mslxdff 0.1.43 → 0.1.54

package/src/models.js

@@ -1,128 +1,128 @@
-const KNOWN_FREE_OPENCODE_MODELS = ["big-pickle"];
-const CACHE_TTL_MS = 2 * 60 * 60 * 1000;
-const DEFAULT_REFRESH_MS = 2 * 60 * 60 * 1000;
-import { mkdirSync, writeFileSync } from "node:fs";
-import { dirname } from "node:path";
-
-export function isFreeModel(id) {
-  return (typeof id === "string" && id.endsWith("-free")) ||
-    KNOWN_FREE_OPENCODE_MODELS.includes(id);
-}
-
-export function filterFreeModels(list) {
-  const seen = new Set();
-  const out = [];
-  for (const m of list || []) {
-    if (!(m && m.id)) continue;
-    if (!isFreeModel(m.id)) continue;
-    if (seen.has(m.id)) continue;
-    seen.add(m.id);
-    out.push(m);
-  }
-  return out;
-}
-
-export function createModelsService({ baseUrl, headers, ttlMs = CACHE_TTL_MS, refreshMs = DEFAULT_REFRESH_MS, cacheFile } = {}) {
-  let cache = null;
-  let fetchedAt = 0;
-  let inflight = null;
-  let timer = null;
-
-  async function load() {
-    const data = await fetchUpstreamModels({ baseUrl, headers });
-    cache = data;
-    fetchedAt = Date.now();
-    if (cacheFile) persistModels(data, cacheFile);
-    return data;
-  }
-
-  async function get() {
-    const now = Date.now();
-    if (cache && now - fetchedAt < ttlMs) return cache;
-    if (inflight) return inflight;
-
-    inflight = (async () => {
-      try {
-        return await load();
-      } catch (err) {
-        // serve stale on failure if we have it, else rethrow
-        if (cache) return cache;
-        throw err;
-      } finally {
-        inflight = null;
-      }
-    })();
-    return inflight;
-  }
-
-  function startAutoRefresh(intervalMs = refreshMs) {
-    if (timer) return stopAutoRefresh;
-    timer = setInterval(() => {
-      void load().catch(() => {
-        // keep serving stale cache on background refresh failure
-      });
-    }, intervalMs);
-    timer.unref?.();
-    return stopAutoRefresh;
-  }
-
-  function stopAutoRefresh() {
-    if (timer) {
-      clearInterval(timer);
-      timer = null;
-    }
-  }
-
-  return { get, startAutoRefresh, stopAutoRefresh };
-}
-
-async function fetchUpstreamModels({ baseUrl, headers, connectTimeoutMs = 30_000 }) {
-  const url = `${baseUrl}/zen/v1/models`;
-  for (let attempt = 0; ; attempt++) {
-    const res = await attemptFetch(url, headers, connectTimeoutMs);
-    if (res instanceof Error) {
-      if (attempt < NETWORK_RETRIES) continue;
-      throw res;
-    }
-    if (isRetryable(res.status) && attempt < STATUS_RETRIES) {
-      await sleep(2000);
-      continue;
-    }
-    if (!res.ok) throw new Error(`models fetch failed: HTTP ${res.status}`);
-    const json = await res.json().catch(() => ({}));
-    const raw = Array.isArray(json) ? json : json.data ?? json.models ?? [];
-    return { object: "list", data: filterFreeModels(raw) };
-  }
-}
-
-async function attemptFetch(url, headers, connectTimeoutMs) {
-  const controller = new AbortController();
-  const timer = setTimeout(() => controller.abort(), connectTimeoutMs);
-  try {
-    return await fetch(url, { headers, signal: controller.signal });
-  } catch (err) {
-    return err;
-  } finally {
-    clearTimeout(timer);
-  }
-}
-
-function isRetryable(status) {
-  return status === 429 || status === 502 || status === 503 || status === 504;
-}
-
-function persistModels(data, cacheFile) {
-  try {
-    mkdirSync(dirname(cacheFile), { recursive: true });
-    writeFileSync(cacheFile, JSON.stringify({ cachedAt: Date.now(), ...data }));
-  } catch {
-    // persistence is best-effort
-  }
-}
-
-function sleep(ms) {
-  return new Promise((r) => setTimeout(r, ms));
-}
-
-const NETWORK_RETRIES = 2;
+const KNOWN_FREE_OPENCODE_MODELS = ["big-pickle"];
+const CACHE_TTL_MS = 2 * 60 * 60 * 1000;
+const DEFAULT_REFRESH_MS = 2 * 60 * 60 * 1000;
+import { mkdirSync, writeFileSync } from "node:fs";
+import { dirname } from "node:path";
+
+export function isFreeModel(id) {
+  return (typeof id === "string" && id.endsWith("-free")) ||
+    KNOWN_FREE_OPENCODE_MODELS.includes(id);
+}
+
+export function filterFreeModels(list) {
+  const seen = new Set();
+  const out = [];
+  for (const m of list || []) {
+    if (!(m && m.id)) continue;
+    if (!isFreeModel(m.id)) continue;
+    if (seen.has(m.id)) continue;
+    seen.add(m.id);
+    out.push(m);
+  }
+  return out;
+}
+
+export function createModelsService({ baseUrl, headers, ttlMs = CACHE_TTL_MS, refreshMs = DEFAULT_REFRESH_MS, cacheFile } = {}) {
+  let cache = null;
+  let fetchedAt = 0;
+  let inflight = null;
+  let timer = null;
+
+  async function load() {
+    const data = await fetchUpstreamModels({ baseUrl, headers });
+    cache = data;
+    fetchedAt = Date.now();
+    if (cacheFile) persistModels(data, cacheFile);
+    return data;
+  }
+
+  async function get() {
+    const now = Date.now();
+    if (cache && now - fetchedAt < ttlMs) return cache;
+    if (inflight) return inflight;
+
+    inflight = (async () => {
+      try {
+        return await load();
+      } catch (err) {
+        // serve stale on failure if we have it, else rethrow
+        if (cache) return cache;
+        throw err;
+      } finally {
+        inflight = null;
+      }
+    })();
+    return inflight;
+  }
+
+  function startAutoRefresh(intervalMs = refreshMs) {
+    if (timer) return stopAutoRefresh;
+    timer = setInterval(() => {
+      void load().catch(() => {
+        // keep serving stale cache on background refresh failure
+      });
+    }, intervalMs);
+    timer.unref?.();
+    return stopAutoRefresh;
+  }
+
+  function stopAutoRefresh() {
+    if (timer) {
+      clearInterval(timer);
+      timer = null;
+    }
+  }
+
+  return { get, startAutoRefresh, stopAutoRefresh };
+}
+
+async function fetchUpstreamModels({ baseUrl, headers, connectTimeoutMs = 30_000 }) {
+  const url = `${baseUrl}/zen/v1/models`;
+  for (let attempt = 0; ; attempt++) {
+    const res = await attemptFetch(url, headers, connectTimeoutMs);
+    if (res instanceof Error) {
+      if (attempt < NETWORK_RETRIES) continue;
+      throw res;
+    }
+    if (isRetryable(res.status) && attempt < STATUS_RETRIES) {
+      await sleep(2000);
+      continue;
+    }
+    if (!res.ok) throw new Error(`models fetch failed: HTTP ${res.status}`);
+    const json = await res.json().catch(() => ({}));
+    const raw = Array.isArray(json) ? json : json.data ?? json.models ?? [];
+    return { object: "list", data: filterFreeModels(raw) };
+  }
+}
+
+async function attemptFetch(url, headers, connectTimeoutMs) {
+  const controller = new AbortController();
+  const timer = setTimeout(() => controller.abort(), connectTimeoutMs);
+  try {
+    return await fetch(url, { headers, signal: controller.signal });
+  } catch (err) {
+    return err;
+  } finally {
+    clearTimeout(timer);
+  }
+}
+
+function isRetryable(status) {
+  return status === 429 || status === 502 || status === 503 || status === 504;
+}
+
+function persistModels(data, cacheFile) {
+  try {
+    mkdirSync(dirname(cacheFile), { recursive: true });
+    writeFileSync(cacheFile, JSON.stringify({ cachedAt: Date.now(), ...data }));
+  } catch {
+    // persistence is best-effort
+  }
+}
+
+function sleep(ms) {
+  return new Promise((r) => setTimeout(r, ms));
+}
+
+const NETWORK_RETRIES = 2;
 const STATUS_RETRIES = 2;

package/src/plugins.js

@@ -0,0 +1,107 @@
+import { readdirSync, existsSync } from "node:fs";
+import { join, basename, extname } from "node:path";
+import { pathToFileURL } from "node:url";
+import os from "node:os";
+
+// mslxdff 插件系统：约定目录下的 *.mjs / *.js 模块，default export：
+//   { name?, version?, description?, hooks?: { "<hook-name>": async (ctx) => nextValue? } }
+// hook 返回数组时可替换流程值（如 model:select 的候选顺序）；返回 undefined 表示只观察。
+// 插件错误一律隔离：加载失败进 errors，hook 抛错不影响主链路。
+
+export function pluginsDir() {
+  return process.env.MSLXDFF_PLUGINS_DIR ||
+    join(os.homedir(), ".config", "mslxdff", "plugins");
+}
+
+// 安装目录下的 plugins/（随仓库/内置分发；auto-update 重装会丢，仅作开发/内置用）
+export function bundledPluginsDir(pkgRoot) {
+  if (!pkgRoot) return null;
+  return join(pkgRoot, "plugins");
+}
+
+// 解析扫描目录列表：env 完全接管；否则安装目录 plugins/ + 用户目录（同名文件用户目录优先）
+export function resolvePluginDirs({ pkgRoot } = {}) {
+  const env = process.env.MSLXDFF_PLUGINS_DIR;
+  if (env) return [env];
+  const dirs = [];
+  const bundled = bundledPluginsDir(pkgRoot);
+  if (bundled) dirs.push(bundled);
+  dirs.push(pluginsDir());
+  return dirs;
+}
+
+const PLUGIN_EXTS = new Set([".mjs", ".js"]);
+
+async function loadFromDir(dir, skipFiles) {
+  const plugins = [];
+  const errors = [];
+  if (!dir || !existsSync(dir)) return { plugins, errors };
+  let files = [];
+  try {
+    files = readdirSync(dir).filter((f) => PLUGIN_EXTS.has(extname(f).toLowerCase()));
+  } catch (err) {
+    errors.push({ file: dir, error: String(err?.message || err) });
+    return { plugins, errors };
+  }
+  files.sort();
+  for (const f of files) {
+    const file = join(dir, f);
+    if (skipFiles?.has(f)) continue; // 用户目录同名文件优先
+    try {
+      const mod = await import(pathToFileURL(file).href);
+      const plugin = mod?.default;
+      if (!plugin || typeof plugin !== "object") {
+        errors.push({ file, error: "no default export object" });
+        continue;
+      }
+      plugins.push({
+        name: typeof plugin.name === "string" && plugin.name ? plugin.name : basename(f, extname(f)),
+        version: typeof plugin.version === "string" ? plugin.version : "",
+        description: typeof plugin.description === "string" ? plugin.description : "",
+        hooks: plugin.hooks && typeof plugin.hooks === "object" ? plugin.hooks : {},
+        file,
+      });
+    } catch (err) {
+      errors.push({ file, error: String(err?.message || err) });
+    }
+  }
+  return { plugins, errors };
+}
+
+export async function loadPlugins({ dir, dirs } = {}) {
+  // 兼容旧签名 loadPlugins({ dir })；新签名 dirs 数组按优先级从低到高（后者覆盖前者同名文件）
+  const list = dirs || (dir ? [dir] : [pluginsDir()]);
+  let plugins = [];
+  const errors = [];
+  const seen = new Set(); // 已加载的 basename，先扫的目录跳过它们 → 后目录（高优先）覆盖
+  for (let i = list.length - 1; i >= 0; i--) {
+    const r = await loadFromDir(list[i], seen);
+    for (const p of r.plugins) seen.add(basename(p.file));
+    plugins = [...r.plugins, ...plugins]; // 低优先目录在前，目录内保持文件名序
+    errors.push(...r.errors);
+  }
+  return { plugins, errors };
+}
+
+// 串行执行某 hook。返回 { value, changed, errors }：
+// - value：最后一个返回非 undefined 值的插件的返回值（链式传递；数组、对象、布尔均可）
+// - changed：是否有插件返回了非 undefined 值（调用方可据此采用 value）
+export async function runHook(plugins, name, ctx) {
+  let value;
+  let changed = false;
+  const errors = [];
+  for (const p of plugins || []) {
+    const fn = p.hooks?.[name];
+    if (typeof fn !== "function") continue;
+    try {
+      const out = await fn(ctx);
+      if (out !== undefined) {
+        value = out;
+        changed = true;
+      }
+    } catch (err) {
+      errors.push({ plugin: p.name, error: String(err?.message || err) });
+    }
+  }
+  return { value, changed, errors };
+}

package/src/reasoning.js

@@ -1,33 +1,33 @@
-const PLACEHOLDER = " ";
-
-const MODEL_RULES = [
-  { match: (m) => /^kimi-/i.test(m || ""), scope: "toolCalls" },
-  { match: (m) => /deepseek/i.test(m || ""), scope: "all" },
-];
-
-export function normalizeModel(model) {
-  return model.startsWith("oc/") ? model.slice(3) : model;
-}
-
-function shouldInject(message, scope) {
-  if (message?.role !== "assistant") return false;
-  const rc = message.reasoning_content;
-  if (typeof rc === "string" && rc.length > 0) return false;
-  if (scope === "toolCalls") {
-    return Array.isArray(message.tool_calls) && message.tool_calls.length > 0;
-  }
-  return true;
-}
-
-function applyRule(body, rule) {
-  if (!rule || !body?.messages) return body;
-  const messages = body.messages.map((m) =>
-    shouldInject(m, rule.scope) ? { ...m, reasoning_content: PLACEHOLDER } : m
-  );
-  return { ...body, messages };
-}
-
-export function injectReasoningContent(model, body) {
-  const rule = MODEL_RULES.find((r) => r.match(model));
-  return applyRule(body, rule);
+const PLACEHOLDER = " ";
+
+const MODEL_RULES = [
+  { match: (m) => /^kimi-/i.test(m || ""), scope: "toolCalls" },
+  { match: (m) => /deepseek/i.test(m || ""), scope: "all" },
+];
+
+export function normalizeModel(model) {
+  return model.startsWith("oc/") ? model.slice(3) : model;
+}
+
+function shouldInject(message, scope) {
+  if (message?.role !== "assistant") return false;
+  const rc = message.reasoning_content;
+  if (typeof rc === "string" && rc.length > 0) return false;
+  if (scope === "toolCalls") {
+    return Array.isArray(message.tool_calls) && message.tool_calls.length > 0;
+  }
+  return true;
+}
+
+function applyRule(body, rule) {
+  if (!rule || !body?.messages) return body;
+  const messages = body.messages.map((m) =>
+    shouldInject(m, rule.scope) ? { ...m, reasoning_content: PLACEHOLDER } : m
+  );
+  return { ...body, messages };
+}
+
+export function injectReasoningContent(model, body) {
+  const rule = MODEL_RULES.find((r) => r.match(model));
+  return applyRule(body, rule);
 }

package/src/routes/chat/broadband-handler.js

@@ -0,0 +1,88 @@
+import { buildFallbackInfo } from "../fallback.js";
+import { relay, SLOW_TOTAL_MS } from "../stream.js";
+import { tryBroadbandRelay } from "../relay-queue.js";
+import { runHook } from "../../plugins.js";
+
+export async function handleBroadbandRelay({
+  model,
+  body,
+  hops,
+  lastErr,
+  requested,
+  useAuto,
+  lockModel,
+  auto,
+  groups,
+  token,
+  bus,
+  logs,
+  handlerCtx,
+  evt,
+  mark,
+  perf0,
+  stages,
+  res,
+  startedAt,
+  plugins,
+}) {
+  const bb = await tryBroadbandRelay({ groups, token, model, body, hops, bus, logs, reqId: handlerCtx.reqId, evt, res, mark, perf0, stages });
+  if (!bb) {
+    evt("relay-miss", { reqId: handlerCtx.reqId, model });
+    return { handled: false };
+  }
+  const isResponse = bb.result && typeof bb.result.status === "number" && typeof bb.result.headers?.get === "function";
+  if (isResponse) {
+    const bbFallback = buildFallbackInfo({ requested, actual: model, lastErr, via: "broadband", useAuto, lockModel });
+    if (bbFallback?.fallback) evt("fallback-notice", { reqId: handlerCtx.reqId, requested, actual: model, reason: bbFallback.reason, notice: bbFallback.notice, via: "broadband" });
+    evt("relay-start", { reqId: handlerCtx.reqId, model, via: "broadband", target: bb.target, group: bb.group, fallback: bbFallback });
+    const out = await relay(res, bb.result, body, {
+      fallback: bbFallback,
+      onFirstChunk: (d) => mark(`ttf-bb-${model}`),
+      onDownstreamAbort: () => evt("client-abort", { reqId: handlerCtx.reqId, model, totalMs: Math.round(Date.now() - startedAt), stages: [...stages] }),
+    });
+    evt("relay-done", { reqId: handlerCtx.reqId, model, via: "broadband", status: out.status, ttfMs: out.ttfMs, totalMs: out.totalMs, aborted: out.aborted, interrupted: out.interrupted ?? false, detail: out.detail ?? null });
+    if (auto && out.status === 200) {
+      const latencyMs = out.totalMs ?? 0;
+      if (out.detail?.stallHits > 0 || (latencyMs && latencyMs > SLOW_TOTAL_MS)) {
+        void auto.recordError(model, { status: 200, slow: true, note: `broadband slow ${latencyMs}ms` });
+        void auto.recordLatency(model, latencyMs);
+      } else {
+        await auto.recordOk(model, { latencyMs });
+      }
+    }
+    evt("result", { model, status: out.status, via: "broadband", timing: bb.result._t ?? null, ttfMs: out.ttfMs, totalMs: out.totalMs, detail: out.detail ?? null, fallback: bbFallback, requested, actual: model });
+    evt("client-response", { requested, actual: model, via: "broadband", fallback: bbFallback, status: out.status, reqId: handlerCtx.reqId });
+    if (plugins?.length) runHook(plugins, "request:completed", { reqId: handlerCtx.reqId, requested, useAuto, hops: handlerCtx.hops, stream: Boolean(body.stream), durationMs: Date.now() - startedAt, via: "broadband", status: out.status, actual: model, fallback: bbFallback }).catch(() => {});
+    return { handled: true };
+  } else if (bb.result && typeof bb.result.status === "number") {
+    const fakeRes = {
+      status: bb.result.status,
+      headers: { get: (k) => bb.result.headers?.[k] || bb.result.headers?.[k.toLowerCase()] || null },
+      text: async () => typeof bb.result.body === "string" ? bb.result.body : JSON.stringify(bb.result.body),
+      body: (() => {
+        const b = bb.result.body || "";
+        const str = typeof b === "string" ? b : JSON.stringify(b);
+        const isSSE = bb.result.headers?.["Content-Type"]?.includes("text/event-stream");
+        if (isSSE) {
+          return (async function* () { yield Buffer.from(str); })();
+        }
+        return null;
+      })(),
+    };
+    const bbLocalFallback = buildFallbackInfo({ requested, actual: model, lastErr, via: "broadband", useAuto, lockModel });
+    if (bbLocalFallback?.fallback) evt("fallback-notice", { reqId: handlerCtx.reqId, requested, actual: model, reason: bbLocalFallback.reason, notice: bbLocalFallback.notice, via: "broadband" });
+    evt("relay-start", { reqId: handlerCtx.reqId, model, via: "broadband-local", target: bb.target, group: bb.group, fallback: bbLocalFallback });
+    const out = await relay(res, fakeRes, body, {
+      fallback: bbLocalFallback,
+      onFirstChunk: (d) => mark(`ttf-bb-${model}`),
+      onDownstreamAbort: () => evt("client-abort", { reqId: handlerCtx.reqId, model, totalMs: Math.round(Date.now() - startedAt), stages: [...stages] }),
+    });
+    evt("relay-done", { reqId: handlerCtx.reqId, model, via: "broadband-local", status: out.status, ttfMs: out.ttfMs, totalMs: out.totalMs, aborted: out.aborted, interrupted: out.interrupted ?? false, detail: out.detail ?? null });
+    evt("result", { model, status: out.status, via: "broadband", timing: null, ttfMs: out.ttfMs, totalMs: out.totalMs, detail: out.detail ?? null, fallback: bbLocalFallback, requested, actual: model });
+    evt("client-response", { requested, actual: model, via: "broadband", fallback: bbLocalFallback, status: out.status, reqId: handlerCtx.reqId });
+    if (plugins?.length) runHook(plugins, "request:completed", { reqId: handlerCtx.reqId, requested, useAuto, hops: handlerCtx.hops, stream: Boolean(body.stream), durationMs: Date.now() - startedAt, via: "broadband", status: out.status, actual: model, fallback: bbLocalFallback }).catch(() => {});
+    return { handled: true };
+  }
+  evt("relay-miss", { reqId: handlerCtx.reqId, model });
+  return { handled: false };
+}

package/src/routes/chat/exhausted-handler.js

@@ -0,0 +1,41 @@
+import { performance } from "node:perf_hooks";
+import { json } from "../helpers.js";
+import { relay } from "../stream.js";
+
+export async function handleExhaustedLocal({ res, body, lastErr, order, handlerCtx, evt, logCall, mark, perf0, stages, done, requested, useAuto }) {
+  const model = lastErr?.model ?? handlerCtx.model;
+  evt("exhausted-local", { reqId: handlerCtx.reqId, lastModel: lastErr?.model ?? model, lastStatus: lastErr?.status ?? 502, order });
+  logCall(lastErr?.model ?? model, lastErr?.status ?? 502);
+  if (lastErr?.upstream) {
+    evt("relay-start", { reqId: handlerCtx.reqId, model: lastErr.model, via: "local-exhausted", isStream: Boolean(body.stream) });
+    const out = await relay(res, lastErr.upstream, body, {
+      onFirstChunk: (d) => mark(`ttf-${lastErr.model}`),
+      onDownstreamAbort: () => evt("client-abort", { reqId: handlerCtx.reqId, model: lastErr.model, totalMs: Math.round(performance.now() - perf0), stages: [...stages] }),
+    });
+    evt("relay-done", { reqId: handlerCtx.reqId, model: lastErr.model, via: "local-exhausted", status: out.status, ttfMs: out.ttfMs, totalMs: out.totalMs, aborted: out.aborted, interrupted: out.interrupted ?? false, detail: out.detail ?? null });
+    evt("result", { reqId: handlerCtx.reqId, model: lastErr.model, status: out.status, via: "local", timing: lastErr.upstream._t ?? null, ttfMs: out.ttfMs, totalMs: out.totalMs, detail: out.detail ?? null });
+    return true;
+  }
+  evt("result", { reqId: handlerCtx.reqId, model, status: lastErr?.status ?? 502, via: "none", timing: null });
+  done({ via: "none", status: lastErr?.status ?? 502, error: lastErr?.message || "all auto models failed" });
+  json(res, 502, { error: lastErr?.message || "all auto models failed" });
+  return true;
+}
+
+export async function handleExhaustedAll({ res, body, lastErr, order, requested, handlerCtx, evt, logCall, mark, perf0, stages }) {
+  evt("exhausted-all", { reqId: handlerCtx.reqId, lastModel: lastErr?.model ?? requested, lastStatus: lastErr?.status ?? 502, order });
+  logCall(lastErr?.model ?? requested, lastErr?.status ?? 502);
+  if (lastErr?.upstream) {
+    evt("relay-start", { reqId: handlerCtx.reqId, model: lastErr.model, via: "local-final", isStream: Boolean(body.stream) });
+    const out = await relay(res, lastErr.upstream, body, {
+      onFirstChunk: (d) => mark(`ttf-${lastErr.model}`),
+      onDownstreamAbort: () => evt("client-abort", { reqId: handlerCtx.reqId, model: lastErr.model, totalMs: Math.round(performance.now() - perf0), stages: [...stages] }),
+    });
+    evt("relay-done", { reqId: handlerCtx.reqId, model: lastErr.model, via: "local-final", status: out.status, ttfMs: out.ttfMs, totalMs: out.totalMs, aborted: out.aborted, interrupted: out.interrupted ?? false, detail: out.detail ?? null });
+    evt("result", { reqId: handlerCtx.reqId, model: lastErr.model, status: out.status, via: "local", timing: lastErr.upstream._t ?? null, ttfMs: out.ttfMs, totalMs: out.totalMs, detail: out.detail ?? null });
+    return true;
+  }
+  evt("result", { reqId: handlerCtx.reqId, model: lastErr?.model ?? requested, status: lastErr?.status ?? 502, via: "none", timing: null });
+  json(res, 502, { error: lastErr?.message || "all auto models failed" });
+  return true;
+}