fix(web): converge session search boundaries (round 9)

2026-07-27 14:46:08 +08:00
parent ba2925c704
commit 0aa7f8c5cf
29 changed files with 629 additions and 157 deletions
@@ -1,6 +1,6 @@
 # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
-#   pnpm run verify-translation-pairing --write
-README.md: 80228a180faba0c556ff720e999b29b5bb1635b6
-README.zh.md: f4b857886bfafa891ceb1bd6b79b27e1fb725819
+#   pnpm run verify-translation-pairing --write packages/client/connection/README.md
+README.md: e40f360cdb5cb7d624fc338e85bc33a2cd569578
+README.zh.md: 96a77db8b881a9f6b981847d8f3926db3985531e
@@ -6,7 +6,7 @@ Wire consumer layer: the client plugin's apply mounts `ctx.connection` (shared a

 ## Keyless fixture

-Any `fixture` query parameter selects the in-memory carrier. `fixture=empty` starts with no Workspace or Session; `fixturePrompt=reject` rejects prompts before acceptance; `fixtureAttach=fail` publishes a Session but rejects its Workspace attachment; `fixtureSessionCreate=drop-response` publishes and frames a Session before dropping the create response; and `fixtureFrames=workspace-first` reverses the default session-first create-frame order. Workspace creation by name/path and caller-preallocated SessionIds remain deterministic enough for assembled Web tests to reconcile list and frame arrival.
+Any `fixture` query parameter selects the in-memory carrier. `fixture=empty` starts with no Workspace or Session; `fixturePrompt=reject` rejects prompts before acceptance; `fixtureAttach=fail` publishes a Session but rejects its Workspace attachment; `fixtureSessionCreate=drop-response` publishes and frames a Session before dropping the create response; and `fixtureFrames=workspace-first` reverses the default session-first create-frame order. Workspace creation by name/path and caller-preallocated SessionIds remain deterministic enough for assembled Web tests to reconcile list and frame arrival. Fixture content search preserves the production-facing `unicode61`-style case, diacritic, and token-phrase behavior and returns a match-centered snippet of at most 120 Unicode code points.

 ## Model Experience

@@ -6,7 +6,7 @@

 ## 无密钥 fixture

-任何 `fixture` 查询参数都会选择内存载体。`fixture=empty` 启动时不含 Workspace 或 Session；`fixturePrompt=reject` 在接受前拒绝提示词；`fixtureAttach=fail` 发布 Session 但拒绝将其附加到 Workspace；`fixtureSessionCreate=drop-response` 在丢弃创建响应前发布 Session 并为其发出帧；`fixtureFrames=workspace-first` 则反转默认的 Session 优先创建帧顺序。按名称／路径创建 Workspace 以及由调用方预先分配 SessionId，均具有足够的确定性，组装后的 Web 测试可以据此协调列表与帧的到达。
+任何 `fixture` 查询参数都会选择内存载体。`fixture=empty` 启动时不含 Workspace 或 Session；`fixturePrompt=reject` 在接受前拒绝提示词；`fixtureAttach=fail` 发布 Session 但拒绝将其附加到 Workspace；`fixtureSessionCreate=drop-response` 在丢弃创建响应前发布 Session 并为其发出帧；`fixtureFrames=workspace-first` 则反转默认的 Session 优先创建帧顺序。按名称／路径创建 Workspace 以及由调用方预先分配 SessionId，均具有足够的确定性，组装后的 Web 测试可以据此协调列表与帧的到达。fixture 内容搜索会保留面向生产环境的 `unicode61` 式大小写、变音符号和 token／短语行为，并返回以匹配位置为中心、最多包含 120 个 Unicode 码点的 snippet。

 ## 模型体验

@@ -307,33 +307,95 @@ function searchEventText(event: SessionEvent): string {
  return event.data.content.flatMap(searchBlockText).map(part => part.trim()).filter(Boolean).join('\n')
 }

+interface FixtureSearchToken {
+  value: string
+  /** Inclusive code-point offset in the whitespace-normalized display text. */
+  start: number
+  /** Exclusive code-point offset in the whitespace-normalized display text. */
+  end: number
+}
+
 /**
 * Browser-safe approximation of SQLite FTS5 unicode61 token boundaries.
 * Keeping phrase matching token-based prevents the development fixture from
 * promising arbitrary within-token substring behavior that production lacks.
 */
-function searchTokens(value: string): string[] {
-  return value
-    .normalize('NFD')
-    .replace(/\p{M}+/gu, '')
-    .toLowerCase()
-    .match(/[\p{L}\p{N}\p{Co}]+/gu) ?? []
-}
-
-/** Count exact contiguous token-phrase occurrences in one fixture document. */
-function phraseMatchCount(document: readonly string[], phrase: readonly string[]): number {
-  if (phrase.length === 0 || phrase.length > document.length) return 0
-  let count = 0
-  for (let start = 0; start <= document.length - phrase.length; start++) {
-    if (phrase.every((token, offset) => document[start + offset] === token)) count++
+function searchTokenSpans(value: string): { text: string; tokens: FixtureSearchToken[] } {
+  const text = value.replace(/\s+/gu, ' ').trim()
+  const characters = Array.from(text)
+  const tokens: FixtureSearchToken[] = []
+  let start: number | undefined
+  let raw = ''
+  const flush = (end: number): void => {
+    if (start !== undefined) {
+      const folded = raw.normalize('NFD').replace(/\p{M}+/gu, '').toLowerCase()
+      if (folded !== '') tokens.push({ value: folded, start, end })
+    }
+    start = undefined
+    raw = ''
  }
-  return count
+  for (let index = 0; index < characters.length; index++) {
+    const character = characters[index] as string
+    const tokenBase = character.normalize('NFD').replace(/\p{M}+/gu, '')
+    if (tokenBase === '') {
+      if (start !== undefined) raw += character
+      continue
+    }
+    if (/^[\p{L}\p{N}\p{Co}]+$/u.test(tokenBase)) {
+      start ??= index
+      raw += character
+    } else {
+      flush(index)
+    }
+  }
+  flush(characters.length)
+  return { text, tokens }
 }

-/** One-line fixture excerpt, bounded so the sidebar remains readable. */
-function searchSnippet(value: string): string {
-  const oneLine = value.replace(/\s+/gu, ' ').trim()
-  return oneLine.length <= 120 ? oneLine : `${oneLine.slice(0, 117)}…`
+interface FixturePhraseMatch {
+  count: number
+  start: number
+  end: number
+}
+
+/** Count exact contiguous token-phrase occurrences and retain the first display span. */
+function phraseMatch(document: readonly FixtureSearchToken[], phrase: readonly string[]): FixturePhraseMatch {
+  if (phrase.length === 0 || phrase.length > document.length) return { count: 0, start: 0, end: 0 }
+  let count = 0
+  let firstStart = 0
+  let firstEnd = 0
+  for (let start = 0; start <= document.length - phrase.length; start++) {
+    if (!phrase.every((token, offset) => document[start + offset]?.value === token)) continue
+    count++
+    if (count === 1) {
+      firstStart = document[start]?.start ?? 0
+      firstEnd = document[start + phrase.length - 1]?.end ?? firstStart
+    }
+  }
+  return { count, start: firstStart, end: firstEnd }
+}
+
+/** Match-centered fixture excerpt, bounded by Unicode code points for the sidebar. */
+function searchSnippet(value: string, matchStart: number, matchEnd: number): string {
+  const characters = Array.from(value)
+  if (characters.length <= 120) return value
+  const boundedStart = Math.min(Math.max(0, matchStart), characters.length - 1)
+  const boundedEnd = Math.min(
+    characters.length,
+    Math.max(boundedStart + 1, matchEnd),
+  )
+  const center = Math.floor((boundedStart + boundedEnd) / 2)
+  let start = Math.min(
+    characters.length - 118,
+    Math.max(0, center - Math.floor(118 / 2)),
+  )
+  let end = start + 118
+  if (start === 0) {
+    end = 119
+  } else if (end === characters.length) {
+    start = characters.length - 119
+  }
+  return `${start > 0 ? '…' : ''}${characters.slice(start, end).join('')}${end < characters.length ? '…' : ''}`
 }

 interface FixtureSearchCandidate {
@@ -342,6 +404,8 @@ interface FixtureSearchCandidate {
  time: number
  text: string
  matchCount: number
+  matchStart: number
+  matchEnd: number
  documentLength: number
 }

@@ -628,21 +692,24 @@ export function createFixtureApi(options: FixtureOptions = {}): ApiProxy {
            details: {},
          })
        }
-        const query = searchTokens(request.payload.query)
+        const query = searchTokenSpans(request.payload.query).tokens.map(token => token.value)
        const matches = sessions.flatMap((summary) => {
          const log = logs.get(summary.sessionId) ?? []
          const current = new Set(foldSurface(log).nodes)
          const best = log.flatMap((event): FixtureSearchCandidate[] => {
            if (!current.has(event.seq)) return []
            const eventText = searchEventText(event)
-            const matchCount = phraseMatchCount(searchTokens(eventText), query)
-            if (matchCount === 0) return []
+            const document = searchTokenSpans(eventText)
+            const match = phraseMatch(document.tokens, query)
+            if (match.count === 0) return []
            return [{
              sessionId: summary.sessionId,
              seq: event.seq,
              time: event.time,
-              text: eventText,
-              matchCount,
+              text: document.text,
+              matchCount: match.count,
+              matchStart: match.start,
+              matchEnd: match.end,
              documentLength: Array.from(eventText).length,
            }]
          }).sort(compareSearchCandidates)[0]
@@ -651,7 +718,7 @@ export function createFixtureApi(options: FixtureOptions = {}): ApiProxy {
        return ok(request, {
          items: matches.slice(0, 20).map(match => ({
            sessionId: match.sessionId,
-            snippet: searchSnippet(match.text),
+            snippet: searchSnippet(match.text, match.matchStart, match.matchEnd),
          })),
          hasMore: matches.length > 20,
        })
@@ -62,6 +62,23 @@ describe('createFixtureApi', () => {
    if (!phrase.result.ok) throw new Error('search failed')
    expect(phrase.result.value.items[0]?.snippet).toContain('fixture 历史消息')

+    timing().appendUser(
+      'fx-alpha',
+      `${'leading context '.repeat(20)}late café token${' trailing context'.repeat(20)}`,
+    )
+    const late = await api.sessions.search(req({ query: 'LATE CAFE TOKEN' }), signal)
+    if (!late.result.ok) throw new Error('late search failed')
+    const lateSnippet = late.result.value.items[0]?.snippet ?? ''
+    expect(lateSnippet).toContain('late café token')
+    expect(lateSnippet.startsWith('…')).toBe(true)
+    expect(lateSnippet.endsWith('…')).toBe(true)
+    expect(Array.from(lateSnippet).length).toBeLessThanOrEqual(120)
+
+    timing().appendUser('fx-alpha', 'Greek final sigma: ος')
+    const finalSigma = await api.sessions.search(req({ query: 'ΟΣ' }), signal)
+    if (!finalSigma.result.ok) throw new Error('final sigma search failed')
+    expect(finalSigma.result.value.items[0]?.snippet).toContain('ος')
+
    const substring = await api.sessions.search(req({ query: 'ixtur' }), signal)
    expect(substring.result).toEqual({
      ok: true,