Make Sanhedrin optional in v2.1.0

hooks/sanhedrin-local.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-# sanhedrin-local.py — Local Qwen3.6-35B-A3B Sanhedrin Executioner.
+# sanhedrin-local.py — OpenAI-compatible Sanhedrin Executioner bridge.
 # Drop-in replacement for the Haiku 4.5 subagent that sanhedrin.sh used to spawn.
 #
 # Reads draft from stdin, prints single-line verdict to stdout:
@@ -8,10 +8,10 @@
 #
 # Architecture:
 #   stdin (draft) -> Vestige /api/deep_reference (single semantic query)
-#                 -> mlx_lm.server localhost:8080 (one-shot judgment)
+#                 -> OpenAI-compatible chat endpoint (one-shot judgment)
 #                 -> stdout (single-line verdict)
 #
-# Fail-open: if mlx-server unreachable, print "yes" and exit 0 (don't break
+# Fail-open: if the endpoint is unreachable, print "yes" and exit 0 (don't break
 # the Cognitive Sandwich on infra errors). The wrapping sanhedrin.sh maps
 # "yes" to exit 0, so this preserves existing fail-open semantics.
 
@@ -35,7 +35,11 @@ VESTIGE_BASE_URL = (
     os.environ.get("VESTIGE_BASE_URL") or f"http://127.0.0.1:{DASHBOARD_PORT}"
 ).rstrip("/")
 
-MLX_ENDPOINT = os.environ.get("MLX_ENDPOINT") or "http://127.0.0.1:8080/v1/chat/completions"
+SANHEDRIN_ENDPOINT = (
+    os.environ.get("VESTIGE_SANHEDRIN_ENDPOINT")
+    or os.environ.get("MLX_ENDPOINT")
+    or "http://127.0.0.1:8080/v1/chat/completions"
+)
 VESTIGE_ENDPOINT = (
     os.environ.get("VESTIGE_DEEP_REFERENCE_ENDPOINT")
     or f"{VESTIGE_BASE_URL}/api/deep_reference"
@@ -43,8 +47,12 @@ VESTIGE_ENDPOINT = (
 VESTIGE_HEALTH = (
     os.environ.get("VESTIGE_HEALTH_ENDPOINT") or f"{VESTIGE_BASE_URL}/api/health"
 )
-MODEL = os.environ.get("VESTIGE_SANDWICH_MODEL") or "mlx-community/Qwen3.6-35B-A3B-4bit"
-MLX_TIMEOUT = env_int("MLX_TIMEOUT", 45)
+MODEL = (
+    os.environ.get("VESTIGE_SANHEDRIN_MODEL")
+    or os.environ.get("VESTIGE_SANDWICH_MODEL")
+    or "mlx-community/Qwen3.6-35B-A3B-4bit"
+)
+SANHEDRIN_TIMEOUT = env_int("VESTIGE_SANHEDRIN_TIMEOUT", env_int("MLX_TIMEOUT", 45))
 VESTIGE_TIMEOUT = env_int("VESTIGE_TIMEOUT", 5)
 THINK_RE = re.compile(r"<think>.*?</think>", re.DOTALL | re.IGNORECASE)
 
@@ -289,7 +297,7 @@ def judge(draft: str, evidence: str) -> str:
             "\n\nOn second thought", "\n\nOh wait",
         ],
     }
-    resp = post_json(MLX_ENDPOINT, body, MLX_TIMEOUT)
+    resp = post_json(SANHEDRIN_ENDPOINT, body, SANHEDRIN_TIMEOUT)
     if not isinstance(resp, dict):
         return ""
     try:

hooks/sanhedrin.sh

@@ -17,25 +17,37 @@
 #   sanhedrin.sh (2-8s Haiku subagent, may block) →
 #   synthesis-stop-validator.sh (existing regex hedge check, may block)
 #
-# Opt-in: set VESTIGE_SANHEDRIN_ENABLED=1 in parent shell.
+# Opt-in: set VESTIGE_SANHEDRIN_ENABLED=1 in parent shell, or install with
+# scripts/install-sandwich.sh --enable-sanhedrin.
 # Re-entrancy lock: VESTIGE_EXECUTIONER_ACTIVE=1 inside the subagent.
 #
 # Ship date 2026-04-20.
 
 set -u
 
-# === OPT-OUT GATE ===
-# Post-Cognitive Sanhedrin is ON by default as of 2026-04-21 (birthday
-# launch day). To disable, set VESTIGE_SANHEDRIN_ENABLED=0 in your
-# environment. Default-on guarantees the Cognitive Sandwich fires on
-# fresh machines, Docker containers, GUI-launched Claude Code, and
-# shells without .zshrc — any case where the Claude Code process lacks
-# a sourced profile. The re-entrancy guard (VESTIGE_EXECUTIONER_ACTIVE)
-# below still prevents fork-bombs from the subagent's own Stop hook.
-if [ "${VESTIGE_SANHEDRIN_ENABLED:-1}" = "0" ]; then
-  exit 0
+# === OPT-IN GATE ===
+# Sanhedrin is heavyweight: the default local backend is a ~19 GB model and
+# needs roughly 20+ GB of free RAM. Keep it disabled unless the user explicitly
+# opts in. The installer writes this env file only for --enable-sanhedrin.
+SANHEDRIN_ENV="${VESTIGE_SANHEDRIN_ENV:-$HOME/.claude/hooks/vestige-sanhedrin.env}"
+if [ -f "$SANHEDRIN_ENV" ]; then
+  set +u
+  set -a
+  # shellcheck disable=SC1090
+  . "$SANHEDRIN_ENV" 2>/dev/null || {
+    set +a
+    set -u
+    exit 0
+  }
+  set +a
+  set -u
 fi
 
+case "${VESTIGE_SANHEDRIN_ENABLED:-0}" in
+  1|true|TRUE|yes|YES|on|ON) ;;
+  *) exit 0 ;;
+esac
+
 # === RE-ENTRANCY GUARD ===
 # The Executioner's own Stop hook will fire when it returns — prevent
 # recursive spawns that would fork-bomb the quota.
@@ -114,11 +126,11 @@ if [ -z "$DRAFT" ]; then
 fi
 
 # === VERIFY local executioner bridge available ===
-# 2026-04-25: switched from Haiku 4.5 subagent to local Qwen3.6-35B-A3B
-# via mlx_lm.server (launchd com.vestige.mlx-server). Bridge script
-# fetches Vestige evidence via HTTP API (VESTIGE_DASHBOARD_PORT, default 3927)
-# then judges via MLX_ENDPOINT (default port 8080). Zero per-token cost, fully offline,
-# sub-second-to-15s verdict latency. Fail-open if mlx-server unreachable.
+# 2026-04-25: switched from Haiku 4.5 subagent to an OpenAI-compatible
+# local/remote endpoint. On Apple Silicon the optional launchd path starts
+# mlx_lm.server; on x86 users can point VESTIGE_SANHEDRIN_ENDPOINT at vLLM,
+# Ollama, llama.cpp, or any compatible /v1/chat/completions endpoint.
+# Fail-open if the endpoint is unreachable.
 BRIDGE="$HOME/.claude/hooks/sanhedrin-local.py"
 if [ ! -x "$BRIDGE" ] && [ ! -f "$BRIDGE" ]; then
   exit 0
@@ -191,15 +203,15 @@ case "$TRIMMED" in
 
 $REASON
 
-The Executioner (local Qwen3.6-35B-A3B via mlx_lm.server, fresh context,
-fed Vestige deep_reference evidence over HTTP) judged your draft and
+The Executioner (Sanhedrin endpoint, fresh context, fed Vestige
+deep_reference evidence over HTTP) judged your draft and
 found a contradiction against a high-trust memory.
 
 You may NOT stop. Rewrite WITHOUT the contradicted claim. Use
 mcp__vestige__deep_reference to inspect the cited memory and cite the
 correct replacement pattern from its \`recommended\` field.
 
-Local-only, zero API cost, fully offline. Bridge script:
+Bridge script:
 ~/.claude/hooks/sanhedrin-local.py
 SANHEDRIN_MSG
     exit 2

hooks/settings.fragment.json

@@ -14,7 +14,6 @@
       {
         "hooks": [
           { "type": "command", "command": "$HOME/.claude/hooks/veto-detector.sh", "timeout": 6 },
-          { "type": "command", "command": "$HOME/.claude/hooks/sanhedrin.sh", "timeout": 70 },
           { "type": "command", "command": "$HOME/.claude/hooks/synthesis-stop-validator.sh", "timeout": 6 }
         ]
       }

hooks/settings.sanhedrin.fragment.json

@@ -0,0 +1,23 @@
+{
+  "hooks": {
+    "UserPromptSubmit": [
+      {
+        "hooks": [
+          { "type": "command", "command": "$HOME/.claude/hooks/synthesis-preflight.sh", "timeout": 8 },
+          { "type": "command", "command": "$HOME/.claude/hooks/cwd-state-injector.sh", "timeout": 8 },
+          { "type": "command", "command": "$HOME/.claude/hooks/vestige-pulse-daemon.sh", "timeout": 6 },
+          { "type": "command", "command": "$HOME/.claude/hooks/preflight-swarm.sh", "timeout": 45 }
+        ]
+      }
+    ],
+    "Stop": [
+      {
+        "hooks": [
+          { "type": "command", "command": "$HOME/.claude/hooks/veto-detector.sh", "timeout": 6 },
+          { "type": "command", "command": "VESTIGE_SANHEDRIN_ENABLED=1 $HOME/.claude/hooks/sanhedrin.sh", "timeout": 70 },
+          { "type": "command", "command": "$HOME/.claude/hooks/synthesis-stop-validator.sh", "timeout": 6 }
+        ]
+      }
+    ]
+  }
+}