APEX/BrowserUse_and_ComputerUse_skills
5
0
Fork 0
Code Issues 6 Pull requests 1 Projects 1 Releases Packages Wiki Activity Actions

docs: update checkpoint/rollback docs for new features

Browse source 
- Reflect that checkpoints are now enabled by default
- Document /rollback diff <N> for previewing changes
- Document /rollback <N> <file> for single-file restore
- Document automatic conversation undo on rollback
- Document terminal command checkpoint coverage
- Update listing example to show change stats
- Fix config path (checkpoints.enabled, not agent.checkpoints_enabled)
- Consolidate features/checkpoints.md to brief summary with link
This commit is contained in:
Teknium 2026-03-16 04:56:22 -07:00 • committed by GitHub
parent 9e845a6e53
commit 00110fb3c3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 115 additions and 159 deletions
Download patch file Download diff file Expand all files Collapse all files

175
website/docs/user-guide/checkpoints-and-rollback.md
View file

@ -6,10 +6,28 @@ description: "Filesystem safety nets for destructive operations using shadow git
# Checkpoints and `/rollback` # Checkpoints and `/rollback`
Hermes Agent can automatically snapshot your project before **destructive operations** (like file write/patch tools) and restore it later with a single command. Hermes Agent automatically snapshots your project before **destructive operations** and lets you restore it with a single command. Checkpoints are **enabled by default** — there's zero cost when no file-mutating tools fire.
This safety net is powered by an internal **Checkpoint Manager** that keeps a separate shadow git repository under `~/.hermes/checkpoints/` — your real project `.git` is never touched. This safety net is powered by an internal **Checkpoint Manager** that keeps a separate shadow git repository under `~/.hermes/checkpoints/` — your real project `.git` is never touched.
## What Triggers a Checkpoint
Checkpoints are taken automatically before:
- **File tools** — `write_file` and `patch`
- **Destructive terminal commands** — `rm`, `mv`, `sed -i`, `truncate`, `shred`, output redirects (`>`), and `git reset`/`clean`/`checkout`
The agent creates **at most one checkpoint per directory per turn**, so long-running sessions don't spam snapshots.
## Quick Reference
| Command | Description |
|---------|-------------|
| `/rollback` | List all checkpoints with change stats |
| `/rollback <N>` | Restore to checkpoint N (also undoes last chat turn) |
| `/rollback diff <N>` | Preview diff between checkpoint N and current state |
| `/rollback <N> <file>` | Restore a single file from checkpoint N |
## How Checkpoints Work ## How Checkpoints Work
At a high level: At a high level:
@ -21,24 +39,11 @@ At a high level:
- Stages and commits the current state with a short, human‑readable reason. - Stages and commits the current state with a short, human‑readable reason.
- These commits form a checkpoint history that you can inspect and restore via `/rollback`. - These commits form a checkpoint history that you can inspect and restore via `/rollback`.
Internally, the Checkpoint Manager:
- Stores shadow repos under:
- `~/.hermes/checkpoints/<hash>/`
- Keeps metadata about:
- The original working directory (`HERMES_WORKDIR` file in the shadow repo).
- Excluded paths such as:
- `node_modules/`, `dist/`, `build/`
- `.venv/`, `__pycache__/`, `*.pyc`
- `.git/`, `.cache/`, `.pytest_cache/`, etc.
The agent creates **at most one checkpoint per directory per turn**, so long running sessions do not spam snapshots.
```mermaid ```mermaid
flowchart LR flowchart LR
user["User command\n(hermes, gateway)"] user["User command\n(hermes, gateway)"]
agent["AIAgent\n(run_agent.py)"] agent["AIAgent\n(run_agent.py)"]
tools["File tools\n(write/patch)"] tools["File & terminal tools"]
cpMgr["CheckpointManager"] cpMgr["CheckpointManager"]
shadowRepo["Shadow git repo\n~/.hermes/checkpoints/<hash>"] shadowRepo["Shadow git repo\n~/.hermes/checkpoints/<hash>"]
@ -50,108 +55,128 @@ flowchart LR
tools -->|"apply changes"| agent tools -->|"apply changes"| agent
``` ```
## Enabling Checkpoints ## Configuration
Checkpoints are controlled by a simple on/off flag and a maximum snapshot count **per directory**: Checkpoints are enabled by default. Configure in `~/.hermes/config.yaml`:
- `checkpoints_enabled` – master switch
- `checkpoint_max_snapshots` – soft cap on history depth per directory
You can configure these in `~/.hermes/config.yaml`:
```yaml ```yaml
agent: checkpoints:
checkpoints_enabled: true enabled: true # master switch (default: true)
checkpoint_max_snapshots: 50 max_snapshots: 50 # max checkpoints per directory
``` ```
Or via CLI flags (exact wiring may depend on your version of the CLI): To disable:
```bash ```yaml
hermes --checkpoints checkpoints:
# or enabled: false
hermes chat --checkpoints
``` ```
When disabled, the Checkpoint Manager is a no‑op and never attempts git operations. When disabled, the Checkpoint Manager is a no‑op and never attempts git operations.
## Listing Checkpoints ## Listing Checkpoints
Hermes exposes an interactive way to list checkpoints for the current working directory. From a CLI session:
From the CLI session where you are working on a project: ```
```bash
# Ask Hermes to show checkpoints for the current directory
/rollback /rollback
``` ```
Hermes responds with a formatted list similar to: Hermes responds with a formatted list showing change statistics:
```text ```text
📸 Checkpoints for /path/to/project: 📸 Checkpoints for /path/to/project:
1. a1b2c3d 2026-03-13 10:24 auto: before apply_patch 1. 4270a8c 2026-03-16 04:36 before patch (1 file, +1/-0)
2. d4e5f6a 2026-03-13 10:15 pre-rollback snapshot (restoring to a1b2c3d0) 2. eaf4c1f 2026-03-16 04:35 before write_file
3. b3f9d2e 2026-03-16 04:34 before terminal: sed -i s/old/new/ config.py (1 file, +1/-1)
Use /rollback <number> to restore, e.g. /rollback 1 /rollback <N> restore to checkpoint N
/rollback diff <N> preview changes since checkpoint N
/rollback <N> <file> restore a single file from checkpoint N
``` ```
Each entry shows: Each entry shows:
- Short hash - Short hash
- Timestamp - Timestamp
- Reason (commit message for the snapshot) - Reason (what triggered the snapshot)
- Change summary (files changed, insertions/deletions)
## Previewing Changes with `/rollback diff`
Before committing to a restore, preview what has changed since a checkpoint:
```
/rollback diff 1
```
This shows a git diff stat summary followed by the actual diff:
```text
test.py | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/test.py b/test.py
--- a/test.py
+++ b/test.py
@@ -1 +1 @@
-print('original content')
+print('modified content')
```
Long diffs are capped at 80 lines to avoid flooding the terminal.
## Restoring with `/rollback` ## Restoring with `/rollback`
Once you have identified the snapshot you want to go back to, use `/rollback` with the number from the list: Restore to a checkpoint by number:
```bash ```
# Restore to the most recent snapshot
/rollback 1 /rollback 1
``` ```
Behind the scenes, Hermes: Behind the scenes, Hermes:
1. Verifies the target commit exists in the shadow repo. 1. Verifies the target commit exists in the shadow repo.
2. Takes a **pre‑rollback snapshot** of the current state so you can “undo the undo” later. 2. Takes a **pre‑rollback snapshot** of the current state so you can "undo the undo" later.
3. Runs `git checkout <hash> -- .` in the shadow repo, restoring tracked files in your working directory. 3. Restores tracked files in your working directory.
4. **Undoes the last conversation turn** so the agent's context matches the restored filesystem state.
On success, Hermes responds with a short summary like: On success:
```text ```text
✅ Restored /path/to/project to a1b2c3d ✅ Restored to checkpoint 4270a8c5: before patch
Reason: auto: before apply_patch A pre-rollback snapshot was saved automatically.
(^_^)b Undid 4 message(s). Removed: "Now update test.py to ..."
4 message(s) remaining in history.
Chat turn undone to match restored file state.
``` ```
If something goes wrong (missing commit, git error), you will see a clear error message and details will be logged. The conversation undo ensures the agent doesn't "remember" changes that have been rolled back, avoiding confusion on the next turn.
## Single-File Restore
Restore just one file from a checkpoint without affecting the rest of the directory:
```
/rollback 1 src/broken_file.py
```
This is useful when the agent made changes to multiple files but only one needs to be reverted.
## Safety and Performance Guards ## Safety and Performance Guards
To keep checkpointing safe and fast, Hermes applies several guardrails: To keep checkpointing safe and fast, Hermes applies several guardrails:
- **Git availability** - **Git availability** — if `git` is not found on `PATH`, checkpoints are transparently disabled.
- If `git` is not found on `PATH`, checkpoints are transparently disabled. - **Directory scope** — Hermes skips overly broad directories (root `/`, home `$HOME`).
- A debug log entry is emitted, but your session continues normally. - **Repository size** — directories with more than 50,000 files are skipped to avoid slow git operations.
- **Directory scope** - **No‑change snapshots** — if there are no changes since the last snapshot, the checkpoint is skipped.
- Hermes skips overly broad directories such as: - **Non‑fatal errors** — all errors inside the Checkpoint Manager are logged at debug level; your tools continue to run.
- Root (`/`)
- Your home directory (`$HOME`)
- This prevents accidental snapshots of your entire filesystem.
- **Repository size**
- Before committing, Hermes performs a quick file count.
- If the directory has more than a configured threshold (e.g. `50,000` files),
checkpoints are skipped to avoid large git operations.
- **No‑change snapshots**
- If there are no changes since the last snapshot, the checkpoint is skipped
instead of committing an empty diff.
All errors inside the Checkpoint Manager are treated as **non‑fatal**: they are logged at debug level and your tools continue to run.
## Where Checkpoints Live ## Where Checkpoints Live
By default, all shadow repos live under: All shadow repos live under:
```text ```text
~/.hermes/checkpoints/ ~/.hermes/checkpoints/
@ -160,21 +185,19 @@ By default, all shadow repos live under:
└── ... └── ...
``` ```
Each `<hash>` is derived from the absolute path of the working directory. Inside each shadow repo you will find: Each `<hash>` is derived from the absolute path of the working directory. Inside each shadow repo you'll find:
- Standard git internals (`HEAD`, `refs/`, `objects/`) - Standard git internals (`HEAD`, `refs/`, `objects/`)
- An `info/exclude` file containing a curated ignore list - An `info/exclude` file containing a curated ignore list
- A `HERMES_WORKDIR` file pointing back to the original project root - A `HERMES_WORKDIR` file pointing back to the original project root
You normally never need to touch these manually; they are documented here so advanced users understand how the safety net works. You normally never need to touch these manually.
## Best Practices ## Best Practices
- **Keep checkpoints enabled** for interactive development and refactors. - **Leave checkpoints enabled** — they're on by default and have zero cost when no files are modified.
- **Use `/rollback` instead of `git reset`** when you want to undo agent‑driven changes only. - **Use `/rollback diff` before restoring** — preview what will change to pick the right checkpoint.
- **Combine with Git branches and worktrees** for maximum safety: - **Use `/rollback` instead of `git reset`** when you want to undo agent-driven changes only.
- Keep each Hermes session in its own worktree/branch. - **Combine with Git worktrees** for maximum safety — keep each Hermes session in its own worktree/branch, with checkpoints as an extra layer.
- Let checkpoints act as an extra layer of protection on top.
For running multiple agents in parallel on the same repo without interfering with each other, see the dedicated guide on [Git worktrees](./git-worktrees.md).
For running multiple agents in parallel on the same repo, see the guide on [Git worktrees](./git-worktrees.md).

99
website/docs/user-guide/features/checkpoints.md
View file

@ -1,97 +1,30 @@
# Filesystem Checkpoints # Filesystem Checkpoints
Hermes can automatically snapshot your working directory before making file changes, giving you a safety net to roll back if something goes wrong. Hermes automatically snapshots your working directory before making file changes, giving you a safety net to roll back if something goes wrong. Checkpoints are **enabled by default**.
## How It Works ## Quick Reference
When enabled, Hermes takes a **one-time snapshot** at the start of each conversation turn before the first file-modifying operation (`write_file` or `patch`). This creates a point-in-time backup you can restore to at any time. | Command | Description |
|---------|-------------|
| `/rollback` | List all checkpoints with change stats |
| `/rollback <N>` | Restore to checkpoint N (also undoes last chat turn) |
| `/rollback diff <N>` | Preview diff between checkpoint N and current state |
| `/rollback <N> <file>` | Restore a single file from checkpoint N |
Under the hood, checkpoints use a **shadow git repository** stored at `~/.hermes/checkpoints/`. This is completely separate from your project's git — no `.git` directory is created in your project, and your own git history is never touched. ## What Triggers Checkpoints
## Enabling Checkpoints - **File tools** — `write_file` and `patch`
- **Destructive terminal commands** — `rm`, `mv`, `sed -i`, output redirects (`>`), `git reset`/`clean`
### Per-session (CLI flag) ## Configuration
```bash
hermes --checkpoints
```
### Permanently (config.yaml)
```yaml ```yaml
# ~/.hermes/config.yaml # ~/.hermes/config.yaml
checkpoints: checkpoints:
enabled: true enabled: true # default: true
max_snapshots: 50 # max checkpoints per directory (default: 50) max_snapshots: 50 # max checkpoints per directory
``` ```
## Rolling Back ## Learn More
Use the `/rollback` slash command: For the full guide — how shadow repos work, diff previews, file-level restore, conversation undo, safety guards, and best practices — see **[Checkpoints and /rollback](../checkpoints-and-rollback.md)**.
```
/rollback # List all available checkpoints
/rollback 1 # Restore to checkpoint #1 (most recent)
/rollback 3 # Restore to checkpoint #3 (further back)
/rollback abc1234 # Restore by git commit hash
```
Example output:
```
📸 Checkpoints for /home/user/project:
1. abc1234 2026-03-10 14:22 before write_file
2. def5678 2026-03-10 14:15 before patch
3. ghi9012 2026-03-10 14:08 before write_file
Use /rollback <number> to restore, e.g. /rollback 1
```
When you restore, Hermes automatically takes a **pre-rollback snapshot** first — so you can always undo your undo.
## What Gets Checkpointed
Checkpoints capture the entire working directory (the project root), excluding common large/sensitive patterns:
- `node_modules/`, `dist/`, `build/`
- `.env`, `.env.*`
- `__pycache__/`, `*.pyc`
- `.venv/`, `venv/`
- `.git/`
- `.DS_Store`, `*.log`
## Performance
Checkpoints are designed to be lightweight:
- **Once per turn** — only the first file operation triggers a snapshot, not every write
- **Skips large directories** — directories with >50,000 files are skipped automatically
- **Skips when nothing changed** — if no files were modified since the last checkpoint, no commit is created
- **Non-blocking** — if a checkpoint fails for any reason, the file operation proceeds normally
## How It Determines the Project Root
When you write to a file like `src/components/Button.tsx`, Hermes walks up the directory tree looking for project markers (`.git`, `pyproject.toml`, `package.json`, `Cargo.toml`, etc.) to find the project root. This ensures the entire project is checkpointed, not just the file's parent directory.
## Platforms
Checkpoints work on both:
- **CLI** — uses your current working directory
- **Gateway** (Telegram, Discord, etc.) — uses `MESSAGING_CWD`
The `/rollback` command is available on all platforms.
## FAQ
**Does this conflict with my project's git?**
No. Checkpoints use a completely separate shadow git repository via `GIT_DIR` environment variables. Your project's `.git/` is never touched.
**How much disk space do checkpoints use?**
Git is very efficient at storing diffs. For most projects, checkpoint data is negligible. Old checkpoints are pruned when `max_snapshots` is exceeded.
**Can I checkpoint without git installed?**
No — git must be available on your PATH. If it's not installed, checkpoints silently disable.
**Can I roll back across sessions?**
Yes! Checkpoints persist in `~/.hermes/checkpoints/` and survive across sessions. You can roll back to a checkpoint from yesterday.