docs: extend harness boundary decision to cover Crush as third harness

DECISIONS.md

@@ -4,24 +4,31 @@ Record *why* things are the way they are. Future-you will thank present-you.
 
 ---
 
-## 2026-05-28 — hyperguild and agentsquad are separate harnesses, not competing implementations
+## 2026-05-28 — three active harnesses: hyperguild, agentsquad, Crush (extends earlier boundary decision)
 
-**Context:** After a grill-me architecture review, the question arose whether `hyperguild`
-and `agentsquad` should be consolidated — they both involve agent orchestration and both
-use LiteLLM routing.
+**Context:** After wiring Crush to LiteLLM in May 2026, there are now three active harnesses.
+The earlier boundary decision only covered hyperguild vs agentsquad. Crush's role was undefined.
 
-**Decision:** Keep separate. Different harnesses targeting different orchestration models.
+**Decision:** Three harnesses, three distinct roles, shared skills layer.
 
-- **hyperguild** = Claude Code + MCP. Supervisor pattern. Skills as SKILL.md files invoked
-  inside Claude Code sessions. Routing pod routes skill calls to local models. Brain MCP
-  for knowledge accumulation. Target: disciplined solo coding sessions.
-- **agentsquad** = OpenCode + LiteLLM. Flat peer-to-peer executor/reviewer agents.
-  Per-agent model routing via piguard virtual model names, risk-tiered approval middleware.
-  Target: multi-agent task execution pipelines.
+| Harness | Engine | Primary use | Brain MCP? | Routing pod? | Skills? |
+|---------|--------|-------------|------------|--------------|---------|
+| **hyperguild** | Claude Code + MCP | Disciplined solo coding sessions, TDD/review/debug workflows | Yes | Yes | Yes (SKILL.md) |
+| **agentsquad** | OpenCode + LiteLLM | Multi-agent task execution, executor/reviewer pipelines | No | No (own routing) | Yes (SKILL.md) |
+| **Crush** | Charmbracelet TUI + LiteLLM | Interactive local coding, quick iterations on flamingo | No (not yet) | No (direct LiteLLM) | Yes (SKILL.md) |
 
-Skills (`mathias/skills`) are shared — both harnesses consume the same SKILL.md files.
+**Crush specifics (as of 2026-05-28):**
+- Config: `~/.config/crush/crush.json` on flamingo (see brain: `homelab/facts/crush-litellm-wiring-2026-05`)
+- Connects directly to LiteLLM at `http://koala:4000/v1/` using `sk-local-123`
+- Auth type: `openai-compat` (not `openai`)
+- Does NOT go through the routing pod — model selection is manual in the Crush UI
+- Brain MCP not wired — Crush has no MCP client capability today; revisit if Crush adds MCP support
 
-**Consequences:** No consolidation work. Both READMEs should state their harness explicitly.
+**Shared across all three:**
+- `mathias/skills` — any SKILL.md file works in all three harnesses
+- LiteLLM proxy on koala (`http://koala:4000/v1/`) — Crush and agentsquad both route through it; hyperguild does too for local model calls
+
+**Consequences:** No consolidation needed. crush.json must be kept in sync when litellm_config.yaml model names change. The `crush.json` canonical location is `~/.config/crush/crush.json` on flamingo — not yet tracked in a dotfiles repo (track as tech debt).
 
 ---
 
@@ -58,7 +65,7 @@ as the top priority. As of 2026-05-28, `internal/skills/review/handlers.go` call
 Status of debug, retrospective, and trainer handlers is unverified.
 
 **Decision:** Treat review as the reference implementation. Verify debug, retrospective,
-trainer against the same pattern before shipping new skill work.
+trainer against the same pattern before shipping new skill work. Tracked in issue #32.
 
 **Consequences:** The April concern may be stale for review. A one-pass audit of the other
 three skill handlers closes this fully.