dsh-plugin-teamflow 0.1.4 → 0.1.5

package/CHANGELOG.md

@@ -2,6 +2,21 @@
 
 > 本插件首次公开发布版本为 **v0.1.0**；发布前的内部迭代（v0.3~v0.13）记录于 `AGENTS.md` §5，对外统一归到 v0.1.0。
 
+## [0.1.5] - 2026-09-01
+
+### 新增
+- **patch 档兑现「单 agent 直改 + 自测即交付」**：阶段集精简为确认单 → 单 agent 直改（2 段，无技术方案/QA/验收），开发完成（自测通过）即统一收口提交。UI 微调（按钮换位置/挪控件/改文案/间距/颜色）、常量调整、单点修复、回滚、笔误修正走最轻路径
+
+### 改进
+- **需求分诊重构为模型主导**：档位判断交给模型（自然语言语义，天然双语）；正则收窄为确定性护栏（架构信号强升/UI 不低于轻量档/显式设计升档）。UI 微调类需求（不改变行为/交互逻辑）不再误判标准档
+- **分诊输出失败自动纠错重试**：只输出开场白无 JSON 时带提示重试一次，仍失败才走正则兜底
+
+### 修复
+- **外部中止（aborted）不再误报「预算熔断」**：重启等外部中止单独标记，明确引导断点续跑（补跑失败任务，已完成任务复用）
+- **patch 档不再误跑架构蓝图**（技术方案块补 `enabled('tech')` 门控）
+- **分支名不再被档位词污染**（「显式的用 patch 模式」不再产出 `feat/patch`）
+- **provider 错误细节记录**（阶段失败记录底层错误信息）
+
 ## [0.1.4] - 2026-08-29
 
 ### 修复

package/lib/host.mjs

@@ -157,9 +157,7 @@ const STAGE_POLICY = {
 			key: "scaffold",
 			when: (o) => !!o.needScaffold
 		},
-		{ key: "tech" },
-		{ key: "dev" },
-		{ key: "acceptance" }
+		{ key: "dev" }
 	]
 };
 /** 按档位 + 条件展开实际执行阶段集（纯函数；未知档回退 full）。 */
@@ -266,7 +264,24 @@ function deriveBranchSlug(requirement, reqId, triageSlug, branchName) {
 	if (branchName && /^[a-z0-9][a-z0-9-_]*$/i.test(branchName)) return String(branchName).replace(/[^a-z0-9-]/gi, "-").toLowerCase().slice(0, 40);
 	if (triageSlug && /^[a-z0-9-]{3,24}$/i.test(triageSlug)) return triageSlug;
 	const en = String(requirement || "").match(/[a-zA-Z][a-zA-Z0-9-]{2,23}/g);
-	if (en && en.length) return en[0].toLowerCase().slice(0, 40);
+	if (en && en.length) {
+		const NOISE = /* @__PURE__ */ new Set([
+			"patch",
+			"lite",
+			"tech",
+			"full",
+			"medium",
+			"mode",
+			"the",
+			"and",
+			"for",
+			"with",
+			"use",
+			"using"
+		]);
+		const hit = en.find((w) => !NOISE.has(w.toLowerCase()));
+		if (hit) return hit.toLowerCase().slice(0, 40);
+	}
 	const num = String(reqId || "").match(/\d+/);
 	if (num) return `r${num[0]}`;
 	return "feature";
@@ -1569,6 +1584,7 @@ async function runAgent(journal, parent, label, phase, prompt, signal) {
 		}
 		stage.status = "failed";
 		stage.outcome = stop === "completed" && text ? "insubstantial" : stop || "error";
+		const errDetail = result && result.error;
 		if (stage.outcome === "insubstantial") {
 			stage.summary = "产出未通过实质校验（含拒绝措辞或内容过短），视为未交付";
 			journal.logs.push({
@@ -1577,11 +1593,11 @@ async function runAgent(journal, parent, label, phase, prompt, signal) {
 				message: `${label} 产出未通过实质校验（拒绝措辞/内容过短）`
 			});
 		} else {
-			stage.summary = `未产出有效结果（stopReason=${stop || "unknown"}）`;
+			stage.summary = `未产出有效结果（stopReason=${stop || "unknown"}${errDetail ? `，error=${String(errDetail).slice(0, 200)}` : ""}）`;
 			journal.logs.push({
 				t: Date.now(),
 				level: "error",
-				message: `${label} 未产出有效结果（stopReason=${stop || "unknown"}）`
+				message: `${label} ${stage.summary}`
 			});
 		}
 		return null;
@@ -1643,6 +1659,19 @@ async function withRetry(journal, parent, label, phase, prompt, signal) {
 				stageTokens
 			};
 		}
+		if (lastStage && lastStage.outcome === "aborted") {
+			journal.logs.push({
+				t: Date.now(),
+				level: "warn",
+				message: `${label} 被外部中止（aborted），未正常产出——非预算问题；可 teamflow_resume 续跑（补跑失败任务，已完成任务复用）`
+			});
+			journal.humanIntervention = true;
+			return {
+				text: null,
+				attempts,
+				stageTokens
+			};
+		}
 		if (lastStage && lastStage.outcome === "degenerated") {
 			journal.logs.push({
 				t: Date.now(),
@@ -2168,8 +2197,8 @@ ${vision ? "[Visual re-check] If QA saved screenshots under the task folder, spo
 5. Chinese Markdown.
 6. [State] End with a state block (phase="acceptance"), summary = acceptance conclusion, verdict = "accepted/rework/reject/needs-human", extra.done = confirmation of this delivery.${STATE_BLOCK_INSTRUCTION}`;
 /** 需求分诊模型 prompt（模型驱动 triage；供 core/triage.runTriage 使用）。 */
-const TRIAGE_PROMPT = (requirement, opts, pre) => `You are a senior research-dev triage analyst. Do ONE thing: analyze which pipeline mode this dev requirement fits, then give the conclusion. No code, no scope speculation.
-[RAW REQUIREMENT]
+const TRIAGE_PROMPT = (requirement, opts, pre, retryHint) => `You are a senior research-dev triage analyst. Do ONE thing: analyze which pipeline mode this dev requirement fits, then give the conclusion. No code, no scope speculation.
+${retryHint ? `[RETRY — YOUR LAST REPLY FAILED]\n${retryHint}\n` : ""}[RAW REQUIREMENT]
 ${requirement}
 ${pre.rationale.length ? `\n[REGEX PRE-FILTER SIGNALS (reference only; judge semantically, don't blindly follow)]\n${pre.rationale.join("\n")}` : ""}
 \n[OPTIONAL SIGNAL] UI work needed: ${opts && opts.needDesign ? "yes" : "not flagged"}
@@ -2183,12 +2212,12 @@ ${pre.rationale.length ? `\n[REGEX PRE-FILTER SIGNALS (reference only; judge sem
 
 [JUDGMENT POINTS]
 1. Distinguish "user-visible functional change" vs "internal tech change": refactors/optimizations, even large code volume, usually go tech, not full.
-2. UI/visual/interaction/buttons/pages involved → at least medium (excludes patch/tech).
+2. **UI feature work** (new screens/components/interactions/pages) → at least medium (excludes patch/tech). **UI micro-adjustments** — moving a button, relocating a control, changing copy/labels, spacing/padding, color tweaks, "move the button", "switch the button position" — are patch-or-lite material, NOT medium: no new interaction logic, no design phase worth the token cost. The line: does it change behavior/interaction logic (medium) or just placement/appearance of existing elements (patch/lite)?
 3. hotfix/single-point/pure numeric/pure docs → patch; clear "add feature X" → pick lite/medium/full by size.
 4. Focused change (even with tests/regression) → lite/tech by nature; not necessarily full.
 5. [M1 ARCHITECTURE CRITERION (important)] **Architecture-level changes** — persistence/localStorage/database/standalone module/abstraction/cross-many-files without an existing reusable wrapper (like a localStorage wrapper, storage layer, state management) — even if they look like "small features", go **at least medium** (must pass the architecture stage and produce a blueprint, avoiding scattered local implementations by dev); such changes collapse under a light "micro feature" tier. Tech-driven rework (refactor/optimize/arch upgrade) is itself tech (tech also runs the lightweight blueprint now).
 
-[OUTPUT] one JSON object only (no other text):
+[OUTPUT] JSON object ONLY — no commentary, no preface, no closing text. The FIRST character of your reply must be '{'. Do NOT say anything like "here is the JSON" or "Let me output the JSON" — output the object itself:
 { "mode": "patch|lite|tech|medium|full", "slug": "<topic words> (3-24 lowercase letters/digits/hyphens, e.g. wallkick-toggle, 7bag-random; used to name the task folder)", "kind": "one-word nature", "needDesign": true|false, "complexity": "small|medium|large", "rationale": ["key argument 1","key argument 2"], "confidence": "high|medium|low" }`;
 /** tech 档 PRD：技术变更单（无功能 AC，重范围/目标/改动面/回归）。 */
 const techChangePrompt = (requirement, root, runId, state) => `You are the senior tech lead. The current workspace IS the target project. This is a **tech-driven rework** requirement (refactor/optimize/upgrade/architecture/dependencies/tech debt) — the product doesn't need a full feature PRD, but needs a **技术变更单** (tech change sheet) as the contract for dev/QA/acceptance and memory write-back.
@@ -2268,140 +2297,72 @@ const MODE_REGISTRY = {
 		desc: "单行/常量/版本号/hotfix：单 agent 直改+自测即交付（无独立 QA）"
 	}
 };
-/** 关键词信号集（命中 → 加重某档倾向）。 */
-const SIGNALS = [
-	{
-		mode: "patch",
-		words: [
-			"hotfix",
-			"热修",
-			"修复 bug",
-			"修 bug",
-			"改个 bug",
-			"版本号",
-			"常量",
-			"一行",
-			"bump",
-			"回滚",
-			"卫生",
-			"笔误",
-			"拼写"
-		]
-	},
-	{
-		mode: "tech",
-		words: [
-			"重构",
-			"优化",
-			"升级",
-			"架构",
-			"性能",
-			"依赖",
-			"脚手架",
-			"缓存",
-			"清理",
-			"遗留债",
-			"工程",
-			"内部改造",
-			"技术债"
-		]
-	},
-	{
-		mode: "lite",
-		words: [
-			"微功能",
-			"小功能",
-			"小增强",
-			"加个",
-			"补一个",
-			"轻微",
-			"顺手"
-		]
-	},
-	{
-		mode: "medium",
-		words: [
-			"界面",
-			"UI",
-			"视觉",
-			"页面",
-			"按钮",
-			"样式",
-			"交互",
-			"布局",
-			"组件",
-			"持久化",
-			"localStorage",
-			"本地存储",
-			"存储",
-			"保存",
-			"恢复",
-			"存档",
-			"独立模块",
-			"抽象",
-			"存储层",
-			"sessionStorage",
-			"IndexedDB",
-			"跨模块",
-			"数据层"
-		]
-	},
-	{
-		mode: "full",
-		words: [
-			"跨模块",
-			"完整",
-			"大型",
-			"对接",
-			"集成",
-			"模块化",
-			"重构为",
-			"二期",
-			"平台"
-		]
-	}
+/** 确定性护栏关键词（双语，仅 fallback 兜底用；主路由是模型——TRIAGE_PROMPT 语义判断）。
+* 架构信号：持久化/存储/独立模块/抽象/跨模块——防「轻档位局部实现塌方」（M1 架构护栏）。
+* UI 信号：UI 相关需求不得落 patch/tech（无设计/QA 的档位）——最低 lite。 */
+const ARCH_SIGNALS = [
+	"持久化",
+	"存储",
+	"保存",
+	"恢复",
+	"存档",
+	"独立模块",
+	"抽象",
+	"存储层",
+	"localStorage",
+	"sessionStorage",
+	"IndexedDB",
+	"跨模块",
+	"数据层",
+	"persistence",
+	"storage",
+	"database",
+	"数据库",
+	"standalone module",
+	"abstraction"
+];
+const UI_SIGNALS = [
+	"界面",
+	"UI",
+	"视觉",
+	"页面",
+	"按钮",
+	"样式",
+	"交互",
+	"布局",
+	"组件",
+	"page",
+	"button",
+	"style",
+	"layout",
+	"component",
+	"visual",
+	"interaction"
 ];
-/** 对原始需求做启发式分诊。返回建议 mode + 判定理由 + 置信。 */
+/** 对原始需求做启发式分诊（兜底路径专用）。返回建议 mode + 判定理由 + 置信。
+* 只做确定性护栏（架构强升/UI 禁轻档/needDesign 升档）——不再逐词匹配五档信号：
+* 主路由是模型（TRIAGE_PROMPT 语义判断，天然双语），正则兜底在模型不可用时宁重勿漏（默认 full）。 */
 function suggestMode(requirement, opts) {
 	const text = String(requirement || "");
-	const hits = [];
-	for (const sig of SIGNALS) for (const w of sig.words) if (text.includes(w)) hits.push({
-		mode: sig.mode,
-		word: w
-	});
-	const rationale = hits.map((h) => `命中「${h.word}」→ ${h.mode}`);
-	const countOf = (m) => hits.filter((h) => h.mode === m).length;
+	const rationale = [];
 	let mode = "full";
-	if (countOf("patch") > 0) mode = "patch";
-	else if (countOf("tech") > 0 && countOf("medium") === 0 && countOf("full") === 0) mode = "tech";
-	else if (countOf("lite") > 0 && countOf("medium") === 0) mode = "lite";
-	else if (countOf("medium") > 0 || opts && opts.needDesign) mode = "medium";
-	else if (hits.length === 0) mode = "full";
-	if ((mode === "patch" || mode === "tech") && opts && opts.needDesign) mode = "medium";
-	if (mode === "patch" && (countOf("tech") > 0 || text.includes("新增") || text.includes("功能"))) mode = "lite";
-	const architectureSignals = [
-		"持久化",
-		"localStorage",
-		"本地存储",
-		"存储",
-		"保存",
-		"恢复",
-		"存档",
-		"独立模块",
-		"抽象",
-		"存储层",
-		"sessionStorage",
-		"IndexedDB",
-		"跨模块",
-		"数据层"
-	];
-	if ((mode === "lite" || mode === "tech" || mode === "patch") && architectureSignals.some((w) => text.includes(w))) {
+	const archHit = ARCH_SIGNALS.find((w) => text.includes(w));
+	if (archHit) {
+		mode = "medium";
+		rationale.push(`架构护栏：需求含「${archHit}」→ 强升 medium（需架构阶段产蓝图，防塌）`);
+	}
+	const uiHit = !archHit ? UI_SIGNALS.find((w) => text.includes(w)) : void 0;
+	if (uiHit) {
+		mode = mode === "full" ? "lite" : mode;
+		rationale.push(`UI 护栏：需求含「${uiHit}」→ 不低于 lite（UI 改动需 QA/验收）`);
+	}
+	if (opts && opts.needDesign && mode !== "medium") {
 		mode = "medium";
-		rationale.push(`架构护栏：需求含「${architectureSignals.find((w) => text.includes(w))}」→ 强升 medium（需架构阶段）`);
+		rationale.push("needDesign=true → 强升 medium（显式要求设计阶段）");
 	}
-	const kind = mode === "patch" ? "热修/单点" : mode === "tech" ? "技术驱动改造" : mode === "lite" ? "微功能" : mode === "medium" ? "标准功能(含UI)" : "完整需求";
-	const confidence = mode === "patch" ? "high" : hits.length >= 2 ? "medium" : "low";
-	if (rationale.length === 0) rationale.push("无强信号，默认 full（护栏优先）");
+	if (rationale.length === 0) rationale.push("无强护栏信号，默认 full（模型不可用时宁重勿漏）");
+	const kind = mode === "medium" ? "标准功能(含UI)" : mode === "lite" ? "微功能" : "完整需求";
+	const confidence = mode === "medium" && !opts?.needDesign ? "medium" : "low";
 	return {
 		mode,
 		kind,
@@ -2459,29 +2420,36 @@ function fallbackVerdict(requirement, opts) {
 		source: "fallback"
 	};
 }
-/** 模型驱动分诊：spawn「分诊分析师」子代理思考一轮；子代理不可用/超时/解析失败 → 正则兜底。 */
+/** 模型驱动分诊：spawn「分诊分析师」子代理思考一轮；子代理不可用/超时/解析失败 → 正则兜底。
+* 解析失败先带纠错提示重试一次（实锤 run tf-mtfo8exi：模型输出「Let me output the JSON.」开场白
+* 后无 JSON——首轮输出预算被思考耗尽/模型停早；重试提示直接输出 JSON 对象本身）。 */
 async function runTriage(requirement, opts, parent, signal) {
 	const subagents = runtime.subagents;
 	if (!subagents || typeof subagents.start !== "function") return fallbackVerdict(requirement, opts);
 	const pre = suggestMode(requirement, opts);
-	let run = null;
-	try {
-		run = await subagents.start(providerName(), {
-			label: "需求分诊",
-			prompt: [{
-				type: "text",
-				text: TRIAGE_PROMPT(requirement, opts, pre)
-			}],
-			parent,
-			signal
-		});
-		const result = await Promise.race([run.result, new Promise((_, rej) => setTimeout(() => rej(/* @__PURE__ */ new Error("triage 超时（90s）")), 9e4))]);
-		const parsed = parseVerdictText(extractText(result && result.output));
-		if (parsed) return parsed;
-	} catch (e) {} finally {
-		if (run && run.dispose) try {
-			await run.dispose();
-		} catch (e) {}
+	for (let attempt = 1; attempt <= 2; attempt++) {
+		let run = null;
+		try {
+			const hint = attempt > 1 ? "Your previous reply contained only a preface (e.g. \"Let me output the JSON.\") with NO JSON object — that is a failed reply. Reply now with the JSON object ITSELF as the first and only content, starting with {." : "";
+			run = await subagents.start(providerName(), {
+				label: "需求分诊",
+				prompt: [{
+					type: "text",
+					text: TRIAGE_PROMPT(requirement, opts, pre, hint)
+				}],
+				parent,
+				signal
+			});
+			const result = await Promise.race([run.result, new Promise((_, rej) => setTimeout(() => rej(/* @__PURE__ */ new Error("triage 超时（90s）")), 9e4))]);
+			const parsed = parseVerdictText(extractText(result && result.output));
+			if (parsed) return parsed;
+		} catch (e) {
+			if (attempt === 2) {}
+		} finally {
+			if (run && run.dispose) try {
+				await run.dispose();
+			} catch (e) {}
+		}
 	}
 	return fallbackVerdict(requirement, opts);
 }
@@ -2976,48 +2944,50 @@ async function executePipeline(journal, parent, requirement, options, signal, re
 			}
 		}
 		let tech = null;
-		if (resumed("技术方案")) {
-			tech = resume.products.tech;
-			timeline.tech = tech;
-			logSkip("技术方案");
-		} else {
-			const isHeavy = !options.lite && options.mode !== "tech" && options.mode !== "patch";
-			journal.logs.push({
-				t: Date.now(),
-				level: "phase",
-				message: isHeavy ? "进入阶段：技术方案" : "进入阶段：架构蓝图"
-			});
-			const label = isHeavy ? "高级全栈工程师 · 技术方案" : "架构师 · 架构蓝图";
-			const techR = await withRetry(journal, parent, label, "技术方案", isHeavy ? techPrompt(prd, design, scaffold, tasks, root, journal.id, state) : architectPrompt(prd, root, journal.id, state), signal);
-			if (!techR.text) throw stageFailError(label, techR);
-			tech = techR.text;
-			timeline.tech = tech;
-			mergeStageState("tech", tech);
-			let bd = extractBlueprint(tech);
-			if (!bd || bd.summary === void 0) try {
-				const techFile = journal.runDocs && journal.workspacePath ? `${journal.workspacePath}/${journal.runDocs}/TECHNICAL.md` : null;
-				if (techFile && existsSync(techFile)) bd = extractBlueprint(readFileSync(techFile, "utf8"));
-				if (bd) journal.logs.push({
+		if (enabled("tech")) {
+			if (resumed("技术方案")) {
+				tech = resume.products.tech;
+				timeline.tech = tech;
+				logSkip("技术方案");
+			} else {
+				const isHeavy = !options.lite && options.mode !== "tech" && options.mode !== "patch";
+				journal.logs.push({
 					t: Date.now(),
-					level: "info",
-					message: "蓝图从任务夹 TECHNICAL.md 提取（模型把蓝图写进了文档而非回复输出）"
+					level: "phase",
+					message: isHeavy ? "进入阶段：技术方案" : "进入阶段：架构蓝图"
 				});
-			} catch (e) {}
-			if (bd && bd.summary !== void 0) try {
-				state.__runCtx = state.__runCtx || {};
-				state.__runCtx.blueprint = bd.render;
-				journal.blueprint = {
-					modules: bd.modules,
-					tasks: bd.tasks
-				};
-			} catch (e) {}
-			else if (/<!-- blueprint -->/.test(String(tech))) journal.logs.push({
-				t: Date.now(),
-				level: "warn",
-				message: "技术方案蓝图块解析失败（JSON 畸形），开发任务将回退整体开发——TECHNICAL.md 蓝图块需人工检查"
-			});
-			noteTaskStageUsage(journal);
-			if (journal.cancelled) return;
+				const label = isHeavy ? "高级全栈工程师 · 技术方案" : "架构师 · 架构蓝图";
+				const techR = await withRetry(journal, parent, label, "技术方案", isHeavy ? techPrompt(prd, design, scaffold, tasks, root, journal.id, state) : architectPrompt(prd, root, journal.id, state), signal);
+				if (!techR.text) throw stageFailError(label, techR);
+				tech = techR.text;
+				timeline.tech = tech;
+				mergeStageState("tech", tech);
+				let bd = extractBlueprint(tech);
+				if (!bd || bd.summary === void 0) try {
+					const techFile = journal.runDocs && journal.workspacePath ? `${journal.workspacePath}/${journal.runDocs}/TECHNICAL.md` : null;
+					if (techFile && existsSync(techFile)) bd = extractBlueprint(readFileSync(techFile, "utf8"));
+					if (bd) journal.logs.push({
+						t: Date.now(),
+						level: "info",
+						message: "蓝图从任务夹 TECHNICAL.md 提取（模型把蓝图写进了文档而非回复输出）"
+					});
+				} catch (e) {}
+				if (bd && bd.summary !== void 0) try {
+					state.__runCtx = state.__runCtx || {};
+					state.__runCtx.blueprint = bd.render;
+					journal.blueprint = {
+						modules: bd.modules,
+						tasks: bd.tasks
+					};
+				} catch (e) {}
+				else if (/<!-- blueprint -->/.test(String(tech))) journal.logs.push({
+					t: Date.now(),
+					level: "warn",
+					message: "技术方案蓝图块解析失败（JSON 畸形），开发任务将回退整体开发——TECHNICAL.md 蓝图块需人工检查"
+				});
+				noteTaskStageUsage(journal);
+				if (journal.cancelled) return;
+			}
 		}
 		let devResults = null;
 		if (resumed("开发")) {
@@ -3244,7 +3214,22 @@ async function executePipeline(journal, parent, requirement, options, signal, re
 			if (journal.cancelled) return;
 		}
 		persistJournal(journal);
-		if (!qaBlocked) {
+		if (!enabled("acceptance")) {
+			journal.logs.push({
+				t: Date.now(),
+				level: "info",
+				message: "patch 档交付完成：单 agent 直改 + 自测即收口（无独立 QA/验收）"
+			});
+			advanceTask(journal, "accepted", null, "patch 直改交付（自测通过）", { by: "dev" });
+			const store = storeFor(scopeKey);
+			const req = store.find("req", journal.reqId);
+			if (req && req.status !== "accepted") {
+				store.pushEvent(req, req.status, "accepted", "patch 交付通过（自测）");
+				req.status = "accepted";
+				store.persist();
+			}
+			journal.status = "completed";
+		} else if (!qaBlocked) {
 			journal.logs.push({
 				t: Date.now(),
 				level: "phase",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "dsh-plugin-teamflow",
-  "version": "0.1.4",
+  "version": "0.1.5",
   "description": "TeamFlow 团队研发流水线（TypeScript）：需求→PRD→设计→架构→技术方案→并行开发→QA→验收；backlog 持久化 + 断点续跑 + 完成汇报 + 防假交付；Web 团队工作台（conversation.view tab + 拖拽看板）",
   "type": "module",
   "main": "./lib/host.mjs",