Make all Cognitive Sandwich hooks opt-in

CHANGELOG.md

@@ -7,13 +7,15 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [2.1.0] - 2026-04-27 — "Cognitive Sandwich Goes Local"
 
-The Sanhedrin Executioner — Vestige's veto layer for Claude Code responses — now runs entirely on a local MLX model (`mlx-community/Qwen3.6-35B-A3B-4bit`). Zero API cost per Claude turn, fully offline, no Anthropic round-trip on the critical path. Combined with four pre-cognitive UserPromptSubmit hooks (synthesis-preflight, cwd-state-injector, vestige-pulse-daemon, preflight-swarm), Vestige now ships a complete "Cognitive Sandwich" — Vestige memories injected before the model thinks, local Sanhedrin veto after the model speaks — installable in one command on a MacBook.
+The Sanhedrin Executioner — Vestige's veto layer for Claude Code responses — can run against a local MLX model (`mlx-community/Qwen3.6-35B-A3B-4bit`) when explicitly enabled. Combined with four pre-cognitive UserPromptSubmit hooks (synthesis-preflight, cwd-state-injector, vestige-pulse-daemon, preflight-swarm), Vestige now ships a complete "Cognitive Sandwich" — Vestige memories injected before the model thinks, optional Sanhedrin veto after the model speaks.
+
+> 2026-05-01 hotfix: Sanhedrin, preflight, and all Vestige Claude Code hooks are optional by default. The default installer activates no hooks, makes no automatic model calls, removes old Vestige hook wiring from previous v2.1.0 installs, no longer starts MLX, and removes the old v2.1.0 MLX launchd job on reinstall. Users who want preflight can opt in with `--enable-preflight`; users who want Sanhedrin can opt in with `--enable-sanhedrin`; Apple Silicon local MLX autostart is a separate `--with-launchd` flag, and x86 users can point `--sanhedrin-endpoint` at any OpenAI-compatible `/v1/chat/completions` endpoint.
 
 ### Added
 
 - **`hooks/`** — first-class harness-side companion to the Vestige MCP server. 9 production hooks designed for `~/.claude/hooks/`:
-  - `sanhedrin.sh` — Stop hook that invokes the local Qwen Executioner via the Python bridge.
+  - `sanhedrin.sh` — optional Stop hook that invokes the Sanhedrin Executioner via the Python bridge only when `VESTIGE_SANHEDRIN_ENABLED=1`.
-  - `sanhedrin-local.py` — local backend that POSTs to `mlx_lm.server` (`localhost:8080`) with Vestige evidence injected via the dashboard `/api/deep_reference` HTTP endpoint. TRUST_FLOOR=0.55 evidence filter + topical-relevance gate + inference-verb ban + 8 worked few-shots covering true positives AND false-positive guards.
+  - `sanhedrin-local.py` — OpenAI-compatible backend that POSTs to the configured Sanhedrin endpoint with Vestige evidence injected via the dashboard `/api/deep_reference` HTTP endpoint. TRUST_FLOOR=0.55 evidence filter + topical-relevance gate + inference-verb ban + 8 worked few-shots covering true positives AND false-positive guards.
   - `synthesis-preflight.sh` — UserPromptSubmit hook that POSTs the user prompt to `/api/deep_reference` and injects the trust-scored reasoning chain into context.
   - `cwd-state-injector.sh` — captures git status, branch, modified files, open PRs/issues.
   - `vestige-pulse-daemon.sh` — surfaces fresh Vestige dream insights from the past 20 min.
@@ -21,18 +23,21 @@ The Sanhedrin Executioner — Vestige's veto layer for Claude Code responses —
   - `synthesis-stop-validator.sh` — Stop hook regex against forbidden hedging patterns.
   - `veto-detector.sh` — fast 50ms regex pre-screen against `veto`-tagged Vestige memories.
   - `synthesis-gate.sh` — legacy v1 trigger (kept for backward compat).
-  - `settings.fragment.json` — JSON snippet merged into `~/.claude/settings.json` by the installer.
+  - `settings.fragment.json` — empty default fragment used to remove old Vestige hook wiring without enabling new hooks.
+  - `settings.preflight.fragment.json` — opt-in UserPromptSubmit hooks used only with `--enable-preflight`.
+  - `settings.sanhedrin.fragment.json` — opt-in JSON snippet used only with `--enable-sanhedrin`.
 - **Dashboard `/api/changelog` endpoint** — bounded REST event feed for recent `DreamCompleted` and `ConnectionDiscovered` events, used by the Pulse hook to inject fresh synthesis into Claude Code context.
 - **`agents/`** — `executioner.md` (legacy/fallback Haiku 4.5 path), `lateral-thinker.md`, `synthesis-composer.md`.
-- **`launchd/com.vestige.mlx-server.plist.template`** — auto-start `mlx_lm.server` with the Qwen3.6-35B-A3B-4bit model on login. Templated with `__HOME__` and `__MODEL__` placeholders.
+- **`launchd/com.vestige.mlx-server.plist.template`** — optional Apple Silicon helper that auto-starts `mlx_lm.server` with the Qwen3.6-35B-A3B-4bit model on login. Templated with `__HOME__` and `__MODEL__` placeholders.
-- **`scripts/install-sandwich.sh`** — one-command installer that stages hooks, agents, plist, jq-merges the settings fragment, and `launchctl load`s the plist. Backs up `settings.json` to `.bak.pre-sandwich`. Supports `--force`, `--no-launchd`, `--include-memory-loader`, `--src=PATH`.
+- **`scripts/install-sandwich.sh`** — one-command installer that stages hooks, agents, jq-merges the settings fragment, and backs up `settings.json` to `.bak.pre-sandwich`. Supports `--force`, `--enable-sanhedrin`, `--with-launchd`, `--sanhedrin-endpoint`, `--sanhedrin-model`, `--include-memory-loader`, `--src=PATH`.
-- **`scripts/check-sandwich-prereqs.sh`** — comprehensive prereq verifier (Apple Silicon, Python 3.10+, jq, uv, mlx-lm, hf, claude, vestige-mcp, model on disk, MCP HTTP up, server up, plist installed, settings wired).
+- **`scripts/check-sandwich-prereqs.sh`** — verifier that default installs have no Vestige hooks wired, with `--preflight` and `--sanhedrin` checks for optional layers.
 - **`docs/COGNITIVE_SANDWICH.md`** — architecture diagram, install guide, performance notes (82 tok/s on M3 Max), uninstall, configuration env vars.
 - **PR #48** — `VESTIGE_DATA_DIR` env-var support + tilde expansion + secure unix perms (thanks @Jelloeater) — directly addresses the ghost env-vars exposed by v2.0.9 cleanup.
 
 ### Changed
 
-- **Sanhedrin Executioner default backend swapped from Anthropic Haiku 4.5 → local `mlx_lm.server` + Qwen3.6-35B-A3B-4bit.** Anthropic API key no longer required for the post-cognitive layer. The `executioner.md` agent definition is retained as manual/fallback only when invoked explicitly via `Task(subagent_type='executioner')`.
+- **Sanhedrin, preflight, and all Vestige Claude Code hooks are optional by default.** Default installs run on x86 and low-memory machines without wiring any Vestige hook, calling Claude, downloading the 19 GB MLX model, or starting MLX. Reinstalling the default v2.1.0 hotfix removes the old Vestige hook wiring and the old mandatory `com.vestige.mlx-server` launchd job if they exist.
+- **Sanhedrin Executioner backend swapped from Anthropic Haiku 4.5 → OpenAI-compatible endpoint, with local `mlx_lm.server` + Qwen3.6-35B-A3B-4bit as the Apple Silicon opt-in path.** Anthropic API key no longer required for the post-cognitive layer. The `executioner.md` agent definition is retained as manual/fallback only when invoked explicitly via `Task(subagent_type='executioner')`.
 - **All hooks sanitized for public release** — replaced hardcoded personal absolute paths with `$HOME` / `$VESTIGE_*` env vars; removed personal regex tokens.
 - **NPM binary installer now follows package version** — `vestige-mcp-server@2.1.0` downloads release assets from `v2.1.0` instead of a stale hardcoded binary tag, while local workspace installs skip the release-asset download before the tag exists.
 
@@ -41,6 +46,7 @@ The Sanhedrin Executioner — Vestige's veto layer for Claude Code responses —
 - `cargo test --workspace --release --no-fail-fast`: **1,229 passing, 0 failed** (366 vestige-core + 358 vestige-mcp lib + 4 vestige-mcp bin + 497 e2e + 4 doctests).
 - Sanhedrin bridge smoke checks: Python bytecode compilation passes, fail-open bridge invocation returns `yes`, and public hook settings validate as JSON.
 - 8-day Sandwich dogfood: **84% pass rate, 16% legitimate vetoes** caught real hallucinations.
+- 2026-05-01 hotfix checks: `cargo test --workspace --no-fail-fast`, `cargo build --release --workspace`, shell/Python/JSON validation, and default/preflight/Sanhedrin installer dry-runs all pass.
 
 ### Closes
 
@@ -48,14 +54,20 @@ The Sanhedrin Executioner — Vestige's veto layer for Claude Code responses —
 
 ### Prerequisites for the Cognitive Sandwich
 
-- macOS Apple Silicon (M1+) — required for MLX
 - Python 3.10+
+- `jq`
+- `vestige-mcp`
+- Claude Code
+
+Optional local MLX Sanhedrin backend:
+
+- macOS Apple Silicon (M1+) — required for the launchd MLX helper only
 - ~22 GB free RAM (Qwen3.6-35B-A3B-4bit at runtime)
 - First-run model download: ~19 GB from Hugging Face (cached locally thereafter)
 
 ### Migration
 
-None required for existing Vestige users. The Cognitive Sandwich is opt-in via `scripts/install-sandwich.sh`. The MCP server, schema, and tool surface are bit-identical to v2.0.9.
+None required for existing Vestige users. The default installer now removes old v2.1.0 Claude Code hook wiring. The Cognitive Sandwich hook layers are opt-in via `--enable-preflight`, `--enable-sanhedrin`, or `--enable-sandwich`. The MCP server, schema, and tool surface are bit-identical to v2.0.9.
 
 ---
 

README.md

@@ -22,10 +22,10 @@ Built on 130 years of memory research — FSRS-6 spaced repetition, prediction e
 
 ## What's New in v2.1.0 "Cognitive Sandwich Goes Local"
 
-v2.1.0 adds an opt-in Claude Code hook harness around the existing Vestige MCP server. The MCP tool surface and database schema stay backward compatible, while the new local Sanhedrin verifier and preflight hooks can inject trusted memory context before Claude answers and check drafts against high-trust Vestige evidence before delivery.
+v2.1.0 adds an opt-in Claude Code hook harness around the existing Vestige MCP server. The MCP tool surface and database schema stay backward compatible, while optional preflight hooks can inject trusted memory context before Claude answers and optional Sanhedrin hooks can check drafts against high-trust Vestige evidence before delivery.
 
-- **Local Sanhedrin Executioner.** The post-response verifier now runs through `mlx_lm.server` with `mlx-community/Qwen3.6-35B-A3B-4bit` by default, so the veto layer can run offline on Apple Silicon without Anthropic API calls.
+- **Optional Sanhedrin Executioner.** The post-response verifier can run through `mlx_lm.server` with `mlx-community/Qwen3.6-35B-A3B-4bit` on Apple Silicon, or through any OpenAI-compatible endpoint on x86, but it is never enabled by default.
-- **One-command Cognitive Sandwich installer.** `scripts/install-sandwich.sh` stages hooks, agents, and a launchd plist, merges the Claude Code hooks block, and prints real verification commands.
+- **One-command Cognitive Sandwich installer.** `scripts/install-sandwich.sh` stages hook files and agents, removes old v2.1.0 hook wiring by default, and only activates Claude Code hooks with explicit `--enable-preflight`, `--enable-sanhedrin`, or `--enable-sandwich`.
 - **Pulse hook backed by `/api/changelog`.** Fresh dream and connection events can be injected into the next Claude Code prompt context without blocking the prompt.
 - **`VESTIGE_DATA_DIR` support.** `--data-dir` now has an env-var fallback, tilde expansion, secure directory creation, and clear precedence docs.
 - **NPM release wrapper fixed.** `vestige-mcp-server@2.1.0` now downloads binaries from the matching `v2.1.0` GitHub release tag instead of an old hardcoded release.

docs/COGNITIVE_SANDWICH.md

@@ -2,7 +2,7 @@
 
 **Vestige's defense-in-depth safety architecture for Claude Code.**
 
-The Cognitive Sandwich wraps every Claude Code response in two layers of cognitive scaffolding:
+The default Cognitive Sandwich installer only stages files and removes old v2.1.0 hook wiring. It activates no Claude Code hooks and makes no automatic model calls. Both the preflight layer and the Stop-hook layer are explicit opt-ins:
 
 ```
 ┌────────────────────────────────────────────────┐
@@ -15,32 +15,31 @@ The Cognitive Sandwich wraps every Claude Code response in two layers of cogniti
 ├────────────────────────────────────────────────┤
 │  🥩 MEAT       — Claude Code reasons            │
 ├────────────────────────────────────────────────┤
-│  🥪 BOTTOM BREAD — Stop hooks                   │
+│  🥪 OPTIONAL BOTTOM BREAD — Stop hooks          │
-│   • Veto-detector (fast 50ms regex pre-screen)  │
+│   • Veto-detector / synthesis validator         │
-│   • Sanhedrin Executioner (LOCAL Qwen3.6-35B)   │
+│   • Sanhedrin Executioner verifier              │
-│   • Synthesis stop validator (hedge detector)   │
 └────────────────────────────────────────────────┘
 ```
 
-The Sanhedrin Executioner is the headline of v2.1.0. As of v2.1.0 it runs entirely on a local MLX model (`mlx-community/Qwen3.6-35B-A3B-4bit`), replacing the v2.0.x Haiku 4.5 subagent. **Zero API cost per Claude turn, fully offline, ~5–15s verdict latency on M-series Apple Silicon.**
+Sanhedrin, preflight, and all Vestige Claude Code hooks are optional. The default installer wires none of them; it does not call Claude, start MLX, require a 19 GB model download, or require 20+ GB of RAM. Users who want preflight context can opt in with `--enable-preflight`. Users who want the post-response verifier can opt in with `--enable-sanhedrin` and point it at any OpenAI-compatible `/v1/chat/completions` endpoint. On Apple Silicon, an additional `--with-launchd` flag can auto-start the local MLX Qwen backend.
 
 ---
 
 ## How a single response flows through the Sandwich
 
 1. **You type a prompt in Claude Code.**
-2. **UserPromptSubmit hooks fire in parallel** (none can block — all fail-open):
+2. **If explicitly enabled, UserPromptSubmit hooks fire in parallel** (none can block — all fail-open):
    - `load-all-memory.sh` (opt-in) — dumps every memory MD into context
    - `synthesis-preflight.sh` — POSTs your prompt to `vestige-mcp` `/api/deep_reference`, injects the trust-scored reasoning chain
    - `cwd-state-injector.sh` — captures git status, branch, open PRs/issues, modified files
    - `vestige-pulse-daemon.sh` — injects fresh Vestige dream insights from the past 20 min into the next prompt context
    - `preflight-swarm.sh` — spawns the `lateral-thinker` subagent in fresh context to surface cross-disciplinary structural parallels
 3. **Claude reads the assembled context and generates a draft.**
-4. **Stop hooks fire serially** (any can VETO with `exit 2`, forcing a rewrite):
+4. **By default, no Vestige Stop hooks are installed.** If explicitly enabled, Stop hooks fire serially (any can VETO with `exit 2`, forcing a rewrite):
    - `veto-detector.sh` — fast regex against `veto`-tagged Vestige memories (~50ms)
-   - `sanhedrin.sh` → `sanhedrin-local.py` — single-shot local Qwen3.6-35B-A3B verdict
+   - `sanhedrin.sh` → `sanhedrin-local.py` — optional single-shot semantic verdict
    - `synthesis-stop-validator.sh` — regex against forbidden patterns (hedging, summary-instead-of-composition)
-5. **If all 3 Stop hooks return `exit 0`, the response is delivered.**
+5. **If all enabled Stop hooks return `exit 0`, the response is delivered.**
 
 ---
 
@@ -82,30 +81,65 @@ curl -fsSL https://raw.githubusercontent.com/samvallad33/vestige/v2.1.0/scripts/
 git clone https://github.com/samvallad33/vestige
 cd vestige
 ./scripts/install-sandwich.sh           # add --force to overwrite existing hooks
-./scripts/check-sandwich-prereqs.sh     # verify everything's wired
+./scripts/check-sandwich-prereqs.sh     # verify no Vestige hooks are wired by default
+```
+
+The default command does not activate any Claude Code hook. It removes old v2.1.0 Vestige hook wiring from `~/.claude/settings.json` while preserving unrelated user hooks.
+
+### Optional Preflight
+
+Preflight is a separate opt-in layer. It includes `preflight-swarm.sh`, which uses `claude -p --model claude-haiku-4-5-20251001`; it is not wired by default.
+
+```bash
+./scripts/install-sandwich.sh --enable-preflight
+./scripts/check-sandwich-prereqs.sh --preflight
+```
+
+### Optional Sanhedrin
+
+Sanhedrin is a separate opt-in layer.
+
+```bash
+# Wire the Sanhedrin Stop hook, using the default OpenAI-compatible endpoint.
+./scripts/install-sandwich.sh --enable-sanhedrin
+
+# Apple Silicon only, and only if the machine has enough memory:
+./scripts/install-sandwich.sh --enable-sanhedrin --with-launchd
+
+# x86 / Linux / Intel Mac: use any OpenAI-compatible endpoint.
+./scripts/install-sandwich.sh \
+  --enable-sanhedrin \
+  --sanhedrin-endpoint=http://127.0.0.1:11434/v1/chat/completions \
+  --sanhedrin-model=qwen2.5:14b
 ```
 
 ### Prerequisites
 
 | Tool | Install |
 |---|---|
-| macOS Apple Silicon (M1+) | required for MLX |
 | Python 3.10+ | typically preinstalled |
 | `jq` | `brew install jq` |
+| `vestige-mcp` | `cargo install vestige-mcp` |
+| Claude Code | https://claude.ai/code |
+
+Optional Apple Silicon local Sanhedrin backend:
+
+| Tool | Install |
+|---|---|
+| macOS Apple Silicon (M1+) | required for MLX launchd only |
 | `uv` | `brew install uv` |
 | `mlx-lm` | `uv tool install mlx-lm` |
 | `huggingface_hub[cli]` | `uv tool install 'huggingface_hub[cli]'` |
-| `vestige-mcp` | `cargo install vestige-mcp` |
-| Claude Code | https://claude.ai/code |
 | Qwen3.6-35B-A3B-4bit | `hf download mlx-community/Qwen3.6-35B-A3B-4bit` (~19 GB) |
 
 ### What the installer does
 
 1. Verifies prereqs (warnings for missing tools, fatal only on jq/python3).
 2. Copies hooks to `~/.claude/hooks/`, agents to `~/.claude/agents/`.
-3. Renders `launchd/com.vestige.mlx-server.plist.template` with your `$HOME` and chosen model, writes to `~/Library/LaunchAgents/`.
+3. Backs up existing `~/.claude/settings.json` to `.bak.pre-sandwich`, then removes old Vestige hook wiring from previous v2.1.0 installs.
-4. `launchctl load` the plist (auto-start mlx_lm.server with the Qwen model on boot).
+4. With `--enable-preflight`, merges the UserPromptSubmit hooks block.
-5. Backs up existing `~/.claude/settings.json` to `.bak.pre-sandwich`, then `jq`-merges the hooks block.
+5. With `--enable-sanhedrin`, writes `~/.claude/hooks/vestige-sanhedrin.env` and merges a Sanhedrin-enabled Stop hooks block.
+6. With `--enable-sanhedrin --with-launchd` on Apple Silicon, renders and loads `launchd/com.vestige.mlx-server.plist.template`.
 
 ### Uninstall
 
@@ -120,7 +154,7 @@ cp ~/.claude/settings.json.bak.pre-sandwich ~/.claude/settings.json
 
 ## Performance notes
 
-On M3 Max 16-core (400 GB/s memory bandwidth):
+Optional local MLX backend on M3 Max 16-core (400 GB/s memory bandwidth):
 - Sanhedrin verdict: 5–15 seconds end-to-end (single deep_reference + single Qwen call)
 - mlx_lm.server token generation: ~82 tok/s
 - mlx_lm.server peak resident memory: ~19.7 GB
@@ -134,11 +168,12 @@ On M3 Max 14-core or M2/M1 Max: closer to 3–7s prompt processing, ~50–60 tok
 
 | Env var | Default | Effect |
 |---|---|---|
-| `VESTIGE_SANHEDRIN_ENABLED` | `1` | Set to `0` to disable Sanhedrin Stop hook entirely |
+| `VESTIGE_SANHEDRIN_ENABLED` | `0` | Set to `1` to enable the optional Sanhedrin Stop hook |
 | `VESTIGE_SWARM_ENABLED` | `1` | Set to `0` to disable preflight lateral-thinker swarm |
 | `VESTIGE_DASHBOARD_PORT` | `3927` | Vestige MCP HTTP API port used by hooks |
-| `MLX_ENDPOINT` | `http://127.0.0.1:8080/v1/chat/completions` | OpenAI-compatible chat completions endpoint for Sanhedrin |
+| `VESTIGE_SANHEDRIN_ENDPOINT` | `http://127.0.0.1:8080/v1/chat/completions` | OpenAI-compatible chat completions endpoint for Sanhedrin |
-| `VESTIGE_SANDWICH_MODEL` | `mlx-community/Qwen3.6-35B-A3B-4bit` | Model launchd serves and Sanhedrin requests |
+| `VESTIGE_SANHEDRIN_MODEL` | `mlx-community/Qwen3.6-35B-A3B-4bit` | Model name sent to the Sanhedrin endpoint |
+| `MLX_ENDPOINT` / `VESTIGE_SANDWICH_MODEL` | legacy aliases | Backward-compatible names still read by the bridge |
 | `VESTIGE_MEMORY_DIR` | (auto) | Override per-user Claude memory dir |
 
 ---
@@ -151,11 +186,12 @@ Full architecture memory: search Vestige for `god-tier-plan` or `cognitive-sandw
 
 ---
 
-## Linux / Intel Mac
+## Linux / Intel Mac / x86
 
-The launchd layer is macOS-arm64-only. On Linux or Intel Mac:
+The base hook harness runs on x86. The launchd MLX helper is macOS-arm64-only.
-- Hooks + agents install fine with `--no-launchd`
-- The Sanhedrin Stop hook will fail-open (mlx-server unreachable → exit 0)
-- Optional: run a remote mlx_lm.server / vLLM / Ollama OpenAI-compatible endpoint and set `MLX_ENDPOINT` to its `/v1/chat/completions` URL
 
-Future v2.2.0 will add Linux-native MLX equivalents.
+On Linux, Windows under WSL, or Intel Mac:
+- Run `scripts/install-sandwich.sh` normally to stage files and remove old Vestige hook wiring. No hooks are activated.
+- If you want Sanhedrin, run an OpenAI-compatible endpoint such as vLLM, Ollama, llama.cpp server, or a remote MLX/vLLM box.
+- Install with `--enable-sanhedrin --sanhedrin-endpoint=<url> --sanhedrin-model=<model>`.
+- If the endpoint is unreachable, Sanhedrin fails open and does not block Claude Code.

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"
+MODEL = (
-MLX_TIMEOUT = env_int("MLX_TIMEOUT", 45)
+    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 ===
+# === OPT-IN GATE ===
-# Post-Cognitive Sanhedrin is ON by default as of 2026-04-21 (birthday
+# Sanhedrin is heavyweight: the default local backend is a ~19 GB model and
-# launch day). To disable, set VESTIGE_SANHEDRIN_ENABLED=0 in your
+# needs roughly 20+ GB of free RAM. Keep it disabled unless the user explicitly
-# environment. Default-on guarantees the Cognitive Sandwich fires on
+# opts in. The installer writes this env file only for --enable-sanhedrin.
-# fresh machines, Docker containers, GUI-launched Claude Code, and
+SANHEDRIN_ENV="${VESTIGE_SANHEDRIN_ENV:-$HOME/.claude/hooks/vestige-sanhedrin.env}"
-# shells without .zshrc — any case where the Claude Code process lacks
+if [ -f "$SANHEDRIN_ENV" ]; then
-# a sourced profile. The re-entrancy guard (VESTIGE_EXECUTIONER_ACTIVE)
+  set +u
-# below still prevents fork-bombs from the subagent's own Stop hook.
+  set -a
-if [ "${VESTIGE_SANHEDRIN_ENABLED:-1}" = "0" ]; then
+  # shellcheck disable=SC1090
-  exit 0
+  . "$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
+# 2026-04-25: switched from Haiku 4.5 subagent to an OpenAI-compatible
-# via mlx_lm.server (launchd com.vestige.mlx-server). Bridge script
+# local/remote endpoint. On Apple Silicon the optional launchd path starts
-# fetches Vestige evidence via HTTP API (VESTIGE_DASHBOARD_PORT, default 3927)
+# mlx_lm.server; on x86 users can point VESTIGE_SANHEDRIN_ENDPOINT at vLLM,
-# then judges via MLX_ENDPOINT (default port 8080). Zero per-token cost, fully offline,
+# Ollama, llama.cpp, or any compatible /v1/chat/completions endpoint.
-# sub-second-to-15s verdict latency. Fail-open if mlx-server unreachable.
+# 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,
+The Executioner (Sanhedrin endpoint, fresh context, fed Vestige
-fed Vestige deep_reference evidence over HTTP) judged your draft and
+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

@@ -1,23 +1 @@
-{
+{}
-  "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": "$HOME/.claude/hooks/veto-detector.sh", "timeout": 6 },
-          { "type": "command", "command": "$HOME/.claude/hooks/sanhedrin.sh", "timeout": 70 },
-          { "type": "command", "command": "$HOME/.claude/hooks/synthesis-stop-validator.sh", "timeout": 6 }
-        ]
-      }
-    ]
-  }
-}

hooks/settings.preflight.fragment.json

@@ -0,0 +1,14 @@
+{
+  "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 }
+        ]
+      }
+    ]
+  }
+}

hooks/settings.sanhedrin.fragment.json

@@ -0,0 +1,13 @@
+{
+  "hooks": {
+    "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 }
+        ]
+      }
+    ]
+  }
+}

scripts/check-sandwich-prereqs.sh

@@ -5,21 +5,53 @@ set -u
 ok()   { printf '  \033[1;32m[ OK ]\033[0m %s\n' "$*"; }
 warn() { printf '  \033[1;33m[WARN]\033[0m %s\n' "$*"; FAIL=1; }
 miss() { printf '  \033[1;31m[MISS]\033[0m %s\n' "$*"; FAIL=1; }
+info() { printf '  \033[1;36m[INFO]\033[0m %s\n' "$*"; }
 
 FAIL=0
+CHECK_PREFLIGHT=0
+CHECK_SANHEDRIN=0
 DASHBOARD_PORT="${VESTIGE_DASHBOARD_PORT:-3927}"
-MLX_ENDPOINT="${MLX_ENDPOINT:-http://127.0.0.1:8080/v1/chat/completions}"
+SANHEDRIN_ENV="${VESTIGE_SANHEDRIN_ENV:-$HOME/.claude/hooks/vestige-sanhedrin.env}"
-MLX_ENDPOINT="${MLX_ENDPOINT%/}"
+
-MLX_MODELS_URL="${MLX_ENDPOINT%/chat/completions}/models"
+for arg in "$@"; do
+  case "$arg" in
+    --preflight|--enable-preflight) CHECK_PREFLIGHT=1 ;;
+    --sanhedrin|--enable-sanhedrin) CHECK_SANHEDRIN=1 ;;
+    -h|--help)
+      cat <<'EOF'
+Usage: scripts/check-sandwich-prereqs.sh [--preflight] [--sanhedrin]
+
+Without flags, verifies that the default install has no Vestige hooks wired.
+With --preflight, checks the optional UserPromptSubmit hook layer.
+With --sanhedrin, checks the optional OpenAI-compatible verifier endpoint.
+EOF
+      exit 0
+      ;;
+  esac
+done
+
+if [ -f "$SANHEDRIN_ENV" ]; then
+  set +u
+  set -a
+  # shellcheck disable=SC1090
+  . "$SANHEDRIN_ENV" 2>/dev/null || true
+  set +a
+  set -u
+fi
+
+SANHEDRIN_ENDPOINT="${VESTIGE_SANHEDRIN_ENDPOINT:-${MLX_ENDPOINT:-http://127.0.0.1:8080/v1/chat/completions}}"
+SANHEDRIN_ENDPOINT="${SANHEDRIN_ENDPOINT%/}"
+SANHEDRIN_MODELS_URL="${SANHEDRIN_ENDPOINT%/chat/completions}/models"
 
 echo "Vestige Cognitive Sandwich — Prereq Check"
 echo
 
 # Platform
-if [ "$(uname -s)" = "Darwin" ] && [ "$(uname -m)" = "arm64" ]; then
+OS_NAME="$(uname -s)"
-  ok "Apple Silicon macOS ($(sw_vers -productVersion 2>/dev/null || echo darwin))"
+ARCH_NAME="$(uname -m)"
-else
+ok "Platform: $OS_NAME $ARCH_NAME"
-  miss "Apple Silicon Mac required (M1+). Detected $(uname -s) $(uname -m)."
+if [ "$OS_NAME" != "Darwin" ] || [ "$ARCH_NAME" != "arm64" ]; then
+  info "Local MLX launchd is Apple Silicon-only; base hooks and endpoint-backed Sanhedrin can run on x86."
 fi
 
 # Python
@@ -35,56 +67,95 @@ fi
 
 # CLI tools
 command -v jq            >/dev/null && ok "jq"            || miss "jq missing — brew install jq"
-command -v uv            >/dev/null && ok "uv"            || miss "uv missing — brew install uv"
+if [ "$CHECK_PREFLIGHT" -eq 1 ]; then
-command -v mlx_lm.server >/dev/null && ok "mlx-lm"        || miss "mlx-lm — uv tool install mlx-lm"
+  command -v claude        >/dev/null && ok "claude CLI"    || miss "claude CLI — install Claude Code"
-command -v hf            >/dev/null && ok "huggingface_hub CLI" || miss "hf — uv tool install 'huggingface_hub[cli]'"
+  command -v vestige-mcp   >/dev/null && ok "vestige-mcp"   || miss "vestige-mcp — cargo install vestige-mcp"
-command -v claude        >/dev/null && ok "claude CLI"    || miss "claude CLI — install Claude Code"
-command -v vestige-mcp   >/dev/null && ok "vestige-mcp"   || miss "vestige-mcp — cargo install vestige-mcp"
 
-# Model on disk — HF cache uses `models--<org>--<name>` (double-dash separators).
+  # Vestige MCP HTTP API
-MODEL="${VESTIGE_SANDWICH_MODEL:-mlx-community/Qwen3.6-35B-A3B-4bit}"
+  if curl -fsS -m 2 "http://127.0.0.1:${DASHBOARD_PORT}/api/health" >/dev/null 2>&1; then
-HF_HOME_DEFAULT="${HF_HOME:-$HOME/.cache/huggingface}"
+    ok "vestige-mcp dashboard responding on :$DASHBOARD_PORT"
-ENC_MODEL="models--$(printf '%s' "$MODEL" | sed 's|/|--|g')"
+  else
-if [ -d "$HF_HOME_DEFAULT/hub/$ENC_MODEL" ]; then
+    warn "vestige-mcp dashboard not responding on :$DASHBOARD_PORT"
-  ok "Model cached: $MODEL"
+  fi
-else
-  printf '  \033[1;33m[INFO]\033[0m Model not yet downloaded — first run will fetch ~19GB\n'
-  printf '         hf download %s\n' "$MODEL"
-  # NOT a failure — first-run download is expected.
-fi
-
-# Vestige MCP HTTP API
-if curl -fsS -m 2 "http://127.0.0.1:${DASHBOARD_PORT}/api/health" >/dev/null 2>&1; then
-  ok "vestige-mcp dashboard responding on :$DASHBOARD_PORT"
-else
-  warn "vestige-mcp dashboard not responding on :$DASHBOARD_PORT"
-fi
-
-# OpenAI-compatible local/remote model endpoint
-if curl -fsS -m 2 "$MLX_MODELS_URL" >/dev/null 2>&1; then
-  ok "model endpoint responding at $MLX_MODELS_URL"
-else
-  warn "model endpoint not responding at $MLX_MODELS_URL — install + load launchd plist or set MLX_ENDPOINT"
-fi
-
-# launchd plist
-if [ -f "$HOME/Library/LaunchAgents/com.vestige.mlx-server.plist" ]; then
-  ok "launchd plist installed"
-else
-  warn "launchd plist missing — run: install-sandwich.sh"
 fi
 
 # Settings hook wiring
-if [ -f "$HOME/.claude/settings.json" ] && \
+if [ "$CHECK_PREFLIGHT" -eq 0 ] && [ "$CHECK_SANHEDRIN" -eq 0 ]; then
-   jq -e '.hooks.UserPromptSubmit and .hooks.Stop' "$HOME/.claude/settings.json" >/dev/null 2>&1; then
+  if [ -f "$HOME/.claude/settings.json" ] && \
-  ok "settings.json hooks block present"
+     jq -e 'any((.hooks.UserPromptSubmit[]?.hooks[]?, .hooks.Stop[]?.hooks[]?); ((.command? // "") | test("synthesis-preflight\\.sh|cwd-state-injector\\.sh|vestige-pulse-daemon\\.sh|preflight-swarm\\.sh|load-all-memory\\.sh|veto-detector\\.sh|sanhedrin\\.sh|synthesis-stop-validator\\.sh|synthesis-gate\\.sh")))' "$HOME/.claude/settings.json" >/dev/null 2>&1; then
+    warn "Vestige hooks are still wired; run: install-sandwich.sh --force"
+  else
+    ok "no Vestige Claude Code hooks wired by default"
+  fi
+fi
+
+if [ "$CHECK_PREFLIGHT" -eq 1 ]; then
+  echo
+  echo "Optional Preflight"
+
+  if [ -f "$HOME/.claude/settings.json" ] && \
+     jq -e 'any(.hooks.UserPromptSubmit[]?.hooks[]?; ((.command? // "") | contains("synthesis-preflight.sh"))) and any(.hooks.UserPromptSubmit[]?.hooks[]?; ((.command? // "") | contains("preflight-swarm.sh")))' "$HOME/.claude/settings.json" >/dev/null 2>&1; then
+    ok "preflight UserPromptSubmit hooks wired"
+  else
+    warn "preflight hooks not wired — run: install-sandwich.sh --enable-preflight"
+  fi
+
+  info "preflight-swarm.sh uses claude -p with Haiku when enabled; default installs do not wire it."
+fi
+
+if [ "$CHECK_SANHEDRIN" -eq 1 ]; then
+  echo
+  echo "Optional Sanhedrin"
+
+  if [ -f "$SANHEDRIN_ENV" ]; then
+    ok "Sanhedrin env file present"
+  else
+    warn "Sanhedrin env file missing — run: install-sandwich.sh --enable-sanhedrin"
+  fi
+
+  if [ "$OS_NAME" = "Darwin" ] && [ "$ARCH_NAME" = "arm64" ]; then
+    command -v uv            >/dev/null && ok "uv"            || warn "uv missing — brew install uv"
+    command -v mlx_lm.server >/dev/null && ok "mlx-lm"        || warn "mlx-lm — uv tool install mlx-lm"
+    command -v hf            >/dev/null && ok "huggingface_hub CLI" || warn "hf — uv tool install 'huggingface_hub[cli]'"
+
+    MODEL="${VESTIGE_SANHEDRIN_MODEL:-${VESTIGE_SANDWICH_MODEL:-mlx-community/Qwen3.6-35B-A3B-4bit}}"
+    HF_HOME_DEFAULT="${HF_HOME:-$HOME/.cache/huggingface}"
+    ENC_MODEL="models--$(printf '%s' "$MODEL" | sed 's|/|--|g')"
+    if [ -d "$HF_HOME_DEFAULT/hub/$ENC_MODEL" ]; then
+      ok "Model cached: $MODEL"
+    else
+      info "Model not cached: $MODEL (local MLX path downloads ~19GB)"
+    fi
+
+    if [ -f "$HOME/Library/LaunchAgents/com.vestige.mlx-server.plist" ]; then
+      ok "launchd plist installed"
+    else
+      info "launchd plist not installed; endpoint-backed Sanhedrin can still run"
+    fi
+  else
+    info "Skipping MLX/launchd checks on $OS_NAME $ARCH_NAME"
+  fi
+
+  if curl -fsS -m 2 "$SANHEDRIN_MODELS_URL" >/dev/null 2>&1; then
+    ok "Sanhedrin model endpoint responding at $SANHEDRIN_MODELS_URL"
+  else
+    warn "Sanhedrin endpoint not responding at $SANHEDRIN_MODELS_URL"
+  fi
+
+  if [ -f "$HOME/.claude/settings.json" ] && \
+     jq -e '.hooks.Stop[]?.hooks[]?.command | contains("sanhedrin.sh")' "$HOME/.claude/settings.json" >/dev/null 2>&1; then
+    ok "Sanhedrin Stop hook wired"
+  else
+    warn "Sanhedrin Stop hook not wired — run: install-sandwich.sh --enable-sanhedrin"
+  fi
 else
-  warn "settings.json missing hooks block — run: install-sandwich.sh"
+  echo
+  info "Sanhedrin is optional and not checked. Use --sanhedrin to verify an enabled endpoint."
 fi
 
 echo
 if [ $FAIL -eq 0 ]; then
-  echo "  Ready. Cognitive Sandwich will fire on next Claude Code prompt."
+  echo "  Ready. Default install has no Vestige Claude Code hooks wired and makes no automatic model calls."
   exit 0
 else
   echo "  Fix the items above, then re-run."

scripts/install-sandwich.sh

@@ -4,26 +4,26 @@
 # Usage:
 #   curl -fsSL https://raw.githubusercontent.com/samvallad33/vestige/v2.1.0/scripts/install-sandwich.sh | sh
 #   # or, from a checkout:
-#   ./scripts/install-sandwich.sh [--force] [--no-launchd] [--include-memory-loader]
+#   ./scripts/install-sandwich.sh [--force] [--enable-preflight] [--enable-sanhedrin] [--with-launchd] [--include-memory-loader]
+#   ./scripts/install-sandwich.sh --enable-sanhedrin --sanhedrin-endpoint=http://127.0.0.1:11434/v1/chat/completions --sanhedrin-model=qwen2.5:14b
 #
 # What it does:
 #   1. Verifies required local tools
-#   2. Stages ~/.claude/hooks/, ~/.claude/agents/, ~/Library/LaunchAgents/
+#   2. Stages ~/.claude/hooks/ and ~/.claude/agents/
 #   3. Copies sanitized hooks + agents
-#   4. Renders launchd plist template with $HOME and chosen MODEL
+#   4. Removes old Vestige hook wiring from ~/.claude/settings.json by default
-#   5. Merges hooks block into ~/.claude/settings.json (preserves existing keys)
+#   5. Optionally enables preflight hooks and/or Sanhedrin. Only with --with-launchd on Apple Silicon,
-#   6. launchctl load com.vestige.mlx-server (auto-starts mlx_lm.server with Qwen3.6-35B-A3B)
+#      auto-starts mlx_lm.server with Qwen3.6-35B-A3B
-#   7. Prints next-steps for model download
 
 set -euo pipefail
 
 VERSION="${VESTIGE_SANDWICH_VERSION:-v2.1.0}"
 REPO="samvallad33/vestige"
-MODEL_ID="${VESTIGE_SANDWICH_MODEL:-mlx-community/Qwen3.6-35B-A3B-4bit}"
+MODEL_ID="${VESTIGE_SANHEDRIN_MODEL:-${VESTIGE_SANDWICH_MODEL:-mlx-community/Qwen3.6-35B-A3B-4bit}}"
 DASHBOARD_PORT="${VESTIGE_DASHBOARD_PORT:-3927}"
-MLX_ENDPOINT="${MLX_ENDPOINT:-http://127.0.0.1:8080/v1/chat/completions}"
+SANHEDRIN_ENDPOINT="${VESTIGE_SANHEDRIN_ENDPOINT:-${MLX_ENDPOINT:-http://127.0.0.1:8080/v1/chat/completions}}"
-MLX_ENDPOINT="${MLX_ENDPOINT%/}"
+SANHEDRIN_ENDPOINT="${SANHEDRIN_ENDPOINT%/}"
-MLX_MODELS_URL="${MLX_ENDPOINT%/chat/completions}/models"
+SANHEDRIN_MODELS_URL="${SANHEDRIN_ENDPOINT%/chat/completions}/models"
 
 HOOKS_DIR="$HOME/.claude/hooks"
 AGENTS_DIR="$HOME/.claude/agents"
@@ -31,45 +31,70 @@ LAUNCHD_DIR="$HOME/Library/LaunchAgents"
 SETTINGS="$HOME/.claude/settings.json"
 
 FORCE=0
-NO_LAUNCHD=0
+ENABLE_PREFLIGHT=0
+ENABLE_SANHEDRIN=0
+WITH_LAUNCHD=0
 INCLUDE_MEMORY_LOADER=0
 SRC=""
 
 for arg in "$@"; do
   case "$arg" in
     --force) FORCE=1 ;;
-    --no-launchd) NO_LAUNCHD=1 ;;
+    --enable-preflight) ENABLE_PREFLIGHT=1 ;;
+    --enable-sandwich) ENABLE_PREFLIGHT=1; ENABLE_SANHEDRIN=1 ;;
+    --enable-sanhedrin) ENABLE_SANHEDRIN=1 ;;
+    --with-launchd) WITH_LAUNCHD=1 ;;
+    --no-launchd) WITH_LAUNCHD=0 ;;
     --include-memory-loader) INCLUDE_MEMORY_LOADER=1 ;;
+    --sanhedrin-endpoint=*|--endpoint=*)
+      SANHEDRIN_ENDPOINT="${arg#*=}"
+      SANHEDRIN_ENDPOINT="${SANHEDRIN_ENDPOINT%/}"
+      SANHEDRIN_MODELS_URL="${SANHEDRIN_ENDPOINT%/chat/completions}/models"
+      ;;
+    --sanhedrin-model=*|--model=*)
+      MODEL_ID="${arg#*=}"
+      ;;
     --src=*) SRC="${arg#--src=}" ;;
     -h|--help)
-      sed -n '2,20p' "$0"
+      sed -n '2,24p' "$0"
       exit 0
       ;;
   esac
 done
 
+if [ "$WITH_LAUNCHD" -eq 1 ] && [ "$ENABLE_SANHEDRIN" -eq 0 ]; then
+  ENABLE_SANHEDRIN=1
+fi
+
 say()  { printf '\033[1;36m[sandwich]\033[0m %s\n' "$*"; }
 warn() { printf '\033[1;33m[sandwich]\033[0m %s\n' "$*" >&2; }
 die()  { printf '\033[1;31m[sandwich]\033[0m %s\n' "$*" >&2; exit 1; }
 
-# --- Platform check (honors --no-launchd for Linux/Intel users) ---
+# --- Platform check ---
-if [ "$(uname -s)" != "Darwin" ]; then
+OS_NAME="$(uname -s)"
-  if [ "$NO_LAUNCHD" -eq 0 ]; then
+ARCH_NAME="$(uname -m)"
-    die "macOS required for the launchd auto-start of mlx_lm.server. Re-run with --no-launchd to install hooks only and run mlx_lm.server manually."
+say "platform: $OS_NAME $ARCH_NAME"
-  fi
+if [ "$ENABLE_SANHEDRIN" -eq 1 ] && [ "$WITH_LAUNCHD" -eq 0 ]; then
-  warn "Non-Darwin platform — installing hooks/agents only (no launchd). Run an OpenAI-compatible model endpoint and set MLX_ENDPOINT if it is not $MLX_ENDPOINT."
+  say "Sanhedrin enabled without launchd; using OpenAI-compatible endpoint: $SANHEDRIN_ENDPOINT"
-elif [ "$(uname -m)" != "arm64" ]; then
+fi
-  warn "Apple Silicon recommended (M1+). Detected $(uname -m). The local Qwen3.6 model requires arm64 + Metal."
+if [ "$WITH_LAUNCHD" -eq 1 ] && { [ "$OS_NAME" != "Darwin" ] || [ "$ARCH_NAME" != "arm64" ]; }; then
+  warn "--with-launchd is Apple Silicon only; skipping local MLX autostart on $OS_NAME $ARCH_NAME"
+  warn "Sanhedrin can still run on x86 via --sanhedrin-endpoint or VESTIGE_SANHEDRIN_ENDPOINT."
+  WITH_LAUNCHD=0
 fi
 
 # --- Prereqs (warnings only, install proceeds) ---
 command -v jq      >/dev/null || die "jq required: brew install jq"
 command -v python3 >/dev/null || die "python3 required (3.10+)"
-command -v claude  >/dev/null || warn "'claude' CLI not found — install Claude Code first."
+if [ "$ENABLE_PREFLIGHT" -eq 1 ]; then
-command -v vestige-mcp >/dev/null || warn "'vestige-mcp' not found — install with: cargo install vestige-mcp"
+  command -v claude  >/dev/null || warn "'claude' CLI not found — preflight-swarm.sh will fail open."
-command -v uv      >/dev/null || warn "'uv' not found — install with: brew install uv"
+  command -v vestige-mcp >/dev/null || warn "'vestige-mcp' not found — Vestige preflight hooks will fail open."
-command -v mlx_lm.server >/dev/null || warn "mlx-lm not installed — run: uv tool install mlx-lm"
+fi
-command -v hf      >/dev/null || warn "'hf' not found — run: uv tool install 'huggingface_hub[cli]'"
+if [ "$WITH_LAUNCHD" -eq 1 ]; then
+  command -v uv      >/dev/null || warn "'uv' not found — install with: brew install uv"
+  command -v mlx_lm.server >/dev/null || warn "mlx-lm not installed — run: uv tool install mlx-lm"
+  command -v hf      >/dev/null || warn "'hf' not found — run: uv tool install 'huggingface_hub[cli]'"
+fi
 
 # --- Resolve source: local checkout or release tarball ---
 if [ -n "$SRC" ]; then
@@ -89,7 +114,21 @@ fi
 [ -d "$SCRIPT_DIR/hooks" ] || die "hooks/ not found in $SCRIPT_DIR — wrong source?"
 
 # --- Stage directories ---
-mkdir -p "$HOOKS_DIR" "$AGENTS_DIR" "$LAUNCHD_DIR"
+mkdir -p "$HOOKS_DIR" "$AGENTS_DIR"
+if [ "$WITH_LAUNCHD" -eq 1 ]; then
+  mkdir -p "$LAUNCHD_DIR"
+fi
+
+# v2.1.0 originally installed the MLX server as part of the default path.
+# Default reinstalls now retire that job; users can restore it with --with-launchd.
+if [ "$WITH_LAUNCHD" -eq 0 ] && [ "$OS_NAME" = "Darwin" ]; then
+  LEGACY_PLIST="$LAUNCHD_DIR/com.vestige.mlx-server.plist"
+  if [ -f "$LEGACY_PLIST" ]; then
+    launchctl unload "$LEGACY_PLIST" 2>/dev/null || true
+    rm -f "$LEGACY_PLIST"
+    say "removed old Sanhedrin launchd job (use --with-launchd to opt back in)"
+  fi
+fi
 
 # --- Copy hooks ---
 copied=0; skipped=0
@@ -121,8 +160,25 @@ for f in "$SCRIPT_DIR/agents"/*.md; do
 done
 say "agents installed to $AGENTS_DIR"
 
-# --- Render launchd plist (macOS only) ---
+# --- Persist optional Sanhedrin env ---
-if [ "$NO_LAUNCHD" -eq 0 ]; then
+quote_env() {
+  printf "'%s'" "$(printf '%s' "$1" | sed "s/'/'\\\\''/g")"
+}
+
+if [ "$ENABLE_SANHEDRIN" -eq 1 ]; then
+  SANHEDRIN_ENV="$HOOKS_DIR/vestige-sanhedrin.env"
+  {
+    printf 'VESTIGE_SANHEDRIN_ENABLED=1\n'
+    printf 'VESTIGE_SANHEDRIN_ENDPOINT=%s\n' "$(quote_env "$SANHEDRIN_ENDPOINT")"
+    printf 'VESTIGE_SANHEDRIN_MODEL=%s\n' "$(quote_env "$MODEL_ID")"
+    printf 'VESTIGE_DASHBOARD_PORT=%s\n' "$(quote_env "$DASHBOARD_PORT")"
+  } > "$SANHEDRIN_ENV"
+  chmod 0600 "$SANHEDRIN_ENV"
+  say "Sanhedrin opt-in config written to $SANHEDRIN_ENV"
+fi
+
+# --- Render launchd plist (Apple Silicon opt-in only) ---
+if [ "$WITH_LAUNCHD" -eq 1 ]; then
   PLIST="$LAUNCHD_DIR/com.vestige.mlx-server.plist"
   TEMPLATE="$SCRIPT_DIR/launchd/com.vestige.mlx-server.plist.template"
   [ -f "$TEMPLATE" ] || die "launchd template missing: $TEMPLATE"
@@ -140,31 +196,80 @@ else
   cp "$SETTINGS" "$HOME/.claude/settings.json.bak.pre-sandwich"
 fi
 TMP_MERGE="$(mktemp)"
-jq -s '.[0] * .[1]' "$SETTINGS" "$SCRIPT_DIR/hooks/settings.fragment.json" > "$TMP_MERGE"
+PREFLIGHT_FRAGMENT="$SCRIPT_DIR/hooks/settings.fragment.json"
+SANHEDRIN_FRAGMENT="$SCRIPT_DIR/hooks/settings.fragment.json"
+if [ "$ENABLE_PREFLIGHT" -eq 1 ]; then
+  PREFLIGHT_FRAGMENT="$SCRIPT_DIR/hooks/settings.preflight.fragment.json"
+fi
+if [ "$ENABLE_SANHEDRIN" -eq 1 ]; then
+  SANHEDRIN_FRAGMENT="$SCRIPT_DIR/hooks/settings.sanhedrin.fragment.json"
+fi
+jq -s '
+  def is_vestige_hook:
+    (.command? // "") as $cmd
+    | [
+        "synthesis-preflight.sh",
+        "cwd-state-injector.sh",
+        "vestige-pulse-daemon.sh",
+        "preflight-swarm.sh",
+        "load-all-memory.sh",
+        "veto-detector.sh",
+        "sanhedrin.sh",
+        "synthesis-stop-validator.sh",
+        "synthesis-gate.sh"
+      ] | any(. as $needle | $cmd | contains($needle));
+
+  def scrub_vestige_hooks:
+    .hooks.UserPromptSubmit = (
+      (.hooks.UserPromptSubmit // [])
+      | map(.hooks = ((.hooks // []) | map(select((is_vestige_hook | not)))))
+      | map(select(((.hooks // []) | length) > 0))
+    )
+    | if ((.hooks.UserPromptSubmit // []) | length) == 0 then del(.hooks.UserPromptSubmit) else . end
+    | .hooks.Stop = (
+      (.hooks.Stop // [])
+      | map(.hooks = ((.hooks // []) | map(select((is_vestige_hook | not)))))
+      | map(select(((.hooks // []) | length) > 0))
+    )
+    | if ((.hooks.Stop // []) | length) == 0 then del(.hooks.Stop) else . end
+    | if ((.hooks // {}) | length) == 0 then del(.hooks) else . end;
+
+  (.[0] | scrub_vestige_hooks) * .[1] * .[2]
+' "$SETTINGS" "$PREFLIGHT_FRAGMENT" "$SANHEDRIN_FRAGMENT" > "$TMP_MERGE"
 mv "$TMP_MERGE" "$SETTINGS"
-say "merged hooks block into $SETTINGS (backup at .bak.pre-sandwich)"
+if [ "$ENABLE_PREFLIGHT" -eq 1 ] || [ "$ENABLE_SANHEDRIN" -eq 1 ]; then
+  enabled_layers=""
+  [ "$ENABLE_PREFLIGHT" -eq 1 ] && enabled_layers="${enabled_layers} preflight"
+  [ "$ENABLE_SANHEDRIN" -eq 1 ] && enabled_layers="${enabled_layers} sanhedrin"
+  say "merged optional hook layer(s) into $SETTINGS:${enabled_layers} (backup at .bak.pre-sandwich)"
+else
+  say "removed Vestige hook wiring from $SETTINGS; default install activates no Claude Code hooks (backup at .bak.pre-sandwich)"
+fi
 
 # --- Next steps ---
 cat <<EOF
 
   ┌──────────────────────────────────────────────────────────────┐
-  │  Cognitive Sandwich installed.                                │
+  │  Cognitive Sandwich files installed. No hooks enabled by default. │
   └──────────────────────────────────────────────────────────────┘
 
   Next steps:
-    1. Download the local model (~19 GB, one-time):
+    1. Restart Claude Code if you enabled optional hooks.
-         hf download $MODEL_ID
+       Default installs activate no Vestige Claude Code hooks and make no model calls.
-    2. Restart Claude Code so it picks up the new hooks.
+    2. Verify the install:
-    3. Verify the install:
          vestige health                 # if vestige CLI installed
          curl http://127.0.0.1:$DASHBOARD_PORT/api/health
-         curl $MLX_MODELS_URL
+         scripts/check-sandwich-prereqs.sh   # from a checkout
-    4. Try a prompt — the Sanhedrin Stop hook will fire and judge
+    3. Optional hook layers:
-       Claude's draft against your Vestige memory before delivery.
+         ./scripts/install-sandwich.sh --enable-preflight
+         ./scripts/install-sandwich.sh --enable-sanhedrin --sanhedrin-endpoint=$SANHEDRIN_ENDPOINT --sanhedrin-model=$MODEL_ID
+       On Apple Silicon with >20 GB free RAM, add --with-launchd to auto-start
+       the local MLX Qwen server. On x86, point --sanhedrin-endpoint at vLLM,
+       Ollama, llama.cpp, or another OpenAI-compatible /v1/chat/completions URL.
 
   To uninstall:
-    launchctl unload $LAUNCHD_DIR/com.vestige.mlx-server.plist
+    launchctl unload $LAUNCHD_DIR/com.vestige.mlx-server.plist 2>/dev/null || true
-    rm $LAUNCHD_DIR/com.vestige.mlx-server.plist
+    rm -f $LAUNCHD_DIR/com.vestige.mlx-server.plist
     cp $HOME/.claude/settings.json.bak.pre-sandwich $HOME/.claude/settings.json
 
 EOF