docs: update Claude Code releases to v2.1.66 (v3.30.1)
- Update latest tracked version: 2.1.63 → 2.1.66 - Add v2.1.66: reduced spurious error logging - Add v2.1.63: HTTP hooks, worktree config sharing, /simplify & /batch, memory leaks wave - Add v2.1.62/61: prompt cache + Windows config fixes - Bump guide: 3.30.0 → 3.30.1 - Update 2.1.x series date range (January-March 2026) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Florian BRUNIAUX
parent
d9187ba17b
commit
29e8b62679
8 changed files with 111 additions and 24 deletions
22
CHANGELOG.md
22
CHANGELOG.md
|
|
@ -6,6 +6,28 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
|
|||
|
||||
## [Unreleased]
|
||||
|
||||
## [3.30.1] - 2026-03-04
|
||||
|
||||
### Documentation
|
||||
|
||||
- **Claude Code Releases**: Updated tracking to v2.1.66
|
||||
- v2.1.66: Reduced spurious error logging
|
||||
- v2.1.63: HTTP hooks (POST JSON to URL), project configs shared across git worktrees, `/simplify` & `/batch` bundled commands, major memory leak wave fixed
|
||||
- v2.1.62: Prompt suggestion cache fix
|
||||
- v2.1.61: Windows config file corruption fix
|
||||
|
||||
### Added
|
||||
|
||||
- **LSP natif documenté** (`guide/ultimate-guide.md`, `guide/cheatsheet.md`, landing cheatsheet) — section complète sur le support LSP natif de Claude Code (v2.0.74+, décembre 2025). Contenu : explication du gain (50ms vs 45s pour navigation codebase, 900x), activation via `ENABLE_LSP_TOOL=1` ou `~/.claude/settings.json`, tableau des 11 langages supportés avec commandes d'install (`tsserver`, `pylsp`, `gopls`, `rust-analyzer`, `kotlin-language-server`, `sourcekit-lsp`...), configuration `.lsp.json` pour les timeouts. Cheatsheet enrichi : ligne LSP avec stat perf + note d'activation. Sources : [aifreeapi.com/en/posts/claude-code-lsp](https://aifreeapi.com/en/posts/claude-code-lsp), Perplexity fact-check mars 2026.
|
||||
|
||||
- **Pattern `docs/solutions/` documenté** (`guide/ultimate-guide.md` §CLAUDE.md as Compounding Memory) — pattern complémentaire à CLAUDE.md pour capitaliser les problèmes résolus entre PRs, inspiré du framework [Compound Engineering (Every.to)](https://every.to/guides/compound-engineering). Distinction claire : CLAUDE.md = règles comportementales, `docs/solutions/` = problèmes résolus avec contexte complet. Inclut exemple de structure avec 3 fichiers illustratifs (auth, iOS StoreKit, Kotlin coroutines).
|
||||
|
||||
- **Voice Mode documenté** (`guide/ultimate-guide.md`, `guide/cheatsheet.md`) — feature native rolling out (~5% des users Pro/Max/Team/Enterprise). `/voice` pour activer, maintenir `Space` pour parler, relâcher pour envoyer. Mixable avec la saisie texte dans le même prompt. Transcription gratuite, ne compte pas dans les rate limits. 4 endroits mis à jour : table quick commands §1.3, table built-in commands §6.1, section voice workarounds §11 (passage du workaround superwhisper/MacWhisper à la feature native), cheatsheet (commandes + shortcuts + features méconnues). Source : [Charly Wargnier / LinkedIn](https://www.linkedin.com/posts/charlywargnier_voice-mode-is-officially-coming-to-claude-ugcPost-7434514836211863552-JvKw).
|
||||
|
||||
- **Smart Concierge + Retex system** — portage du système développé sur Méthode Aristote vers ce projet. Hook `UserPromptSubmit` (`smart-suggest.sh`) qui analyse chaque prompt en langage naturel et suggère 0 ou 1 outil pertinent (max 1 par prompt, silent sur slash commands, dedup si l'outil est déjà dans le prompt, log ROI dans `~/.claude/logs/smart-suggest.jsonl`). 22 patterns en 2 tiers adaptés aux outils de ce projet : Tier 1 découverte (retex, whitepaper-density/journalist/coherence, pdf-generator, sync, security-audit, audit-repo-docs, boldguy-linkedin-answer, guide-recap, park, update-whitepapers), Tier 2 contextuel (release, changelog, version, code-reviewer, debugger, audit-agents-skills, update-threat-db, audit-prose, release-notes-generator, security-check).
|
||||
- **Commande `/retex`** — capture de lessons learned (fausses pistes, bugs, rollbacks) dans `.claude/memories/retex-*.md` avec index global `retex-index.md`. Structure : what happened, root cause, prevention rule, tags, severity, scope. Mode direct (`/retex "description"`) et interactif.
|
||||
- **Rule `retex-review.md`** — auto-loaded à chaque session, affiche les 3 retex récents au démarrage, surfacing contextuel inline si pattern matchant une prevention rule existante (max 1 warning par type par session).
|
||||
|
||||
## [3.30.0] - 2026-03-03
|
||||
|
||||
### Added
|
||||
|
|
|
|||
|
|
@ -6,7 +6,7 @@
|
|||
|
||||
<p align="center">
|
||||
<a href="https://github.com/FlorianBruniaux/claude-code-ultimate-guide/stargazers"><img src="https://img.shields.io/github/stars/FlorianBruniaux/claude-code-ultimate-guide?style=for-the-badge" alt="Stars"/></a>
|
||||
<a href="./CHANGELOG.md"><img src="https://img.shields.io/badge/Updated-Mar_3,_2026_·_v3.30.0-brightgreen?style=for-the-badge" alt="Last Update"/></a>
|
||||
<a href="./CHANGELOG.md"><img src="https://img.shields.io/badge/Updated-Mar_4,_2026_·_v3.30.1-brightgreen?style=for-the-badge" alt="Last Update"/></a>
|
||||
<a href="./quiz/"><img src="https://img.shields.io/badge/Quiz-274_questions-orange?style=for-the-badge" alt="Quiz"/></a>
|
||||
<a href="./examples/"><img src="https://img.shields.io/badge/Templates-175-green?style=for-the-badge" alt="Templates"/></a>
|
||||
<a href="./guide/security-hardening.md"><img src="https://img.shields.io/badge/🛡️_Threat_DB-24_CVEs_·_655_malicious_skills-red?style=for-the-badge" alt="Threat Database"/></a>
|
||||
|
|
@ -846,7 +846,7 @@ See [CONTRIBUTING.md](./CONTRIBUTING.md) for guidelines.
|
|||
|
||||
---
|
||||
|
||||
*Version 3.30.0 | Updated daily · Mar 3, 2026 | Crafted with Claude*
|
||||
*Version 3.30.1 | Updated daily · Mar 4, 2026 | Crafted with Claude*
|
||||
|
||||
<!-- SEO Keywords -->
|
||||
<!-- claude code, claude code tutorial, anthropic cli, ai coding assistant, claude code mcp,
|
||||
|
|
|
|||
2
VERSION
2
VERSION
|
|
@ -1 +1 @@
|
|||
3.30.0
|
||||
3.30.1
|
||||
|
|
|
|||
|
|
@ -12,7 +12,7 @@ tags: [cheatsheet, reference]
|
|||
|
||||
**Written with**: Claude (Anthropic)
|
||||
|
||||
**Version**: 3.30.0 | **Last Updated**: February 2026
|
||||
**Version**: 3.30.1 | **Last Updated**: February 2026
|
||||
|
||||
---
|
||||
|
||||
|
|
@ -38,6 +38,7 @@ tags: [cheatsheet, reference]
|
|||
| `/rc` | Alias for /remote-control |
|
||||
| `/mobile` | Get Claude mobile app download links |
|
||||
| `/fast` | Toggle fast mode (2.5x speed, 6x cost) |
|
||||
| `/voice` | Toggle voice input (hold Space to speak, release to send) |
|
||||
| `/debug` | Systematic troubleshooting |
|
||||
| `/exit` | Quit (or Ctrl+D) |
|
||||
|
||||
|
|
@ -56,6 +57,7 @@ tags: [cheatsheet, reference]
|
|||
| `Shift+Enter` | New line |
|
||||
| `Ctrl+B` | Background tasks |
|
||||
| `Alt+T` | Toggle thinking |
|
||||
| `Space` (hold) | Voice input (requires `/voice` enabled) |
|
||||
| `Ctrl+D` | Exit |
|
||||
|
||||
---
|
||||
|
|
@ -84,9 +86,12 @@ tags: [cheatsheet, reference]
|
|||
| **Agent Teams** | v2.1.32 | Multi-agent coordination (TeamCreate/SendMessage) |
|
||||
| **Auto-Memories** | v2.1.32 | Automatic cross-session context capture |
|
||||
| **Session Forking** | v2.1.19 | Rewind + create parallel timeline |
|
||||
| **LSP Tool** | v2.0.74 | Code intelligence (go-to-def, refs) |
|
||||
| **LSP Tool** | v2.0.74 | IDE-like navigation: symbols, types, refs. ~50ms vs 45s with grep. 11 languages |
|
||||
| **Voice Mode** | v2.1.x | Native voice input, free transcription, no rate limit impact |
|
||||
| **Remote Control** | v2.1.51 | Control local session from phone/browser (Research Preview, Pro/Max) |
|
||||
|
||||
**Activate LSP**: Add to `~/.claude/settings.json` → `{ "env": { "ENABLE_LSP_TOOL": "1" } }` (requires LSP server installed for your language: `tsserver`, `pylsp`, `gopls`, `rust-analyzer`, `sourcekit-lsp`...)
|
||||
|
||||
**Pro tip**: These aren't "secrets"—they're in the [CHANGELOG](https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md). Read it!
|
||||
|
||||
---
|
||||
|
|
@ -608,4 +613,4 @@ where.exe claude; claude doctor; claude mcp list
|
|||
|
||||
**Author**: Florian BRUNIAUX | [@Méthode Aristote](https://methode-aristote.fr) | Written with Claude
|
||||
|
||||
*Last updated: February 2026 | Version 3.30.0*
|
||||
*Last updated: February 2026 | Version 3.30.1*
|
||||
|
|
|
|||
|
|
@ -10,20 +10,24 @@ tags: [reference, release]
|
|||
> **Full details**: [github.com/anthropics/claude-code/CHANGELOG.md](https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md)
|
||||
> **Machine-readable**: [claude-code-releases.yaml](../machine-readable/claude-code-releases.yaml)
|
||||
|
||||
**Latest**: v2.1.63 | **Updated**: 2026-02-27
|
||||
**Latest**: v2.1.66 | **Updated**: 2026-03-04
|
||||
|
||||
---
|
||||
|
||||
## Quick Jump
|
||||
|
||||
- [2.1.x Series (January-February 2026)](#21x-series-january-february-2026) — Worktree isolation, background agents, ConfigChange hook, Fast mode Opus 4.6, 1M context, claude.ai MCP connectors, remote-control, auto-memory, /copy command, HTTP hooks, worktree config sharing
|
||||
- [2.1.x Series (January-March 2026)](#21x-series-january-march-2026) — Worktree isolation, background agents, ConfigChange hook, Fast mode Opus 4.6, 1M context, claude.ai MCP connectors, remote-control, auto-memory, /copy command, HTTP hooks, worktree config sharing
|
||||
- [2.0.x Series (Nov 2025 - Jan 2026)](#20x-series-november-2025---january-2026) — Opus 4.5, Claude in Chrome, Background agents
|
||||
- [Breaking Changes Summary](#breaking-changes-summary)
|
||||
- [Milestone Features](#milestone-features)
|
||||
|
||||
---
|
||||
|
||||
## 2.1.x Series (January-February 2026)
|
||||
## 2.1.x Series (January-March 2026)
|
||||
|
||||
### v2.1.66 (2026-03-04)
|
||||
|
||||
- **Fixed**: Reduced spurious error logging
|
||||
|
||||
### v2.1.63 (2026-02-27)
|
||||
|
||||
|
|
|
|||
|
|
@ -16,7 +16,7 @@ tags: [guide, reference, workflows, agents, hooks, mcp, security]
|
|||
|
||||
**Last updated**: January 2026
|
||||
|
||||
**Version**: 3.30.0
|
||||
**Version**: 3.30.1
|
||||
|
||||
---
|
||||
|
||||
|
|
@ -364,6 +364,7 @@ These 7 commands are the ones I use most frequently:
|
|||
| `/exit` or `Ctrl+D` | Exit Claude Code | Done working |
|
||||
| `/plan` | Enter Plan Mode | Safe exploration |
|
||||
| `/rewind` | Undo changes | Made a mistake |
|
||||
| `/voice` | Toggle voice input | Speak instead of type |
|
||||
|
||||
### Quick Actions & Shortcuts
|
||||
|
||||
|
|
@ -4344,6 +4345,19 @@ Month 3: 50 rules → 50 mistakes prevented + faster onboarding
|
|||
|
||||
**Anti-pattern**: Preemptively documenting everything. Instead, treat CLAUDE.md as a **living document** that grows through actual mistakes caught during development.
|
||||
|
||||
#### Going further: capitalizing solutions across PRs
|
||||
|
||||
CLAUDE.md captures behavioral rules. For solved technical problems, a complementary pattern from [Every.to's Compound Engineering](https://every.to/guides/compound-engineering): a `docs/solutions/` directory that turns each non-trivial problem into searchable documentation.
|
||||
|
||||
```
|
||||
docs/solutions/
|
||||
├── auth-token-refresh-race-condition.md
|
||||
├── ios-storekit2-receipt-validation.md
|
||||
└── kotlin-coroutine-timeout-pattern.md
|
||||
```
|
||||
|
||||
Each file documents: the problem, the solution, why it works, and edge cases. Claude reads these files when similar patterns appear — the third time a related issue surfaces, the fix is already there. The distinction with CLAUDE.md is intentional: CLAUDE.md contains rules, `docs/solutions/` contains solved problems with their full context.
|
||||
|
||||
### Build for the Model 6 Months Out
|
||||
|
||||
> **"Don't design your workflows around the limitations of today's model. Build for where the technology will be in six months."**
|
||||
|
|
@ -4767,7 +4781,7 @@ The `.claude/` folder is your project's Claude Code directory for memory, settin
|
|||
| Personal preferences | `CLAUDE.md` | ❌ Gitignore |
|
||||
| Personal permissions | `settings.local.json` | ❌ Gitignore |
|
||||
|
||||
### 3.30.0 Version Control & Backup
|
||||
### 3.30.1 Version Control & Backup
|
||||
|
||||
**Problem**: Without version control, losing your Claude Code configuration means hours of manual reconfiguration across agents, skills, hooks, and MCP servers.
|
||||
|
||||
|
|
@ -7582,6 +7596,7 @@ Slash commands are shortcuts for common workflows.
|
|||
| `/status` | Show session info |
|
||||
| `/plan` | Enter Plan Mode |
|
||||
| `/rewind` | Undo changes |
|
||||
| `/voice` | Toggle voice input (hold Space to speak, release to send) |
|
||||
| `/simplify` | Review changed code and fix over-engineering |
|
||||
| `/batch` | Large-scale changes via parallel worktree agents |
|
||||
| `/insights` | Generate usage analytics report |
|
||||
|
|
@ -11837,7 +11852,42 @@ my-plugin/
|
|||
└── README.md # Documentation
|
||||
```
|
||||
|
||||
**LSP server configuration (`.lsp.json`)** — supports `startupTimeout` (v2.1.50+) to control how long Claude waits for a server to initialize before treating it as unresponsive:
|
||||
### LSP Native Support (v2.0.74+)
|
||||
|
||||
Since v2.0.74 (December 2025), Claude Code natively integrates with Language Server Protocol servers. Instead of navigating your codebase through text search (grep), Claude connects to the LSP server of your project and understands symbols, types, and cross-references — the same way an IDE does.
|
||||
|
||||
**Why it matters**: Finding all call sites of a function drops from ~45 seconds (text search) to ~50ms (LSP). Claude also gets automatic diagnostics after every file edit — errors and warnings appear in real time, without a separate build step.
|
||||
|
||||
**Supported languages (11)**: Python, TypeScript, JavaScript, Go, Rust, Java, C/C++, C#, PHP, Kotlin, Ruby.
|
||||
|
||||
#### Activation
|
||||
|
||||
```bash
|
||||
# Option 1 — one-time env variable
|
||||
ENABLE_LSP_TOOL=1 claude
|
||||
|
||||
# Option 2 — persist in ~/.claude/settings.json
|
||||
{
|
||||
"env": {
|
||||
"ENABLE_LSP_TOOL": "1"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
The LSP server for your language must already be installed on the machine — Claude Code connects to it, it doesn't install it. Common servers:
|
||||
|
||||
| Language | Server | Install |
|
||||
|----------|--------|---------|
|
||||
| TypeScript | `tsserver` | Bundled with TypeScript |
|
||||
| Python | `pylsp` | `pip install python-lsp-server` |
|
||||
| Go | `gopls` | `go install golang.org/x/tools/gopls@latest` |
|
||||
| Rust | `rust-analyzer` | `rustup component add rust-analyzer` |
|
||||
| Kotlin | `kotlin-language-server` | Via IntelliJ or standalone |
|
||||
| Swift | `sourcekit-lsp` | Bundled with Xcode |
|
||||
|
||||
#### Timeout configuration (`.lsp.json`)
|
||||
|
||||
Controls how long Claude waits for an LSP server to initialize before treating it as unresponsive (v2.1.50+):
|
||||
|
||||
```json
|
||||
{
|
||||
|
|
@ -21591,7 +21641,7 @@ Use rebase for clean history before push, merge for shared branches.
|
|||
> **Tip**: These resources evolve quickly. Star repos you find useful to track updates.
|
||||
|
||||
**Additional topics from ykdojo worth exploring** (not yet integrated in this guide):
|
||||
- **Voice transcription workflows** - Using superwhisper/MacWhisper for faster input than typing
|
||||
- **Voice transcription workflows** - Native voice input now available via `/voice` (rolling out, Pro/Max/Team/Enterprise). Hold Space to speak, release to send. Transcription is free and doesn't count against rate limits. Previously required superwhisper/MacWhisper as external workarounds.
|
||||
- **Tmux for autonomous testing** - Running interactive tools in tmux sessions for automated testing
|
||||
- **cc-safe security tool** - Auditing approved commands to prevent accidental deletions
|
||||
- **Cascade method** - Multitasking pattern with 3-4 terminal tabs for parallel work streams
|
||||
|
|
@ -22144,4 +22194,4 @@ We'll evaluate and add it to this section if it meets quality criteria.
|
|||
|
||||
**Contributions**: Issues and PRs welcome.
|
||||
|
||||
**Last updated**: January 2026 | **Version**: 3.30.0
|
||||
**Last updated**: January 2026 | **Version**: 3.30.1
|
||||
|
|
|
|||
|
|
@ -3,8 +3,8 @@
|
|||
# Purpose: Track Claude Code product releases for documentation sync
|
||||
# Maintained: Manual updates when new releases are announced
|
||||
|
||||
latest: "2.1.63"
|
||||
updated: "2026-02-27"
|
||||
latest: "2.1.66"
|
||||
updated: "2026-03-04"
|
||||
|
||||
# ════════════════════════════════════════════════════════════════
|
||||
# RELEASES (newest first, condensed highlights only)
|
||||
|
|
@ -12,9 +12,15 @@ updated: "2026-02-27"
|
|||
releases:
|
||||
|
||||
# ─────────────────────────────────────────────────────────────
|
||||
# 2.1.x Series (January-February 2026)
|
||||
# 2.1.x Series (January-March 2026)
|
||||
# ─────────────────────────────────────────────────────────────
|
||||
|
||||
- version: "2.1.66"
|
||||
date: "2026-03-04"
|
||||
highlights:
|
||||
- "Reduced spurious error logging"
|
||||
breaking: []
|
||||
|
||||
- version: "2.1.63"
|
||||
date: "2026-02-27"
|
||||
highlights:
|
||||
|
|
|
|||
|
|
@ -3,7 +3,7 @@
|
|||
# Source: guide/ultimate-guide.md
|
||||
# Purpose: Condensed index for LLMs to quickly answer user questions about Claude Code
|
||||
|
||||
version: "3.30.0"
|
||||
version: "3.30.1"
|
||||
updated: "2026-03-03"
|
||||
|
||||
# ════════════════════════════════════════════════════════════════
|
||||
|
|
@ -1426,7 +1426,7 @@ ecosystem:
|
|||
- "Cross-links modified → Update all 4 repos"
|
||||
history:
|
||||
- date: "2026-01-20"
|
||||
event: "Code Landing sync v3.30.0, 66 templates, cross-links"
|
||||
event: "Code Landing sync v3.30.1, 66 templates, cross-links"
|
||||
commit: "5b5ce62"
|
||||
- date: "2026-01-20"
|
||||
event: "Cowork Landing fix (paths, README, UI badges)"
|
||||
|
|
@ -1438,7 +1438,7 @@ ecosystem:
|
|||
onboarding_matrix_meta:
|
||||
version: "2.0.0"
|
||||
last_updated: "2026-02-05"
|
||||
aligned_with_guide: "3.30.0"
|
||||
aligned_with_guide: "3.30.1"
|
||||
changelog:
|
||||
- version: "2.0.0"
|
||||
date: "2026-02-05"
|
||||
|
|
@ -1466,7 +1466,7 @@ onboarding_matrix:
|
|||
core: [rules, sandbox_native_guide, commands]
|
||||
time_budget: "5 min"
|
||||
topics_max: 3
|
||||
note: "SECURITY FIRST - sandbox before commands (v3.30.0 critical fix)"
|
||||
note: "SECURITY FIRST - sandbox before commands (v3.30.1 critical fix)"
|
||||
|
||||
beginner_15min:
|
||||
core: [rules, sandbox_native_guide, workflow, essential_commands]
|
||||
|
|
@ -1551,7 +1551,7 @@ onboarding_matrix:
|
|||
- default: agent_validation_checklist
|
||||
time_budget: "60 min"
|
||||
topics_max: 6
|
||||
note: "Dual-instance pattern for quality workflows (v3.30.0)"
|
||||
note: "Dual-instance pattern for quality workflows (v3.30.1)"
|
||||
|
||||
learn_security:
|
||||
intermediate_30min:
|
||||
|
|
@ -1562,7 +1562,7 @@ onboarding_matrix:
|
|||
- default: permission_modes
|
||||
time_budget: "30 min"
|
||||
topics_max: 4
|
||||
note: "NEW goal (v3.30.0) - Security-focused learning path"
|
||||
note: "NEW goal (v3.30.1) - Security-focused learning path"
|
||||
|
||||
power_60min:
|
||||
core: [sandbox_native_guide, mcp_secrets_management, security_hardening]
|
||||
|
|
@ -1587,7 +1587,7 @@ onboarding_matrix:
|
|||
core: [rules, sandbox_native_guide, workflow, essential_commands, context_management, plan_mode]
|
||||
time_budget: "60 min"
|
||||
topics_max: 6
|
||||
note: "Security foundation + core workflow (v3.30.0 sandbox added)"
|
||||
note: "Security foundation + core workflow (v3.30.1 sandbox added)"
|
||||
|
||||
intermediate_120min:
|
||||
core: [plan_mode, agents, skills, config_hierarchy, git_mcp_guide, hooks, mcp_servers]
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue