CB-527: retire the ollama profile from the worker choice

The ollama backend is decommissioned, so the example config stops pointing
readers at a dead host and the guard allowlist stops carrying an entry with
no profile behind it — a stale entry there is dead permission, and that list
is the only thing keeping a worker off the primary's subscription.

The second illustrative profile survives as gx11: the example exists to show
`placement: weighted` having something to choose between, and a one-profile
example would quietly stop demonstrating that.

It also moves the CB-523 auto-compact override onto the surviving profile.
That guard had been attached to `ollama` alone, so retiring the profile would
have removed the fleet's only protection against the failure it was written
for — a worker whose prompt is rejected before auto-compact ever fires. The
window belongs on every profile, not on whichever one happened to hit it.

bridged/bridged.example.yaml

@@ -116,15 +116,21 @@ workers:
     # configDir: /Users/me/.ccs/instances/gx10   # CLAUDE_CONFIG_DIR — inherit that profile's skills/MCP
     # cwd: /Users/me/src/myrepo       # pin the working dir; omit to inherit the primary's
     # parityOverlay: [".claude/settings.local.json", ".env", ".envrc"]   # never add .mcp.json — see above
-  ollama:
-    baseUrl: http://ollama.ltms.dev  # local/self-hosted; usually no token
+  gx11:                              # a second backend, so `placement: weighted` has a choice
+    baseUrl: http://gx01.gw:8000     # self-hosted; ccs handles the model + token
     placement: tab
     workspace: bridged-workers
     tabLabel: "worker: {profile} #{n}"
     mcpUrl: http://127.0.0.1:8765/mcp
-    argv: ["ccs", "ollama"]
+    argv: ["ccs", "gx11"]
     weight: 0.5
     maxLoad: 2
+    # Pin an auto-compact window BELOW the served model's context ceiling. The global
+    # ~/.claude/settings.json value is shared by every ccs instance and the primary, so the
+    # per-profile override belongs here. Equal to the ceiling means auto-compact never fires
+    # before the server rejects the prompt, which kills a worker mid-turn (CB-523).
+    env:
+      CLAUDE_CODE_AUTO_COMPACT_WINDOW: "280000"
   # CB-402: a second coding-agent kind, proving the PeerLauncher SPI is provider-neutral.
   # opencode is provider-agnostic and uses NONE of Claude's private seams: no ANTHROPIC_BASE_URL /
   # SubscriptionGuard (so it needs no `guard` host entry), no --mcp-config / --append-system-prompt.
@@ -179,7 +185,6 @@ guard:
   offSubscriptionHosts:
     - gx00.gw
     - gx01.gw
-    - ollama.ltms.dev
 
 # Spawn-readiness gate (CB-306). The launcher blocks until the worker's herdr status is
 # injectable (IDLE/BLOCKED/DONE) or the timeout elapses. 0 disables the gate.