- build-your-own-agent: Split combined quote into 2 independent blockquotes
- build-your-own-agent + mcp-integration: Add missing "our" in namespacing quote (2 places)
- mcp-integration: Add Qwen Code (double underscore) to naming table - fork chose
  Claude Code convention over Gemini CLI, a notable design decision
- mcp-integration: Fix "原文:" prefix → bare quote format (R6 issue #5 residual)
- mcp-integration: Fix pre-existing error in overview table and naming comparison
  table - Qwen Code uses double underscore, not single (verified: 04-tools.md L98)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

New file: docs/tools/oh-my-openagent.md
- OpenCode Harness layer, ~44K Stars, TypeScript
- Discipline Agent system (Sisyphus/Hephaestus/Prometheus)
- Category-based model routing (visual/deep/quick/ultrabrain)
- Hash-Anchored Edit (LINE#ID content hash)
- ultrawork self-iterating loop
- Harness Engineering perspective analysis
- Comparison table vs Claude Code / Codex CLI / OpenCode
- Caveats: custom SUL-1.0 license, dependent on OpenCode

Cross-references:
- architecture-deep-dive: Add as Harness Engineering practice case
- model-routing: Add Harness-layer routing trend (#5)
- tools/README: Add to index

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

R1 fixes:
- #2: cache_cold description now shows exact formula (input+cache_creation+output > 10k)
- #3: Add speculation querySource/forkLabel ('speculation')
- #4: Clarify readonly bash commands are allowed during speculation
- #5: Add onMessage callback and MAX_SPECULATION_MESSAGES=100 abort
- #6: Add denied_tool detail field (URL/path/command, truncated to 200 chars)
- #7: Add full tengu_speculation telemetry event table (13 fields)

R2 fixes:
- R2-1: Add speculation feedback message ([ANT-ONLY] ... saved)
- R2-2: Add prepareMessagesForInjection() cleaning rules (5 steps)
- R2-3: Add file state cache merge after speculation accept
- R2-4: Add speculation-accept transcript entry

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* Add Claude Code Prompt Suggestions deep-dive as standalone doc (+290 lines)

New file docs/tools/claude-code/08-prompt-suggestions.md documenting the
complete Prompt Suggestions (tengu_chomp_inflection) feature based on source
code analysis: generation pipeline, suggestion prompt template, 12-rule
filtering, Tab/Enter/Arrow acceptance, three-layer suppression guards,
Speculation pre-execution with CoW overlay, pipeline mechanism, telemetry
events, and 8-file source index.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* Rename to 10-prompt-suggestions.md (avoid numbering conflict with 08/09)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* Add 10-prompt-suggestions to README.md index

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* Address review feedback: add source disclaimer, fix --bare vs -p, fix PR ref

- Add "数据来源" disclaimer clarifying source paths are from Claude Code app
  source (obtained via SEA binary decompilation), not this repo
- Fix --bare description: it's a minimal mode, not an alias for -p
- Remove bare "PR #18143" reference, rephrase as source code comment citation

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* Address review: clarify env var three-state logic and timestamp default values

- Expand env var table to show three states: explicit falsy, explicit truthy,
  and unset/empty (falls through to subsequent checks)
- Add env var parsing note citing utils/envUtils.ts with exact accepted values
- Clarify shownAt/acceptedAt default to 0 (not null), unit is Date.now() ms,
  and acceptance check uses acceptedAt > shownAt

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* Address qwen3.6-plus-preview R1+R2 review: 10 fixes

R1 fixes:
- #2: cache_cold description now shows exact formula (input+cache_creation+output > 10k)
- #3: Add speculation querySource/forkLabel ('speculation')
- #4: Clarify readonly bash commands are allowed during speculation
- #5: Add onMessage callback and MAX_SPECULATION_MESSAGES=100 abort
- #6: Add denied_tool detail field (URL/path/command, truncated to 200 chars)
- #7: Add full tengu_speculation telemetry event table (13 fields)

R2 fixes:
- R2-1: Add speculation feedback message ([ANT-ONLY] ... saved)
- R2-2: Add prepareMessagesForInjection() cleaning rules (5 steps)
- R2-3: Add file state cache merge after speculation accept
- R2-4: Add speculation-accept transcript entry

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* Address qwen3.6-plus-preview R3 review: 7 fixes

- R3-1: tools_executed counts tool_result && !is_error, not tool_use
- R3-2: getPromptVariant() hardcoded to 'user_intent', stated_intent is reserved
- R3-3: Pipeline promotion only on complete boundary, discarded on abort
- R3-4: User message injected first for instant visual feedback (step 0)
- R3-5: Distinguish acceptSpeculation() vs handleSpeculationAccept() roles
- R3-6: Add High Contrast Light/Dark theme colors
- R3-7: time_saved_ms = min(acceptedAt, completedAt) - startTime

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

- #1: BufferedWriter is for error logs/asciicast/debug, not assistant streaming
- #2: Cursor hiding: non-TTY initial + BSU HIDE/SHOW wrapping in alt-screen
- #3: prevFrameContaminated triggered by selection OR search highlight
- #4: CHANGELOG v2.1.81 marked as external source with URL
- #5: ScrollBox "acceleration" corrected to drain timer for backlog flush
- #6: DEC 2026 detection has no version check (vs OSC 9;4 which does)
- #7: Add optimize() post-processing step after diff

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* Add Claude Code terminal rendering deep-dive (11-terminal-rendering.md, +342 lines)

Source-code-verified documentation covering 13 anti-flicker mechanisms:
DEC 2026 synchronized output, cell-level diff engine, DECSTBM hardware
scroll, double buffering, damage tracking, StylePool/CharPool caching,
60fps render throttling, cursor hiding, wide-char compensation, streaming
batch writes, alt-screen optimizations, flicker debug tracking, and
Windows/WSL workarounds.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* Address qwen3.6-plus-preview R1 review: 7 fixes

- #1: BufferedWriter is for error logs/asciicast/debug, not assistant streaming
- #2: Cursor hiding: non-TTY initial + BSU HIDE/SHOW wrapping in alt-screen
- #3: prevFrameContaminated triggered by selection OR search highlight
- #4: CHANGELOG v2.1.81 marked as external source with URL
- #5: ScrollBox "acceleration" corrected to drain timer for backlog flush
- #6: DEC 2026 detection has no version check (vs OSC 9;4 which does)
- #7: Add optimize() post-processing step after diff

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* Address Copilot + qwen R2 review: 7 fixes

Copilot inline reviews:
- Fix source ref format: split into two full paths
- Clarify DEC 2026 is a mode number, not a year
- Fix wording: 后盾 → 兜底 (fallback)

qwen R2 fixes:
- R2-1: VTE does have version check (>= 6800), clarify "except VTE"
- R2-2: Add ink/optimizer.ts (93 LOC) to source file index
- R2-3/R2-4: Low priority, deferred

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

- Chrome Extension item (#5): add daemon browser as alternative approach
  (gstack's /browse: long-lived Chromium + CDP, ~100ms/command)
- /review improvements: add gstack's structured review methodology
  (SQL safety, LLM trust boundary, conditional side effects)
  and proactive trigger + /qa + /ship pipeline patterns
- Update /review report reference to 5-way comparison (+ gstack)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Replace generic one-liners with specific user scenarios and impacts:
- #1: npm postinstall reading ~/.ssh/ and ~/.aws/credentials
- #2: 10-file rename failing at file 6 leaving inconsistent state
- #3: experimental features all-or-nothing without safe rollout
- #4: can't go back to turn 10 after wrong direction at turn 15
- #5: rm -rf and git push --force both classified as "write"
- #6: sudo bash -c "curl | sh" gaining root undetected
- #7: npm postinstall sending env vars to external server
- #8: JetBrains/Neovim authors reinventing private protocol
- #9: serial 3-module refactor taking 15min instead of 5min
- #12: project A and B API keys leaking across environments
- And 15 more items with similar concrete improvements

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

User questioned necessity of p2-core item-20 ConfigTool. Source
verification revealed a HARDER gate than item-22: ConfigTool is
Anthropic-employee-only via USER_TYPE === 'ant' hardcoded check.

Evidence from /root/git/claude-code-leaked/tools.ts:214-215:

  ...(process.env.USER_TYPE === 'ant' ? [ConfigTool] : []),
  ...(process.env.USER_TYPE === 'ant' ? [TungstenTool] : []),

External Claude Code users NEVER see ConfigTool. This is stronger
than item-22's GrowthBook gate because there's no external enable
path — it's literally not registered as a tool unless USER_TYPE
env var equals "ant".

Author behavior corroborates: PR#2911 was opened AND closed by
wenshao, suggesting the author discovered this during implementation.

Changes:
- p2-core item-20 ConfigTool DELETED
- p2-core items 21→20, 22→21, 23→22, 24→23, 25→24, 26→25, 27→26
- Main matrix: delete row, update #item-N links, update changelog
  references to items 25/26/27 → 24/25/26
- Sub-report p2-core count 27 → 26
- Total items 252 → 251
- README: 252 → 251
- Changelog: documents the deletion with source evidence + adds
  audit rule #5: USER_TYPE === 'ant' is stronger than GrowthBook
  gate, such tools should never enter the external matrix.

Verified: 14+9+27+26+22+20+34+41+16+9+33 = 251 matches matrix count.

Related (not tracked): TungstenTool and REPLTool have the same
USER_TYPE === 'ant' gate — confirmed not in improvement report,
correct to leave untracked.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

…04 详情

扫描窗口：2026-04-26 11:40 UTC（上次扫描 1cf3196）→ 2026-04-27 02:30 UTC。

## 🟢 OPEN→MERGED 转换（4 项 + 2 项 carryover）

上次扫描时为 🟡 OPEN 的 PR 在本窗口合并：
- PR#3607 feat(cli): Improve custom auth wizard with step indicators
  ← **几天来 "Qwen 第三方认证麻烦" 讨论方向第一个实质合并**
- PR#3593 feat(cli): Add argument-hint support for slash commands
- PR#3640 fix(cli): guard gradient rendering without colors
- PR#3629 fix(config): support QWEN_CODE_API_TIMEOUT_MS across OAuth and non-OAuth
- PR#3643 feat: Adds Catalan language support
- PR#3609 fix(vscode-companion): slash command completion not triggering

## 🟢 本窗口新合并（1 项）

- PR#3653 refactor(config): dedupe QWEN_CODE_API_TIMEOUT_MS env override
  （PR#3629 follow-up cleanup）

## 🟡 新 OPEN（6 项）

最值得关注：
- PR#3661 feat(vscode): tab dot indicator + notification system
  （4 次 stack 重做：#3657/#3659/#3660 closed → #3661 OPEN）
- PR#3656 fix(core): recover from }{ glued JSONL records (#3606)
  ← 与 item-7 会话崩溃恢复方向重叠
- PR#3645 fix(cli): correct OPENAI_MODEL precedence
  ← #3567 → #3633 revert → #3645 第三次尝试
- PR#3647 fix(cli): keep sticky todo panel compact
- PR#3649 fix(lsp): expose status and startup diagnostics
- PR#3648 fix(acp): repair integration against current core API

## 📝 item-28 详细更新（PR#3604 OPEN）

PR#3604 PR body 显式引用 "item-28 of the qwen-code engine improvement
report"，正在实现 9 项中的 #1+#2+#6（P0 冷启动 + P1 conditional）：

- 子项 #1 外层 Promise.all — refreshCache 4 层串行 → 并行
- 子项 #2 内层 Promise.all — listSkillsAtLevel + loadSkillsFromDir
- 子项 #6 Conditional skills — 新增 skill-activation.ts (118 行
  picomatch registry，project-root scoped) + coreToolScheduler.ts
  文件路径触发 hook + <system-reminder> 通知

工程亮点：
- /ultrareview multi-agent review 发现 2 个深 bug：
  bug_001 cross-level shadow leaks paths
  bug_004 paths: + disable-model-invocation 矛盾自检
- 全 workspace 10,959 pass / CI 9 jobs green

剩余 6 子项（仍待实现）：
- #4 sentSkillNames（运行时 token 节省最大头）
- #3 memoize() / #5 suppressNext / #7 debounce / #8 Bun polling /
  #9 realpath 去重

## README 同步

已合并 PR 计数：94 → 101。

…oyment + packaging contract 钉死

来源: chiga0 在 Issue #3803 留长篇 design-level critique (GPT-5 Codex 协助生成)
"Mode B 是对的, 但 deployment + packaging 契约必须先显式化, 否则同一套
 code path 要同时服务 local CLI / remote devbox / enterprise cloud 三个场景,
 边界会糊"

6 项契约:

1. Deployment forms 3 类:
   - Local single-machine (主装, loopback 自动起 daemon)
   - Cloud/devbox remote-runtime (workspace 与 runtime 必须 colocate)
   - ❌ Local workspace + remote daemon (不推荐, daemon 看不到 local 资源)

   核心 invariant: daemon host = runtime host
   File access / shell tools / LSP / provider auth / MCP servers / skills
   全部在 daemon environment 求值

2. Server / client / adapter 3 层 package boundary:
   @qwen-code/daemon-server (qwen serve / HTTP / EventBus / ACP bridge / FS / sandbox)
   @qwen-code/daemon-client (DaemonClient / DaemonSessionClient / typed event /
                            reducer / reconnect / heartbeat / capability negotiation)
   @qwen-code/daemon-adapters-* (tui / channel / ide-web / output sinks)

   3 条 dependency direction 规则 (即使不物理拆分也 enforce):
   - server code 不可依赖 TUI / IDE / channel adapter
   - adapter 只可依赖 SDK / protocol / reducer surface
   - shared reducer + typed protocol helper 必须住 client/protocol 层
     不能在 packages/cli/src/serve/

3. Local auto-daemon UX (新设计草图):
   qwen → discover daemon → if absent auto-start qwen serve on loopback
        → attach TUI → lifecycle policy on TUI exit
   Wave 6 release hardening 前补 (PR 28 npm alpha 之前)

4. Sandbox runner model:
   当前 Stage 1: qwen serve → qwen --acp child 全在 daemon host
   期望未来: client → daemon control plane → runtime worker / sandbox runner
   daemon 保 control plane, sandbox 独立 fail+restart
   sandbox 挂 ≠ daemon 挂
   MCP / skills 必须在 runtime worker 跑, 不在 client
   client capability reverse RPC 严格 scoped 到 editor/clipboard/browser/notification/file_picker
   不能 silently 成为 MCP/skill 执行 fallback

5. Client default migration gate 3-condition checklist:
   - control-plane parity (9 项 dialog 全 wire 化)
   - reducer / adapter quality (无 raw event spam)
   - auto-daemon lifecycle (上面第 3 点)
   当前 PR#4266 / PR#4267 draft 合规 (behind-flag experiment)

6. 文档更新建议: Deployment forms + Package boundary + Auto-daemon UX
   + Runtime locality + Sandbox runner model + Client migration gate

文档同步:
- §01 §三 双部署模式: 加 §三·一 Deployment forms 3-form 表
  + 核心不变式 daemon host = runtime host
- §04 §五 Runtime locality: 加 2026-05-18 升级 callout, 互链 §01 §三·一 + §06 §三·二
- §06 §三·二: 新 section "Deployment + package contract (chiga0 #3803 comment)"
  完整 6 项 + 当前 codebase 对照表

当前对照:
- 1 Deployment forms: ✅ 已加 §三·一 3-form 表
- 2 Package boundary: ⚠️ daemon-server/daemon-client/daemon-adapters 未官方命名
- 3 Auto-daemon UX: ❌ Wave 6 前补
- 4 Runtime locality: ✅ §04 §五 + 已加 callout 互链
- 5 Sandbox runner model: Wave 5 PR 24 后或 Stage 2 独立
- 6 Client migration gate: ✅ 已加 §三·二 #5 3-condition checklist

之前立 zero-cost abstraction 原则后，3 处旧措辞未同步：

§04 §六 Deployment shape matrix line 309:
- "1. Local - Local" 之前列 "现有用户默认迁移目标" + 含 TUI
- 修: 拆为 1 (本地单用户 TUI in-process) + 1b (multi-client 协作 daemon)
- 标 🌟 永久 default UX

§06 §三·二 Shape 表 line 256:
- "Local - Local 本机 daemon/runtime/workspace" 之前是 "qwen 默认迁移目标"
- 修: 拆为本地单用户 TUI (不存在 daemon) + multi-client 协作 (loopback daemon)

§06 §三·二 #3 Local auto-daemon UX 段:
- 之前是 "local TUI 默认走 daemon 不能变成..."
- 改为 "仅 multi-client 协作场景, 不作 local TUI default"
- 加 callout 引 #3803 reply 4483031818
- 提议 Mode A 可能更合适
- 标 "Wave 6 前不入主线"

§06 §三·二 #5 Client default migration gate:
- 之前 "TUI / channel / IDE default 切换必须等..."
- 改为 ⚠️ TUI default 永远不切换, gate 仅适用 channel/web/IDE
- 区分 PR#4266 (TUI exp = opt-in advanced 永远 behind flag)
  vs PR#4267 (IDE exp = 合规 behind-flag for default migration)
- 引 #4175 reply 4483033542 (Wave 5 PR 26 scope 收紧)

跨章节一致性现在符合:
- §02 §7 🌟 设计原则段 (本地 TUI in-process)
- §04 §一 Mode B 拓扑核心特征 (重写 callout)
- §04 §二 TUI 形态 4 种 (🌟 #1 优先级标注)
- §04 §六 Deployment shape matrix (本次修)
- §06 §三·二 (本次修 3 处)

总账数 (35 MERGED + 5 OPEN + 3 CLOSED, Wave plan 22.5/31 ≈ 73%) 全章节一致 ✅

剩余非冲突项 (未在本次修):
- §03 http-api 内容停留较早 (没有 Wave 1-5 PR refs), 可后续 refresh
- §05 permission-auth 同上, 可后续 refresh