mirror of
https://github.com/luongnv89/claude-howto.git
synced 2026-08-26 00:22:31 +02:00
docs: sync to Claude Code v2.1.206 (#151)
* docs: correct stale content for Claude Code v2.1.206
Fix content that no longer matches current Claude Code behavior:
- 04-subagents: remove the /agents creation-wizard instructions
(wizard removed in v2.1.198); point users to ask Claude or edit
.claude/agents/ files directly. Explore agent now inherits the
session model (capped at Opus) instead of Haiku; subagents run in
the background by default.
- Rename the default permission mode "default" -> "Manual" (v2.1.200)
across README, CATALOG, INDEX, LEARNING-ROADMAP, resources,
claude_concepts_guide, and 09-advanced-features, noting that
"default" still works as an alias.
- README: update the stale "latest v2.1.160" currency claims to v2.1.206.
- Reconcile the contradictory /simplify vs /code-review history:
they are distinct current skills (/simplify split back out in v2.1.154).
Refresh metadata footers to v2.1.206 / July 11, 2026 and add Claude
Sonnet 5 to Compatible Models on every edited file.
* docs: add Claude Code v2.1.206 feature coverage
Document new features and options that landed through v2.1.206:
- Skills: /dataviz bundled skill, skill stacking (loads all leading
skills, up to 5), and the ${CLAUDE_PROJECT_DIR} substitution.
- Slash commands: /dataviz row and ${CLAUDE_PROJECT_DIR} mention.
- Subagents already covered in the correctness commit; CLI adds
--append-subagent-system-prompt, CLAUDE_ENABLE_STREAM_WATCHDOG,
a Claude Sonnet 5 model row (new default, 1M context), and the
/model "Org default" note.
- MCP: roots/list working-directory discovery and the untrusted-
workspace pending-approval behavior for self-approved .mcp.json.
- Hooks: agent_needs_input / agent_completed Notification values and
the prompt_id input field.
- Plugins: marketplace renames / displayName / defaultEnabled fields.
- Checkpoints: "Summarize up to here" backward targeted compaction.
Refresh metadata footers to v2.1.206 / July 11, 2026 and add Claude
Sonnet 5 to Compatible Models on every edited file.
* docs: qualify Sonnet 5 default scope and reconcile bundled-skills list
- Sonnet 5 default is tier-dependent (Pro/Team seats); Opus 4.8 remains
default on Max/Team Premium/Enterprise PAYG/API — was overstated as
the flat default.
- Add missing /simplify row to the bundled-skills table (it was already
referenced as a distinct skill in the /code-review row) and drop the
hard skill count in favor of pointing at the commands reference.
This commit is contained in:
@@ -45,13 +45,14 @@ Use the `/rewind` command (alias: `/checkpoint`) for quick access:
|
||||
|
||||
## Rewind Options
|
||||
|
||||
When you rewind, you are presented with a menu of five options:
|
||||
When you rewind, you are presented with a menu of six options:
|
||||
|
||||
1. **Restore code and conversation** -- Revert both files and messages to that checkpoint
|
||||
2. **Restore conversation** -- Rewind messages only, keep your current code as-is
|
||||
3. **Restore code** -- Revert file changes only, keep the full conversation history
|
||||
4. **Summarize from here** -- Compress the conversation from this point forward into an AI-generated summary, freeing context window space. Messages before the selected point stay intact. No files on disk are changed. The original messages are preserved in the session transcript. You can optionally provide instructions to focus the summary on specific topics.
|
||||
5. **Never mind** -- Cancel and return to the current state
|
||||
5. **Summarize up to here** -- The backward counterpart: compress everything *before* the selected point into an AI-generated summary, keeping the messages from this point forward intact. Together with "Summarize from here" this gives you bidirectional, targeted compaction of your context window. No files on disk are changed, and the original messages are preserved in the session transcript.
|
||||
6. **Never mind** -- Cancel and return to the current state
|
||||
|
||||
> **Note**: After restoring the conversation or summarizing, the original prompt from the selected message is restored into the input field so you can re-send or edit it.
|
||||
|
||||
@@ -327,10 +328,10 @@ Remember: checkpoints are not a replacement for git. Use checkpoints for rapid e
|
||||
|
||||
---
|
||||
|
||||
**Last Updated**: June 28, 2026
|
||||
**Claude Code Version**: 2.1.195
|
||||
**Last Updated**: July 11, 2026
|
||||
**Claude Code Version**: 2.1.206
|
||||
**Sources**:
|
||||
- https://code.claude.com/docs/en/checkpointing
|
||||
- https://code.claude.com/docs/en/settings
|
||||
- https://github.com/anthropics/claude-code/releases/tag/v2.1.117
|
||||
**Compatible Models**: Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
|
||||
**Compatible Models**: Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
|
||||
|
||||
Reference in New Issue
Block a user