mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-26 01:01:40 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 5
4395 commits 908 branches 10 tags 1.8 GiB
Commit graph

3 commits

Author SHA1 Message Date
Teknium
cc6e8941db
feat(honcho): context injection overhaul, 5-tool surface, cost safety, session isolation (#10619) 
Salvaged from PR #9884 by erosika. Cherry-picked plugin changes onto
current main with minimal core modifications.

Plugin changes (plugins/memory/honcho/):
- New honcho_reasoning tool (5th tool, splits LLM calls from honcho_context)
- Two-layer context injection: base context (summary + representation + card)
  on contextCadence, dialectic supplement on dialecticCadence
- Multi-pass dialectic depth (1-3 passes) with early bail-out on strong signal
- Cold/warm prompt selection based on session state
- dialecticCadence defaults to 3 (was 1) — ~66% fewer Honcho LLM calls
- Session summary injection for conversational continuity
- Bidirectional peer targeting on all 5 tools
- Correctness fixes: peer param fallback, None guard on set_peer_card,
  schema validation, signal_sufficient anchored regex, mid->medium level fix

Core changes (~20 lines across 3 files):
- agent/memory_manager.py: Enhanced sanitize_context() to strip full
  <memory-context> blocks and system notes (prevents leak from saveMessages)
- run_agent.py: gateway_session_key param for stable per-chat Honcho sessions,
  on_turn_start() call before prefetch_all() for cadence tracking,
  sanitize_context() on user messages to strip leaked memory blocks
- gateway/run.py: skip_memory=True on 2 temp agents (prevents orphan sessions),
  gateway_session_key threading to main agent

Tests: 509 passed (3 skipped — honcho SDK not installed locally)
Docs: Updated honcho.md, memory-providers.md, tools-reference.md, SKILL.md

Co-authored-by: erosika <erosika@users.noreply.github.com>
 2026-04-15 19:12:19 -07:00
erosika
c02c3dc723 fix(honcho): plugin drift overhaul -- observation config, chunking, setup wizard, docs, dead code cleanup 
Salvaged from PR #5045 by erosika.

- Replace memoryMode/peer_memory_modes with granular per-peer observation config
- Add message chunking for Honcho API limits (25k chars default)
- Add dialectic input guard (10k chars default)
- Add dialecticDynamic toggle for reasoning level auto-bump
- Rewrite setup wizard with cloud/local deployment picker
- Switch peer card/profile/search from session.context() to direct peer APIs
- Add server-side observation sync via get_peer_configuration()
- Fix base_url/baseUrl config mismatch for self-hosted setups
- Fix local auth leak (cloud API keys no longer sent to local instances)
- Remove dead code: memoryMode, peer_memory_modes, linkedHosts, suppress flags, SOUL.md aiPeer sync
- Add post_setup hook to memory_setup.py for provider-specific setup wizards
- Comprehensive README rewrite with full config reference
- New optional skill: autonomous-ai-agents/honcho
- Expanded memory-providers.md with multi-profile docs
- 9 new tests (chunking, dialectic guard, peer lookups), 14 dead tests removed
- Fix 2 pre-existing TestResolveConfigPath filesystem isolation failures
 2026-04-05 12:34:11 -07:00
teknium1
f2e24faaca feat: optional skills — official skills shipped but not activated by default 
Add 'optional-skills/' directory for official skills that ship with the repo
but are not copied to ~/.hermes/skills/ during setup. They are:
- NOT shown to the model in the system prompt
- NOT copied during hermes setup/update
- Discoverable via 'hermes skills search' labeled as 'official'
- Installable via 'hermes skills install' with builtin trust (no third-party warning)
- Auto-categorized on install based on directory structure

Implementation:
- OptionalSkillSource adapter in tools/skills_hub.py (search/fetch/inspect)
- Added to create_source_router() as first source (highest priority)
- Trust level 'builtin' for official skills in skills_guard.py
- Friendly install message for official skills (no third-party warning)
- 'official' label in cyan in search results and skill list

First optional skill: Blackbox CLI (autonomous-ai-agents/blackbox)
- Multi-model coding agent with built-in judge/Chairman pattern
- Delegates to Claude, Codex, Gemini, and Blackbox models
- Open-source CLI (GPL-3.0, TypeScript, forked from Gemini CLI)
- Requires paid Blackbox AI API key

Refs: #475
 2026-03-06 01:24:11 -08:00