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 |
|