fix(dashboard): normalize Unicode correction keywords

CHANGELOG.md

@@ -13,6 +13,7 @@ All notable changes to this project will be documented in this file. See [standa
 
 ### 🐛 Bug Fixes
 
+- Course-correction matching normalizes prompts and keywords to Unicode NFC, so composed and decomposed accents match. Stored prompt summaries and the 60-second correction window are unchanged. Fixes [#573](https://github.com/Tencent/teamai-cli/issues/573).
 - Course-correction detection matches keywords in space-separated scripts as whole words, so Spanish "segundo" no longer counts as `undo` (for [#564](https://github.com/Tencent/teamai-cli/issues/564)).
 - MCP `requires` is resolved from `PATH` (including Windows `PATHEXT`), so `teamai mcp inject` no longer skips servers such as `uvx` on Windows ([#540](https://github.com/Tencent/teamai-cli/pull/540), for [#539](https://github.com/Tencent/teamai-cli/issues/539)).
 - The GitHub and CNB providers resolve their CLI to a launchable absolute path and start it through cross-spawn, so on Windows they no longer answer "installed" while every call fails silently ([#520](https://github.com/Tencent/teamai-cli/pull/520)).

docs/usage-guide.md

@@ -1254,6 +1254,8 @@ sharing:
 
 The prompt is checked when the `UserPromptSubmit` hook captures it, so a change to the team keywords applies to new prompts after the next `teamai pull`; sessions recorded earlier are not re-evaluated.
 
+Matching normalizes both the prompt and keywords to Unicode NFC. For example, `réessaye` matches `re\u0301essaye`, where `\u0301` is a combining acute accent. Accents remain significant, so `reessaye` does not match. Normalization applies only to matching and does not change the stored prompt summary or the 60-second correction window.
+
 Intervention data is automatically aggregated and reported to the team's `stats/<user>.yaml` during `teamai pull`, and shown in the "Session Autonomy" leaderboard of `teamai digest`, with team averages and per-person intervention rate rankings — useful for verifying whether a skill/rule reduces intervention rates after rollout. Tools without a transcript (e.g. Cursor) degrade gracefully, tracking only `correction`.
 
 #### Conversation Volume & Token Usage

docs/usage-guide.zh-CN.md

@@ -1221,6 +1221,8 @@ sharing:
 
 匹配在 `UserPromptSubmit` hook 捕获 prompt 时完成，因此修改团队纠偏词后，下一次 `teamai pull` 之后的新 prompt 才会生效；之前记录的会话不会重新评估。
 
+匹配时，prompt 和纠偏词都会转换为 Unicode NFC 形式。例如，`réessaye` 可以匹配 `re\u0301essaye`，其中 `\u0301` 是组合尖音符。重音符号仍有区别，因此 `reessaye` 不匹配。规范化仅用于匹配，不会改变已存储的 prompt 摘要或 60 秒的纠偏时间窗口。
+
 干预数据会随 `teamai pull` 自动聚合上报到团队 `stats/<user>.yaml`，并在 `teamai digest` 的「会话自主性」榜单中给出团队均值与人均干预率排行，可用于验证某个 skill / rule 上线后干预率是否下降。无 transcript 的工具（如 Cursor）会优雅降级，只统计 `correction`。
 
 #### 对话量与 Token 用量

src/__tests__/dashboard-collector.test.ts

@@ -163,6 +163,37 @@ describe('parseHookEvent', () => {
     }
   });
 
+  it.each([
+    ['NFC keyword and NFD prompt', 'r\u00e9essaye', 're\u0301essaye'],
+    ['NFD keyword and NFC prompt', 're\u0301essaye', 'r\u00e9essaye'],
+    ['NFD keyword and uppercase prompt', 're\u0301essaye', 'R\u00c9ESSAYE!'],
+    ['NFD prompt past the summary limit', 'r\u00e9essaye', `${'x '.repeat(150)}re\u0301essaye`],
+  ])('matches canonically equivalent text: %s', async (_label, keyword, prompt) => {
+    const event = await parseHookEvent(
+      JSON.stringify({ hook_event_name: 'UserPromptSubmit', session_id: 's', prompt }),
+      'claude',
+      { correctionKeywords: [keyword] },
+    );
+    expect(event?.correction).toBe(true);
+    expect(event?.promptSummary).toBe(prompt.slice(0, 200));
+  });
+
+  it.each([
+    ['missing accent', 'reessaye'],
+    ['different accent', 're\u0300essaye'],
+    ['letter prefix', 'pre\u0301essaye'],
+    ['letter suffix', 're\u0301essayez'],
+    ['underscore prefix', 'test_re\u0301essaye'],
+    ['underscore suffix', 're\u0301essaye_it'],
+  ])('does not match a team keyword with a %s', async (_label, prompt) => {
+    const event = await parseHookEvent(
+      JSON.stringify({ hook_event_name: 'UserPromptSubmit', session_id: 's', prompt }),
+      'claude',
+      { correctionKeywords: ['r\u00e9essaye'] },
+    );
+    expect(event?.correction).toBe(false);
+  });
+
   it('checks the full prompt, not only the 200-char summary', async () => {
     const prompt = `${'x '.repeat(150)}wrong`;
     const raw = JSON.stringify({ hook_event_name: 'UserPromptSubmit', session_id: 's', prompt });
@@ -734,6 +765,26 @@ describe('parseHookEvent interventions', () => {
 describe('rebuildSessions interventions', () => {
   const now = new Date().toISOString();
 
+  it.each([
+    ['NFC keyword and NFD prompt', 'r\u00e9essaye', 're\u0301essaye'],
+    ['NFD keyword and NFC prompt', 're\u0301essaye', 'r\u00e9essaye'],
+  ])('counts a Unicode correction within the time window: %s', async (_label, keyword, prompt) => {
+    const event = await parseHookEvent(
+      JSON.stringify({ hook_event_name: 'UserPromptSubmit', session_id: 's', prompt }),
+      'claude',
+      { correctionKeywords: [keyword] },
+    );
+    if (!event) throw new Error('Expected a prompt-submit event');
+
+    for (const [gap, expected] of [[0, 1], [60_000, 1], [60_001, 0]]) {
+      const sessions = rebuildSessions([
+        { type: 'stop', timestamp: now, sessionId: 's', tool: 'claude' },
+        { ...event, timestamp: new Date(new Date(now).getTime() + gap).toISOString() },
+      ]);
+      expect(sessions[0]?.interventions.correction, `gap ${gap}`).toBe(expected);
+    }
+  });
+
   it('defaults to zero interventions', () => {
     const sessions = rebuildSessions([
       { type: 'session_start', timestamp: now, sessionId: 's1', tool: 'claude', cwd: '/p' },
@@ -742,6 +793,14 @@ describe('rebuildSessions interventions', () => {
     expect(sessions[0].interventionCount).toBe(0);
   });
 
+  it('normalizes built-in keywords when a legacy event has no correction flag', () => {
+    const sessions = rebuildSessions([
+      { type: 'stop', timestamp: now, sessionId: 's', tool: 'claude' },
+      { type: 'prompt_submit', timestamp: now, sessionId: 's', tool: 'claude', promptSummary: '\u3061\u304b\u3099\u3046' },
+    ]);
+    expect(sessions[0]?.interventions.correction).toBe(1);
+  });
+
   it('takes interrupt/toolReject from the latest stop snapshot (idempotent)', () => {
     const sessions = rebuildSessions([
       { type: 'session_start', timestamp: now, sessionId: 's1', tool: 'claude', cwd: '/p' },

src/dashboard-collector.ts

@@ -824,7 +824,7 @@ function wordBoundaryPattern(keyword: string): RegExp {
 
 /** True when `lower` contains `keyword`, whole-word for spaced scripts, substring otherwise. */
 function containsKeyword(lower: string, keyword: string): boolean {
-  const k = keyword.trim().toLowerCase();
+  const k = keyword.trim().normalize('NFC').toLowerCase();
   if (!k) return false;
   if (UNSPACED_SCRIPT_RE.test(k)) return lower.includes(k);
   return wordBoundaryPattern(k).test(lower);
@@ -836,7 +836,7 @@ function containsKeyword(lower: string, keyword: string): boolean {
  */
 function isCorrectionPrompt(text?: string, extraKeywords: readonly string[] = []): boolean {
   if (!text) return false;
-  const lower = text.toLowerCase();
+  const lower = text.normalize('NFC').toLowerCase();
   return [...CORRECTION_KEYWORDS, ...extraKeywords].some((k) => containsKeyword(lower, k));
 }