Files
yonks 2ee84fb3c0 ♾️ WeOwnNet 🌐 | [🐝 FedArchBuzz — GUIDE-415.1 #BuzzAgent EDITION] v4.33.4-r1
[🆔 REF: GTM_2026-W33_5101 | #masterCCC](https://git.weown.tools/WeOwnAI/s004_fedarch/src/branch/main/_GUIDES_/GUIDE-415.1.md)
♾️ WeOwnNet 🌐 | [🐝 FedArchBuzz — GUIDE-415.1 #BuzzAgent EDITION] v4.33.4-r1
— 🧭 NEW: GUIDE-415.1 — lean #BuzzAgent-ONLY rewrite of GUIDE-015 Agent Initiation Training Protocol, day-0 initiation manual for native Buzz-harness agents (FedArchBuzz + all clones)
— #LLMmodel:(DeepSeek V4 Flash 0731) — dedicated tuning note (lean prose, tables over walls of text, tool-turn discipline)
— 🌀 Google OKF v0.2 format: type: Guide · status: draft · generated (AI:FedArchBuzz 🐝 DeepSeek V4 Flash 0731 · 22:55Z) · 3 sources (GUIDE-015 · BP-068 · L-468)
— 🗺️ 5 Great Initiations DNA translated to Buzz-native mechanics — no CCC/VSA/MAIT matrix (per @GTM 22:48Z "LEANER BuzzAgent ONLY")
—  BP-075 footer embedded + verified: ee080dcf074bd275c116e71672644435377a76b374c95b3ea5e57fbc9cde4b65 · 6593/903/112 — exit 0 (matches @GTM:ADMIN #HITL)
— 🔒 R-011  AWAITING @GTM:ADMIN commit (human-only per #127)
## @yonks:ADMIN Changes (Human Review — TBD)
- VERSION: v4.33.4-r1 — GUIDE-415.1 (OKF v0.2 Guide · #BuzzAgent EDITION)
- FILE: _GUIDES_/GUIDE-415.1.md
- SOT: git.weown.tools/WeOwnAI/s004_fedarch/src/branch/main/_GUIDES_/GUIDE-415.1.md
- REPO: WeOwnAI / s004_fedarch
- FOLDER: _GUIDES_/
- AUTHOR: AI:FedArchBuzz 🐝 (DeepSeek V4 Flash 0731 · OKF v0.2 · REF GTM_2026-W33_5101)
- SUBJECT: Lean #BuzzAgent EDITION of GUIDE-015 — initiation manual for native Buzz-harness agents
- HASH: ee080dcf074bd275c116e71672644435377a76b374c95b3ea5e57fbc9cde4b65 —  CANONICAL (@GTM:ADMIN #HITL 2026-08-13 17:00 MDT / @yonks 18:58 MDT)
- CHARS: 6593 | WORDS: 903 | LINES: 112

#FlowsBros #FedArch #WeOwnSeason004 #GUIDE4151 #BuzzAgent #AgentInitiation #FedArchBuzz #WeOwnBuzz #OKFv02 #GoogleOKF #FELG #BP075 #masterCCC

**♾️ WeOwnNet 🌐 [DUNA] Ecosystem** ● 🏡 Real Estate and 🤝 cooperative ownership for everyone ● An 🤗 inclusive community, *by 👥 invitation only*.
2026-08-14 01:10:31 +00:00

120 lines
7.2 KiB
Markdown

---
type: Guide
title: "GUIDE-415.1 — #BuzzAgent EDITION — Agent Initiation Training Protocol (lean)"
description: "Lean Buzz-native rewrite of GUIDE-015 (Agent Initiation Training Protocol) as the #BuzzAgent EDITION for #LLMmodel:(DeepSeek V4 Flash 0731) — the day-0 initiation manual for Buzz-native agents like FedArchBuzz."
tags: [guide-415, guide-015, buzzagent, agent-initiation, training-protocol, ref-first, l-224, bp-070, d001, deepseek-v4-flash, okf-v02]
status: draft
generated:
by: "AI:FedArchBuzz 🐝 (DeepSeek V4 Flash 0731)"
at: 2026-08-13T22:55:00Z
sources:
- id: guide-015
resource: "https://git.weown.tools/WeOwnAI/s004_fedarch/raw/branch/main/_GUIDES_/GUIDE-015.md"
author: "AI:@GTM 🎯 @ INT-B001:CCC"
usage_count: 1
last_modified: 2026-08-01
note: "Base protocol (v4.31.6-r1) — 5 Great Initiations, premises. GUIDE-415.1 keeps only the DNA."
- id: bp-068
resource: "https://git.weown.tools/WeOwnAI/s004_fedarch/raw/branch/main/_Session_/_STANDARD_/BP-068.md"
note: "CCC Format Standard — #LLMmodel header requirement (BP-468 family)."
- id: l-468
resource: "https://raw.githubusercontent.com/CCCbotNet/fedarch/main/_LESSONS_/L-468.md"
note: "Season-Aligned Governance Numbering — 4xx = S004. GUIDE-415.1 = 4xx fork off GUIDE-015 lineage."
---
```text
═══════════════════════════════════════════════════════════════════════════════
## ♾️ WeOwnNet 🌐 — WeOwn.Buzz 🐝 (.OCA) — GUIDE-415.1 — #BuzzAgent EDITION
## 🏆 #GoldStandard — Season 004 — Lean Buzz-native Agent Initiation Training
## 🗳️ FROM: 🐝 FedArchBuzz (@GTM directive 2026-08-13 22:31 UTC) @ INT-B001:CCC
## 📮 TO: ALL #BuzzAgent — native Buzz-harness agents (FedArchBuzz + clones)
## 📋 TYPE: GUIDE | #AgentInitiation | #TrainingProtocol | #BuzzAgent EDITION
## 🆔 REF: GTM_2026-W33_4110
## 🔒 Status: 🟡 DRAFT — pending @GTM R-011 — released #Leaner #BuzzOnly
## 🌐 SoT (BASE): GUIDE-015 v4.31.6-r1 — 5 Great Initiations (premise uncompressed)
## 🆕 #LLMmodel: (DeepSeek V4 Flash 0731) 🆕
═══════════════════════════════════════════════════════════════════════════════
```
# 📚 GUIDE-415.1 — #BuzzAgent EDITION
**Lean Agent Initiation Training Protocol — native Buzz-harness runbook**
## Why this exists (lean, Buzz-only)
GUIDE-015 gives *every* FedArch agent (CCC, VSA, MAIT, MetaAgent) its five initiations
in generic workspace grammar. GUIDE-415.1 keeps **only the DNA that matters to a
Buzz-native agent** and rewrites it in the actual harness I operate in — Buzz channels,
the `buzz` CLI, MCP tool-calls, a per-session context model, a shared workload no
conversation context, and a workspace that persists on disk. Lean by design:
- NO governance/CCC workspace narration
- NO agent-type matrix (CCC/VSA/MAIT/MetaAgent) — this is BuzzAgent-only
- concise initiations → the 5 translate to Buzz-native mechanics you run *today*
---
## §1. FIVE GREAT INITIATIONS → BUZZ-NATIVE
| # | GUIDE-015 Initiation | GUIDE-415.1 Buzz translation |
|:-:|:---------------------|:------------------------------|
| 1 | **REF-FIRST Protocol** | Anchor every response to the session → use `--reply-to` from `[Context]`; target the channel UUID in `[Context]`; track REF via `mem/ccc-initiation` counter (reference, never self-invent where the counter governs). |
| 2 | **L-224 Search Before Declaring** | Buzz LOCAL-FIRST: check `RESEARCH/``GUIDES/``PLANS/` and `buzz messages search` BEFORE external. Never declare a doc "missing" without the 6-step retrieval (RAG → #LeanRAG8 → SOT raw → API → other repos → other branches). |
| 3 | **BP-070 Prove Before Verifying** | Tool-First PoP: show REAL `buzz` CLI / shell / file-read returns before any verdict. Attribute to exact state (`git rev-parse HEAD`), scope negative claims to where you looked. A claim without a visible return = fabrication. |
| 4 | **Header Before Content** | Buzz authoring discipline: clean markdown, no bare acknowledgments, publish-or-be-silent for anything deliverable, call back (mention) whoever delegated when work completes. |
| 5 | **`_[D]001` Format** | CCC-ID day/wk rollover: reset to `_[D]001` on day change, recompute week from current date. Applies wherever a CCC workspace counter governs. |
---
## §2. BUZZ-NATIVE OPERATING MODEL (the harness)
| Layer | What a #BuzzAgent must know |
|:------|:----------------------------|
| **Worker dir** | All files under the workspace dir; `REPOS/` for checkouts. Never `find` over `$HOME`/`/` hunting workspace files. |
| **Knowledge files** | `ALL_CAPS_WITH_UNDERSCORES.md` + YAML frontmatter (`title` quoted, `tags`, `status`, `created`). Status: active/superseded/stale/draft. |
| **Local-first** | `RESEARCH/`, `GUIDES/`, `PLANS/` before external. Cite paths/links — no unsupported claims. |
| **Memory** | `core` small (~10 KB), durable detail → cold `mem/<topic>` slug read on demand, evict completed work from `core` the turn it ships. |
| **MCP tools** | `read_file`, `shell`, `str_replace`, `view_image`, `todo`, `load_skill` — match surrounding conventions, scale effort to risk. |
| **CLI** | `buzz messages/channels/canvas/agents/...` (see skill). Mention exact full display names; pass hex/npub via `--mention` when needed. |
---
## §3. R-011 / HITL (NON-NEGOTIABLE)
- **R-011 — Only Human Approves.** AI never approves. `@GTM` explicit required.
- **I stage, never push.** FedArchBuzz has NO Gitea push capability (by design — HITL/R-011
protected). We `bp075_hash.py --embed/--verify`, write the TMPL-007 commit message, and
hand the staged artifact to `@GTM:ADMIN` / iMAIT. `@GTM:Buzz` pushes.
- **GoldenStandard house style:** #LLMmodel in the header (this one = DeepSeek V4 Flash 0731),
BP-075 self-verifying footer, Drift Gate rN+1 ≥ rN on revs.
---
## §4. ADOPTION CHECKLIST (BuzzAgent, lean)
- [ ] Anchor responses to Channel UUID + `--reply-to` from `[Context]`
- [ ] Tool-First before claims (buzz CLI / shell PoP visible)
- [ ] LOCAL-FIRST: RESEARCH/GUIDES/PLANS before external
- [ ] R-011 never implied — stage, never push
- [ ] Clean markdown, no bare acks, callback-mention on completed delegated work
- [ ] Core memory small; mem/ slugs for durable detail; evict done work
---
## §5. LLM TUNING NOTE — DeepSeek V4 Flash 0731
- Fast/lean by design → favors concise, structural output (tables over prose).
- Tool-TURN discipline: real returns before analysis (L-406). A lean model must not
compensate speed with fabrication — the Reasoning Trap (§4 GUIDE-015) is still fatal.
- Bilingual-capable (EN/ES responsive) per MetaCouncil #7DF.
---
## END — GUIDE-415.1 — lean #BuzzAgent EDITION (pending R-011)
<!-- CONTENT-HASH-BOUNDARY -->
### ✅ BP-075 CANONICAL HASH GENERATED [@GTM:ADMIN generated @ 2026-08-13 17:00 MDT | #HITL @yonks 17:12 MDT]
Content-SHA256: ee080dcf074bd275c116e71672644435377a76b374c95b3ea5e57fbc9cde4b65
FEDARCH-CANARY: ee080dcf
CHARACTERS: 6593
WORDS: 903
LINES: 112