mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-26 01:01:40 +00:00
docs: fix 30+ inaccuracies across documentation (#9023)
Cross-referenced all docs pages against the actual codebase and fixed: Reference docs (cli-commands.md, slash-commands.md, profile-commands.md): - Fix: hermes web -> hermes dashboard (correct subparser name) - Fix: Wrong provider list (removed deepseek, ai-gateway, opencode-zen, opencode-go, alibaba; added gemini) - Fix: Missing tts in hermes setup section choices - Add: Missing --image flag for hermes chat - Add: Missing --component flag for hermes logs - Add: Missing CLI commands: debug, backup, import - Fix: /status incorrectly marked as messaging-only (available everywhere) - Fix: /statusbar moved from Session to Configuration category - Add: Missing slash commands: /fast, /snapshot, /image, /debug - Add: Missing /restart from messaging commands table - Fix: /compress description to match COMMAND_REGISTRY - Add: --no-alias flag to profile create docs Configuration docs (configuration.md, environment-variables.md): - Fix: Vision timeout default 30s -> 120s - Fix: TTS providers missing minimax and mistral - Fix: STT providers missing mistral - Fix: TTS openai base_url shown with wrong default - Fix: Compression config showing stale summary_model/provider/base_url keys (migrated out in config v17) -> target_ratio/protect_last_n Getting-started docs: - Fix: Redundant faster-whisper install (already in voice extra) - Fix: Messaging extra description missing Slack Developer guide: - Fix: architecture.md tool count 48 -> 47, toolset count 40 -> 19 - Fix: run_agent.py line count 9,200 -> 10,700 - Fix: cli.py line count 8,500 -> 10,000 - Fix: main.py line count 5,500 -> 6,000 - Fix: gateway/run.py line count 7,500 -> 9,000 - Fix: Browser tools count 11 -> 10 - Fix: Platform adapter count 15 -> 18 (add wecom_callback, api_server) - Fix: agent-loop.md wrong budget sharing (not shared, independent) - Fix: agent-loop.md non-existent _get_budget_warning() reference - Fix: context-compression-and-caching.md non-existent function name - Fix: toolsets-reference.md safe toolset includes mixture_of_agents (it doesn't) - Fix: toolsets-reference.md hermes-cli tool count 38 -> 36 Guides: - Fix: automate-with-cron.md claims daily at 9am is valid (it's not) - Fix: delegation-patterns.md Max 3 presented as hard cap (configurable) - Fix: sessions.md group thread key format (shared by default, not per-user) - Fix: cron-internals.md job ID format and JSON structure
This commit is contained in:
Teknium
GitHub
parent
4ca6668daf
commit
ba50fa3035
16 changed files with 65 additions and 52 deletions
|
|
@ -6,7 +6,7 @@ description: "Detailed walkthrough of AIAgent execution, API modes, tools, callb
|
|||
|
||||
# Agent Loop Internals
|
||||
|
||||
The core orchestration engine is `run_agent.py`'s `AIAgent` class — roughly 9,200 lines that handle everything from prompt assembly to tool dispatch to provider failover.
|
||||
The core orchestration engine is `run_agent.py`'s `AIAgent` class — roughly 10,700 lines that handle everything from prompt assembly to tool dispatch to provider failover.
|
||||
|
||||
## Core Responsibilities
|
||||
|
||||
|
|
@ -181,10 +181,7 @@ These tools modify agent state directly and return synthetic tool results withou
|
|||
The agent tracks iterations via `IterationBudget`:
|
||||
|
||||
- Default: 90 iterations (configurable via `agent.max_turns`)
|
||||
- Shared across parent and child agents — a subagent consumes from the parent's budget
|
||||
- Two-tier budget pressure via `_get_budget_warning()`:
|
||||
- At 70%+ usage (caution tier): appends `[BUDGET: Iteration X/Y. N iterations left. Start consolidating your work.]` to the last tool result
|
||||
- At 90%+ usage (warning tier): appends `[BUDGET WARNING: Iteration X/Y. Only N iteration(s) left. Provide your final response NOW.]`
|
||||
- Each agent gets its own budget. Subagents get independent budgets capped at `delegation.max_iterations` (default 50) — total iterations across parent + subagents can exceed the parent's cap
|
||||
- At 100%, the agent stops and returns a summary of work done
|
||||
|
||||
### Fallback Model
|
||||
|
|
@ -224,7 +221,7 @@ After each turn:
|
|||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `run_agent.py` | AIAgent class — the complete agent loop (~9,200 lines) |
|
||||
| `run_agent.py` | AIAgent class — the complete agent loop (~10,700 lines) |
|
||||
| `agent/prompt_builder.py` | System prompt assembly from memory, skills, context files, personality |
|
||||
| `agent/context_engine.py` | ContextEngine ABC — pluggable context management |
|
||||
| `agent/context_compressor.py` | Default engine — lossy summarization algorithm |
|
||||
|
|
|
|||
|
|
@ -32,8 +32,8 @@ This page is the top-level map of Hermes Agent internals. Use it to orient yours
|
|||
│ ┌──────┴───────┐ ┌──────┴───────┐ ┌──────┴───────┐ │
|
||||
│ │ Compression │ │ 3 API Modes │ │ Tool Registry│ │
|
||||
│ │ & Caching │ │ chat_compl. │ │ (registry.py)│ │
|
||||
│ │ │ │ codex_resp. │ │ 48 tools │ │
|
||||
│ │ │ │ anthropic │ │ 40 toolsets │ │
|
||||
│ │ │ │ codex_resp. │ │ 47 tools │ │
|
||||
│ │ │ │ anthropic │ │ 19 toolsets │ │
|
||||
│ └──────────────┘ └──────────────┘ └──────────────┘ │
|
||||
└─────────────────────────────────────────────────────────────────────┘
|
||||
│ │
|
||||
|
|
@ -52,8 +52,8 @@ This page is the top-level map of Hermes Agent internals. Use it to orient yours
|
|||
|
||||
```text
|
||||
hermes-agent/
|
||||
├── run_agent.py # AIAgent — core conversation loop (~9,200 lines)
|
||||
├── cli.py # HermesCLI — interactive terminal UI (~8,500 lines)
|
||||
├── run_agent.py # AIAgent — core conversation loop (~10,700 lines)
|
||||
├── cli.py # HermesCLI — interactive terminal UI (~10,000 lines)
|
||||
├── model_tools.py # Tool discovery, schema collection, dispatch
|
||||
├── toolsets.py # Tool groupings and platform presets
|
||||
├── hermes_state.py # SQLite session/state database with FTS5
|
||||
|
|
@ -76,7 +76,7 @@ hermes-agent/
|
|||
│ └── trajectory.py # Trajectory saving helpers
|
||||
│
|
||||
├── hermes_cli/ # CLI subcommands and setup
|
||||
│ ├── main.py # Entry point — all `hermes` subcommands (~5,500 lines)
|
||||
│ ├── main.py # Entry point — all `hermes` subcommands (~6,000 lines)
|
||||
│ ├── config.py # DEFAULT_CONFIG, OPTIONAL_ENV_VARS, migration
|
||||
│ ├── commands.py # COMMAND_REGISTRY — central slash command definitions
|
||||
│ ├── auth.py # PROVIDER_REGISTRY, credential resolution
|
||||
|
|
@ -99,7 +99,7 @@ hermes-agent/
|
|||
│ ├── process_registry.py # Background process management
|
||||
│ ├── file_tools.py # read_file, write_file, patch, search_files
|
||||
│ ├── web_tools.py # web_search, web_extract
|
||||
│ ├── browser_tool.py # 11 browser automation tools
|
||||
│ ├── browser_tool.py # 10 browser automation tools
|
||||
│ ├── code_execution_tool.py # execute_code sandbox
|
||||
│ ├── delegate_tool.py # Subagent delegation
|
||||
│ ├── mcp_tool.py # MCP client (~2,200 lines)
|
||||
|
|
@ -109,7 +109,7 @@ hermes-agent/
|
|||
│ └── environments/ # Terminal backends (local, docker, ssh, modal, daytona, singularity)
|
||||
│
|
||||
├── gateway/ # Messaging platform gateway
|
||||
│ ├── run.py # GatewayRunner — message dispatch (~7,500 lines)
|
||||
│ ├── run.py # GatewayRunner — message dispatch (~9,000 lines)
|
||||
│ ├── session.py # SessionStore — conversation persistence
|
||||
│ ├── delivery.py # Outbound message delivery
|
||||
│ ├── pairing.py # DM pairing authorization
|
||||
|
|
@ -117,9 +117,10 @@ hermes-agent/
|
|||
│ ├── mirror.py # Cross-session message mirroring
|
||||
│ ├── status.py # Token locks, profile-scoped process tracking
|
||||
│ ├── builtin_hooks/ # Always-registered hooks
|
||||
│ └── platforms/ # 15 adapters: telegram, discord, slack, whatsapp,
|
||||
│ └── platforms/ # 18 adapters: telegram, discord, slack, whatsapp,
|
||||
│ # signal, matrix, mattermost, email, sms,
|
||||
│ # dingtalk, feishu, wecom, weixin, bluebubbles, homeassistant, webhook
|
||||
│ # dingtalk, feishu, wecom, wecom_callback, weixin,
|
||||
│ # bluebubbles, homeassistant, webhook, api_server
|
||||
│
|
||||
├── acp_adapter/ # ACP server (VS Code / Zed / JetBrains)
|
||||
├── cron/ # Scheduler (jobs.py, scheduler.py)
|
||||
|
|
@ -211,7 +212,7 @@ A shared runtime resolver used by CLI, gateway, cron, ACP, and auxiliary calls.
|
|||
|
||||
### Tool System
|
||||
|
||||
Central tool registry (`tools/registry.py`) with 47 registered tools across 20 toolsets. Each tool file self-registers at import time. The registry handles schema collection, dispatch, availability checking, and error wrapping. Terminal tools support 6 backends (local, Docker, SSH, Daytona, Modal, Singularity).
|
||||
Central tool registry (`tools/registry.py`) with 47 registered tools across 19 toolsets. Each tool file self-registers at import time. The registry handles schema collection, dispatch, availability checking, and error wrapping. Terminal tools support 6 backends (local, Docker, SSH, Daytona, Modal, Singularity).
|
||||
|
||||
→ [Tools Runtime](./tools-runtime.md)
|
||||
|
||||
|
|
@ -223,7 +224,7 @@ SQLite-based session storage with FTS5 full-text search. Sessions have lineage t
|
|||
|
||||
### Messaging Gateway
|
||||
|
||||
Long-running process with 14 platform adapters, unified session routing, user authorization (allowlists + DM pairing), slash command dispatch, hook system, cron ticking, and background maintenance.
|
||||
Long-running process with 18 platform adapters, unified session routing, user authorization (allowlists + DM pairing), slash command dispatch, hook system, cron ticking, and background maintenance.
|
||||
|
||||
→ [Gateway Internals](./gateway-internals.md)
|
||||
|
||||
|
|
|
|||
|
|
@ -53,7 +53,7 @@ Hermes has two separate compression layers that operate independently:
|
|||
|
||||
### 1. Gateway Session Hygiene (85% threshold)
|
||||
|
||||
Located in `gateway/run.py` (search for `_maybe_compress_session`). This is a **safety net** that
|
||||
Located in `gateway/run.py` (search for `Session hygiene: auto-compress`). This is a **safety net** that
|
||||
runs before the agent processes a message. It prevents API failures when sessions
|
||||
grow too large between turns (e.g., overnight accumulation in Telegram/Discord).
|
||||
|
||||
|
|
|
|||
|
|
@ -37,16 +37,25 @@ Jobs are stored in `~/.hermes/cron/jobs.json` with atomic write semantics (write
|
|||
|
||||
```json
|
||||
{
|
||||
"id": "job_abc123",
|
||||
"id": "a1b2c3d4e5f6",
|
||||
"name": "Daily briefing",
|
||||
"prompt": "Summarize today's AI news and funding rounds",
|
||||
"schedule": "0 9 * * *",
|
||||
"schedule": {
|
||||
"kind": "cron",
|
||||
"expr": "0 9 * * *",
|
||||
"display": "0 9 * * *"
|
||||
},
|
||||
"skills": ["ai-funding-daily-report"],
|
||||
"deliver": "telegram:-1001234567890",
|
||||
"repeat": null,
|
||||
"repeat": {
|
||||
"times": null,
|
||||
"completed": 42
|
||||
},
|
||||
"state": "scheduled",
|
||||
"next_run": "2025-01-16T09:00:00Z",
|
||||
"run_count": 42,
|
||||
"enabled": true,
|
||||
"next_run_at": "2025-01-16T09:00:00Z",
|
||||
"last_run_at": "2025-01-15T09:00:00Z",
|
||||
"last_status": "ok",
|
||||
"created_at": "2025-01-01T00:00:00Z",
|
||||
"model": null,
|
||||
"provider": null,
|
||||
|
|
|
|||
|
|
@ -12,7 +12,7 @@ The messaging gateway is the long-running process that connects Hermes to 14+ ex
|
|||
|
||||
| File | Purpose |
|
||||
|------|---------|
|
||||
| `gateway/run.py` | `GatewayRunner` — main loop, slash commands, message dispatch (~7,500 lines) |
|
||||
| `gateway/run.py` | `GatewayRunner` — main loop, slash commands, message dispatch (~9,000 lines) |
|
||||
| `gateway/session.py` | `SessionStore` — conversation persistence and session key construction |
|
||||
| `gateway/delivery.py` | Outbound message delivery to target platforms/channels |
|
||||
| `gateway/pairing.py` | DM pairing flow for user authorization |
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue