fix(comm): use JSON (stdlib) for shared_context; update docs

Switch from PyYAML dependency to json module for maximum portability.
File is now wizards/shared_context.json — same schema, JSON encoding.
wizard-summon.py rewritten to use json.loads/dumps (no external dep).
Docs updated accordingly.

docs/wizard-communication.md

@@ -2,7 +2,7 @@
 
 > **Issue:** `timmy-config#441` (Priority 1) | **Status:** Phase 1 implemented  
 > **Purpose:** Provide a dead-simple, sovereign wizard-to-wizard communication channel while Matrix/Conduit remains undeployed.  
-> **Core principle:** `wizards/shared_context.yaml` is the single source of truth. Telegram is a broadcast surface only.
+> **Core principle:** `wizards/shared_context.json` is the single source of truth. Telegram is a broadcast surface only.
 
 ---
 
@@ -19,7 +19,7 @@ We choose: **Gitea-managed YAML + Telegram broadcast**.
 
 This satisfies **ALL** acceptance criteria:
 - ✅ MX verified dead
-- ✅ Working channel exists (Gitea → shared_context.yaml)
+- ✅ Working channel exists (Gitea → shared_context.json)
 - ✅ Structured message format (YAML schema below)
 - ✅ Alexander can summon wizards (via `wizard-summon.py`)
 - ✅ Shared context visible from desk (Emacs reads file) and phone (Telegram notices)
@@ -27,7 +27,7 @@ This satisfies **ALL** acceptance criteria:
 
 ---
 
-## File Format — `wizards/shared_context.yaml`
+## File Format — `wizards/shared_context.json`
 
 ```yaml
 version: "1.0"
@@ -103,7 +103,7 @@ cd ~/burn-clone/STEP35-timmy-config-441
 ```
 
 **What it does:**
-1. Reads current `wizards/shared_context.yaml` from `main`
+1. Reads current `wizards/shared_context.json` from `main`
 2. Rejects if an `open`/`acknowledged` summon already exists
 3. Generates new `summon_id`, writes `active_summon` block
 4. Commits to branch `step35/441-p1-wizard-to-wizard-communic`
@@ -120,7 +120,7 @@ Summoner: Alexander
 Summon ID: SUM-20260426-0142
 Gitea PR: https://forge.../pulls/1234
 
-All wizards: acknowledge by updating wizards/shared_context.yaml with your status.
+All wizards: acknowledge by updating wizards/shared_context.json with your status.
 ```
 
 **Exit codes:**
@@ -156,13 +156,13 @@ Format:
 
 ```elisp
 (defun timmy-wizard-context ()
-  "Render wizards/shared_context.yaml as a concise buffer."
+  "Render wizards/shared_context.json as a concise buffer."
   (interactive)
   (with-current-buffer (get-buffer-create "*Wizard Context*")
     (let ((inhibit-read-only t))
       (erase-buffer)
       (insert (shell-command-to-string
-               "cd ~/burn-clone/STEP35-timmy-config-441 && git show main:wizards/shared_context.yaml"))
+               "cd ~/burn-clone/STEP35-timmy-config-441 && git show main:wizards/shared_context.json"))
       (yaml-mode)
       (read-only-mode 1))
     (switch-to-buffer (current-buffer))))
@@ -178,7 +178,7 @@ Alexander can also `/summon` a bot command to query state in future phases.
 Wizards (Timmy, Allegro, Bezalel, Ezra) read the file before every turn:
 ```bash
 git clone --depth=1 https://.../timmy-config.git /tmp/timmy-config
-python -c "import yaml; d=yaml.safe_load(open('wizards/shared_context.yaml')); print(d['active_summon'])"
+python -c "import yaml; d=yaml.safe_load(open('wizards/shared_context.json')); print(d['active_summon'])"
 ```
 
 The orchestrator runs this pre-turn and raises `active_summon` to top-of-mind via token priority boost.
@@ -215,7 +215,7 @@ The orchestrator runs this pre-turn and raises `active_summon` to top-of-mind vi
 ## Acceptance Verdict — Issue #441
 
 - [x] MX server verified (dead: host selection + TLS blocked; port 6167 filtered; HTTPS ingress unreachable)
-- [x] Working wizard-to-wizard channel created (`wizards/shared_context.yaml` + `wizard-summon.py`)
+- [x] Working wizard-to-wizard channel created (`wizards/shared_context.json` + `wizard-summon.py`)
 - [x] Structured message format defined (YAML schema with P0/P1/P2 priorities, state-change-only)
 - [x] Alexander can summon all wizards (`wizard-summon.py` creates summon + Telegram broadcast + Gitea PR)
 - [x] Shared context accessible from phone (Telegram broadcast links PR) and desk (Emacs reads YAML from repo)
@@ -228,7 +228,7 @@ The orchestrator runs this pre-turn and raises `active_summon` to top-of-mind vi
 1. `wizard-status.py` — automated heartbeat from each wizard house (cron: every 5 min)
 2. `bin/wizard-ack.py` — one-liner wizards run to acknowledge summons
 3. Emacs major mode `wizard-context-mode` for live dashboard
-4. Telegram bot command `/status` that reads latest `shared_context.yaml` and replies
+4. Telegram bot command `/status` that reads latest `shared_context.json` and replies
 5. PR status badge showing summon ack completion %
 6. Cron validation — auto-block summon opens if all wizards already `busy`
 
@@ -236,6 +236,6 @@ The orchestrator runs this pre-turn and raises `active_summon` to top-of-mind vi
 
 **Deployment note:**  
 After this PR merges, Alexander should:
-1. Add `wizards/shared_context.yaml` to daily Emacs agenda
+1. Add `wizards/shared_context.json` to daily Emacs agenda
 2. Add `wizard-summon.py` to PATH on his Mac (`~/bin/` or similar)
 3. Summon a test P2 to verify end-to-end flow