一顆該更新的 worker 都找不到」時會停手而不是重建一整套
|
||||
//（Arcrun#97 的另一道門：名字對不上時別假裝這是全新安裝）。
|
||||
const result = await downloadAndDeploy(ctx, 'main', { force: opts.force, mode: 'update' });
|
||||
|
||||
// 資源解析階段喊停：什麼都沒建、什麼都沒部。原文照印，然後非零離開——
|
||||
// 不能混進「部分失敗」的黃字裡帶過（那正是使用者不會發現的那種失敗）。
|
||||
if (result.blocked) {
|
||||
console.log(chalk.yellow('\n ⚠ 更新沒有進行，你的實例維持原樣。\n'));
|
||||
console.log(' ' + result.message.split('\n').join('\n '));
|
||||
console.log('');
|
||||
process.exit(1);
|
||||
}
|
||||
|
||||
if (result.implemented) {
|
||||
// message 含部分失敗清單（「部署 X/Y 成功，N 失敗：✗ ...」）——必須印出來，
|
||||
|
||||
+103
-14
@@ -3,6 +3,8 @@
|
||||
* 使用 CF REST API 直接存取用戶的 KV namespace，不依賴 Wrangler CLI
|
||||
*/
|
||||
|
||||
import type { LiveBinding, ResourceApi, ScriptBindings } from './resource-resolver.js';
|
||||
|
||||
const CF_API_BASE = 'https://api.cloudflare.com/client/v4';
|
||||
|
||||
export interface CfKvClientOptions {
|
||||
@@ -83,7 +85,7 @@ export class CfKvClient {
|
||||
* 與 CfKvClient（綁單一 namespace 的 KV 操作）職責不同——這個是帳號層級的資源管理。
|
||||
* 對應 SDD：.agents/specs/arcrun/sdk-and-website/self-hosted-init.md §3 step 1-2
|
||||
*/
|
||||
export class CfAccountClient {
|
||||
export class CfAccountClient implements ResourceApi {
|
||||
private accountBase: string;
|
||||
private headers: Record<string, string>;
|
||||
|
||||
@@ -96,6 +98,16 @@ export class CfAccountClient {
|
||||
}
|
||||
|
||||
private async cf<T>(path: string, init?: RequestInit): Promise<T> {
|
||||
const { ok, status, result, error } = await this.cfRaw<T>(path, init);
|
||||
if (!ok) throw new Error(`CF API ${path} 失敗：${error ?? `HTTP ${status}`}`);
|
||||
return result as T;
|
||||
}
|
||||
|
||||
/** 同 cf()，但把 HTTP status 交回呼叫端自己判斷（要區分「404 不存在」和「其他錯誤」時用）。 */
|
||||
private async cfRaw<T>(
|
||||
path: string,
|
||||
init?: RequestInit,
|
||||
): Promise<{ ok: boolean; status: number; result?: T; error?: string }> {
|
||||
const res = await fetch(`${this.accountBase}${path}`, {
|
||||
...init,
|
||||
headers: { ...this.headers, ...(init?.headers ?? {}) },
|
||||
@@ -104,10 +116,13 @@ export class CfAccountClient {
|
||||
| { success: boolean; result: T; errors?: Array<{ message: string }> }
|
||||
| null;
|
||||
if (!res.ok || !data?.success) {
|
||||
const msg = data?.errors?.map(e => e.message).join('; ') ?? `HTTP ${res.status}`;
|
||||
throw new Error(`CF API ${path} 失敗：${msg}`);
|
||||
return {
|
||||
ok: false,
|
||||
status: res.status,
|
||||
error: data?.errors?.map(e => e.message).filter(Boolean).join('; ') || `HTTP ${res.status}`,
|
||||
};
|
||||
}
|
||||
return data.result;
|
||||
return { ok: true, status: res.status, result: data.result };
|
||||
}
|
||||
|
||||
/** 驗證 token 能存取此 account（權限不足會在後續建立操作報錯，這裡先確認 account 可達）。*/
|
||||
@@ -126,12 +141,16 @@ export class CfAccountClient {
|
||||
return map;
|
||||
}
|
||||
|
||||
/** 建立 KV namespace（若同名已存在則回傳既有 id，冪等）。*/
|
||||
async ensureKvNamespace(title: string, existing?: Map<string, string>): Promise<string> {
|
||||
const known = existing ?? (await this.listKvNamespaces());
|
||||
const found = known.get(title);
|
||||
if (found) return found;
|
||||
|
||||
/**
|
||||
* 無條件新建一顆 KV namespace。
|
||||
*
|
||||
* 🔴 Arcrun#97：這裡**故意沒有**「找不到同名就順手建一顆」的 ensure 版本。
|
||||
* 「照名字找 → 找不到 → 新建 → 綁上去」正是把使用者實例洗成空的那條路
|
||||
* （安裝器取的名字跟我們的 binding 名不一樣，永遠對不上 ⇒ 每次更新都新建）。
|
||||
* 要不要建，一律先經過 resource-resolver 的 planResources 判斷；那裡只有在
|
||||
* 「確定沒有任何已部署的 worker 綁過這個 binding」時才會排進 create。
|
||||
*/
|
||||
async createKvNamespace(title: string): Promise<string> {
|
||||
const result = await this.cf<{ id: string; title: string }>(
|
||||
'/storage/kv/namespaces',
|
||||
{ method: 'POST', body: JSON.stringify({ title }) },
|
||||
@@ -139,6 +158,24 @@ export class CfAccountClient {
|
||||
return result.id;
|
||||
}
|
||||
|
||||
/**
|
||||
* 讀一顆已部署 worker 現在綁著哪些資源——**使用者那側的事實**（Arcrun#97 的唯一真相源）。
|
||||
* CF：`GET /accounts/{id}/workers/scripts/{script}/settings` → `result.bindings[]`。
|
||||
*
|
||||
* - script 不存在（404）→ `{ deployed: false }`，這是「還沒部署」，不是錯誤。
|
||||
* - 其他任何失敗 → throw。呼叫端必須把它當「我不知道」而**不是**「它沒有」——
|
||||
* 把查不到當成不存在，就是 #97 的根因。
|
||||
*/
|
||||
async getScriptBindings(script: string): Promise<ScriptBindings> {
|
||||
const path = `/workers/scripts/${encodeURIComponent(script)}/settings`;
|
||||
const res = await this.cfRaw<{ bindings?: RawWorkerBinding[] }>(path);
|
||||
if (!res.ok) {
|
||||
if (res.status === 404) return { deployed: false, bindings: [] };
|
||||
throw new Error(`讀 ${script} 綁定失敗：${res.error}`);
|
||||
}
|
||||
return { deployed: true, bindings: normalizeBindings(res.result?.bindings ?? []) };
|
||||
}
|
||||
|
||||
/** 查 workers.dev subdomain（cypher-executor WORKER_SUBDOMAIN 用，組對內 component URL）。*/
|
||||
async getWorkersSubdomain(): Promise<string> {
|
||||
const result = await this.cf<{ subdomain: string }>('/workers/subdomain');
|
||||
@@ -153,14 +190,66 @@ export class CfAccountClient {
|
||||
return map;
|
||||
}
|
||||
|
||||
async ensureD1Database(name: string, existing?: Map<string, string>): Promise<string> {
|
||||
const known = existing ?? (await this.listD1Databases());
|
||||
const found = known.get(name);
|
||||
if (found) return found;
|
||||
/** 無條件新建 D1。沒有 ensure 版本，理由同 createKvNamespace（Arcrun#97）。 */
|
||||
async createD1Database(name: string): Promise<string> {
|
||||
const result = await this.cf<{ uuid: string; name: string }>(
|
||||
'/d1/database',
|
||||
{ method: 'POST', body: JSON.stringify({ name }) },
|
||||
);
|
||||
return result.uuid;
|
||||
}
|
||||
|
||||
/** 帳號上現有的 Vectorize index 名單（判斷「綁著的那顆還在不在」用）。 */
|
||||
async listVectorizeIndexes(): Promise<string[]> {
|
||||
const result = await this.cf<Array<{ name: string }>>('/vectorize/v2/indexes');
|
||||
return (result ?? []).map(i => i.name);
|
||||
}
|
||||
|
||||
/**
|
||||
* 新建 KBDB embed 用的 Vectorize index（**bge-m3 = 1024 維 / cosine**，見 deploy.ts 常數說明）。
|
||||
* 已存在（409 / already exists）視為成功——並行或重跑不該炸。沒有 ensure 版本：
|
||||
* 「要不要建」由 planResources 判斷，這裡只負責建（Arcrun#97）。
|
||||
*/
|
||||
async createVectorizeIndex(name: string): Promise<string> {
|
||||
const res = await this.cfRaw<{ name: string }>('/vectorize/v2/indexes', {
|
||||
method: 'POST',
|
||||
body: JSON.stringify({
|
||||
name,
|
||||
config: { dimensions: 1024, metric: 'cosine' },
|
||||
description: 'arcrun KBDB embed module — bge-m3 1024d (issue #7 / #59)',
|
||||
}),
|
||||
});
|
||||
if (res.ok) return name;
|
||||
const detail = (res.error ?? '').toLowerCase();
|
||||
if (res.status === 409 || /already exists|duplicate|conflict/.test(detail)) return name;
|
||||
throw new Error(`建 Vectorize index ${name} 失敗：${res.error}`);
|
||||
}
|
||||
}
|
||||
|
||||
/** CF `/settings` 回的 binding 原始形狀（同一種資源在不同 API 版本欄位名不一，故全都收）。 */
|
||||
interface RawWorkerBinding {
|
||||
type?: string;
|
||||
name?: string;
|
||||
namespace_id?: string;
|
||||
id?: string;
|
||||
database_id?: string;
|
||||
index_name?: string;
|
||||
}
|
||||
|
||||
/** 把 CF 的 binding 陣列收斂成 resolver 認得的三種資源。不認得的型別直接略過。 */
|
||||
function normalizeBindings(raw: RawWorkerBinding[]): LiveBinding[] {
|
||||
const out: LiveBinding[] = [];
|
||||
for (const b of raw) {
|
||||
if (!b?.name) continue;
|
||||
if (b.type === 'kv_namespace') {
|
||||
const value = b.namespace_id ?? b.id;
|
||||
if (value) out.push({ kind: 'kv_namespace', binding: b.name, value });
|
||||
} else if (b.type === 'd1' || b.type === 'd1_database') {
|
||||
const value = b.id ?? b.database_id;
|
||||
if (value) out.push({ kind: 'd1', binding: b.name, value });
|
||||
} else if (b.type === 'vectorize') {
|
||||
if (b.index_name) out.push({ kind: 'vectorize', binding: b.name, value: b.index_name });
|
||||
}
|
||||
}
|
||||
return out;
|
||||
}
|
||||
|
||||
+235
-69
@@ -20,6 +20,19 @@ import { tmpdir, homedir } from 'node:os';
|
||||
import { join } from 'node:path';
|
||||
import { createHash } from 'node:crypto';
|
||||
import chalk from 'chalk';
|
||||
import { CfAccountClient } from './cf-api.js';
|
||||
import {
|
||||
applyResourcePlan,
|
||||
bindingKey,
|
||||
parseWranglerRequirements,
|
||||
planResources,
|
||||
ResourcePlanBlocked,
|
||||
TABLE_KIND,
|
||||
type BindingRequirement,
|
||||
type ResourceApi,
|
||||
type ResourceKind,
|
||||
type ResolvedResource,
|
||||
} from './resource-resolver.js';
|
||||
|
||||
/** 部署狀態 manifest：記錄上次成功部署每個 worker 的內容指紋（content hash），
|
||||
* 讓 acr update 跳過未變動的 worker（壓測 2026-06-12：22/23 成功後重跑仍全部
|
||||
@@ -107,7 +120,15 @@ export function buildDownloadHeaders(token = giteaToken()): Record<string, strin
|
||||
}
|
||||
|
||||
/**
|
||||
* init 要建立的 KV namespace（title）。
|
||||
* arcrun 各 worker 會用到的 KV **binding 名**清單。
|
||||
*
|
||||
* 🔴 Arcrun#97 之後，這份清單**不再是「要去 CF 上建的資源標題」**——
|
||||
* 真正要哪些綁定，是部署當下從每份 wrangler.toml 讀出來的（parseWranglerRequirements），
|
||||
* 要不要建則由 resource-resolver 依「已部署的 worker 綁著什麼」決定。
|
||||
* 這裡保留成一份**文件與離線測試用的期望清單**（測試會比對 toml 沒有漏綁），
|
||||
* 不再被任何執行路徑拿去「照名字 ensure」。
|
||||
*
|
||||
* 原始出處保留如下：
|
||||
* 前 7 個權威來源：.claude/rules/01-tech-stack.md 資料儲存表（cypher-executor 用）。
|
||||
* SUBMISSIONS_KV：registry worker 用（component 投稿）。漏建會讓 registry deploy 失敗 →
|
||||
* 壓測 §2.6/#11「20/21」根因（registry/wrangler.toml 綁 SUBMISSIONS_KV，但注入清單沒有它，
|
||||
@@ -151,8 +172,11 @@ export interface DeployContext {
|
||||
accountId: string;
|
||||
apiToken: string;
|
||||
workerSubdomain: string;
|
||||
kvNamespaceIds: Record<string, string>; // title → id
|
||||
d1DatabaseId?: string; // KBDB Base D1 (arcrun-kbdb); injected into kbdb wrangler.toml
|
||||
/** binding → KV namespace id。**由 downloadAndDeploy 內部的資源解析填入，呼叫端不要自己給**
|
||||
* （Arcrun#97：呼叫端「照名字 ensure 一輪再傳進來」正是把使用者實例洗空的那條路）。*/
|
||||
kvNamespaceIds?: Record<string, string>;
|
||||
/** KBDB Base D1 id；同上，由資源解析填入。*/
|
||||
d1DatabaseId?: string;
|
||||
// self-hosted 單租戶旗標。true（self-hosted）→ 注入 MULTI_TENANT="false" 到 worker [vars]，
|
||||
// 讓 MCP partner-auth 走 namespace 明碼分支（mcp-account-source §5.5）。
|
||||
// 未設 / false → 不注入（官方 SaaS 多租戶，行為不變）。
|
||||
@@ -190,6 +214,11 @@ export interface DeployResult {
|
||||
cypherExecutorUrl?: string;
|
||||
mcpUrl?: string; // self-hosted 自己的 MCP worker URL（mcp-account-source §3）
|
||||
message: string;
|
||||
/** true = 資源解析階段就喊停（Arcrun#97），**一顆資源沒建、一個 worker 沒部**。
|
||||
* 呼叫端要以非零結束並把 message 原文印出來，不要當成一般部分失敗帶過。*/
|
||||
blocked?: boolean;
|
||||
/** 這趟實際用上的資源（沿用/新建各是哪一顆）。呼叫端寫 config 用這個，不要自己再查一次。*/
|
||||
resources?: Map<string, ResolvedResource>;
|
||||
}
|
||||
|
||||
/** 偵測 wrangler 是否已安裝（用戶前置：裝 CF CLI）。*/
|
||||
@@ -219,8 +248,10 @@ export function wranglerAvailable(): boolean {
|
||||
export async function downloadAndDeploy(
|
||||
ctx: DeployContext,
|
||||
ref = 'main',
|
||||
opts: { force?: boolean } = {},
|
||||
opts: { force?: boolean; mode?: 'init' | 'update'; api?: ResourceApi } = {},
|
||||
): Promise<DeployResult> {
|
||||
const mode = opts.mode ?? 'update';
|
||||
const api = opts.api ?? new CfAccountClient(ctx.accountId, ctx.apiToken);
|
||||
// 1. 下載 + 解壓 Gitea archive tarball
|
||||
let root: string;
|
||||
try {
|
||||
@@ -262,28 +293,123 @@ export async function downloadAndDeploy(
|
||||
}
|
||||
|
||||
const failures: string[] = [];
|
||||
const allDirs = [...tier1, ...tier2];
|
||||
|
||||
// 2.6 語義查詢（issue #7 / T2.4）：開 kbdb_embed → 先確保 Vectorize index 存在（REST，冪等），
|
||||
// 再由 injectWranglerConfig 取消 kbdb toml 的 [[vectorize]]+[ai] 註解 → embed 模組上線。
|
||||
// 失敗不致命（收進 failures，base 仍可部署、維持 keyword）。
|
||||
if (ctx.kbdbEmbed) {
|
||||
// ── 2.6 資源解析：先看「這些 worker 現在綁著什麼」，再決定沿用還是新建（Arcrun#97）──────
|
||||
//
|
||||
// 🔴 這一段取代了舊的「照名字 ensure 一輪 KV/D1/Vectorize 再注入」。
|
||||
// 舊做法用 binding 名當資源標題去找，對不上就新建一顆空的綁上去——
|
||||
// 安裝器建的資源本來就不叫那個名字，於是**每次更新都對不上、每次都新建**：
|
||||
// 2026-08-12 一次更新生了 9 顆 KV + 1 顆 D1，使用者的工作流／登入／子庫全部從畫面上消失。
|
||||
//
|
||||
// 現在：已部署 worker 上的綁定＝事實，原樣沿用；只有「確定沒人綁過」才建；
|
||||
// 任何說不準的情況（讀不到綁定／綁著的資源不見了／同名綁定指向兩顆／一顆 worker 都找不到）
|
||||
// → 整趟停手，**在動任何東西之前**。
|
||||
//
|
||||
// 需求是從「注入後的 toml」解析的（renderWranglerToml 帶空 map 當預覽），
|
||||
// 所以「解析看到的」和「最後寫進去的」保證是同一份檔案的同一種樣子。
|
||||
const requirements: BindingRequirement[] = [];
|
||||
const tomlPreviews = new Map<string, string>(); // dir → 注入前的原文
|
||||
for (const dir of allDirs) {
|
||||
const tomlPath = join(dir, 'wrangler.toml');
|
||||
if (!existsSync(tomlPath)) continue;
|
||||
const raw = readFileSync(tomlPath, 'utf8');
|
||||
tomlPreviews.set(dir, raw);
|
||||
const preview = renderWranglerToml(raw, ctx, new Map());
|
||||
const parsed = parseWranglerRequirements(preview);
|
||||
if (!parsed.script) continue; // 沒宣告 name 的 toml 不該存在；跳過而非亂猜
|
||||
for (const b of parsed.bindings) {
|
||||
requirements.push({ ...b, worker: parsed.script });
|
||||
}
|
||||
}
|
||||
|
||||
let resolved = new Map<string, ResolvedResource>();
|
||||
if (requirements.length > 0) {
|
||||
process.stdout.write(chalk.gray(' → 對照你帳號上已部署的 worker，確認每個綁定該用哪顆資源...'));
|
||||
let plan;
|
||||
try {
|
||||
process.stdout.write(chalk.gray(' → 開語義查詢：確保 Vectorize index 存在...'));
|
||||
await ensureVectorizeIndex(ctx);
|
||||
// Arcrun#11 根因修復：光建 index 不夠——Vectorize 要 filter 某 metadata 欄位，該欄必須先建
|
||||
// metadata index，否則帶 owner_id/entry_type/source 過濾的語意查詢一律回 0。冪等，隨 index 一起確保。
|
||||
await ensureVectorizeMetadataIndexes(ctx);
|
||||
plan = await planResources(api, requirements, mode);
|
||||
} catch (e) {
|
||||
console.log(chalk.yellow(' ✗'));
|
||||
return {
|
||||
implemented: true,
|
||||
blocked: true,
|
||||
message:
|
||||
`資源解析失敗（${e instanceof Error ? e.message : String(e)}）。\n` +
|
||||
`沒有建立任何資源、沒有部署任何 worker——你現在的實例維持原樣。`,
|
||||
};
|
||||
}
|
||||
if (plan.blockers.length > 0) {
|
||||
console.log(chalk.yellow(' ✗'));
|
||||
return {
|
||||
implemented: true,
|
||||
blocked: true,
|
||||
message:
|
||||
`停手：有 ${plan.blockers.length} 件事我不敢自己決定。\n` +
|
||||
plan.blockers.map((b) => ` • ${b}`).join('\n') +
|
||||
`\n\n沒有建立任何資源、沒有部署任何 worker——你現在的實例維持原樣。`,
|
||||
};
|
||||
}
|
||||
try {
|
||||
resolved = await applyResourcePlan(api, plan);
|
||||
} catch (e) {
|
||||
console.log(chalk.yellow(' ✗'));
|
||||
const raw = e instanceof Error ? e.message : String(e);
|
||||
const detail = e instanceof ResourcePlanBlocked
|
||||
? e.blockers.map((b) => ` • ${b}`).join('\n')
|
||||
: ` • ${raw}`;
|
||||
// D1 建不起來最常見的根因是 token 沒勾 D1 權限（KV/Worker 建得起來、只有 D1 報 auth error）。
|
||||
// 這句提示在改版前就有，別隨著搬家弄丟——它是使用者唯一能自己解掉的那個錯。
|
||||
const hint = /d1/i.test(raw) && /auth/i.test(raw)
|
||||
? '\n → CF token 缺 D1 權限：補勾「Account / D1 / Edit」重產 token 填回 .env 再跑一次。'
|
||||
: '';
|
||||
return {
|
||||
implemented: true,
|
||||
blocked: true,
|
||||
message: `停手：\n${detail}${hint}\n\n沒有部署任何 worker——你現在的實例維持原樣。`,
|
||||
};
|
||||
}
|
||||
console.log(chalk.green(' ✓'));
|
||||
const adopted = [...resolved.values()].filter((r) => r.origin === 'adopted');
|
||||
const created = [...resolved.values()].filter((r) => r.origin === 'created');
|
||||
if (adopted.length > 0) {
|
||||
console.log(chalk.gray(` 沿用你既有的 ${adopted.length} 個資源（不論它們叫什麼名字）：`));
|
||||
for (const r of adopted) console.log(chalk.gray(` = ${r.binding} → ${r.value}（讀自 ${r.from}）`));
|
||||
}
|
||||
if (created.length > 0) {
|
||||
console.log(chalk.yellow(` 新建 ${created.length} 個（目前沒有任何已部署的 worker 綁著它們）：`));
|
||||
for (const r of created) console.log(chalk.yellow(` + ${r.binding} → ${r.value}`));
|
||||
}
|
||||
}
|
||||
|
||||
// 解析結果回填 ctx，供 applyD1Migration / 呼叫端寫 config 使用。
|
||||
// KBDB 的 migration 打 kbdb worker 的 `DB`；沒有它才退回 cypher 的 `CREDENTIALS_DB`（同一顆庫）。
|
||||
ctx.kvNamespaceIds = Object.fromEntries(
|
||||
[...resolved.values()].filter((r) => r.kind === 'kv_namespace').map((r) => [r.binding, r.value]),
|
||||
);
|
||||
ctx.d1DatabaseId =
|
||||
resolved.get(bindingKey('d1', 'DB'))?.value
|
||||
?? resolved.get(bindingKey('d1', 'CREDENTIALS_DB'))?.value;
|
||||
|
||||
// 2.7 語義查詢（issue #7 / T2.4）：index 本體已由上面的資源解析處理（沿用既有 / 需要才新建）。
|
||||
// 這裡只補 metadata index——Vectorize 要 filter 某欄位必須先為該欄建 index，
|
||||
// 否則帶 owner_id/entry_type/source 過濾的語意查詢一律回 0 命中（Arcrun#11 根因）。
|
||||
// 冪等；失敗不致命（收進 failures，base 仍可部署、維持 keyword）。
|
||||
const vectorizeIndex = resolved.get(bindingKey('vectorize', 'VECTORIZE'))?.value;
|
||||
if (vectorizeIndex) {
|
||||
try {
|
||||
process.stdout.write(chalk.gray(` → 語義查詢 metadata index（${vectorizeIndex}）...`));
|
||||
await ensureVectorizeMetadataIndexes(ctx, vectorizeIndex);
|
||||
console.log(chalk.green(' ✓'));
|
||||
} catch (e) {
|
||||
console.log(chalk.yellow(' ⚠'));
|
||||
failures.push(`Vectorize index (${KBDB_VECTORIZE_INDEX}): ${e instanceof Error ? e.message : String(e)}`);
|
||||
failures.push(`Vectorize metadata index (${vectorizeIndex}): ${e instanceof Error ? e.message : String(e)}`);
|
||||
}
|
||||
}
|
||||
|
||||
// 3. 對每個 worker：注入 KV id（+ cypher WORKER_SUBDOMAIN）→ wrangler deploy。tier1 先 tier2 後。
|
||||
// 逐 worker 串流進度（每個含 pnpm install + wrangler deploy，沉默會讓人以為卡住——
|
||||
// 壓測 2026-06-11 richblack 觀察：「D1 ✓」後停很久其實在這個迴圈靜默部署 20+ worker）。
|
||||
const allDirs = [...tier1, ...tier2];
|
||||
let deployed = 0;
|
||||
let skipped = 0;
|
||||
// 內容指紋 manifest：未變動且上次成功的 worker 跳過（key 用 worker 名，不用 temp 絕對路徑）。
|
||||
@@ -296,7 +422,7 @@ export async function downloadAndDeploy(
|
||||
const label = dir.replace(/^.*\.component-builds\//, '').replace(/^.*\//, '');
|
||||
process.stdout.write(chalk.gray(` [${i + 1}/${allDirs.length}] ${label} ...`));
|
||||
try {
|
||||
injectWranglerConfig(tomlPath, ctx);
|
||||
injectWranglerConfig(tomlPath, ctx, resolved, tomlPreviews.get(dir));
|
||||
// 注入後算指紋：與 manifest 比，相同 = 上次成功部過且內容沒變 → 跳過。
|
||||
const hash = dirContentHash(dir, ctx.accountId);
|
||||
if (manifest[label] === hash) {
|
||||
@@ -434,35 +560,6 @@ async function applyD1Migration(ctx: DeployContext, sql: string): Promise<void>
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* 確保 KBDB embed 用的 Vectorize index 存在（issue #7 / T2.4）。
|
||||
* REST `POST /accounts/{id}/vectorize/v2/indexes`（dimensions=1024 / metric=cosine，對齊 bge-m3）。
|
||||
* ⚠️ 這行別寫成 `**dimensions=1024**/metric`——`*` 緊接 `/` 會提早關掉 block comment（實撞 TS1127）。
|
||||
* 維度必須與 `kbdb/src/embed.ts` 的 `DEFAULT_EMBED_MODEL` 一致——不一致時 upsert 直接被 CF 拒絕。
|
||||
* 冪等：已存在（CF 回「already exists」類錯）視為成功，不報錯。用 init 已驗的 apiToken+accountId。
|
||||
*/
|
||||
async function ensureVectorizeIndex(ctx: DeployContext): Promise<void> {
|
||||
const url = `https://api.cloudflare.com/client/v4/accounts/${ctx.accountId}/vectorize/v2/indexes`;
|
||||
const res = await fetch(url, {
|
||||
method: 'POST',
|
||||
headers: { Authorization: `Bearer ${ctx.apiToken}`, 'Content-Type': 'application/json' },
|
||||
body: JSON.stringify({
|
||||
name: KBDB_VECTORIZE_INDEX,
|
||||
config: { dimensions: 1024, metric: 'cosine' },
|
||||
description: 'arcrun KBDB embed module — bge-m3 1024d (issue #7 / #59)',
|
||||
}),
|
||||
signal: AbortSignal.timeout(60_000),
|
||||
});
|
||||
if (res.ok) return;
|
||||
// 冪等：已存在 → 視為成功（CF 回 409 或 errors 含 already exists / duplicate）。
|
||||
const json = (await res.json().catch(() => null)) as
|
||||
| { success?: boolean; errors?: Array<{ message?: string; code?: number }> }
|
||||
| null;
|
||||
const msg = (json?.errors?.map(e => e.message).filter(Boolean).join('; ') || `HTTP ${res.status}`).toLowerCase();
|
||||
if (res.status === 409 || /already exists|duplicate|conflict/.test(msg)) return;
|
||||
throw new Error(msg);
|
||||
}
|
||||
|
||||
/** embed 過濾用的 Vectorize metadata index 欄位（型別 string；對齊 embedOnWrite 寫入的 metadata）。 */
|
||||
export const KBDB_VECTORIZE_META_FIELDS = ['owner_id', 'entry_type', 'source'] as const;
|
||||
|
||||
@@ -471,9 +568,12 @@ export const KBDB_VECTORIZE_META_FIELDS = ['owner_id', 'entry_type', 'source'] a
|
||||
* Vectorize v2：要對某 metadata 欄位下 filter，必須先為該欄建 metadata index，否則帶過濾的語意查詢一律回 0。
|
||||
* REST `POST /accounts/{id}/vectorize/v2/indexes/{index}/metadata_index/create`（indexType=string）。
|
||||
* 冪等：已存在（409 / already exists）視為成功。async 生效（建立後才 upsert 的向量才會被收錄 → 既有向量另需 reindex）。
|
||||
*
|
||||
* 🔴 index 名由呼叫端傳入（= 資源解析沿用到的那顆），**不是**寫死 KBDB_VECTORIZE_INDEX：
|
||||
* 使用者實例上那顆 index 叫什麼是他那側的事實，我們把 metadata index 建到「他真的在用的那顆」上。
|
||||
*/
|
||||
async function ensureVectorizeMetadataIndexes(ctx: DeployContext): Promise<void> {
|
||||
const url = `https://api.cloudflare.com/client/v4/accounts/${ctx.accountId}/vectorize/v2/indexes/${KBDB_VECTORIZE_INDEX}/metadata_index/create`;
|
||||
async function ensureVectorizeMetadataIndexes(ctx: DeployContext, indexName: string): Promise<void> {
|
||||
const url = `https://api.cloudflare.com/client/v4/accounts/${ctx.accountId}/vectorize/v2/indexes/${indexName}/metadata_index/create`;
|
||||
for (const propertyName of KBDB_VECTORIZE_META_FIELDS) {
|
||||
const res = await fetch(url, {
|
||||
method: 'POST',
|
||||
@@ -596,21 +696,31 @@ export function discoverWorkerDirs(root: string): { tier1: string[]; tier2: stri
|
||||
* - 每個 worker toml 都有 `workers_dev = true` → strip routes 後純靠 workers.dev URL，自架可達。
|
||||
* - R2（`[[r2_buckets]]`）是 dead storage（registry-canon Phase 1.5），且綁卡違背開源免費 → 一併移除。
|
||||
*/
|
||||
function injectWranglerConfig(tomlPath: string, ctx: DeployContext): void {
|
||||
function injectWranglerConfig(
|
||||
tomlPath: string,
|
||||
ctx: DeployContext,
|
||||
resolved: Map<string, ResolvedResource>,
|
||||
original?: string,
|
||||
): void {
|
||||
if (!existsSync(tomlPath)) return;
|
||||
let toml = readFileSync(tomlPath, 'utf8');
|
||||
|
||||
// 對每個已建立的 KV namespace：把對應 binding 的 id 換成用戶的。
|
||||
// 匹配 `[[kv_namespaces]] ... binding = "NAME" ... id = "OLD"` 的 id 行。
|
||||
for (const [binding, id] of Object.entries(ctx.kvNamespaceIds)) {
|
||||
if (!id) continue;
|
||||
const re = new RegExp(
|
||||
`(binding\\s*=\\s*"${binding}"\\s*\\n\\s*id\\s*=\\s*")[^"]*(")`,
|
||||
'g',
|
||||
);
|
||||
toml = toml.replace(re, `$1${id}$2`);
|
||||
}
|
||||
// original = 資源解析階段讀到的原文。用它而不是重讀檔案，確保「解析看到的」與「寫回去的」同源。
|
||||
const toml = original ?? readFileSync(tomlPath, 'utf8');
|
||||
writeFileSync(tomlPath, renderWranglerToml(toml, ctx, resolved), 'utf8');
|
||||
}
|
||||
|
||||
/**
|
||||
* 把一份 repo 內的 wrangler.toml 轉成「要部到這個用戶帳號上的樣子」。
|
||||
*
|
||||
* 純函式（好離線測、也好當預覽用）。帶空 `resolved` 呼叫 = 預覽：得到的是
|
||||
* 「除了資源 id 以外都已經定案」的 toml，資源解析就是照這份預覽去數需求的
|
||||
* ⇒ 解析階段看到的 binding 清單，與最後真的寫進檔案的，保證一致（Arcrun#97 的教訓：
|
||||
* 兩段程式對同一份檔案有不同想像，就會出現「以為沒有、其實有」）。
|
||||
*/
|
||||
export function renderWranglerToml(
|
||||
toml: string,
|
||||
ctx: DeployContext,
|
||||
resolved: Map<string, ResolvedResource>,
|
||||
): string {
|
||||
// cypher-executor 的 WORKER_SUBDOMAIN（vars）換成用戶帳號 subdomain
|
||||
if (ctx.workerSubdomain && /WORKER_SUBDOMAIN/.test(toml)) {
|
||||
toml = toml.replace(
|
||||
@@ -629,14 +739,6 @@ function injectWranglerConfig(tomlPath: string, ctx: DeployContext): void {
|
||||
);
|
||||
}
|
||||
|
||||
// KBDB Base: inject user's D1 database_id into [[d1_databases]] (placeholder in repo toml)
|
||||
if (ctx.d1DatabaseId && /database_id\s*=/.test(toml)) {
|
||||
toml = toml.replace(
|
||||
/(database_id\s*=\s*")[^"]*(")/,
|
||||
`$1${ctx.d1DatabaseId}$2`,
|
||||
);
|
||||
}
|
||||
|
||||
// self-hosted：注入 MULTI_TENANT="false" 到 [vars]（mcp-account-source §5.5）。
|
||||
// 修「部署沒注入 → worker c.env.MULTI_TENANT===undefined → MCP 走 partner-key → 401」。
|
||||
// 只對有 [vars] 的 worker（mcp / cypher-executor）生效；其餘無 [vars] 的不動。
|
||||
@@ -668,7 +770,71 @@ function injectWranglerConfig(tomlPath: string, ctx: DeployContext): void {
|
||||
toml = toml.replace(/# (\[ai\])\n# (binding = "AI")/, '$1\n$2');
|
||||
}
|
||||
|
||||
writeFileSync(tomlPath, toml, 'utf8');
|
||||
// 資源 id 一律最後注入，且**照 binding 名逐個對號**（不是「檔案裡第一個 database_id」那種盲換）。
|
||||
// 空 map = 預覽模式，這步什麼也不做。
|
||||
return applyResolvedBindings(toml, resolved);
|
||||
}
|
||||
|
||||
/**
|
||||
* 把解析好的資源 id 寫進對應的 binding 區塊。
|
||||
*
|
||||
* 逐個 `[[table]]` 區塊掃：先在區塊內找 `binding = "X"`，再改同一區塊裡的值欄位
|
||||
* （KV→`id`、D1→`database_id`、Vectorize→`index_name`）。
|
||||
* 🔴 刻意**不用**「全檔第一個 database_id」這種寫法：cypher（`CREDENTIALS_DB`）與
|
||||
* kbdb（`DB`）各有自己的 D1 綁定，盲換會把兩邊當成同一個東西——而使用者的實例
|
||||
* 完全可以兩邊指向不同庫。誰綁誰是使用者那側的事實，我們只是原樣搬過去。
|
||||
*/
|
||||
export function applyResolvedBindings(
|
||||
toml: string,
|
||||
resolved: Map<string, ResolvedResource>,
|
||||
): string {
|
||||
if (resolved.size === 0) return toml;
|
||||
|
||||
const VALUE_KEY: Record<ResourceKind, string> = {
|
||||
kv_namespace: 'id',
|
||||
d1: 'database_id',
|
||||
vectorize: 'index_name',
|
||||
};
|
||||
|
||||
const out: string[] = [];
|
||||
let block: string[] = [];
|
||||
let kind: ResourceKind | null = null;
|
||||
|
||||
const flush = (): void => {
|
||||
if (kind) {
|
||||
const binding = block
|
||||
.map((l) => l.trim())
|
||||
.filter((l) => !l.startsWith('#'))
|
||||
.map((l) => l.match(/^binding\s*=\s*"([^"]*)"/)?.[1])
|
||||
.find((b): b is string => !!b);
|
||||
const hit = binding ? resolved.get(bindingKey(kind, binding)) : undefined;
|
||||
if (hit) {
|
||||
const key = VALUE_KEY[kind];
|
||||
const re = new RegExp(`^(\\s*${key}\\s*=\\s*")[^"]*(")(.*)$`);
|
||||
const at = block.findIndex((l) => !l.trim().startsWith('#') && re.test(l));
|
||||
if (at >= 0) {
|
||||
block[at] = block[at].replace(re, `$1${hit.value}$2$3`);
|
||||
} else {
|
||||
// 區塊裡本來沒有這個欄位（例如新版 toml 只寫 binding）→ 補一行，不要靜默略過。
|
||||
block.push(`${key} = "${hit.value}"`);
|
||||
}
|
||||
}
|
||||
}
|
||||
out.push(...block);
|
||||
block = [];
|
||||
};
|
||||
|
||||
for (const line of toml.split('\n')) {
|
||||
const table = line.trim().match(/^\[\[?([A-Za-z0-9_]+)\]?\]$/);
|
||||
if (table) {
|
||||
flush();
|
||||
kind = TABLE_KIND[table[1]] ?? null;
|
||||
}
|
||||
block.push(line);
|
||||
}
|
||||
flush();
|
||||
|
||||
return out.join('\n');
|
||||
}
|
||||
|
||||
/**
|
||||
|
||||
+38
-20
@@ -6,9 +6,11 @@
|
||||
* 不是假設齊備直接動手 → 缺一個就卡（test_arcrun/4 的 D1 大跑去讀原始碼自己想辦法）。
|
||||
* - **裝完驗收**：部署後逐項確認（KV / D1 / migration / cypher 可達），缺哪項明確報哪項
|
||||
* + 給一鍵補裝指令。不是靜默印灰字（原本 harness/MCP 失敗只 console.log 灰字，用戶不知道）。
|
||||
* - **冪等**：重跑檢查後「什麼也沒動」（ensureKvNamespace / ensureD1Database 本就冪等）。
|
||||
* - **冪等**：重跑檢查後「什麼也沒動」。
|
||||
*
|
||||
* 本檔只做「偵測 + 報告」，不自己建資源（建資源仍走 cf-api 的 ensure*，由 init 編排）。
|
||||
* 本檔只做「偵測 + 報告」，不自己建資源（要不要建由 resource-resolver 判斷，deploy.ts 編排）。
|
||||
* 🔴 Arcrun#97：報告裡的 fix 指令也算「產品的一部分」——一句「acr update（冪等重建）」
|
||||
* 接在誤報的「缺 KV」後面，就是把使用者直接推去執行那個把實例洗空的動作。
|
||||
*/
|
||||
|
||||
import { execFileSync } from 'node:child_process';
|
||||
@@ -77,42 +79,58 @@ export function printPreflight(title: string, items: PreflightItem[]): void {
|
||||
*/
|
||||
export async function verifyInstall(opts: {
|
||||
cf: CfAccountClient;
|
||||
requiredKv: readonly string[];
|
||||
expectD1Name?: string;
|
||||
/** binding → KV namespace id（部署實際用上的那幾顆）。*/
|
||||
kvNamespaceIds: Record<string, string>;
|
||||
/** 部署實際用上的 D1 id（沒有 D1 就不傳）。*/
|
||||
d1DatabaseId?: string;
|
||||
cypherUrl?: string;
|
||||
}): Promise<{ items: PreflightItem[]; allOk: boolean }> {
|
||||
const items: PreflightItem[] = [];
|
||||
|
||||
// KV：實查 CF 上現有 namespace，比對必需清單
|
||||
// KV：核對「部署實際綁上去的那幾顆 id」在帳號上還在不在。
|
||||
// 🔴 Arcrun#97：這裡**不能**用「帳號上有沒有叫 WEBHOOKS 的 namespace」來驗。
|
||||
// 安裝器裝出來的實例，資源名字是 arcrun-rag-<instance>-kv-webhooks——照名字驗會誤報「缺」，
|
||||
// 而那句誤報底下就寫著「fix: acr update（冪等重建）」⇒ 使用者照做，就被重建成空的。
|
||||
// 驗的對象永遠是 id（我們真的綁上去的那顆），不是名字。
|
||||
const kvBindings = Object.entries(opts.kvNamespaceIds);
|
||||
try {
|
||||
const existing = await opts.cf.listKvNamespaces();
|
||||
const have = new Set(existing.keys());
|
||||
const missing = opts.requiredKv.filter((t) => !have.has(t));
|
||||
const ids = new Set((await opts.cf.listKvNamespaces()).values());
|
||||
const missing = kvBindings.filter(([, id]) => !ids.has(id)).map(([b]) => b);
|
||||
items.push(
|
||||
missing.length === 0
|
||||
? { name: `KV namespaces (${opts.requiredKv.length})`, ok: true }
|
||||
: { name: 'KV namespaces', ok: false, detail: `缺 ${missing.join(', ')}`, fix: 'acr update（冪等重建）' },
|
||||
? { name: `KV namespaces (${kvBindings.length})`, ok: true }
|
||||
: {
|
||||
name: 'KV namespaces',
|
||||
ok: false,
|
||||
detail: `這幾個 binding 綁著的 namespace 在帳號上找不到：${missing.join(', ')}`,
|
||||
fix: '先確認那幾顆是被刪了還是 token 看不到——不要直接重跑安裝（會綁到空的）',
|
||||
},
|
||||
);
|
||||
} catch (e) {
|
||||
items.push({ name: 'KV namespaces', ok: false, detail: msg(e), fix: 'acr update' });
|
||||
items.push({ name: 'KV namespaces', ok: false, detail: msg(e), fix: '檢查 CF token 的 KV 讀取權限' });
|
||||
}
|
||||
|
||||
// D1：實查 CF 上是否有該庫
|
||||
if (opts.expectD1Name) {
|
||||
// D1：同理，核對實際綁上去的那顆 id 還在不在（不是核對有沒有叫 arcrun-kbdb 的庫）。
|
||||
if (opts.d1DatabaseId) {
|
||||
try {
|
||||
const dbs = await opts.cf.listD1Databases();
|
||||
const ids = new Set((await opts.cf.listD1Databases()).values());
|
||||
items.push(
|
||||
dbs.has(opts.expectD1Name)
|
||||
? { name: `D1 ${opts.expectD1Name}`, ok: true }
|
||||
: { name: `D1 ${opts.expectD1Name}`, ok: false, detail: '不存在', fix: 'CF token 補勾「Account / D1 / Edit」權限 → 重產 token 填回 .env → acr update' },
|
||||
ids.has(opts.d1DatabaseId)
|
||||
? { name: `D1 ${opts.d1DatabaseId}`, ok: true }
|
||||
: {
|
||||
name: `D1 ${opts.d1DatabaseId}`,
|
||||
ok: false,
|
||||
detail: '這顆 D1 在帳號上找不到',
|
||||
fix: '先確認它是被刪了還是 token 看不到——不要直接重跑安裝（會綁到空的）',
|
||||
},
|
||||
);
|
||||
} catch (e) {
|
||||
// D1 建失敗最常見根因：CF token 沒勾 D1 權限（KV/Worker 能建但 D1 報 Authentication error）。
|
||||
// D1 讀不到最常見根因：CF token 沒勾 D1 權限（KV/Worker 能建但 D1 報 Authentication error）。
|
||||
const m = msg(e);
|
||||
const fix = /auth/i.test(m)
|
||||
? 'token 缺 D1 權限：CF token 補勾「Account / D1 / Edit」→ 重產 token 填回 .env → acr update'
|
||||
: 'acr update（冪等重試）';
|
||||
items.push({ name: `D1 ${opts.expectD1Name}`, ok: false, detail: m, fix });
|
||||
: '檢查 CF token 的 D1 讀取權限';
|
||||
items.push({ name: `D1 ${opts.d1DatabaseId}`, ok: false, detail: m, fix });
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -0,0 +1,408 @@
|
||||
/**
|
||||
* resource-resolver.ts — 資源解析：「已部署的 worker 現在綁著什麼，那就是事實」
|
||||
*
|
||||
* 🔴 Arcrun#97（2026-08-12 實害，leo 的實例中了）：
|
||||
* 舊做法叫「照名字 ensure」——`acr update` 拿 **binding 名**（`WEBHOOKS`）當成 Cloudflare 上的
|
||||
* **資源標題**去找，找不到就**新建一顆空的、然後綁到 worker 上**。
|
||||
* 安裝器建的資源不叫那個名字（它叫 `arcrun-rag-<instance>-kv-webhooks`）⇒ 一次例行更新
|
||||
* 新建了 9 顆 KV、1 顆 D1，使用者的工作流／登入狀態／子庫**在畫面上全部消失**。
|
||||
* 資料沒有被刪，但 worker 被綁去空的那幾顆——從使用者的角度，他的東西就是不見了。
|
||||
*
|
||||
* 根因不是「KV 那段寫錯」，是**「用名字猜使用者的資源」這個做法本身**：
|
||||
* 名字是**使用者那側的事實**（安裝器要怎麼取名由它決定，而且它有權改），
|
||||
* 我們不能拿自己的命名慣例去對號入座，更不能在對不上的時候自作主張生一顆新的。
|
||||
* ——所以修法不是「多比對幾種名字」，是**不再用名字當識別**。
|
||||
*
|
||||
* ── 新規則（三句話）────────────────────────────────────────────────
|
||||
* 1. **已部署的 worker 上綁著什麼，那就是事實** → 原封不動沿用，不管那顆資源叫什麼名字。
|
||||
* 2. **只有「確定沒有任何人綁過它」才准新建**（新版本新增的 binding、或真的全新帳號）。
|
||||
* 3. **只要有一點說不準就整趟停手**（讀不到綁定／綁著的資源不見了／同一個 binding 指向兩顆／
|
||||
* 該更新的 worker 一顆都不在），**什麼都不建、什麼都不部署**，把話說清楚讓人來判斷。
|
||||
*
|
||||
* ── 為什麼拆成 plan / apply 兩段 ─────────────────────────────────────
|
||||
* `planResources()` **完全不寫入**，只回一份「要沿用什麼、要新建什麼、有什麼不敢動的」。
|
||||
* `applyResourcePlan()` 看到有任何 blocker 就直接拒絕執行。
|
||||
* ⇒「被擋下的時候一顆資源都不會被建出來」是**結構上的保證**，
|
||||
* 不是靠某個人記得在對的地方寫 early return。#97 正是死在「先動手、後判斷」。
|
||||
*/
|
||||
|
||||
/** 這支負責的資源種類。要加新種類（R2/Queue/Hyperdrive…）就加在這裡，
|
||||
* 一律走同一道門——不准任何呼叫端自己「照名字 ensure」繞過去。 */
|
||||
export type ResourceKind = 'kv_namespace' | 'd1' | 'vectorize';
|
||||
|
||||
/** 從已部署 worker 上讀回來的一條綁定。`value`：KV/D1 是資源 id，Vectorize 是 index 名。 */
|
||||
export interface LiveBinding {
|
||||
kind: ResourceKind;
|
||||
binding: string;
|
||||
value: string;
|
||||
}
|
||||
|
||||
export interface ScriptBindings {
|
||||
/** false = 這顆 worker 在帳號上還不存在（全新部署），不是「讀取失敗」。讀取失敗要 throw。 */
|
||||
deployed: boolean;
|
||||
bindings: LiveBinding[];
|
||||
}
|
||||
|
||||
/** resolver 需要的 CF 能力（收窄成介面，方便離線測試餵假帳號）。 */
|
||||
export interface ResourceApi {
|
||||
getScriptBindings(script: string): Promise<ScriptBindings>;
|
||||
/** title → id */
|
||||
listKvNamespaces(): Promise<Map<string, string>>;
|
||||
/** name → uuid */
|
||||
listD1Databases(): Promise<Map<string, string>>;
|
||||
listVectorizeIndexes(): Promise<string[]>;
|
||||
createKvNamespace(title: string): Promise<string>;
|
||||
createD1Database(name: string): Promise<string>;
|
||||
createVectorizeIndex(name: string): Promise<string>;
|
||||
}
|
||||
|
||||
/** 「這顆 worker 需要這個 binding」。createName 只在**真的要新建**時才會被拿來當名字用。 */
|
||||
export interface BindingRequirement {
|
||||
kind: ResourceKind;
|
||||
binding: string;
|
||||
/** 需要它的 worker script 名（= wrangler.toml 的 `name`）。 */
|
||||
worker: string;
|
||||
createName: string;
|
||||
}
|
||||
|
||||
export interface PlannedAdopt {
|
||||
kind: ResourceKind;
|
||||
binding: string;
|
||||
value: string;
|
||||
/** 從哪顆已部署的 worker 上讀到的 */
|
||||
from: string;
|
||||
}
|
||||
|
||||
export interface PlannedCreate {
|
||||
kind: ResourceKind;
|
||||
binding: string;
|
||||
createName: string;
|
||||
wantedBy: string[];
|
||||
/** 其他也指向同一顆資源的 binding（見 shareSameResource）。建一顆，大家共用。 */
|
||||
alsoBind: string[];
|
||||
}
|
||||
|
||||
export interface ResourcePlan {
|
||||
adopt: PlannedAdopt[];
|
||||
create: PlannedCreate[];
|
||||
/** 非空 = 整趟停手。applyResourcePlan 會拒絕執行。 */
|
||||
blockers: string[];
|
||||
}
|
||||
|
||||
export interface ResolvedResource {
|
||||
kind: ResourceKind;
|
||||
binding: string;
|
||||
value: string;
|
||||
origin: 'adopted' | 'created';
|
||||
from?: string;
|
||||
}
|
||||
|
||||
/** plan 被擋下時丟這個，讓呼叫端能把每一條原因原文轉給使用者。 */
|
||||
export class ResourcePlanBlocked extends Error {
|
||||
constructor(readonly blockers: string[]) {
|
||||
super(`資源解析被擋下（${blockers.length} 項）`);
|
||||
this.name = 'ResourcePlanBlocked';
|
||||
}
|
||||
}
|
||||
|
||||
export function bindingKey(kind: ResourceKind, binding: string): string {
|
||||
return `${kind}:${binding}`;
|
||||
}
|
||||
|
||||
const KIND_LABEL: Record<ResourceKind, string> = {
|
||||
kv_namespace: 'KV namespace',
|
||||
d1: 'D1 資料庫',
|
||||
vectorize: 'Vectorize index',
|
||||
};
|
||||
|
||||
function msg(e: unknown): string {
|
||||
return e instanceof Error ? e.message : String(e);
|
||||
}
|
||||
|
||||
/**
|
||||
* 決定每個 binding 要沿用哪顆資源／要不要新建，**不寫入任何東西**。
|
||||
*
|
||||
* @param mode 'update' = 這台照定義已經裝過了（見下方「一顆都不在」規則）；'init' = 全新安裝，允許從零建。
|
||||
*/
|
||||
export async function planResources(
|
||||
api: ResourceApi,
|
||||
requirements: readonly BindingRequirement[],
|
||||
mode: 'update' | 'init',
|
||||
): Promise<ResourcePlan> {
|
||||
const blockers: string[] = [];
|
||||
const adopt: PlannedAdopt[] = [];
|
||||
const create: PlannedCreate[] = [];
|
||||
|
||||
// ── 1. 先讀「即將被覆蓋的每一顆 worker」現在綁著什麼 ──────────────────
|
||||
// 讀取失敗 ≠ 沒有綁。#97 的災情就是把「我查不到」當成「它不存在」。
|
||||
const scripts = [...new Set(requirements.map((r) => r.worker))].sort();
|
||||
const live = new Map<string, LiveBinding[]>();
|
||||
let readFailed = false;
|
||||
for (const script of scripts) {
|
||||
try {
|
||||
const res = await api.getScriptBindings(script);
|
||||
if (res.deployed) live.set(script, res.bindings);
|
||||
} catch (e) {
|
||||
readFailed = true;
|
||||
blockers.push(
|
||||
`讀不到已部署的 worker「${script}」目前綁著哪些資源（${msg(e)}）。` +
|
||||
`不確定它現在用的是哪一顆，就不能重新綁——整趟更新停手，沒有動任何東西。`,
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
// 「這台照定義已經裝過了，卻一顆 worker 都找不到」= 我對不上它的實例（名字不同／token 看不到）。
|
||||
// 這種時候繼續走下去，等於把一整套資源重新生一遍再綁上去——正是 #97 的形狀，只是換一道門進來。
|
||||
if (mode === 'update' && !readFailed && live.size === 0 && scripts.length > 0) {
|
||||
blockers.push(
|
||||
`在這個 Cloudflare 帳號上找不到任何一顆要更新的 worker（找過：${scripts.join('、')}）。` +
|
||||
`acr update 的前提是「這台已經裝好了」——對不上就不猜：` +
|
||||
`可能是 API token 看得到的帳號不對，或這台實例的 worker 用了別的名字。` +
|
||||
`已停手，沒有新建任何資源。`,
|
||||
);
|
||||
}
|
||||
|
||||
// ── 2. 逐個 binding 決定：沿用 / 新建 / 停手 ─────────────────────────
|
||||
const byKey = new Map<string, BindingRequirement[]>();
|
||||
for (const req of requirements) {
|
||||
const key = bindingKey(req.kind, req.binding);
|
||||
const list = byKey.get(key);
|
||||
if (list) list.push(req);
|
||||
else byKey.set(key, [req]);
|
||||
}
|
||||
|
||||
const existingCache = new Map<ResourceKind, Set<string>>();
|
||||
const listExisting = async (kind: ResourceKind): Promise<Set<string>> => {
|
||||
const hit = existingCache.get(kind);
|
||||
if (hit) return hit;
|
||||
let set: Set<string>;
|
||||
if (kind === 'kv_namespace') set = new Set((await api.listKvNamespaces()).values());
|
||||
else if (kind === 'd1') set = new Set((await api.listD1Databases()).values());
|
||||
else set = new Set(await api.listVectorizeIndexes());
|
||||
existingCache.set(kind, set);
|
||||
return set;
|
||||
};
|
||||
|
||||
for (const [, reqs] of byKey) {
|
||||
const { kind, binding } = reqs[0];
|
||||
|
||||
const found: Array<{ value: string; script: string }> = [];
|
||||
for (const [script, bindings] of live) {
|
||||
const hit = bindings.find((b) => b.kind === kind && b.binding === binding);
|
||||
if (hit) found.push({ value: hit.value, script });
|
||||
}
|
||||
const distinct = [...new Set(found.map((f) => f.value))];
|
||||
|
||||
// 2a. 同一個 binding 名在不同 worker 上指向不同資源 → 分不出哪個才是使用者要的。
|
||||
// 自己挑一個 = 有一半機率把另外那半的資料從畫面上抹掉。不猜。
|
||||
if (distinct.length > 1) {
|
||||
blockers.push(
|
||||
`綁定「${binding}」在不同 worker 上指向不同的 ${KIND_LABEL[kind]}` +
|
||||
`（${found.map((f) => `${f.script} → ${f.value}`).join('、')}）。` +
|
||||
`分不出哪一顆才是你在用的，不猜——停手。`,
|
||||
);
|
||||
continue;
|
||||
}
|
||||
|
||||
// 2b. 有人綁著它 → 這就是事實，沿用。名字長什麼樣完全不看。
|
||||
if (distinct.length === 1) {
|
||||
const value = distinct[0];
|
||||
let existing: Set<string>;
|
||||
try {
|
||||
existing = await listExisting(kind);
|
||||
} catch (e) {
|
||||
blockers.push(
|
||||
`查不到帳號上的 ${KIND_LABEL[kind]} 清單，無法確認「${binding}」綁著的 ${value} 還在不在` +
|
||||
`（${msg(e)}）。不確定就不動——停手。`,
|
||||
);
|
||||
continue;
|
||||
}
|
||||
if (!existing.has(value)) {
|
||||
// 這正是 #97 的入口：舊版在這裡會安靜地新建一顆空的頂上去。
|
||||
blockers.push(
|
||||
`worker「${found[0].script}」的「${binding}」綁著 ${KIND_LABEL[kind]} ${value}，` +
|
||||
`但這顆在你的 Cloudflare 帳號上找不到了。` +
|
||||
`這裡**不會**幫你新建一顆空的頂上去（Arcrun#97 的災情就是那樣來的）——` +
|
||||
`請先確認那顆資源是被刪掉了，還是這把 API token 看不到它。`,
|
||||
);
|
||||
continue;
|
||||
}
|
||||
adopt.push({ kind, binding, value, from: found[0].script });
|
||||
continue;
|
||||
}
|
||||
|
||||
// 2c. 沒有任何已部署的 worker 綁過它 → 新版本新增的 binding，或全新帳號。
|
||||
// 這種情況下新建不會弄丟任何東西（本來就沒有東西可丟）。
|
||||
create.push({
|
||||
kind,
|
||||
binding,
|
||||
createName: reqs[0].createName,
|
||||
wantedBy: [...new Set(reqs.map((r) => r.worker))],
|
||||
alsoBind: [],
|
||||
});
|
||||
}
|
||||
|
||||
return { adopt, create: shareSameResource(adopt, create, byKey), blockers };
|
||||
}
|
||||
|
||||
/**
|
||||
* 收斂「不同 binding 其實是同一顆資源」的情況。
|
||||
*
|
||||
* 判準是 **toml 自己宣告的名字**（`database_name` / `index_name`），不是使用者那側的資源名——
|
||||
* cypher 的 `CREDENTIALS_DB` 與 kbdb 的 `DB` 都寫 `database_name = "arcrun-kbdb"`，
|
||||
* 那是**我們**在宣告「這兩個綁定指向同一顆庫」，跟 #97 那種「拿名字去猜使用者的資源」是兩回事。
|
||||
*
|
||||
* 沒有這一步會出兩種錯：
|
||||
* ① 全新安裝時建出兩顆同名 D1，KBDB 的資料與 credential 目錄從此分家。
|
||||
* ② 一邊已部署（沿用既有）、另一邊沒有（新建一顆空的）→ 半套資料，比全壞更難查。
|
||||
*/
|
||||
function shareSameResource(
|
||||
adopt: PlannedAdopt[],
|
||||
create: PlannedCreate[],
|
||||
byKey: Map<string, BindingRequirement[]>,
|
||||
): PlannedCreate[] {
|
||||
const declaredName = (kind: ResourceKind, binding: string): string | undefined =>
|
||||
byKey.get(bindingKey(kind, binding))?.[0]?.createName;
|
||||
|
||||
const out: PlannedCreate[] = [];
|
||||
const groups = new Map<string, PlannedCreate>();
|
||||
|
||||
for (const c of create) {
|
||||
const groupKey = `${c.kind} ${c.createName}`;
|
||||
|
||||
// ① 已經有 binding 沿用到同一顆（依 toml 宣告）→ 跟著沿用，不要另外建一顆。
|
||||
const twin = adopt.find(
|
||||
(a) => a.kind === c.kind && declaredName(a.kind, a.binding) === c.createName,
|
||||
);
|
||||
if (twin) {
|
||||
adopt.push({ kind: c.kind, binding: c.binding, value: twin.value, from: twin.from });
|
||||
continue;
|
||||
}
|
||||
|
||||
// ② 同一趟裡有多個 binding 要建同一顆 → 建一次，其他人共用。
|
||||
const head = groups.get(groupKey);
|
||||
if (head) {
|
||||
head.alsoBind.push(c.binding);
|
||||
head.wantedBy = [...new Set([...head.wantedBy, ...c.wantedBy])];
|
||||
continue;
|
||||
}
|
||||
groups.set(groupKey, c);
|
||||
out.push(c);
|
||||
}
|
||||
return out;
|
||||
}
|
||||
|
||||
/**
|
||||
* 照 plan 動手：沿用的原樣帶出來，該建的才建。
|
||||
* 有任何 blocker 直接丟 ResourcePlanBlocked，**一顆都不建**。
|
||||
*/
|
||||
export async function applyResourcePlan(
|
||||
api: ResourceApi,
|
||||
plan: ResourcePlan,
|
||||
): Promise<Map<string, ResolvedResource>> {
|
||||
if (plan.blockers.length > 0) throw new ResourcePlanBlocked(plan.blockers);
|
||||
|
||||
const out = new Map<string, ResolvedResource>();
|
||||
for (const a of plan.adopt) {
|
||||
out.set(bindingKey(a.kind, a.binding), {
|
||||
kind: a.kind,
|
||||
binding: a.binding,
|
||||
value: a.value,
|
||||
origin: 'adopted',
|
||||
from: a.from,
|
||||
});
|
||||
}
|
||||
const madeSoFar: string[] = [];
|
||||
for (const c of plan.create) {
|
||||
let value: string;
|
||||
try {
|
||||
if (c.kind === 'kv_namespace') value = await api.createKvNamespace(c.createName);
|
||||
else if (c.kind === 'd1') value = await api.createD1Database(c.createName);
|
||||
else value = await api.createVectorizeIndex(c.createName);
|
||||
} catch (e) {
|
||||
// 半途失敗：已經建出來的那幾顆還沒被綁到任何 worker 上。**要講出來**——
|
||||
// 不講的話它們就是帳號上一批沒人認得的孤兒，而且下次重跑會再建一批。
|
||||
const orphans = madeSoFar.length > 0
|
||||
? `\n 已經建好但還沒綁上任何 worker 的：${madeSoFar.join('、')}（重跑前可先刪掉，或留著讓下次沿用）`
|
||||
: '';
|
||||
throw new Error(`建 ${KIND_LABEL[c.kind]}「${c.createName}」失敗：${msg(e)}${orphans}`);
|
||||
}
|
||||
madeSoFar.push(`${KIND_LABEL[c.kind]} ${c.createName}`);
|
||||
for (const binding of [c.binding, ...c.alsoBind]) {
|
||||
out.set(bindingKey(c.kind, binding), { kind: c.kind, binding, value, origin: 'created' });
|
||||
}
|
||||
}
|
||||
return out;
|
||||
}
|
||||
|
||||
// ─────────────────────────────────────────────────────────────────────────────
|
||||
// wrangler.toml → 需求清單
|
||||
// ─────────────────────────────────────────────────────────────────────────────
|
||||
|
||||
export interface WranglerRequirements {
|
||||
/** worker script 名（toml 頂層 `name`）。空字串 = 這份 toml 沒宣告 name（不該發生）。 */
|
||||
script: string;
|
||||
bindings: Array<{ kind: ResourceKind; binding: string; createName: string }>;
|
||||
}
|
||||
|
||||
/** wrangler.toml 的 table 名 → 資源種類。需求解析與注入共用同一張表，兩邊才不會對不上。 */
|
||||
export const TABLE_KIND: Record<string, ResourceKind> = {
|
||||
kv_namespaces: 'kv_namespace',
|
||||
d1_databases: 'd1',
|
||||
vectorize: 'vectorize',
|
||||
};
|
||||
|
||||
/**
|
||||
* 從 wrangler.toml 抽出「這顆 worker 需要哪些資源綁定」。
|
||||
*
|
||||
* 刻意寫成行掃描而不引 TOML parser：注入端（injectWranglerConfig）本來就是純文字操作，
|
||||
* 兩邊用同一種視角看這份檔案才不會對不上。註解掉的區塊**不算需求**
|
||||
* （kbdb 的 `[[vectorize]]` 預設是註解狀態，要開語義查詢時才會被取消註解 → 那時才成為需求）。
|
||||
*/
|
||||
export function parseWranglerRequirements(toml: string): WranglerRequirements {
|
||||
let script = '';
|
||||
let seenTable = false;
|
||||
const bindings: WranglerRequirements['bindings'] = [];
|
||||
|
||||
let kind: ResourceKind | null = null;
|
||||
let binding = '';
|
||||
let createName = '';
|
||||
|
||||
const flush = (): void => {
|
||||
if (kind && binding) {
|
||||
bindings.push({ kind, binding, createName: createName || binding });
|
||||
}
|
||||
kind = null;
|
||||
binding = '';
|
||||
createName = '';
|
||||
};
|
||||
|
||||
for (const raw of toml.split('\n')) {
|
||||
const line = raw.trim();
|
||||
if (line === '' || line.startsWith('#')) continue;
|
||||
|
||||
const table = line.match(/^\[\[?([A-Za-z0-9_]+)\]?\]$/);
|
||||
if (table) {
|
||||
flush();
|
||||
seenTable = true;
|
||||
kind = TABLE_KIND[table[1]] ?? null;
|
||||
continue;
|
||||
}
|
||||
|
||||
const kv = line.match(/^([A-Za-z0-9_]+)\s*=\s*"([^"]*)"/);
|
||||
if (!kv) continue;
|
||||
const [, key, value] = kv;
|
||||
|
||||
if (!seenTable && key === 'name') {
|
||||
script = value;
|
||||
continue;
|
||||
}
|
||||
if (!kind) continue;
|
||||
if (key === 'binding') binding = value;
|
||||
// 只有 D1／Vectorize 在 toml 裡帶得出「名字」；KV 沒有，退回用 binding 名（見 flush）。
|
||||
else if (key === 'database_name' || key === 'index_name') createName = value;
|
||||
}
|
||||
flush();
|
||||
|
||||
return { script, bindings };
|
||||
}
|
||||
@@ -0,0 +1,532 @@
|
||||
/**
|
||||
* Arcrun#97 迴歸守衛 —— 「跑完更新，使用者的東西還在原地」
|
||||
*
|
||||
* 2026-08-12 實害：leo 跑了一次例行更新，跑完工作流一支都沒有、portal 把他登出、
|
||||
* 總圖是空的、子庫全不見。資料沒被刪，但 worker 被重新綁到 9 顆新建的空 KV + 1 顆空 D1 上。
|
||||
*
|
||||
* 根因：更新「照名字」確保資源存在——拿 binding 名（WEBHOOKS）當 CF 上的資源標題去找，
|
||||
* 安裝器建的資源叫 `arcrun-rag-<instance>-kv-webhooks`，永遠對不上 ⇒ 每次更新都新建一顆綁上去。
|
||||
*
|
||||
* 這份測試用一台**照安裝器命名慣例**的假實例（不是 leo 的實例，不碰 leo21c）跑真正的
|
||||
* 解析程式碼（planResources / applyResourcePlan / renderWranglerToml），對照更新前後：
|
||||
* ① 工作流數、登入狀態、子庫數 ② 帳號上的資源顆數 ③ 找不到既有資源時要停手
|
||||
*/
|
||||
|
||||
import { test } from 'node:test';
|
||||
import assert from 'node:assert/strict';
|
||||
import { readFileSync } from 'node:fs';
|
||||
import { join } from 'node:path';
|
||||
import { fileURLToPath } from 'node:url';
|
||||
|
||||
import {
|
||||
planResources,
|
||||
applyResourcePlan,
|
||||
parseWranglerRequirements,
|
||||
bindingKey,
|
||||
ResourcePlanBlocked,
|
||||
type BindingRequirement,
|
||||
type ResourceApi,
|
||||
type ScriptBindings,
|
||||
type LiveBinding,
|
||||
type ResolvedResource,
|
||||
} from '../src/lib/resource-resolver.ts';
|
||||
import {
|
||||
renderWranglerToml,
|
||||
REQUIRED_KV_NAMESPACES,
|
||||
type DeployContext,
|
||||
} from '../src/lib/deploy.ts';
|
||||
import { CfAccountClient } from '../src/lib/cf-api.ts';
|
||||
|
||||
const REPO = join(fileURLToPath(new URL('.', import.meta.url)), '..', '..');
|
||||
|
||||
/** 這台假實例上跑著的四顆 worker（有資源綁定的那幾顆）。 */
|
||||
const WORKER_TOMLS = [
|
||||
'cypher-executor/wrangler.toml',
|
||||
'registry/wrangler.toml',
|
||||
'mcp/wrangler.toml',
|
||||
'kbdb/wrangler.toml',
|
||||
];
|
||||
|
||||
const CTX: DeployContext = {
|
||||
accountId: 'acct-test',
|
||||
apiToken: 'tok-test',
|
||||
workerSubdomain: 'yuga3bse',
|
||||
selfHosted: true,
|
||||
kbdbEmbed: true,
|
||||
};
|
||||
|
||||
// ─────────────────────────────────────────────────────────────────────────────
|
||||
// 假的 Cloudflare 帳號：完全照「安裝器裝出來」的樣子命名
|
||||
// ─────────────────────────────────────────────────────────────────────────────
|
||||
|
||||
const INSTANCE = 'yuga3bse';
|
||||
|
||||
interface FakeOpts {
|
||||
/** 讓某顆 worker 的綁定讀取失敗（模擬 API 掛掉 / 權限不足）。 */
|
||||
failBindingsFor?: string;
|
||||
/** 從帳號上「弄不見」某顆 KV，但 worker 上還綁著它（模擬資源被刪）。 */
|
||||
deleteKvTitle?: string;
|
||||
/** 完全沒有任何已部署的 worker（模擬名字對不上 / token 看錯帳號）。 */
|
||||
nothingDeployed?: boolean;
|
||||
}
|
||||
|
||||
class FakeCloudflare implements ResourceApi {
|
||||
/** title → id */
|
||||
kv = new Map<string, string>();
|
||||
/** name → uuid */
|
||||
d1 = new Map<string, string>();
|
||||
vectorize: string[] = [];
|
||||
/** script → bindings */
|
||||
scripts = new Map<string, LiveBinding[]>();
|
||||
|
||||
/** 使用者的東西：kvId → (key → value) */
|
||||
kvData = new Map<string, Map<string, string>>();
|
||||
/** d1Id → 子庫名單 */
|
||||
d1Libraries = new Map<string, string[]>();
|
||||
|
||||
/** 這趟總共建立了什麼（驗「顆數不增加」用）。 */
|
||||
createdKv: string[] = [];
|
||||
createdD1: string[] = [];
|
||||
createdVectorize: string[] = [];
|
||||
|
||||
constructor(private opts: FakeOpts = {}) {
|
||||
// 安裝器的命名慣例：arcrun-rag-<instance>-kv-<binding 小寫>
|
||||
for (const binding of REQUIRED_KV_NAMESPACES) {
|
||||
const title = `arcrun-rag-${INSTANCE}-kv-${binding.toLowerCase()}`;
|
||||
const id = `kvid-${binding.toLowerCase()}`;
|
||||
this.kv.set(title, id);
|
||||
this.kvData.set(id, new Map());
|
||||
}
|
||||
this.d1.set(`arcrun-rag-${INSTANCE}-kbdb`, 'd1id-kbdb');
|
||||
this.vectorize.push(`arcrun-rag-${INSTANCE}-embed`);
|
||||
|
||||
// 使用者的東西
|
||||
this.kvData.get('kvid-webhooks')!.set('webhook:leo:daily-digest', '{}');
|
||||
this.kvData.get('kvid-webhooks')!.set('webhook:leo:inbox-sync', '{}');
|
||||
this.kvData.get('kvid-webhooks')!.set('webhook:leo:rag-ingest', '{}');
|
||||
this.kvData.get('kvid-sessions_kv')!.set('session:leo-abc123', '{"user":"leo"}');
|
||||
this.d1Libraries.set('d1id-kbdb', ['general', '課程', '客戶', '研究']);
|
||||
|
||||
if (!opts.nothingDeployed) {
|
||||
const kvB = (b: string): LiveBinding =>
|
||||
({ kind: 'kv_namespace', binding: b, value: `kvid-${b.toLowerCase()}` });
|
||||
this.scripts.set('arcrun-cypher-executor', [
|
||||
kvB('EXEC_CONTEXT'), kvB('WEBHOOKS'), kvB('CREDENTIALS_KV'), kvB('ANALYTICS_KV'),
|
||||
kvB('RECIPES'), kvB('USERS_KV'), kvB('SESSIONS_KV'),
|
||||
{ kind: 'd1', binding: 'CREDENTIALS_DB', value: 'd1id-kbdb' },
|
||||
]);
|
||||
this.scripts.set('arcrun-registry', [kvB('SUBMISSIONS_KV'), kvB('ANALYTICS_KV')]);
|
||||
this.scripts.set('arcrun-mcp', [kvB('OAUTH_KV')]);
|
||||
this.scripts.set('arcrun-kbdb', [
|
||||
{ kind: 'd1', binding: 'DB', value: 'd1id-kbdb' },
|
||||
{ kind: 'vectorize', binding: 'VECTORIZE', value: `arcrun-rag-${INSTANCE}-embed` },
|
||||
]);
|
||||
}
|
||||
|
||||
if (opts.deleteKvTitle) this.kv.delete(opts.deleteKvTitle);
|
||||
}
|
||||
|
||||
async getScriptBindings(script: string): Promise<ScriptBindings> {
|
||||
if (this.opts.failBindingsFor === script) throw new Error('HTTP 500 (CF API 暫時掛掉)');
|
||||
const b = this.scripts.get(script);
|
||||
return b ? { deployed: true, bindings: b } : { deployed: false, bindings: [] };
|
||||
}
|
||||
async listKvNamespaces(): Promise<Map<string, string>> { return new Map(this.kv); }
|
||||
async listD1Databases(): Promise<Map<string, string>> { return new Map(this.d1); }
|
||||
async listVectorizeIndexes(): Promise<string[]> { return [...this.vectorize]; }
|
||||
async createKvNamespace(title: string): Promise<string> {
|
||||
const id = `NEW-kvid-${this.createdKv.length}`;
|
||||
this.kv.set(title, id);
|
||||
this.kvData.set(id, new Map()); // 新建的是**空的**——災情就是綁到這種東西上
|
||||
this.createdKv.push(title);
|
||||
return id;
|
||||
}
|
||||
async createD1Database(name: string): Promise<string> {
|
||||
const id = `NEW-d1id-${this.createdD1.length}`;
|
||||
this.d1.set(name, id);
|
||||
this.d1Libraries.set(id, []);
|
||||
this.createdD1.push(name);
|
||||
return id;
|
||||
}
|
||||
async createVectorizeIndex(name: string): Promise<string> {
|
||||
this.vectorize.push(name);
|
||||
this.createdVectorize.push(name);
|
||||
return name;
|
||||
}
|
||||
}
|
||||
|
||||
// ─────────────────────────────────────────────────────────────────────────────
|
||||
// 共用：從真的 wrangler.toml 解析需求（走與 downloadAndDeploy 相同的路徑）
|
||||
// ─────────────────────────────────────────────────────────────────────────────
|
||||
|
||||
function collectRequirements(): { requirements: BindingRequirement[]; tomls: Map<string, string> } {
|
||||
const requirements: BindingRequirement[] = [];
|
||||
const tomls = new Map<string, string>();
|
||||
for (const rel of WORKER_TOMLS) {
|
||||
const raw = readFileSync(join(REPO, rel), 'utf8');
|
||||
tomls.set(rel, raw);
|
||||
const parsed = parseWranglerRequirements(renderWranglerToml(raw, CTX, new Map()));
|
||||
for (const b of parsed.bindings) requirements.push({ ...b, worker: parsed.script });
|
||||
}
|
||||
return { requirements, tomls };
|
||||
}
|
||||
|
||||
/** 模擬「部署」：把解析結果注入 toml，再從注入後的 toml 讀回 worker 實際會綁到的資源。 */
|
||||
function deployAndReadBindings(
|
||||
tomls: Map<string, string>,
|
||||
resolved: Map<string, ResolvedResource>,
|
||||
): Map<string, Map<string, string>> {
|
||||
const out = new Map<string, Map<string, string>>();
|
||||
for (const [rel, raw] of tomls) {
|
||||
const rendered = renderWranglerToml(raw, CTX, resolved);
|
||||
const script = parseWranglerRequirements(rendered).script;
|
||||
const bound = new Map<string, string>();
|
||||
let kind: string | null = null;
|
||||
let binding = '';
|
||||
for (const line of rendered.split('\n')) {
|
||||
const t = line.trim();
|
||||
if (t.startsWith('#')) continue;
|
||||
const table = t.match(/^\[\[?([A-Za-z0-9_]+)\]?\]$/);
|
||||
if (table) { kind = table[1]; binding = ''; continue; }
|
||||
const m = t.match(/^([A-Za-z0-9_]+)\s*=\s*"([^"]*)"/);
|
||||
if (!m) continue;
|
||||
if (m[1] === 'binding') binding = m[2];
|
||||
else if (binding && (
|
||||
(kind === 'kv_namespaces' && m[1] === 'id')
|
||||
|| (kind === 'd1_databases' && m[1] === 'database_id')
|
||||
|| (kind === 'vectorize' && m[1] === 'index_name')
|
||||
)) bound.set(binding, m[2]);
|
||||
}
|
||||
out.set(script, bound);
|
||||
}
|
||||
return out;
|
||||
}
|
||||
|
||||
// ═════════════════════════════════════════════════════════════════════════════
|
||||
// ① 更新前後：工作流數、登入狀態、子庫數 —— 三個都不能少
|
||||
// ═════════════════════════════════════════════════════════════════════════════
|
||||
|
||||
test('#97 ①：安裝器裝出來的實例跑更新——工作流／登入／子庫更新前後完全一致', async () => {
|
||||
const cf = new FakeCloudflare();
|
||||
const { requirements, tomls } = collectRequirements();
|
||||
|
||||
const before = {
|
||||
workflows: cf.kvData.get('kvid-webhooks')!.size,
|
||||
sessions: cf.kvData.get('kvid-sessions_kv')!.size,
|
||||
libraries: cf.d1Libraries.get('d1id-kbdb')!.length,
|
||||
};
|
||||
assert.deepEqual(before, { workflows: 3, sessions: 1, libraries: 4 }, '前置資料要先擺好');
|
||||
|
||||
const plan = await planResources(cf, requirements, 'update');
|
||||
assert.deepEqual(plan.blockers, [], '一台健康的實例不該有任何 blocker');
|
||||
const resolved = await applyResourcePlan(cf, plan);
|
||||
|
||||
const bound = deployAndReadBindings(tomls, resolved);
|
||||
|
||||
// 更新後，worker 綁到的還是使用者原本那幾顆（名字完全沒對上，但那不重要）
|
||||
const cypher = bound.get('arcrun-cypher-executor')!;
|
||||
assert.equal(cypher.get('WEBHOOKS'), 'kvid-webhooks');
|
||||
assert.equal(cypher.get('SESSIONS_KV'), 'kvid-sessions_kv');
|
||||
assert.equal(cypher.get('CREDENTIALS_DB'), 'd1id-kbdb');
|
||||
assert.equal(bound.get('arcrun-kbdb')!.get('DB'), 'd1id-kbdb');
|
||||
assert.equal(bound.get('arcrun-mcp')!.get('OAUTH_KV'), 'kvid-oauth_kv');
|
||||
assert.equal(bound.get('arcrun-registry')!.get('SUBMISSIONS_KV'), 'kvid-submissions_kv');
|
||||
assert.equal(bound.get('arcrun-kbdb')!.get('VECTORIZE'), `arcrun-rag-${INSTANCE}-embed`);
|
||||
|
||||
const after = {
|
||||
workflows: cf.kvData.get(cypher.get('WEBHOOKS')!)!.size,
|
||||
sessions: cf.kvData.get(cypher.get('SESSIONS_KV')!)!.size,
|
||||
libraries: cf.d1Libraries.get(bound.get('arcrun-kbdb')!.get('DB')!)!.length,
|
||||
};
|
||||
assert.deepEqual(after, before, '更新後使用者看到的東西必須跟更新前一模一樣');
|
||||
});
|
||||
|
||||
// ═════════════════════════════════════════════════════════════════════════════
|
||||
// ② 帳號上的資源顆數不增加（災情當天：9 顆 KV → 18 顆、1 顆 D1 → 2 顆）
|
||||
// ═════════════════════════════════════════════════════════════════════════════
|
||||
|
||||
test('#97 ②：更新不會在帳號上多生任何資源', async () => {
|
||||
const cf = new FakeCloudflare();
|
||||
const kvBefore = cf.kv.size;
|
||||
const d1Before = cf.d1.size;
|
||||
const vecBefore = cf.vectorize.length;
|
||||
assert.deepEqual([kvBefore, d1Before, vecBefore], [9, 1, 1]);
|
||||
|
||||
const { requirements } = collectRequirements();
|
||||
const plan = await planResources(cf, requirements, 'update');
|
||||
await applyResourcePlan(cf, plan);
|
||||
|
||||
assert.deepEqual(cf.createdKv, [], '不該新建任何 KV');
|
||||
assert.deepEqual(cf.createdD1, [], '不該新建任何 D1');
|
||||
assert.deepEqual(cf.createdVectorize, [], '不該新建任何 Vectorize index');
|
||||
assert.deepEqual([cf.kv.size, cf.d1.size, cf.vectorize.length], [9, 1, 1]);
|
||||
});
|
||||
|
||||
test('#97 ②對照組：舊的「照名字 ensure」在同一台實例上會生 9 顆 KV + 1 顆 D1', async () => {
|
||||
// 這段是**修好之前**的演算法（commit e69d6bb 時的 cli/src/commands/update.ts:52-68 與
|
||||
// cf-api.ts 的 ensureKvNamespace/ensureD1Database），照原樣重寫在這裡當對照組。
|
||||
// 目的：把「災情是怎麼發生的」釘成可執行的事實，而不是只留在 issue 的文字裡。
|
||||
const cf = new FakeCloudflare();
|
||||
const existing = await cf.listKvNamespaces();
|
||||
for (const title of REQUIRED_KV_NAMESPACES) {
|
||||
if (!existing.get(title)) await cf.createKvNamespace(title); // ← 名字對不上 ⇒ 每個都新建
|
||||
}
|
||||
const d1s = await cf.listD1Databases();
|
||||
if (!d1s.get('arcrun-kbdb')) await cf.createD1Database('arcrun-kbdb');
|
||||
|
||||
assert.equal(cf.createdKv.length, 9, '舊做法：9 顆 KV 全部重建（對上災情當天的數字）');
|
||||
assert.equal(cf.createdD1.length, 1, '舊做法：D1 也重建一顆');
|
||||
assert.equal(cf.kv.size, 18, '9 → 18');
|
||||
assert.equal(cf.d1.size, 2, '1 → 2');
|
||||
// 而且新建的那幾顆是空的 —— 使用者的工作流就是這樣「不見」的
|
||||
assert.equal(cf.kvData.get(cf.kv.get('WEBHOOKS')!)!.size, 0);
|
||||
});
|
||||
|
||||
// ═════════════════════════════════════════════════════════════════════════════
|
||||
// ③ 反向驗證：找不到既有資源 → 停下來說清楚，不是安靜新建一顆綁上去
|
||||
// ═════════════════════════════════════════════════════════════════════════════
|
||||
|
||||
test('#97 ③-a：worker 綁著的 KV 在帳號上不見了 → 停手，一顆都不建', async () => {
|
||||
const cf = new FakeCloudflare({ deleteKvTitle: `arcrun-rag-${INSTANCE}-kv-webhooks` });
|
||||
const { requirements } = collectRequirements();
|
||||
|
||||
const plan = await planResources(cf, requirements, 'update');
|
||||
assert.ok(plan.blockers.length > 0, '要有 blocker');
|
||||
const said = plan.blockers.join('\n');
|
||||
assert.match(said, /WEBHOOKS/, '要指名是哪個綁定');
|
||||
assert.match(said, /kvid-webhooks/, '要指名是哪一顆資源');
|
||||
assert.match(said, /找不到/, '要說清楚發生什麼事');
|
||||
assert.ok(!plan.create.some((c) => c.binding === 'WEBHOOKS'), '絕不能把它排進「要新建」');
|
||||
|
||||
await assert.rejects(() => applyResourcePlan(cf, plan), ResourcePlanBlocked);
|
||||
assert.deepEqual(cf.createdKv, [], '被擋下時一顆資源都不能被建出來');
|
||||
assert.deepEqual(cf.createdD1, []);
|
||||
});
|
||||
|
||||
test('#97 ③-b：讀不到某顆 worker 現在綁什麼 → 當「我不知道」而不是「它沒有」', async () => {
|
||||
const cf = new FakeCloudflare({ failBindingsFor: 'arcrun-cypher-executor' });
|
||||
const { requirements } = collectRequirements();
|
||||
|
||||
const plan = await planResources(cf, requirements, 'update');
|
||||
assert.match(plan.blockers.join('\n'), /arcrun-cypher-executor/);
|
||||
await assert.rejects(() => applyResourcePlan(cf, plan), ResourcePlanBlocked);
|
||||
assert.deepEqual(cf.createdKv, []);
|
||||
});
|
||||
|
||||
test('#97 ③-c：update 卻一顆 worker 都找不到 → 停手，不當成全新安裝重建一整套', async () => {
|
||||
const cf = new FakeCloudflare({ nothingDeployed: true });
|
||||
const { requirements } = collectRequirements();
|
||||
|
||||
const plan = await planResources(cf, requirements, 'update');
|
||||
assert.match(plan.blockers.join('\n'), /找不到任何一顆要更新的 worker/);
|
||||
await assert.rejects(() => applyResourcePlan(cf, plan), ResourcePlanBlocked);
|
||||
assert.deepEqual(cf.createdKv, []);
|
||||
});
|
||||
|
||||
test('#97 ③-d：同一個 binding 在不同 worker 上指向不同資源 → 不猜，停手', async () => {
|
||||
const cf = new FakeCloudflare();
|
||||
// registry 的 ANALYTICS_KV 被指到別顆（真實情境：有人手動改過其中一邊）
|
||||
cf.scripts.get('arcrun-registry')!.find((b) => b.binding === 'ANALYTICS_KV')!.value = 'kvid-other';
|
||||
cf.kv.set('some-other-kv', 'kvid-other');
|
||||
const { requirements } = collectRequirements();
|
||||
|
||||
const plan = await planResources(cf, requirements, 'update');
|
||||
assert.match(plan.blockers.join('\n'), /ANALYTICS_KV/);
|
||||
assert.deepEqual(cf.createdKv, []);
|
||||
});
|
||||
|
||||
// ═════════════════════════════════════════════════════════════════════════════
|
||||
// 合法的新建：只有「確定沒人綁過」時才准
|
||||
// ═════════════════════════════════════════════════════════════════════════════
|
||||
|
||||
test('#97：新版本新增的 binding（沒有任何已部署 worker 綁過）才准新建', async () => {
|
||||
const cf = new FakeCloudflare();
|
||||
cf.scripts.set('arcrun-mcp', []); // mcp 已部署，但還沒有 OAUTH_KV（舊版本裝的）
|
||||
cf.kv.delete(`arcrun-rag-${INSTANCE}-kv-oauth_kv`);
|
||||
const { requirements } = collectRequirements();
|
||||
|
||||
const plan = await planResources(cf, requirements, 'update');
|
||||
assert.deepEqual(plan.blockers, []);
|
||||
assert.deepEqual(plan.create.map((c) => c.binding), ['OAUTH_KV'], '只有這一個該建');
|
||||
await applyResourcePlan(cf, plan);
|
||||
assert.deepEqual(cf.createdKv, ['OAUTH_KV']);
|
||||
assert.equal(cf.kv.size, 9, '刪掉一顆、補建一顆 → 還是 9 顆');
|
||||
});
|
||||
|
||||
test('#97：全新帳號跑 init → 該建的都建（不會被 update 的停手規則卡住）', async () => {
|
||||
const cf = new FakeCloudflare({ nothingDeployed: true });
|
||||
cf.kv.clear(); cf.d1.clear(); cf.vectorize.length = 0;
|
||||
const { requirements } = collectRequirements();
|
||||
|
||||
const plan = await planResources(cf, requirements, 'init');
|
||||
assert.deepEqual(plan.blockers, [], 'init 在空帳號上不該停手');
|
||||
await applyResourcePlan(cf, plan);
|
||||
assert.equal(cf.createdKv.length, REQUIRED_KV_NAMESPACES.length);
|
||||
assert.deepEqual(cf.createdD1, ['arcrun-kbdb']);
|
||||
assert.equal(cf.createdVectorize.length, 1);
|
||||
});
|
||||
|
||||
test('#97：一邊已部署一邊沒有 → 跟著沿用同一顆，不要另外建一顆空的', async () => {
|
||||
const cf = new FakeCloudflare();
|
||||
cf.scripts.delete('arcrun-cypher-executor'); // cypher 還沒部（kbdb 已部，DB → d1id-kbdb）
|
||||
const { requirements, tomls } = collectRequirements();
|
||||
|
||||
const plan = await planResources(cf, requirements, 'update');
|
||||
assert.deepEqual(plan.blockers, []);
|
||||
assert.ok(!plan.create.some((c) => c.kind === 'd1'), 'CREDENTIALS_DB 不該被當成新資源建一顆');
|
||||
|
||||
const resolved = await applyResourcePlan(cf, plan);
|
||||
const bound = deployAndReadBindings(tomls, resolved);
|
||||
assert.equal(bound.get('arcrun-cypher-executor')!.get('CREDENTIALS_DB'), 'd1id-kbdb',
|
||||
'credential 目錄要跟 KBDB 在同一顆庫');
|
||||
assert.deepEqual(cf.createdD1, []);
|
||||
});
|
||||
|
||||
test('#97：部署出去的 toml 不得殘留官方 prod 的資源 id（自架寫進官方庫 = 跨租戶外洩）', async () => {
|
||||
// repo 的 toml 裡 database_id 預設是官方 prod D1。舊版在「D1 解析失敗」時只是把它跳過不注入，
|
||||
// 於是自架用戶的 kbdb worker 就這樣綁著官方那顆庫部署出去。現在不是失敗就跳過，是整趟停手。
|
||||
const cf = new FakeCloudflare();
|
||||
const { requirements, tomls } = collectRequirements();
|
||||
const resolved = await applyResourcePlan(cf, await planResources(cf, requirements, 'update'));
|
||||
|
||||
const OFFICIAL_D1 = '0c580910-e00b-4f8e-9c57-ac54ea52242f';
|
||||
for (const [rel, raw] of tomls) {
|
||||
const rendered = renderWranglerToml(raw, CTX, resolved);
|
||||
assert.doesNotMatch(rendered, new RegExp(OFFICIAL_D1), `${rel} 還帶著官方 prod D1 的 id`);
|
||||
assert.doesNotMatch(rendered, /REPLACE_WITH_REAL_KV_ID/, `${rel} 還留著占位 KV id`);
|
||||
}
|
||||
});
|
||||
|
||||
// ═════════════════════════════════════════════════════════════════════════════
|
||||
// 做法本身的看守：不准再出現「照名字 ensure」這種原語
|
||||
// ═════════════════════════════════════════════════════════════════════════════
|
||||
|
||||
test('#97 紅線：cf-api 不得再提供任何「找不到同名就順手建一顆」的 ensure 原語', () => {
|
||||
const src = readFileSync(join(REPO, 'cli/src/lib/cf-api.ts'), 'utf8');
|
||||
assert.doesNotMatch(src, /\bensureKvNamespace\b|\bensureD1Database\b|\bensureVectorizeIndex\b/,
|
||||
'ensure* 是 #97 的凶器：把「查不到」當成「不存在」再自作主張新建。'
|
||||
+ '要建資源一律先過 resource-resolver 的 planResources。');
|
||||
});
|
||||
|
||||
test('#97 紅線：只有 resource-resolver 能決定「要不要建」，指令層不得自己呼叫 create*', () => {
|
||||
for (const rel of ['cli/src/commands/init.ts', 'cli/src/commands/update.ts']) {
|
||||
const src = readFileSync(join(REPO, rel), 'utf8');
|
||||
assert.doesNotMatch(src, /\.create(KvNamespace|D1Database|VectorizeIndex)\s*\(/,
|
||||
`${rel} 不該自己建資源——那樣就繞過了「先看已部署的 worker 綁著什麼」這道判斷。`);
|
||||
}
|
||||
});
|
||||
|
||||
// ═════════════════════════════════════════════════════════════════════════════
|
||||
// 底層零件
|
||||
// ═════════════════════════════════════════════════════════════════════════════
|
||||
|
||||
test('parseWranglerRequirements：讀得出 script 名與三種資源綁定，且不把註解掉的區塊當需求', () => {
|
||||
const toml = [
|
||||
'name = "arcrun-kbdb" # 註解不影響',
|
||||
'',
|
||||
'[[d1_databases]]',
|
||||
'binding = "DB"',
|
||||
'database_name = "arcrun-kbdb"',
|
||||
'database_id = "placeholder"',
|
||||
'',
|
||||
'[vars]',
|
||||
'ENVIRONMENT = "production"',
|
||||
'',
|
||||
'# [[vectorize]]',
|
||||
'# binding = "VECTORIZE"',
|
||||
'# index_name = "arcrun-kbdb-embed-m3"',
|
||||
].join('\n');
|
||||
const r = parseWranglerRequirements(toml);
|
||||
assert.equal(r.script, 'arcrun-kbdb');
|
||||
assert.deepEqual(r.bindings, [{ kind: 'd1', binding: 'DB', createName: 'arcrun-kbdb' }]);
|
||||
});
|
||||
|
||||
test('KV 沒有 title 欄位 → 真要新建時用 binding 名', () => {
|
||||
const r = parseWranglerRequirements('name = "w"\n[[kv_namespaces]]\nbinding = "WEBHOOKS"\nid = "x"');
|
||||
assert.deepEqual(r.bindings, [{ kind: 'kv_namespace', binding: 'WEBHOOKS', createName: 'WEBHOOKS' }]);
|
||||
});
|
||||
|
||||
test('注入是照 binding 對號，不是盲換「檔案裡第一個 database_id」', () => {
|
||||
const cypher = readFileSync(join(REPO, 'cypher-executor/wrangler.toml'), 'utf8');
|
||||
const resolved = new Map<string, ResolvedResource>([
|
||||
[bindingKey('d1', 'CREDENTIALS_DB'), { kind: 'd1', binding: 'CREDENTIALS_DB', value: 'MINE', origin: 'adopted' }],
|
||||
[bindingKey('kv_namespace', 'WEBHOOKS'), { kind: 'kv_namespace', binding: 'WEBHOOKS', value: 'KV-MINE', origin: 'adopted' }],
|
||||
]);
|
||||
const out = renderWranglerToml(cypher, CTX, resolved);
|
||||
const bound = parseWranglerRequirements(out);
|
||||
assert.ok(bound.bindings.some((b) => b.binding === 'CREDENTIALS_DB'));
|
||||
assert.match(out, /binding = "CREDENTIALS_DB"\ndatabase_name = "arcrun-kbdb"\ndatabase_id = "MINE"/);
|
||||
assert.match(out, /binding = "WEBHOOKS"\nid = "KV-MINE"/);
|
||||
// 沒被解析到的綁定不能被亂改（EXEC_CONTEXT 這次沒進 resolved）
|
||||
assert.match(out, /binding = "EXEC_CONTEXT"\nid = "616967a852eb450a8c01731f71ac8edd"/);
|
||||
});
|
||||
|
||||
test('renderWranglerToml 帶空 map = 預覽：解析看到的 binding 與注入後的完全一致', () => {
|
||||
for (const rel of WORKER_TOMLS) {
|
||||
const raw = readFileSync(join(REPO, rel), 'utf8');
|
||||
const preview = parseWranglerRequirements(renderWranglerToml(raw, CTX, new Map()));
|
||||
const resolved = new Map<string, ResolvedResource>(
|
||||
preview.bindings.map((b) => [
|
||||
bindingKey(b.kind, b.binding),
|
||||
{ kind: b.kind, binding: b.binding, value: `v-${b.binding}`, origin: 'adopted' as const },
|
||||
]),
|
||||
);
|
||||
const after = parseWranglerRequirements(renderWranglerToml(raw, CTX, resolved));
|
||||
assert.deepEqual(
|
||||
after.bindings.map((b) => `${b.kind}:${b.binding}`).sort(),
|
||||
preview.bindings.map((b) => `${b.kind}:${b.binding}`).sort(),
|
||||
`${rel}: 預覽與實際注入看到的綁定必須一致`,
|
||||
);
|
||||
}
|
||||
});
|
||||
|
||||
test('repo 的 toml 綁定總集合 = REQUIRED_KV_NAMESPACES（漏綁會讓某顆 worker 部署失敗）', () => {
|
||||
const { requirements } = collectRequirements();
|
||||
const kv = [...new Set(requirements.filter((r) => r.kind === 'kv_namespace').map((r) => r.binding))];
|
||||
assert.deepEqual(kv.sort(), [...REQUIRED_KV_NAMESPACES].sort());
|
||||
});
|
||||
|
||||
test('CfAccountClient.getScriptBindings：404 = 還沒部署；其他錯誤要 throw（不能當成「沒有綁」）', async () => {
|
||||
const orig = globalThis.fetch;
|
||||
try {
|
||||
globalThis.fetch = (async () =>
|
||||
new Response(JSON.stringify({ success: false, errors: [{ message: 'not found' }] }), { status: 404 })
|
||||
) as typeof fetch;
|
||||
const cf = new CfAccountClient('a', 't');
|
||||
assert.deepEqual(await cf.getScriptBindings('nope'), { deployed: false, bindings: [] });
|
||||
|
||||
globalThis.fetch = (async () =>
|
||||
new Response(JSON.stringify({ success: false, errors: [{ message: 'boom' }] }), { status: 500 })
|
||||
) as typeof fetch;
|
||||
await assert.rejects(() => new CfAccountClient('a', 't').getScriptBindings('x'), /boom/);
|
||||
} finally {
|
||||
globalThis.fetch = orig;
|
||||
}
|
||||
});
|
||||
|
||||
test('CfAccountClient.getScriptBindings：讀得懂 CF 回的 kv/d1/vectorize 三種綁定形狀', async () => {
|
||||
const orig = globalThis.fetch;
|
||||
try {
|
||||
globalThis.fetch = (async () => new Response(JSON.stringify({
|
||||
success: true,
|
||||
result: {
|
||||
bindings: [
|
||||
{ type: 'kv_namespace', name: 'WEBHOOKS', namespace_id: 'kv1' },
|
||||
{ type: 'd1', name: 'DB', id: 'db1' },
|
||||
{ type: 'vectorize', name: 'VECTORIZE', index_name: 'idx1' },
|
||||
{ type: 'plain_text', name: 'ENVIRONMENT', text: 'production' },
|
||||
{ type: 'service', name: 'SVC_SET', service: 'arcrun-set' },
|
||||
],
|
||||
},
|
||||
}), { status: 200 })) as typeof fetch;
|
||||
const res = await new CfAccountClient('a', 't').getScriptBindings('arcrun-cypher-executor');
|
||||
assert.equal(res.deployed, true);
|
||||
assert.deepEqual(res.bindings, [
|
||||
{ kind: 'kv_namespace', binding: 'WEBHOOKS', value: 'kv1' },
|
||||
{ kind: 'd1', binding: 'DB', value: 'db1' },
|
||||
{ kind: 'vectorize', binding: 'VECTORIZE', value: 'idx1' },
|
||||
]);
|
||||
} finally {
|
||||
globalThis.fetch = orig;
|
||||
}
|
||||
});
|
||||
@@ -1,6 +1,6 @@
|
||||
import type { ParsedTriplets, NodeRole } from './triplet-parser';
|
||||
import { resolveNodeRole, isVirtualIoName } from './triplet-parser';
|
||||
import { wasmWorkerUrl } from '../lib/component-loader';
|
||||
import { wasmWorkerUrl, RUNTIME_NATIVE_COMPONENT_IDS } from '../lib/component-loader';
|
||||
import { resolveRecipe } from '../routes/recipes';
|
||||
import type { RecipeDefinition } from '../routes/recipes';
|
||||
import { branchHintFor } from '../lib/branch-hints';
|
||||
@@ -44,8 +44,12 @@ export type NodeInfo = {
|
||||
status: NodeStatus;
|
||||
componentId?: string;
|
||||
type: NodeRole;
|
||||
/** found 時標來源庫：零件 registry（component）或 recipe 庫（recipe）。 */
|
||||
source?: 'component' | 'recipe';
|
||||
/**
|
||||
* found 時標來源庫：零件 registry（component）、recipe 庫（recipe），
|
||||
* 或 cypher-executor 自帶、無須查 registry 即保證解析得動的執行期原生零件（builtin，
|
||||
* Arcrun#88——component-loader.ts 的 RUNTIME_NATIVE_COMPONENT_IDS）。
|
||||
*/
|
||||
source?: 'component' | 'recipe' | 'builtin';
|
||||
/** 零件契約（found 時附上，讓 AI 知道怎麼填 payload）。 */
|
||||
input_schema?: unknown;
|
||||
/** 成功率（found 時附上，讓「被測過幾次」看得見）。 */
|
||||
@@ -212,6 +216,25 @@ export async function searchNodes(
|
||||
continue;
|
||||
}
|
||||
|
||||
// ── 執行期原生零件（Arcrun#88）：查 registry 之前先比對 ──────────────────
|
||||
// component-loader.ts 的 RUNTIME_NATIVE_COMPONENT_IDS＝trigger_workflow／
|
||||
// BUILTIN_COMPONENTS／LOGIC_BINDING_MAP／WASM_HTTP_RUNNER_IDS 的聯集——
|
||||
// 這些零件 cypher-executor 自己就能 resolve，從不查 registry，執行期保證解析得動。
|
||||
// 病史：registry 是空的／未部署新版 `/catalog` 端點時，這批零件（if_control／
|
||||
// http_request／switch…）會被下面「兩庫都查過沒有」誤判成 not_found——
|
||||
// 而 leo 08-11 實測探測工作流證明它們跑得動。命中即 found，不受 registry 健康狀態影響。
|
||||
// target=recipe（使用者明確只要查 recipe 庫）不適用——這些從來不是 recipe。
|
||||
if (wantComponents && RUNTIME_NATIVE_COMPONENT_IDS.has(componentId)) {
|
||||
nodeResults[nodeName] = {
|
||||
status: 'found',
|
||||
componentId,
|
||||
type: role,
|
||||
source: 'builtin',
|
||||
branch_hint: branchHintFor(componentId),
|
||||
};
|
||||
continue;
|
||||
}
|
||||
|
||||
// registry 完全查不通（未部署／網路失敗）⇒ 誠實回 unknown。
|
||||
// **不能誤判 not_found**——那會讓 AI 以為零件不存在而重寫 code，正是要避免的事。
|
||||
// 舊 registry 沒有 /catalog 端點（no_endpoint）→ 退回逐顆查（相容路徑）。
|
||||
|
||||
@@ -88,6 +88,33 @@ const LOGIC_BINDING_MAP: Record<string, keyof Bindings> = {
|
||||
// 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）。
|
||||
};
|
||||
|
||||
/**
|
||||
* 「查得到 vs 真的有」的單一真相源（Arcrun#88，2026-08-11）。
|
||||
*
|
||||
* 病因：`/cypher/search`（`search-nodes.ts`）只查 component registry（`SUBMISSIONS_KV`，
|
||||
* 經 `submitComponent`/`index-only` 才會有記錄）；而本檔 0/1/5/7 四步驟能直接解析、
|
||||
* **完全不查 registry** 的一整類零件（trigger_workflow、BUILTIN_COMPONENTS、
|
||||
* LOGIC_BINDING_MAP、WASM_HTTP_RUNNER_IDS）從未被 submit 過（也不需要——它們是
|
||||
* cypher-executor 自帶的，不是投稿存量）。實測 leo21c 實例：`/components/catalog`
|
||||
* 404（registry 是舊版沒這端點／索引空），search 因此對 `if_control`／`http_request`
|
||||
* 誠實地回「兩庫都查過沒有」——但這兩顆其實跑得動（leo 08-11 探測工作流已證）。
|
||||
*
|
||||
* 修法：把「執行期真的解析得動」的這份清單匯出給 search-nodes.ts，在查 registry
|
||||
* **之前**先比對——讓「查得到」不受 registry 是否可達／是否已 backfill 影響。
|
||||
*
|
||||
* 刻意不做的事：不去掃 `registry/components/*` 目錄當清單來源——那是零件原始碼
|
||||
* 存放處，含已標記待刪的死碼（`km_writer`／`kbdb_upsert_block`，見
|
||||
* `system-dev/docs/3-specs/arcrun-usable/cleanup-dead-code.md`）；07-30 曾把這類死碼
|
||||
* 誤灌進 registry（leo 點名的錯）。這裡改用**執行期真正拿去 resolve 的白名單本身**
|
||||
* （本檔 1/5/7 步驟既有的三份清單）——精確等於「解析得動」，不會多一顆、不會少一顆。
|
||||
*/
|
||||
export const RUNTIME_NATIVE_COMPONENT_IDS: ReadonlySet<string> = new Set([
|
||||
'trigger_workflow',
|
||||
...BUILTIN_COMPONENTS.keys(),
|
||||
...Object.keys(LOGIC_BINDING_MAP),
|
||||
...WASM_HTTP_RUNNER_IDS,
|
||||
]);
|
||||
|
||||
export function createComponentLoader(env: Bindings) {
|
||||
return async (componentId: string): Promise<ComponentRunner> => {
|
||||
|
||||
|
||||
@@ -0,0 +1,116 @@
|
||||
/**
|
||||
* Arcrun#88：「零件目錄會說『這顆零件不存在』，但同一台實例上那顆零件跑得動」
|
||||
*
|
||||
* 病史（leo21c 實例實測，2026-08-11）：
|
||||
* `/cypher/search` 對 `if_control`／`http_request` 回 `not_found`，
|
||||
* 但兩者其實由 component-loader.ts 直接解析（LOGIC_BINDING_MAP／WASM_HTTP_RUNNER_IDS），
|
||||
* 從不查 registry；registry catalog 端點在該實例回 404（`GET /components/catalog` →
|
||||
* `{"success":false,"error":"零件 catalog 不存在"}`），search 因此誤判成「兩庫都查過沒有」。
|
||||
*
|
||||
* 本測試複現病史的環境條件（wrangler.test.toml 未設 WORKER_SUBDOMAIN → registryBase
|
||||
* undefined → catalog.status='unreachable'，等價於「registry 完全連不到」），
|
||||
* 驗證修法：RUNTIME_NATIVE_COMPONENT_IDS 的成員必須在 registry 查詢**之前**就短路成 found，
|
||||
* 不受 registry 健康狀態影響——因為它們的存在性從不依賴 registry。
|
||||
*/
|
||||
import { describe, it, expect, vi, afterEach } from 'vitest';
|
||||
import { parseTriplets } from '../src/actions/triplet-parser';
|
||||
import { searchNodes } from '../src/actions/search-nodes';
|
||||
|
||||
afterEach(() => {
|
||||
vi.unstubAllGlobals();
|
||||
});
|
||||
|
||||
const IF_CONTROL_TRIPLETS = [
|
||||
'input >> ON_SUCCESS >> if_control',
|
||||
];
|
||||
|
||||
const HTTP_REQUEST_TRIPLETS = [
|
||||
'input >> ON_SUCCESS >> http_request',
|
||||
];
|
||||
|
||||
const MULTI_BUILTIN_TRIPLETS = [
|
||||
'input >> ON_SUCCESS >> switch',
|
||||
'input >> ON_SUCCESS >> filter',
|
||||
'input >> ON_SUCCESS >> code',
|
||||
];
|
||||
|
||||
const FAKE_COMPONENT_TRIPLETS = [
|
||||
'input >> ON_SUCCESS >> totally_made_up_component_xyz',
|
||||
];
|
||||
|
||||
describe('Arcrun#88：執行期原生零件不受 registry 健康狀態影響', () => {
|
||||
it('if_control（LOGIC_BINDING_MAP 成員）在 registry 不可達時仍回 found', async () => {
|
||||
const parsed = parseTriplets(IF_CONTROL_TRIPLETS);
|
||||
expect(parsed).not.toBeNull();
|
||||
const { nodeResults, missingNodes } = await searchNodes(parsed!, undefined, {
|
||||
// 無 WORKER_SUBDOMAIN／REGISTRY_BASE_URL → registryBase undefined → catalog unreachable
|
||||
});
|
||||
expect(nodeResults.if_control.status).toBe('found');
|
||||
expect(nodeResults.if_control.source).toBe('builtin');
|
||||
// if_control 會分岔，branch_hint 應隨 found 一併附上（不必逐顆再查一次）
|
||||
expect(nodeResults.if_control.branch_hint?.edge_types).toEqual(['ON_TRUE', 'ON_FALSE']);
|
||||
expect(missingNodes).not.toContain('if_control');
|
||||
});
|
||||
|
||||
it('http_request（WASM_HTTP_RUNNER_IDS 成員）在 registry 不可達時仍回 found', async () => {
|
||||
const parsed = parseTriplets(HTTP_REQUEST_TRIPLETS);
|
||||
const { nodeResults, missingNodes } = await searchNodes(parsed!, undefined, {});
|
||||
expect(nodeResults.http_request.status).toBe('found');
|
||||
expect(nodeResults.http_request.source).toBe('builtin');
|
||||
expect(missingNodes).not.toContain('http_request');
|
||||
});
|
||||
|
||||
it('switch／filter／code（同一批白名單的其他成員）也回 found，不逐一漏網', async () => {
|
||||
const parsed = parseTriplets(MULTI_BUILTIN_TRIPLETS);
|
||||
const { nodeResults } = await searchNodes(parsed!, undefined, {});
|
||||
expect(nodeResults.switch.status).toBe('found');
|
||||
expect(nodeResults.filter.status).toBe('found');
|
||||
expect(nodeResults.code.status).toBe('found');
|
||||
});
|
||||
|
||||
it('registry 完全連不到時，真正不存在的名字誠實回 unknown（不敢空口說沒有——既有行為，修法沒有動它）', async () => {
|
||||
const parsed = parseTriplets(FAKE_COMPONENT_TRIPLETS);
|
||||
const { nodeResults } = await searchNodes(parsed!, undefined, {});
|
||||
expect(nodeResults.totally_made_up_component_xyz.status).toBe('unknown');
|
||||
});
|
||||
|
||||
it('registry 查得到但目錄是空的（複現 leo21c 實例 catalog 404 的真實症狀）：真正不存在的名字回 not_found', async () => {
|
||||
// 複現生產實測：GET /components/catalog → HTTP 200 空陣列（本測試模擬「registry 活著但沒東西」，
|
||||
// 與 leo21c 實例的「404 零件 catalog 不存在」殊途同歸——都會落到「查得到、目錄無此零件」）。
|
||||
vi.stubGlobal('fetch', vi.fn(async () =>
|
||||
new Response(JSON.stringify({ success: true, data: { components: [], count: 0 } }), {
|
||||
status: 200,
|
||||
headers: { 'Content-Type': 'application/json' },
|
||||
}),
|
||||
));
|
||||
const parsed = parseTriplets(FAKE_COMPONENT_TRIPLETS);
|
||||
const { nodeResults, missingNodes } = await searchNodes(parsed!, undefined, {
|
||||
WORKER_SUBDOMAIN: 'test-sub',
|
||||
});
|
||||
expect(nodeResults.totally_made_up_component_xyz.status).toBe('not_found');
|
||||
expect(missingNodes).toContain('totally_made_up_component_xyz');
|
||||
});
|
||||
|
||||
it('registry 目錄是空的（catalog 通但無資料）時，執行期原生零件依然 found——這才是 Arcrun#88 的核心場景', async () => {
|
||||
// 這就是 leo21c 實例的真實狀態：registry 活著、目錄卻沒有任何一顆執行期原生零件的記錄
|
||||
// （SUBMISSIONS_KV 從未收到 if_control/http_request 的 submit）。若沒有本次修法，
|
||||
// 這裡會落到「兩庫都查過沒有」→ not_found，正是 Arcrun#88 回報的病徵。
|
||||
vi.stubGlobal('fetch', vi.fn(async () =>
|
||||
new Response(JSON.stringify({ success: true, data: { components: [], count: 0 } }), {
|
||||
status: 200,
|
||||
headers: { 'Content-Type': 'application/json' },
|
||||
}),
|
||||
));
|
||||
const parsed = parseTriplets(IF_CONTROL_TRIPLETS);
|
||||
const { nodeResults } = await searchNodes(parsed!, undefined, { WORKER_SUBDOMAIN: 'test-sub' });
|
||||
expect(nodeResults.if_control.status).toBe('found');
|
||||
expect(nodeResults.if_control.source).toBe('builtin');
|
||||
});
|
||||
|
||||
it('target=recipe 明確只查 recipe 庫時，執行期原生零件不搶答 found（尊重使用者明確限庫）', async () => {
|
||||
const parsed = parseTriplets(IF_CONTROL_TRIPLETS);
|
||||
const { nodeResults } = await searchNodes(parsed!, undefined, {}, 'discover', 'recipe');
|
||||
// if_control 從來不是 recipe，target=recipe 下不該被 builtin 短路成 found
|
||||
expect(nodeResults.if_control.status).not.toBe('found');
|
||||
});
|
||||
});
|
||||
@@ -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(
|
||||
|
||||
@@ -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)
|
||||
|
||||
@@ -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