Skip to content

Add robust unified config system, memory retention with cleanup, expanded CLIs and CI-enabled test harness#1

Merged
akbad merged 65 commits intomainfrom
feature/auto-delete-retention
Dec 26, 2025
Merged

Add robust unified config system, memory retention with cleanup, expanded CLIs and CI-enabled test harness#1
akbad merged 65 commits intomainfrom
feature/auto-delete-retention

Conversation

@akbad
Copy link
Copy Markdown
Owner

@akbad akbad commented Dec 10, 2025

Summary

Major additions:

  1. Unified configuration system ➔ layered YAML config architecture for all of Beehive (agents, tools, paths, retention policies). Supports team defaults with local overrides.

  2. Memory auto-cleanup ➔ retention-based cleanup for AI memory backends with soft-delete to trash before permanent removal.

  3. PAL MCP integration ➔ dynamic per-CLI configuration generation for PAL (Gemini, Codex, Claude) with role-based prompt routing.

  4. Developer experience ➔ Makefile for local CI commands, improved documentation, mypy type checking fixes.

Unified configuration system

A general-purpose config layer for Beehive dealing with:

  • Enabled agents (Claude, Gemini, Codex, OpenCode)
  • Tool server ports and paths
  • Retention periods per storage backend
  • File paths (expandable with ~ and env vars)

Config hierarchy

env vars
↑
local.yml (personal overrides)
↑
queen.yml (team settings)
↑
comb.yml (fixed/upstream)

Components (lib/pollen/)

  • config_loader.py ➔ central config loader with typed accessors, path expansion, duration parsing
  • config_cli.py ➔ shell interface (get-config agents, get-config --check agent claude)
  • validate_config.py ➔ config validation with type checking
  • CONFIGURATION.md ➔ full reference documentation

Memory auto-cleanup

How it works

Old memories are soft-deleted to .wax/trash/ with a 30-day grace period (configurable), then permanently removed. Runs automatically on beehive start or manually via CLI.

Handlers (lib/pollen/cleanup/handlers/)

Backend Default retention period Method
claude-mem 30d SQLite DELETE + VACUUM
serena 90d Move .md files to trash
qdrant 180d REST API scroll + delete
memory-mcp 365d JSONL rewrite

CLI scripts (bin/)

  • beehive-prune ➔ runs cleanup of stale memories based on configured retention periods
  • beehive-empty-trash ➔ purges trash (purgatory for stale memories) immediately
  • beehive-wipe ➔ complete data erasure

PAL MCP integration

Replaces static per-CLI JSON configs with dynamically generated configurations, allowing users to tweak exactly which models and roles to use with each CLI.

Components

  • configs/pal/settings.yaml ➔ base PAL settings and role definitions
  • configs/scripts/generate-pal-configs.py ➔ generates CLI-specific configs from templates
  • queen.ymlpal: section controls model and role settings per CLI

Infrastructure

  • CI workflow (.github/workflows/ci.yml) ➔ pytest + mypy on push/PR
  • Makefilemake test, make typecheck, make ci for local dev
  • Python packagingpyproject.toml with uv, dev dependencies
  • Type safety ➔ mypy-clean with cast() for TypedDict accessors, proper handler typing
  • Test suite ➔ fully covers handlers, trash, and state management

akbad added 21 commits December 7, 2025 07:35
…uv tool` and `check-prereqs` helper script instead of `python3`/`pip`/`brew`
…trypoints, dependency groups and pytest config
@akbad akbad changed the title Add robust, unified config system, memory retention with cleanup, expanded CLIs and test harness Add robust, unified config system, memory retention with cleanup, expanded CLIs and CI-enabled test harness Dec 11, 2025
@akbad akbad changed the title Add robust, unified config system, memory retention with cleanup, expanded CLIs and CI-enabled test harness Add robust unified config system, memory retention with cleanup, expanded CLIs and CI-enabled test harness Dec 11, 2025
@akbad akbad force-pushed the feature/auto-delete-retention branch from 4f6fea2 to eb7c267 Compare December 26, 2025 09:19
@akbad
Copy link
Copy Markdown
Owner Author

akbad commented Dec 26, 2025

Absolutely ridiculous scope creep. But the code is pristine. Goodnight

@akbad akbad merged commit bac158e into main Dec 26, 2025
2 checks passed
@akbad akbad deleted the feature/auto-delete-retention branch December 26, 2025 11:11
akbad added a commit that referenced this pull request Mar 12, 2026
…nded CLIs, MCP fixes and CI-enabled test harness (#1)
akbad pushed a commit that referenced this pull request Apr 3, 2026
Ranks all 7 platforms: Hermes Agent (#1), OpenHands (#2), Letta (#3),
CoPaw (#4), OpenFang (#5), Memoh (#6), OpenClaw (#7). Recommends
Hermes + OpenHands as optimal integration stack. Includes head-to-head
matrix, top 10 feature merge ideas, tradeoff analysis, and phased
next steps.

https://claude.ai/code/session_01Ta99Gdof2dBsruDBdNRFZz
akbad added a commit that referenced this pull request Apr 3, 2026
* Add agent framework evaluation: Bureau vs OpenClaw, CoPaw, Hermes, Memoh, LettaBot, LocalAGI

Compares Bureau's competitive position against six always-on multi-channel
assistant frameworks. Documents two-track development plan: Track A
(multi-channel expansion) and Track B (dev tool improvements) with
concrete sprint ordering.

https://claude.ai/code/session_01Ta99Gdof2dBsruDBdNRFZz

* Add integration analysis reports for CoPaw, Letta/LettaBot, Memoh, OpenFang

Four detailed reports comparing Bureau integration fit across memory
architecture, security model, channel support, SWE features, and
autonomous capabilities. Hermes, OpenClaw, and OpenHands reports
still in progress.

https://claude.ai/code/session_01Ta99Gdof2dBsruDBdNRFZz

* Add high-impact feature merge brainstorms to CoPaw, Letta, Memoh reports

Each report now includes a Section 12 with 8-12 creative, technically
specific ideas for Bureau integration that leverage the unique
combination of both platforms.

https://claude.ai/code/session_01Ta99Gdof2dBsruDBdNRFZz

* Add high-impact feature merge brainstorms to Memoh and OpenFang reports

Memoh: 12 ideas including per-role container isolation, parallel
debugging swarms, and container-isolated MCP server vetting.
OpenFang: feature merge section with autonomous Hands + Bureau
coding role combinations.

https://claude.ai/code/session_01Ta99Gdof2dBsruDBdNRFZz

* Add OpenHands integration analysis report

Covers Docker sandbox architecture, 77.6% SWE-bench performance,
event stream state management, and integration proposal with Bureau
as orchestrator and OpenHands as sandboxed execution backend.

https://claude.ai/code/session_01Ta99Gdof2dBsruDBdNRFZz

* Add high-impact feature merge brainstorms to OpenHands report

11 ideas including verified code reviews via sandbox execution,
step-gated editing with test rollback, multi-model tournament
execution, and real attack testing in Scrimmage Mode sandboxes.

https://claude.ai/code/session_01Ta99Gdof2dBsruDBdNRFZz

* Add Hermes Agent and OpenClaw integration analysis reports

Hermes: 5-layer memory architecture, autonomous learning loop,
6 channels, 6 execution backends. Rated strongest integration
candidate for Bureau.

OpenClaw: 23+ channels, 346k stars, companion apps, voice/canvas.
Maximalist option with highest reward/risk. 9 CVEs in March 2026.

https://claude.ai/code/session_01Ta99Gdof2dBsruDBdNRFZz

* Add high-impact feature merge brainstorms to Hermes Agent report

12 ideas including role-scoped evolving memory, Assess Mode with
episodic recall, self-improving skills via feedback loop, zero-
clarification dispatch, and cross-backend execution routing.

https://claude.ai/code/session_01Ta99Gdof2dBsruDBdNRFZz

* Add high-impact feature merge brainstorms to OpenClaw report

10 ideas including voice-driven code review via Talk Mode, Live
Canvas diff theater, companion app Micro Mode approvals, ClawHub
skill transpiler, and iMessage CI/CD war room.

https://claude.ai/code/session_01Ta99Gdof2dBsruDBdNRFZz

* Add synthesis README with ranked integration recommendations

Ranks all 7 platforms: Hermes Agent (#1), OpenHands (#2), Letta (#3),
CoPaw (#4), OpenFang (#5), Memoh (#6), OpenClaw (#7). Recommends
Hermes + OpenHands as optimal integration stack. Includes head-to-head
matrix, top 10 feature merge ideas, tradeoff analysis, and phased
next steps.

https://claude.ai/code/session_01Ta99Gdof2dBsruDBdNRFZz

---------

Co-authored-by: Claude <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant