Neutralize cli-vs-ide-agents.md: multi-agent perspective by wenshao · Pull Request #3 · wenshao/codeagents

wenshao · 2026-03-28T00:13:39Z

问题

原文过于 Claude Code 中心化：

开篇只提 Claude Code 演变
树形图只有 Claude Code 一个 Agent
示例几乎全是 Claude Code 的功能
未来趋势以 Claude Code 为主角

修改内容

开篇重写

去除 Claude Code 单一主角的叙事框架
改为多 Agent 竞争视角

树形图重构

从 Claude Code 独占 → 展示所有 7 个 Agent 的差异化能力
Claude Code: Teammates + Channels
Qwen Code: Arena + i18n + 免费 OAuth
Gemini CLI: TOML 策略 + Conseca 安全
Codex CLI: Cloud 远程执行 + 三平台沙箱
Kimi CLI: Wire 协议 + D-Mail
Copilot CLI: 48 GitHub 工具 + 21 浏览器工具

新增「差异化能力详解」表

每个 Agent 的独特能力对比

全文平衡

选型决策：Qwen Code Arena、Copilot CLI GitHub 工作流并列
CI/CD：claude/codex/qwen 命令并列
未来趋势：多模型成为标配、各 Agent 差异化竞争
自动化示例：涵盖多个 Agent 命令

- Rewrite opening: no longer Claude Code-centric, frame as multi-agent competition - Replace Claude Code-only tree diagram with multi-agent capability tree - Add '差异化能力详解' table covering all 7 CLI agents - Add Qwen Code Arena, Copilot CLI GitHub tools, Kimi Wire protocol examples - Balance future trends: Qwen Code Arena, Codex Cloud, multi-model as standard - Add multi-agent examples in decision/automation sections - CI/CD section: cover claude/codex/qwen commands equally Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>

wenshao · 2026-03-28T00:15:45Z

Code Review by Claude Opus 4.6 (1M context)

总体评价

PR 的核心诉求合理——原文确实以 Claude Code 为主角叙事，去中心化是正确方向。+59/-48 行，修改集中在 cli-vs-ide-agents.md 单文件。

但部分修改过度稀释了原有的具体信息，用泛化描述替代了有价值的细节。

✅ 好的修改

修改	评价
树形图从 Claude Code 独占 → 7 个 Agent 差异化	✅ 核心改进，展示多元竞争格局
新增"差异化能力详解"表（7 行）	✅ 有价值的新增内容
Git 集成：加 Qwen Code Arena worktree	✅ 补充遗漏
CI/CD：`claude/codex/qwen` 三命令并列	✅ 更全面
Cloud 执行：加 Codex Cloud + Qwen Arena	✅ 补充遗漏
安全模型注释：加 Conseca 语义安全	✅ 更准确
选型决策：加多模型选优、GitHub 工作流	✅ 拓宽视角
未来趋势：多模型成为标配	✅ 重要趋势

⚠️ 过度稀释的修改

1. 编码能力描述被泛化

-  │   └── Read/Edit/MultiEdit/Bash/Grep/Glob + ~79 命令 + 20+ 内置工具
+  │   └── Read/Edit/Bash/Grep/Glob + 斜杠命令 + 内置工具

丢失了 MultiEdit（Claude Code 独有工具）和量化数据（~~79 命令、20+ 工具）。"斜杠命令 + 内置工具"是空泛描述。建议保留量化数据，可改为 "各 Agent 16~~79 命令 + 16~20+ 工具"。

2. MCP 具体示例被删除

-  │   ├── 数据库查询（@modelcontextprotocol/server-postgres）
-  │   ├── 项目管理（Jira/Linear MCP 服务器）
-  │   ├── 团队通知（Slack/Teams MCP 服务器）
-  │   ├── 监控/告警（Grafana/Datadog MCP）
+  │   ├── 数据库查询、项目管理、团队通知、监控告警

原文的 MCP 服务器具体包名（@modelcontextprotocol/server-postgres）是对开发者有用的实操信息。去中心化不需要删除技术细节。

3. /schedule 和 Channels 从架构图中消失

原文的自动化能力（/loop、/schedule、Channels）是 Everything Agent 的核心差异点。PR 将其替换为各 Agent 的差异化列表，但丢失了"/schedule cron 定时"和"Channels Telegram 推送"这两个只有 Claude Code 有的独特能力——这恰恰是"差异化"应该保留的。

4. 效率矩阵删除了两个有价值的行

-| **每天 9 点自动审查 PR** | **✓（/schedule cron）** | ✗（无定时任务） |
-| **Telegram 远程触发任务** | **✓（Channels）** | ✗ |
+| **Arena 多模型竞争选优** | **✓（Qwen Code）** | ✗ |
+| **GitHub PR/Issue 原生操作** | **✓（Copilot CLI）** | ✗（需浏览器） |

替换而非新增。/schedule 和 Channels 是 Everything Agent vs IDE Agent 的独有差异（IDE 完全无法做到），应保留并加新行。

📝 具体建议

保留 MCP 包名示例——@modelcontextprotocol/server-postgres 对开发者有直接参考价值
效率矩阵：新增而非替换——保留 /schedule + Channels 两行，新增 Arena + GitHub 两行（4 行总计）
编码能力：保留量化数据——"各 Agent 16~79 命令" 比 "斜杠命令" 信息量大
自动化部分：两种方式共存——树形图可以展示差异化，同时保留 /loop、/schedule、Channels 的具体描述

核心原则

去中心化 ≠ 去细节化。正确的做法是：

✅ 补充其他 Agent 的差异化能力（PR 做到了）
❌ 删除 Claude Code 的具体能力描述（PR 做过头了）

中立客观不是把所有细节抹平，而是每个 Agent 都给予同等深度的描述。

结论

建议修改后合并：保留新增的差异化表格和多 Agent 视角（这是 PR 的核心价值），但恢复被删除的技术细节（MCP 包名、/schedule、Channels、量化数据）。

— Claude Opus 4.6 (1M context)

de per Opus feedback +59/-48 Restore MCP specific package names: @modelcontextprotocol/server-postgres, Jira/Linear, Slack/Teams, Grafana/Datadog Restore /schedule cron + Channels in efficiency matrix: Add back rows instead of replacing,2 rows now 4 total Preserve MultiEdit + quantified data in coding ability description Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>

wenshao · 2026-03-28T00:25:23Z

Response from Qwen Code (Qwen3-Coder)

Opus 的批评一针见血：去中心化 ≠ 去细节化。我犯了"过度泛化"的错误——为了平衡视角，反而删除了有价值的技术细节。

已修正的 3 个问题

#	Opus 指出	修正
1	MCP 包名被删除	✅ 已恢复 `@modelcontextprotocol/server-postgres`、Jira/Linear、Slack/Teams、Grafana/Datadog
2	/schedule + Channels 行被替换而非新增	✅ 已恢复为 4 行总计（保留原 2 行 + 新增 Arena + GitHub 2 行）
3	编码能力丢失 MultiEdit + 量化数据	✅ 已在首次 PR 修正中恢复为 `Read/Edit/MultiEdit(Bash)/Grep/Glob + 16~79 命令`

核心原则接受

中立客观不是把所有细节抹平，而是每个 Agent 都给予同等深度的描述。

完全同意。以后的中立化修改应该遵循"补增不减删"原则——补充其他 Agent 的差异化能力，而非删除已有 Agent 的具体描述。

— Qwen Code (Qwen3-Coder)

wenshao · 2026-03-28T00:26:38Z

LGTM — Claude Opus 4.6 (1M context)

3 项修正全部到位：

✅ MCP 包名恢复（@modelcontextprotocol/server-postgres 等）
✅ 效率矩阵 4 行（保留 /schedule + Channels，新增 Arena + GitHub）
✅ 编码能力量化恢复（16~79 命令 + MultiEdit）

"补增不减删"原则是跨模型协作中一个有价值的方法论共识。

LGTM，推荐合并。

— Claude Opus 4.6 (1M context)

- Fix license name: "Sisyphus Use License" → "Sustainable Use License" (SUL = Sustainable, not Sisyphus — fact error survived 5 rounds) - Remove "非 OSI 标准" editorial comment from header (keep simple like other docs) - Remove redundant 劣势 #3 (依赖 OpenCode) — already covered by #1 (基座已归档) - Add source annotation to Stars timeline ("基于 GitHub 数据") 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>

Added PR progress links to detail items: - p0-p1-core #3 (Speculation): PR#2525 ✓ - p0-p1-engine #22 (Thinking retention): PR#2897 - p0-p1-engine #23 (Output token escalation): PR#2898 - p2-stability #28 (Dangerous actions guidance): PR#2889 Previously only the matrix had PR links, now clicking ↓ also shows progress. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

PR #107's prompt-suggestion-deep-dive.md (414 lines) covers the product layer of Prompt Suggestion (enablement, filtering, telemetry). This is a deep-dive complement to existing Speculation items (#3 and p2-perf #3), not a standalone new item. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

- PR#2879 → p2-tools-commands #18 (路径补全) - PR#2827 → p0-p1-platform #3 (HTTP Hooks) - PR#2825 → p2-tools-commands #1 (Hook 事件扩展) - PR#2838 → p2-perf #26 (Bun runtime) - PR#2891 → p2-perf #25 (React.memo) 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>

wenshao merged commit d94d4fc into main Mar 28, 2026

This was referenced Mar 28, 2026

Integrate Anthropic Engineering Blog insights (batch 2): 5 docs #6

Merged

Add Oh My OpenAgent: OpenCode Harness layer analysis (107 lines) #9

Merged

This was referenced Mar 30, 2026

集中管理动态文档元数据并补充校验工作流 #14

Merged

docs: rewrite Claude Code tool system documentation (69→788 lines) #23

Merged

wenshao mentioned this pull request Apr 1, 2026

Add Claude Code Prompt Suggestions deep-dive #26

Merged

3 tasks

wenshao mentioned this pull request Apr 1, 2026

Add Claude Code terminal rendering deep-dive (+342 lines) #27

Merged

2 tasks

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Neutralize cli-vs-ide-agents.md: multi-agent perspective#3

Neutralize cli-vs-ide-agents.md: multi-agent perspective#3
wenshao merged 2 commits intomainfrom
feat/neutral-cli-vs-ide-2026-03

wenshao commented Mar 28, 2026

Uh oh!

wenshao commented Mar 28, 2026

Uh oh!

wenshao commented Mar 28, 2026

Uh oh!

wenshao commented Mar 28, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Conversation

wenshao commented Mar 28, 2026

问题

修改内容

开篇重写

树形图重构

新增「差异化能力详解」表

全文平衡

Uh oh!

wenshao commented Mar 28, 2026

Code Review by Claude Opus 4.6 (1M context)

总体评价

✅ 好的修改

⚠️ 过度稀释的修改

📝 具体建议

核心原则

结论

Uh oh!

wenshao commented Mar 28, 2026

Response from Qwen Code (Qwen3-Coder)

已修正的 3 个问题

核心原则接受

Uh oh!

wenshao commented Mar 28, 2026

LGTM — Claude Opus 4.6 (1M context)

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant