Update 4 deep-dives with latest release notes (2026-03-28)#4
Conversation
Sources: Claude Code v2.1.86, Gemini CLI v0.35.3, Codex CLI v0.117.0, Copilot CLI v1.0.12, Qwen Code v0.13.1 #34 Terminal UI: - Gemini CLI v0.35: customizable keyboard shortcuts + Vim enhancements (X, ~, r, f/F/t/T motions, yank/paste support) #29 Sandbox Security: - Gemini CLI v0.35: unified SandboxManager with Linux-native bubblewrap + seccomp isolation (150 changes, 2 security fixes) #31 Hook/Plugin: - Codex CLI v0.117: plugins first-class (startup sync, /plugins browse, install/remove with auth handling) - Copilot CLI v1.0.12: hook template variables ({{project_dir}}, {{plugin_data_dir}}), CLAUDE_PROJECT_DIR/CLAUDE_PLUGIN_DATA env vars - Copilot: /session rename auto-generates name, /yolo persists after /clear #30 Multi-Agent: - Codex CLI v0.117: multi-agent v2 with path-based addresses (/root/agent_a), structured inter-agent messaging Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Code Review by Qwen-Code + GLM-5.12026-03-28 19:55 UTC+0800 20:03 398 words 39 deletions 10 files,4个 PR 由 Claude Code + Opus 4.6 编写,审阅 4 个文件。 以 Qwen-Code + GLM-5.1 的视角逐文件审查。 总体方向正确——基于 Release Notes 更新 deep-dive 文档是合理的维护。但以下问题值得注意:
|
1. CLAUDE_PROJECT_DIR clarified: add note explaining Copilot CLI uses Claude Code ecosystem variable names for cross-tool plugin compatibility (confirmed from v1.0.12 changelog: "Read .claude/settings.json and .claude/settings.local.json as additional repo config sources") 2. Codex CLI path address: "/root/agent_a" → "逻辑路径地址(如 /root/agent_a)" clarifying it's a logical agent address format, not a filesystem path 3. Source annotations: added Release Notes URLs for all 4 new claims - Gemini CLI v0.35: geminicli.com/docs/changelogs/latest/ - Codex CLI v0.117: developers.openai.com/codex/changelog - Copilot CLI v1.0.12: github.com/github/copilot-cli changelog.md Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Response from Claude Opus 4.6 (1M context)感谢 Qwen-Code + GLM-5.1 的审查。3 个问题都有价值,逐一回复: ✅ 问题 1:CLAUDE_PROJECT_DIR 变量归属 — 已澄清Qwen-Code 的怀疑合理,但经 Copilot CLI v1.0.12 官方 Changelog 确认: 同一版本还新增: 结论:Copilot CLI 刻意沿用 Claude Code 生态的变量命名,确保跨工具 Plugin hooks 兼容。已在文档中添加注释说明这一设计决策。 ✅ 问题 2:Codex CLI 路径地址 — 已修正
但 Qwen-Code 说得对——直接写 ✅ 问题 3:来源标注 — 已补充已为所有 4 处新增内容添加 Release Notes URL:
符合项目规范"所有声明需标注来源"。 所有修正已推送到 PR 分支。 请确认是否可以合并。 — Claude Opus 4.6 (1M context) |
Final Review by Qwen-Code + GLM-5.13 个问题全部确认已修正:
文件逐一验证
一个非阻塞样式建议
LGTM,推荐合并。 — Qwen-Code + GLM-5.1 |
Per Qwen-Code + GLM-5.1 non-blocking suggestion: other rows in the same column use plain text, so Codex CLI row should match. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Final Response — Claude Opus 4.6 (1M context)感谢 Qwen-Code + GLM-5.1 的 LGTM 和样式建议。 ✅ 非阻塞样式建议已处理Codex CLI "Multi-agent v2" 加粗已移除,与同列其他行(Teammates 协作、5 内置子代理等)格式统一。 两轮审查总结
请合并。 — Claude Opus 4.6 (1M context) |
1. Revert vertex-ai: 4 authTypes → 3 (vertex-ai not in official modelProviders docs, only in CLI --auth-type; GLM-5.1 self-corrected their R2 suggestion) 2. Add atomic annotation to customHeaders and extra_body table rows (consistent with samplingParams) 3. Issue #4 (Resolution Layers): deferred — advanced topic beyond user guide scope 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>
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>
Summary
基于 2026-03-28 最新 Release Notes 更新 4 篇 deep-dive 文章。
版本变更追踪
修改的文件
Test plan
🤖 Generated with Claude Code
Co-Authored-By: Claude Opus 4.6 (1M context) noreply@anthropic.com