Hermes Agent

---
name: hermes-agent
description: hermes-agent — 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-config-editing
 - hermes-windows
---
# 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/

## Quick Start

```bash
# 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 auth Interactive credential manager
hermes auth add PROVIDER Add OAuth or API-key credential (e.g. nous, openai-codex, qwen-oauth)
hermes auth list List stored credentials
hermes auth remove PROVIDER Remove a stored credential
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
```

### Troubleshooting Cron Errors

When a cron job reports errors:

1. **Check if the script exists.** For `no_agent: true` jobs, the script path is absolute — verify it with `ls <path>`. If missing, the job is orphaned and should be removed.
2. **Check the last run status.** `cronjob action='list'` shows `last_status` and `last_run_at` — a pattern of repeated errors on a stale job means it's abandoned.
3. **Distinguish ghost jobs from real failures.** A cron job that references a non-existent script (e.g., `mission-tick.sh`) is not a runtime bug — it's an orphaned job from a deleted project. Remove it with `cronjob action='remove'`.
4. **Check for paused vs active state.** Paused jobs won't run; scheduled jobs will. Don't waste time debugging a paused job.

### 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](https://hermes-agent.nousresearch.com/docs/reference/slash-commands).
The registry of record is `hermes_cli/commands.py` for the classic Python CLI and gateway surfaces. The separate TypeScript `--tui` also has its own slash registry under `ui-tui/src/app/slash/commands/`; check both before adding or renaming a command. As of the current TUI, `/switch` is an alias of `/sessions` (along with `/session` and `/resume`). Registering `/switch` as a Python-side model command creates a split-brain collision: autocomplete/help may describe model switching while `hermes --tui` executes the session picker. Use `/model` for model switching or choose a non-conflicting command name.

### 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/skills/` | Installed skills |
| `~/.hermes/skills/DIRECTORY.md` | Generated index of installed skills; regenerate with `python ~/.hermes/scripts/regen_skill_directory.py` (user-local — verify it exists) |
| `~/.hermes/sessions/` | Gateway routing index, request dumps, *.jsonl transcripts (and optional per-session JSON snapshots when sessions.write_json_snapshots: true) |
~/.hermes/state.db Canonical session store (SQLite + FTS5)
~/.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) — see Context Compression Tuning below |
| `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) |

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

### Context Compression Tuning

Hermes compresses older messages when context nears the model's limit. Two settings control this — they serve different purposes and should NOT be equal:

- **`threshold`** (OEM default 0.50) — *when* compression activates. Context usage exceeds this ratio of `context_length`, and Hermes starts summarizing older messages to make room.
- **`target_ratio`** (OEM default 0.20) — how aggressively to compress *down to*. A lower number means more aggressive compression, but setting it too low causes constant re-triggering because context fills back up quickly after each summary cycle.

**The relationship matters:** `threshold` must be **higher than** `target_ratio`. If they're equal (e.g., both 0.80), compression triggers at the threshold and tries to compress *to* the same value — it does summarization work with almost zero gain, wasting tokens on summaries that barely move the needle.

If `target_ratio` is too low relative to threshold (OEM's 0.20 vs 0.50 = 4x gap), every compression cycle eats a big chunk of context. This creates constant churn: compress → fill up again quickly → compress again, burning tokens on repeated summaries.

**Tuning for long-context models (96K+ effective):**
1. Set `threshold` close to where your model's quality starts degrading (the "long context tail"). For Qwen3.6-27B at 96K effective: **0.85–0.90**.
2. Set `target_ratio` below threshold with enough gap to create meaningful room, but not so low that it causes thrashing. **0.65–0.75** is reasonable for most setups.
3. Avoid equal values — they produce wasted compute on minimal gain.

Example tuned config:
```yaml
compression:
 enabled: true
 threshold: 0.85 # wait until context is genuinely full
 target_ratio: 0.70 # compress down to leave room before next cycle
```

### 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` |
| OpenCode Zen | API key | `OPENCODE_ZEN_API_KEY` |
| OpenCode Go | API key | `OPENCODE_GO_API_KEY` |
| Qwen OAuth | OAuth | `hermes auth add 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 where the active profile permits it; unavailable in the default profile |
| `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 **on by default** — tool output (terminal stdout, `read_file`, web content, subagent summaries, etc.) is scanned for strings that look like API keys, tokens, and secrets before it enters the conversation context and logs. Leave it enabled for normal use:

```bash
hermes config set security.redact_secrets true # keep enabled globally
```

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

Disable only when you deliberately need raw credential-like strings for debugging or redactor development:
```bash
hermes config set security.redact_secrets false
```

**Credential-bearing file edits:** Do not use `patch` on files such as voice configs, cron JSON, or integration settings when nearby lines may contain plaintext credentials. Unified diffs can echo unchanged surrounding secrets even when ordinary read output is redacted. Use a narrowly scoped script that changes the exact JSON/YAML field without printing file contents, then verify only the non-secret field value or a boolean comparison.

### 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:

```bash
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`)

```bash
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:
```yaml
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 interactively
terminal(command="tmux new-session -d -s resumed 'hermes --resume <session-id>'", timeout=10)

# Resume a specific session with a one-shot follow-up query.
# Global flags must precede the `chat` subcommand; `-q` belongs to `chat`.
terminal(command="hermes --profile <profile> --resume <session-id> chat -q 'Continue from the previous blocker and verify the result.'", timeout=300)
```

### 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/` in the upstream Hermes repo.

### 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`, and
orchestrator profiles can opt into the broader `kanban` toolset. Normal
sessions still have zero `kanban_*` schema footprint unless configured.

- **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/orchestrator toolset:** `kanban_show`, `kanban_complete`,
 `kanban_block`, `kanban_heartbeat`, `kanban_comment`, `kanban_create`,
 `kanban_link`; profiles that explicitly enable the `kanban` toolset
 outside a dispatcher-spawned task also get `kanban_list` and
 `kanban_unblock` for board routing.
- **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 `failure_limit` consecutive spawn failures
 (default 2; configurable via `kanban.failure_limit` or per-task
 `max_retries`).
- **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` (user-local — verify it exists)
(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, inspect the child
environment through an approved terminal diagnostic in a profile that permits
host-side execution, or use a dedicated no-agent diagnostic script; do not
invoke the blocked sandbox from the default profile. Full diagnostic
recipe: follow the sandbox recovery steps in this skill.

### Testing / Contributing

**`scripts/run_tests.sh` (user-local — verify it exists) 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:

```bash
"/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.

---

## 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 auth` — re-authenticate OAuth providers (or `hermes auth add <provider>`)
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 length resolution

Hermes resolves context length from the active runtime model/provider unless you pin `model.context_length` in `config.yaml`. A pinned value wins immediately and bypasses auto-resolution for the main model. That is why context can appear "stuck" across model/provider switches even when the runtime changes.

Practical rule:
- If you want true auto behavior, leave `model.context_length` unset.
- If you need to force a fixed window, set `model.context_length` explicitly.

For local servers (LM Studio, Ollama, vLLM, llama.cpp), Hermes can often query the endpoint and infer the active model's context window. For remote/cloud providers, behavior depends on what the provider exposes and what Hermes knows about that provider/model. If detection fails, Hermes falls back to configured/default values rather than guessing perfectly.

To enable true auto-detection again:
- Remove `model.context_length` from `config.yaml`, or set it to `0`/`null` if the current code path treats those as "unset".
- Start a new session after the change. Existing sessions keep the context window they started with.

To intentionally override auto-detection:
- Set `model.context_length` under `model:`.
- Example: `hermes config set model.context_length 128000`
- Then start a new session so the new window is picked up.

Pitfalls:
- Do NOT set `model.context_length: auto` unless the current Hermes version explicitly supports that literal. In current practice, true auto means the key is absent (or sometimes `0`/`null`), not the string `auto`.
- `settings.context_length` does NOT control the main runtime context window. It is easy to write that key and think you changed the limit when you did not.
- When a user asks for "auto," do not overwrite their config with a fresh fixed number while troubleshooting. First inspect whether `model.context_length` is pinned and remove that pin if true auto is the goal.
- If the displayed context length does not match expectations, inspect the live config and remember that `.env` model/provider overrides can change the active runtime while a pinned `model.context_length` still forces the window.

### 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:
```bash
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`

### Platform-specific issues
- **Discord bot silent**: Must enable **Message Content Intent** in Bot → Privileged Gateway Intents. For full setup flow (permissions, OAuth2 scopes, guild install), see [discord-connect](../../productivity/discord-connect/SKILL.md).
- **Slack bot only works in DMs**: Must subscribe to `message.channels` event. Without it, the bot ignores public channels.
- **Windows-specific issues** (`Alt+Enter` newline, WinError 10106, UTF-8 BOM config, test suite, line endings): see the dedicated **Windows-Specific Quirks** section above.

### Repeated /v1/chat/completions calls (model spam)

Symptom: LM Studio or another local server shows repeated chat completions every few seconds, even when you're not actively chatting.

Key facts (use these first):

- Hermes does NOT run health checks via /v1/chat/completions. A legitimate health check would be a lightweight HTTP GET to an endpoint like /health or /v1/models — never full chat calls.
- The environment_probe flag only probes local toolchain (Python/pip/uv); it does not ping models.
- If you see repeated POST /v1/chat/completions with 2-message conversations on the same model, this is almost always a stuck agent loop or runaway session — not normal behavior.

Diagnosis steps:

1) Confirm which machine is sending traffic:
 - Check Hermes gateway logs: tail ~/.hermes/logs/gateway.log | grep "chat/completions"
 - If nothing shows up recently, the local Hermes instance isn't the source.
 - On Windows (the remote node), check LM Studio active connections or network tab to see which client is calling /v1/chat/completions.

2) Look for stuck processes:
 - Linux/macOS: ps aux | grep -iE "hermes|gateway" | grep -v grep
 - Windows: Task Manager → Processes → look for multiple python.exe or hermes instances. End duplicates that aren't intentionally running (e.g., a hung agent loop).
 - If you're using Hermes Desktop in remote-gateway mode, close it temporarily to see if the spam stops.

3) Check dashboard-backend:
 - It has /health endpoints but does NOT use chat completions as health checks.
 - If logs show repeated internal calls to /v1/chat/completions from the backend process, that's a bug — disable or kill the backend until fixed.

4) Identify by user-agent:
 - LM Studio and Hermes logs often include the User-Agent (e.g., "hermes-gateway/...", "dashboard-backend", etc.). Use this to pinpoint which client is spamming.

If the pattern persists after killing obvious culprits, escalate to checking config.yaml and .env for any custom health-check or probe scripts that may have been added manually — Hermes itself does not include one using chat completions.
If `auxiliary` tasks (vision, compression, session_search) fail silently, the `auto` provider can't find a backend. Either set `OPENROUTER_API_KEY` or `GOOGLE_API_KEY`, or explicitly configure each auxiliary task's provider:

### Local custom-provider vision hangs

On current builds, a configured vision route such as `auxiliary.vision.provider: custom:<name>` can normalize to `<name>` inside `resolve_vision_provider_client()`. If both `providers.custom:<name>` and a legacy `providers.<name>` block exist, vision may use the legacy block's base URL while ordinary auxiliary calls use the named custom provider correctly.

Diagnosis:
- Resolve or log the actual vision client and inspect `client.base_url`; do not trust config readback alone.
- Compare it with a direct capped request to the intended endpoint.
- If the local vision model has `parallel: 1`, a timed-out uncapped request can occupy its only slot and make later tests queue. Verify slot recovery with a short capped text request before retesting.

A second local-endpoint pitfall is that `_build_call_kwargs()` currently omits `max_tokens` for ordinary OpenAI-compatible auxiliary calls. Some multimodal models do not stop promptly on image requests without an output cap. A configuration-level workaround is an explicit intended `auxiliary.vision.base_url` plus `auxiliary.vision.extra_body.max_tokens` (choose a practical real-analysis cap, commonly 512–2048). Verify through `call_llm(task='vision', ...)`, not only raw curl. If a small explicit cap makes the same image return immediately, the model/mmproj is healthy and the hang is request shaping or stale endpoint routing.

### Compression / summary model issues

If you set a local compression/summary model (e.g., via `compression.summary_model`) but Hermes still uses the old provider or silently fails:

- **Check the provider is fully defined.** Setting `compression.summary_provider: custom:<name>` is not enough — if that provider block in config.yaml has no `base_url`/`api_key`, Hermes cannot reach it and will ignore the compression model or fall back. Always verify:
 - providers.<name>.base_url is set (e.g., your LM Studio endpoint)
 - providers.<name>.api_key is set (even if dummy, e.g., "lm-studio")
- **Compression uses the same provider as the primary model, with a different model name.** The internal compressor overrides only the model; it does not switch providers. If your primary model points at LM Studio and your compression model is another model available at that endpoint, ensure both models are actually loaded in LM Studio.
- **/compress does nothing if context is too short.** Hermes only compresses when token count exceeds a threshold (default ~111k tokens; 0.85 * context_length). If under the threshold:
 - No log entry appears for compression
 - No API call is made
 - The command silently no-ops
- **To verify routing:**
 - Either let a session grow long enough and run `/compress`
 - Or inspect `~/.hermes/logs/gateway.log` after a real compression event for:
 - "Session split detected" (compression)
 - provider / model references that match your local endpoint
```bash
hermes config set auxiliary.vision.provider <your_provider>
hermes config set auxiliary.vision.model <model_name>
```

---

## Where to Find Things

| Looking for... | Location |
|----------------|----------|
| Config options | `hermes config edit` or [Configuration docs](https://hermes-agent.nousresearch.com/docs/user-guide/configuration) |
| Available tools | `hermes tools list` or [Tools reference](https://hermes-agent.nousresearch.com/docs/reference/tools-reference) |
| Slash commands | `/help` in session or [Slash commands reference](https://hermes-agent.nousresearch.com/docs/reference/slash-commands) |
| Skills catalog | `hermes skills browse` or [Skills catalog](https://hermes-agent.nousresearch.com/docs/reference/skills-catalog) |
| Provider setup | `hermes model` or [Providers guide](https://hermes-agent.nousresearch.com/docs/integrations/providers) |
| Platform setup | `hermes gateway setup` or [Messaging docs](https://hermes-agent.nousresearch.com/docs/user-guide/messaging/) |
| MCP servers | `hermes mcp list` or [MCP guide](https://hermes-agent.nousresearch.com/docs/user-guide/features/mcp) |
| Profiles | `hermes profile list` or [Profiles docs](https://hermes-agent.nousresearch.com/docs/user-guide/profiles) |
| Cron jobs | `hermes cron list` or [Cron docs](https://hermes-agent.nousresearch.com/docs/user-guide/features/cron) |
| Memory | `hermes memory status` or [Memory docs](https://hermes-agent.nousresearch.com/docs/user-guide/features/memory) |
| Env variables | `hermes config env-path` or [Env vars reference](https://hermes-agent.nousresearch.com/docs/reference/environment-variables) |
| CLI commands | `hermes --help` or [CLI reference](https://hermes-agent.nousresearch.com/docs/reference/cli-commands) |
| Gateway logs | `~/.hermes/logs/gateway.log` |
| Session files | `hermes sessions browse` (reads state.db) |
| 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`:**
```python
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

```bash
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` (user-local — verify it exists) 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:

```bash
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:

```python
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, 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:
.

**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

## Hermes configuration and CLI-ecosystem management (consolidated)

The configuration ecosystem previously split across multiple narrow skills (`hermes-config-editing`, `hermes-desktop-config`, `hermes-provider-switching`, `hermes-windows`) is consolidated here:

IMPORTANT (agent constraint):
- The agent CANNOT write ~/.hermes/config.yaml directly (enforced).
- Always use one of these for configuration changes:
 - hermes config set <key> <value> for simple, supported keys.
 - hermes config edit to open the file in the user's editor; give them exact edits.
 - A Python script via terminal that reads/writes config.yaml using yaml.safe_load/dump (preferred for multi-field or nested changes).
- For provider/auxiliary routing:
 - Define providers under providers: with a custom:<name> key, api URL, default_model, etc.
 - Update auxiliary.<task>.provider and .model to target the new provider.
 - Always leave vision unchanged unless explicitly asked; it is pinned separately (Mac LM Studio).

Configuring auxiliary providers (e.g., Unsloth, local endpoints):
- Use this when routing auxiliary tasks (compression, web_extract, skills_hub, etc.) to a specific provider/endpoint.
- If direct writes to config.yaml are blocked, use:
 - hermes config edit with precise instructions, or
 - A small Python script that:
 - Loads config via yaml.safe_load,
 - Updates providers + auxiliary entries,
 - Dumps back with yaml.dump.
- When adding a new provider (e.g., Unsloth on another machine):
 - Use a clear key like custom:my-local-server.
 - Set api, default_model, and key_env/api_key as appropriate.
- Wire auxiliary tasks by setting each task’s provider and model to that new provider.
- Always verify live:
 - Send a quick test request (curl or requests) to the endpoint.
 - Confirm it responds and note the actual "model" in the response.
Pitfalls:
- **OpenAI image generation backend is separate from OpenAI Codex.** For generated images use `image_gen.provider: openai` with `image_gen.model: gpt-image-2-medium` (or low/high). Do not set the main/chat model to `gpt-image-2-medium`; that model is only for the `image_generate` backend and will 400 if used as a chat model. If `image_generate` reports `OPENAI_API_KEY not set` while `hermes auth list` shows `openai-api`, check whether the tool/cron process exported `~/.hermes/.env`; the OpenAI image plugin may need the local fallback patch reapplied via the apply-patches helper (user-local — verify it exists).
- **OpenAI Codex auxiliary routing must not set `base_url`.** For `auxiliary.<task>.provider: openai-codex`, set `model` only. If `base_url: https://chatgpt.com/backend-api/codex` is present, `_resolve_task_provider_model()` treats it as a `custom` endpoint and the OpenAI SDK calls `/chat/completions`, which hits Cloudflare/HTML instead of the Codex Responses adapter. Fix by removing `base_url`, `api_key`, and `api_mode` from the affected auxiliary task entries, then verify resolution returns `('openai-codex', '<model>', None)` and a smoke `call_llm(task='title_generation', ...)` succeeds.
- **Local-first resolution. When the user names a model that looks like a GGUF filename or a known local model, query every configured local LM Studio / llama.cpp endpoint FIRST before routing through OpenRouter or any cloud provider.** Defaulting to OpenRouter for a model the user runs locally is a hard correction — route local models to local endpoints. Check curl http://<ip>:<port>/v1/models on each local endpoint before touching cloud configs.
- Users often say "use gpt-4o-2024-08-06" while their server is actually running a different model under that label (e.g., Unsloth serving an OSS model). Always:
 - Trust the live response's "model" field over what the user or UI claims.
 - Update config to reflect the actual model name from the endpoint.
- Ensure reachability:
 - Ping the host first, then test the port (e.g., 8888) with curl.
 - Timeouts mean service not running, wrong bind address, or firewall — do not assume config is at fault.

After config changes, verify via:
- hermes config show (confirm model/auxiliary sections), or
- A small Python script that prints affected config entries.

### What this consolidated section covers

- Configure and verify model/provider swaps, including safe full-provider and per-subsystem overrides.
- Edit advanced configuration safely (including compression thresholds and auxiliary provider blocks).
- Handle local/global setup paths for the desktop gateway and dashboard connection.
- Handle Windows reinstall/update/launcher edge cases in a single operational workflow.

### Recommended operating flow

1. Confirm scope: global runtime switch vs subsystem override before editing.
2. Validate current auth/config state and read active profile-specific values.
3. **If the user names a model that could be local** (GGUF filename, no provider prefix, model known to run on a local LM Studio instance), query each configured local endpoint (`curl <ip>:<port>/v1/models`) before touching cloud providers. Match the model ID from the live response.
4. Apply minimal delta edits for the target component (`config.yaml` via supported tooling, not manual scattered edits).
5. Restart/refresh only where required by process scope (gateway or terminal backend).
6. Verify with readback before reporting success.

### Consolidated reference files

The historical reference files and templates from the original narrow skills are consolidated into this skill's own `references/` and `templates/`.

## Self-Check / Safety (mandatory)

Before declaring any Hermes config/setup task complete:

1) Verify externally:
 - Run the command/query and confirm it matches what you promised (hermes status, hermes tools, etc.).
2) Scope check:
 - Confirm the change is exactly in the requested scope; no sneaky global or production changes.
3) Memory/skill updates:
 - Do not overwrite canonical docs solely on agent reasoning; compare with existing skill/AGENTS.md first.

Human-only gates (do NOT auto-execute without explicit approval):
- Switching provider/model/config values (`model.provider`, `model.default`, aux providers/task overrides).
- Editing credentials, API keys, or `.env` entries used by live runtime.
- Restarting/stopping gateway, services, or terminal/backend workers.
- Removing/enabling/disabling installed skills/tools/skills indexes.
- Running destructive shell operations affecting Hermes code/config or project-critical files.

For these:
- Present the proposed change in 3–6 bullets.
- Wait for explicit go-ahead before executing.