hermes-agent/agent
teknium1 b159002078 feat: multi-agent architecture — named agents with routing, tool policies, and isolated workspaces
Implements the full multi-agent system for Hermes Agent, allowing a single
installation to host multiple named agents, each with its own model,
personality, toolset, workspace, and session history.

## New Files

- gateway/agent_registry.py: AgentConfig, ToolPolicy, SubagentPolicy,
  AgentRegistry, TOOL_PROFILES (minimal/coding/messaging/full), and
  normalize_tool_config() for shorthand YAML parsing

- gateway/router.py: BindingRouter with 7-tier deterministic routing
  (chat_id > peer > guild+type > guild > platform+type > platform > default)

## Core Changes

- model_tools.py: get_tool_definitions() accepts agent_tool_policy for
  per-agent tool filtering; handle_function_call() extended enabled_tools
  check to gate ALL tool calls (defense-in-depth)

- gateway/session.py: build_session_key() now accepts agent_id and dm_scope
  parameters, replacing hardcoded 'agent:main' with 'agent:{agent_id}'

- tools/memory_tool.py: MemoryStore accepts memory_dir parameter for
  per-agent memory isolation

- agent/prompt_builder.py: build_context_files_prompt() accepts
  agent_workspace for SOUL.md lookup; build_skills_system_prompt()
  accepts agent_skills_dir for per-agent skill overlay

- run_agent.py: AIAgent accepts agent_tool_policy and agent_workspace,
  passes policy through to get_tool_definitions()

- gateway/run.py: Initializes AgentRegistry + BindingRouter, resolves
  agent per-message in _handle_message(), passes config to _run_agent(),
  adds /agents command

- cli.py: --agent flag for selecting named agent profiles, /agents
  slash command, agent config override for model/personality/tools

- hermes_cli/config.py: agents/bindings in DEFAULT_CONFIG, version 7

- tools/delegate_tool.py: Configurable max_depth per-agent, tool policy
  inheritance from parent to child

## Config Format

agents:
  main:
    default: true
  coder:
    model: anthropic/claude-sonnet-4
    personality: 'You are a coding assistant.'
    tools: coding  # or [tool1, tool2] or {profile: x, deny: [...]}

bindings:
  - agent: coder
    telegram: '-100123456'

## Tests

168 new tests across 3 test files (agent_registry, router, integration).
All 3106 tests pass.
2026-03-11 03:21:12 -07:00
..
__init__.py Refactor Terminal and AIAgent cleanup 2026-02-21 22:31:43 -08:00
auxiliary_client.py fix: vision auto-detection now falls back to custom/local endpoints 2026-03-09 15:36:19 -07:00
context_compressor.py fix: use correct role for summary message in context compressor 2026-03-08 23:09:04 -07:00
display.py fix: replace silent exception swallowing with debug logging across tools 2026-03-10 06:59:20 -07:00
insights.py chore: add GLM/Kimi/MiniMax models to insights pricing (zero cost) 2026-03-06 19:12:14 -08:00
model_metadata.py chore: add context lengths for Kimi and MiniMax models 2026-03-06 19:01:38 -08:00
prompt_builder.py feat: multi-agent architecture — named agents with routing, tool policies, and isolated workspaces 2026-03-11 03:21:12 -07:00
prompt_caching.py Refactor Terminal and AIAgent cleanup 2026-02-21 22:31:43 -08:00
redact.py Merge PR #713: docs: clarify Telegram token regex constraint 2026-03-10 16:59:54 -07:00
skill_commands.py feat: platform-conditional skill loading + Apple/macOS skills 2026-03-07 00:47:54 -08:00
trajectory.py Refactor Terminal and AIAgent cleanup 2026-02-21 22:31:43 -08:00