dsh-connect-workbuddy 5.0.0 → 5.2.1

package/lib/index.js

@@ -1,4 +1,4 @@
-import { $ as REFUSES_OFF_MODEL_IDS, A as workbuddyAccountId, At as withFileLock, B as isCredentialRejectedError, C as defaultDesktopAuthDirs, Ct as macosBundleExecutable, D as isVaultAccountId, Dt as workbuddyAppExecutableCandidates, E as isEncryptedCredentialError, Et as readAtRestKey, F as WorkBuddyUpstreamClient, G as parseCreditMultiplier, H as knownRegionOf, I as classifyUpstreamError, J as perturbChannelFingerprints, K as parseReasoning, L as declaredTools, M as CREDENTIAL_REJECTED_CODE, N as WORKBUDDY_FALLBACK_SYSTEM_PROMPT, O as legacyWorkbuddyOwnAuthPath, P as WorkBuddyCredentialRejectedError, Q as busyDisplaySuffix, R as forceNeutralHead, S as defaultDesktopAuthCandidates, St as isWorkbuddyBundle, T as hasEncryptedCredentialFields, Tt as openEncryptedField, U as modelIdOfBody, V as isFirstMessageGateBody, W as openingEvidenceOfBody, X as regionOf, Y as prepareChatBody, Z as attachBusyLevels, _ as WORKBUDDY_AUTH_FILENAME, _t as deriveAtRestKeyId, a as readHostHeartbeat, at as withEffectiveOff, b as WorkBuddyEncryptedCredentialError, c as WORKBUDDY_CONNECT_VERSION, ct as pickImageModel, d as FALLBACK_WORKBUDDY_MODELS_GLOBAL, dt as NATIVE_MODALITY_BY_MODEL_ID, et as defaultOffModelIds, f as WorkBuddyCatalog, ft as imageDefaultFor, g as ENCRYPTED_CREDENTIAL_CODE, gt as deriveAtRestKey, h as fallbackModelsFor, ht as clearAtRestKeyCache, i as processStartTimeMs, it as recordRefusal, j as workbuddyOwnAuthPath, jt as writeFileAtomic, k as parseWorkBuddyAuth, kt as resolveDshHome, l as piAiRuntimeInfo, lt as parseQueueAnswer, m as deriveCatalog, mt as WORKBUDDY_APP_EXECUTABLE_ENV, n as clearHostHeartbeat, nt as offDefaultFor, o as workbuddyHostHeartbeatPath, ot as DEFAULT_IMAGE_SIZE, p as applyContextBudgets, pt as nativeModalityOf, q as parseUpstreamModel, r as isHeartbeatProcessAlive, rt as offRefused, s as writeHostHeartbeat, st as WorkBuddyImageError, t as WORKBUDDY_HOST_HEARTBEAT_FILENAME, tt as lastRefusalFor, u as FALLBACK_WORKBUDDY_MODELS, ut as queueNoticeText, v as WORKBUDDY_AUTH_FILE_ENV, vt as fetchAtRestKeyPayload, w as defaultDesktopAuthPath, wt as macosNestedAppBundles, x as authFileName, xt as isEncryptedFieldWrapper, y as WorkBuddyCredentialStore, yt as findWorkbuddyAppExecutable, z as isConversationIdGateBody } from "./host-heartbeat-D313ENPV.js";
+import { $ as regionOf, A as parseWorkBuddyAuth, At as workbuddyAppExecutableCandidates, B as forceNeutralHead, C as defaultDesktopAuthCandidates, D as isEncryptedCredentialError, Dt as macosNestedAppBundles, E as hasEncryptedCredentialFields, Et as macosBundleExecutable, F as WORKBUDDY_FALLBACK_SYSTEM_PROMPT, G as knownRegionOf, H as isConversationIdGateBody, I as WorkBuddyCredentialRejectedError, J as parseCreditMultiplier, K as modelIdOfBody, L as WorkBuddyUpstreamClient, M as workbuddyOwnAuthPath, Mt as resolveDshHome, N as CONTEXT_OVERFLOW_MARKER, Nt as withFileLock, O as isVaultAccountId, Ot as openEncryptedField, P as CREDENTIAL_REJECTED_CODE, Pt as writeFileAtomic, Q as prepareChatBody, R as classifyUpstreamError, S as authFileName, St as findWorkbuddyAppExecutable, T as defaultDesktopAuthPath, Tt as isWorkbuddyBundle, U as isCredentialRejectedError, V as isContextTooLongBody, W as isFirstMessageGateBody, X as parseUpstreamModel, Y as parseReasoning, Z as perturbChannelFingerprints, _ as ENCRYPTED_CREDENTIAL_CODE, _t as WORKBUDDY_APP_EXECUTABLE_ENV, a as readHostHeartbeat, at as offDefaultFor, b as WorkBuddyCredentialStore, bt as deriveAtRestKeyId, c as WORKBUDDY_CONNECT_VERSION, ct as withEffectiveOff, d as FALLBACK_WORKBUDDY_MODELS_GLOBAL, dt as pickImageModel, et as attachBusyLevels, f as WorkBuddyCatalog, ft as parseQueueAnswer, g as withoutRouters, gt as nativeModalityOf, h as fallbackModelsFor, ht as imageDefaultFor, i as processStartTimeMs, it as lastRefusalFor, j as workbuddyAccountId, k as legacyWorkbuddyOwnAuthPath, kt as readAtRestKey, l as piAiRuntimeInfo, lt as DEFAULT_IMAGE_SIZE, m as deriveCatalog, mt as NATIVE_MODALITY_BY_MODEL_ID, n as clearHostHeartbeat, nt as REFUSES_OFF_MODEL_IDS, o as workbuddyHostHeartbeatPath, ot as offRefused, p as applyContextBudgets, pt as queueNoticeText, q as openingEvidenceOfBody, r as isHeartbeatProcessAlive, rt as defaultOffModelIds, s as writeHostHeartbeat, st as recordRefusal, t as WORKBUDDY_HOST_HEARTBEAT_FILENAME, tt as busyDisplaySuffix, u as FALLBACK_WORKBUDDY_MODELS, ut as WorkBuddyImageError, v as WORKBUDDY_AUTH_FILENAME, vt as clearAtRestKeyCache, w as defaultDesktopAuthDirs, wt as isEncryptedFieldWrapper, x as WorkBuddyEncryptedCredentialError, xt as fetchAtRestKeyPayload, y as WORKBUDDY_AUTH_FILE_ENV, yt as deriveAtRestKey, z as declaredTools } from "./host-heartbeat-Icz67WtG.js";
 import z from "@deepseek-ai/schemastery";
 import { appendFile, mkdir, readFile, writeFile } from "node:fs/promises";
 import { randomBytes, randomUUID, timingSafeEqual } from "node:crypto";
@@ -589,16 +589,80 @@ function foldModernContext(context) {
 function transcript(context) {
 	return context;
 }
-function withLegacyContext(api, generation) {
+/**
+* Rewrite every historical assistant message to the identity this adapter stamps.
+*
+* ISSUE #102. pi-ai replays a thinking block as `thinking` only when the message
+* that produced it names the same `provider` / `api` / `model` as the request in
+* flight (`utils/transform-messages.js`, the `isSameModel` branch); everything
+* else is flattened to `{type:'text', text: thinking}`.
+*
+* The durable transcript the HOST hands back does not carry the identity. The
+* agent loop writes `source.provider = request.provider`, and `request.provider`
+* is the ROUTE id (`workbuddy` / `workbuddy-global`), while this adapter stamps
+* `provider: WORKBUDDY_MODEL_IDENTITY` on the model. So:
+*
+*   - CN sessions survive by COINCIDENCE: its route id happens to equal the
+*     identity (`workbuddy` === `workbuddy`).
+*   - GLOBAL sessions never match (`workbuddy-global` !== `workbuddy`), so every
+*     historical thinking block is downgraded on EVERY turn — not only when the
+*     user switches regions, which is what #59's write-up assumed.
+*
+* The model then sees a context in which all of its own past reasoning was
+* plain assistant text, and writes its new reasoning into `text` to match. That
+* is the reported symptom: reasoning collapses to a character or two while the
+* answer channel fills with working notes.
+*
+* WHY REWRITING IS SAFE. Every message here was produced by THIS plugin, in THIS
+* region — the transcript never contains another provider's assistant turns
+* (`dsh-llm` splits history by provider before the API sees it). The identity is
+* already the field this adapter stamps on the models it serves, and it resolves
+* as a registry key in both regions (issue #75). Nothing about routing, billing
+* or the destination changes: `baseUrl` comes from the model, not from the
+* message.
+*
+* Only `provider` is rewritten. `api` is left alone on purpose: a legacy
+* (`dsh-foreign`) message carries an api this plugin never sends, and claiming
+* `openai-completions` for it would assert a wire shape that message was never
+* built for. The `provider` mismatch is what decides the downgrade, and fixing
+* it is enough — `isSameModel` still requires the model id and api to match, so
+* a genuinely different model keeps degrading (covered by a test).
+*
+* Returns the same object when nothing changed, so the common case (an
+* already-normalized transcript) allocates nothing.
+*/
+function alignAssistantIdentities(context, identity = WORKBUDDY_MODEL_IDENTITY) {
+	const messages = context.messages;
+	if (!Array.isArray(messages) || messages.length === 0) return context;
+	let changed = false;
+	const next = messages.map((message) => {
+		if (typeof message !== "object" || message === null) return message;
+		const record = message;
+		if (record["role"] !== "assistant") return message;
+		if (record["provider"] === identity) return message;
+		changed = true;
+		return {
+			...record,
+			provider: identity
+		};
+	});
+	return changed ? {
+		...context,
+		messages: next
+	} : context;
+}
+function withLegacyContext(api, generation, identity = WORKBUDDY_MODEL_IDENTITY) {
+	/** One place so both branches and both entry points agree on the order. */
+	const prepare = (context) => alignAssistantIdentities(generation === "modern" ? foldModernContext(context) : adaptLegacyPiAiContext(context), identity);
 	if (generation === "modern") return {
 		...api,
-		stream: (model, context, options) => api.stream(model, transcript(foldModernContext(context)), options),
-		streamSimple: (model, context, options) => api.streamSimple(model, transcript(foldModernContext(context)), options)
+		stream: (model, context, options) => api.stream(model, transcript(prepare(context)), options),
+		streamSimple: (model, context, options) => api.streamSimple(model, transcript(prepare(context)), options)
 	};
 	return {
 		...api,
-		stream: (model, context, options) => api.stream(model, transcript(adaptLegacyPiAiContext(context)), options),
-		streamSimple: (model, context, options) => api.streamSimple(model, transcript(adaptLegacyPiAiContext(context)), options)
+		stream: (model, context, options) => api.stream(model, transcript(prepare(context)), options),
+		streamSimple: (model, context, options) => api.streamSimple(model, transcript(prepare(context)), options)
 	};
 }
 /**
@@ -673,7 +737,10 @@ const NO_REASONING_EFFORTS = { efforts: [{
 * catalog has six of them (`default`, `glm-5.0`, `glm-4.7`, `glm-4.6`,
 * `hunyuan-chat`, `hunyuan-image-alpha`), the live global one two
 * (`default-model`, `deep-model`), and EVERY entry of both static fallback lists
-* — the inherited `high` is not a tier that model has. `resolveReasoningLevel`
+* — the inherited `high` is not a tier that model has. (`default-model` is the
+* international `auto` router and is not offered as a row since 5.0.1; the
+* measurement is kept verbatim because the defect it documents was observed
+* against the full roster.) `resolveReasoningLevel`
 * then throws `UNSUPPORTED_REASONING_EFFORT` before the request is even built,
 * so the model is unusable locally: no wire call, no upstream error, nothing to
 * retry. Introduced by v4.11.0, which made the profile default explicit; before
@@ -773,7 +840,7 @@ function createWorkBuddyAdapter(options) {
 				}
 			} },
 			models: buildModels(),
-			api: withContextRescue(withLegacyContext(openAICompletionsApi(), generation), options.resolveContextRescue)
+			api: withContextRescue(withLegacyContext(openAICompletionsApi(), generation, modelIdentity), options.resolveContextRescue)
 		}),
 		getModels: () => buildModels()
 	};
@@ -3190,6 +3257,34 @@ function createWorkBuddyShim(options) {
 	const onRequestBody = options.onRequestBody;
 	const onUpstreamUsage = options.onUpstreamUsage;
 	const SHARED_SECRET = randomBytes(32).toString("base64url");
+	/**
+	* Whether this process's prompts have been PROVEN to need the invisible
+	* perturbation before the gateway will accept them.
+	*
+	* WHY THIS EXISTS (measured 2026-10-22). The retry ladder below is
+	* discover-by-failing: a request goes out unmodified, is refused with `11128`,
+	* and the ladder re-sends a perturbed copy. That is correct the first time and
+	* wasteful every time after — the prompt SHAPE that carries a fingerprinted
+	* substring does not change between turns of a session, so the plugin was
+	* paying one refused request (~209ms measured) on EVERY request, forever.
+	*
+	* So once the perturbation is what made a request succeed, the next request
+	* starts from the perturbed form and skips the doomed first attempt. The
+	* saving is one round trip plus one refused request per turn.
+	*
+	* WHY A PROCESS-LOCAL FLAG AND NOT A CONFIG. The gateway's fingerprint list is
+	* a snapshot the upstream can change at any time, in either direction: a rule
+	* can be withdrawn as easily as added. A persisted flag would therefore
+	* outlive the condition that justified it and could keep perturbing prompts a
+	* gateway no longer objects to. In memory it is forgotten at restart, which is
+	* the natural expiry for "what this gateway refused recently".
+	*
+	* AND IT SELF-CORRECTS. If a perturbed body is EVER refused with the channel
+	* gate, the flag is cleared and the request falls back to the plain ladder —
+	* so a withdrawn rule, or a different model behind the same gateway, cannot
+	* leave the plugin stuck sending a shape that no longer helps.
+	*/
+	let channelNeedsPerturbation = false;
 	/** Constant-time bearer check; absent or mismatched bearers are rejected. */
 	function bearerOk(req) {
 		const header = req.headers.authorization;
@@ -3323,7 +3418,25 @@ function createWorkBuddyShim(options) {
 		}
 		const controller = new AbortController();
 		res.on("close", () => controller.abort());
-		let result = await client.chatStream(credential, prepared, controller.signal);
+		/**
+		* The body to send FIRST, which is the perturbed form once this process has
+		* proven the gateway demands it.
+		*
+		* `perturbChannelFingerprints` is consulted only when the flag is set, so a
+		* fresh process still pays the plain attempt — that is what discovers
+		* whether the gate is on at all (see `channelNeedsPerturbation`).
+		*
+		* The perturbed form is a purely additive transform: it inserts zero-width
+		* spaces and changes no word the model reads, so starting from it is not a
+		* behaviour change, only a saved round trip.
+		*/
+		const preferred = channelNeedsPerturbation ? perturbChannelFingerprints(prepared) ?? prepared : prepared;
+		let result = await client.chatStream(credential, preferred, controller.signal);
+		if (channelNeedsPerturbation && !result.ok && result.kind === "channel_reject") {
+			channelNeedsPerturbation = false;
+			logger?.warn("dsh-connect-workbuddy: a perturbed body was refused too; clearing the learned preference and retrying from the plain form");
+			result = await client.chatStream(credential, prepared, controller.signal);
+		}
 		/**
 		* The retry ladder that does not depend on knowing the fingerprint
 		* (issue #98, both halves).
@@ -3371,6 +3484,7 @@ function createWorkBuddyShim(options) {
 					logger?.warn("dsh-connect-workbuddy: the channel gate refused the body again; retrying once with an invisible perturbation of the scanned text");
 					result = await client.chatStream(credential, rescued, controller.signal);
 					retriedWithPerturbation = true;
+					if (result.ok) channelNeedsPerturbation = true;
 				}
 			}
 		}
@@ -3503,7 +3617,8 @@ function createWorkBuddyShim(options) {
 			const refusedTier = reasoningTierRefusal(result);
 			const receipt = refusedTier ?? detail?.tips ?? detail?.displayMsg ?? clippedUpstreamText(result.message, 400);
 			const advice = refusedTier !== void 0 ? "这不是账号或网络问题：该模型实测拒绝「off」推理档位，请到模型卡片里取消该行的「可关闭思考」勾选后重试" : result.kind === "client" ? "该请求被上游按参数拒绝：与网络、账号、额度都无关，换账号也不会改变结果，请按上面的提示调整后重试" : shortfall === void 0 ? "" : "建议换一个模型继续，或稍后等待该账号的额度恢复";
-			const body = siblingGate !== void 0 ? siblingGate : advice === "" ? receipt : `${receipt.replace(/[。.]$/u, "")}。${advice}`;
+			const overflow = isContextTooLongBody(result.message) ? `${CONTEXT_OVERFLOW_MARKER}。` : "";
+			const body = siblingGate !== void 0 ? siblingGate : `${overflow}${advice === "" ? receipt : `${receipt.replace(/[。.]$/u, "")}。${advice}`}`;
 			writeOpenAIError(res, KIND_STATUS[result.kind], result.kind, `workbuddy 上游失败：${failoverReasonText(result)}（http ${result.status}）${note}${why}${stamp}。${body}`, hostErrorCode(result.kind));
 			return;
 		}
@@ -4203,6 +4318,199 @@ async function probeModel(input) {
 	};
 }
 /**
+* Smallest spacing between content chunks, in milliseconds, that still counts
+* as generation.
+*
+* Guards the divide-by-zero case where a fast model delivers every token in a
+* single burst: `chunks === 1` means the stream told us nothing about the RATE,
+* and the run reports no speed rather than an invented one. The same applies
+* when the first and last content chunk land in the same millisecond.
+*/
+const MIN_GENERATION_MS = 1;
+/** Build the request body for one speed run. */
+function tpsProbeRequestBody(modelId) {
+	return JSON.stringify({
+		model: modelId,
+		messages: [{
+			role: "system",
+			content: "You are a throughput benchmark. Output a long, uninterrupted sequence of short words separated by spaces. No preamble, no explanation, no code block."
+		}, {
+			role: "user",
+			content: "List the numbers from 1 to 400 in words, separated by single spaces."
+		}],
+		max_tokens: 256,
+		...OFF_REASONING_FIELDS,
+		stream: true
+	});
+}
+/**
+* Ask for the lowest reasoning effort available.
+*
+* A reasoning model asked to count spends its `max_tokens` inside the reasoning
+* channel; the stream then carries thinking deltas and little or no content, and
+* timing it would measure the wrong thing. `none` is the widest supported
+* spelling; gateways that do not know it ignore the field (measured: the CN
+* gateway answers 200 with it).
+*/
+const OFF_REASONING_FIELDS = { reasoning_effort: "none" };
+/**
+* Read one SSE stream INCREMENTALLY, timing each content deltas arrival.
+*
+* The incremental read is the measurement. `response.text()` buffers the whole
+* body and hands it over once, which erases the only signal a throughput number
+* is made of: the interval between the first and last content chunk. A version of
+* this file that parsed a buffered string reported the PARSING time, not the
+* generation time, and looked entirely plausible — which is why the reader takes
+* the response body and not a string.
+*
+* Only `choices[0].delta.content` is timed. A reasoning delta is not output:
+* counting it would report a reasoning model as fast because it produced a lot of
+* private thinking, and reasoning models are precisely the ones where the
+* distinction matters.
+*
+* `startedAt` is the caller's clock reading taken BEFORE the request went out.
+* Defaulting it to "now" would turn time-to-first-token into "time to start
+* reading" — a plausible-looking number wrong by the whole connect+TTFB.
+*
+* Never throws on a malformed frame: the upstream is allowed to send comments,
+* blank lines and `[DONE]`, and a stream that ends early still reports what it
+* timed.
+*/
+async function readTimedStream(body, startedAt) {
+	const reader = body.getReader();
+	const decoder = new TextDecoder();
+	let pending = "";
+	let firstAt;
+	let lastAt;
+	let usage;
+	try {
+		while (true) {
+			const { done, value } = await reader.read();
+			if (done) break;
+			const arrival = Date.now();
+			pending += decoder.decode(value, { stream: true });
+			const lines = pending.split("\n");
+			pending = lines.pop() ?? "";
+			for (const line of lines) {
+				const reading = timingsOfLine(line, arrival);
+				if (reading.usage !== void 0) usage = reading.usage;
+				if (reading.content !== void 0) {
+					if (firstAt === void 0) firstAt = arrival;
+					lastAt = arrival;
+				}
+			}
+		}
+	} catch {} finally {
+		reader.cancel().catch(() => {});
+	}
+	const outputTokens = typeof usage?.["completion_tokens"] === "number" ? usage["completion_tokens"] : void 0;
+	const credit = typeof usage?.["credit"] === "number" ? usage["credit"] : void 0;
+	return {
+		...outputTokens === void 0 ? {} : { outputTokens },
+		...firstAt === void 0 ? {} : { firstContentMs: firstAt - startedAt },
+		...firstAt === void 0 || lastAt === void 0 ? {} : { generationMs: lastAt - firstAt },
+		...credit === void 0 ? {} : { credit }
+	};
+}
+/**
+* What one SSE line says: whether it carried content, and any usage frame.
+*
+* Split out so the frame grammar is testable without a stream. The `arrival`
+* timestamp is threaded in by the reader, because a parser that read the clock
+* itself would be timing the parse, not the arrival.
+*/
+function timingsOfLine(line, _arrival) {
+	if (!line.startsWith("data:")) return {};
+	const payload = line.slice(5).trim();
+	if (payload === "" || payload === "[DONE]") return {};
+	let frame;
+	try {
+		frame = JSON.parse(payload);
+	} catch {
+		return {};
+	}
+	if (typeof frame !== "object" || frame === null || Array.isArray(frame)) return {};
+	const record = frame;
+	const usageField = record["usage"];
+	const usage = typeof usageField === "object" && usageField !== null && !Array.isArray(usageField) ? usageField : void 0;
+	const choices = record["choices"];
+	const first = Array.isArray(choices) ? choices[0] : void 0;
+	const delta = typeof first === "object" && first !== null ? first["delta"] : void 0;
+	const content = typeof delta === "object" && delta !== null ? delta["content"] : void 0;
+	return {
+		...typeof content === "string" && content !== "" ? { content } : {},
+		...usage === void 0 ? {} : { usage }
+	};
+}
+/** The middle value; undefined for an empty list. */
+function median(values) {
+	if (values.length === 0) return void 0;
+	const sorted = [...values].sort((a, b) => a - b);
+	const middle = Math.floor(sorted.length / 2);
+	return sorted.length % 2 === 1 ? sorted[middle] : Math.round((sorted[middle - 1] + sorted[middle]) / 2);
+}
+/**
+* Reduce several run readings to one sample.
+*
+* The median per quantity is taken SEPARATELY rather than picking one "winner"
+* run: a run whose stream was truncated may still have timed its first chunk
+* honestly, and throwing that away would lose information for no reason. A
+* quantity with no usable reading is omitted, never filled in.
+*/
+function summarizeTps(modelId, runs, attempted) {
+	const complete = runs.length === attempted && attempted > 0;
+	const speeds = [];
+	const firsts = [];
+	let outputTokens;
+	let credit;
+	for (const run of runs) {
+		if (run.firstContentMs !== void 0) firsts.push(run.firstContentMs);
+		if (run.generationMs !== void 0 && run.generationMs >= MIN_GENERATION_MS && run.outputTokens !== void 0 && run.outputTokens > 0) speeds.push(run.outputTokens / (run.generationMs / 1e3));
+		if (run.outputTokens !== void 0) outputTokens = run.outputTokens;
+		if (run.credit !== void 0) credit = (credit ?? 0) + run.credit;
+	}
+	const tokensPerSecond = median(speeds.map((speed) => Math.round(speed)));
+	const reason = tokensPerSecond !== void 0 ? void 0 : runs.length === 0 ? "all-failed" : outputTokens === void 0 ? "no-usage" : "few-chunks";
+	return {
+		modelId,
+		...tokensPerSecond === void 0 ? {} : { tokensPerSecond },
+		...outputTokens === void 0 ? {} : { outputTokens },
+		...median(firsts) === void 0 ? {} : { timeToFirstTokenMs: median(firsts) },
+		samples: runs.length,
+		...credit === void 0 ? {} : { credit: Math.round(credit * 100) / 100 },
+		complete,
+		...reason === void 0 ? {} : { reason }
+	};
+}
+/**
+* Measure one model's output speed.
+*
+* Runs {@link TPS_PROBE_RUNS} times and takes per-quantity medians (see
+* {@link summarizeTps} for why a median and not a mean). A failed run is dropped
+* rather than counted as zero — a model that answered twice at 400 tok/s did not
+* get slower because the third request timed out — but the sample count records
+* the shortfall so the card can say "n/3".
+*
+* Never throws: this is a diagnostic the user asked for, and a dead model must
+* produce a result row, not an exception.
+*/
+async function measureTps(input) {
+	const runs = input.runs ?? 3;
+	const readings = [];
+	for (let index = 0; index < runs; index++) {
+		if (input.signal?.aborted === true) break;
+		const startedAt = Date.now();
+		try {
+			const answer = await input.client.probeChat(input.credential, tpsProbeRequestBody(input.modelId), input.signal);
+			if (!answer.ok || answer.response === void 0) continue;
+			readings.push(await readTimedStream(answer.response.body, startedAt));
+		} catch {
+			continue;
+		}
+	}
+	return summarizeTps(input.modelId, readings, runs);
+}
+/**
 * Check in every account, one at a time.
 *
 * Idempotent by design (see the module note): an account already checked in
@@ -5369,6 +5677,17 @@ const WORKBUDDY_CHECKIN_PATH = "/plugins/dsh-connect-workbuddy/checkin";
 */
 const WORKBUDDY_PROBE_PATH = "/plugins/dsh-connect-workbuddy/probe";
 /**
+* Plugin-owned OUTPUT-SPEED measurement endpoint (issue #92).
+*
+* Separate from {@link WORKBUDDY_PROBE_PATH} because the two ask opposite
+* questions and cost different amounts: the availability probe sends 25,000
+* input tokens and caps output at one (measured `credit 0.72`), while this one
+* sends ~35 input tokens and caps output at 256 (measured `credit 0.01`–`0.15`).
+* Sharing the route would mean sharing its one-model-per-request cap and its
+* cost wording, and the two would then be wrong for each other.
+*/
+const WORKBUDDY_TPS_PATH = "/plugins/dsh-connect-workbuddy/tps";
+/**
 * Plugin-owned account-pool endpoint: one batch action per call.
 *
 * `?action=checkin` claims the daily reward for every account of a region;
@@ -6224,6 +6543,28 @@ function registerWorkBuddyStatusRoute(ctx, deps) {
 				}
 			}
 		});
+		const disposeTps = ctx.webServer.register({
+			kind: "exact",
+			path: WORKBUDDY_TPS_PATH,
+			handler: async (req, res) => {
+				if (req.method !== "POST") return json(res, 405, { error: "method not allowed" });
+				if (!loopbackOrigin(req)) return json(res, 403, { error: "origin-not-trusted" });
+				if (deps.measureTps === void 0) return json(res, 503, { error: "tps measurement unavailable" });
+				const region = requestRegion(req, res);
+				if (region === void 0) return;
+				try {
+					const body = await readJsonBody(req);
+					const modelIds = Array.isArray(body.modelIds) ? body.modelIds.filter((id) => typeof id === "string" && id !== "") : [];
+					if (modelIds.length === 0) return json(res, 400, { error: "modelIds must be a non-empty array of strings" });
+					if (modelIds.length > 1) return json(res, 400, { error: "a tps measurement accepts exactly one model" });
+					const results = [];
+					for (const modelId of modelIds) results.push(...await deps.measureTps(region, [modelId]));
+					json(res, 200, { results });
+				} catch (error) {
+					json(res, 500, { error: safeMessage(error) });
+				}
+			}
+		});
 		const disposePool = ctx.webServer.register({
 			kind: "exact",
 			path: WORKBUDDY_POOL_PATH,
@@ -6499,6 +6840,7 @@ function registerWorkBuddyStatusRoute(ctx, deps) {
 			disposeUsage();
 			disposeAccountCredits();
 			disposeProbe();
+			disposeTps();
 			disposePool();
 			disposeOAuth();
 			disposeTransfer();
@@ -6889,7 +7231,7 @@ function apply(ctx, config) {
 	}));
 	const configuredModels = (value, region, liveModels = []) => {
 		const state = regionStateOf(value, region);
-		const roster = state.lastCatalog?.length ? state.lastCatalog : liveModels.length ? liveModels : fallbackModelsFor(region);
+		const roster = state.lastCatalog?.length ? withoutRouters(state.lastCatalog) : liveModels.length ? liveModels : fallbackModelsFor(region);
 		const declared = withImageSelection(deriveCatalog(roster, new Set(state.enabledModelIds ?? []), state.contextBudgets ?? {}), new Set(state.imageModelIds ?? []));
 		return withEffectiveOff(declared, new Set(savedOffModelIds(state, declared))).map((model) => model.reasoning === void 0 || lastRefusalFor(model.id) === void 0 ? model : {
 			...model,
@@ -6911,7 +7253,7 @@ function apply(ctx, config) {
 	const savedOffModelIds = (state, roster) => state.offModelIds ?? defaultOffModelIds(roster);
 	const displayModels = (value, region) => {
 		const state = regionStateOf(value, region);
-		if (state.lastCatalog?.length) return state.lastCatalog;
+		if (state.lastCatalog?.length) return withoutRouters(state.lastCatalog);
 		const live = stacks[region]?.catalog?.current();
 		return live?.length ? live : fallbackModelsFor(region);
 	};
@@ -7149,6 +7491,51 @@ function apply(ctx, config) {
 			}));
 			return results;
 		},
+		/**
+		* Output-speed measurement (issue #92), region-scoped like every other
+		* spending path.
+		*
+		* Deliberately NOT routed through the probe's failover machinery: a speed
+		* number describes the MODEL, and having the pool silently serve the run
+		* from a different account would attach one account's rate limit (6004) to
+		* another's measurement. The selected credential runs all three samples, so
+		* "it failed" means this account could not measure it, which is the honest
+		* answer.
+		*/
+		async measureTps(region, modelIds, options) {
+			let credential;
+			try {
+				credential = await stacks[region].store.resolve();
+			} catch (error) {
+				const message = error instanceof Error ? error.message.slice(0, 300) : String(error).slice(0, 300);
+				return modelIds.map((modelId) => ({
+					modelId,
+					outcome: "credential-rejected",
+					samples: 0,
+					message
+				}));
+			}
+			const results = [];
+			for (const modelId of modelIds) {
+				const sample = await measureTps({
+					client,
+					credential,
+					modelId,
+					...options?.signal === void 0 ? {} : { signal: options.signal }
+				});
+				results.push({
+					modelId: sample.modelId,
+					outcome: sample.tokensPerSecond === void 0 ? "failed" : "ok",
+					...sample.tokensPerSecond === void 0 ? {} : { tokensPerSecond: sample.tokensPerSecond },
+					...sample.timeToFirstTokenMs === void 0 ? {} : { timeToFirstTokenMs: sample.timeToFirstTokenMs },
+					...sample.outputTokens === void 0 ? {} : { outputTokens: sample.outputTokens },
+					samples: sample.samples,
+					...sample.reason === void 0 ? {} : { reason: sample.reason },
+					...sample.credit === void 0 ? {} : { credit: sample.credit }
+				});
+			}
+			return results;
+		},
 		regionUsable(region, usable) {
 			if (stacks[region].catalog.setRegionUsable(usable)) invalidateCatalog();
 		},
@@ -8014,4 +8401,4 @@ function apply(ctx, config) {
 	});
 }
 //#endregion
-export { CREDENTIAL_REJECTED_CODE, Config, DEFAULT_PROBE_INPUT_TOKENS, ENCRYPTED_CREDENTIAL_CODE, FALLBACK_WORKBUDDY_MODELS, FALLBACK_WORKBUDDY_MODELS_GLOBAL, NATIVE_MODALITY_BY_MODEL_ID, PROBE_INPUT_TOKEN_CHOICES, PROBE_MAX_TOKENS, PROBE_SYSTEM_PROMPT, REFUSES_OFF_MODEL_IDS, WORKBUDDY_ACCOUNTS_REFRESH_PATH, WORKBUDDY_APP_EXECUTABLE_ENV, WORKBUDDY_AUTH_FILENAME, WORKBUDDY_AUTH_FILE_ENV, WORKBUDDY_CHECKIN_PATH, WORKBUDDY_CONNECT_VERSION, WORKBUDDY_GLOBAL_PROVIDER, WORKBUDDY_HOST_HEARTBEAT_FILENAME, WORKBUDDY_MODELS_REFRESH_PATH, WORKBUDDY_PROBE_PATH, WORKBUDDY_PROVIDER, WORKBUDDY_PROVIDERS, WORKBUDDY_PROVIDER_DISPLAY_NAMES, WORKBUDDY_REGIONS, WORKBUDDY_REGION_PARAM, WORKBUDDY_SETTINGS_NS, WORKBUDDY_STREAM_IDLE_TIMEOUT_MS, WORKBUDDY_USAGE_PATH, WorkBuddyCatalog, WorkBuddyCredentialRejectedError, WorkBuddyCredentialStore, WorkBuddyEncryptedCredentialError, WorkBuddyUpstreamClient, apply, asVolatile, authFileName, classifyUpstreamError, clearAtRestKeyCache, clearHostHeartbeat, cooldownOf, createAccountUsabilityProbe, createWorkBuddyAdapter, createWorkBuddyShim, creditOfStream, defaultDesktopAuthCandidates, defaultDesktopAuthDirs, defaultDesktopAuthPath, defaultOffModelIds, deriveAtRestKey, deriveAtRestKeyId, deriveCatalog, fallbackModelsFor, fetchAtRestKeyPayload, findWorkbuddyAppExecutable, hasEncryptedCredentialFields, imageDefaultFor, inject, isCredentialRejectedError, isEncryptedCredentialError, isEncryptedFieldWrapper, isHeartbeatProcessAlive, isWorkbuddyBundle, knownRegionOf, legacyAttributionRegion, legacyWorkbuddyOwnAuthPath, macosBundleExecutable, macosNestedAppBundles, modelIdOfBody, name, nativeModalityOf, nextRegionEnabled, nextRegionSlots, offDefaultFor, openEncryptedField, outcomeOfFailure, parseCreditMultiplier, parseReasoning, parseRetryAfter, parseUpstreamModel, parseWorkBuddyAuth, prepareChatBody, probeModel, probeRequestBody, probeSucceeded, processStartTimeMs, readAtRestKey, readHostHeartbeat, regionCleared, regionEnabled, regionEnabledOf, regionOf, regionOfProvider, regionOfStatusUrl, regionStateOf, registerWorkBuddyStatusRoute, resolveCredentialRecovery, selectAccountFor, settingsNamespaceOf, toPersistedWorkBuddyModel, unwrapVolatileDeep, withEffectiveOff, withWorkBuddyRegion, workBuddyDisplayName, workBuddyModelInput, workBuddyThinkingLevelMap, workBuddyWebStatus, workbuddyAccountId, workbuddyAppExecutableCandidates, workbuddyHostHeartbeatPath, workbuddyOwnAuthPath, writeHostHeartbeat };
+export { CREDENTIAL_REJECTED_CODE, Config, DEFAULT_PROBE_INPUT_TOKENS, ENCRYPTED_CREDENTIAL_CODE, FALLBACK_WORKBUDDY_MODELS, FALLBACK_WORKBUDDY_MODELS_GLOBAL, NATIVE_MODALITY_BY_MODEL_ID, PROBE_INPUT_TOKEN_CHOICES, PROBE_MAX_TOKENS, PROBE_SYSTEM_PROMPT, REFUSES_OFF_MODEL_IDS, WORKBUDDY_ACCOUNTS_REFRESH_PATH, WORKBUDDY_APP_EXECUTABLE_ENV, WORKBUDDY_AUTH_FILENAME, WORKBUDDY_AUTH_FILE_ENV, WORKBUDDY_CHECKIN_PATH, WORKBUDDY_CONNECT_VERSION, WORKBUDDY_GLOBAL_PROVIDER, WORKBUDDY_HOST_HEARTBEAT_FILENAME, WORKBUDDY_MODELS_REFRESH_PATH, WORKBUDDY_PROBE_PATH, WORKBUDDY_PROVIDER, WORKBUDDY_PROVIDERS, WORKBUDDY_PROVIDER_DISPLAY_NAMES, WORKBUDDY_REGIONS, WORKBUDDY_REGION_PARAM, WORKBUDDY_SETTINGS_NS, WORKBUDDY_STREAM_IDLE_TIMEOUT_MS, WORKBUDDY_TPS_PATH, WORKBUDDY_USAGE_PATH, WorkBuddyCatalog, WorkBuddyCredentialRejectedError, WorkBuddyCredentialStore, WorkBuddyEncryptedCredentialError, WorkBuddyUpstreamClient, apply, asVolatile, authFileName, classifyUpstreamError, clearAtRestKeyCache, clearHostHeartbeat, cooldownOf, createAccountUsabilityProbe, createWorkBuddyAdapter, createWorkBuddyShim, creditOfStream, defaultDesktopAuthCandidates, defaultDesktopAuthDirs, defaultDesktopAuthPath, defaultOffModelIds, deriveAtRestKey, deriveAtRestKeyId, deriveCatalog, fallbackModelsFor, fetchAtRestKeyPayload, findWorkbuddyAppExecutable, hasEncryptedCredentialFields, imageDefaultFor, inject, isCredentialRejectedError, isEncryptedCredentialError, isEncryptedFieldWrapper, isHeartbeatProcessAlive, isWorkbuddyBundle, knownRegionOf, legacyAttributionRegion, legacyWorkbuddyOwnAuthPath, macosBundleExecutable, macosNestedAppBundles, modelIdOfBody, name, nativeModalityOf, nextRegionEnabled, nextRegionSlots, offDefaultFor, openEncryptedField, outcomeOfFailure, parseCreditMultiplier, parseReasoning, parseRetryAfter, parseUpstreamModel, parseWorkBuddyAuth, prepareChatBody, probeModel, probeRequestBody, probeSucceeded, processStartTimeMs, readAtRestKey, readHostHeartbeat, regionCleared, regionEnabled, regionEnabledOf, regionOf, regionOfProvider, regionOfStatusUrl, regionStateOf, registerWorkBuddyStatusRoute, resolveCredentialRecovery, selectAccountFor, settingsNamespaceOf, toPersistedWorkBuddyModel, unwrapVolatileDeep, withEffectiveOff, withWorkBuddyRegion, workBuddyDisplayName, workBuddyModelInput, workBuddyThinkingLevelMap, workBuddyWebStatus, workbuddyAccountId, workbuddyAppExecutableCandidates, workbuddyHostHeartbeatPath, workbuddyOwnAuthPath, writeHostHeartbeat };

package/locale/en.json

@@ -1,6 +1,6 @@
 {
   "meta": {
-    "title": "WorkBuddy Model Access",
+    "title": "dsh-connect-workbuddy",
     "description": "Connects locally signed-in WorkBuddy models, CN and international alike, to DSH, reading each model's credit multiplier from the upstream catalog on every refresh, with per-model image input toggles, account switching backed by an auto-failing-over pool, manual daily check-in, and read-only credit overviews shown as compact pills on the card and in the composer."
   }
 }

package/locale/zh.json

@@ -1,6 +1,6 @@
 {
   "meta": {
-    "title": "WorkBuddy 模型接入",
+    "title": "dsh-connect-workbuddy",
     "description": "将本机登录的 WorkBuddy 模型（国内版与国际版）接入 DSH，每次刷新按上游目录自动读取每个模型的积分倍率，支持逐模型图片输入开关、多账号切换与账号池自动换号，并提供每日签到、卡片与输入框里的胶囊积分读数等只读积分概览。"
   }
 }

package/package.json

@@ -2,7 +2,7 @@
   "name": "dsh-connect-workbuddy",
   "displayName": "DSH Connect WorkBuddy",
   "description": "把本机登录的 WorkBuddy 模型（国内版与国际版）接入 DeepSeek Harness：每次刷新按上游目录自动读取每个模型的积分倍率，支持逐模型图片输入开关、多账号切换与账号池自动换号，并提供每日签到、卡片与输入框里的胶囊积分读数等只读积分概览。",
-  "version": "5.0.0",
+  "version": "5.2.1",
   "author": "dingminhua",
   "copyright": "Copyright (c) 2026 LaoDing",
   "license": "MIT",