@goodandready/dsh-opencode-provider 0.5.18 → 0.5.19

package/CHANGELOG.md

@@ -1,5 +1,11 @@
 # Changelog
 
+## 0.5.19
+
+- **Per-model soft cooldown**: quota/free-tier/rate-limit rejections now cool only that key+model (`quota` 5m, `rate-limit` 60s); other models on the same account remain usable. Invalid credentials still cool the account. If every key is cooling, the request degrades to the normal candidate list instead of failing before dispatch.
+- **Service status**: `/state` exposes the usage check time, latency and error, plus catalog source (`live`/`snapshot`), count and fetch time. Settings shows a compact Service status card.
+- 105 tests; engine matrix/install matrix remain green.
+
 ## 0.5.18
 
 - **Compatibility range**: `engines.dsh`, DSH peer ranges and `dsh.compatibility.dsh` now use `>=0.2.1-rc.2 <0.2.2-0`; `dshReleases` keeps the tested rc.2/rc.3/rc.4 records. Future `0.2.1` RCs are admitted automatically; the next minor remains excluded.

package/README.md

@@ -130,12 +130,12 @@ npm pack
 Install the **packed tarball** into a profile:
 
 ```bash
-dsh plugin --profile web add /absolute/path/to/goodandready-dsh-opencode-provider-0.5.18.tgz
+dsh plugin --profile web add /absolute/path/to/goodandready-dsh-opencode-provider-0.5.19.tgz
 # DSH Desktop:
-dsh plugin --profile desktop add /absolute/path/to/goodandready-dsh-opencode-provider-0.5.18.tgz
+dsh plugin --profile desktop add /absolute/path/to/goodandready-dsh-opencode-provider-0.5.19.tgz
 
 # Or install the published package:
-dsh plugin --profile web add @goodandready/dsh-opencode-provider@0.5.18
+dsh plugin --profile web add @goodandready/dsh-opencode-provider@0.5.19
 ```
 
 Restart dsh (or DSH Desktop), then pick **OpenCode (plugin)** or **OpenCode Go (plugin)** in the model picker.

package/README.ru.md

@@ -129,12 +129,12 @@ npm pack
 Установка из **упакованного tarball**:
 
 ```bash
-dsh plugin --profile web add /absolute/path/to/goodandready-dsh-opencode-provider-0.5.18.tgz
+dsh plugin --profile web add /absolute/path/to/goodandready-dsh-opencode-provider-0.5.19.tgz
 # DSH Desktop:
-dsh plugin --profile desktop add /absolute/path/to/goodandready-dsh-opencode-provider-0.5.18.tgz
+dsh plugin --profile desktop add /absolute/path/to/goodandready-dsh-opencode-provider-0.5.19.tgz
 
 # Либо установка опубликованного пакета из npm:
-dsh plugin --profile web add @goodandready/dsh-opencode-provider@0.5.18
+dsh plugin --profile web add @goodandready/dsh-opencode-provider@0.5.19
 ```
 
 После установки перезапустите dsh (или DSH Desktop) и выберите **OpenCode (plugin)** или **OpenCode Go (plugin)** в списке моделей.

package/README.zh.md

@@ -124,12 +124,12 @@ npm pack
 通过**打包文件 (.tgz)**安装：
 
 ```bash
-dsh plugin --profile web add /absolute/path/to/goodandready-dsh-opencode-provider-0.5.18.tgz
+dsh plugin --profile web add /absolute/path/to/goodandready-dsh-opencode-provider-0.5.19.tgz
 # DSH 桌面端：
-dsh plugin --profile desktop add /absolute/path/to/goodandready-dsh-opencode-provider-0.5.18.tgz
+dsh plugin --profile desktop add /absolute/path/to/goodandready-dsh-opencode-provider-0.5.19.tgz
 
 # 或从 npm 安装已发布版本：
-dsh plugin --profile web add @goodandready/dsh-opencode-provider@0.5.18
+dsh plugin --profile web add @goodandready/dsh-opencode-provider@0.5.19
 ```
 
 安装完成后重启 dsh 或 DSH 桌面端，在模型选择器中选择 **OpenCode (plugin)** 或 **OpenCode Go (plugin)** 即可。

package/lib/client.js

@@ -25,6 +25,17 @@ window.__ModuleLoader__.load({
 				keyStatusUnchecked: "Key unchecked",
 				checkKey: "Check key",
 				keyStatusHint: "A key check reads the usage endpoint; it does not send a model request.",
+				serviceStatus: "Service status",
+				serviceOk: "Reachable",
+				serviceDegraded: "Degraded",
+				usageEndpoint: "Usage endpoint",
+				catalogStatus: "Model catalog",
+				catalogLive: "live",
+				catalogSnapshot: "snapshot",
+				catalogAge: "updated {age}",
+				checkedAt: "checked {time}",
+				latencyValue: "{ms} ms",
+				notChecked: "not checked",
 				keySource: "Source",
 				keyWritable: "Writable",
 				pasteKey: "Paste a key",
@@ -218,6 +229,17 @@ window.__ModuleLoader__.load({
 				keyStatusUnchecked: "未检查",
 				checkKey: "检查密钥",
 				keyStatusHint: "检查仅读取用量端点，不会发送模型请求。",
+				serviceStatus: "服务状态",
+				serviceOk: "可访问",
+				serviceDegraded: "异常",
+				usageEndpoint: "用量端点",
+				catalogStatus: "模型目录",
+				catalogLive: "实时",
+				catalogSnapshot: "快照",
+				catalogAge: "更新于 {age}",
+				checkedAt: "检查于 {time}",
+				latencyValue: "{ms} ms",
+				notChecked: "未检查",
 				keySource: "来源",
 				keyWritable: "可写",
 				pasteKey: "粘贴密钥",
@@ -1854,6 +1876,13 @@ window.__ModuleLoader__.load({
 			if (status === "expired" || status === "invalid") return "oc-badge-bad";
 			return "oc-badge-warn";
 		}
+		function ageText(at) {
+			if (at === void 0) return "";
+			const minutes = Math.max(0, Math.round((Date.now() - at) / 6e4));
+			if (minutes < 1) return "now";
+			if (minutes < 60) return `${minutes}m`;
+			return `${Math.round(minutes / 60)}h`;
+		}
 		function OpenCodeSettingsPage(props) {
 			const { t } = props;
 			const [state, setState] = (0, react.useState)(null);
@@ -2300,6 +2329,62 @@ window.__ModuleLoader__.load({
 							})
 						]
 					}),
+					/* @__PURE__ */ (0, react_jsx_runtime.jsxs)("section", {
+						className: "oc-card",
+						children: [
+							/* @__PURE__ */ (0, react_jsx_runtime.jsxs)("h3", {
+								className: "oc-card-title",
+								children: [t("serviceStatus"), /* @__PURE__ */ (0, react_jsx_runtime.jsx)("span", {
+									className: `oc-badge ${state.service.usageError === void 0 ? "oc-badge-ok" : "oc-badge-warn"}`,
+									children: state.service.usageError === void 0 ? t("serviceOk") : t("serviceDegraded")
+								})]
+							}),
+							/* @__PURE__ */ (0, react_jsx_runtime.jsxs)("div", {
+								className: "oc-row",
+								children: [
+									/* @__PURE__ */ (0, react_jsx_runtime.jsx)("span", {
+										className: "oc-hint",
+										children: t("usageEndpoint")
+									}),
+									/* @__PURE__ */ (0, react_jsx_runtime.jsx)("span", {
+										className: `oc-badge ${state.service.usageError === void 0 ? "oc-badge-ok" : "oc-badge-bad"}`,
+										children: state.service.usageCheckedAt === void 0 ? t("notChecked") : t("checkedAt").replace("{time}", new Date(state.service.usageCheckedAt).toLocaleTimeString())
+									}),
+									state.service.usageLatencyMs === void 0 ? null : /* @__PURE__ */ (0, react_jsx_runtime.jsx)("span", {
+										className: "oc-badge",
+										children: t("latencyValue").replace("{ms}", String(state.service.usageLatencyMs))
+									})
+								]
+							}),
+							state.service.usageError === void 0 ? null : /* @__PURE__ */ (0, react_jsx_runtime.jsx)("p", {
+								className: "oc-hint",
+								children: state.service.usageError
+							}),
+							/* @__PURE__ */ (0, react_jsx_runtime.jsxs)("div", {
+								className: "oc-row",
+								children: [
+									/* @__PURE__ */ (0, react_jsx_runtime.jsx)("span", {
+										className: "oc-hint",
+										children: t("catalogStatus")
+									}),
+									/* @__PURE__ */ (0, react_jsx_runtime.jsxs)("span", {
+										className: `oc-badge ${state.catalog.source === "live" ? "oc-badge-ok" : "oc-badge-warn"}`,
+										children: [
+											state.catalog.source === "live" ? t("catalogLive") : t("catalogSnapshot"),
+											" · ",
+											state.catalog.count,
+											" ",
+											t("modelCount")
+										]
+									}),
+									state.catalog.fetchedAt === void 0 ? null : /* @__PURE__ */ (0, react_jsx_runtime.jsx)("span", {
+										className: "oc-badge",
+										children: t("catalogAge").replace("{age}", ageText(state.catalog.fetchedAt))
+									})
+								]
+							})
+						]
+					}),
 					/* @__PURE__ */ (0, react_jsx_runtime.jsxs)("section", {
 						className: "oc-card",
 						children: [

package/lib/index.d.ts

@@ -190,6 +190,8 @@ declare class OpenCodeAdapter extends LlmAdapter {
   private stickyWrites;
   /** key fingerprint → cooldown deadline and the rejection that caused it. */
   private readonly cooldowns;
+  /** key + model → short soft rejection; other models stay usable. */
+  private readonly modelCooldowns;
   private readonly sticky;
   private readonly routing;
   private warnedTools;
@@ -215,6 +217,11 @@ declare class OpenCodeAdapter extends LlmAdapter {
   private send;
   private keyId;
   private coolingDown;
+  /** Current model-scoped soft cooldown for one key, if any. */
+  modelHealth(key: string, model: string): {
+    coolingUntil: number;
+    reason: string;
+  } | undefined;
   /** Current cooldown for one resolved key, if any. */
   accountHealth(key: string): {
     coolingUntil: number;
@@ -225,6 +232,9 @@ declare class OpenCodeAdapter extends LlmAdapter {
   private loadCooldowns;
   private pruneCooldowns;
   private persistCooldowns;
+  private modelCoolingDown;
+  private markRejection;
+  private markModelCooldown;
   private markCooldown;
   private isTransient;
 }
@@ -247,6 +257,7 @@ interface UsageResult {
   readonly report?: UsageReport;
   readonly error?: string;
   readonly keyStatus?: UsageKeyStatus;
+  readonly latencyMs?: number;
   readonly checkedAt: number;
 }
 interface UsageWindowPayload {

package/lib/index.js

@@ -18,7 +18,7 @@ const DEFAULT_GO_API_BASE = "https://opencode.ai/inference/go";
 const DEFAULT_GO_ZEN_BASE = "https://opencode.ai/zen/go/v1";
 const DEFAULT_USAGE_URL = "https://opencode.ai/zen/go/v1/usage";
 const DEFAULT_AUTH_ENTRY = "opencode-go";
-const DEFAULT_USER_AGENT = "dsh-opencode-provider/0.5.18";
+const DEFAULT_USER_AGENT = "dsh-opencode-provider/0.5.19";
 const DEFAULT_CONTEXT_WINDOW = 262144;
 const DEFAULT_MAX_TOKENS = 32768;
 const DEFAULT_GENERATE_MAX_TOKENS = 32768;
@@ -1090,6 +1090,17 @@ function describeModel(meta, provider) {
 	}
 	return parts.join(" · ");
 }
+function catalogStatus(provider, config, count) {
+	const cached = catalogCache.get(`${provider}|${modelsUrlFor(provider, config)}`);
+	return cached === void 0 ? {
+		source: "snapshot",
+		count
+	} : {
+		source: "live",
+		count,
+		fetchedAt: cached.at
+	};
+}
 function clearCatalogCache() {
 	catalogCache.clear();
 }
@@ -3100,6 +3111,8 @@ var OpenCodeAdapter = class extends LlmAdapter {
 	stickyWrites = Promise.resolve();
 	/** key fingerprint → cooldown deadline and the rejection that caused it. */
 	cooldowns = /* @__PURE__ */ new Map();
+	/** key + model → short soft rejection; other models stay usable. */
+	modelCooldowns = /* @__PURE__ */ new Map();
 	sticky = /* @__PURE__ */ new Map();
 	routing = [];
 	warnedTools = false;
@@ -3202,7 +3215,10 @@ var OpenCodeAdapter = class extends LlmAdapter {
 				}
 			}
 		}
-		const initial = keys.find((entry) => fallback || !this.coolingDown(entry.key)) ?? keys[0];
+		const eligible = fallback ? keys : keys.filter((entry) => !this.coolingDown(entry.key) && !this.modelCoolingDown(entry.key, options.model));
+		const ordered = eligible.length > 0 ? eligible : keys;
+		const forced = !fallback && eligible.length === 0;
+		const initial = ordered[0];
 		const url = endpointFor(options.provider, model.transport, options.model, config);
 		let images;
 		if (hasImages(options)) {
@@ -3226,8 +3242,8 @@ var OpenCodeAdapter = class extends LlmAdapter {
 		let lastError;
 		let lastAccount = initial?.label ?? "default";
 		let loggedAny = false;
-		for (const [index, entry] of keys.entries()) {
-			if (!fallback && this.coolingDown(entry.key)) continue;
+		for (const [index, entry] of ordered.entries()) {
+			if (!fallback && !forced && (this.coolingDown(entry.key) || this.modelCoolingDown(entry.key, options.model))) continue;
 			lastAccount = entry.label ?? "default";
 			const attemptReason = index === 0 ? reason : "rotation";
 			const attemptStartedAt = Date.now();
@@ -3254,9 +3270,9 @@ var OpenCodeAdapter = class extends LlmAdapter {
 					const error = classifyResponseError(response.status, text, response.headers);
 					lastError = error;
 					logAttempt(false, error.code);
-					const canRotate = index < keys.length - 1;
+					const canRotate = index < ordered.length - 1;
 					if (error.code === "INVALID_CREDENTIAL" || error.code === "RATE_LIMIT" || error.code === "QUOTA") {
-						if (!fallback) this.markCooldown(entry.key, response.status, response.headers, error.code);
+						if (!fallback) this.markRejection(entry.key, options.model, response.status, response.headers, error.code);
 						responseFailure = true;
 						if (canRotate) continue;
 					}
@@ -3297,8 +3313,8 @@ var OpenCodeAdapter = class extends LlmAdapter {
 				}
 				lastError = classified;
 				const transient = this.isTransient(classified);
-				if (transient && !responseFailure && !fallback) this.markCooldown(entry.key, 0);
-				if (!(index < keys.length - 1 && transient)) {
+				if (transient && !responseFailure && !fallback) this.markRejection(entry.key, options.model, 0, void 0, classified.code);
+				if (!(index < ordered.length - 1 && transient)) {
 					if (!fallback && config.quotaFallbackModel !== "" && isGoProvider(options.provider) && classified.code === "QUOTA") break;
 					throw classified;
 				}
@@ -3453,6 +3469,20 @@ var OpenCodeAdapter = class extends LlmAdapter {
 		}
 		return true;
 	}
+	/** Current model-scoped soft cooldown for one key, if any. */
+	modelHealth(key, model) {
+		const id = `${this.keyId(key)}:${model}`;
+		const entry = this.modelCooldowns.get(id);
+		if (entry === void 0) return void 0;
+		if (entry.until <= Date.now()) {
+			this.modelCooldowns.delete(id);
+			return;
+		}
+		return {
+			coolingUntil: entry.until,
+			reason: entry.reason
+		};
+	}
 	/** Current cooldown for one resolved key, if any. */
 	accountHealth(key) {
 		const id = this.keyId(key);
@@ -3505,6 +3535,30 @@ var OpenCodeAdapter = class extends LlmAdapter {
 			await writeFile(this.cooldownPath, payload, "utf8");
 		}).catch(() => {});
 	}
+	modelCoolingDown(key, model) {
+		const id = `${this.keyId(key)}:${model}`;
+		const entry = this.modelCooldowns.get(id);
+		if (entry === void 0) return false;
+		if (entry.until <= Date.now()) {
+			this.modelCooldowns.delete(id);
+			return false;
+		}
+		return true;
+	}
+	markRejection(key, model, status, headers, code) {
+		if (code === "QUOTA" || code === "RATE_LIMIT") {
+			this.markModelCooldown(key, model, code);
+			return;
+		}
+		this.markCooldown(key, status, headers, code);
+	}
+	markModelCooldown(key, model, code) {
+		const delayMs = code === "QUOTA" ? 3e5 : 6e4;
+		this.modelCooldowns.set(`${this.keyId(key)}:${model}`, {
+			until: Date.now() + delayMs,
+			reason: code === "QUOTA" ? "quota" : "rate-limit"
+		});
+	}
 	markCooldown(key, status, headers, code) {
 		let delayMs = 3e4;
 		let reason = "transport";
@@ -4779,7 +4833,13 @@ async function buildState(ctx, deps) {
 		key: keyInfo,
 		accounts,
 		models,
+		catalog: catalogStatus(GO_PROVIDER, config, models.length),
 		usage: usage ?? null,
+		service: {
+			...usage?.checkedAt === void 0 ? {} : { usageCheckedAt: usage.checkedAt },
+			...usage?.latencyMs === void 0 ? {} : { usageLatencyMs: usage.latencyMs },
+			...usage?.error === void 0 ? {} : { usageError: usage.error }
+		},
 		routing: deps.adapter.routingTrace(),
 		auth: {
 			entry: config.openCodeAuthEntry,
@@ -5360,7 +5420,9 @@ function createUsageReader(config, resolveKey, fetchImpl = fetch) {
 			if (Date.now() - cached.checkedAt < ttl) return cached;
 		}
 		const result = async () => {
+			const startedAt = Date.now();
 			const signal = AbortSignal.timeout(USAGE_TIMEOUT_MS);
+			const latency = () => Math.max(0, Date.now() - startedAt);
 			try {
 				let response;
 				let lastNetworkError;
@@ -5386,23 +5448,27 @@ function createUsageReader(config, resolveKey, fetchImpl = fetch) {
 					return {
 						error: "usage endpoint rejected the key (inference may still work)",
 						keyStatus: /expired/i.test(body) ? "expired" : "invalid",
+						latencyMs: latency(),
 						checkedAt: Date.now()
 					};
 				}
 				if (!response.ok) return {
 					error: `usage endpoint returned HTTP ${response.status}`,
 					keyStatus: "unavailable",
+					latencyMs: latency(),
 					checkedAt: Date.now()
 				};
 				return {
 					report: normalizeUsage(await response.json()),
 					keyStatus: "ok",
+					latencyMs: latency(),
 					checkedAt: Date.now()
 				};
 			} catch (error) {
 				return {
 					error: error instanceof Error ? error.message : "usage request failed",
 					keyStatus: "unavailable",
+					latencyMs: latency(),
 					checkedAt: Date.now()
 				};
 			}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@goodandready/dsh-opencode-provider",
-  "version": "0.5.18",
+  "version": "0.5.19",
   "description": "OpenCode / OpenCode Go LLM provider plugin for DeepSeek Harness (dsh).",
   "license": "MIT",
   "type": "module",