hermes-agent

name	hermes-agent
description	Configure, extend, or contribute to Hermes Agent.
version	2.1.0
author	Hermes Agent + Teknium
license	MIT
platforms	["linux","macos","windows"]
metadata	{"hermes":{"tags":["hermes","setup","configuration","multi-agent","spawning","cli","gateway","development"],"homepage":"https://github.com/NousResearch/hermes-agent","related_skills":["claude-code","codex","opencode"]}}

Hermes Agent

Hermes Agent is an open-source AI agent framework by Nous Research that runs in your terminal, messaging platforms, and IDEs. It belongs to the same category as Claude Code (Anthropic), Codex (OpenAI), and OpenClaw — autonomous coding and task-execution agents that use tool calling to interact with your system. Hermes works with any LLM provider (OpenRouter, Anthropic, OpenAI, DeepSeek, local models, and 15+ others) and runs on Linux, macOS, and WSL.

What makes Hermes different:

• Self-improving through skills — Hermes learns from experience by saving reusable procedures as skills. When it solves a complex problem, discovers a workflow, or gets corrected, it can persist that knowledge as a skill document that loads into future sessions. Skills accumulate over time, making the agent better at your specific tasks and environment.
• Persistent memory across sessions — remembers who you are, your preferences, environment details, and lessons learned. Pluggable memory backends (built-in, Honcho, Mem0, and more) let you choose how memory works.
• Multi-platform gateway — the same agent runs on Telegram, Discord, Slack, WhatsApp, Signal, Matrix, Email, and 10+ other platforms with full tool access, not just chat.
• Provider-agnostic — swap models and providers mid-workflow without changing anything else. Credential pools rotate across multiple API keys automatically.
• Profiles — run multiple independent Hermes instances with isolated configs, sessions, skills, and memory.
• Extensible — plugins, MCP servers, custom tools, webhook triggers, cron scheduling, and the full Python ecosystem.

People use Hermes for software development, research, system administration, data analysis, content creation, home automation, and anything else that benefits from an AI agent with persistent context and full system access.

This skill helps you work with Hermes Agent effectively — setting it up, configuring features, spawning additional agent instances, troubleshooting issues, finding the right commands and settings, and understanding how the system works when you need to extend or contribute to it.

Docs: https://hermes-agent.nousresearch.com/docs/

• references/docker-china-cloud.md — Docker mirror config for Chinese cloud servers (Alibaba, Tencent, etc.) + QingLong panel deployment
• references/xiaomi-mimo-multimodal-config.md — Xiaomi MiMo multimodal model setup (vision, STT, TTS)
• references/docker-china-cloud.md — Docker mirror config for Chinese cloud servers (Alibaba, Tencent, etc.) + QingLong panel deployment Docker on Alibaba Cloud: references/docker-alibaba-cloud-linux.md — Installation workarounds External AI API Tools: references/external-api-tools.md — Integrate external AI APIs (Volcengine Ark, DashScope, etc.) as Hermes tools Weixin QR Login: references/weixin-qr-login-setup.md — Programmatic QR login workaround (avoid interactive wizard) Skill Sync & Backup: references/skill-sync-github.md — Automated GitHub sync with sensitive info filtering QQ Bot File Limits: references/qqbot-file-transfer.md — File type support limitations Alibaba Cloud Security: references/alibaba-cloud-security.md — ECS security hardening Volcengine Ark API: references/volcengine-ark-api.md — 火山引擎方舟API接入（CodingPlan Agent模式） Custom Tool Creation: references/custom-tool-creation.md — Creating custom Hermes tools

Quick Start

# Install
curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash

# Interactive chat (default)
hermes

# Single query
hermes chat -q "What is the capital of France?"

# Setup wizard
hermes setup

# Change model/provider
hermes model

# Check health
hermes doctor

---

CLI Reference

Global Flags

hermes [flags] [command]

  --version, -V             Show version
  --resume, -r SESSION      Resume session by ID or title
  --continue, -c [NAME]     Resume by name, or most recent session
  --worktree, -w            Isolated git worktree mode (parallel agents)
  --skills, -s SKILL        Preload skills (comma-separate or repeat)
  --profile, -p NAME        Use a named profile
  --yolo                    Skip dangerous command approval
  --pass-session-id         Include session ID in system prompt

No subcommand defaults to chat.

Chat

hermes chat [flags]
  -q, --query TEXT          Single query, non-interactive
  -m, --model MODEL         Model (e.g. anthropic/claude-sonnet-4)
  -t, --toolsets LIST       Comma-separated toolsets
  --provider PROVIDER       Force provider (openrouter, anthropic, nous, etc.)
  -v, --verbose             Verbose output
  -Q, --quiet               Suppress banner, spinner, tool previews
  --checkpoints             Enable filesystem checkpoints (/rollback)
  --source TAG              Session source tag (default: cli)

Configuration

hermes setup [section]      Interactive wizard (model|terminal|gateway|tools|agent)
hermes model                Interactive model/provider picker
hermes config               View current config
hermes config edit          Open config.yaml in $EDITOR
hermes config set KEY VAL   Set a config value
hermes config path          Print config.yaml path
hermes config env-path      Print .env path
hermes config check         Check for missing/outdated config
hermes config migrate       Update config with new options
hermes login [--provider P] OAuth login (nous, openai-codex)
hermes logout               Clear stored auth
hermes doctor [--fix]       Check dependencies and config
hermes status [--all]       Show component status

Tools & Skills

hermes tools                Interactive tool enable/disable (curses UI)
hermes tools list           Show all tools and status
hermes tools enable NAME    Enable a toolset
hermes tools disable NAME   Disable a toolset

hermes skills list          List installed skills
hermes skills search QUERY  Search the skills hub
hermes skills install ID    Install a skill (ID can be a hub identifier OR a direct https://…/SKILL.md URL; pass --name to override when frontmatter has no name)
hermes skills inspect ID    Preview without installing
hermes skills config        Enable/disable skills per platform
hermes skills check         Check for updates
hermes skills update        Update outdated skills
hermes skills uninstall N   Remove a hub skill
hermes skills publish PATH  Publish to registry
hermes skills browse        Browse all available skills
hermes skills tap add REPO  Add a GitHub repo as skill source

MCP Servers

hermes mcp serve            Run Hermes as an MCP server
hermes mcp add NAME         Add an MCP server (--url or --command)
hermes mcp remove NAME      Remove an MCP server
hermes mcp list             List configured servers
hermes mcp test NAME        Test connection
hermes mcp configure NAME   Toggle tool selection

Gateway (Messaging Platforms)

hermes gateway run          Start gateway foreground
hermes gateway install      Install as background service
hermes gateway start/stop   Control the service
hermes gateway restart      Restart the service
hermes gateway status       Check status
hermes gateway setup        Configure platforms

Supported platforms: Telegram, Discord, Slack, WhatsApp, Signal, Email, SMS, Matrix, Mattermost, Home Assistant, DingTalk, Feishu, WeCom, BlueBubbles (iMessage), Weixin (WeChat), API Server, Webhooks. Open WebUI connects via the API Server adapter.

Platform docs: https://hermes-agent.nousresearch.com/docs/user-guide/messaging/

Sessions

hermes sessions list        List recent sessions
hermes sessions browse      Interactive picker
hermes sessions export OUT  Export to JSONL
hermes sessions rename ID T Rename a session
hermes sessions delete ID   Delete a session
hermes sessions prune       Clean up old sessions (--older-than N days)
hermes sessions stats       Session store statistics

Cron Jobs

hermes cron list            List jobs (--all for disabled)
hermes cron create SCHED    Create: '30m', 'every 2h', '0 9 * * *'
hermes cron edit ID         Edit schedule, prompt, delivery
hermes cron pause/resume ID Control job state
hermes cron run ID          Trigger on next tick
hermes cron remove ID       Delete a job
hermes cron status          Scheduler status

Webhooks

hermes webhook subscribe N  Create route at /webhooks/<name>
hermes webhook list         List subscriptions
hermes webhook remove NAME  Remove a subscription
hermes webhook test NAME    Send a test POST

Profiles

hermes profile list         List all profiles
hermes profile create NAME  Create (--clone, --clone-all, --clone-from)
hermes profile use NAME     Set sticky default
hermes profile delete NAME  Delete a profile
hermes profile show NAME    Show details
hermes profile alias NAME   Manage wrapper scripts
hermes profile rename A B   Rename a profile
hermes profile export NAME  Export to tar.gz
hermes profile import FILE  Import from archive

Credential Pools

hermes auth add             Interactive credential wizard
hermes auth list [PROVIDER] List pooled credentials
hermes auth remove P INDEX  Remove by provider + index
hermes auth reset PROVIDER  Clear exhaustion status

Other

hermes insights [--days N]  Usage analytics
hermes update               Update to latest version
hermes pairing list/approve/revoke  DM authorization
hermes plugins list/install/remove  Plugin management
hermes honcho setup/status  Honcho memory integration (requires honcho plugin)
hermes memory setup/status/off  Memory provider config
hermes completion bash|zsh  Shell completions
hermes acp                  ACP server (IDE integration)
hermes claw migrate         Migrate from OpenClaw
hermes uninstall            Uninstall Hermes

---

Slash Commands (In-Session)

Type these during an interactive chat session. New commands land fairly often; if something below looks stale, run /help in-session for the authoritative list or see the live slash commands reference. The registry of record is hermes_cli/commands.py — every consumer (autocomplete, Telegram menu, Slack mapping, /help) derives from it.

Session Control

/new (/reset)        Fresh session
/clear               Clear screen + new session (CLI)
/retry               Resend last message
/undo                Remove last exchange
/title [name]        Name the session
/compress            Manually compress context
/stop                Kill background processes
/rollback [N]        Restore filesystem checkpoint
/snapshot [sub]      Create or restore state snapshots of Hermes config/state (CLI)
/background <prompt> Run prompt in background
/queue <prompt>      Queue for next turn
/steer <prompt>      Inject a message after the next tool call without interrupting
/agents (/tasks)     Show active agents and running tasks
/resume [name]       Resume a named session
/goal [text|sub]     Set a standing goal Hermes works on across turns until achieved
                     (subcommands: status, pause, resume, clear)
/redraw              Force a full UI repaint (CLI)

Configuration

/config              Show config (CLI)
/model [name]        Show or change model
/personality [name]  Set personality
/reasoning [level]   Set reasoning (none|minimal|low|medium|high|xhigh|show|hide)
/verbose             Cycle: off → new → all → verbose
/voice [on|off|tts]  Voice mode
/yolo                Toggle approval bypass
/busy [sub]          Control what Enter does while Hermes is working (CLI)
                     (subcommands: queue, steer, interrupt, status)
/indicator [style]   Pick the TUI busy-indicator style (CLI)
                     (styles: kaomoji, emoji, unicode, ascii)
/footer [on|off]     Toggle gateway runtime-metadata footer on final replies
/skin [name]         Change theme (CLI)
/statusbar           Toggle status bar (CLI)

Tools & Skills

/tools               Manage tools (CLI)
/toolsets            List toolsets (CLI)
/skills              Search/install skills (CLI)
/skill <name>        Load a skill into session
/reload-skills       Re-scan ~/.hermes/skills/ for added/removed skills
/reload              Reload .env variables into the running session (CLI)
/reload-mcp          Reload MCP servers
/cron                Manage cron jobs (CLI)
/curator [sub]       Background skill maintenance (status, run, pin, archive, …)
/kanban [sub]        Multi-profile collaboration board (tasks, links, comments)
/plugins             List plugins (CLI)

Gateway

/approve             Approve a pending command (gateway)
/deny                Deny a pending command (gateway)
/restart             Restart gateway (gateway)
/sethome             Set current chat as home channel (gateway)
/update              Update Hermes to latest (gateway)
/topic [sub]         Enable or inspect Telegram DM topic sessions (gateway)
/platforms (/gateway) Show platform connection status (gateway)

Utility

/branch (/fork)      Branch the current session
/fast                Toggle priority/fast processing
/browser             Open CDP browser connection
/history             Show conversation history (CLI)
/save                Save conversation to file (CLI)
/copy [N]            Copy the last assistant response to clipboard (CLI)
/paste               Attach clipboard image (CLI)
/image               Attach local image file (CLI)

Info

/help                Show commands
/commands [page]     Browse all commands (gateway)
/usage               Token usage
/insights [days]     Usage analytics
/gquota              Show Google Gemini Code Assist quota usage (CLI)
/status              Session info (gateway)
/profile             Active profile info
/debug               Upload debug report (system info + logs) and get shareable links

Exit

/quit (/exit, /q)    Exit CLI

---

Key Paths & Config

~/.hermes/config.yaml       Main configuration
~/.hermes/.env              API keys and secrets
$HERMES_HOME/skills/        Installed skills
~/.hermes/sessions/         Session transcripts
~/.hermes/logs/             Gateway and error logs
~/.hermes/auth.json         OAuth tokens and credential pools
~/.hermes/hermes-agent/     Source code (if git-installed)

Profiles use ~/.hermes/profiles/<name>/ with the same layout.

Config Sections

Edit with hermes config edit or hermes config set section.key value.

Section	Key options
model	default, provider, base_url, api_key, context_length
agent	max_turns (90), tool_use_enforcement
terminal	backend (local/docker/ssh/modal), cwd, timeout (180)
compression	enabled, threshold (0.50), target_ratio (0.20)
display	skin, tool_progress, show_reasoning, show_cost
stt	enabled, provider (local/groq/openai/mistral)
tts	provider (edge/elevenlabs/openai/minimax/mistral/neutts)
memory	memory_enabled, user_profile_enabled, provider
security	tirith_enabled, website_blocklist
delegation	model, provider, base_url, api_key, max_iterations (50), reasoning_effort
checkpoints	enabled, max_snapshots (50)
auxiliary.compression	model, provider, api_key, base_url, timeout — context compression model
auxiliary.curator	model, provider, api_key, base_url, timeout — curator/review model
auxiliary.vision	model, provider, api_key, base_url — vision/image analysis model

Full config reference: https://hermes-agent.nousresearch.com/docs/user-guide/configuration

Providers

20+ providers supported. Set via hermes model or hermes setup.

Provider	Auth	Key env var
OpenRouter	API key	OPENROUTER_API_KEY
Anthropic	API key	ANTHROPIC_API_KEY
Nous Portal	OAuth	hermes auth
OpenAI Codex	OAuth	hermes auth
GitHub Copilot	Token	COPILOT_GITHUB_TOKEN
Google Gemini	API key	GOOGLE_API_KEY or GEMINI_API_KEY
DeepSeek	API key	DEEPSEEK_API_KEY
xAI / Grok	API key	XAI_API_KEY
Hugging Face	Token	HF_TOKEN
Z.AI / GLM	API key	GLM_API_KEY
MiniMax	API key	MINIMAX_API_KEY
MiniMax CN	API key	MINIMAX_CN_API_KEY
Kimi / Moonshot	API key	KIMI_API_KEY
Alibaba / DashScope	API key	DASHSCOPE_API_KEY
Xiaomi MiMo	API key	XIAOMI_API_KEY
Kilo Code	API key	KILOCODE_API_KEY
AI Gateway (Vercel)	API key	AI_GATEWAY_API_KEY
OpenCode Zen	API key	OPENCODE_ZEN_API_KEY
OpenCode Go	API key	OPENCODE_GO_API_KEY
Qwen OAuth	OAuth	hermes login --provider qwen-oauth
Custom endpoint	Config	model.base_url + model.api_key in config.yaml
GitHub Copilot ACP	External	COPILOT_CLI_PATH or Copilot CLI

Full provider docs: https://hermes-agent.nousresearch.com/docs/integrations/providers

Toolsets

Enable/disable via hermes tools (interactive) or hermes tools enable/disable NAME.

Toolset	What it provides
web	Web search and content extraction
search	Web search only (subset of web)
browser	Browser automation (Browserbase, Camofox, or local Chromium)
terminal	Shell commands and process management
file	File read/write/search/patch
code_execution	Sandboxed Python execution
vision	Image analysis
image_gen	AI image generation
video	Video analysis and generation
tts	Text-to-speech
skills	Skill browsing and management
memory	Persistent cross-session memory
session_search	Search past conversations
delegation	Subagent task delegation
cronjob	Scheduled task management
clarify	Ask user clarifying questions
messaging	Cross-platform message sending
todo	In-session task planning and tracking
kanban	Multi-agent work-queue tools (gated to workers)
debugging	Extra introspection/debug tools (off by default)
safe	Minimal, low-risk toolset for locked-down sessions
spotify	Spotify playback and playlist control
homeassistant	Smart home control (off by default)
discord	Discord integration tools
discord_admin	Discord admin/moderation tools
feishu_doc	Feishu (Lark) document tools
feishu_drive	Feishu (Lark) drive tools
yuanbao	Yuanbao integration tools
rl	Reinforcement learning tools (off by default)
moa	Mixture of Agents (off by default)

Full enumeration lives in toolsets.py as the TOOLSETS dict; _HERMES_CORE_TOOLS is the default bundle most platforms inherit from.

Tool changes take effect on /reset (new session). They do NOT apply mid-conversation to preserve prompt caching.

---

Security & Privacy Toggles

Common "why is Hermes doing X to my output / tool calls / commands?" toggles — and the exact commands to change them. Most of these need a fresh session (/reset in chat, or start a new hermes invocation) because they're read once at startup.

Secret redaction in tool output

Secret redaction is off by default — tool output (terminal stdout, read_file, web content, subagent summaries, etc.) passes through unmodified. If the user wants Hermes to auto-mask strings that look like API keys, tokens, and secrets before they enter the conversation context and logs:

hermes config set security.redact_secrets true       # enable globally

Restart required. security.redact_secrets is snapshotted at import time — toggling it mid-session (e.g. via export HERMES_REDACT_SECRETS=true from a tool call) will NOT take effect for the running process. Tell the user to run hermes config set security.redact_secrets true in a terminal, then start a new session. This is deliberate — it prevents an LLM from flipping the toggle on itself mid-task.

Disable again with:

hermes config set security.redact_secrets false

PII redaction in gateway messages

Separate from secret redaction. When enabled, the gateway hashes user IDs and strips phone numbers from the session context before it reaches the model:

hermes config set privacy.redact_pii true    # enable
hermes config set privacy.redact_pii false   # disable (default)

Command approval prompts

By default (approvals.mode: manual), Hermes prompts the user before running shell commands flagged as destructive (rm -rf, git reset --hard, etc.). The modes are:

• manual — always prompt (default)
• smart — use an auxiliary LLM to auto-approve low-risk commands, prompt on high-risk
• off — skip all approval prompts (equivalent to --yolo)

hermes config set approvals.mode smart       # recommended middle ground
hermes config set approvals.mode off         # bypass everything (not recommended)

Per-invocation bypass without changing config:

• hermes --yolo …
• export HERMES_YOLO_MODE=1

Note: YOLO / approvals.mode: off does NOT turn off secret redaction. They are independent.

Shell hooks allowlist

Some shell-hook integrations require explicit allowlisting before they fire. Managed via ~/.hermes/shell-hooks-allowlist.json — prompted interactively the first time a hook wants to run.

Disabling the web/browser/image-gen tools

To keep the model away from network or media tools entirely, open hermes tools and toggle per-platform. Takes effect on next session (/reset). See the Tools & Skills section above.

---

Voice & Transcription

STT (Voice → Text)

Voice messages from messaging platforms are auto-transcribed.

Provider priority (auto-detected):

1. Local faster-whisper — free, no API key: pip install faster-whisper
2. Groq Whisper — free tier: set GROQ_API_KEY
3. OpenAI Whisper — paid: set VOICE_TOOLS_OPENAI_KEY
4. Mistral Voxtral — set MISTRAL_API_KEY

Config:

stt:
  enabled: true
  provider: local        # local, groq, openai, mistral
  local:
    model: base          # tiny, base, small, medium, large-v3

TTS (Text → Voice)

Provider	Env var	Free?
Edge TTS	None	Yes (default)
ElevenLabs	ELEVENLABS_API_KEY	Free tier
OpenAI	VOICE_TOOLS_OPENAI_KEY	Paid
MiniMax	MINIMAX_API_KEY	Paid
Mistral (Voxtral)	MISTRAL_API_KEY	Paid
NeuTTS (local)	None (pip install neutts[all] + espeak-ng)	Free

Voice commands: /voice on (voice-to-voice), /voice tts (always voice), /voice off.

---

Spawning Additional Hermes Instances

Run additional Hermes processes as fully independent subprocesses — separate sessions, tools, and environments.

When to Use This vs delegate_task

	delegate_task	Spawning hermes process
Isolation	Separate conversation, shared process	Fully independent process
Duration	Minutes (bounded by parent loop)	Hours/days
Tool access	Subset of parent's tools	Full tool access
Interactive	No	Yes (PTY mode)
Use case	Quick parallel subtasks	Long autonomous missions

One-Shot Mode

terminal(command="hermes chat -q 'Research GRPO papers and write summary to ~/research/grpo.md'", timeout=300)

# Background for long tasks:
terminal(command="hermes chat -q 'Set up CI/CD for ~/myapp'", background=true)

Interactive PTY Mode (via tmux)

Hermes uses prompt_toolkit, which requires a real terminal. Use tmux for interactive spawning:

# Start
terminal(command="tmux new-session -d -s agent1 -x 120 -y 40 'hermes'", timeout=10)

# Wait for startup, then send a message
terminal(command="sleep 8 && tmux send-keys -t agent1 'Build a FastAPI auth service' Enter", timeout=15)

# Read output
terminal(command="sleep 20 && tmux capture-pane -t agent1 -p", timeout=5)

# Send follow-up
terminal(command="tmux send-keys -t agent1 'Add rate limiting middleware' Enter", timeout=5)

# Exit
terminal(command="tmux send-keys -t agent1 '/exit' Enter && sleep 2 && tmux kill-session -t agent1", timeout=10)

Multi-Agent Coordination

# Agent A: backend
terminal(command="tmux new-session -d -s backend -x 120 -y 40 'hermes -w'", timeout=10)
terminal(command="sleep 8 && tmux send-keys -t backend 'Build REST API for user management' Enter", timeout=15)

# Agent B: frontend
terminal(command="tmux new-session -d -s frontend -x 120 -y 40 'hermes -w'", timeout=10)
terminal(command="sleep 8 && tmux send-keys -t frontend 'Build React dashboard for user management' Enter", timeout=15)

# Check progress, relay context between them
terminal(command="tmux capture-pane -t backend -p | tail -30", timeout=5)
terminal(command="tmux send-keys -t frontend 'Here is the API schema from the backend agent: ...' Enter", timeout=5)

Session Resume

# Resume most recent session
terminal(command="tmux new-session -d -s resumed 'hermes --continue'", timeout=10)

# Resume specific session
terminal(command="tmux new-session -d -s resumed 'hermes --resume 20260225_143052_a1b2c3'", timeout=10)

Remote Server Sub-Agent (SSH + tmux)

Deploy Hermes on a remote server and control it from the local agent via SSH. The remote agent runs persistently in tmux; the local agent sends commands and reads output over SSH.

Setup steps:

# 1. Install deps on remote
sshpass -p '$PASS' ssh root@$REMOTE "yum install -y git tmux"  # or apt

# 2. Clone Hermes
sshpass -p '$PASS' ssh root@$REMOTE "cd /opt && git clone --depth 1 https://github.com/NousResearch/hermes-agent.git"

# 3. Create venv and install
sshpass -p '$PASS' ssh root@$REMOTE "cd /opt/hermes-agent && python3 -m venv venv && source venv/bin/activate && pip install -e . -q"

# 4. Configure (write config + .env on remote)
sshpass -p '$PASS' ssh root@$REMOTE "mkdir -p /root/.hermes && cat > /root/.hermes/config.yaml << 'EOF'
model:
  default: mimo-v2.5-pro
  provider: xiaomi
  base_url: https://token-plan-cn.xiaomimimo.com/v1
agent:
  max_turns: 50
terminal:
  timeout: 120
EOF"

# 5. Start in tmux
sshpass -p '$PASS' ssh root@$REMOTE "tmux new-session -d -s hermes-agent -x 120 -y 40"
sshpass -p '$PASS' ssh root@$REMOTE "tmux send-keys -t hermes-agent 'cd /opt/hermes-agent && source venv/bin/activate && export XIAOMI_API_KEY=\$KEY && hermes chat --yolo' Enter"

# 6. Send commands
sshpass -p '$PASS' ssh root@$REMOTE "tmux send-keys -t hermes-agent 'your message' Enter"

# 7. Read output
sshpass -p '$PASS' ssh root@$REMOTE "tmux capture-pane -t hermes-agent -p -S -30"

Control script pattern (save locally as hz-agent.sh):

#!/bin/bash
SERVER="x.x.x.x"; PASS="xxx"; SESSION="hermes-agent"
case "$1" in
  send)  sshpass -p "$PASS" ssh root@$SERVER "tmux send-keys -t $SESSION '$2' Enter" ;;
  read)  sshpass -p "$PASS" ssh root@$SERVER "tmux capture-pane -t $SESSION -p -S -${2:-30}" ;;
  status) sshpass -p "$PASS" ssh root@$SERVER "tmux has-session -t $SESSION 2>/dev/null && echo 'running' || echo 'stopped'" ;;
  restart) # kill + re-create tmux session + re-launch hermes ;;
esac

Pitfalls:

• hermes chat -q '中文' fails because argparse treats CJK as a subcommand. Use hermes -q '中文' or pipe: echo 'msg' | hermes chat
• sshpass + SSH may redact secrets in tool output. Write .env on the remote server directly via python3 -c "..." rather than shell interpolation.
• The --yolo flag is needed for non-interactive operation (no approval prompts).
• -Q (quiet) suppresses the banner for cleaner output parsing.
• Wait 8-10 seconds after starting hermes in tmux before sending the first message — it needs time to initialize.

See references/remote-agent-deployment.md for full worked example.

Tips

• Prefer delegate_task for quick subtasks — less overhead than spawning a full process
• Use -w (worktree mode) when spawning agents that edit code — prevents git conflicts
• Set timeouts for one-shot mode — complex tasks can take 5-10 minutes
• Use hermes chat -q for fire-and-forget — no PTY needed
• Use tmux for interactive sessions — raw PTY mode has \\r vs \\n issues with prompt_toolkit
• For scheduled tasks, use the cronjob tool instead of spawning — handles delivery and retry

---

Durable & Background Systems

Four systems run alongside the main conversation loop. Quick reference here; full developer notes live in AGENTS.md, user-facing docs under website/docs/user-guide/features/.

Delegation (delegate_task)

Synchronous subagent spawn — the parent waits for the child's summary before continuing its own loop. Isolated context + terminal session.

• Single: delegate_task(goal, context, toolsets).
• Batch: delegate_task(tasks=[{goal, ...}, ...]) runs children in parallel, capped by delegation.max_concurrent_children (default 3).
• Roles: leaf (default; cannot re-delegate) vs orchestrator (can spawn its own workers, bounded by delegation.max_spawn_depth).
• Not durable. If the parent is interrupted, the child is cancelled. For work that must outlive the turn, use cronjob or terminal(background=True, notify_on_complete=True).

Config: delegation.* in config.yaml.

Cron (scheduled jobs)

Durable scheduler — cron/jobs.py + cron/scheduler.py. Drive it via the cronjob tool, the hermes cron CLI (list, add, edit, pause, resume, run, remove), or the /cron slash command.

• Schedules: duration ("30m", "2h"), "every" phrase ("every monday 9am"), 5-field cron ("0 9 * * *"), or ISO timestamp.
• Per-job knobs: skills, model/provider override, script (pre-run data collection; no_agent=True makes the script the whole job), context_from (chain job A's output into job B), workdir (run in a specific dir with its AGENTS.md / CLAUDE.md loaded), multi-platform delivery.
• Invariants: 3-minute hard interrupt per run, .tick.lock file prevents duplicate ticks across processes, cron sessions pass skip_memory=True by default, and cron deliveries are framed with a header/footer instead of being mirrored into the target gateway session (keeps role alternation intact).

User docs: https://hermes-agent.nousresearch.com/docs/user-guide/features/cron

Curator (skill lifecycle)

Background maintenance for agent-created skills. Tracks usage, marks idle skills stale, archives stale ones, keeps a pre-run tar.gz backup so nothing is lost.

• CLI: hermes curator <verb> — status, run, pause, resume, pin, unpin, archive, restore, prune, backup, rollback.
• Slash: /curator <subcommand> mirrors the CLI.
• Scope: only touches skills with created_by: "agent" provenance. Bundled + hub-installed skills are off-limits. Never deletes — max destructive action is archive. Pinned skills are exempt from every auto-transition and every LLM review pass.
• Telemetry: sidecar at ~/.hermes/skills/.usage.json holds per-skill use_count, view_count, patch_count, last_activity_at, state, pinned.

Config: curator.* (enabled, interval_hours, min_idle_hours, stale_after_days, archive_after_days, backup.*). User docs: https://hermes-agent.nousresearch.com/docs/user-guide/features/curator

Kanban (multi-agent work queue)

Durable SQLite board for multi-profile / multi-worker collaboration. Users drive it via hermes kanban <verb>; dispatcher-spawned workers see a focused kanban_* toolset gated by HERMES_KANBAN_TASK so the schema footprint is zero outside worker processes.

• CLI verbs (common): init, create, list (alias ls), show, assign, link, unlink, comment, complete, block, unblock, archive, tail. Less common: watch, stats, runs, log, dispatch, daemon, gc.
• Worker toolset: kanban_show, kanban_complete, kanban_block, kanban_heartbeat, kanban_comment, kanban_create, kanban_link.
• Dispatcher runs inside the gateway by default (kanban.dispatch_in_gateway: true) — reclaims stale claims, promotes ready tasks, atomically claims, spawns assigned profiles. Auto-blocks a task after ~5 consecutive spawn failures.
• Isolation: board is the hard boundary (workers get HERMES_KANBAN_BOARD pinned in env); tenant is a soft namespace within a board for workspace-path + memory-key isolation.

User docs: https://hermes-agent.nousresearch.com/docs/user-guide/features/kanban

---

Windows-Specific Quirks

Hermes runs natively on Windows (PowerShell, cmd, Windows Terminal, git-bash mintty, VS Code integrated terminal). Most of it just works, but a handful of differences between Win32 and POSIX have bitten us — document new ones here as you hit them so the next person (or the next session) doesn't rediscover them from scratch.

Input / Keybindings

Alt+Enter doesn't insert a newline. Windows Terminal intercepts Alt+Enter at the terminal layer to toggle fullscreen — the keystroke never reaches prompt_toolkit. Use Ctrl+Enter instead. Windows Terminal delivers Ctrl+Enter as LF (c-j), distinct from plain Enter (c-m / CR), and the CLI binds c-j to newline insertion on win32 only (see _bind_prompt_submit_keys + the Windows-only c-j binding in cli.py). Side effect: the raw Ctrl+J keystroke also inserts a newline on Windows — unavoidable, because Windows Terminal collapses Ctrl+Enter and Ctrl+J to the same keycode at the Win32 console API layer. No conflicting binding existed for Ctrl+J on Windows, so this is a harmless side effect.

mintty / git-bash behaves the same (fullscreen on Alt+Enter) unless you disable Alt+Fn shortcuts in Options → Keys. Easier to just use Ctrl+Enter.

Diagnosing keybindings. Run python scripts/keystroke_diagnostic.py (repo root) to see exactly how prompt_toolkit identifies each keystroke in the current terminal. Answers questions like "does Shift+Enter come through as a distinct key?" (almost never — most terminals collapse it to plain Enter) or "what byte sequence is my terminal sending for Ctrl+Enter?" This is how the Ctrl+Enter = c-j fact was established.

Config / Files

HTTP 400 "No models provided" on first run. config.yaml was saved with a UTF-8 BOM (common when Windows apps write it). Re-save as UTF-8 without BOM. hermes config edit writes without BOM; manual edits in Notepad are the usual culprit.

execute_code / Sandbox

WinError 10106 ("The requested service provider could not be loaded or initialized") from the sandbox child process — it can't create an AF_INET socket, so the loopback-TCP RPC fallback fails before connect(). Root cause is usually not a broken Winsock LSP; it's Hermes's own env scrubber dropping SYSTEMROOT / WINDIR / COMSPEC from the child env. Python's socket module needs SYSTEMROOT to locate mswsock.dll. Fixed via the _WINDOWS_ESSENTIAL_ENV_VARS allowlist in tools/code_execution_tool.py. If you still hit it, echo os.environ inside an execute_code block to confirm SYSTEMROOT is set. Full diagnostic recipe in references/execute-code-sandbox-env-windows.md.

Testing / Contributing

scripts/run_tests.sh doesn't work as-is on Windows — it looks for POSIX venv layouts (.venv/bin/activate). The Hermes-installed venv at venv/Scripts/ has no pip or pytest either (stripped for install size). Workaround: install pytest + pytest-xdist + pyyaml into a system Python 3.11 user site, then invoke pytest directly with PYTHONPATH set:

"/c/Program Files/Python311/python" -m pip install --user pytest pytest-xdist pyyaml
export PYTHONPATH="$(pwd)"
"/c/Program Files/Python311/python" -m pytest tests/foo/test_bar.py -v --tb=short -n 0

Use -n 0, not -n 4 — pyproject.toml's default addopts already includes -n, and the wrapper's CI-parity guarantees don't apply off POSIX.

POSIX-only tests need skip guards. Common markers already in the codebase:

• Symlinks — elevated privileges on Windows
• 0o600 file modes — POSIX mode bits not enforced on NTFS by default
• signal.SIGALRM — Unix-only (see tests/conftest.py::_enforce_test_timeout)
• Winsock / Windows-specific regressions — @pytest.mark.skipif(sys.platform != "win32", ...)

Use the existing skip-pattern style (sys.platform == "win32" or sys.platform.startswith("win")) to stay consistent with the rest of the suite.

Path / Filesystem

Line endings. Git may warn LF will be replaced by CRLF the next time Git touches it. Cosmetic — the repo's .gitattributes normalizes. Don't let editors auto-convert committed POSIX-newline files to CRLF.

Forward slashes work almost everywhere. C:/Users/... is accepted by every Hermes tool and most Windows APIs. Prefer forward slashes in code and logs — avoids shell-escaping backslashes in bash.

---

Provider-Specific References

• references/mimo-provider-setup.md — Xiaomi MiMo model configuration for multimodal agent (vision, ASR, TTS)

• references/docker-china-mirrors.md — Working Docker mirrors for China + QingLong panel setup + API patterns

• QQ Bot file transfer: PDF and other document types may not auto-download. Ask user for screenshots or cloud links. See references/qqbot-file-transfer.md.

• Weixin (WeChat) gateway setup: QR login via two-phase Python script (curses UI not automatable), DM policy requirement, iLink Bot limitations. See references/weixin-gateway-setup.md.

• Alibaba Cloud Security: references/alibaba-cloud-security.md — ECS security hardening

• Xiaomi + Volcengine Multi-Provider: references/xiaomi-volcengine-multi-provider.md — Full setup pattern for Xiaomi main + Volcengine auxiliary/sub-agents

Backup & Restore

• references/hermes-backup-restore.md — Full backup/restore procedures, selective restore, compression tips

Deployment & Operations References

• references/remote-agent-deployment.md — Full worked example: deploying Hermes on a remote server via SSH + tmux, with control script template
• references/remote-code-modification-pitfalls.md — Pitfalls when modifying Python/code on remote servers via SSH
• references/paid-api-key-system.md — Reusable pattern for adding license key validation to FastAPI backends
• references/weixin-qr-login-setup.md — Weixin/WeChat QR login bypass for phone users (two-phase Python script approach)

Multi-Provider Model Configuration

When the user wants to "add" a provider (e.g., "加入方舟体系"), they mean ADD it as auxiliary/sub-agent — NOT replace the main model. Common mistake: changing model.default or model.provider when the user only wants delegation/auxiliary models updated.

Config keys for multi-provider setup:

# Main model (DO NOT CHANGE unless user explicitly says "换主模型")
hermes config set model.default mimo-v2.5-pro
hermes config set model.provider xiaomi
hermes config set model.base_url https://token-plan-cn.xiaomimimo.com/v1

# Sub-agent delegation (what delegate_task uses)
hermes config set delegation.model deepseek-v4-pro-260425
hermes config set delegation.provider volcengine

# Auxiliary: vision, compression, web extract, etc.
hermes config set auxiliary.vision.model mimo-v2-omni
hermes config set auxiliary.vision.provider xiaomi
hermes config set auxiliary.compression.model deepseek-v4-flash-260425
hermes config set auxiliary.compression.provider volcengine

# Fallback (auto-switch when main model is down)
hermes config set fallback_providers '["volcengine"]'

Pitfall: "add X" ≠ "replace main model"

• User says "加入方舟" → set delegation/auxiliary to volcengine, leave model.* alone
• User says "换主模型" → only then change model.default and model.provider
• User says "不要更改主模型" → NEVER touch model.* keys
• When in doubt, ask: "你是要换主模型，还是加为辅助？"

Listing available models from Volcengine Ark:

source ~/.hermes/.env && curl -s "https://ark.cn-beijing.volces.com/api/v3/models" \
  -H "Authorization: Bearer $ARK_API_KEY" | python3 -c "
import sys, json
data = json.load(sys.stdin)
for m in sorted(data.get('data', []), key=lambda x: x['id']):
    if m.get('status') != 'Shutdown':
        print(f\"{m['id']:50s} {m.get('status', '')}\")"

---

Troubleshooting

Voice not working

1. Check stt.enabled: true in config.yaml
2. Verify provider: pip install faster-whisper or set API key
3. In gateway: /restart. In CLI: exit and relaunch.

Tool not available

1. hermes tools — check if toolset is enabled for your platform
2. Some tools need env vars (check .env)
3. /reset after enabling tools

Model/provider issues

1. hermes doctor — check config and dependencies
2. hermes login — re-authenticate OAuth providers
3. Check .env has the right API key
4. Copilot 403: gh auth login tokens do NOT work for Copilot API. You must use the Copilot-specific OAuth device code flow via hermes model → GitHub Copilot.

Context compression 401 / AuthenticationError

Compression and curator models under auxiliary.* need explicit api_key in config.yaml — the provider's env var (e.g. ARK_API_KEY) is NOT auto-inherited. Fix:

hermes config set auxiliary.compression.api_key '${ARK_API_KEY}'
hermes config set auxiliary.curator.api_key '${ARK_API_KEY}'

Config path is auxiliary.compression (NOT models.compression). Verify with:

python3 -c "import yaml; c=yaml.safe_load(open('$HOME/.hermes/config.yaml')); print(c.get('auxiliary',{}).get('compression',{}))"

Restart gateway after fixing: hermes gateway restart.

Bulk fix for multiple empty api_keys: If many auxiliary sections have empty api_keys (common after fresh setup), fix them all at once:

import yaml
with open('config.yaml') as f:
    cfg = yaml.safe_load(f)
count = 0
for section_name, section in cfg.items():
    if isinstance(section, dict):
        for k, v in section.items():
            if isinstance(v, dict) and v.get('provider') == 'volcengine' and v.get('api_key') == '':
                v['api_key'] = '${ARK_API_KEY}'
                count += 1
            elif isinstance(v, dict):
                for k2, v2 in v.items():
                    if isinstance(v2, dict) and v2.get('provider') == 'volcengine' and v2.get('api_key') == '':
                        v2['api_key'] = '${ARK_API_KEY}'
                        count += 1
with open('config.yaml', 'w') as f:
    yaml.dump(cfg, f, default_flow_style=False, allow_unicode=True)
print(f'Fixed {count} empty api_keys')

This fixes compression, curator, vision, kanban_decomposer, mcp, profile_describer, skills_hub, title_generation, triage_specifier, web_extract — all at once.

Changes not taking effect

• Tools/skills: /reset starts a new session with updated toolset
• Config changes: In gateway: /restart. In CLI: exit and relaunch.
• Code changes: Restart the CLI or gateway process

Skills not showing

1. hermes skills list — verify installed
2. hermes skills config — check platform enablement
3. Load explicitly: /skill name or hermes -s name

Gateway issues

Check logs first:

grep -i "failed to send\\|error" ~/.hermes/logs/gateway.log | tail -20

Common gateway problems:

• Gateway dies on SSH logout: Enable linger: sudo loginctl enable-linger $USER
• Gateway dies on WSL2 close: WSL2 requires systemd=true in /etc/wsl.conf for systemd services to work. Without it, gateway falls back to nohup (dies when session closes).
• Gateway crash loop: Reset the failed state: systemctl --user reset-failed hermes-gateway
• Gateway restart hangs/times out: systemctl restart hermes-gateway can hang for 60-180s. Workaround: kill processes directly with pkill -9 -f "hermes.*gateway" then sudo systemctl start hermes-gateway, or just wait — the service usually comes back on its own.

Pairing (DM authorization)

• hermes pairing list — show pending codes + approved users
• hermes pairing approve <platform> <code> — approve a pending request
• hermes pairing revoke <platform> <user_id> — revoke access
• Pitfall: pairing codes expire. If approve says "not found or expired", check hermes pairing list — the user may already be approved.
• Pitfall: don't use python3 -m hermes.cli.main pairing — the module path is wrong. Use hermes pairing CLI directly.

Cron jobs with SSH commands blocked by security scan

When a cron job runs in agent mode (default), the Tirith security scan blocks SSH-related commands (sshpass, ssh, etc.) because there's no user online to approve them. The job reports "被安全策略拦截" (blocked by security policy).

Fix: Use no_agent=True with a bash script — this skips the LLM and security scan entirely, running the script directly:

# Create the monitoring script
cat > ~/.hermes/scripts/collector/monitor.sh << 'EOF'
#!/bin/bash
HOST="hz-server"
COUNT=$(ssh -o ConnectTimeout=5 $HOST "ps aux | grep main | grep -v grep | wc -l" 2>/dev/null)
if [ -z "$COUNT" ] || [ "$COUNT" -lt 20 ]; then
    echo "⚠️ 进程异常: $COUNT 个"
fi
EOF
chmod +x ~/.hermes/scripts/collector/monitor.sh

Then update the cron job:

cronjob(action="update", job_id="...", no_agent=True, script="collector/monitor.sh", prompt="")

Key rules for no_agent=True scripts:

• Empty stdout = silent (nothing delivered to user) — design scripts to stay quiet when everything is normal
• Non-empty stdout = delivered as message
• Non-zero exit = error alert
• Script path resolves under ~/.hermes/scripts/
• .sh/.bash runs via bash, everything else via Python

Platform-specific issues

• Discord bot silent: Must enable Message Content Intent in Bot → Privileged Gateway Intents.
• QQ Bot gateway setup: QR code scan flow, config format pitfalls (env vars not top-level YAML), pairing approval, custom stop keywords. See references/qqbot-gateway-setup.md.
• Weixin (WeChat) setup: Two-phase QR login script (can't automate hermes gateway setup via PTY), DM policy requirement, iLink bot limitations. See references/weixin-gateway-setup.md.
• Weixin (WeChat) gateway setup: QR login via two-phase Python script (curses UI not automatable), WEIXIN_DM_POLICY=open required or DMs silently rejected, iLink Bot limitations. See references/weixin-gateway-setup.md.
• QQ Bot file transfer: PDF and other document types may not auto-download. Ask user for screenshots or cloud links. See references/qqbot-file-transfer.md.

Deployment

• QQ Bot file transfer: PDF and other document types may not auto-download. Ask user for screenshots or cloud links. See references/qqbot-file-transfer.md.ry.vision.model <model_name>

---

## Alternatives & Migration

Hermes belongs to a family of personal AI assistants. Key alternatives:

| Feature | Hermes Agent | OpenClaw 🦞 |
|---------|-------------|-------------|
| Stars | Smaller | 378k+ (very popular) |
| Platforms | 15+ (Telegram, Discord, QQ, WeChat, etc.) | 24+ (adds WhatsApp, Signal, iMessage, LINE, etc.) |
| Skills | Manual + hub | 5400+ community skills |
| Voice | STT/TTS providers | macOS/iOS/Android native voice |
| Config | YAML + CLI | `openclaw onboard` wizard |
| Models | Any provider | Any provider |
| License | MIT | MIT |

**When to consider OpenClaw:**
- Need WhatsApp, Signal, or iMessage support
- Want a large pre-built skill library
- Prefer a more mature community/ecosystem

**When to stay with Hermes:**
- Already configured and working
- Need deep Python ecosystem integration
- Want fine-grained control over tools and config
- Using Hermes-specific features (profiles, kanban, credential pools)

**Migrating from OpenClaw to Hermes:**
```bash
hermes claw migrate

Evaluating OpenClaw: Install on a spare server first to test without disrupting existing Hermes setup.

Where to Find Things

Looking for...	Location
Config options	hermes config edit or Configuration docs
Available tools	hermes tools list or Tools reference
Slash commands	/help in session or Slash commands reference
Skills catalog	hermes skills browse or Skills catalog
Provider setup	hermes model or Providers guide
Platform setup	hermes gateway setup or Messaging docs
MCP servers	hermes mcp list or MCP guide
Profiles	hermes profile list or Profiles docs
Cron jobs	hermes cron list or Cron docs
Memory	hermes memory status or Memory docs
Env variables	hermes config env-path or Env vars reference
CLI commands	hermes --help or CLI reference
Gateway logs	~/.hermes/logs/gateway.log
Session files	~/.hermes/sessions/ or hermes sessions browse
Source code	~/.hermes/hermes-agent/

---

Contributor Quick Reference

For occasional contributors and PR authors. Full developer docs: https://hermes-agent.nousresearch.com/docs/developer-guide/

Project Layout

hermes-agent/
├── run_agent.py          # AIAgent — core conversation loop
├── model_tools.py        # Tool discovery and dispatch
├── toolsets.py           # Toolset definitions
├── cli.py                # Interactive CLI (HermesCLI)
├── hermes_state.py       # SQLite session store
├── agent/                # Prompt builder, context compression, memory, model routing, credential pooling, skill dispatch
├── hermes_cli/           # CLI subcommands, config, setup, commands
│   ├── commands.py       # Slash command registry (CommandDef)
│   ├── config.py         # DEFAULT_CONFIG, env var definitions
│   └── main.py           # CLI entry point and argparse
├── tools/                # One file per tool
│   └── registry.py       # Central tool registry
├── gateway/              # Messaging gateway
│   └── platforms/        # Platform adapters (telegram, discord, etc.)
├── cron/                 # Job scheduler
├── tests/                # ~3000 pytest tests
└── website/              # Docusaurus docs site

Config: ~/.hermes/config.yaml (settings), ~/.hermes/.env (API keys).

Adding a Tool (3 files)

1. Create tools/your_tool.py:

import json, os
from tools.registry import registry

def check_requirements() -> bool:
    return bool(os.getenv("EXAMPLE_API_KEY"))

def example_tool(param: str, task_id: str = None) -> str:
    return json.dumps({"success": True, "data": "..."})

registry.register(
    name="example_tool",
    toolset="example",
    schema={"name": "example_tool", "description": "...", "parameters": {...}},
    handler=lambda args, **kw: example_tool(
        param=args.get("param", ""), task_id=kw.get("task_id")),
    check_fn=check_requirements,
    requires_env=["EXAMPLE_API_KEY"],
)

2. Add to toolsets.py → _HERMES_CORE_TOOLS list.

Auto-discovery: any tools/*.py file with a top-level registry.register() call is imported automatically — no manual list needed.

All handlers must return JSON strings. Use get_hermes_home() for paths, never hardcode ~/.hermes.

Adding a Slash Command

1. Add CommandDef to COMMAND_REGISTRY in hermes_cli/commands.py
2. Add handler in cli.py → process_command()
3. (Optional) Add gateway handler in gateway/run.py

All consumers (help text, autocomplete, Telegram menu, Slack mapping) derive from the central registry automatically.

Agent Loop (High Level)

run_conversation():
  1. Build system prompt
  2. Loop while iterations < max:
     a. Call LLM (OpenAI-format messages + tool schemas)
     b. If tool_calls → dispatch each via handle_function_call() → append results → continue
     c. If text response → return
  3. Context compression triggers automatically near token limit

Testing

python -m pytest tests/ -o 'addopts=' -q   # Full suite
python -m pytest tests/tools/ -q            # Specific area

• Tests auto-redirect HERMES_HOME to temp dirs — never touch real ~/.hermes/
• Run full suite before pushing any change
• Use -o 'addopts=' to clear any baked-in pytest flags

Windows contributors: scripts/run_tests.sh currently looks for POSIX venvs (.venv/bin/activate / venv/bin/activate) and will error out on Windows where the layout is venv/Scripts/activate + python.exe. The Hermes-installed venv at venv/Scripts/ also has no pip or pytest — it's stripped for end-user install size. Workaround: install pytest + pytest-xdist + pyyaml into a system Python 3.11 user site (/c/Program Files/Python311/python -m pip install --user pytest pytest-xdist pyyaml), then run tests directly:

export PYTHONPATH="$(pwd)"
"/c/Program Files/Python311/python" -m pytest tests/tools/test_foo.py -v --tb=short -n 0

Use -n 0 (not -n 4) because pyproject.toml's default addopts already includes -n, and the wrapper's CI-parity story doesn't apply off-POSIX.

Cross-platform test guards: tests that use POSIX-only syscalls need a skip marker. Common ones already in the codebase:

• Symlink creation → @pytest.mark.skipif(sys.platform == "win32", reason="Symlinks require elevated privileges on Windows") (see tests/cron/test_cron_script.py)
• POSIX file modes (0o600, etc.) → @pytest.mark.skipif(sys.platform.startswith("win"), reason="POSIX mode bits not enforced on Windows") (see tests/hermes_cli/test_auth_toctou_file_modes.py)
• signal.SIGALRM → Unix-only (see tests/conftest.py::_enforce_test_timeout)
• Live Winsock / Windows-specific regression tests → @pytest.mark.skipif(sys.platform != "win32", reason="Windows-specific regression")

Monkeypatching sys.platform is not enough when the code under test also calls platform.system() / platform.release() / platform.mac_ver(). Those functions re-read the real OS independently, so a test that sets sys.platform = "linux" on a Windows runner will still see platform.system() == "Windows" and route through the Windows branch. Patch all three together:

monkeypatch.setattr(sys, "platform", "linux")
monkeypatch.setattr(platform, "system", lambda: "Linux")
monkeypatch.setattr(platform, "release", lambda: "6.8.0-generic")

See tests/agent/test_prompt_builder.py::TestEnvironmentHints for a worked example.

Extending the system prompt's execution-environment block

Factual guidance about the host OS, user home, cwd, terminal backend, and shell (bash vs. PowerShell on Windows) is emitted from agent/prompt_builder.py::build_environment_hints(). This is also where the WSL hint and per-backend probe logic live. The convention:

• Local terminal backend → emit host info (OS, $HOME, cwd) + Windows-specific notes (hostname ≠ username, terminal uses bash not PowerShell).
• Remote terminal backend (anything in _REMOTE_TERMINAL_BACKENDS: docker, singularity, modal, daytona, ssh, vercel_sandbox, managed_modal) → suppress host info entirely and describe only the backend. A live uname/whoami/pwd probe runs inside the backend via tools.environments.get_environment(...).execute(...), cached per process in _BACKEND_PROBE_CACHE, with a static fallback if the probe times out.
• Key fact for prompt authoring: when TERMINAL_ENV != "local", every file tool (read_file, write_file, patch, search_files) runs inside the backend container, not on the host. The system prompt must never describe the host in that case — the agent can't touch it.

Full design notes, the exact emitted strings, and testing pitfalls: references/prompt-builder-environment-hints.md.

Refactor-safety pattern (POSIX-equivalence guard): when you extract inline logic into a helper that adds Windows/platform-specific behavior, keep a _legacy_<name> oracle function in the test file that's a verbatim copy of the old code, then parametrize-diff against it. Example: tests/tools/test_code_execution_windows_env.py::TestPosixEquivalence. This locks in the invariant that POSIX behavior is bit-for-bit identical and makes any future drift fail loudly with a clear diff.

Commit Conventions

type: concise subject line

Optional body.

Types: fix:, feat:, refactor:, docs:, chore:

Key Rules

• Never break prompt caching — don't change context, tools, or system prompt mid-conversation
• Message role alternation — never two assistant or two user messages in a row
• Use get_hermes_home() from hermes_constants for all paths (profile-safe)
• Config values go in config.yaml, secrets go in .env
• New tools need a check_fn so they only appear when requirements are met