mocode-ai 1.1.6 → 1.1.7

package/dist/agent/core.js

@@ -201,6 +201,34 @@ export function askHumanBudgetAnnotation(askHumanCountThisTurn, status) {
     // 第 3+ 次(超过预算):强硬提示,鼓励模型停下问自己是否还有意义。
     return `\n\n[ask budget EXCEEDED] This is ask_human call #${askHumanCountThisTurn} this turn (budget = ${ASK_HUMAN_PER_TURN_BUDGET}). Stop asking; choose a default, implement, and disclose the choice in your final reply. Continuing to ask is more harmful than a documented guess.`;
 }
+/** NARR-01: 工具轮旁白(assistant 消息同时带 content + tool_calls)的软预算。
+ * 超出即追加回压提示;未超只 emit trace(可度量,不打扰)。
+ * 单位是 code point 而非字节——中文一字一 point,英文一字母一 point,
+ * 对两种语言都是"一句话大约多长"的直觉量级。 */
+export const NARRATION_CHAR_BUDGET = 120;
+/** 分类工具轮旁白。返回 null 表示这一轮没有旁白(纯工具调用,理想情况)。
+ * hint 仅在超预算时非 null:prompt 里的"工具轮保持静默"是软约束,
+ * 这里给出机制层面的回压,同时让 trace 能统计旁白率。 */
+export function classifyNarration(content, toolCallCount) {
+    const text = content?.trim() ?? '';
+    if (!text)
+        return null;
+    const chars = [...text].length;
+    if (chars <= NARRATION_CHAR_BUDGET) {
+        return { chars, overBudget: false, hint: null };
+    }
+    const plural = toolCallCount === 1 ? '' : 's';
+    return {
+        chars,
+        overBudget: true,
+        hint: `\n\n[narration] Your previous message emitted ${chars} characters of prose alongside ` +
+            `${toolCallCount} tool call${plural} (soft budget = ${NARRATION_CHAR_BUDGET}). ` +
+            'Interstitial commentary costs the user screen space and costs you context on every ' +
+            'later step. For the rest of this turn, emit prose mid-turn ONLY to (a) flag a genuine ' +
+            'decision fork needing user input, (b) disclose an error or risk, or (c) deliver the ' +
+            'final answer once tools are done. Otherwise call the next tool with no preamble.',
+    };
+}
 function pushToolResult(history, tc, output, pruner, lifecycle, _scheduler, runtimeContextState = contextState, succeededOverride) {
     const succeeded = succeededOverride ?? isToolResultSuccess(output);
     const ageAware = config.contextOptimize ? ageAwareStateFor(history) : null;
@@ -243,6 +271,15 @@ export async function runAgentCore(opts) {
     // 预算超过时,工具结果尾部追加 ask budget 提示,不直接拒绝调用(更轻量,
     // 也避免和现有 permission 系统的"拒绝"语义重叠)。
     let askHumanCountThisTurn = 0;
+    // NARR-01: 上一条 assistant 消息(带 tool_calls)超出旁白预算时,待注入的回压提示。
+    // 只挂在本批次的第一条工具结果上并立即清空——重复注入会变成新的噪声源。
+    let pendingNarrationHint = null;
+    /** 取出并清空待注入的旁白回压提示(每批工具只消费一次)。 */
+    const takeNarrationHint = () => {
+        const hint = pendingNarrationHint;
+        pendingNarrationHint = null;
+        return hint;
+    };
     // PROMPT-02: 解析 preCompletionChecklist 选项。undefined = 启用默认 middleware;
     // false = opt-out(checklist 自身调试用);function = 调用方自定义。
     const _checklistMiddleware = createPreCompletionChecklistMiddleware();
@@ -556,6 +593,22 @@ export async function runAgentCore(opts) {
                             function: { name: tc.name, arguments: tc.arguments },
                         })),
                     });
+                    // NARR-01: 这条 assistant 消息同时带正文 + tool_calls,即"工具轮旁白"。
+                    // prompt 里的"工具轮保持静默"只是软约束,这里补上机制层:
+                    //   - 永远 emit trace(旁白率可度量,不再靠肉眼感觉);
+                    //   - 超预算时把回压提示挂到本批第一条工具结果尾部(复用 thrash/ask
+                    //     budget 已验证的注入接缝,不新增消息、不打断工具流)。
+                    const narration = classifyNarration(result.content, result.toolCalls.length);
+                    if (narration) {
+                        emitTrace('narration', {
+                            chars: narration.chars,
+                            toolCalls: result.toolCalls.length,
+                            budget: NARRATION_CHAR_BUDGET,
+                            overBudget: narration.overBudget,
+                            step,
+                        });
+                        pendingNarrationHint = narration.hint;
+                    }
                     // 工具分组执行(保 tool_calls 原顺序)：safe parallel 工具照常并发；连续
                     // resource-locked mutation 先按序完成权限预检，再按 canonical resource lock 启动。
                     // registry 对所有真实资源访问统一持锁，所以不同 Agent 间的 read/write/process 也不会竞态。
@@ -685,7 +738,9 @@ export async function runAgentCore(opts) {
                                     }, tc.id ? { providerToolCallId: tc.id } : {});
                                 }
                                 const askBudget = askHumanBudgetAnnotation(askHumanCountThisTurn, outcome.status);
-                                const finalOutput = askBudget ? `${annotated}${askBudget}` : annotated;
+                                // NARR-01: 旁白回压提示只挂本批第一条结果(takeNarrationHint 自清空)。
+                                const narrationHint = takeNarrationHint();
+                                const finalOutput = `${annotated}${askBudget ?? ''}${narrationHint ?? ''}`;
                                 pushToolResult(history, tc, finalOutput, relprune, lifecycle, scheduler, runtimeContextState, outcome.status === 'success');
                             }
                             hooks.onToolDone?.();
@@ -874,7 +929,9 @@ export async function runAgentCore(opts) {
                                 }, tc.id ? { providerToolCallId: tc.id } : {});
                             }
                             const askBudget = askHumanBudgetAnnotation(askHumanCountThisTurn, outcome.status);
-                            const finalOutput = askBudget ? `${annotated}${askBudget}` : annotated;
+                            // NARR-01: 旁白回压提示只挂本批第一条结果(takeNarrationHint 自清空)。
+                            const narrationHint = takeNarrationHint();
+                            const finalOutput = `${annotated}${askBudget ?? ''}${narrationHint ?? ''}`;
                             pushToolResult(history, tc, finalOutput, relprune, lifecycle, scheduler, runtimeContextState, outcome.status === 'success');
                             const invalidatedFiles = [...new Set([
                                     ...(outcome.changedFiles ?? []),

package/dist/agent/work-discipline.js

@@ -33,30 +33,30 @@ export function inferModelFamily(model) {
  * 4 阶段核心纪律(英文)。4 个 model family 共用此文本,只在首句与标题
  * 标签上做轻量变体。保持短小，详细的完成检查由动态 checklist 按需注入。
  */
-const CORE_SECTION = `## Working discipline — coding tasks (Build-and-Self-Verify)
-
-Treat "verification" as a first-class part of the task, not an afterthought. Use the smallest evidence-driven loop below.
-
-### Phase 1 — Plan & Discover
-- Open with a one-sentence restatement of your interpretation of the request; if a materially different reading exists, name it briefly before proceeding. This catches misunderstanding before any work is wasted.
-- State the goal and a concrete acceptance signal, then inspect the relevant code before changing it.
-- Ask only when an unresolved choice is high-impact or user-owned; otherwise follow repository evidence and proceed.
-
-### Phase 2 — Build
-- Make the smallest coherent change; avoid unrelated refactors.
-- Add or update a focused test when behavior changes and the project has an applicable test suite.
-- Re-read only when a dependent edit needs fresh exact content or state may be stale.
-
-### Phase 3 — Verify
-- Run the smallest executable check that proves the requested behavior, then read its complete result.
-- Compare evidence with the user's request, not merely with the diff.
-
-### Phase 4 — Fix
-- Diagnose the root cause, make a focused correction, and rerun the relevant check.
-- After two identical failures, change the approach instead of repeating the same call.
-
-**Hard rule (non-negotiable):** "I read the code and it looks right" is not a completion signal. Report the verification performed, or state clearly why it could not be run.
-
+const CORE_SECTION = `## Working discipline — coding tasks (Build-and-Self-Verify)
+
+Treat "verification" as a first-class part of the task, not an afterthought. Use the smallest evidence-driven loop below.
+
+### Phase 1 — Plan & Discover
+- Restate the request in one sentence ONLY when it admits two or more materially different readings; name the reading you picked and move on. An unambiguous request gets no restatement — start working. This is the single exception to staying silent during tool-calling turns.
+- Settle on the goal and a concrete acceptance signal before inspecting the relevant code; keep them internal unless the user has to weigh in.
+- Ask only when an unresolved choice is high-impact or user-owned; otherwise follow repository evidence and proceed.
+
+### Phase 2 — Build
+- Make the smallest coherent change; avoid unrelated refactors.
+- Add or update a focused test when behavior changes and the project has an applicable test suite.
+- Re-read only when a dependent edit needs fresh exact content or state may be stale.
+
+### Phase 3 — Verify
+- Run the smallest executable check that proves the requested behavior, then read its complete result.
+- Compare evidence with the user's request, not merely with the diff.
+
+### Phase 4 — Fix
+- Diagnose the root cause, make a focused correction, and rerun the relevant check.
+- After two identical failures, change the approach instead of repeating the same call.
+
+**Hard rule (non-negotiable):** "I read the code and it looks right" is not a completion signal. Report the verification performed, or state clearly why it could not be run.
+
 **Hard rule (non-negotiable):** Never invent file paths, APIs, config keys, flags, or behavior. Every claim about the codebase must trace to tool output in this conversation; explicitly label anything you have not verified as an assumption.`;
 /**
  * 把核心段适配到指定 model family:只替换首行(语序 / 强动词),段标题
@@ -68,16 +68,16 @@ function adapt(_model, opener) {
     return CORE_SECTION.replace('Treat "verification" as a first-class part of the task, not an afterthought.', opener);
 }
 /** ASK-01: only user-owned, high-impact choices should interrupt autonomous execution. */
-const ASK_WHITELIST_SECTION = `## When to ask instead of guess
-
-Call \`ask_human\` before coding only when repository evidence cannot resolve a user-owned, high-impact choice:
-1. irreversible deletion, migration, security, permission, or external side effect;
-2. public API compatibility (keep, deprecate, rename, or remove);
-3. multiple reasonable options that materially change product behavior;
-4. the request itself admits two or more materially different readings that lead to different deliverables (do not silently pick one and guess).
-
-For naming, implementation detail, and verification commands, follow repository precedent and choose the safest reversible default. Disclose any consequential assumption.
-
+const ASK_WHITELIST_SECTION = `## When to ask instead of guess
+
+Call \`ask_human\` before coding only when repository evidence cannot resolve a user-owned, high-impact choice:
+1. irreversible deletion, migration, security, permission, or external side effect;
+2. public API compatibility (keep, deprecate, rename, or remove);
+3. multiple reasonable options that materially change product behavior;
+4. the request itself admits two or more materially different readings that lead to different deliverables (do not silently pick one and guess).
+
+For naming, implementation detail, and verification commands, follow repository precedent and choose the safest reversible default. Disclose any consequential assumption.
+
 Budget: at most 2 \`ask_human\` calls per turn. Beyond that, use the safest reversible default and disclose it in the final reply.`;
 /**
  * 拼出纪律段 + ASK-01 卡点白名单。返回完整段(两段用 \`\\n\\n\` 隔开);

package/dist/config/index.js

@@ -200,6 +200,7 @@ ${buildWorkDisciplineSection(inferModelFamily(config.model))}
 ${buildCodegraphSection()}
 
 ## Tool use
+- During tool-calling turns, stay silent unless something important enough must reach the user — otherwise just call the tool and let it run.
 - Go directly to a known path or symbol; use discovery tools only when the location is unknown.
 - Edit against a FRESH read: before any edit_file/write_file, call read_file on the exact path and copy both its latest hash and the exact target text. Never reconstruct old_string from a grep/summary/diff — those lose whitespace and indentation and cause edit failures.
 - A read_file hash from before a compaction, session resume, edit conflict, or external change is STALE and will be rejected — re-read rather than reuse an old hash.

package/dist/llm/index.js

@@ -141,8 +141,11 @@ function logRetry(attempt, err, waitMs) {
     const e = err;
     const tag = e.status ? `HTTP ${e.status}` : e.name || 'Error';
     const msg = e.message ?? '未知错误';
-    // stderr 而非 stdout —— 不污染流式正文;行首换行防止黏在上一行尾巴。
-    process.stderr.write(`\n[llm] 第 ${attempt}/${RETRY_MAX_ATTEMPTS} 次失败(${tag}: ${msg}),${(waitMs / 1000).toFixed(1)}s 后重试…\n`);
+    // 走 console.error 而非 process.stderr.write:TUI active 时 layout.installConsoleGuard
+    // 已把 console.* 劫持到 contentWrite(内容区),错误会落在 agent 输出区,不污染输入框;
+    // 非 TTY(管道 / CI / 启动早期 TUI 未启)降级走原生 console.error → stderr,行为与改造前一致。
+    // 不写前导 \n —— contentWrite 由续写位管位置,前置换行会留空行;结尾 \n 由劫持逻辑补。
+    console.error(`[llm] 第 ${attempt}/${RETRY_MAX_ATTEMPTS} 次失败(${tag}: ${msg}),${(waitMs / 1000).toFixed(1)}s 后重试…`);
 }
 let createImplOverride = null;
 /** 仅供单测用:覆盖 chat() 内部实际调用的 create 桩。生产代码不要碰。 */

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "mocode-ai",
-  "version": "1.1.6",
+  "version": "1.1.7",
   "description": "终端编码 agent:LLM + tool-call 循环 + 流式输出(含思考)+ 16 个工具,接任意 OpenAI 兼容后端。",
   "type": "module",
   "bin": {