README: herdr-centric bridged as leading approach; bump wiki

- Swap leading approach to the bridged message server driving herdr
  (AgentAPI retained as fallback injector); add mermaid overview
- Update status to Design (2026-07-11)
- Advance wiki submodule to new docs

README.md

@@ -9,26 +9,45 @@ Sibling of [`crush-bridge`](https://git.ltms.dev/systems/vms) (which drives a he
 process*, so it inherits `CLAUDE.md`, hooks, skills, and MCP — just pointed at a
 cheaper/local model.
 
-## Leading approach — AgentAPI
+## Leading approach — herdr-centric message server (`bridged`)
 
-[`coder/agentapi`](https://github.com/coder/agentapi) wraps the Claude Code **CLI** as an
-HTTP server (`POST /message`, `GET /messages`, `GET /events` SSE, `GET /status`). The
-worker's model is whatever env its wrapped `claude` process launches with — so the worker
-server runs with `ANTHROPIC_BASE_URL=https://ollama.ltms.dev` + a bearer token, and the
-primary Opus session talks to it over HTTP.
+A small always-on message server, **`bridged`**, controls
+[herdr](https://herdr.dev) (an agent multiplexer) over its Unix-socket API and exposes a
+clean 2-way messaging API (HTTP/SSE + optional broker). herdr owns the PTYs, multiplexing,
+persistence, and **agent-status events**; `bridged` owns policy (subscription boundary,
+session lifecycle, status-gated delivery) and the client contract. The worker `claude`
+launches with `ANTHROPIC_BASE_URL=https://ollama.ltms.dev` + a bearer token; the primary
+Opus stays env-clean and talks to `bridged` over HTTP.
 
-```
-  Opus (Claude Code, subscription, env CLEAN)
-        │  HTTP  POST /message ─┐
-        ▼                       ▼
-  agentapi server  ──launches──►  claude  (ANTHROPIC_BASE_URL=ollama.ltms.dev, worker model)
-        ▲  GET /events (SSE) ◄──┘
+```mermaid
+flowchart LR
+    OPUS["Opus — primary<br/>(Claude Code, env CLEAN)"]
+    BD["bridged<br/>message server<br/>(not a claude process)"]
+    HERDR["herdr<br/>panes · agent-status"]
+    W["worker claude<br/>ANTHROPIC_BASE_URL set"]
+    M["ollama.ltms.dev<br/>(worker model)"]
+
+    OPUS -->|"POST /message · SSE /events"| BD
+    BD -->|"Unix socket<br/>send_text · events.subscribe"| HERDR
+    HERDR -->|"drives PTY"| W
+    W -->|"inference"| M
+
+    classDef ext fill:#2b6cb0,stroke:#1a365d,color:#ffffff;
+    classDef core fill:#2f855a,stroke:#22543d,color:#ffffff;
+    class OPUS ext
+    class BD,HERDR core
 ```
 
 - **Subscription boundary:** the *primary* never sets `ANTHROPIC_BASE_URL` (stays on
-  Pro/Max). Only the *secondary* process is off-subscription.
+  Pro/Max). Only the *secondary* process is off-subscription — and `bridged` itself is a
+  plain daemon (no Anthropic quota), so it may poll/subscribe freely.
+- **Symmetric 2-way:** herdr can inject a turn into *either* pane (typing keystrokes is
+  subscription-safe), so primary→worker and worker→primary use one mechanism.
 - **Different model per process** sidesteps Claude Code's lack of per-subagent provider
   routing — the worker isn't a subagent, it's its own configured process.
+- **AgentAPI** ([`coder/agentapi`](https://github.com/coder/agentapi)) is retained only as a
+  swappable *fallback injector* behind the same interface. See the wiki for the full
+  design, comparison, and rationale.
 
 ## Docs
 
@@ -46,4 +65,6 @@ Gitea wiki.
 
 ## Status
 
-🟡 Planning — AgentAPI selected as the primary approach (2026-07-08).
+🟢 Design — herdr-centric **`bridged`** message server selected as the primary approach
+(2026-07-11), superseding the AgentAPI plan (2026-07-08). AgentAPI retained as fallback
+injector.