Compare commits
3 Commits
perf/lazy-
...
fix/741
| Author | SHA1 | Date | |
|---|---|---|---|
| fe619a1774 | |||
| 8194e9c651 | |||
|
|
95d11dfd8e |
223
agent/session_model_metadata.py
Normal file
223
agent/session_model_metadata.py
Normal file
@@ -0,0 +1,223 @@
|
||||
"""
|
||||
Session Model Metadata — Persist model context info per session
|
||||
|
||||
When a session switches models mid-conversation, context length and
|
||||
token budget need to be updated to prevent silent truncation.
|
||||
|
||||
Issue: #741
|
||||
"""
|
||||
|
||||
import json
|
||||
import logging
|
||||
from dataclasses import dataclass, asdict
|
||||
from pathlib import Path
|
||||
from typing import Any, Dict, Optional
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
HERMES_HOME = Path.home() / ".hermes"
|
||||
|
||||
|
||||
# Common model context lengths (tokens)
|
||||
KNOWN_CONTEXT_LENGTHS = {
|
||||
# Anthropic
|
||||
"claude-opus-4-6": 200000,
|
||||
"claude-sonnet-4": 200000,
|
||||
"claude-3.5-sonnet": 200000,
|
||||
"claude-3-haiku": 200000,
|
||||
|
||||
# OpenAI
|
||||
"gpt-4o": 128000,
|
||||
"gpt-4-turbo": 128000,
|
||||
"gpt-4": 8192,
|
||||
"gpt-3.5-turbo": 16385,
|
||||
|
||||
# Nous / open models
|
||||
"hermes-3-llama-3.1-405b": 131072,
|
||||
"hermes-3-llama-3.1-70b": 131072,
|
||||
"deepseek-r1": 131072,
|
||||
"deepseek-v3": 131072,
|
||||
|
||||
# Local
|
||||
"llama-3.1-8b": 131072,
|
||||
"llama-3.1-70b": 131072,
|
||||
"qwen-2.5-72b": 131072,
|
||||
|
||||
# Xiaomi
|
||||
"mimo-v2-pro": 131072,
|
||||
"mimo-v2-flash": 131072,
|
||||
|
||||
# Defaults
|
||||
"default": 4096,
|
||||
}
|
||||
|
||||
# Reserve tokens for system prompt, response, and overhead
|
||||
TOKEN_RESERVE = 2000
|
||||
|
||||
|
||||
@dataclass
|
||||
class ModelMetadata:
|
||||
"""Metadata for a model in a session."""
|
||||
model: str
|
||||
provider: str
|
||||
context_length: int
|
||||
available_for_input: int # context_length - reserve
|
||||
current_tokens_used: int = 0
|
||||
|
||||
@property
|
||||
def remaining_tokens(self) -> int:
|
||||
"""Tokens remaining for new input."""
|
||||
return max(0, self.available_for_input - self.current_tokens_used)
|
||||
|
||||
@property
|
||||
def utilization_pct(self) -> float:
|
||||
"""Percentage of context used."""
|
||||
if self.available_for_input == 0:
|
||||
return 0.0
|
||||
return (self.current_tokens_used / self.available_for_input) * 100
|
||||
|
||||
def to_dict(self) -> Dict[str, Any]:
|
||||
return asdict(self)
|
||||
|
||||
|
||||
def get_context_length(model: str) -> int:
|
||||
"""Get context length for a model."""
|
||||
model_lower = model.lower()
|
||||
|
||||
# Check exact match
|
||||
if model_lower in KNOWN_CONTEXT_LENGTHS:
|
||||
return KNOWN_CONTEXT_LENGTHS[model_lower]
|
||||
|
||||
# Check partial match
|
||||
for key, length in KNOWN_CONTEXT_LENGTHS.items():
|
||||
if key in model_lower:
|
||||
return length
|
||||
|
||||
return KNOWN_CONTEXT_LENGTHS["default"]
|
||||
|
||||
|
||||
def create_metadata(model: str, provider: str = "", current_tokens: int = 0) -> ModelMetadata:
|
||||
"""Create model metadata."""
|
||||
context_length = get_context_length(model)
|
||||
available = max(0, context_length - TOKEN_RESERVE)
|
||||
|
||||
return ModelMetadata(
|
||||
model=model,
|
||||
provider=provider,
|
||||
context_length=context_length,
|
||||
available_for_input=available,
|
||||
current_tokens_used=current_tokens
|
||||
)
|
||||
|
||||
|
||||
def check_model_switch(
|
||||
old_model: str,
|
||||
new_model: str,
|
||||
current_tokens: int
|
||||
) -> Dict[str, Any]:
|
||||
"""
|
||||
Check impact of switching models mid-session.
|
||||
|
||||
Returns:
|
||||
Dict with switch analysis including warnings
|
||||
"""
|
||||
old_ctx = get_context_length(old_model)
|
||||
new_ctx = get_context_length(new_model)
|
||||
|
||||
old_available = old_ctx - TOKEN_RESERVE
|
||||
new_available = new_ctx - TOKEN_RESERVE
|
||||
|
||||
result = {
|
||||
"old_model": old_model,
|
||||
"new_model": new_model,
|
||||
"old_context": old_ctx,
|
||||
"new_context": new_ctx,
|
||||
"current_tokens": current_tokens,
|
||||
"fits_in_new": current_tokens <= new_available,
|
||||
"truncation_needed": max(0, current_tokens - new_available),
|
||||
"warning": None,
|
||||
}
|
||||
|
||||
if not result["fits_in_new"]:
|
||||
result["warning"] = (
|
||||
f"Switching to {new_model} ({new_ctx:,} ctx) with {current_tokens:,} tokens "
|
||||
f"will truncate {result['truncation_needed']:,} tokens of history. "
|
||||
f"Consider starting a new session."
|
||||
)
|
||||
|
||||
if new_ctx < old_ctx:
|
||||
reduction = old_ctx - new_ctx
|
||||
result["warning"] = (
|
||||
f"New model has {reduction:,} fewer tokens of context. "
|
||||
f"({old_ctx:,} -> {new_ctx:,})"
|
||||
)
|
||||
|
||||
return result
|
||||
|
||||
|
||||
class SessionModelTracker:
|
||||
"""Track model metadata for a session."""
|
||||
|
||||
def __init__(self, session_id: str):
|
||||
self.session_id = session_id
|
||||
self.metadata: Optional[ModelMetadata] = None
|
||||
self.history: list = [] # Model switch history
|
||||
|
||||
def set_model(self, model: str, provider: str = "", tokens_used: int = 0):
|
||||
"""Set the current model for the session."""
|
||||
old_model = self.metadata.model if self.metadata else None
|
||||
|
||||
self.metadata = create_metadata(model, provider, tokens_used)
|
||||
|
||||
# Record switch in history
|
||||
if old_model and old_model != model:
|
||||
self.history.append({
|
||||
"from": old_model,
|
||||
"to": model,
|
||||
"tokens_at_switch": tokens_used,
|
||||
"context_length": self.metadata.context_length
|
||||
})
|
||||
|
||||
logger.info(
|
||||
"Session %s: model=%s context=%d available=%d",
|
||||
self.session_id[:12], model,
|
||||
self.metadata.context_length,
|
||||
self.metadata.available_for_input
|
||||
)
|
||||
|
||||
def update_tokens(self, tokens: int):
|
||||
"""Update current token usage."""
|
||||
if self.metadata:
|
||||
self.metadata.current_tokens_used = tokens
|
||||
|
||||
def get_remaining(self) -> int:
|
||||
"""Get remaining tokens."""
|
||||
if not self.metadata:
|
||||
return 0
|
||||
return self.metadata.remaining_tokens
|
||||
|
||||
def can_fit(self, additional_tokens: int) -> bool:
|
||||
"""Check if additional tokens fit in context."""
|
||||
if not self.metadata:
|
||||
return False
|
||||
return self.metadata.remaining_tokens >= additional_tokens
|
||||
|
||||
def get_warning(self) -> Optional[str]:
|
||||
"""Get warning if context is running low."""
|
||||
if not self.metadata:
|
||||
return None
|
||||
|
||||
util = self.metadata.utilization_pct
|
||||
if util > 90:
|
||||
return f"Context {util:.0f}% full. Consider compression or new session."
|
||||
if util > 75:
|
||||
return f"Context {util:.0f}% full."
|
||||
return None
|
||||
|
||||
def to_dict(self) -> Dict[str, Any]:
|
||||
"""Export state."""
|
||||
return {
|
||||
"session_id": self.session_id,
|
||||
"metadata": self.metadata.to_dict() if self.metadata else None,
|
||||
"history": self.history
|
||||
}
|
||||
160
hermes-already-has-routines.md
Normal file
160
hermes-already-has-routines.md
Normal file
@@ -0,0 +1,160 @@
|
||||
# Hermes Agent Has Had "Routines" Since March
|
||||
|
||||
Anthropic just announced [Claude Code Routines](https://claude.com/blog/introducing-routines-in-claude-code) — scheduled tasks, GitHub event triggers, and API-triggered agent runs. Bundled prompt + repo + connectors, running on their infrastructure.
|
||||
|
||||
It's a good feature. We shipped it two months ago.
|
||||
|
||||
---
|
||||
|
||||
## The Three Trigger Types — Side by Side
|
||||
|
||||
Claude Code Routines offers three ways to trigger an automation:
|
||||
|
||||
**1. Scheduled (cron)**
|
||||
> "Every night at 2am: pull the top bug from Linear, attempt a fix, and open a draft PR."
|
||||
|
||||
Hermes equivalent — works today:
|
||||
```bash
|
||||
hermes cron create "0 2 * * *" \
|
||||
"Pull the top bug from the issue tracker, attempt a fix, and open a draft PR." \
|
||||
--name "Nightly bug fix" \
|
||||
--deliver telegram
|
||||
```
|
||||
|
||||
**2. GitHub Events (webhook)**
|
||||
> "Flag PRs that touch the /auth-provider module and post to #auth-changes."
|
||||
|
||||
Hermes equivalent — works today:
|
||||
```bash
|
||||
hermes webhook subscribe auth-watch \
|
||||
--events "pull_request" \
|
||||
--prompt "PR #{pull_request.number}: {pull_request.title} by {pull_request.user.login}. Check if it touches the auth-provider module. If yes, summarize the changes." \
|
||||
--deliver slack
|
||||
```
|
||||
|
||||
**3. API Triggers**
|
||||
> "Read the alert payload, find the owning service, post a triage summary to #oncall."
|
||||
|
||||
Hermes equivalent — works today:
|
||||
```bash
|
||||
hermes webhook subscribe alert-triage \
|
||||
--prompt "Alert: {alert.name} — Severity: {alert.severity}. Find the owning service, investigate, and post a triage summary with proposed first steps." \
|
||||
--deliver slack
|
||||
```
|
||||
|
||||
Every use case in their blog post — backlog triage, docs drift, deploy verification, alert correlation, library porting, bespoke PR review — has a working Hermes implementation. No new features needed. It's been shipping since March 2026.
|
||||
|
||||
---
|
||||
|
||||
## What's Different
|
||||
|
||||
| | Claude Code Routines | Hermes Agent |
|
||||
|---|---|---|
|
||||
| **Scheduled tasks** | ✅ Schedule-based | ✅ Any cron expression + human-readable intervals |
|
||||
| **GitHub triggers** | ✅ PR, issue, push events | ✅ Any GitHub event via webhook subscriptions |
|
||||
| **API triggers** | ✅ POST to unique endpoint | ✅ POST to webhook routes with HMAC auth |
|
||||
| **MCP connectors** | ✅ Native connectors | ✅ Full MCP client support |
|
||||
| **Script pre-processing** | ❌ | ✅ Python scripts run before agent, inject context |
|
||||
| **Skill chaining** | ❌ | ✅ Load multiple skills per automation |
|
||||
| **Daily limit** | 5-25 runs/day | **Unlimited** |
|
||||
| **Model choice** | Claude only | **Any model** — Claude, GPT, Gemini, DeepSeek, Qwen, local |
|
||||
| **Delivery targets** | GitHub comments | Telegram, Discord, Slack, SMS, email, GitHub comments, webhooks, local files |
|
||||
| **Infrastructure** | Anthropic's servers | **Your infrastructure** — VPS, home server, laptop |
|
||||
| **Data residency** | Anthropic's cloud | **Your machines** |
|
||||
| **Cost** | Pro/Max/Team/Enterprise subscription | Your API key, your rates |
|
||||
| **Open source** | No | **Yes** — MIT license |
|
||||
|
||||
---
|
||||
|
||||
## Things Hermes Does That Routines Can't
|
||||
|
||||
### Script Injection
|
||||
|
||||
Run a Python script *before* the agent. The script's stdout becomes context. The script handles mechanical work (fetching, diffing, computing); the agent handles reasoning.
|
||||
|
||||
```bash
|
||||
hermes cron create "every 1h" \
|
||||
"If CHANGE DETECTED, summarize what changed. If NO_CHANGE, respond with [SILENT]." \
|
||||
--script ~/.hermes/scripts/watch-site.py \
|
||||
--name "Pricing monitor" \
|
||||
--deliver telegram
|
||||
```
|
||||
|
||||
The `[SILENT]` pattern means you only get notified when something actually happens. No spam.
|
||||
|
||||
### Multi-Skill Workflows
|
||||
|
||||
Chain specialized skills together. Each skill teaches the agent a specific capability, and the prompt ties them together.
|
||||
|
||||
```bash
|
||||
hermes cron create "0 8 * * *" \
|
||||
"Search arXiv for papers on language model reasoning. Save the top 3 as Obsidian notes." \
|
||||
--skills "arxiv,obsidian" \
|
||||
--name "Paper digest"
|
||||
```
|
||||
|
||||
### Deliver Anywhere
|
||||
|
||||
One automation, any destination:
|
||||
|
||||
```bash
|
||||
--deliver telegram # Telegram home channel
|
||||
--deliver discord # Discord home channel
|
||||
--deliver slack # Slack channel
|
||||
--deliver sms:+15551234567 # Text message
|
||||
--deliver telegram:-1001234567890:42 # Specific Telegram forum topic
|
||||
--deliver local # Save to file, no notification
|
||||
```
|
||||
|
||||
### Model-Agnostic
|
||||
|
||||
Your nightly triage can run on Claude. Your deploy verification can run on GPT. Your cost-sensitive monitors can run on DeepSeek or a local model. Same automation system, any backend.
|
||||
|
||||
---
|
||||
|
||||
## The Limits Tell the Story
|
||||
|
||||
Claude Code Routines: **5 routines per day** on Pro. **25 on Enterprise.** That's their ceiling.
|
||||
|
||||
Hermes has no daily limit. Run 500 automations a day if you want. The only constraint is your API budget, and you choose which models to use for which tasks.
|
||||
|
||||
A nightly backlog triage on Sonnet costs roughly $0.02-0.05. A monitoring check on DeepSeek costs fractions of a cent. You control the economics.
|
||||
|
||||
---
|
||||
|
||||
## Get Started
|
||||
|
||||
Hermes Agent is open source and free. The automation infrastructure — cron scheduler, webhook platform, skill system, multi-platform delivery — is built in.
|
||||
|
||||
```bash
|
||||
pip install hermes-agent
|
||||
hermes setup
|
||||
```
|
||||
|
||||
Set up a scheduled task in 30 seconds:
|
||||
```bash
|
||||
hermes cron create "0 9 * * 1" \
|
||||
"Generate a weekly AI news digest. Search the web for major announcements, trending repos, and notable papers. Keep it under 500 words with links." \
|
||||
--name "Weekly digest" \
|
||||
--deliver telegram
|
||||
```
|
||||
|
||||
Set up a GitHub webhook in 60 seconds:
|
||||
```bash
|
||||
hermes gateway setup # enable webhooks
|
||||
hermes webhook subscribe pr-review \
|
||||
--events "pull_request" \
|
||||
--prompt "Review PR #{pull_request.number}: {pull_request.title}" \
|
||||
--skills "github-code-review" \
|
||||
--deliver github_comment
|
||||
```
|
||||
|
||||
Full automation templates gallery: [hermes-agent.nousresearch.com/docs/guides/automation-templates](https://hermes-agent.nousresearch.com/docs/guides/automation-templates)
|
||||
|
||||
Documentation: [hermes-agent.nousresearch.com](https://hermes-agent.nousresearch.com)
|
||||
|
||||
GitHub: [github.com/NousResearch/hermes-agent](https://github.com/NousResearch/hermes-agent)
|
||||
|
||||
---
|
||||
|
||||
*Hermes Agent is built by [Nous Research](https://nousresearch.com). Open source, model-agnostic, runs on your infrastructure.*
|
||||
105
tests/test_session_model_metadata.py
Normal file
105
tests/test_session_model_metadata.py
Normal file
@@ -0,0 +1,105 @@
|
||||
"""
|
||||
Tests for session model metadata
|
||||
|
||||
Issue: #741
|
||||
"""
|
||||
|
||||
import unittest
|
||||
from agent.session_model_metadata import (
|
||||
get_context_length,
|
||||
create_metadata,
|
||||
check_model_switch,
|
||||
SessionModelTracker,
|
||||
)
|
||||
|
||||
|
||||
class TestContextLength(unittest.TestCase):
|
||||
|
||||
def test_known_model(self):
|
||||
ctx = get_context_length("claude-opus-4-6")
|
||||
self.assertEqual(ctx, 200000)
|
||||
|
||||
def test_partial_match(self):
|
||||
ctx = get_context_length("anthropic/claude-sonnet-4")
|
||||
self.assertEqual(ctx, 200000)
|
||||
|
||||
def test_unknown_model(self):
|
||||
ctx = get_context_length("unknown-model-xyz")
|
||||
self.assertEqual(ctx, 4096)
|
||||
|
||||
|
||||
class TestModelMetadata(unittest.TestCase):
|
||||
|
||||
def test_create(self):
|
||||
meta = create_metadata("gpt-4o", "openai", 1000)
|
||||
self.assertEqual(meta.context_length, 128000)
|
||||
self.assertEqual(meta.current_tokens_used, 1000)
|
||||
self.assertGreater(meta.remaining_tokens, 0)
|
||||
|
||||
def test_utilization(self):
|
||||
meta = create_metadata("gpt-4o", "openai", 64000)
|
||||
self.assertAlmostEqual(meta.utilization_pct, 50.0, delta=1)
|
||||
|
||||
|
||||
class TestModelSwitch(unittest.TestCase):
|
||||
|
||||
def test_safe_switch(self):
|
||||
result = check_model_switch("gpt-3.5-turbo", "gpt-4o", 5000)
|
||||
self.assertTrue(result["fits_in_new"])
|
||||
self.assertIsNone(result["warning"])
|
||||
|
||||
def test_truncation_warning(self):
|
||||
result = check_model_switch("gpt-4o", "gpt-3.5-turbo", 20000)
|
||||
self.assertFalse(result["fits_in_new"])
|
||||
self.assertIsNotNone(result["warning"])
|
||||
self.assertIn("truncate", result["warning"].lower())
|
||||
|
||||
def test_downgrade_warning(self):
|
||||
result = check_model_switch("claude-opus-4-6", "gpt-4", 5000)
|
||||
self.assertIsNotNone(result["warning"])
|
||||
|
||||
|
||||
class TestSessionModelTracker(unittest.TestCase):
|
||||
|
||||
def test_set_model(self):
|
||||
tracker = SessionModelTracker("test")
|
||||
tracker.set_model("gpt-4o", "openai")
|
||||
self.assertEqual(tracker.metadata.model, "gpt-4o")
|
||||
|
||||
def test_update_tokens(self):
|
||||
tracker = SessionModelTracker("test")
|
||||
tracker.set_model("gpt-4o")
|
||||
tracker.update_tokens(5000)
|
||||
self.assertEqual(tracker.metadata.current_tokens_used, 5000)
|
||||
|
||||
def test_remaining(self):
|
||||
tracker = SessionModelTracker("test")
|
||||
tracker.set_model("gpt-4o")
|
||||
tracker.update_tokens(10000)
|
||||
self.assertGreater(tracker.get_remaining(), 0)
|
||||
|
||||
def test_can_fit(self):
|
||||
tracker = SessionModelTracker("test")
|
||||
tracker.set_model("gpt-4o")
|
||||
tracker.update_tokens(10000)
|
||||
self.assertTrue(tracker.can_fit(5000))
|
||||
self.assertFalse(tracker.can_fit(200000))
|
||||
|
||||
def test_warning_low_context(self):
|
||||
tracker = SessionModelTracker("test")
|
||||
tracker.set_model("gpt-4o")
|
||||
tracker.update_tokens(115000) # ~90% used
|
||||
warning = tracker.get_warning()
|
||||
self.assertIsNotNone(warning)
|
||||
|
||||
def test_model_switch_history(self):
|
||||
tracker = SessionModelTracker("test")
|
||||
tracker.set_model("gpt-4o", "openai")
|
||||
tracker.update_tokens(5000)
|
||||
tracker.set_model("claude-opus-4-6", "anthropic")
|
||||
self.assertEqual(len(tracker.history), 1)
|
||||
self.assertEqual(tracker.history[0]["from"], "gpt-4o")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
593
website/docs/guides/automation-templates.md
Normal file
593
website/docs/guides/automation-templates.md
Normal file
@@ -0,0 +1,593 @@
|
||||
---
|
||||
sidebar_position: 15
|
||||
title: "Automation Templates"
|
||||
description: "Ready-to-use automation recipes — scheduled tasks, GitHub event triggers, API webhooks, and multi-skill workflows"
|
||||
---
|
||||
|
||||
# Automation Templates
|
||||
|
||||
Copy-paste recipes for common automation patterns. Each template uses Hermes's built-in [cron scheduler](/docs/user-guide/features/cron) for time-based triggers and [webhook platform](/docs/user-guide/messaging/webhooks) for event-driven triggers.
|
||||
|
||||
Every template works with **any model** — not locked to a single provider.
|
||||
|
||||
:::tip Three Trigger Types
|
||||
| Trigger | How | Tool |
|
||||
|---------|-----|------|
|
||||
| **Schedule** | Runs on a cadence (hourly, nightly, weekly) | `cronjob` tool or `/cron` slash command |
|
||||
| **GitHub Event** | Fires on PR opens, pushes, issues, CI results | Webhook platform (`hermes webhook subscribe`) |
|
||||
| **API Call** | External service POSTs JSON to your endpoint | Webhook platform (config.yaml routes or `hermes webhook subscribe`) |
|
||||
|
||||
All three support delivery to Telegram, Discord, Slack, SMS, email, GitHub comments, or local files.
|
||||
:::
|
||||
|
||||
---
|
||||
|
||||
## Development Workflow
|
||||
|
||||
### Nightly Backlog Triage
|
||||
|
||||
Label, prioritize, and summarize new issues every night. Delivers a digest to your team channel.
|
||||
|
||||
**Trigger:** Schedule (nightly)
|
||||
|
||||
```bash
|
||||
hermes cron create "0 2 * * *" \
|
||||
"You are a project manager triaging the NousResearch/hermes-agent GitHub repo.
|
||||
|
||||
1. Run: gh issue list --repo NousResearch/hermes-agent --state open --json number,title,labels,author,createdAt --limit 30
|
||||
2. Identify issues opened in the last 24 hours
|
||||
3. For each new issue:
|
||||
- Suggest a priority label (P0-critical, P1-high, P2-medium, P3-low)
|
||||
- Suggest a category label (bug, feature, docs, security)
|
||||
- Write a one-line triage note
|
||||
4. Summarize: total open issues, new today, breakdown by priority
|
||||
|
||||
Format as a clean digest. If no new issues, respond with [SILENT]." \
|
||||
--name "Nightly backlog triage" \
|
||||
--deliver telegram
|
||||
```
|
||||
|
||||
### Automatic PR Code Review
|
||||
|
||||
Review every pull request automatically when it's opened. Posts a review comment directly on the PR.
|
||||
|
||||
**Trigger:** GitHub webhook
|
||||
|
||||
**Option A — Dynamic subscription (CLI):**
|
||||
|
||||
```bash
|
||||
hermes webhook subscribe github-pr-review \
|
||||
--events "pull_request" \
|
||||
--prompt "Review this pull request:
|
||||
Repository: {repository.full_name}
|
||||
PR #{pull_request.number}: {pull_request.title}
|
||||
Author: {pull_request.user.login}
|
||||
Action: {action}
|
||||
Diff URL: {pull_request.diff_url}
|
||||
|
||||
Fetch the diff with: curl -sL {pull_request.diff_url}
|
||||
|
||||
Review for:
|
||||
- Security issues (injection, auth bypass, secrets in code)
|
||||
- Performance concerns (N+1 queries, unbounded loops, memory leaks)
|
||||
- Code quality (naming, duplication, error handling)
|
||||
- Missing tests for new behavior
|
||||
|
||||
Post a concise review. If the PR is a trivial docs/typo change, say so briefly." \
|
||||
--skills "github-code-review" \
|
||||
--deliver github_comment
|
||||
```
|
||||
|
||||
**Option B — Static route (config.yaml):**
|
||||
|
||||
```yaml
|
||||
platforms:
|
||||
webhook:
|
||||
enabled: true
|
||||
extra:
|
||||
port: 8644
|
||||
secret: "your-global-secret"
|
||||
routes:
|
||||
github-pr-review:
|
||||
events: ["pull_request"]
|
||||
secret: "github-webhook-secret"
|
||||
prompt: |
|
||||
Review PR #{pull_request.number}: {pull_request.title}
|
||||
Repository: {repository.full_name}
|
||||
Author: {pull_request.user.login}
|
||||
Diff URL: {pull_request.diff_url}
|
||||
Review for security, performance, and code quality.
|
||||
skills: ["github-code-review"]
|
||||
deliver: "github_comment"
|
||||
deliver_extra:
|
||||
repo: "{repository.full_name}"
|
||||
pr_number: "{pull_request.number}"
|
||||
```
|
||||
|
||||
Then in GitHub: **Settings → Webhooks → Add webhook** → Payload URL: `http://your-server:8644/webhooks/github-pr-review`, Content type: `application/json`, Secret: `github-webhook-secret`, Events: **Pull requests**.
|
||||
|
||||
### Docs Drift Detection
|
||||
|
||||
Weekly scan of merged PRs to find API changes that need documentation updates.
|
||||
|
||||
**Trigger:** Schedule (weekly)
|
||||
|
||||
```bash
|
||||
hermes cron create "0 9 * * 1" \
|
||||
"Scan the NousResearch/hermes-agent repo for documentation drift.
|
||||
|
||||
1. Run: gh pr list --repo NousResearch/hermes-agent --state merged --json number,title,files,mergedAt --limit 30
|
||||
2. Filter to PRs merged in the last 7 days
|
||||
3. For each merged PR, check if it modified:
|
||||
- Tool schemas (tools/*.py) — may need docs/reference/tools-reference.md update
|
||||
- CLI commands (hermes_cli/commands.py, hermes_cli/main.py) — may need docs/reference/cli-commands.md update
|
||||
- Config options (hermes_cli/config.py) — may need docs/user-guide/configuration.md update
|
||||
- Environment variables — may need docs/reference/environment-variables.md update
|
||||
4. Cross-reference: for each code change, check if the corresponding docs page was also updated in the same PR
|
||||
|
||||
Report any gaps where code changed but docs didn't. If everything is in sync, respond with [SILENT]." \
|
||||
--name "Docs drift detection" \
|
||||
--deliver telegram
|
||||
```
|
||||
|
||||
### Dependency Security Audit
|
||||
|
||||
Daily scan for known vulnerabilities in project dependencies.
|
||||
|
||||
**Trigger:** Schedule (daily)
|
||||
|
||||
```bash
|
||||
hermes cron create "0 6 * * *" \
|
||||
"Run a dependency security audit on the hermes-agent project.
|
||||
|
||||
1. cd ~/.hermes/hermes-agent && source .venv/bin/activate
|
||||
2. Run: pip audit --format json 2>/dev/null || pip audit 2>&1
|
||||
3. Run: npm audit --json 2>/dev/null (in website/ directory if it exists)
|
||||
4. Check for any CVEs with CVSS score >= 7.0
|
||||
|
||||
If vulnerabilities found:
|
||||
- List each one with package name, version, CVE ID, severity
|
||||
- Check if an upgrade is available
|
||||
- Note if it's a direct dependency or transitive
|
||||
|
||||
If no vulnerabilities, respond with [SILENT]." \
|
||||
--name "Dependency audit" \
|
||||
--deliver telegram
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## DevOps & Monitoring
|
||||
|
||||
### Deploy Verification
|
||||
|
||||
Trigger smoke tests after every deployment. Your CI/CD pipeline POSTs to the webhook when a deploy completes.
|
||||
|
||||
**Trigger:** API call (webhook)
|
||||
|
||||
```bash
|
||||
hermes webhook subscribe deploy-verify \
|
||||
--events "deployment" \
|
||||
--prompt "A deployment just completed:
|
||||
Service: {service}
|
||||
Environment: {environment}
|
||||
Version: {version}
|
||||
Deployed by: {deployer}
|
||||
|
||||
Run these verification steps:
|
||||
1. Check if the service is responding: curl -s -o /dev/null -w '%{http_code}' {health_url}
|
||||
2. Search recent logs for errors: check the deployment payload for any error indicators
|
||||
3. Verify the version matches: curl -s {health_url}/version
|
||||
|
||||
Report: deployment status (healthy/degraded/failed), response time, any errors found.
|
||||
If healthy, keep it brief. If degraded or failed, provide detailed diagnostics." \
|
||||
--deliver telegram
|
||||
```
|
||||
|
||||
Your CI/CD pipeline triggers it:
|
||||
|
||||
```bash
|
||||
curl -X POST http://your-server:8644/webhooks/deploy-verify \
|
||||
-H "Content-Type: application/json" \
|
||||
-H "X-Hub-Signature-256: sha256=$(echo -n '{"service":"api","environment":"prod","version":"2.1.0","deployer":"ci","health_url":"https://api.example.com/health"}' | openssl dgst -sha256 -hmac 'your-secret' | cut -d' ' -f2)" \
|
||||
-d '{"service":"api","environment":"prod","version":"2.1.0","deployer":"ci","health_url":"https://api.example.com/health"}'
|
||||
```
|
||||
|
||||
### Alert Triage
|
||||
|
||||
Correlate monitoring alerts with recent changes to draft a response. Works with Datadog, PagerDuty, Grafana, or any alerting system that can POST JSON.
|
||||
|
||||
**Trigger:** API call (webhook)
|
||||
|
||||
```bash
|
||||
hermes webhook subscribe alert-triage \
|
||||
--prompt "Monitoring alert received:
|
||||
Alert: {alert.name}
|
||||
Severity: {alert.severity}
|
||||
Service: {alert.service}
|
||||
Message: {alert.message}
|
||||
Timestamp: {alert.timestamp}
|
||||
|
||||
Investigate:
|
||||
1. Search the web for known issues with this error pattern
|
||||
2. Check if this correlates with any recent deployments or config changes
|
||||
3. Draft a triage summary with:
|
||||
- Likely root cause
|
||||
- Suggested first response steps
|
||||
- Escalation recommendation (P1-P4)
|
||||
|
||||
Be concise. This goes to the on-call channel." \
|
||||
--deliver slack
|
||||
```
|
||||
|
||||
### Uptime Monitor
|
||||
|
||||
Check endpoints every 30 minutes. Only notify when something is down.
|
||||
|
||||
**Trigger:** Schedule (every 30 min)
|
||||
|
||||
```python title="~/.hermes/scripts/check-uptime.py"
|
||||
import urllib.request, json, time
|
||||
|
||||
ENDPOINTS = [
|
||||
{"name": "API", "url": "https://api.example.com/health"},
|
||||
{"name": "Web", "url": "https://www.example.com"},
|
||||
{"name": "Docs", "url": "https://docs.example.com"},
|
||||
]
|
||||
|
||||
results = []
|
||||
for ep in ENDPOINTS:
|
||||
try:
|
||||
start = time.time()
|
||||
req = urllib.request.Request(ep["url"], headers={"User-Agent": "Hermes-Monitor/1.0"})
|
||||
resp = urllib.request.urlopen(req, timeout=10)
|
||||
elapsed = round((time.time() - start) * 1000)
|
||||
results.append({"name": ep["name"], "status": resp.getcode(), "ms": elapsed})
|
||||
except Exception as e:
|
||||
results.append({"name": ep["name"], "status": "DOWN", "error": str(e)})
|
||||
|
||||
down = [r for r in results if r.get("status") == "DOWN" or (isinstance(r.get("status"), int) and r["status"] >= 500)]
|
||||
if down:
|
||||
print("OUTAGE DETECTED")
|
||||
for r in down:
|
||||
print(f" {r['name']}: {r.get('error', f'HTTP {r[\"status\"]}')} ")
|
||||
print(f"\nAll results: {json.dumps(results, indent=2)}")
|
||||
else:
|
||||
print("NO_ISSUES")
|
||||
```
|
||||
|
||||
```bash
|
||||
hermes cron create "every 30m" \
|
||||
"If the script reports OUTAGE DETECTED, summarize which services are down and suggest likely causes. If NO_ISSUES, respond with [SILENT]." \
|
||||
--script ~/.hermes/scripts/check-uptime.py \
|
||||
--name "Uptime monitor" \
|
||||
--deliver telegram
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Research & Intelligence
|
||||
|
||||
### Competitive Repository Scout
|
||||
|
||||
Monitor competitor repos for interesting PRs, features, and architectural decisions.
|
||||
|
||||
**Trigger:** Schedule (daily)
|
||||
|
||||
```bash
|
||||
hermes cron create "0 8 * * *" \
|
||||
"Scout these AI agent repositories for notable activity in the last 24 hours:
|
||||
|
||||
Repos to check:
|
||||
- anthropics/claude-code
|
||||
- openai/codex
|
||||
- All-Hands-AI/OpenHands
|
||||
- Aider-AI/aider
|
||||
|
||||
For each repo:
|
||||
1. gh pr list --repo <repo> --state all --json number,title,author,createdAt,mergedAt --limit 15
|
||||
2. gh issue list --repo <repo> --state open --json number,title,labels,createdAt --limit 10
|
||||
|
||||
Focus on:
|
||||
- New features being developed
|
||||
- Architectural changes
|
||||
- Integration patterns we could learn from
|
||||
- Security fixes that might affect us too
|
||||
|
||||
Skip routine dependency bumps and CI fixes. If nothing notable, respond with [SILENT].
|
||||
If there are findings, organize by repo with brief analysis of each item." \
|
||||
--skills "competitive-pr-scout" \
|
||||
--name "Competitor scout" \
|
||||
--deliver telegram
|
||||
```
|
||||
|
||||
### AI News Digest
|
||||
|
||||
Weekly roundup of AI/ML developments.
|
||||
|
||||
**Trigger:** Schedule (weekly)
|
||||
|
||||
```bash
|
||||
hermes cron create "0 9 * * 1" \
|
||||
"Generate a weekly AI news digest covering the past 7 days:
|
||||
|
||||
1. Search the web for major AI announcements, model releases, and research breakthroughs
|
||||
2. Search for trending ML repositories on GitHub
|
||||
3. Check arXiv for highly-cited papers on language models and agents
|
||||
|
||||
Structure:
|
||||
## Headlines (3-5 major stories)
|
||||
## Notable Papers (2-3 papers with one-sentence summaries)
|
||||
## Open Source (interesting new repos or major releases)
|
||||
## Industry Moves (funding, acquisitions, launches)
|
||||
|
||||
Keep each item to 1-2 sentences. Include links. Total under 600 words." \
|
||||
--name "Weekly AI digest" \
|
||||
--deliver telegram
|
||||
```
|
||||
|
||||
### Paper Digest with Notes
|
||||
|
||||
Daily arXiv scan that saves summaries to your note-taking system.
|
||||
|
||||
**Trigger:** Schedule (daily)
|
||||
|
||||
```bash
|
||||
hermes cron create "0 8 * * *" \
|
||||
"Search arXiv for the 3 most interesting papers on 'language model reasoning' OR 'tool-use agents' from the past day. For each paper, create an Obsidian note with the title, authors, abstract summary, key contribution, and potential relevance to Hermes Agent development." \
|
||||
--skills "arxiv,obsidian" \
|
||||
--name "Paper digest" \
|
||||
--deliver local
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## GitHub Event Automations
|
||||
|
||||
### Issue Auto-Labeling
|
||||
|
||||
Automatically label and respond to new issues.
|
||||
|
||||
**Trigger:** GitHub webhook
|
||||
|
||||
```bash
|
||||
hermes webhook subscribe github-issues \
|
||||
--events "issues" \
|
||||
--prompt "New GitHub issue received:
|
||||
Repository: {repository.full_name}
|
||||
Issue #{issue.number}: {issue.title}
|
||||
Author: {issue.user.login}
|
||||
Action: {action}
|
||||
Body: {issue.body}
|
||||
Labels: {issue.labels}
|
||||
|
||||
If this is a new issue (action=opened):
|
||||
1. Read the issue title and body carefully
|
||||
2. Suggest appropriate labels (bug, feature, docs, security, question)
|
||||
3. If it's a bug report, check if you can identify the affected component from the description
|
||||
4. Post a helpful initial response acknowledging the issue
|
||||
|
||||
If this is a label or assignment change, respond with [SILENT]." \
|
||||
--deliver github_comment
|
||||
```
|
||||
|
||||
### CI Failure Analysis
|
||||
|
||||
Analyze CI failures and post diagnostics on the PR.
|
||||
|
||||
**Trigger:** GitHub webhook
|
||||
|
||||
```yaml
|
||||
# config.yaml route
|
||||
platforms:
|
||||
webhook:
|
||||
enabled: true
|
||||
extra:
|
||||
routes:
|
||||
ci-failure:
|
||||
events: ["check_run"]
|
||||
secret: "ci-secret"
|
||||
prompt: |
|
||||
CI check failed:
|
||||
Repository: {repository.full_name}
|
||||
Check: {check_run.name}
|
||||
Status: {check_run.conclusion}
|
||||
PR: #{check_run.pull_requests.0.number}
|
||||
Details URL: {check_run.details_url}
|
||||
|
||||
If conclusion is "failure":
|
||||
1. Fetch the log from the details URL if accessible
|
||||
2. Identify the likely cause of failure
|
||||
3. Suggest a fix
|
||||
If conclusion is "success", respond with [SILENT].
|
||||
deliver: "github_comment"
|
||||
deliver_extra:
|
||||
repo: "{repository.full_name}"
|
||||
pr_number: "{check_run.pull_requests.0.number}"
|
||||
```
|
||||
|
||||
### Auto-Port Changes Across Repos
|
||||
|
||||
When a PR merges in one repo, automatically port the equivalent change to another.
|
||||
|
||||
**Trigger:** GitHub webhook
|
||||
|
||||
```bash
|
||||
hermes webhook subscribe auto-port \
|
||||
--events "pull_request" \
|
||||
--prompt "PR merged in the source repository:
|
||||
Repository: {repository.full_name}
|
||||
PR #{pull_request.number}: {pull_request.title}
|
||||
Author: {pull_request.user.login}
|
||||
Action: {action}
|
||||
Merge commit: {pull_request.merge_commit_sha}
|
||||
|
||||
If action is 'closed' and pull_request.merged is true:
|
||||
1. Fetch the diff: curl -sL {pull_request.diff_url}
|
||||
2. Analyze what changed
|
||||
3. Determine if this change needs to be ported to the Go SDK equivalent
|
||||
4. If yes, create a branch, apply the equivalent changes, and open a PR on the target repo
|
||||
5. Reference the original PR in the new PR description
|
||||
|
||||
If action is not 'closed' or not merged, respond with [SILENT]." \
|
||||
--skills "github-pr-workflow" \
|
||||
--deliver log
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Business Operations
|
||||
|
||||
### Stripe Payment Monitoring
|
||||
|
||||
Track payment events and get summaries of failures.
|
||||
|
||||
**Trigger:** API call (webhook)
|
||||
|
||||
```bash
|
||||
hermes webhook subscribe stripe-payments \
|
||||
--events "payment_intent.succeeded,payment_intent.payment_failed,charge.dispute.created" \
|
||||
--prompt "Stripe event received:
|
||||
Event type: {type}
|
||||
Amount: {data.object.amount} cents ({data.object.currency})
|
||||
Customer: {data.object.customer}
|
||||
Status: {data.object.status}
|
||||
|
||||
For payment_intent.payment_failed:
|
||||
- Identify the failure reason from {data.object.last_payment_error}
|
||||
- Suggest whether this is a transient issue (retry) or permanent (contact customer)
|
||||
|
||||
For charge.dispute.created:
|
||||
- Flag as urgent
|
||||
- Summarize the dispute details
|
||||
|
||||
For payment_intent.succeeded:
|
||||
- Brief confirmation only
|
||||
|
||||
Keep responses concise for the ops channel." \
|
||||
--deliver slack
|
||||
```
|
||||
|
||||
### Daily Revenue Summary
|
||||
|
||||
Compile key business metrics every morning.
|
||||
|
||||
**Trigger:** Schedule (daily)
|
||||
|
||||
```bash
|
||||
hermes cron create "0 8 * * *" \
|
||||
"Generate a morning business metrics summary.
|
||||
|
||||
Search the web for:
|
||||
1. Current Bitcoin and Ethereum prices
|
||||
2. S&P 500 status (pre-market or previous close)
|
||||
3. Any major tech/AI industry news from the last 12 hours
|
||||
|
||||
Format as a brief morning briefing, 3-4 bullet points max.
|
||||
Deliver as a clean, scannable message." \
|
||||
--name "Morning briefing" \
|
||||
--deliver telegram
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Multi-Skill Workflows
|
||||
|
||||
### Security Audit Pipeline
|
||||
|
||||
Combine multiple skills for a comprehensive weekly security review.
|
||||
|
||||
**Trigger:** Schedule (weekly)
|
||||
|
||||
```bash
|
||||
hermes cron create "0 3 * * 0" \
|
||||
"Run a comprehensive security audit of the hermes-agent codebase.
|
||||
|
||||
1. Check for dependency vulnerabilities (pip audit, npm audit)
|
||||
2. Search the codebase for common security anti-patterns:
|
||||
- Hardcoded secrets or API keys
|
||||
- SQL injection vectors (string formatting in queries)
|
||||
- Path traversal risks (user input in file paths without validation)
|
||||
- Unsafe deserialization (pickle.loads, yaml.load without SafeLoader)
|
||||
3. Review recent commits (last 7 days) for security-relevant changes
|
||||
4. Check if any new environment variables were added without being documented
|
||||
|
||||
Write a security report with findings categorized by severity (Critical, High, Medium, Low).
|
||||
If nothing found, report a clean bill of health." \
|
||||
--skills "codebase-security-audit" \
|
||||
--name "Weekly security audit" \
|
||||
--deliver telegram
|
||||
```
|
||||
|
||||
### Content Pipeline
|
||||
|
||||
Research, draft, and prepare content on a schedule.
|
||||
|
||||
**Trigger:** Schedule (weekly)
|
||||
|
||||
```bash
|
||||
hermes cron create "0 10 * * 3" \
|
||||
"Research and draft a technical blog post outline about a trending topic in AI agents.
|
||||
|
||||
1. Search the web for the most discussed AI agent topics this week
|
||||
2. Pick the most interesting one that's relevant to open-source AI agents
|
||||
3. Create an outline with:
|
||||
- Hook/intro angle
|
||||
- 3-4 key sections
|
||||
- Technical depth appropriate for developers
|
||||
- Conclusion with actionable takeaway
|
||||
4. Save the outline to ~/drafts/blog-$(date +%Y%m%d).md
|
||||
|
||||
Keep the outline to ~300 words. This is a starting point, not a finished post." \
|
||||
--name "Blog outline" \
|
||||
--deliver local
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Quick Reference
|
||||
|
||||
### Cron Schedule Syntax
|
||||
|
||||
| Expression | Meaning |
|
||||
|-----------|---------|
|
||||
| `every 30m` | Every 30 minutes |
|
||||
| `every 2h` | Every 2 hours |
|
||||
| `0 2 * * *` | Daily at 2:00 AM |
|
||||
| `0 9 * * 1` | Every Monday at 9:00 AM |
|
||||
| `0 9 * * 1-5` | Weekdays at 9:00 AM |
|
||||
| `0 3 * * 0` | Every Sunday at 3:00 AM |
|
||||
| `0 */6 * * *` | Every 6 hours |
|
||||
|
||||
### Delivery Targets
|
||||
|
||||
| Target | Flag | Notes |
|
||||
|--------|------|-------|
|
||||
| Same chat | `--deliver origin` | Default — delivers to where the job was created |
|
||||
| Local file | `--deliver local` | Saves output, no notification |
|
||||
| Telegram | `--deliver telegram` | Home channel, or `telegram:CHAT_ID` for specific |
|
||||
| Discord | `--deliver discord` | Home channel, or `discord:CHANNEL_ID` |
|
||||
| Slack | `--deliver slack` | Home channel |
|
||||
| SMS | `--deliver sms:+15551234567` | Direct to phone number |
|
||||
| Specific thread | `--deliver telegram:-100123:456` | Telegram forum topic |
|
||||
|
||||
### Webhook Template Variables
|
||||
|
||||
| Variable | Description |
|
||||
|----------|-------------|
|
||||
| `{pull_request.title}` | PR title |
|
||||
| `{issue.number}` | Issue number |
|
||||
| `{repository.full_name}` | `owner/repo` |
|
||||
| `{action}` | Event action (opened, closed, etc.) |
|
||||
| `{__raw__}` | Full JSON payload (truncated at 4000 chars) |
|
||||
| `{sender.login}` | GitHub user who triggered the event |
|
||||
|
||||
### The [SILENT] Pattern
|
||||
|
||||
When a cron job's response contains `[SILENT]`, delivery is suppressed. Use this to avoid notification spam on quiet runs:
|
||||
|
||||
```
|
||||
If nothing noteworthy happened, respond with [SILENT].
|
||||
```
|
||||
|
||||
This means you only get notified when the agent has something to report.
|
||||
@@ -153,6 +153,7 @@ const sidebars: SidebarsConfig = {
|
||||
'guides/use-voice-mode-with-hermes',
|
||||
'guides/build-a-hermes-plugin',
|
||||
'guides/automate-with-cron',
|
||||
'guides/automation-templates',
|
||||
'guides/cron-troubleshooting',
|
||||
'guides/work-with-skills',
|
||||
'guides/delegation-patterns',
|
||||
|
||||
Reference in New Issue
Block a user