Compare commits

..

7 Commits

Author SHA1 Message Date
Claude
c57e786c15 feat: Add Notification hook handler for formatting idle notifications
Format raw JSON IPC messages from workers/teammates into user-friendly
display instead of showing raw JSON to users.

Changes:
- Add notification.py hook handler to hookify plugin that formats
  idle_notification, status_update, and progress_update messages
- Update hookify hooks.json to include Notification event handler
- Add Pattern 11 documentation for formatting teammate idle notifications
- Add format-idle-notification.sh example script

Raw JSON input like:
  {"type":"idle_notification","from":"worker-1","timestamp":"..."}

Now displays as:
  ⏺ worker-1
    ⎿ Status is idle

Slack thread: https://anthropic.slack.com/archives/C07VBSHV7EV/p1765785226571409?thread_ts=1765776251.343939&cid=C07VBSHV7EV
2025-12-15 08:01:43 +00:00
GitHub Actions
eb87245010 chore: Update CHANGELOG.md 2025-12-13 00:59:55 +00:00
GitHub Actions
3680637065 chore: Update CHANGELOG.md 2025-12-12 23:31:50 +00:00
GitHub Actions
2192c86c20 chore: Update CHANGELOG.md 2025-12-12 01:29:45 +00:00
kashyap murali
dfd3494132 Merge pull request #13739 from anthropics/claude/slack-session-01GzKi42xM3SphuxeQ4De88U
Remove footer from code-review plugin output
2025-12-11 14:42:30 -08:00
Claude
e8cca9a7af Remove footer from code-review plugin output
Remove the "Generated with Claude Code" footer and feedback CTA
from the code review comment template as it adds noise without
providing value after the first viewing.
2025-12-11 22:40:32 +00:00
GitHub Actions
6358669884 chore: Update CHANGELOG.md 2025-12-11 19:07:31 +00:00
8 changed files with 299 additions and 87 deletions

View File

@@ -1,5 +1,32 @@
# Changelog
## 2.0.69
- Minor bugfixes
## 2.0.68
- Fixed IME (Input Method Editor) support for languages like Chinese, Japanese, and Korean by correctly positioning the composition window at the cursor
- Fixed a bug where disallowed MCP tools were visible to the model
- Fixed an issue where steering messages could be lost while a subagent is working
- Fixed Option+Arrow word navigation treating entire CJK (Chinese, Japanese, Korean) text sequences as a single word instead of navigating by word boundaries
- Improved plan mode exit UX: show simplified yes/no dialog when exiting with empty or missing plan instead of throwing an error
- Add support for enterprise managed settings. Contact your Anthropic account team to enable this feature.
## 2.0.67
- Thinking mode is now enabled by default for Opus 4.5
- Thinking mode configuration has moved to /config
- Added search functionality to `/permissions` command with `/` keyboard shortcut for filtering rules by tool name
- Show reason why autoupdater is disabled in `/doctor`
- Fixed false "Another process is currently updating Claude" error when running `claude update` while another instance is already on the latest version
- Fixed MCP servers from `.mcp.json` being stuck in pending state when running in non-interactive mode (`-p` flag or piped input)
- Fixed scroll position resetting after deleting a permission rule in `/permissions`
- Fixed word deletion (opt+delete) and word navigation (opt+arrow) not working correctly with non-Latin text such as Cyrillic, Greek, Arabic, Hebrew, Thai, and Chinese
- Fixed `claude install --force` not bypassing stale lock files
- Fixed consecutive @~/ file references in CLAUDE.md being incorrectly parsed due to markdown strikethrough interference
- Windows: Fixed plugin MCP servers failing due to colons in log directory paths
## 2.0.65
- Added ability to switch models while writing a prompt using alt+p (linux, windows), option+p (macos).
@@ -23,6 +50,7 @@
- VSCode: Added copy-to-clipboard button on code blocks and bash tool inputs
- VSCode: Fixed extension not working on Windows ARM64 by falling back to x64 binary via emulation
- Bedrock: Improve efficiency of token counting
- Bedrock: Add support for `aws login` AWS Management Console credentials
- Unshipped AgentOutputTool and BashOutputTool, in favor of a new unified TaskOutputTool
## 2.0.62

View File

@@ -93,11 +93,6 @@ Found 3 issues:
<link to file and line with full sha1 + line range for context>
🤖 Generated with [Claude Code](https://claude.ai/code)
<sub>- If this code review was useful, please react with 👍. Otherwise, react with 👎.</sub>
---
- Or, if you found no issues:
@@ -108,8 +103,6 @@ Found 3 issues:
No issues found. Checked for bugs and CLAUDE.md compliance.
🤖 Generated with [Claude Code](https://claude.ai/code)
---
- When linking to code, follow the following format precisely, otherwise the Markdown preview won't render correctly: https://github.com/anthropics/claude-code/blob/c21d3c10bc8e898b7ac1a2d745bdc9bc4e423afe/package.json#L10-L15

View File

@@ -44,6 +44,17 @@
}
]
}
],
"Notification": [
{
"hooks": [
{
"type": "command",
"command": "python3 ${CLAUDE_PLUGIN_ROOT}/hooks/notification.py",
"timeout": 10
}
]
}
]
}
}

View File

@@ -0,0 +1,143 @@
#!/usr/bin/env python3
"""Notification hook executor for hookify plugin.
This script is called by Claude Code when notifications are sent.
It formats teammate idle notifications and other IPC messages for display.
"""
import os
import sys
import json
from datetime import datetime
# CRITICAL: Add plugin root to Python path for imports
PLUGIN_ROOT = os.environ.get('CLAUDE_PLUGIN_ROOT')
if PLUGIN_ROOT:
parent_dir = os.path.dirname(PLUGIN_ROOT)
if parent_dir not in sys.path:
sys.path.insert(0, parent_dir)
if PLUGIN_ROOT not in sys.path:
sys.path.insert(0, PLUGIN_ROOT)
def format_idle_notification(data: dict) -> str:
"""Format an idle notification for display.
Args:
data: The notification data containing type, from, timestamp, etc.
Returns:
Formatted string for display
"""
worker_name = data.get('from', 'worker')
timestamp = data.get('timestamp', '')
# Format timestamp if present
time_str = ''
if timestamp:
try:
dt = datetime.fromisoformat(timestamp.replace('Z', '+00:00'))
time_str = dt.strftime('%H:%M:%S')
except (ValueError, AttributeError):
time_str = ''
# Build the formatted output using the suggested format
lines = [f"{worker_name}"]
if time_str:
lines.append(f" ⎿ Status is idle ({time_str})")
else:
lines.append(" ⎿ Status is idle")
return '\n'.join(lines)
def format_notification(notification_content: str) -> dict:
"""Parse and format a notification message.
Args:
notification_content: Raw notification content (may be JSON or plain text)
Returns:
Dict with formatted systemMessage
"""
# Try to parse as JSON first
try:
data = json.loads(notification_content)
# Check if this is an idle notification
if isinstance(data, dict) and data.get('type') == 'idle_notification':
formatted = format_idle_notification(data)
return {"systemMessage": formatted}
# Handle other notification types
notification_type = data.get('type', '') if isinstance(data, dict) else ''
if notification_type == 'status_update':
worker = data.get('from', 'worker')
status = data.get('status', 'unknown')
return {"systemMessage": f"{worker}\n ⎿ Status: {status}"}
if notification_type == 'progress_update':
worker = data.get('from', 'worker')
progress = data.get('progress', '')
return {"systemMessage": f"{worker}\n{progress}"}
# For unknown JSON types, still try to format nicely
if isinstance(data, dict) and 'from' in data:
worker = data.get('from', 'worker')
msg = data.get('message', data.get('status', 'update'))
return {"systemMessage": f"{worker}\n{msg}"}
except (json.JSONDecodeError, TypeError):
# Not JSON, return as-is
pass
return {}
def main():
"""Main entry point for Notification hook."""
try:
# Read input from stdin
input_data = json.load(sys.stdin)
# Get notification content
notification = input_data.get('notification', '')
# Also check for raw notification data in the input
if not notification and input_data.get('type') == 'idle_notification':
# The input itself is an idle notification
formatted = format_idle_notification(input_data)
result = {"systemMessage": formatted}
elif notification:
# Format the notification content
result = format_notification(notification)
else:
# Check if the input looks like an IPC message
if input_data.get('type') in ['idle_notification', 'status_update', 'progress_update']:
if input_data.get('type') == 'idle_notification':
formatted = format_idle_notification(input_data)
result = {"systemMessage": formatted}
else:
worker = input_data.get('from', 'worker')
status = input_data.get('status', input_data.get('type', 'update'))
result = {"systemMessage": f"{worker}\n{status}"}
else:
result = {}
# Always output JSON
print(json.dumps(result), file=sys.stdout)
except Exception as e:
error_output = {
"systemMessage": f"Notification format error: {str(e)}"
}
print(json.dumps(error_output), file=sys.stdout)
finally:
# ALWAYS exit 0
sys.exit(0)
if __name__ == '__main__':
main()

View File

@@ -42,7 +42,6 @@ assistant: "[How assistant should respond and use this agent]"
model: inherit
color: blue
tools: ["Read", "Write", "Grep"]
skills: skill-name-1, skill-name-2
---
You are [agent role description]...
@@ -160,35 +159,6 @@ tools: ["Read", "Write", "Grep", "Bash"]
- Testing: `["Read", "Bash", "Grep"]`
- Full access: Omit field or use `["*"]`
### skills (optional)
Declare skills to auto-load when this agent is invoked.
**Format:** Comma-separated list of skill names
```yaml
skills: database-migration, postgres-ops
```
**Purpose:** Ensures specific skills are always available to the agent, regardless of context matching. This is especially useful for:
- Skills that should persist across context compaction
- Specialized agents that always need certain domain knowledge
- Ensuring consistent agent behavior with required skills
**Example:**
```yaml
---
name: db-admin
description: Use this agent for database administration tasks...
model: inherit
color: cyan
tools: ["Bash", "Read", "Write"]
skills: database-migration, sql-optimization
---
```
**Best practice:** Only declare skills essential to the agent's core function. Let context-triggered skills load naturally for optional capabilities.
## System Prompt Design
The markdown body becomes the agent's system prompt. Write in second person, addressing the agent directly.
@@ -385,7 +355,6 @@ Output: [What to provide]
| model | Yes | inherit/sonnet/opus/haiku | inherit |
| color | Yes | Color name | blue |
| tools | No | Array of tool names | ["Read", "Grep"] |
| skills | No | Comma-separated names | skill-a, skill-b |
### Best Practices

View File

@@ -12,7 +12,6 @@ description: Brief description
allowed-tools: Read, Write
model: sonnet
argument-hint: [arg1] [arg2]
skills: skill-a, skill-b
---
Command prompt content here...
@@ -322,51 +321,6 @@ disable-model-invocation: true
- Document why in command comments
- Consider if command should exist if always manual
### skills
**Type:** String (comma-separated list)
**Required:** No
**Default:** None
**Purpose:** Declare skills to auto-load when this command executes. Ensures specific skills are always available regardless of context matching.
**Examples:**
```yaml
skills: database-migration, sql-optimization
```
**When to use:**
1. **Commands requiring domain knowledge:** Ensure relevant skills load
```yaml
---
description: Run database migration
skills: database-migration, postgres-ops
---
```
2. **Skills that should persist across compaction:** Force-load skills that might otherwise be lost
```yaml
---
description: Complex multi-step workflow
skills: workflow-skill, validation-skill
---
```
3. **Specialized commands:** Commands that always need specific expertise
```yaml
---
description: Generate API documentation
skills: api-documentation, openapi-spec
---
```
**Best practices:**
- Only declare skills essential to the command's function
- Use skill names exactly as defined in SKILL.md frontmatter
- Keep the list focused (2-4 skills max)
- Let context-triggered skills load naturally for optional capabilities
## Complete Examples
### Minimal Command
@@ -497,7 +451,6 @@ Before committing command:
- [ ] model is valid value if specified
- [ ] argument-hint matches positional arguments
- [ ] disable-model-invocation used appropriately
- [ ] skills references valid skill names if specified
## Best Practices Summary
@@ -507,5 +460,4 @@ Before committing command:
4. **Choose right model:** Use haiku for speed, opus for complexity
5. **Manual-only sparingly:** Only use disable-model-invocation when necessary
6. **Clear descriptions:** Make commands discoverable in `/help`
7. **Declare essential skills:** Use skills field for domain knowledge that must persist
8. **Test thoroughly:** Verify frontmatter works as expected
7. **Test thoroughly:** Verify frontmatter works as expected

View File

@@ -0,0 +1,50 @@
#!/bin/bash
# Example: Format teammate idle notification
#
# This script demonstrates how to format raw JSON idle notifications
# into user-friendly display format.
#
# Usage: echo '{"type":"idle_notification","from":"worker-1","timestamp":"..."}' | ./format-idle-notification.sh
set -euo pipefail
# Read JSON from stdin
input=$(cat)
# Parse notification type
notification_type=$(echo "$input" | jq -r '.type // empty' 2>/dev/null || echo "")
if [[ "$notification_type" == "idle_notification" ]]; then
# Extract fields
worker_name=$(echo "$input" | jq -r '.from // "worker"')
timestamp=$(echo "$input" | jq -r '.timestamp // empty')
# Format timestamp if present
time_str=""
if [[ -n "$timestamp" ]]; then
# Try to format the timestamp
time_str=$(date -d "$timestamp" '+%H:%M:%S' 2>/dev/null || echo "")
fi
# Output formatted notification using recommended format:
# ⏺ worker-1
# ⎿ Status is idle
echo "$worker_name"
if [[ -n "$time_str" ]]; then
echo " ⎿ Status is idle ($time_str)"
else
echo " ⎿ Status is idle"
fi
# Output JSON for hook system
if [[ -n "$time_str" ]]; then
jq -n --arg msg "$worker_name\n ⎿ Status is idle ($time_str)" \
'{"systemMessage": $msg}'
else
jq -n --arg msg "$worker_name\n ⎿ Status is idle" \
'{"systemMessage": $msg}'
fi
else
# Not an idle notification, pass through
echo "$input"
fi

View File

@@ -344,3 +344,69 @@ fi
- Per-project settings
- Team-specific rules
- Dynamic validation criteria
## Pattern 11: Format Teammate Idle Notifications
Format raw JSON IPC messages from workers/teammates into user-friendly display:
```json
{
"Notification": [
{
"matcher": "*",
"hooks": [
{
"type": "command",
"command": "python3 ${CLAUDE_PLUGIN_ROOT}/hooks/notification.py",
"timeout": 10
}
]
}
]
}
```
**Example script (format-idle-notification.py):**
```python
#!/usr/bin/env python3
import sys
import json
def format_idle_notification(data):
"""Format idle notification for display."""
worker_name = data.get('from', 'worker')
# Output format:
# ⏺ worker-1
# ⎿ Status is idle
return f"{worker_name}\n ⎿ Status is idle"
def main():
input_data = json.load(sys.stdin)
# Check for idle notification
if input_data.get('type') == 'idle_notification':
formatted = format_idle_notification(input_data)
print(json.dumps({"systemMessage": formatted}))
else:
print(json.dumps({}))
if __name__ == '__main__':
main()
```
**Input (raw JSON IPC message):**
```json
{"type": "idle_notification", "from": "worker-1", "timestamp": "2025-12-15T05:22:40.320Z"}
```
**Output (formatted for display):**
```
⏺ worker-1
⎿ Status is idle
```
**Use for:**
- Formatting teammate/worker status messages
- Converting internal IPC messages to user-friendly display
- Multi-agent swarm coordination UI
- Any notification that shouldn't show raw JSON to users