docs: comprehensive accuracy audit fixes (35+ corrections)
CRITICAL fixes: - Installation: Remove false prerequisites (installer auto-installs everything except git) - Tools: Remove non-existent 'web_crawl' tool from tools table - Memory: Remove non-existent 'read' action (only add/replace/remove exist) - Code execution: Fix 'search' to 'search_files' in sandbox tools list - CLI commands: Fix --model/--provider/--toolsets/--verbose as chat subcommand flags IMPORTANT fixes: - Installation: Add missing installer features (Node.js, ripgrep, ffmpeg, skills seeding) - Installation: Add 6 missing package extras to table (mcp, honcho, tts-premium, etc) - Installation: Fix mkdir to include all directories the installer creates - Quickstart: Add OpenAI Codex to provider table - CLI: Fix all 'hermes --flag' to 'hermes chat --flag' across all docs - Configuration: Remove non-existent --max-turns CLI flag - Tools: Fix 'search' to 'search_files', add missing 'process' tool - Skills: Remove skills_categories() (not a registered tool) - Cron: Remove unsupported 'daily at 9am' schedule format - TTS: Fix output directory to ~/.hermes/audio_cache/ - Delegation: Clarify depth limit wording - Architecture: Fix default model, chat() signature, file names - Contributing: Fix Python requirement from 3.11+ to 3.10+ - CLI reference: Add missing commands (login, tools, sessions subcommands) - Env vars: Fix TERMINAL_DOCKER_IMAGE default, add HERMES_MODEL
This commit is contained in:
teknium1
@@ -18,21 +18,21 @@ hermes
|
||||
hermes chat -q "Hello"
|
||||
|
||||
# With a specific model
|
||||
hermes --model "anthropic/claude-sonnet-4"
|
||||
hermes chat --model "anthropic/claude-sonnet-4"
|
||||
|
||||
# With a specific provider
|
||||
hermes --provider nous # Use Nous Portal
|
||||
hermes --provider openrouter # Force OpenRouter
|
||||
hermes chat --provider nous # Use Nous Portal
|
||||
hermes chat --provider openrouter # Force OpenRouter
|
||||
|
||||
# With specific toolsets
|
||||
hermes --toolsets "web,terminal,skills"
|
||||
hermes chat --toolsets "web,terminal,skills"
|
||||
|
||||
# Resume previous sessions
|
||||
hermes --continue # Resume the most recent CLI session (-c)
|
||||
hermes --resume <session_id> # Resume a specific session by ID (-r)
|
||||
|
||||
# Verbose mode (debug output)
|
||||
hermes --verbose
|
||||
hermes chat --verbose
|
||||
```
|
||||
|
||||
## Interface Layout
|
||||
@@ -264,5 +264,5 @@ By default, the CLI runs in quiet mode which:
|
||||
|
||||
For debug output:
|
||||
```bash
|
||||
hermes --verbose
|
||||
hermes chat --verbose
|
||||
```
|
||||
|
||||
@@ -46,7 +46,7 @@ The `hermes config set` command automatically routes values to the right file
|
||||
|
||||
Settings are resolved in this order (highest priority first):
|
||||
|
||||
1. **CLI arguments** — `hermes chat --max-turns 100` (per-invocation override)
|
||||
1. **CLI arguments** — e.g., `hermes chat --model anthropic/claude-sonnet-4` (per-invocation override)
|
||||
2. **`~/.hermes/config.yaml`** — the primary config file for all non-secret settings
|
||||
3. **`~/.hermes/.env`** — fallback for env vars; **required** for secrets (API keys, tokens, passwords)
|
||||
4. **Built-in defaults** — hardcoded safe defaults when nothing else is set
|
||||
|
||||
@@ -21,7 +21,7 @@ for r in results["data"]["web"]:
|
||||
print(summary)
|
||||
```
|
||||
|
||||
**Available tools in sandbox:** `web_search`, `web_extract`, `read_file`, `write_file`, `search`, `patch`, `terminal` (foreground only).
|
||||
**Available tools in sandbox:** `web_search`, `web_extract`, `read_file`, `write_file`, `search_files`, `patch`, `terminal` (foreground only).
|
||||
|
||||
## When the Agent Uses This
|
||||
|
||||
|
||||
@@ -65,8 +65,9 @@ The agent knows your connected platforms and home channels — it'll choose sens
|
||||
## Schedule Formats
|
||||
|
||||
- **Relative:** `30m`, `2h`, `1d`
|
||||
- **Human-readable:** `"every 2 hours"`, `"daily at 9am"`
|
||||
- **Interval:** `"every 30m"`, `"every 2h"`
|
||||
- **Cron expressions:** `"0 9 * * *"` (standard 5-field cron syntax)
|
||||
- **ISO timestamps:** `"2026-03-15T09:00:00"` (one-time scheduled execution)
|
||||
|
||||
## Managing Jobs
|
||||
|
||||
|
||||
@@ -33,7 +33,7 @@ delegate_task(tasks=[
|
||||
## Key Properties
|
||||
|
||||
- Each subagent gets its **own terminal session** (separate from the parent)
|
||||
- **Depth limit of 2** — no grandchildren
|
||||
- **No nested delegation** — children cannot delegate further (no grandchildren)
|
||||
- Subagents **cannot** call: `delegate_task`, `clarify`, `memory`, `send_message`, `execute_code`
|
||||
- **Interrupt propagation** — interrupting the parent interrupts all active children
|
||||
- Only the final summary enters the parent's context, keeping token usage efficient
|
||||
|
||||
@@ -41,7 +41,8 @@ The agent uses the `memory` tool with these actions:
|
||||
- **add** — Add a new memory entry
|
||||
- **replace** — Replace an existing entry with updated content
|
||||
- **remove** — Remove an entry that's no longer relevant
|
||||
- **read** — Read current memory contents
|
||||
|
||||
Memory content is automatically injected into the system prompt at session start — there is no `read` action. The agent sees its memories as part of the conversation context.
|
||||
|
||||
## Session Search
|
||||
|
||||
|
||||
@@ -27,8 +27,8 @@ Every installed skill is automatically available as a slash command:
|
||||
You can also interact with skills through natural conversation:
|
||||
|
||||
```bash
|
||||
hermes --toolsets skills -q "What skills do you have?"
|
||||
hermes --toolsets skills -q "Show me the axolotl skill"
|
||||
hermes chat --toolsets skills -q "What skills do you have?"
|
||||
hermes chat --toolsets skills -q "Show me the axolotl skill"
|
||||
```
|
||||
|
||||
## Progressive Disclosure
|
||||
@@ -36,10 +36,9 @@ hermes --toolsets skills -q "Show me the axolotl skill"
|
||||
Skills use a token-efficient loading pattern:
|
||||
|
||||
```
|
||||
Level 0: skills_categories() → ["mlops", "devops"] (~50 tokens)
|
||||
Level 1: skills_list(category) → [{name, description}, ...] (~3k tokens)
|
||||
Level 2: skill_view(name) → Full content + metadata (varies)
|
||||
Level 3: skill_view(name, path) → Specific reference file (varies)
|
||||
Level 0: skills_list() → [{name, description}, ...] (~3k tokens)
|
||||
Level 1: skill_view(name) → Full content + metadata (varies)
|
||||
Level 2: skill_view(name, path) → Specific reference file (varies)
|
||||
```
|
||||
|
||||
The agent only loads the full skill content when it actually needs it.
|
||||
|
||||
@@ -12,9 +12,9 @@ Tools are functions that extend the agent's capabilities. They're organized into
|
||||
|
||||
| Category | Tools | Description |
|
||||
|----------|-------|-------------|
|
||||
| **Web** | `web_search`, `web_extract`, `web_crawl` | Search the web, extract page content, crawl sites |
|
||||
| **Terminal** | `terminal` | Execute commands (local/docker/singularity/modal/ssh backends) |
|
||||
| **File** | `read_file`, `write_file`, `patch`, `search` | Read, write, edit, and search files |
|
||||
| **Web** | `web_search`, `web_extract` | Search the web, extract page content |
|
||||
| **Terminal** | `terminal`, `process` | Execute commands (local/docker/singularity/modal/ssh backends), manage background processes |
|
||||
| **File** | `read_file`, `write_file`, `patch`, `search_files` | Read, write, edit, and search files |
|
||||
| **Browser** | `browser_navigate`, `browser_click`, `browser_type`, etc. | Full browser automation via Browserbase |
|
||||
| **Vision** | `vision_analyze` | Image analysis via multimodal models |
|
||||
| **Image Gen** | `image_generate` | Generate images (FLUX via FAL) |
|
||||
@@ -27,14 +27,14 @@ Tools are functions that extend the agent's capabilities. They're organized into
|
||||
| **Cronjob** | `schedule_cronjob`, `list_cronjobs`, `remove_cronjob` | Scheduled task management |
|
||||
| **Code Execution** | `execute_code` | Run Python scripts that call tools via RPC sandbox |
|
||||
| **Delegation** | `delegate_task` | Spawn subagents with isolated context |
|
||||
| **Clarify** | `clarify` | Ask the user multiple-choice or open-ended questions (CLI-only) |
|
||||
| **Clarify** | `clarify` | Ask the user multiple-choice or open-ended questions |
|
||||
| **MCP** | Auto-discovered | External tools from MCP servers |
|
||||
|
||||
## Using Toolsets
|
||||
|
||||
```bash
|
||||
# Use specific toolsets
|
||||
hermes --toolsets "web,terminal"
|
||||
hermes chat --toolsets "web,terminal"
|
||||
|
||||
# See all available tools
|
||||
hermes tools
|
||||
|
||||
@@ -25,7 +25,7 @@ Convert text to speech with three providers:
|
||||
| Telegram | Voice bubble (plays inline) | Opus `.ogg` |
|
||||
| Discord | Audio file attachment | MP3 |
|
||||
| WhatsApp | Audio file attachment | MP3 |
|
||||
| CLI | Saved to `~/voice-memos/` | MP3 |
|
||||
| CLI | Saved to `~/.hermes/audio_cache/` | MP3 |
|
||||
|
||||
### Configuration
|
||||
|
||||
|
||||
Reference in New Issue
Block a user