chore: bump version to 1.0.1

* fix: chunk IN clauses to stay within DB parameter limits

psycopg caps query parameters at 65 535 and SQLite defaults to 999.
assign_buckets, prune_workstreams, and count_skill_resources_bulk were
passing unbounded lists into single IN(...) clauses, causing
OperationalError during rebalancer runs on full-size hash rings.

Chunk sizes: 10 000 (PostgreSQL), 500 (SQLite).

* fix: deduplicate assign_buckets input, add chunking regression tests

Address review feedback: deduplicate bucket list before chunking to
prevent inflated rowcount from cross-chunk duplicates. Add tests that
exercise the multi-chunk path (1200 buckets > SQLite chunk_size of 500)
and verify dedup preserves accurate counts.

.env.example

@@ -1,29 +1,49 @@
 # =============================================================================
 # Turnstone Environment Variables
-# Copy to .env and adjust values for your deployment
+# Copy to .env and adjust values for your deployment.
+#
+# Usage:
+# Single node: docker compose --profile production up
+# 10-node cluster: docker compose --profile cluster up
 # =============================================================================
 
 # -- LLM Backend --------------------------------------------------------------
 LLM_BASE_URL=http://host.docker.internal:8000/v1
-OPENAI_API_KEY=sk-...
-# ANTHROPIC_API_KEY=sk-ant-...  # Set instead for Anthropic provider
-# TAVILY_API_KEY=tvly-...       # For web search fallback (local models only)
+OPENAI_API_KEY=dummy
+# ANTHROPIC_API_KEY=sk-ant-...# Set instead of OPENAI_API_KEY for Anthropic
+# TAVILY_API_KEY=tvly-... # Web search fallback (local models only)
+# MODEL=# Override default model alias
 
-# -- Database (production profile) --------------------------------------------
+# -- Authentication (required) ------------------------------------------------
+# Generate with: python -c "import secrets; print(secrets.token_hex(32))"
+TURNSTONE_JWT_SECRET=changeme-to-32-bytes-of-hex
+
+# -- Database ------------------------------------------------------------------
+# Single-node default is SQLite (zero config). Set these for PostgreSQL:
 # DB_BACKEND=postgresql
 # POSTGRES_USER=turnstone
 # POSTGRES_PASSWORD=changeme
 # DATABASE_URL=postgresql+psycopg://turnstone:changeme@postgres:5432/turnstone
 
-# -- Redis ---------------------------------------------------------------------
-# REDIS_PASSWORD=
-# REDIS_PORT=6379
-
-# -- Authentication ------------------------------------------------------------
-# TURNSTONE_AUTH_ENABLED=true
-# TURNSTONE_AUTH_TOKEN=your-secret-token
-# TURNSTONE_JWT_SECRET=python -c "import secrets; print(secrets.token_hex(32))"
-
 # -- Ports ---------------------------------------------------------------------
 # SERVER_PORT=8080
 # CONSOLE_PORT=8090
+
+# -- Workspace -----------------------------------------------------------------
+# Bind-mount a host directory into the container at /workspace.
+# The model can read/write files here. Default: empty Docker volume.
+# WORKSPACE_MOUNT=/path/to/your/project
+
+# -- Agent behavior ------------------------------------------------------------
+# SKIP_PERMISSIONS=true # Auto-approve all tool calls (dev only)
+# MCP_CONFIG=/workspace/mcp.json# MCP server configuration file
+
+# -- Discord channel gateway ---------------------------------------------------
+# TURNSTONE_DISCORD_TOKEN=
+# TURNSTONE_DISCORD_GUILD=0
+
+# -- Cluster (profile: cluster) -----------------------------------------------
+# These are set per-node in compose.yaml; only override for custom topologies.
+# TURNSTONE_NODE_ID=node-1
+# TURNSTONE_ADVERTISE_URL=http://server-1:8080
+

.github/renovate.json

@@ -83,7 +83,7 @@
     {
       "description": "Infrastructure dependencies",
       "groupName": "Infrastructure",
-      "matchPackageNames": ["structlog", "redis", "croniter", "discord.py"],
+      "matchPackageNames": ["structlog", "croniter", "discord.py"],
       "schedule": ["before 9am on the first day of the month"],
       "automerge": true,
       "matchUpdateTypes": ["patch"]
@@ -101,7 +101,6 @@
       "matchPackageNames": [
         "ruff",
         "mypy",
-        "types-redis",
         "pytest",
         "pytest-cov",
         "pre-commit"

.github/workflows/ci.yml

@@ -2,9 +2,10 @@ name: CI
 
 on:
   push:
-    branches: [main]
+    branches: [main, "stable/*"]
+    tags: ["v*"]
   pull_request:
-    branches: [main]
+    branches: [main, "stable/*"]
 
 jobs:
   lint:
@@ -25,8 +26,8 @@ jobs:
       - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6
         with:
           python-version: "3.14"
-      - run: pip install mypy types-redis
-      - run: pip install -e ".[mq]"
+      - run: pip install mypy
+      - run: pip install -e ".[all]"
       - run: mypy turnstone/
 
   test:
@@ -39,7 +40,7 @@ jobs:
       - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6
         with:
           python-version: ${{ matrix.python-version }}
-      - run: pip install -e ".[test,mq]"
+      - run: pip install -e ".[test]"
       - run: pytest tests/ -m "not live" --cov=turnstone --cov-report=term-missing --cov-report=xml -q
       - uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7
         if: always()
@@ -68,7 +69,7 @@ jobs:
       - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6
         with:
           python-version: "3.14"
-      - run: pip install -e ".[test,mq,postgres]"
+      - run: pip install -e ".[test,postgres]"
       - run: pytest tests/ -m "not live" --storage-backend=postgresql -q
         env:
           TURNSTONE_TEST_PG_URL: postgresql+psycopg://postgres:postgres@localhost:5432/turnstone_test

.github/workflows/docker-publish.yml

@@ -0,0 +1,75 @@
+name: Publish Docker Image
+
+on:
+  workflow_run:
+    workflows: ["CI"]
+    types: [completed]
+
+permissions:
+  contents: read
+  packages: write
+
+env:
+  REGISTRY: ghcr.io
+  IMAGE_NAME: ${{ github.repository }}
+
+jobs:
+  docker:
+    if: github.event.workflow_run.conclusion == 'success'
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+        with:
+          ref: ${{ github.event.workflow_run.head_sha }}
+          fetch-depth: 0
+
+      - name: Resolve release tag
+        id: tag
+        run: |
+          TAG=$(git tag --points-at HEAD | grep '^v' | head -1)
+          if [ -z "$TAG" ]; then
+            echo "No v* tag at HEAD — skipping publish"
+            echo "skip=true" >> "$GITHUB_OUTPUT"
+          else
+            echo "tag=${TAG}" >> "$GITHUB_OUTPUT"
+            echo "skip=false" >> "$GITHUB_OUTPUT"
+          fi
+
+      - name: Log in to GHCR
+        if: steps.tag.outputs.skip == 'false'
+        uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Compute Docker tags
+        if: steps.tag.outputs.skip == 'false'
+        id: tags
+        env:
+          REF: ${{ steps.tag.outputs.tag }}
+        run: |
+          VERSION="${REF#v}"
+          FULL="${REGISTRY}/${IMAGE_NAME}"
+          FULL="${FULL,,}"
+
+          if echo "$VERSION" | grep -qE '(a|b|rc)[0-9]+$'; then
+            TAGS="${FULL}:${VERSION},${FULL}:experimental"
+          else
+            MINOR="${VERSION%.*}"
+            TAGS="${FULL}:${VERSION},${FULL}:${MINOR},${FULL}:stable,${FULL}:latest"
+          fi
+          echo "tags=${TAGS}" >> "$GITHUB_OUTPUT"
+
+      - uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3
+        if: steps.tag.outputs.skip == 'false'
+
+      - name: Build and push
+        if: steps.tag.outputs.skip == 'false'
+        uses: docker/build-push-action@14487ce63c7a62a4a324b0bfb37086795e31c6c1 # v6
+        with:
+          context: .
+          push: true
+          tags: ${{ steps.tags.outputs.tags }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max

.github/workflows/docker-scan.yml

@@ -2,7 +2,7 @@ name: Docker Security Scan
 
 on:
   push:
-    branches: [main]
+    branches: [main, "stable/*"]
   schedule:
     - cron: "0 6 * * 1"  # Weekly Monday 06:00 UTC
 

.github/workflows/publish.yml

@@ -1,8 +1,9 @@
 name: Publish to PyPI
 
 on:
-  push:
-    tags: ["v*"]
+  workflow_run:
+    workflows: ["CI"]
+    types: [completed]
 
 permissions:
   contents: write
@@ -10,20 +11,43 @@ permissions:
 
 jobs:
   publish:
+    if: github.event.workflow_run.conclusion == 'success'
     runs-on: ubuntu-latest
     environment: pypi
     steps:
       - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
+        with:
+          ref: ${{ github.event.workflow_run.head_sha }}
+          fetch-depth: 0
+
+      - name: Resolve release tag
+        id: tag
+        run: |
+          TAG=$(git tag --points-at HEAD | grep '^v' | head -1)
+          if [ -z "$TAG" ]; then
+            echo "No v* tag at HEAD — skipping publish"
+            echo "skip=true" >> "$GITHUB_OUTPUT"
+          else
+            echo "tag=${TAG}" >> "$GITHUB_OUTPUT"
+            echo "skip=false" >> "$GITHUB_OUTPUT"
+          fi
+
       - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6
+        if: steps.tag.outputs.skip == 'false'
         with:
           python-version: "3.14"
       - run: pip install build
+        if: steps.tag.outputs.skip == 'false'
       - run: python -m build
+        if: steps.tag.outputs.skip == 'false'
       - uses: pypa/gh-action-pypi-publish@ed0c53931b1dc9bd32cbe73a98c7f6766f8a527e # release/v1
+        if: steps.tag.outputs.skip == 'false'
 
       - name: Create GitHub Release
+        if: steps.tag.outputs.skip == 'false'
         uses: softprops/action-gh-release@153bb8e04406b158c6c84fc1615b65b24149a1fe # v2
         with:
+          tag_name: ${{ steps.tag.outputs.tag }}
           generate_release_notes: true
           draft: false
-          prerelease: ${{ contains(github.ref, '-') }}
+          prerelease: ${{ contains(steps.tag.outputs.tag, 'a') || contains(steps.tag.outputs.tag, 'b') || contains(steps.tag.outputs.tag, 'rc') }}

.pre-commit-config.yaml

@@ -10,7 +10,7 @@ repos:
     rev: v1.19.1
     hooks:
       - id: mypy
-        additional_dependencies: [types-redis>=4.6, redis>=7.2]
+        additional_dependencies: []
         args: [--config-file=pyproject.toml]
         pass_filenames: false
         entry: mypy turnstone/

.trivyignore

@@ -2,3 +2,39 @@
 # https://avd.aquasec.com/nvd/cve-2026-25210
 # Review: remove this entry once a patched libexpat1 is published
 CVE-2026-25210
+
+# ncurses buffer overflow — no fix in Debian 13 repos yet
+# Affects libncursesw6, libtinfo6, ncurses-base, ncurses-bin
+# https://avd.aquasec.com/nvd/cve-2025-69720
+CVE-2025-69720
+
+# nghttp2 DoS via malformed HTTP/2 frames — no fix in Debian 13 repos yet
+# Affects libnghttp2-14
+# https://avd.aquasec.com/nvd/cve-2026-27135
+CVE-2026-27135
+
+# systemd arbitrary code execution via spurious IPC — no fix in Debian 13 repos yet
+# Affects libsystemd0, libudev1
+# https://avd.aquasec.com/nvd/cve-2026-29111
+CVE-2026-29111
+
+# glibc iconv() DoS — fix_deferred, no patched libc in Debian 13 yet
+# Affects libc-bin, libc6
+# https://avd.aquasec.com/nvd/cve-2026-4046
+CVE-2026-4046
+
+# minimatch ReDoS — transitive npm dep (MCP server), no direct exposure
+# https://avd.aquasec.com/nvd/cve-2026-27903
+CVE-2026-27903
+# https://avd.aquasec.com/nvd/cve-2026-27904
+CVE-2026-27904
+
+# picomatch ReDoS — transitive npm dep, no direct exposure
+# https://avd.aquasec.com/nvd/cve-2026-33671
+CVE-2026-33671
+
+# node-tar path traversal — transitive npm dep, not used to extract untrusted archives
+# https://avd.aquasec.com/nvd/cve-2026-29786
+CVE-2026-29786
+# https://avd.aquasec.com/nvd/cve-2026-31802
+CVE-2026-31802

Dockerfile

@@ -1,6 +1,6 @@
 # =============================================================================
 # Turnstone — Docker build with uv for reproducible, locked installs
-# Single image for all services: server, bridge, console, sim, eval
+# Single image for all services: server, console, channel, eval
 # =============================================================================
 
 FROM python:3.14-slim
@@ -8,33 +8,39 @@ FROM python:3.14-slim
 LABEL org.opencontainers.image.title="turnstone" \
       org.opencontainers.image.description="Multi-node AI orchestration platform"
 
-COPY --from=ghcr.io/astral-sh/uv:0.11.2 /uv /usr/local/bin/uv
+COPY --from=ghcr.io/astral-sh/uv:0.11.3 /uv /usr/local/bin/uv
 
 # Remove the slim image's man page exclusion so man-db has actual content
 RUN rm -f /etc/dpkg/dpkg.cfg.d/docker
 
 # System dependencies: psycopg (libpq5), developer tooling for agent workflows
 RUN apt-get update && apt-get upgrade -y && apt-get install -y --no-install-recommends \
-    libpq5 git curl jq man-db manpages \
+    libpq5 git curl jq man-db manpages procps file \
     && rm -rf /var/lib/apt/lists/*
 
+# Node.js LTS (for npx-based MCP servers like @modelcontextprotocol/server-github)
+COPY --from=node:24-slim /usr/local/bin/node /usr/local/bin/node
+COPY --from=node:24-slim /usr/local/lib/node_modules /usr/local/lib/node_modules
+RUN ln -s ../lib/node_modules/npm/bin/npm-cli.js /usr/local/bin/npm \
+    && ln -s ../lib/node_modules/npm/bin/npx-cli.js /usr/local/bin/npx
+
 # Non-root user
 RUN useradd --create-home --shell /bin/bash turnstone
 
 WORKDIR /app
 
-# Compile bytecode for faster startup
-ENV UV_COMPILE_BYTECODE=1
-
 # Install dependencies first (cached layer — only re-runs when deps change)
 COPY pyproject.toml uv.lock README.md LICENSE ./
 RUN uv sync --frozen --no-install-project --no-dev \
-    --extra all
+    --no-compile --extra all
 
 # Install the project itself
 COPY turnstone/ turnstone/
 RUN uv sync --frozen --no-dev \
-    --extra all
+    --no-compile --extra all
+
+# Compile bytecode in a separate step (avoids fd exhaustion during install)
+RUN python -m compileall -q .venv turnstone/
 
 # Add venv to PATH so entry points are found
 ENV PATH="/app/.venv/bin:$PATH"
@@ -49,6 +55,9 @@ COPY docker/entrypoint.sh /usr/local/bin/entrypoint.sh
 WORKDIR /data
 RUN chown turnstone:turnstone /data
 
+# Workspace mount point — bind-mount a host directory here
+RUN mkdir -p /workspace && chown turnstone:turnstone /workspace
+
 USER turnstone
 
 ENTRYPOINT ["entrypoint.sh"]

QUICKSTART.md

@@ -45,9 +45,9 @@ That's it — no flags, no arguments. The wizard prompts for everything.
 The wizard supports two deployment modes:
 
 - **Single-node production** (`docker compose --profile production up`) —
-  1 server + bridge + console + PostgreSQL + Redis. Good for most use cases.
+  1 server + console + PostgreSQL. Good for most use cases.
 - **Multi-node cluster** (`docker compose --profile cluster up`) —
-  10-node server/bridge fleet + PostgreSQL + Redis. For high-throughput or
+  10-node server fleet + console + PostgreSQL. For high-throughput or
   HA deployments.
 
 ## Example Session

README.md

@@ -5,418 +5,136 @@
 [![Python](https://img.shields.io/pypi/pyversions/turnstone)](https://pypi.org/project/turnstone/)
 [![License](https://img.shields.io/badge/license-BSL--1.1-blue)](LICENSE)
 
-Experimental multi-node AI orchestration platform. Deploy tool-using AI agents across a cluster of servers, driven by message queues or interactive interfaces.
+Multi-node AI orchestration platform. Deploy tool-using AI agents across a cluster of servers with direct HTTP routing, interactive interfaces, and enterprise governance.
 
-> **Beta — Use at your own risk.** Turnstone is under active development and has not reached a stable release. APIs, configuration formats, and database schemas may change between versions without migration paths. We make no guarantees of determinism, reliability, or backward compatibility. Evaluate thoroughly before deploying to any environment where these properties matter.
+<p align="center">
+  <img src="docs/assets/hero.png" alt="Turnstone console — multi-workstream AI orchestration with mermaid diagrams" width="960"/>
+</p>
 
 Named after the [Ruddy Turnstone](https://en.wikipedia.org/wiki/Ruddy_turnstone) (*Arenaria interpres*) — a shorebird that flips stones to discover what's hiding underneath.
 
+### Release Tracks
+
+| Track | Install | Docker | Description |
+|-------|---------|--------|-------------|
+| **Stable** | `pip install turnstone` | `ghcr.io/turnstonelabs/turnstone:stable` | Production-grade. Bugfixes only. |
+| **Experimental** | `pip install turnstone --pre` | `ghcr.io/turnstonelabs/turnstone:experimental` | New features. May have rough edges. |
+
+See [docs/releasing.md](docs/releasing.md) for the full release process.
+
 ## What it does
 
-Turnstone gives LLMs tools — shell, files, search, web, planning — and orchestrates multi-turn conversations where the model investigates, acts, and reports. It runs as:
+Turnstone gives LLMs tools — shell, files, search, web, planning — and orchestrates multi-turn conversations where the model investigates, acts, and reports.
 
 - **Interactive sessions** — terminal CLI or browser UI with parallel workstreams
-- **Queue-driven agents** — trigger workstreams via message queue, stream progress, approve or auto-approve tool use
-- **Multi-node clusters** — generic work load-balances across nodes, directed work routes to a specific server
-- **Cluster dashboard** — real-time view of all nodes and workstreams, reverse proxy for server UIs
-- **Intent validation** — an LLM judge evaluates every tool call before approval, presenting risk assessments and evidence-based recommendations so users can make informed decisions instead of blindly approving raw tool calls
-- **Governance & compliance** — RBAC, OIDC SSO (Okta, Azure AD, Google, Keycloak), tool policies, skills (reusable behavioral profiles with security scanning), usage tracking, and append-only audit logs
-- **Cluster simulator** — test the stack at scale (up to 1000 nodes) without an LLM backend
-
-Works with any OpenAI-compatible API (vLLM, llama.cpp, NVIDIA NIM) or Anthropic's native Messages API. Supports [MCP](https://modelcontextprotocol.io/) for external tool servers with native deferred tool loading on Anthropic and OpenAI APIs (BM25 fallback for local models).
+- **Cluster dashboard** — real-time view of all nodes and workstreams with console routing proxy
+- **Intent validation** — LLM judge evaluates every tool call with risk assessments and evidence
+- **Governance** — RBAC, OIDC SSO, tool policies, skills, usage tracking, audit logs
+- **Multi-provider** — OpenAI-compatible APIs (vLLM, llama.cpp, NIM) and Anthropic Messages API
+- **MCP support** — external tool servers with native deferred loading (Anthropic/OpenAI) or BM25 fallback
 
 <p align="center">
-  <img src="docs/diagrams/architecture-overview.svg" alt="Turnstone system architecture — data flow from clients through gateways, Redis MQ, cluster nodes, to LLM providers" width="960"/>
+  <img src="docs/diagrams/architecture-overview.svg" alt="Turnstone system architecture" width="960"/>
 </p>
 
 ## Quickstart
 
-### Interactive (terminal)
-
 ```bash
 pip install turnstone
+
+# Terminal REPL
 turnstone --base-url http://localhost:8000/v1
-```
 
-### Interactive (browser)
-
-```bash
+# Browser UI
 turnstone-server --port 8080 --base-url http://localhost:8000/v1
-```
 
-### Queue-driven (programmatic)
-
-```bash
-pip install turnstone[mq]
-turnstone-bridge --server-url http://localhost:8080 --redis-host localhost
-```
-
-```python
-from turnstone.mq import TurnstoneClient
-
-with TurnstoneClient() as client:
-    # Generic — any available node picks it up
-    result = client.send_and_wait("Analyze the error logs", auto_approve=True)
-    print(result.content)
-
-    # Directed — must run on a specific server
-    result = client.send_and_wait(
-        "Check disk I/O on this server",
-        target_node="server-12",
-        auto_approve=True,
-    )
-```
-
-### Cluster dashboard
-
-```bash
+# Cluster dashboard
 pip install turnstone[console]
-turnstone-console --redis-host localhost --port 8090
+turnstone-console --port 8090
 ```
 
-Then open `http://localhost:8090` for the cluster-wide dashboard. Create workstreams from the console and interact with any node's server UI through the built-in reverse proxy — no direct server port access required.
-
 ### Docker
 
 ```bash
 cp .env.example .env  # edit LLM_BASE_URL, OPENAI_API_KEY, etc.
-docker compose up     # starts redis + server + bridge + console (SQLite)
+docker compose --profile production up
 ```
 
-For production with PostgreSQL:
+See [QUICKSTART.md](QUICKSTART.md) for the bootstrap wizard and [docs/docker.md](docs/docker.md) for Docker configuration and profiles.
 
-```bash
-# Requires POSTGRES_PASSWORD and DB_BACKEND=postgresql in .env (or exported)
-docker compose --profile production up  # adds PostgreSQL, uses it as database
+### Programmatic (SDK)
+
+```python
+from turnstone.sdk import TurnstoneServer
+
+with TurnstoneServer("http://localhost:8080", token="tok_xxx") as client:
+    ws = client.create_workstream(name="demo")
+    result = client.send_and_wait("Analyze the error logs", ws.ws_id, auto_approve=True)
+    print(result.content)
 ```
 
-Console dashboard at http://localhost:8090. See [docs/docker.md](docs/docker.md) for configuration, scaling, and profiles.
-
-### Simulator
-
-Test the multi-node stack at scale without an LLM backend:
-
-```bash
-docker compose --profile sim up redis console sim
-```
-
-Or standalone:
-
-```bash
-pip install turnstone[sim]
-turnstone-sim --nodes 100 --scenario steady --duration 60 --mps 10
-```
-
-See [docs/simulator.md](docs/simulator.md) for scenarios, CLI reference, and metrics.
-
-## Architecture
-
-### Diagrams
-
-Detailed UML diagrams are available in [`docs/diagrams/`](docs/diagrams/):
-
-| Diagram | Description |
-|---------|-------------|
-| [System Context](docs/diagrams/png/01-system-context.png) | Top-level components and external dependencies |
-| [Package Structure](docs/diagrams/png/02-package-structure.png) | Python modules and dependency graph |
-| [Core Engine Classes](docs/diagrams/png/03-core-engine-classes.png) | SessionUI protocol, ChatSession, LLMProvider, WorkstreamManager |
-| [Conversation Turn](docs/diagrams/png/04-conversation-turn.png) | Full message lifecycle through the engine (provider-agnostic) |
-| [Tool Pipeline](docs/diagrams/png/05-tool-pipeline.png) | Three-phase prepare/approve/execute |
-| [MQ Protocol](docs/diagrams/png/06-mq-protocol.png) | 9 inbound + 19 outbound message types |
-| [Message Routing](docs/diagrams/png/07-message-routing.png) | Multi-node routing scenarios |
-| [Redis Key Schema](docs/diagrams/png/08-redis-key-schema.png) | All Redis keys, types, and TTLs |
-| [Workstream States](docs/diagrams/png/09-workstream-states.png) | State machine transitions |
-| [Simulator](docs/diagrams/png/10-simulator-architecture.png) | SimCluster, dispatchers, scenarios |
-| [Console Data Flow](docs/diagrams/png/11-console-data-flow.png) | Dashboard data collection threads |
-| [Deployment](docs/diagrams/png/12-deployment.png) | Docker Compose service topology |
-| [SDK Architecture](docs/diagrams/png/13-sdk-architecture.png) | Python + TypeScript client libraries |
-| [Storage Architecture](docs/diagrams/png/14-storage-architecture.png) | Pluggable database backends (SQLite + PostgreSQL) |
-| [Auth Architecture](docs/diagrams/png/15-auth-architecture.png) | JWT, scopes, token types, login flows |
-| [Channel Architecture](docs/diagrams/png/16-channel-architecture.png) | Discord/Slack adapter protocol and routing |
-| [Notify Flow](docs/diagrams/png/17-notify-flow.png) | Channel notification dispatch |
-| [Watch Architecture](docs/diagrams/png/18-watch-architecture.png) | Periodic command polling daemon |
-| [Governance Architecture](docs/diagrams/png/19-governance-architecture.png) | RBAC, policies, audit, usage enforcement flow |
-| [WS Template Architecture](docs/diagrams/png/21-ws-template-architecture.png) | Workstream template application and lifecycle |
-| [Judge Architecture](docs/diagrams/png/22-judge-architecture.png) | Intent validation two-tier evaluation pipeline |
-| [OIDC Architecture](docs/diagrams/png/25-oidc-architecture.png) | OIDC SSO authorization code flow with PKCE |
-
-### Governance
-
-Turnstone includes a built-in governance layer for enterprise deployments — manage who can do what, which tools run unattended, and where every token goes.
-
-- **RBAC** — 15 granular permissions, 3 built-in roles (admin / operator / viewer), custom roles, privilege escalation prevention
-- **OIDC SSO** — single sign-on via any OpenID Connect provider (Okta, Azure AD, Google, Keycloak); Authorization Code Flow with PKCE, auto-provisioning, claim-based role mapping with demotion propagation; see [docs/oidc.md](docs/oidc.md)
-- **Tool policies** — glob-pattern rules (`allow` / `deny` / `ask`) with priority ordering; automate approvals or lock down dangerous tools
-- **Skills** — reusable behavioral profiles with system prompts, `{{variable}}` substitution, session config (model, temperature, token budget), install-time security scanning, version history, external discovery (skills.sh / GitHub), and runtime `skill` tool for model-driven skill activation
-- **Usage tracking** — per-request token and tool metrics, aggregation by day / model / user, automatic 90-day pruning
-- **Audit logging** — append-only event trail for all admin mutations, IP-aware, 365-day retention
-
-All governance features are managed through the console admin panel (13 tabs) and the full REST API. Runtime settings (model, tools, rate limiting, health, judge, memory) are configurable via the admin Settings tab — no config file edits or restarts needed for most changes. See [docs/governance.md](docs/governance.md) for setup and [docs/settings.md](docs/settings.md) for the settings reference.
-
-### Intent Validation (LLM Judge)
-
-Every tool call that requires human approval is evaluated by an intent validation judge that provides a structured risk assessment alongside the approval prompt — so instead of "approve this bash command?", users see a verdict with risk level, confidence, recommendation, and reasoning.
-
-The system uses a two-tier evaluation pipeline:
-
-1. **Heuristic tier** (instant, free) — 36 pattern-based rules classify tool calls by severity. Catches destructive commands (`rm -rf /`, `DROP TABLE`), privilege escalation (`sudo`), credential access, supply chain risks, browser data export, cloud infrastructure mutations, and more. Results appear immediately.
-2. **LLM judge tier** (async) — A full LLM evaluation runs in the background with access to `read_file` and `list_directory` for evidence gathering. The judge can inspect files that a write would overwrite, check directory contents before a delete, and cite specific evidence in its reasoning. Results update the UI progressively when ready.
-
-The judge defaults to the same model as the session (self-consistency) but can be configured to use a separate model — useful when running a small local model for tasks but wanting a commercial model for safety evaluation.
-
-```toml
-[judge]
-enabled = true           # on by default
-model = ""               # empty = same as session model
-provider = ""            # empty = same as session provider
-timeout = 60.0           # generous for local models
-```
-
-Verdicts are persisted for audit and exposed via Prometheus metrics (`turnstone_judge_verdicts_total`, `turnstone_judge_llm_latency_seconds`).
-
-Skills are also scanned at install time — the scanner evaluates content, supply chain, vulnerability, and declared capability risk across four independent axes. Results populate `scan_status` (tier) and `scan_report` (structured JSON breakdown) on the skill record so administrators can assess risk before enabling a skill.
-
-Tool execution results are evaluated by an output guard before entering the conversation — detecting prompt injection payloads in fetched content, credential leakage in command output, and encoded payloads. Detected credentials are automatically redacted.
-
-See [docs/judge.md](docs/judge.md) for the full guide.
-
-## Multi-node routing
-
-Each Turnstone server runs a bridge process. Bridges share a Redis instance for coordination:
-
-| Redis Key | Purpose |
-|-----------|---------|
-| `turnstone:inbound` | Shared work queue — generic tasks, any node |
-| `turnstone:inbound:{node_id}` | Per-node queue — directed tasks |
-| `turnstone:ws:{ws_id}` | Workstream ownership — auto-routes follow-ups |
-| `turnstone:node:{node_id}` | Node heartbeat + metadata for discovery |
-| `turnstone:events:{ws_id}` | Per-workstream event pub/sub |
-| `turnstone:events:global` | Global event pub/sub |
-| `turnstone:events:cluster` | Cluster-wide state changes (for turnstone-console) |
-
-**Routing rules:**
-1. Message has `target_node` → routes to that node's queue
-2. Message has `ws_id` → looks up owner, routes to owning node
-3. Neither → shared queue, next available bridge picks it up
-
-Bridges BLPOP from their per-node queue (priority) then the shared queue. Directed work always takes precedence.
-
 ## Tools
 
-15 built-in tools, 2 agent tools, plus external tools via MCP:
+Built-in tools for shell, files, search, web, memory, notifications, and autonomous sub-agents — plus external tools via [MCP](https://modelcontextprotocol.io/) with native deferred loading. See [docs/tools.md](docs/tools.md) for the full reference and [docs/mcp.md](docs/mcp.md) for MCP configuration.
 
-| Tool | Description | Auto-approved |
-|------|-------------|:---:|
-| `bash` | Execute shell commands | |
-| `read_file` | Read file contents (text or images with vision models) | yes |
-| `write_file` | Write/create files | |
-| `edit_file` | Fuzzy-match file editing | |
-| `search` | Search files by name/content | yes |
-| `math` | Sandboxed Python evaluation | |
-| `man` | Read man pages | yes |
-| `web_fetch` | Fetch URL content | |
-| `web_search` | Web search (provider-native or Tavily) | |
-| `memory` | Structured persistent memory (save/search/delete/list) | yes |
-| `recall` | Search conversation history | yes |
-| `notify` | Send notifications to linked channels | yes |
-| `watch` | Periodic command polling with conditions | |
-| `task` | Spawn autonomous sub-agent | |
-| `plan` | Explore codebase, write .plan.md | |
-| `mcp__*` | External tools from MCP servers | |
+## Architecture
 
-When the total tool count exceeds a configurable threshold (default 20), MCP tools are automatically deferred using native `defer_loading` on Anthropic and OpenAI APIs, or a transparent client-side BM25 search for local models. The LLM discovers deferred tools on demand via a `tool_search` capability — no configuration needed beyond `--tool-search auto` (the default).
+**Single-node**: Client → Server (direct HTTP + SSE). No external dependencies beyond the database.
 
-### MCP Tool Servers
+**Multi-node**: Client → Console (hash ring routing proxy) → Server nodes. The console maintains a 65536-entry bucket cache for O(1) workstream routing. A rebalancer daemon redistributes buckets when nodes join or leave.
 
-Turnstone supports the [Model Context Protocol](https://modelcontextprotocol.io/) (MCP) for connecting external tool servers. MCP tools are discovered at startup, converted to OpenAI function-calling format, and merged with built-in tools. Each MCP tool is prefixed with `mcp__{server}__{tool}` to avoid name collisions. Tool lists stay fresh via push notifications (`tools.listChanged`), periodic polling for servers without push, and manual `/mcp refresh`.
+| Component | Purpose |
+|-----------|---------|
+| `turnstone` | Terminal CLI (REPL) |
+| `turnstone-server` | Web UI + REST API + SSE events |
+| `turnstone-console` | Cluster dashboard + routing proxy + admin panel |
+| `turnstone-channel` | Channel gateway (Discord, with adapters for Slack/Teams planned) |
+| `turnstone-admin` | User/token management CLI |
+| `turnstone-eval` | Eval harness for prompt/tool optimization |
+| `turnstone-bootstrap` | LLM-guided setup wizard |
 
-Configure via `config.toml` or `--mcp-config`:
+### Diagrams
 
-```toml
-[mcp.servers.github]
-command = "npx"
-args = ["-y", "@modelcontextprotocol/server-github"]
+UML diagrams in [`docs/diagrams/`](docs/diagrams/):
 
-[mcp.servers.github.env]
-GITHUB_TOKEN = "ghp_..."
-```
+| Diagram | Description |
+|---------|-------------|
+| [System Context](docs/diagrams/png/01-system-context.png) | Components and external dependencies |
+| [Package Structure](docs/diagrams/png/02-package-structure.png) | Python modules and dependency graph |
+| [Core Engine](docs/diagrams/png/03-core-engine-classes.png) | SessionUI, ChatSession, LLMProvider |
+| [Conversation Turn](docs/diagrams/png/04-conversation-turn.png) | Message lifecycle through the engine |
+| [Tool Pipeline](docs/diagrams/png/05-tool-pipeline.png) | Prepare / approve / execute |
+| [Workstream States](docs/diagrams/png/09-workstream-states.png) | State machine transitions |
+| [Console Data Flow](docs/diagrams/png/11-console-data-flow.png) | Dashboard data collection |
+| [Deployment](docs/diagrams/png/12-deployment.png) | Docker Compose topology |
+| [Auth](docs/diagrams/png/15-auth-architecture.png) | JWT, scopes, login flows |
+| [Channels](docs/diagrams/png/16-channel-architecture.png) | Discord adapter + routing |
+| [Judge](docs/diagrams/png/22-judge-architecture.png) | Intent validation pipeline |
+| [OIDC](docs/diagrams/png/25-oidc-architecture.png) | SSO authorization code flow |
 
-Or use a standard MCP JSON config file:
+## Documentation
 
-```bash
-turnstone --mcp-config ~/.config/turnstone/mcp.json
-turnstone-server --mcp-config ~/.config/turnstone/mcp.json
-```
-
-Use `/mcp` in the REPL to list connected tools, `/mcp refresh` to re-fetch tool lists from servers. MCP tools require user approval by default (overridden by `--skip-permissions` or UI auto-approve).
-
-### Multi-Model and Multi-Provider Support
-
-Turnstone supports multiple model backends per server instance, including different LLM providers. `ChatSession` delegates all API communication to pluggable `LLMProvider` adapters — the internal message format stays OpenAI-like, and each provider translates at the API boundary. Define named models in `config.toml` and select per-workstream or switch mid-session with `/model <alias>`.
-
-```toml
-[models.local]
-base_url = "http://localhost:8000/v1"
-model = "qwen3-32b"
-# provider defaults to "openai" (works with vLLM, llama.cpp, etc.)
-
-[models.claude]
-provider = "anthropic"
-api_key = "sk-ant-..."
-model = "claude-opus-4-6"
-context_window = 200000
-
-[models.openai]
-base_url = "https://api.openai.com/v1"
-api_key = "sk-..."
-model = "gpt-5"
-context_window = 400000
-
-[model]
-default = "local"              # which model to use by default
-fallback = ["claude", "openai"]  # try these if the primary is unreachable
-agent_model = "claude"         # optional: separate model for plan/task sub-agents
-```
-
-Supported providers: `"openai"` (default -- OpenAI, vLLM, llama.cpp, any OpenAI-compatible API) and `"anthropic"` (Anthropic Messages API, requires `pip install turnstone[anthropic]`).
-
-Use `/model` to show available models, `/model claude` to switch. Workstreams created via the API accept an optional `model` parameter.
-
-## Configuration
-
-All entry points read `~/.config/turnstone/config.toml`. CLI flags override config values.
-
-```toml
-[api]
-base_url = "http://localhost:8000/v1"
-api_key = ""
-# tavily_key = ""      # only needed for local/vLLM models without native search
-
-[model]
-name = ""              # empty = auto-detect
-temperature = 0.5
-reasoning_effort = "medium"
-default = "default"    # model alias for new workstreams
-fallback = []          # ordered list of fallback model aliases
-agent_model = ""       # model alias for plan/task sub-agents
-
-[tools]
-timeout = 30
-skip_permissions = false
-search = "auto"            # "auto" (enable when >threshold tools), "on", "off"
-search_threshold = 20      # min tools before tool search activates
-search_max_results = 5     # max tools returned per search query
-
-[server]
-host = "0.0.0.0"
-port = 8080
-max_workstreams = 50       # auto-evicts oldest idle when full
-
-[redis]
-host = "localhost"
-port = 6379
-password = ""
-
-[bridge]
-server_url = "http://localhost:8080"
-node_id = ""           # empty = hostname_xxxx
-
-[console]
-host = "0.0.0.0"
-port = 8090
-url = "http://localhost:8090"  # used by CLI /cluster commands
-poll_interval = 10
-
-[health]
-backend_probe_interval = 30
-backend_probe_timeout = 5
-circuit_breaker_threshold = 5
-circuit_breaker_cooldown = 60
-
-[ratelimit]
-enabled = true
-requests_per_second = 10.0
-burst = 20
-
-[database]
-backend = "sqlite"     # "sqlite" (default) or "postgresql"
-path = ".turnstone.db" # SQLite file path (relative to working directory)
-# url = "postgresql+psycopg://user:pass@host:5432/turnstone"  # PostgreSQL
-# pool_size = 2        # PostgreSQL connection pool size (per process)
-
-[judge]
-enabled = true         # intent validation for tool approvals (--no-judge to disable)
-model = ""             # empty = same as session model (self-consistency)
-provider = ""          # empty = same as session provider
-timeout = 60.0         # LLM judge timeout in seconds
-confidence_threshold = 0.7
-
-[mcp]
-config_path = ""       # path to MCP JSON config file (alternative to TOML sections)
-refresh_interval = 14400  # periodic refresh for servers without push notifications (seconds, 0 to disable)
-
-[mcp.servers.example]  # one section per MCP server
-command = "npx"
-args = ["-y", "@modelcontextprotocol/server-example"]
-# type = "stdio"       # "stdio" (default) or "http"
-# url = ""             # for HTTP transport
-```
-
-Precedence: CLI args > environment variables > config.toml > defaults.
-
-## Workstreams
-
-Parallel independent conversations, each with its own session and state:
-
-| Symbol | State | Meaning |
-|--------|-------|---------|
-| `·` | idle | Waiting for input |
-| `◌` | thinking | Model is generating |
-| `▸` | running | Tool execution in progress |
-| `◆` | attention | Waiting for approval |
-| `✖` | error | Something went wrong |
-
-Idle workstreams are automatically cleaned up after 2 hours (configurable). In multi-node deployments, workstream ownership is tracked in Redis — follow-up messages auto-route to the owning node.
-
-## Monitoring
-
-`/metrics` endpoint exposes Prometheus-format metrics:
-
-- `turnstone_tokens_total{direction}` — prompt/completion token counters
-- `turnstone_tool_calls_total{tool}` — per-tool invocation counts
-- `turnstone_workstream_context_ratio{ws_id}` — per-workstream context utilization
-- `turnstone_http_request_duration_seconds` — request latency histogram
-- `turnstone_workstreams_by_state{state}` — workstream state gauges
-- `turnstone_sse_connections_active` — current open SSE connections
-- `turnstone_ratelimit_rejected_total` — requests rejected by rate limiter
-- `turnstone_backend_up` — LLM backend reachability (0/1)
-- `turnstone_circuit_state` — circuit breaker state (0=closed, 1=open, 2=half_open)
-- `turnstone_workstreams_evicted_total` — workstreams auto-evicted at capacity
-- `turnstone_judge_verdicts_total{tier,risk_level}` — intent validation verdicts by tier and risk
-- `turnstone_judge_llm_latency_seconds` — LLM judge evaluation latency histogram
-- `turnstone_judge_enabled` — whether the intent validation judge is active (0/1)
-
-Per-workstream metrics are labeled by `ws_id` (bounded by `[server].max_workstreams`).
-
-### Health & Rate Limiting
-
-**Health degradation.** A background `BackendHealthMonitor` probes the LLM backend every `backend_probe_interval` seconds. When the backend is unreachable, `/health` reports `"status": "degraded"` (HTTP 200) and the `turnstone_backend_up` gauge drops to 0.
-
-**Circuit breaker.** After `circuit_breaker_threshold` consecutive probe failures the circuit opens (CLOSED -> OPEN). While open, `ChatSession._create_stream_with_retry` skips the backend entirely and returns an error. After `circuit_breaker_cooldown` seconds the circuit enters HALF_OPEN, allowing a single probe. A successful probe closes the circuit; a failure re-opens it.
-
-**Per-IP rate limiting.** When `[ratelimit].enabled` is true, each client IP is tracked with a token-bucket limiter (`requests_per_second` / `burst`). Rate limiting is applied in `do_GET`/`do_POST` after authentication but before route dispatch. `/health` and `/metrics` are exempt. Requests that exceed the limit receive HTTP 429 with a `Retry-After` header.
-
-**Workstream eviction.** When `WorkstreamManager.create()` would exceed `max_workstreams`, the oldest IDLE workstream is automatically evicted and the `turnstone_workstreams_evicted_total` counter is incremented. Configure via `[server].max_workstreams` (default 50).
+| Topic | Link |
+|-------|------|
+| Configuration reference | [docs/settings.md](docs/settings.md) |
+| API reference | [docs/api-reference.md](docs/api-reference.md) |
+| Docker deployment | [docs/docker.md](docs/docker.md) |
+| Intent validation (judge) | [docs/judge.md](docs/judge.md) |
+| Governance & RBAC | [docs/governance.md](docs/governance.md) |
+| OIDC SSO | [docs/oidc.md](docs/oidc.md) |
+| TLS / mTLS | [docs/tls.md](docs/tls.md) |
+| Channel integrations | [docs/channels.md](docs/channels.md) |
+| Console dashboard | [docs/console.md](docs/console.md) |
+| Eval harness | [docs/eval.md](docs/eval.md) |
+| Tools reference | [docs/tools.md](docs/tools.md) |
+| MCP integration | [docs/mcp.md](docs/mcp.md) |
 
 ## Requirements
 
 - Python 3.11+
-- An OpenAI-compatible API endpoint ([vLLM](https://github.com/vllm-project/vllm), [NVIDIA NIM](https://build.nvidia.com/), [llama.cpp](https://github.com/ggml-org/llama.cpp), etc.) or an Anthropic API key
-- Redis (for message queue bridge — `pip install turnstone[mq]`)
-- Anthropic provider (optional — `pip install turnstone[anthropic]`)
-- PostgreSQL (optional, for production — `pip install turnstone[postgres]`)
-- Math sandbox packages (optional — `pip install turnstone[sandbox]` for sympy, numpy, scipy, pytest)
-- [Git LFS](https://git-lfs.com/) (for cloning — diagram PNGs are stored in LFS)
+- An OpenAI-compatible API endpoint or Anthropic API key
+- Optional: PostgreSQL (`pip install turnstone[postgres]`), Anthropic (`pip install turnstone[anthropic]`)
+- [Git LFS](https://git-lfs.com/) for cloning (diagram PNGs)
 
 ## License
 

deploy/docker-compose.tls.yml

@@ -3,12 +3,12 @@
 # Usage (requires base compose.yaml with production profile):
 #   docker compose -f compose.yaml -f deploy/docker-compose.tls.yml --profile production up
 #
-# The tls-init service bootstraps a CA and issues a cert for Redis.
+# The tls-init service bootstraps a CA and issues certs.
 # All turnstone services auto-provision their own certs via the
 # console's ACME endpoint.
 
 services:
-  # Bootstrap: create CA + Redis cert before anything starts.
+  # Bootstrap: create CA before anything starts.
   # Runs as root to create directories in the volume, then chowns
   # to turnstone:turnstone with restrictive perms (keys 0600).
   tls-init:
@@ -19,7 +19,7 @@ services:
       - -c
       - |
         set -e
-        turnstone-admin tls-bootstrap --out /certs --issue redis
+        turnstone-admin tls-bootstrap --out /certs
         chown -R turnstone:turnstone /certs
         find /certs -type d -exec chmod 750 {} +
         find /certs -type f -name '*key.pem' -exec chmod 600 {} +
@@ -45,11 +45,7 @@ services:
       - turnstone-console
       - --host=0.0.0.0
       - --port=8090
-      - --redis-host=redis
-      - --redis-port=6379
       - --poll-interval=${CONSOLE_POLL_INTERVAL:-10}
-      - --redis-tls
-      - --redis-tls-ca=/certs/ca.pem
 
   # Server: auto-provisions certs via console ACME, serves HTTPS
   server:
@@ -64,41 +60,14 @@ services:
     # Disable healthcheck — server serves HTTPS with mTLS which the
     # stdlib healthcheck script can't satisfy. The base compose
     # healthcheck uses plain HTTP which won't work on an HTTPS listener.
-    # TODO: wire healthcheck with client cert from /certs volume
     healthcheck:
       disable: true
 
-  # Bridge: mTLS to server + Redis TLS
-  bridge:
-    depends_on:
-      console:
-        condition: service_healthy
-      server:
-        condition: service_started
-      redis:
-        condition: service_healthy
-    volumes:
-      - tls-certs:/certs:ro
-    environment:
-      TURNSTONE_TLS_ENABLED: "true"
-      TURNSTONE_TLS_SANS: "bridge"
-    command:
-      - turnstone-bridge
-      - --server-url=http://server:8080
-      - --redis-host=redis
-      - --redis-port=6379
-      - --heartbeat-ttl=${HEARTBEAT_TTL:-60}
-      - --approval-timeout=${APPROVAL_TIMEOUT:-3600}
-      - --redis-tls
-      - --redis-tls-ca=/certs/ca.pem
-
-  # Channel: Redis TLS
+  # Channel: TLS
   channel:
     depends_on:
       console:
         condition: service_healthy
-      redis:
-        condition: service_healthy
     volumes:
       - tls-certs:/certs:ro
     environment:
@@ -109,38 +78,8 @@ services:
       - -c
       - >-
         turnstone-channel
-        --redis-host=redis
-        --redis-port=6379
-        --redis-tls
-        --redis-tls-ca=/certs/ca.pem
         --http-host=0.0.0.0
         $${TURNSTONE_DISCORD_GUILD:+--discord-guild $$TURNSTONE_DISCORD_GUILD}
 
-  # Redis: TLS with certs from bootstrap
-  redis:
-    depends_on:
-      tls-init:
-        condition: service_completed_successfully
-    volumes:
-      - tls-certs:/certs:ro
-    command:
-      - sh
-      - -c
-      - |
-        ARGS="--tls-port 6379 --port 0 \
-          --tls-cert-file /certs/certs/redis/cert.pem \
-          --tls-key-file /certs/certs/redis/key.pem \
-          --tls-ca-cert-file /certs/ca.pem \
-          --tls-auth-clients no"
-        if [ -n "$$REDIS_PASSWORD" ]; then
-          ARGS="$$ARGS --requirepass $$REDIS_PASSWORD"
-        fi
-        exec redis-server $$ARGS
-    healthcheck:
-      test: ["CMD-SHELL", "if [ -n \"$$REDIS_PASSWORD\" ]; then redis-cli --tls --cacert /certs/ca.pem -a $$REDIS_PASSWORD ping; else redis-cli --tls --cacert /certs/ca.pem ping; fi"]
-      interval: 5s
-      timeout: 3s
-      retries: 5
-
 volumes:
   tls-certs:

deploy/helm/turnstone/Chart.yaml

@@ -10,7 +10,3 @@ dependencies:
     version: ~18.5.0
     repository: https://charts.bitnami.com/bitnami
     condition: postgresql.enabled
-  - name: redis
-    version: ~25.3.0
-    repository: https://charts.bitnami.com/bitnami
-    condition: redis.enabled

deploy/helm/turnstone/templates/NOTES.txt

@@ -25,14 +25,10 @@ Then open: http://localhost:{{ .Values.console.service.port }}
 
 Components deployed:
   - Server:  {{ include "turnstone.fullname" . }}-server  ({{ .Values.server.replicas }} replica(s))
-  - Bridge:  {{ include "turnstone.fullname" . }}-bridge  ({{ .Values.bridge.replicas }} replica(s))
   - Console: {{ include "turnstone.fullname" . }}-console ({{ .Values.console.replicas }} replica(s))
 {{- if .Values.postgresql.enabled }}
   - PostgreSQL (bitnami subchart)
 {{- end }}
-{{- if .Values.redis.enabled }}
-  - Redis (bitnami subchart)
-{{- end }}
 
 {{- if not .Values.llm.apiKey }}
 {{- if not .Values.llm.existingSecret }}

deploy/helm/turnstone/templates/_helpers.tpl

@@ -110,28 +110,6 @@ Determine the PostgreSQL username.
 {{- end }}
 {{- end }}
 
-{{/*
-Determine the Redis host.
-*/}}
-{{- define "turnstone.redis.host" -}}
-{{- if .Values.redis.enabled }}
-{{- printf "%s-redis-master" .Release.Name }}
-{{- else }}
-{{- .Values.redis.external.host }}
-{{- end }}
-{{- end }}
-
-{{/*
-Determine the Redis port.
-*/}}
-{{- define "turnstone.redis.port" -}}
-{{- if .Values.redis.enabled }}
-{{- printf "6379" }}
-{{- else }}
-{{- .Values.redis.external.port | toString }}
-{{- end }}
-{{- end }}
-
 {{/*
 Determine the secret name for LLM API keys.
 */}}

deploy/helm/turnstone/templates/configmap.yaml

@@ -14,8 +14,6 @@ data:
   TURNSTONE_SERVER_PORT: {{ .Values.server.service.port | quote }}
   TURNSTONE_CONSOLE_HOST: "0.0.0.0"
   TURNSTONE_CONSOLE_PORT: {{ .Values.console.service.port | quote }}
-  TURNSTONE_REDIS_HOST: {{ include "turnstone.redis.host" . | quote }}
-  TURNSTONE_REDIS_PORT: {{ include "turnstone.redis.port" . | quote }}
   TURNSTONE_POLL_INTERVAL: "5"
   {{- if .Values.llm.baseUrl }}
   TURNSTONE_LLM_BASE_URL: {{ .Values.llm.baseUrl | quote }}

deploy/helm/turnstone/templates/deployment-bridge.yaml

@@ -1,45 +0,0 @@
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: {{ include "turnstone.fullname" . }}-bridge
-  labels:
-    {{- include "turnstone.labels" . | nindent 4 }}
-    app.kubernetes.io/component: bridge
-spec:
-  replicas: {{ .Values.bridge.replicas }}
-  selector:
-    matchLabels:
-      {{- include "turnstone.selectorLabels" . | nindent 6 }}
-      app.kubernetes.io/component: bridge
-  template:
-    metadata:
-      labels:
-        {{- include "turnstone.selectorLabels" . | nindent 8 }}
-        app.kubernetes.io/component: bridge
-    spec:
-      serviceAccountName: {{ include "turnstone.serviceAccountName" . }}
-      containers:
-        - name: bridge
-          image: {{ include "turnstone.image" . }}
-          imagePullPolicy: {{ .Values.image.pullPolicy }}
-          command:
-            - turnstone-bridge
-            - --server-url={{ printf "http://%s-server:%s" (include "turnstone.fullname" .) (.Values.server.service.port | toString) }}
-            - --redis-host={{ include "turnstone.redis.host" . }}
-            - --redis-port={{ include "turnstone.redis.port" . }}
-          envFrom:
-            - configMapRef:
-                name: {{ include "turnstone.fullname" . }}-config
-            - secretRef:
-                name: {{ include "turnstone.llm.secretName" . }}
-                optional: true
-          {{- if and .Values.auth.enabled .Values.auth.existingSecret }}
-          env:
-            - name: TURNSTONE_AUTH_TOKEN
-              valueFrom:
-                secretKeyRef:
-                  name: {{ .Values.auth.existingSecret }}
-                  key: TURNSTONE_AUTH_TOKEN
-          {{- end }}
-          resources:
-            {{- toYaml .Values.bridge.resources | nindent 12 }}

deploy/helm/turnstone/templates/deployment-console.yaml

@@ -26,8 +26,6 @@ spec:
             - turnstone-console
             - --host=0.0.0.0
             - --port={{ .Values.console.service.port }}
-            - --redis-host={{ include "turnstone.redis.host" . }}
-            - --redis-port={{ include "turnstone.redis.port" . }}
           ports:
             - name: http
               containerPort: {{ .Values.console.service.port }}
@@ -38,13 +36,13 @@ spec:
             - secretRef:
                 name: {{ include "turnstone.llm.secretName" . }}
                 optional: true
-          {{- if and .Values.auth.enabled .Values.auth.existingSecret }}
+          {{- if or .Values.auth.existingSecret .Values.auth.jwtSecret }}
           env:
-            - name: TURNSTONE_AUTH_TOKEN
+            - name: TURNSTONE_JWT_SECRET
               valueFrom:
                 secretKeyRef:
-                  name: {{ .Values.auth.existingSecret }}
-                  key: TURNSTONE_AUTH_TOKEN
+                  name: {{ include "turnstone.auth.secretName" . }}
+                  key: TURNSTONE_JWT_SECRET
           {{- end }}
           readinessProbe:
             httpGet:

deploy/helm/turnstone/templates/deployment-server.yaml

@@ -41,12 +41,12 @@ spec:
           env:
             - name: TURNSTONE_DB_URL
               value: "postgresql+psycopg://$(TURNSTONE_DB_USER):$(POSTGRES_PASSWORD)@$(TURNSTONE_DB_HOST):$(TURNSTONE_DB_PORT)/$(TURNSTONE_DB_NAME)"
-          {{- if and .Values.auth.enabled .Values.auth.existingSecret }}
-            - name: TURNSTONE_AUTH_TOKEN
+          {{- if or .Values.auth.existingSecret .Values.auth.jwtSecret }}
+            - name: TURNSTONE_JWT_SECRET
               valueFrom:
                 secretKeyRef:
-                  name: {{ .Values.auth.existingSecret }}
-                  key: TURNSTONE_AUTH_TOKEN
+                  name: {{ include "turnstone.auth.secretName" . }}
+                  key: TURNSTONE_JWT_SECRET
           {{- end }}
           readinessProbe:
             httpGet:

deploy/helm/turnstone/templates/secret.yaml

@@ -15,14 +15,7 @@ data:
   {{- else if and (not .Values.postgresql.enabled) .Values.database.external.password }}
   POSTGRES_PASSWORD: {{ .Values.database.external.password | b64enc | quote }}
   {{- end }}
-  {{- if and .Values.auth.enabled .Values.auth.token (not .Values.auth.existingSecret) }}
-  TURNSTONE_AUTH_TOKEN: {{ .Values.auth.token | b64enc | quote }}
-  {{- end }}
-  {{- if and .Values.redis.enabled .Values.redis.auth }}
-  {{- if .Values.redis.auth.password }}
-  REDIS_PASSWORD: {{ .Values.redis.auth.password | b64enc | quote }}
-  {{- end }}
-  {{- else if and (not .Values.redis.enabled) .Values.redis.external.password }}
-  REDIS_PASSWORD: {{ .Values.redis.external.password | b64enc | quote }}
+  {{- if and .Values.auth.jwtSecret (not .Values.auth.existingSecret) }}
+  TURNSTONE_JWT_SECRET: {{ .Values.auth.jwtSecret | b64enc | quote }}
   {{- end }}
 {{- end }}

deploy/helm/turnstone/values.yaml

@@ -24,16 +24,6 @@ postgresql:
     database: turnstone
     username: turnstone
 
-# -- Redis configuration
-redis:
-  enabled: true
-  architecture: standalone
-  # External Redis settings (used when redis.enabled is false)
-  external:
-    host: ""
-    port: 6379
-    existingSecret: ""
-
 # -- Turnstone server (main API + web UI)
 server:
   replicas: 1
@@ -48,17 +38,6 @@ server:
     type: ClusterIP
     port: 8080
 
-# -- Turnstone bridge (Redis MQ connector)
-bridge:
-  replicas: 1
-  resources:
-    requests:
-      cpu: 250m
-      memory: 256Mi
-    limits:
-      cpu: "1"
-      memory: 512Mi
-
 # -- Turnstone console (cluster dashboard)
 console:
   replicas: 1
@@ -80,10 +59,9 @@ llm:
   apiKey: ""
   existingSecret: ""
 
-# -- Authentication
+# -- Authentication (always enabled, JWT secret required)
 auth:
-  enabled: false
-  token: ""
+  jwtSecret: ""
   existingSecret: ""
 
 # -- Ingress configuration

deploy/openshell/turnstone-policy.yaml

@@ -1,8 +1,8 @@
 # OpenShell sandbox policy for Turnstone AI orchestration platform.
 #
 # This policy wraps a turnstone-server process (the primary sandbox target).
-# The bridge, console, and channel gateway are separate processes that would
-# each need their own sandbox with a tailored policy variant.
+# The console and channel gateway are separate processes that would each
+# need their own sandbox with a tailored policy variant.
 #
 # Usage:
 #   openshell sandbox run \
@@ -23,7 +23,6 @@
 #
 # Customization points (search for "CUSTOMIZE"):
 #   - OIDC issuer endpoint
-#   - Redis host/port (if not localhost)
 #   - MCP HTTP server endpoints
 #   - Additional tool binaries
 #   - web_fetch domain allowlist
@@ -166,20 +165,6 @@ network_policies:
   #     - path: /usr/bin/python3*
   #     - path: /usr/local/bin/python3*
 
-  # --- Redis (MQ) ---
-  # CUSTOMIZE: if Redis is not on localhost, add host + allowed_ips.
-  # localhost is blocked by default SSRF protection, so we need allowed_ips.
-
-  redis:
-    name: redis-mq
-    endpoints:
-      - port: 6379
-        allowed_ips:
-          - "127.0.0.1"
-    binaries:
-      - path: /usr/bin/python3*
-      - path: /usr/local/bin/python3*
-
   # --- Discord (channel integration) ---
   # Uncomment if using turnstone-channel with Discord adapter.
 

deploy/terraform/examples/aws-ecs-basic/outputs.tf

@@ -22,8 +22,3 @@ output "rds_endpoint" {
   description = "RDS PostgreSQL endpoint."
   value       = module.turnstone.rds_endpoint
 }
-
-output "redis_endpoint" {
-  description = "ElastiCache Redis endpoint."
-  value       = module.turnstone.redis_endpoint
-}

deploy/terraform/examples/aws-ecs-basic/variables.tf

@@ -10,7 +10,7 @@ variable "vpc_id" {
 }
 
 variable "private_subnet_ids" {
-  description = "List of private subnet IDs for ECS tasks, RDS, and ElastiCache."
+  description = "List of private subnet IDs for ECS tasks and RDS."
   type        = list(string)
 }
 

deploy/terraform/modules/aws-ecs/elasticache.tf

@@ -1,30 +0,0 @@
-# ---------- ElastiCache Subnet Group ----------
-
-resource "aws_elasticache_subnet_group" "this" {
-  name       = "${var.name_prefix}-${var.environment}"
-  subnet_ids = var.private_subnet_ids
-  tags       = local.common_tags
-}
-
-# ---------- ElastiCache Redis Replication Group ----------
-
-resource "aws_elasticache_replication_group" "this" {
-  replication_group_id = "${var.name_prefix}-${var.environment}"
-  description          = "Turnstone Redis for MQ and session state"
-
-  engine               = "redis"
-  engine_version       = "7.1"
-  node_type            = var.redis_node_type
-  num_cache_clusters   = 1
-  port                 = 6379
-
-  subnet_group_name  = aws_elasticache_subnet_group.this.name
-  security_group_ids = [aws_security_group.redis.id]
-
-  at_rest_encryption_enabled = true
-  transit_encryption_enabled = true
-
-  automatic_failover_enabled = false
-
-  tags = local.common_tags
-}

deploy/terraform/modules/aws-ecs/iam.tf

@@ -40,8 +40,8 @@ resource "aws_iam_role_policy" "ecs_execution_secrets" {
           [
             aws_secretsmanager_secret.openai_api_key.arn,
             aws_secretsmanager_secret.db_password.arn,
+            aws_secretsmanager_secret.jwt_secret.arn,
           ],
-          var.auth_token != "" ? [aws_secretsmanager_secret.auth_token[0].arn] : [],
         )
       },
     ]

deploy/terraform/modules/aws-ecs/main.tf

@@ -27,7 +27,6 @@ locals {
     { name = "TURNSTONE_ENV", value = var.environment },
     { name = "TURNSTONE_DB_BACKEND", value = "postgresql" },
     { name = "TURNSTONE_LLM_BASE_URL", value = var.llm_base_url },
-    { name = "TURNSTONE_REDIS_URL", value = "redis://${aws_elasticache_replication_group.this.primary_endpoint_address}:6379/0" },
   ]
 
   # Secrets pulled from Secrets Manager at container start.
@@ -42,20 +41,26 @@ locals {
     },
   ]
 
-  auth_env = var.auth_token != "" ? [
-    { name = "TURNSTONE_AUTH_ENABLED", value = "true" },
-  ] : []
-
-  auth_secrets = var.auth_token != "" ? [
+  auth_secrets = [
     {
-      name      = "TURNSTONE_AUTH_TOKEN"
-      valueFrom = aws_secretsmanager_secret_version.auth_token[0].arn
+      name      = "TURNSTONE_JWT_SECRET"
+      valueFrom = aws_secretsmanager_secret_version.jwt_secret.arn
     },
-  ] : []
+  ]
 }
 
 # ---------- Secrets Manager ----------
 
+resource "aws_secretsmanager_secret" "jwt_secret" {
+  name = "${var.name_prefix}-${var.environment}-jwt-secret"
+  tags = local.common_tags
+}
+
+resource "aws_secretsmanager_secret_version" "jwt_secret" {
+  secret_id     = aws_secretsmanager_secret.jwt_secret.id
+  secret_string = var.jwt_secret
+}
+
 resource "aws_secretsmanager_secret" "openai_api_key" {
   name = "${var.name_prefix}-${var.environment}-openai-api-key"
   tags = local.common_tags
@@ -66,17 +71,7 @@ resource "aws_secretsmanager_secret_version" "openai_api_key" {
   secret_string = var.openai_api_key
 }
 
-resource "aws_secretsmanager_secret" "auth_token" {
-  count = var.auth_token != "" ? 1 : 0
-  name  = "${var.name_prefix}-${var.environment}-auth-token"
-  tags  = local.common_tags
-}
 
-resource "aws_secretsmanager_secret_version" "auth_token" {
-  count         = var.auth_token != "" ? 1 : 0
-  secret_id     = aws_secretsmanager_secret.auth_token[0].id
-  secret_string = var.auth_token
-}
 
 resource "aws_secretsmanager_secret" "db_password" {
   name = "${var.name_prefix}-${var.environment}-db-password"
@@ -141,7 +136,7 @@ resource "aws_ecs_task_definition" "server" {
         { containerPort = 8080, protocol = "tcp" },
       ]
 
-      environment = concat(local.common_env, local.auth_env)
+      environment = local.common_env
       secrets     = concat(local.common_secrets, local.auth_secrets)
 
       logConfiguration = {
@@ -187,57 +182,6 @@ resource "aws_ecs_service" "server" {
   depends_on = [aws_lb_target_group.server]
 }
 
-# ---------- Bridge Task Definition + Service ----------
-
-resource "aws_ecs_task_definition" "bridge" {
-  family                   = "${var.name_prefix}-bridge"
-  requires_compatibilities = ["FARGATE"]
-  network_mode             = "awsvpc"
-  cpu                      = var.bridge_cpu
-  memory                   = var.bridge_memory
-  execution_role_arn       = aws_iam_role.ecs_execution.arn
-  task_role_arn            = aws_iam_role.ecs_task.arn
-  tags                     = local.common_tags
-
-  container_definitions = jsonencode([
-    {
-      name      = "bridge"
-      image     = local.full_image
-      essential = true
-      command   = ["turnstone-bridge"]
-
-      environment = concat(local.common_env, local.auth_env)
-      secrets     = concat(local.common_secrets, local.auth_secrets)
-
-      logConfiguration = {
-        logDriver = "awslogs"
-        options = {
-          "awslogs-group"         = aws_cloudwatch_log_group.this.name
-          "awslogs-region"        = data.aws_region.current.name
-          "awslogs-stream-prefix" = "bridge"
-        }
-      }
-    },
-  ])
-}
-
-resource "aws_ecs_service" "bridge" {
-  name            = "${var.name_prefix}-bridge"
-  cluster         = aws_ecs_cluster.this.id
-  task_definition = aws_ecs_task_definition.bridge.arn
-  desired_count   = 1
-  launch_type     = "FARGATE"
-  tags            = local.common_tags
-
-  network_configuration {
-    subnets          = var.private_subnet_ids
-    security_groups  = [aws_security_group.ecs_tasks.id]
-    assign_public_ip = false
-  }
-
-  depends_on = [aws_ecs_service.server]
-}
-
 # ---------- Console Task Definition + Service ----------
 
 resource "aws_ecs_task_definition" "console" {
@@ -261,7 +205,7 @@ resource "aws_ecs_task_definition" "console" {
         { containerPort = 8090, protocol = "tcp" },
       ]
 
-      environment = concat(local.common_env, local.auth_env)
+      environment = local.common_env
       secrets     = concat(local.common_secrets, local.auth_secrets)
 
       logConfiguration = {

deploy/terraform/modules/aws-ecs/outputs.tf

@@ -22,8 +22,3 @@ output "rds_endpoint" {
   description = "Endpoint of the RDS PostgreSQL instance (host:port)."
   value       = aws_db_instance.this.endpoint
 }
-
-output "redis_endpoint" {
-  description = "Primary endpoint of the ElastiCache Redis replication group."
-  value       = aws_elasticache_replication_group.this.primary_endpoint_address
-}

deploy/terraform/modules/aws-ecs/security.tf

@@ -112,22 +112,3 @@ resource "aws_vpc_security_group_ingress_rule" "rds_from_ecs" {
   referenced_security_group_id = aws_security_group.ecs_tasks.id
   tags                         = local.common_tags
 }
-
-# ---------- Redis Security Group ----------
-
-resource "aws_security_group" "redis" {
-  name        = "${var.name_prefix}-redis-${var.environment}"
-  description = "Allow Redis access from ECS tasks"
-  vpc_id      = var.vpc_id
-  tags        = local.common_tags
-}
-
-resource "aws_vpc_security_group_ingress_rule" "redis_from_ecs" {
-  security_group_id            = aws_security_group.redis.id
-  description                  = "Redis from ECS tasks"
-  from_port                    = 6379
-  to_port                      = 6379
-  ip_protocol                  = "tcp"
-  referenced_security_group_id = aws_security_group.ecs_tasks.id
-  tags                         = local.common_tags
-}

deploy/terraform/modules/aws-ecs/variables.tf

@@ -6,7 +6,7 @@ variable "vpc_id" {
 }
 
 variable "private_subnet_ids" {
-  description = "List of private subnet IDs for ECS tasks, RDS, and ElastiCache."
+  description = "List of private subnet IDs for ECS tasks and RDS."
   type        = list(string)
 }
 
@@ -50,14 +50,6 @@ variable "db_instance_class" {
   default     = "db.t4g.micro"
 }
 
-# --- ElastiCache ---
-
-variable "redis_node_type" {
-  description = "ElastiCache node type for Redis."
-  type        = string
-  default     = "cache.t4g.micro"
-}
-
 # --- ECS Task Sizing ---
 
 variable "server_cpu" {
@@ -72,18 +64,6 @@ variable "server_memory" {
   default     = 1024
 }
 
-variable "bridge_cpu" {
-  description = "CPU units for the bridge task."
-  type        = number
-  default     = 256
-}
-
-variable "bridge_memory" {
-  description = "Memory (MiB) for the bridge task."
-  type        = number
-  default     = 512
-}
-
 variable "console_cpu" {
   description = "CPU units for the console task."
   type        = number
@@ -110,11 +90,10 @@ variable "name_prefix" {
   default     = "turnstone"
 }
 
-variable "auth_token" {
-  description = "Optional authentication token for the Turnstone API. Empty string disables auth."
+variable "jwt_secret" {
+  description = "JWT signing secret for Turnstone auth (required, min 32 characters)."
   type        = string
   sensitive   = true
-  default     = ""
 }
 
 variable "certificate_arn" {

docker/mcp-ddg.json

@@ -1,7 +0,0 @@
-{
-  "mcpServers": {
-    "ddg": {
-      "url": "http://ddg-search:3000/mcp"
-    }
-  }
-}

docs/api-reference.md

@@ -2,8 +2,6 @@
 
 ## Overview
 
-> See also: [MQ Protocol diagram](diagrams/png/06-mq-protocol.png) | [Message Routing diagram](diagrams/png/07-message-routing.png) | [Redis Key Schema diagram](diagrams/png/08-redis-key-schema.png)
-
 `turnstone-server` exposes a browser-based chat UI backed by a
 **Starlette** ASGI application served by **uvicorn**. The server uses
 **Server-Sent Events (SSE)** via `sse-starlette` for real-time streaming
@@ -58,7 +56,7 @@ console.log(result.content);
 
 ## Authentication
 
-When auth is enabled (`[auth].enabled = true` or `TURNSTONE_AUTH_ENABLED=1`), all API endpoints except public paths require a valid token.
+Auth is always enabled. All API endpoints except public paths require a valid token.
 
 ### Sending Credentials
 
@@ -67,15 +65,14 @@ Include a token in one of two ways:
 - **Bearer header**: `Authorization: Bearer <token>`
 - **Cookie**: `turnstone_auth=<token>` (set automatically by the login endpoint)
 
-The server accepts three token types:
+The server accepts two token types:
 
 | Type | Format | Example |
 |------|--------|---------|
 | JWT | Base64 segments separated by dots | `eyJhbG...` |
 | API token | `ts_` prefix + 64 hex chars | `ts_a1b2c3d4...` |
-| Config token | Arbitrary string from `config.toml` | `my-secret-token` |
 
-JWTs are the recommended credential for browser sessions. API tokens are suitable for programmatic access and CI/CD. Config tokens are a simple option for single-node deployments.
+JWTs are the recommended credential for browser sessions. API tokens are suitable for programmatic access and CI/CD.
 
 ### `POST /v1/api/auth/login`
 
@@ -523,7 +520,7 @@ inactivity.
 
 Each SSE connection to a workstream receives its own delivery queue.  Events
 produced by the worker thread are fanned out to all registered listener queues,
-so multiple consumers (browser, bridge, console proxy, SDK) can connect
+so multiple consumers (browser, console proxy, SDK) can connect
 simultaneously and each receives every event.  On reconnect the client receives
 a full history replay, so no catch-up mechanism is needed.
 
@@ -1859,3 +1856,54 @@ turnstone_tokens_total{type="completion"} 12150
 turnstone_tool_calls_total{tool="bash"} 7
 turnstone_tool_calls_total{tool="read_file"} 3
 ```
+
+---
+
+## Console Routing Proxy Endpoints
+
+These endpoints are served by the console (`turnstone-console`) and proxy
+requests to the correct server node via the hash ring bucket cache. In
+multi-node deployments, clients (SDK, channel gateway) talk to the console
+instead of individual server nodes.
+
+### `POST /v1/api/route/workstreams/new`
+
+Create a workstream via hash-ring routing. The console generates the `ws_id`,
+routes to the assigned node, and includes `node_url` in the response for
+direct SSE connections.
+
+### `POST /v1/api/route/send`
+
+Proxy a message to the workstream's assigned server node.
+
+### `POST /v1/api/route/approve`
+
+Proxy an approval response to the workstream's assigned server node.
+
+### `POST /v1/api/route/cancel`
+
+Cancel generation on a workstream.
+
+### `POST /v1/api/route/command`
+
+Send a slash command to a workstream.
+
+### `POST /v1/api/route/plan`
+
+Send plan review feedback to a workstream.
+
+### `POST /v1/api/route/workstreams/close`
+
+Close a workstream.
+
+### `GET /v1/api/route?ws_id=X`
+
+Look up which server node owns a workstream. Returns `{"node_url": "...", "node_id": "..."}`.
+Used by channel adapters to open direct SSE connections to the correct server node.
+
+### `GET /metrics` (Console)
+
+Prometheus metrics for the console routing layer. Includes:
+`turnstone_router_requests_total`, `turnstone_router_request_duration_seconds`,
+`turnstone_ring_membership_size`, `turnstone_ring_version`,
+`turnstone_ring_rebalance_total`, `turnstone_ring_migrations_total`.

docs/architecture.md

@@ -18,10 +18,9 @@ plugs in.
 |---------|--------|----------|---------|
 | `turnstone` | `turnstone.cli` | `TerminalUI` | Interactive terminal REPL |
 | `turnstone-server` | `turnstone.server` | `WebUI` | Browser-based chat (HTTP + SSE) |
-| `turnstone-bridge` | `turnstone.mq.bridge` | Bridge | Message queue ↔ HTTP API bridge |
 | `turnstone-console` | `turnstone.console.server` | ClusterCollector | Cluster dashboard (aggregates all nodes) |
 | `turnstone-eval` | `turnstone.eval` | `NullUI` | Headless evaluation and prompt optimization |
-| `turnstone-channel` | `turnstone.channels.cli` | ChannelAdapter | Channel gateway (Discord, Slack, etc.) via Redis MQ |
+| `turnstone-channel` | `turnstone.channels.cli` | ChannelAdapter | Channel gateway (Discord, Slack, etc.) |
 | `turnstone-admin` | `turnstone.core.admin_cli` | — | Offline user and API token management |
 
 ---
@@ -42,7 +41,7 @@ turnstone/
       __init__.py     create_provider() + create_client() factory functions
     workstream.py     Parallel workstream manager (WorkstreamState, Workstream, WorkstreamManager)
     tools.py          Tool schema loader (JSON -> OpenAI function-calling format)
-    mcp_client.py     MCPClientManager — MCP server connections, tool discovery, dynamic refresh, async-sync bridge
+    mcp_client.py     MCPClientManager — MCP server connections, tool discovery, dynamic refresh
     tool_search.py    Dynamic tool search — BM25 index, session-scoped tool visibility
     watch.py          WatchRunner daemon — periodic command polling, condition DSL, result dispatch
     judge.py          Intent validation — heuristic rules + LLM judge, advisory verdicts
@@ -74,20 +73,15 @@ turnstone/
     _base.py          Shared httpx async client, auth, error handling
     _sync.py          Background event loop for sync wrappers
     _types.py         TurnResult + TurnstoneAPIError
-  mq/
-    protocol.py       Inbound/outbound message dataclasses (JSON serialization)
-    broker.py         Abstract MessageBroker protocol + RedisBroker
-    bridge.py         Bridge service (queue ↔ turnstone-server HTTP API)
-    client.py         TurnstoneClient library + TurnResult for MQ-based access
   console/
-    collector.py      ClusterCollector — aggregates state from all nodes via Redis + HTTP
-    scheduler.py      TaskScheduler — background cron/at scheduler, dispatches via MQ
+    collector.py      ClusterCollector — aggregates state from all nodes via SSE
+    scheduler.py      TaskScheduler — background cron/at scheduler, dispatches via HTTP
     server.py         Cluster dashboard HTTP server + SSE + CLI entry point
     static/           Cluster dashboard web UI (page-specific HTML, CSS, JS)
   channels/
     cli.py            Unified channel gateway entry point (turnstone-channel)
     _protocol.py      ChannelAdapter protocol, ChannelEvent dataclass
-    _routing.py       ChannelRouter — channel/thread ↔ workstream mapping via MQ
+    _routing.py       ChannelRouter — channel/thread ↔ workstream mapping via HTTP
     _config.py        Base ChannelConfig dataclass
     discord/          Discord adapter (bot, cog, views, streaming, config)
   shared_static/      Shared design system (base.css, auth.js, theme.js, toast.js, utils.js, kb.js)
@@ -704,8 +698,7 @@ supports_vision = true
    sub-agents, allowing a cheaper model for autonomous loops
 
 **Per-workstream selection:** `POST /v1/api/workstreams/new` accepts an optional
-`"model"` field. The bridge `CreateWorkstreamMessage` carries the same field
-through the MQ protocol, along with `skill` (skill name)
+`"model"` field, along with `skill` (skill name)
 which can override the model before workstream creation.
 
 ### Tool Output Truncation
@@ -1023,13 +1016,10 @@ limits using a token-bucket algorithm. Each IP gets a `TokenBucket` with
 Turnstone supports three authentication mechanisms, unified behind an
 `AuthResult` dataclass that carries `user_id`, `scopes`, and `token_source`:
 
-1. **Config-file tokens** — static secrets in `config.toml` `[[auth.tokens]]`
-   or the `TURNSTONE_AUTH_TOKEN` env var. Validated in-memory via
-   `hmac.compare_digest`. Map to scopes through their role (`read` or `full`).
-2. **API tokens** — database-backed, prefixed `ts_`, stored as SHA-256 hashes
+1. **API tokens** — database-backed, prefixed `ts_`, stored as SHA-256 hashes
    in the `api_tokens` table. Can be exchanged for JWTs via
    `POST /v1/api/auth/login`.
-3. **JWTs** — short-lived HMAC-SHA256 session tokens (default 24h) issued after
+2. **JWTs** — short-lived HMAC-SHA256 session tokens (default 24h) issued after
    successful credential validation. Contain `sub` (user_id), `scopes`, and
    `src` (origin) in claims.
 
@@ -1053,9 +1043,8 @@ Three hierarchical scopes control endpoint access:
 2. **Token extraction** — `Authorization: Bearer <token>` header first, then
    `turnstone_auth` cookie as fallback.
 3. **Token type detection** — dots in the token indicate JWT; `ts_` prefix
-   indicates API token; otherwise config-file token.
-4. **Validation** — JWT signature check, API token hash lookup in storage, or
-   config-token hmac comparison.
+   indicates API token.
+4. **Validation** — JWT signature check or API token hash lookup in storage.
 5. **Scope check** — `required_scope(method, path)` determines the minimum
    scope; the request is rejected with 403 if the token lacks it.
 6. **Context propagation** — on success, `ctx_user_id` is set so structured
@@ -1205,95 +1194,39 @@ calls `_fg_event.wait()`, which blocks the worker thread until the user
 switches to that workstream. The `_bg_attention_notify` callback writes a
 bell + status line to stderr to alert the user.
 
-### Message Queue Bridge
-
-```
-Main thread              Global SSE thread         Per-WS SSE threads (×N)
-+------------------+     +------------------+      +-------------------+
-| Inbound loop     |     | GET /events/glob |      | GET /events?ws_id |
-| BLPOP on Redis   |     | Parse SSE via    |      | Parse SSE via     |
-|                  |     |   httpx-sse      |      |   httpx-sse       |
-| Dispatch to      |     | Forward state    |      | Forward content,  |
-|   handler        |     |   changes        |      |   tool results    |
-| POST to server   |     | Detect turn      |      | Handle approval   |
-| Publish ACK      |     |   completion     |      |   forwarding      |
-+------------------+     +------------------+      +-------------------+
-       |                         |                         |
-       +-- Redis inbound queue   +-- Redis pub/sub         +-- Redis pub/sub
-           (RPUSH/BLPOP)             (PUBLISH)                 (PUBLISH)
-                                                               + response queue
-                                                                 (BLPOP on
-                                                                  approval)
-```
-
-**Approval flow:** When a per-WS SSE thread receives an `approve_request`, it checks
-the workstream's `auto_approve_tools` set. If all requested tools are in the set, the
-bridge auto-approves via `POST /v1/api/approve`. Otherwise, it publishes an
-`ApprovalRequestEvent` to the outbound channel with a `request_id`, then blocks on
-`BLPOP` of a Redis response queue (`turnstone:resp:{request_id}`) until the client pushes
-a response or the approval timeout (default 3600s / 1 hour) expires.
-
-**Cancellation:** The `CancelMessage` (type `"cancel"`) is a routed inbound message.
-The bridge dispatches it to `POST /v1/api/cancel` on the server owning the workstream,
-which sets the cooperative cancel flag and unblocks any pending approval/plan waits.
-
-**Completion detection:** The bridge tracks which `correlation_id` maps to which
-`ws_id` for active sends. The server accumulates content tokens in the WebUI and
-piggybacks the full response text onto the `ws_state → idle` global SSE event.
-When the bridge receives this event, it emits a synthetic `TurnCompleteEvent`
-carrying the correlation ID and the server-provided `content`. This lets downstream
-consumers (e.g. the Discord bot) recover the full response when individual
-`ContentEvent`s were missed, and serves as the primary delivery path for
-bidirectional notification DM forwarding.
-
-**Multi-node routing:** Each bridge retrieves its `node_id` from the server's
-`/health` endpoint on startup (with exponential backoff retry). The server
-generates the `node_id` (`{hostname}_{4hex}`) and is the sole authority for
-node identity. The bridge BLPOPs
-from both `turnstone:inbound:{node_id}` (directed, priority) and `turnstone:inbound` (shared).
-Messages with `target_node` set are pushed to the target's per-node queue. Messages
-for existing workstreams are auto-routed via `turnstone:ws:{ws_id}` ownership keys in Redis.
-If a bridge picks up a shared-queue message for a workstream owned by another node, it
-re-routes to that node's queue (1 extra hop). Bridges publish heartbeats to
-`turnstone:node:{node_id}` with configurable TTL for node discovery.
-On startup, `_recover_workstreams` re-registers ownership of existing
-workstreams and publishes `WorkstreamCreatedEvent` to the cluster channel
-so the console collector picks them up immediately.
-
 ### Cluster Console
 
 ```
-Monitoring (3 daemon threads)        Control + Proxy (async Starlette)
+Monitoring (2 daemon threads)        Control + Proxy (async Starlette)
 +------------------+                 +----------------------------+
-| Event subscriber |                 | POST /v1/api/cluster/      |
-| SUBSCRIBE on     |                 |   workstreams/new          |
-| events:cluster   |                 |   → LPUSH to Redis         |
-+------------------+                 |     inbound:{node_id}      |
-| Node discovery   |                 +----------------------------+
-| SCAN node:* keys |                 | GET /node/{node_id}/       |
-| every 15 seconds |                 |   → httpx.AsyncClient      |
-+------------------+                 |     proxy to server_url    |
-| Poll loop        |                 | GET /node/{id}/v1/api/events |
-| GET /v1/api/dash |                 |   → SSE stream proxy       |
-| GET /health      |                 | POST /node/{id}/v1/api/send  |
-| ThreadPoolExec   |                 |   → forwarded to server    |
+| Node discovery   |                 | POST /v1/api/cluster/      |
+| Service registry |                 |   workstreams/new          |
+| every 60 seconds |                 |   → POST to target server  |
 +------------------+                 +----------------------------+
+| SSE manager      |                 | GET /node/{node_id}/       |
+| asyncio loop     |                 |   → httpx.AsyncClient      |
+| 1 task per node  |                 |     proxy to server_url    |
+| /events/global   |                 | GET /node/{id}/v1/api/events |
+| snapshot+deltas  |                 |   → SSE stream proxy       |
++------------------+                 | POST /node/{id}/v1/api/send  |
+                                     |   → forwarded to server    |
+                                     +----------------------------+
 ```
 
 The console HTTP layer is a Starlette/ASGI app served by uvicorn. The SSE
 endpoint uses `EventSourceResponse` with the same listener queue pattern as
-the main server. `ClusterCollector`'s background threads (event subscriber,
-node discovery, poll loop) use sync Redis clients and `ThreadPoolExecutor`
-for parallel HTTP polling. The poll loop diffs workstream IDs between poll
-cycles and fans out synthetic `ws_created`/`ws_closed` SSE events for any
-changes, ensuring browser clients stay in sync even when real-time cluster
-events are missed (e.g. bridge startup recovery).
+the main server. `ClusterCollector` runs two daemon threads: a discovery loop
+that queries the service registry every 60 seconds, and an SSE manager that
+runs a single asyncio event loop multiplexing persistent SSE connections to
+all nodes via `GET /v1/api/events/global`. Each node delivers a full snapshot
+on connect followed by real-time delta events — state changes, health
+transitions, and aggregate metrics arrive sub-second instead of on a 15-second
+poll cycle.
 
 The console has two write-path capabilities:
 
-1. **Workstream creation** — pushes `CreateWorkstreamMessage` to Redis inbound
-   queues targeting specific nodes. The bridge on each node picks up the message
-   and creates the workstream on the local server. Auto-selects the node with
+1. **Workstream creation** — sends HTTP requests to target server nodes
+   to create workstreams. Auto-selects the node with
    the most available capacity if no target is specified. When a `skill`
    field is present, the server resolves the skill BEFORE `mgr.create()`
    (applying the model override to the creation request) and snapshot-applies
@@ -1360,7 +1293,7 @@ event loop on a daemon thread.
 
 **Event types**: 27 standalone dataclasses in `events.py` with a type-registry
 pattern matching `OutboundEvent.from_json()` from `mq/protocol.py`. Events are
-decoupled from the MQ package so SDK consumers don't need the `redis` dependency.
+decoupled from server internals.
 
 **TypeScript SDK**: `sdk/typescript/` — separate npm package with the same API
 surface. Zero browser dependencies, SSE via `fetch` + `ReadableStream` parsing.
@@ -1381,20 +1314,19 @@ with TurnstoneServer("http://localhost:8080", token="tok_xxx") as client:
 
 > See also: [Channel Integrations guide](channels.md)
 
-The `turnstone-channel` gateway bridges external messaging platforms
-(Discord, Slack, Teams) to the turnstone cluster via Redis MQ. Each
+The `turnstone-channel` gateway connects external messaging platforms
+(Discord, Slack, Teams) to the turnstone cluster via HTTP. Each
 platform adapter implements the `ChannelAdapter` protocol and translates
-between platform-native events and turnstone MQ messages.
+between platform-native events and turnstone server API calls.
 
 The `ChannelRouter` manages bidirectional routing: it maps platform
 channel/thread IDs to turnstone workstream IDs, handles workstream
 creation and stale-route recovery, and resolves platform users to
 turnstone identities via the `channel_users` table. When an evicted
 workstream is reactivated, the router uses atomic resume via the
-`resume_ws` field on `CreateWorkstreamMessage` — the server resumes
+`resume_ws` field on the workstream creation request — the server resumes
 the old workstream's conversation during creation in a single HTTP
-request, eliminating ordering fragility. The bridge emits a
-`WorkstreamResumedEvent` to confirm success.
+request, eliminating ordering fragility.
 
 Discord ships as the first adapter. See [channels.md](channels.md) for
 setup instructions, configuration reference, and the adapter development
@@ -1403,7 +1335,7 @@ guide.
 ### Notification Subsystem
 
 The `notify` tool enables the LLM to send notifications to users or
-channels without going through MQ. The server calls the channel gateway
+channels directly. The server calls the channel gateway
 directly over HTTP for lower latency: `_exec_notify()` queries the
 `services` database table for healthy channel gateways (heartbeat within
 120 seconds), authenticates with a service JWT (`aud: turnstone-channel`),

docs/assets/hero.png

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75c1832b6079e8628f4bbf4ce98d37880c4de133636b7555e3869990b046ddc6
+size 567704

docs/channels.md

@@ -1,9 +1,10 @@
 # Channel Integrations
 
 The `turnstone-channel` gateway connects external messaging platforms to
-turnstone workstreams via Redis MQ. Each platform adapter translates
+turnstone workstreams via direct HTTP to the server (single-node) or the
+console routing proxy (multi-node). Each platform adapter translates
 platform-native events (messages, button clicks, slash commands) into
-turnstone MQ messages, and renders workstream output back into the
+turnstone API calls, and renders workstream output back into the
 platform's UI.
 
 Discord ships as the first adapter. The adapter protocol is designed for
@@ -20,10 +21,9 @@ Discord Gateway
 turnstone-channel  (Discord adapter)
       |
       v
-  Redis MQ
-      |
-      v
-turnstone-bridge  ──>  turnstone-server
+turnstone-server   (direct HTTP)
+      or
+turnstone-console  (routing proxy, multi-node)
 ```
 
 Key components:
@@ -34,10 +34,7 @@ Key components:
   `send_approval_request()`, `send_plan_review()`, and `create_thread()`.
 - **ChannelRouter** (`turnstone/channels/_routing.py`) — maps
   channel/thread IDs to turnstone workstream IDs. Handles workstream
-  creation via MQ, stale route detection, and user identity resolution.
-- **AsyncRedisBroker** (`turnstone/mq/async_broker.py`) — async Redis
-  client compatible with discord.py's event loop. Used by the router for
-  pub/sub and queue operations.
+  creation via HTTP, stale route detection, and user identity resolution.
 - **channel_users table** — maps `(channel_type, channel_user_id)` to a
   turnstone `user_id`. Messages from unlinked users are silently dropped.
 - **channel_routes table** — persistent channel-to-workstream mappings.
@@ -84,8 +81,7 @@ TURNSTONE_DISCORD_GUILD=123456789  # optional, restrict to one guild
 turnstone-channel \
   --discord-token "your-bot-token" \
   --discord-guild 123456789 \
-  --redis-host localhost \
-  --redis-port 6379
+  --server-url http://localhost:8080
 ```
 
 **Docker Compose** (production profile):
@@ -138,7 +134,7 @@ An admin can also force-link or unlink users via the console admin panel
   thread auto-creates a new workstream and atomically resumes the
   previous workstream via the `resume_ws` field on
   `CreateWorkstreamMessage`. The server resumes the workstream during
-  creation (same HTTP request), and the bridge emits a
+  creation (same HTTP request), and the server emits a
   `WorkstreamResumedEvent` back to the channel. The thread receives a
   *"Resumed: {name} ({count} messages restored)"* confirmation.
 
@@ -160,8 +156,7 @@ an orange embed with:
 - Tool name and argument preview
 - **Approve** (green), **Reject** (red), **Always Approve** (gray) buttons
 - Only linked users can interact with approval buttons
-- The approval decision is forwarded through MQ to the bridge, which
-  relays it to the server
+- The approval decision is forwarded to the server via HTTP
 
 Buttons use static `custom_id` values so they survive bot restarts.
 Correlation data (`ws_id`, `correlation_id`) is stored in the embed footer.
@@ -181,7 +176,7 @@ Plan review requests are displayed as a blue embed with:
 - **Approve Plan** (green) button — approves the plan with empty feedback
 - **Request Changes** (gray) button — opens a modal for feedback text
   (up to 2000 characters)
-- Feedback is forwarded through MQ as a `PlanFeedbackMessage`
+- Feedback is forwarded to the server via HTTP
 
 ---
 
@@ -192,15 +187,12 @@ Plan review requests are displayed as a blue embed with:
 | `--discord-token` | `TURNSTONE_DISCORD_TOKEN` | — | Bot token (required to enable Discord) |
 | `--discord-guild` | — | `0` (all guilds) | Restrict to a single Discord guild |
 | `--discord-channels` | — | empty (all) | Comma-separated channel IDs to allow |
-| `--redis-host` | `REDIS_HOST` | `localhost` | Redis host |
-| `--redis-port` | — | `6379` | Redis port |
-| `--redis-password` | `REDIS_PASSWORD` | — | Redis password |
-| `--redis-db` | — | `0` | Redis DB number |
+| `--server-url` | `TURNSTONE_SERVER_URL` | `http://localhost:8080` | Server URL (single-node) |
+| `--console-url` | `TURNSTONE_CONSOLE_URL` | — | Console URL (multi-node routing proxy) |
 | `--model` | — | server default | Default model for new workstreams |
 | `--auto-approve` | — | `false` | Auto-approve ALL tool calls (skips approval buttons entirely) |
 | `--http-host` | — | `127.0.0.1` | HTTP server bind address for notify endpoint |
 | `--http-port` | `TURNSTONE_CHANNEL_PORT` | `8091` | HTTP server port |
-| `--auth-token` | `TURNSTONE_CHANNEL_AUTH_TOKEN` | — | Static auth token for `/v1/api/notify` (alternative to JWT) |
 | `--log-level` | `TURNSTONE_LOG_LEVEL` | `INFO` | Log level |
 | `--log-format` | `TURNSTONE_LOG_FORMAT` | `auto` | Log format (`auto`/`json`/`text`) |
 
@@ -232,13 +224,13 @@ See [Security: Database Schema](security.md#database-schema) for the
 3. **Eviction** — the server evicts an idle workstream for capacity. The
    route is preserved and the thread stays open.
 4. **Reactivation** — the next message in the thread detects the stale
-   route (no MQ owner) and creates a new workstream with the old `ws_id`
-   as `resume_ws` on the `CreateWorkstreamMessage`. The server resumes
+   route and creates a new workstream with the old `ws_id`
+   as `resume_ws` on the creation request. The server resumes
    the workstream during creation (no separate command or reverse lookup
-   needed). The bridge emits a `WorkstreamResumedEvent` to the channel, and
+   needed). The channel receives a `WorkstreamResumedEvent`, and
    the thread displays *"Resumed: {name} ({count} messages restored)"*.
    If the old workstream was pruned, a fresh one starts with no error.
-5. **Close** — `/close` command closes the workstream via MQ, deletes the
+5. **Close** — `/close` command closes the workstream via HTTP, deletes the
    route, unsubscribes from events, and archives the Discord thread.
 
 ---
@@ -264,7 +256,7 @@ Two modes:
 
 ### Delivery Flow
 
-Notifications bypass MQ for lower latency. The server calls the channel
+Notifications use direct HTTP for low latency. The server calls the channel
 gateway directly over HTTP:
 
 1. The LLM calls the `notify` tool with a message and target
@@ -328,11 +320,11 @@ The `services` table schema:
 ### Security
 
 - **Authentication** — the gateway's `POST /v1/api/notify` endpoint
-  requires authentication. Configure either `TURNSTONE_JWT_SECRET`
-  (the server mints JWTs with `aud: turnstone-channel` automatically)
-  or a static token via `--auth-token`. If neither is set, the
-  gateway fails closed and rejects all requests with 401. Server JWTs
-  (`aud: turnstone-server`) are rejected.
+  requires authentication. Configure `TURNSTONE_JWT_SECRET` so the
+  server can mint JWTs with `aud: turnstone-channel` automatically.
+  If the secret is not set, the gateway fails closed and rejects all
+  requests with 401. Server JWTs (`aud: turnstone-server`) are
+  rejected.
 - **Rate limit** — maximum 5 notifications per turn. The counter only
   increments on successful delivery, so failures don't consume the
   budget.

docs/console.md

@@ -1,16 +1,16 @@
 # Cluster Dashboard (turnstone-console)
 
-`turnstone-console` is a cluster management service that provides cluster-wide visibility and control across all turnstone nodes. It connects to the shared Redis broker, discovers nodes via heartbeat keys, polls each node's HTTP API for workstream data, and subscribes to a cluster event channel for real-time state changes.
+`turnstone-console` is a cluster management service that provides cluster-wide visibility and control across all turnstone nodes. It discovers nodes via the `services` database table and subscribes to each node's SSE event stream for real-time workstream, health, and metric updates.
 
-The console also supports **workstream creation** (dispatched via MQ to target nodes) and a **reverse proxy** that serves each node's server UI through the console port — so users only need network access to the console, not to individual server nodes.
+The console also supports **workstream creation** (dispatched via HTTP proxy to target nodes) and a **reverse proxy** that serves each node's server UI through the console port — so users only need network access to the console, not to individual server nodes.
 
 ## Architecture
 
 > See also: [Console Data Flow diagram](diagrams/png/11-console-data-flow.png)
 
 ```
-                        ┌── Redis ←── turnstone-bridge ←── turnstone-server
-                        │    (MQ)        (per node)           (per node)
+                        ┌── services table ──  turnstone-server
+                        │   (node registry)      (per node)
 turnstone-console ──────┤
    (one instance)       │
                         └── turnstone-server (direct HTTP proxy)
@@ -21,45 +21,28 @@ turnstone-console ──────┤
 
 Data flows in two directions:
 
-- **Inbound (monitoring):** Bridges publish state changes to `{prefix}:events:cluster` on Redis pub/sub. The console subscribes for real-time updates and periodically polls each node's `GET /v1/api/dashboard` for full workstream snapshots.
-- **Outbound (control):** The console pushes `CreateWorkstreamMessage` to Redis inbound queues targeting specific nodes. Bridges pick up these messages and create workstreams on their local servers.
+- **Inbound (monitoring):** The console discovers nodes via the `services` database table (nodes register on startup and send periodic heartbeats). It opens a persistent SSE connection to each node's `GET /v1/api/events/global` endpoint, receiving a full snapshot on connect followed by real-time delta events (state changes, health transitions, aggregate metrics).
+- **Outbound (control):** The console proxies workstream creation requests to target nodes via HTTP.
 - **Proxy (pass-through):** The console reverse-proxies each node's server UI at `/node/{node_id}/`, forwarding HTTP and SSE traffic so the browser never contacts server nodes directly.
 
 ### Data Sources
 
 | Source | Method | Direction | Data |
 |--------|--------|-----------|------|
-| Redis heartbeats | `SCAN turnstone:node:*` | Read | Node discovery (node_id, server_url, started) |
-| Redis pub/sub | `SUBSCRIBE turnstone:events:cluster` | Read | State changes, creates, closes, renames |
-| Node HTTP API | `GET {server_url}/v1/api/dashboard` | Read | Full workstream list with tokens, context, activity |
-| Node HTTP API | `GET {server_url}/health` | Read | Node health status |
-| Redis inbound queue | `RPUSH turnstone:inbound:{node_id}` | Write | Workstream creation commands |
+| `services` table | Database query | Read | Node discovery (node_id, server_url, started) |
+| Node SSE | `GET {server_url}/v1/api/events/global` | Stream | Snapshot on connect, then real-time delta events (state, health, aggregate) |
+| Node HTTP API | `POST {server_url}/v1/api/workstreams/new` | Write | Workstream creation |
 | Node HTTP API | `GET/POST {server_url}/*` | Proxy | Server UI, API requests, SSE streams |
 
-### Redis Key: Cluster Event Channel
-
-Bridges publish to `{prefix}:events:cluster` whenever a workstream state change, creation, closure, or rename occurs. Events include `node_id` so the console can attribute them to the correct node.
-
-Event types on the cluster channel:
-
-| Event | Fields | Trigger |
-|-------|--------|---------|
-| `cluster_state` | ws_id, state, node_id, tokens, context_ratio, activity | Workstream state transition |
-| `ws_created` | ws_id, name, node_id | New workstream created |
-| `ws_closed` | ws_id | Workstream closed |
-| `ws_rename` | ws_id, name | Workstream renamed |
-
 ---
 
 ## ClusterCollector
 
-The collector (`turnstone/console/collector.py`) maintains an in-memory snapshot of all nodes and workstreams. Three daemon threads handle data acquisition:
+The collector (`turnstone/console/collector.py`) maintains an in-memory snapshot of all nodes and workstreams. Two daemon threads handle data acquisition:
 
-1. **Event subscriber** — subscribes to `{prefix}:events:cluster` via `RedisBroker.subscribe_cluster()`. Applies state changes, creates, closes, and renames to the in-memory model immediately.
+1. **Node discovery** — queries the `services` database table every 60 seconds. Adds newly discovered nodes, removes expired ones (stale heartbeats), emits `node_joined` / `node_lost` events to SSE listeners, and spawns/cancels SSE tasks for new/lost nodes.
 
-2. **Node discovery** — scans heartbeat keys every 15 seconds via `broker.list_nodes()`. Adds newly discovered nodes, removes expired ones, emits `node_joined` / `node_lost` events to SSE listeners.
-
-3. **Poll loop** — fetches `GET /v1/api/dashboard` and `GET /health` from each known node every 10 seconds. Uses `ThreadPoolExecutor(max_workers=50)` for parallelism. Each poll replaces the node's workstream list with the authoritative server data.
+2. **SSE manager** — a single asyncio event loop on one thread multiplexes persistent SSE connections to all discovered nodes via `GET /v1/api/events/global`. Each connection receives a `node_snapshot` on connect (workstreams, health, aggregate) followed by real-time delta events (`ws_state`, `ws_created`, `ws_closed`, `ws_rename`, `health_changed`, `aggregate`). On disconnect, the node is marked unreachable and the connection is retried with exponential backoff (1s–30s). An `?expected_node_id=` query parameter provides identity verification against IP reuse (server returns 409 on mismatch).
 
 A `get_snapshot()` method builds the full cluster state under a single lock acquisition — overview aggregates and per-node workstream lists in one atomic read. This is served both as a REST endpoint and as the initial SSE event on client connect.
 
@@ -70,7 +53,7 @@ All reads and writes to the node/workstream map are protected by a single `threa
 ### Scale Considerations
 
 - **50,000 workstreams** (1,000 nodes × 50 per node) at ~500 bytes each = ~25 MB in memory
-- **1,000 nodes** polled in parallel — fan-out concurrency is configurable via `cluster.node_fan_out_limit` (default 200), yielding 5 batches at ~100ms each = ~0.5 second poll cycle
+- **1,000 nodes** connected via persistent SSE — a single asyncio event loop multiplexes all connections with negligible overhead. Ensure `ulimit -n` >= 4096 for fd headroom
 - **Filtering and pagination** run in-memory on the full workstream list — sub-millisecond at this scale
 - **SSE fan-out** uses per-client queues (2,000 events) — backed-up clients get events dropped, not blocking
 - **Database** — for clusters sharing PostgreSQL, use [PgBouncer](pgbouncer.md) in transaction pooling mode
@@ -183,7 +166,7 @@ Full cluster state in a single response — all nodes with their workstreams plu
 
 ### `POST /v1/api/cluster/workstreams/new`
 
-Create a new workstream on a target node. Dispatches a `CreateWorkstreamMessage` through the Redis MQ pipeline — the bridge on the target node picks it up and creates the workstream on the server. Requires `write` scope.
+Create a new workstream on a target node. The console proxies the creation request to the target node's HTTP API. Requires `write` scope.
 
 Request:
 
@@ -197,9 +180,9 @@ Request:
 
 All fields are optional:
 - `node_id` — targeting mode:
-  - **omitted or `"auto"`** — console picks the reachable node with the most available capacity (max_ws - ws_total) and pushes to its directed queue.
-  - **`"pool"`** — pushes to the shared inbound queue; the next available bridge picks it up (true general-pool dispatch).
-  - **specific node ID** — pushes to that node's directed queue.
+  - **omitted or `"auto"`** — console picks the reachable node with the most available capacity (max_ws - ws_total) and proxies the request to it.
+  - **`"pool"`** — console picks a reachable node with available capacity using round-robin selection.
+  - **specific node ID** — proxies the request to that node directly.
 - `name` — workstream display name. Auto-generated if omitted.
 - `model` — model alias from the target node's registry. Uses the node's default model if omitted.
 
@@ -213,7 +196,7 @@ Response:
 }
 ```
 
-Creation is asynchronous — the response confirms the MQ message was dispatched. A `ws_created` event on the cluster SSE stream confirms the workstream was actually created.
+The response confirms the workstream creation request was proxied to the target node. A `ws_created` event on the cluster SSE stream confirms the workstream was actually created.
 
 ### `GET /v1/api/cluster/events`
 
@@ -395,7 +378,7 @@ Breadcrumb: `Cluster > Running` or `Cluster > db-west-04`. Server-side paginated
 
 Triggered by the "+ new" header button. A modal dialog with:
 
-- **Node selector** — dropdown with three targeting modes: "Auto (best available)" picks the node with the most headroom, "General pool (any node)" pushes to the shared queue for any bridge to pick up, or a specific node from the list (showing capacity).
+- **Node selector** — dropdown with three targeting modes: "Auto (best available)" picks the node with the most headroom, "General pool (any node)" picks a node with available capacity using round-robin, or a specific node from the list (showing capacity).
 - **Profile** — optional dropdown listing enabled skills. Applies the skill's model, auto-approve policy, token budget, and other behavioral settings at creation time.
 - **Name** — optional text input. Auto-generated if left empty.
 - **Model** — optional text input for a model alias from the target node's registry.
@@ -482,17 +465,17 @@ to create the initial admin user and receive a JWT in one step. See
 
 ## Scheduled Tasks
 
-The console includes a background **TaskScheduler** daemon that creates workstreams on a timed basis via the MQ broker. It supports cron-based recurring schedules and one-shot `at` schedules.
+The console includes a background **TaskScheduler** daemon that creates workstreams on a timed basis via HTTP proxy to target nodes. It supports cron-based recurring schedules and one-shot `at` schedules.
 
 ### Architecture
 
 The scheduler runs as a daemon thread inside the console process. Every `check_interval` seconds (default 15) it:
 
-1. Acquires a distributed lock via Redis `SET NX EX` (prevents duplicate dispatch in multi-console deployments)
+1. Acquires a distributed lock via the `system_settings` table (prevents duplicate dispatch in multi-console deployments)
 2. Queries the storage backend for tasks whose `next_run <= now` and `enabled = true`
-3. Dispatches each due task as one or more `CreateWorkstreamMessage` via MQ
+3. Dispatches each due task as one or more workstream creation requests via HTTP proxy
 4. Updates `last_run` and computes the next `next_run` (or disables one-shot `at` tasks)
-5. Releases the lock via Lua script (safe conditional delete)
+5. Releases the lock
 
 Run history is automatically pruned (runs older than 90 days) approximately once per hour.
 
@@ -508,7 +491,7 @@ Run history is automatically pruned (runs older than 90 days) approximately once
 | Mode | Behavior |
 |------|----------|
 | `auto` | Picks the reachable node with the most available capacity |
-| `pool` | Pushes to the shared inbound queue (any bridge picks it up) |
+| `pool` | Picks a reachable node with available capacity using round-robin |
 | `all` | Fan-out to all reachable nodes (capped at `max_fan_out`, default 20) |
 | `<node_id>` | Targets a specific node by ID |
 
@@ -645,12 +628,6 @@ CLI flags for `turnstone-console`:
 |------|---------|-------------|
 | `--host` | `0.0.0.0` | Bind host |
 | `--port` | `8090` | HTTP port |
-| `--redis-host` | `localhost` | Redis host |
-| `--redis-port` | `6379` | Redis port |
-| `--redis-password` | `$REDIS_PASSWORD` | Redis password |
-| `--redis-db` | `0` | Redis DB |
-| `--poll-interval` | `10` | Node polling interval (seconds) |
-| `--auth-token` | `$TURNSTONE_AUTH_TOKEN` | Bearer token for server node communication and proxy |
 | `--log-level` | `INFO` | Log level |
 
 Config file (`~/.config/turnstone/config.toml`):
@@ -660,12 +637,6 @@ Config file (`~/.config/turnstone/config.toml`):
 host = "0.0.0.0"
 port = 8090
 url = "http://localhost:8090"   # used by CLI /cluster commands
-poll_interval = 10
-
-[redis]
-host = "localhost"
-port = 6379
-password = "my-redis-password"
 ```
 
 ---
@@ -673,17 +644,11 @@ password = "my-redis-password"
 ## Deployment
 
 ```bash
-# Start Redis
-redis-server
-
 # Start turnstone servers (one per node)
 turnstone-server --port 8080
 
-# Start bridges (one per server)
-turnstone-bridge --server-url http://localhost:8080 --node-id node-a
-
 # Start cluster console (one instance)
-turnstone-console --redis-host localhost --port 8090 --auth-token "$TURNSTONE_AUTH_TOKEN"
+turnstone-console --port 8090
 ```
 
 Open `http://localhost:8090` for the cluster dashboard. Create workstreams via the "+ new" button. Click any workstream to open the proxied server UI — no direct access to server ports required.

docs/design/consistent-hash-ring.md

@@ -0,0 +1,168 @@
+# Consistent Hash Ring — Reference Design
+
+**Status**: Reference (not currently in the hot path)
+**Date**: 2026-03-30
+
+## Overview
+
+This document describes a consistent hash ring algorithm evaluated during
+the design of the direct HTTP transport routing system. The current
+implementation uses weight-proportional bucket assignment with a
+donor/recipient rebalancing algorithm (see `direct-http-transport.md`).
+The consistent hash ring is documented here as a reference for future
+scalability work — if the cluster grows beyond the point where the
+weight-proportional approach is sufficient, the ring provides a
+proven alternative with stronger stability guarantees.
+
+## When to consider the ring approach
+
+The current weight-proportional seeding + donor/recipient rebalancer works
+well when:
+- Cluster size is moderate (< 50 nodes)
+- Nodes join/leave infrequently
+- The rebalancer runs centrally (in the console)
+
+The consistent hash ring becomes advantageous when:
+- Cluster size grows large (50+ nodes) and frequent membership changes
+  cause the donor/recipient algorithm to churn
+- Decentralized routing is needed (each node computes the ring locally,
+  no central console required)
+- Cross-language determinism is important (multiple implementations must
+  agree on the same assignment without sharing state)
+
+## Algorithm
+
+### Hash function: FNV-1a (32-bit)
+
+```python
+def fnv1a_32(data: bytes) -> int:
+    """FNV-1a 32-bit hash.
+
+    Basis: 0x811C9DC5, Prime: 0x01000193.
+    XOR each byte, then multiply by prime (masked to 32 bits).
+    """
+    h = 0x811C9DC5
+    for b in data:
+        h ^= b
+        h = (h * 0x01000193) & 0xFFFFFFFF
+    return h
+```
+
+Known test vectors:
+- `fnv1a_32(b"")` = `0x811C9DC5` (basis value)
+- `fnv1a_32(b"foobar")` = `0xBF9CF968`
+
+Cross-language implementations:
+- **Python**: loop above (no dependencies)
+- **Go**: same algorithm with `uint32` arithmetic
+- **TypeScript**: same algorithm with `>>> 0` for unsigned 32-bit
+
+### Virtual nodes
+
+Each physical node with weight `w` gets `w * 150` virtual positions on a
+16-bit ring (65536 positions). Virtual node `i` of physical node `N` is
+placed at:
+
+```
+position = fnv1a_32(f"{N.node_id}:{i}".encode()) % 65536
+```
+
+With 150 vnodes per unit weight:
+- 2 equal-weight nodes: ~50/50 split (measured: 38-62% range due to
+  hash variance, stddev ~3% with large vnode counts)
+- 3 nodes at weights 2:1:1: ~50/25/25 (within 10% tolerance)
+
+### Lookup
+
+```python
+def owner(bucket: int) -> str:
+    """O(log n) bisect-right walk to find the next virtual node clockwise."""
+    idx = bisect_right(positions, bucket)
+    if idx >= len(positions):
+        idx = 0  # wrap around
+    return vnode_map[positions[idx]]
+```
+
+### Stability properties
+
+The consistent hash ring guarantees:
+- **Node addition**: adding a node moves at most `1/N` of buckets (where N
+  is the new node count). Other nodes' buckets are unaffected.
+- **Node removal**: only the removed node's buckets are reassigned. Buckets
+  owned by surviving nodes don't move.
+- **Determinism**: same membership list always produces the same ring.
+  No coordination needed between processes.
+
+### Full assignment precomputation
+
+```python
+def assignments() -> list[tuple[int, str]]:
+    """Compute all 65536 bucket-to-node mappings."""
+    return [(b, owner(b)) for b in range(65536)]
+```
+
+This produces a complete assignment table that can be loaded into a flat
+array for O(1) request-time lookup. The ring itself is never consulted
+on the hot path.
+
+## Data structures
+
+```python
+@dataclass(frozen=True, slots=True)
+class RingNode:
+    node_id: str
+    url: str
+    weight: int = 1
+
+class HashRing:
+    """Immutable consistent hash ring. Thread-safe (no mutable state)."""
+
+    def __init__(self, nodes: Sequence[RingNode], vnodes_per_unit: int = 150):
+        # Validate no duplicate node_ids
+        # Build sorted array of (position, node_id) tuples
+        # positions[i] = fnv1a_32(f"{node_id}:{i}".encode()) % RING_SIZE
+
+    def owner(self, bucket: int) -> RingNode | None:
+        # bisect_right + wrap
+
+    @property
+    def version(self) -> int:
+        # Deterministic hash of membership: fnv1a_32 of sorted node_id:weight pairs
+
+    def assignments(self) -> list[tuple[int, str]]:
+        # Precompute all 65536 bucket assignments
+```
+
+## Comparison with current approach
+
+| Aspect | Weight-proportional (current) | Consistent hash ring |
+|--------|------------------------------|---------------------|
+| Seeding | Exact weight split, deterministic | Hash-based, ~3% variance |
+| Node addition | Donor/recipient moves only excess | Ring moves ~1/N buckets |
+| Node removal | Dead buckets → most underloaded | Ring redistributes to clockwise neighbors |
+| Cross-node churn | Zero (only donor→recipient) | Zero (ring stability guarantee) |
+| Decentralized | No (needs central rebalancer) | Yes (each node computes locally) |
+| Complexity | Simple weight arithmetic | Virtual node construction + bisect |
+
+## Test vectors
+
+For cross-language implementation validation:
+
+```json
+{
+  "fnv1a_32": [
+    {"input": "", "output": 2166136261},
+    {"input": "foobar", "output": 3215766888}
+  ],
+  "bucket_of": [
+    {"ws_id": "a3f100000000000000000000000000000", "bucket": 41969},
+    {"ws_id": "00000000000000000000000000000000", "bucket": 0},
+    {"ws_id": "ffff0000000000000000000000000000", "bucket": 65535}
+  ],
+  "ring_single_node": {
+    "nodes": [{"node_id": "n1", "weight": 1}],
+    "vnodes_per_unit": 150,
+    "expected_n1_buckets": 65536
+  }
+}
+```

docs/diagrams/01-system-context.puml

@@ -13,24 +13,22 @@ cloud "LLM Providers" as llm {
     component [OpenAI-compatible API\n(OpenAI, vLLM, llama.cpp)] as llm_openai
     component [Anthropic Messages API] as llm_anthropic
 }
-database "Redis" as redis
 database "SQLite\n(.turnstone.db)" as sqlite
 
 ' Turnstone System Boundary
 package "Turnstone Platform" {
     component [turnstone\n(CLI)] as cli <<entry point>>
     component [turnstone-server\n(HTTP + SSE)] as server <<entry point>>
-    component [turnstone-bridge\n(Queue ↔ HTTP)] as bridge <<service>>
-    component [turnstone-console\n(Dashboard)] as console <<service>>
+    component [turnstone-console\n(Dashboard + Router)] as console <<service>>
     component [turnstone-eval\n(Headless)] as eval <<entry point>>
-    component [turnstone-sim\n(Simulator)] as sim <<service>>
+    component [turnstone-channel\n(Channel Gateway)] as channel <<service>>
 }
 
 ' User connections
 cli_user --> cli : stdin / stdout
 browser_user --> server : HTTP + SSE\n(port 8080)
 browser_user --> console : HTTP + SSE\n(port 8090)
-ext_client --> redis : Redis LIST\n(push commands)
+ext_client --> server : HTTP + SSE\n(SDK / API)
 eval_user --> eval : Python API
 
 ' Internal connections
@@ -43,26 +41,16 @@ server --> sqlite : SQLite
 eval --> llm : LLM Provider API\n(non-streaming)
 eval --> sqlite : SQLite
 
-bridge --> server : HTTP REST\n(POST /v1/api/send, etc.)
-bridge <-- server : SSE\n(GET /v1/api/events)
-bridge --> redis : Redis LIST + PUBSUB\n+ STRING (routing, heartbeats)
+console --> server : HTTP proxy\n(hash-ring bucket lookup,\nproxy /node/{id}/* traffic)
 
-console --> redis : Redis PUBSUB + STRING + LIST\n(cluster events, heartbeats,\nworkstream creation commands)
-console --> server : HTTP polling + reverse proxy\n(GET /v1/api/dashboard,\nproxy /node/{id}/* traffic)
-
-sim --> redis : Redis LIST + PUBSUB\n+ STRING (heartbeats)
+channel --> server : HTTP + SSE\n(POST /v1/api/send,\nGET /v1/api/events)
 
 ' Notes
-note right of sim
-  Simulator replaces Server+Bridge
-  with lightweight SimNodes that
-  publish to the same Redis channels.
-end note
-
-note right of redis
-  Shared message broker:
-  - LIST: command queues
-  - STRING: heartbeats, routing
-  - PUBSUB: event broadcast
+note right of console
+  Multi-node router:
+  - Hash-ring bucket lookup
+  - Proxies create/send/approve
+  - Direct SSE from client to node
+  - HTTP polling for dashboard
 end note
 @enduml

docs/diagrams/02-package-structure.puml

@@ -6,13 +6,12 @@ title Turnstone — Package & Module Structure
 skinparam component {
     BackgroundColor<<entry>> #B8D4E3
     BackgroundColor<<core>> #C8E6C9
-    BackgroundColor<<mq>> #FFE0B2
-    BackgroundColor<<sim>> #E1BEE7
     BackgroundColor<<console>> #B2EBF2
     BackgroundColor<<ui>> #F0F4C3
     BackgroundColor<<artifact>> #ECEFF1
     BackgroundColor<<sdk>> #FFCDD2
     BackgroundColor<<api>> #D1C4E9
+    BackgroundColor<<channel>> #FFE0B2
 }
 
 ' Entry points
@@ -45,23 +44,11 @@ package "turnstone/core/" <<Rectangle>> {
     component [model_registry.py\nModelRegistry] as registry <<core>>
 }
 
-' MQ subsystem
-package "turnstone/mq/" <<Rectangle>> {
-    component [protocol.py\n28 message types] as protocol <<mq>>
-    component [broker.py\nMessageBroker, RedisBroker] as broker <<mq>>
-    component [bridge.py\nturnstone-bridge] as bridge <<mq>>
-    component [client.py\nTurnstoneClient] as client <<mq>>
-}
-
-' Simulator
-package "turnstone/sim/" <<Rectangle>> {
-    component [cluster.py\nSimCluster] as simcluster <<sim>>
-    component [node.py\nSimNode, SimWorkstream] as simnode <<sim>>
-    component [engine.py\nSimEngine] as simengine <<sim>>
-    component [scenario.py\n5 scenarios] as scenario <<sim>>
-    component [sim/config.py\nSimConfig] as simconfig <<sim>>
-    component [sim/metrics.py\nSim metrics] as simmetrics <<sim>>
-    component [sim/cli.py\nturnstone-sim] as simcli <<sim>>
+' Channels
+package "turnstone/channels/" <<Rectangle>> {
+    component [_routing.py\nChannelRouter] as router <<channel>>
+    component [discord/bot.py\nDiscordBot] as discordbot <<channel>>
+    component [gateway.py\nturnstone-channel] as gateway <<channel>>
 }
 
 ' Console
@@ -146,35 +133,17 @@ mcp --> config
 registry --> config
 tools --> schemas
 
-' MQ dependencies
-bridge --> protocol
-bridge --> broker
-bridge --> config
-client --> protocol
-client --> broker
-
-' Sim dependencies
-simcli --> simcluster
-simcli --> simconfig
-simcli --> scenario
-simcluster --> simnode
-simcluster --> broker
-simcluster --> simmetrics
-simcluster --> simconfig
-simnode --> simengine
-simnode --> protocol
-simnode --> simconfig
-simnode --> simmetrics
-scenario --> broker
-scenario --> protocol
-scenario --> simconfig
-scenario --> simmetrics
+' Channel dependencies
+gateway --> discordbot
+gateway --> router
+discordbot --> sdkserver : HTTP + SSE
+router --> storage : channel_routes
 
 ' Console dependencies
 consoleserver --> collector
 consoleserver --> config
 consoleserver --> auth
-collector --> broker
+collector --> server : HTTP polling
 
 ' API dependencies
 serverspec --> openapi

docs/diagrams/06-mq-protocol.puml

@@ -1,265 +0,0 @@
-@startuml
-!theme plain
-title Turnstone — Message Queue Protocol Types
-skinparam classAttributeIconSize 0
-skinparam packageStyle rectangle
-skinparam packageBorderThickness 2
-
-package "Inbound Messages (Client → Bridge)" as InPkg #FFF3E0 {
-
-    abstract class "InboundMessage" as IM {
-        + type: str
-        + correlation_id: str  {auto: uuid4().hex[:12]}
-        + timestamp: float  {auto: time.time()}
-        --
-        + to_json() → str
-        + {static} from_json(raw) → InboundMessage
-    }
-
-    class SendMessage {
-        type = "send"
-        --
-        + ws_id: str
-        + message: str
-        + auto_approve: bool = False
-        + auto_approve_tools: list[str] = []
-        + name: str = ""
-        + target_node: str = ""
-    }
-
-    class ApproveMessage {
-        type = "approve"
-        --
-        + ws_id: str
-        + request_id: str
-        + approved: bool = True
-        + feedback: str | None
-        + always: bool = False
-    }
-
-    class PlanFeedbackMessage {
-        type = "plan_feedback"
-        --
-        + ws_id: str
-        + request_id: str
-        + feedback: str
-    }
-
-    class CommandMessage {
-        type = "command"
-        --
-        + ws_id: str
-        + command: str
-    }
-
-    class CreateWorkstreamMessage {
-        type = "create_workstream"
-        --
-        + name: str = ""
-        + auto_approve: bool = False
-        + auto_approve_tools: list[str] = []
-        + target_node: str = ""
-        + initial_message: str = ""
-        + skill: str = ""
-        + user_id: str = ""
-    }
-
-    class CloseWorkstreamMessage {
-        type = "close_workstream"
-        --
-        + ws_id: str
-    }
-
-    class ListWorkstreamsMessage {
-        type = "list_workstreams"
-    }
-
-    class HealthMessage {
-        type = "health"
-    }
-
-    class ListNodesMessage {
-        type = "list_nodes"
-    }
-
-    class CancelMessage {
-        type = "cancel"
-        --
-        + ws_id: str
-    }
-
-    IM <|-- SendMessage
-    IM <|-- ApproveMessage
-    IM <|-- PlanFeedbackMessage
-    IM <|-- CommandMessage
-    IM <|-- CreateWorkstreamMessage
-    IM <|-- CloseWorkstreamMessage
-    IM <|-- ListWorkstreamsMessage
-    IM <|-- HealthMessage
-    IM <|-- ListNodesMessage
-    IM <|-- CancelMessage
-}
-
-package "Outbound Events (Bridge → Client)" as OutPkg #E3F2FD {
-
-    abstract class "OutboundEvent" as OE {
-        + type: str
-        + ws_id: str
-        + correlation_id: str
-        + timestamp: float
-        --
-        + to_json() → str
-        + {static} from_json(raw) → OutboundEvent
-    }
-
-    package "Streaming" #BBDEFB {
-        class ContentEvent {
-            type = "content"
-            + text: str
-        }
-        class ReasoningEvent {
-            type = "reasoning"
-            + text: str
-        }
-        class StreamEndEvent {
-            type = "stream_end"
-        }
-    }
-
-    package "Tools" #C8E6C9 {
-        class ToolInfoEvent {
-            type = "tool_info"
-            + items: list
-        }
-        class ApprovalRequestEvent {
-            type = "approval_request"
-            + items: list
-            ..
-            correlation_id = request_id
-        }
-        class ToolOutputChunkEvent {
-            type = "tool_output_chunk"
-            + call_id: str
-            + chunk: str
-        }
-        class ToolResultEvent {
-            type = "tool_result"
-            + call_id: str
-            + name: str
-            + output: str
-            + is_error: bool
-        }
-        class PlanReviewEvent {
-            type = "plan_review"
-            + content: str
-        }
-    }
-
-    package "Status" #FFF9C4 {
-        class AckEvent {
-            type = "ack"
-            + status: str
-            + detail: str
-        }
-        class StatusEvent {
-            type = "status"
-            + prompt_tokens: int
-            + completion_tokens: int
-            + total_tokens: int
-            + context_window: int
-            + pct: float
-            + effort: str
-            + cache_creation_tokens: int
-            + cache_read_tokens: int
-        }
-        class StateChangeEvent {
-            type = "state_change"
-            + state: str
-        }
-        class TurnCompleteEvent {
-            type = "turn_complete"
-            + content: str
-        }
-    }
-
-    package "Lifecycle" #F8BBD0 {
-        class WorkstreamCreatedEvent {
-            type = "ws_created"
-            + name: str
-        }
-        class WorkstreamClosedEvent {
-            type = "ws_closed"
-        }
-        class WorkstreamListEvent {
-            type = "ws_list"
-            + workstreams: list
-        }
-        class WorkstreamRenameEvent {
-            type = "ws_rename"
-            + name: str
-        }
-    }
-
-    package "System" #E0E0E0 {
-        class HealthResponseEvent {
-            type = "health_response"
-            + data: dict
-        }
-        class ErrorEvent {
-            type = "error"
-            + message: str
-        }
-        class InfoEvent {
-            type = "info"
-            + message: str
-        }
-        class NodeListEvent {
-            type = "node_list"
-            + nodes: list
-        }
-        class ClusterStateEvent {
-            type = "cluster_state"
-            + state: str
-            + node_id: str
-            + tokens: int
-            + context_ratio: float
-            + activity: str
-            + activity_state: str
-        }
-    }
-
-    OE <|-- ContentEvent
-    OE <|-- ReasoningEvent
-    OE <|-- StreamEndEvent
-    OE <|-- ToolInfoEvent
-    OE <|-- ApprovalRequestEvent
-    OE <|-- ToolResultEvent
-    OE <|-- PlanReviewEvent
-    OE <|-- AckEvent
-    OE <|-- StatusEvent
-    OE <|-- StateChangeEvent
-    OE <|-- TurnCompleteEvent
-    OE <|-- WorkstreamCreatedEvent
-    OE <|-- WorkstreamClosedEvent
-    OE <|-- WorkstreamListEvent
-    OE <|-- WorkstreamRenameEvent
-    OE <|-- HealthResponseEvent
-    OE <|-- ErrorEvent
-    OE <|-- InfoEvent
-    OE <|-- NodeListEvent
-    OE <|-- ClusterStateEvent
-}
-
-SendMessage -[hidden]down- OE
-
-note bottom of IM
-  **Deserialization**: Strict type-dispatch via _INBOUND_REGISTRY.
-  Unknown type raises ValueError.
-end note
-
-note bottom of OE
-  **Deserialization**: Lenient type-dispatch via _OUTBOUND_REGISTRY.
-  Unknown type falls back to base OutboundEvent.
-end note
-
-@enduml

docs/diagrams/07-message-routing.puml

@@ -1,105 +0,0 @@
-@startuml
-!theme plain
-title Turnstone — Multi-Node Message Routing
-
-skinparam sequenceArrowThickness 1.5
-
-participant "TurnstoneClient" as Client
-collections "Redis" as Redis
-participant "Bridge-A\n(node_id: nodeA)" as BridgeA
-participant "Bridge-B\n(node_id: nodeB)" as BridgeB
-participant "Server-A" as ServerA
-
-== Scenario A: New Message — No Workstream Affinity ==
-
-Client -> Redis : RPUSH turnstone:inbound\n{type:"send", message:"...", ws_id:""}
-note right of Redis : Shared queue — any bridge can pick up
-
-BridgeA -> Redis : BLPOP [turnstone:inbound:nodeA,\n         turnstone:inbound]
-Redis --> BridgeA : SendMessage (from shared queue)
-
-BridgeA -> ServerA : POST /v1/api/workstreams/new\n{name:"", auto_approve:false}
-ServerA --> BridgeA : {ws_id:"abc12345", name:"ws-abc1"}
-
-BridgeA -> Redis : SET turnstone:ws:abc12345 "nodeA"
-note right : Register workstream ownership
-
-BridgeA -> ServerA : GET /v1/api/events?ws_id=abc12345
-note right : Start per-WS SSE thread
-
-BridgeA -> Redis : PUBLISH turnstone:events:global\nWorkstreamCreatedEvent
-
-BridgeA -> Redis : PUBLISH turnstone:events:cluster\nClusterStateEvent(ws_id, state:"idle", node_id:"nodeA")
-
-BridgeA -> ServerA : POST /v1/api/send\n{message:"...", ws_id:"abc12345"}
-ServerA --> BridgeA : {status:"ok"}
-
-BridgeA -> Redis : PUBLISH turnstone:events:abc12345\nAckEvent(status:"ok")
-
-... SSE events flow: content, tool_output_chunk, tool_result, status, state_change ...
-
-BridgeA -> Redis : PUBLISH turnstone:events:abc12345\nContentEvent, ToolResultEvent, ...
-BridgeA -> Redis : PUBLISH turnstone:events:global\nStateChangeEvent(state:"idle", content:"...")
-BridgeA -> Redis : PUBLISH turnstone:events:abc12345\nTurnCompleteEvent(content:"...")
-
-== Scenario B: Directed Message to Specific Node ==
-
-Client -> Redis : RPUSH turnstone:inbound:nodeB\n{type:"send", target_node:"nodeB", ...}
-note right : Per-node queue — only nodeB picks up
-
-BridgeB -> Redis : BLPOP [turnstone:inbound:nodeB,\n         turnstone:inbound]
-Redis --> BridgeB : SendMessage (from per-node queue, priority)
-
-note right of BridgeB : Process locally on nodeB
-
-== Scenario C: Re-routing (Lands on Wrong Node) ==
-
-Client -> Redis : RPUSH turnstone:inbound\n{type:"send", ws_id:"abc12345"}
-
-BridgeB -> Redis : BLPOP [..., turnstone:inbound]
-Redis --> BridgeB : SendMessage (ws_id: abc12345)
-
-BridgeB -> Redis : GET turnstone:ws:abc12345
-Redis --> BridgeB : "nodeA"
-
-note right of BridgeB : Owner is nodeA, not me — re-route
-
-BridgeB -> Redis : RPUSH turnstone:inbound:nodeA\n(re-routed message)
-
-BridgeA -> Redis : BLPOP [turnstone:inbound:nodeA, ...]
-Redis --> BridgeA : SendMessage (from per-node queue)
-note right of BridgeA : Process locally — I own this workstream
-
-== Scenario D: Approval via Response Queue ==
-
-BridgeA <- ServerA : SSE: {type:"approve_request", items:[...]}
-
-note right of BridgeA
-  Bridge checks auto-approve:
-  1. _ws_auto_approve[ws_id]? → auto
-  2. All tools in safe set? → auto
-     (read_file, search, man,
-      memory, recall)
-  3. Otherwise → manual approval
-end note
-
-BridgeA -> Redis : PUBLISH turnstone:events:abc12345\nApprovalRequestEvent(correlation_id: req_xyz)
-
-Client <- Redis : (subscribed) ApprovalRequestEvent
-
-Client -> Redis : RPUSH turnstone:resp:req_xyz\nApproveMessage(approved:true)
-note right : Response queue — bypasses inbound queue
-
-BridgeA -> Redis : BLPOP turnstone:resp:req_xyz\n(spawned approval thread, timeout 300s)
-Redis --> BridgeA : ApproveMessage
-
-BridgeA -> ServerA : POST /v1/api/approve\n{approved:true, ws_id:"abc12345"}
-
-== Heartbeat (continuous) ==
-
-BridgeA -> Redis : SET turnstone:node:nodeA\n{server_url, started} EX 60
-note right : Every 30s — TTL 60s
-
-BridgeB -> Redis : SET turnstone:node:nodeB\n{server_url, started} EX 60
-
-@enduml

docs/diagrams/08-redis-key-schema.puml

@@ -1,98 +0,0 @@
-@startuml
-!theme plain
-title Turnstone — Redis Key Schema
-
-skinparam component {
-    BackgroundColor<<LIST>> #BBDEFB
-    BackgroundColor<<STRING>> #C8E6C9
-    BackgroundColor<<PUBSUB>> #FFE0B2
-}
-
-skinparam note {
-    BackgroundColor #FAFAFA
-}
-
-package "Queues (Redis LIST)" #E3F2FD {
-    component [**turnstone:inbound**\n\nShared command queue.\nAny bridge can consume.\n\nOps: RPUSH (write), BLPOP (read)] as inbound <<LIST>>
-
-    component [**turnstone:inbound:{node_id}**\n\nPer-node directed queue.\nPriority over shared queue.\n\nOps: RPUSH (write), BLPOP (read)] as inbound_node <<LIST>>
-
-    component [**turnstone:resp:{request_id}**\n\nPer-request response queue.\nFor approval / plan feedback.\nTTL: 600s\n\nOps: RPUSH + EXPIRE (write), BLPOP (read)] as resp <<LIST>>
-}
-
-package "Routing (Redis STRING)" #E8F5E9 {
-    component [**turnstone:ws:{ws_id}**\n\nWorkstream → node ownership.\nValue: node_id string.\nNo TTL.\n\nOps: SET, GET, DEL] as ws_owner <<STRING>>
-
-    component [**turnstone:node:{node_id}**\n\nNode heartbeat + metadata.\nValue: JSON {server_url, started, ...}\nTTL: 60s (refreshed every 30s)\n\nOps: SET with EX, GET, SCAN] as node_hb <<STRING>>
-}
-
-package "Event Channels (Redis PUBSUB)" #FFF3E0 {
-    component [**turnstone:events:global**\n\nGlobal event broadcast.\nAll state changes, ws lifecycle.\n\nOps: PUBLISH, SUBSCRIBE] as evt_global <<PUBSUB>>
-
-    component [**turnstone:events:{ws_id}**\n\nPer-workstream events.\nContent, tools, status.\n\nOps: PUBLISH, SUBSCRIBE] as evt_ws <<PUBSUB>>
-
-    component [**turnstone:events:cluster**\n\nCluster-wide state changes.\nUsed by Console dashboard.\n\nOps: PUBLISH, SUBSCRIBE] as evt_cluster <<PUBSUB>>
-}
-
-' Readers / Writers
-
-actor "TurnstoneClient" as client
-actor "Bridge" as bridge
-actor "SimNode" as sim
-actor "Console\nCollector" as console
-actor "Scenario\n(injector)" as scenario
-
-' Queue interactions
-client --> inbound : RPUSH\n(send commands)
-client --> inbound_node : RPUSH\n(directed)
-scenario --> inbound : RPUSH\n(inject load)
-scenario --> inbound_node : RPUSH\n(directed scenario)
-bridge --> inbound : BLPOP\n(consume)
-bridge --> inbound_node : BLPOP\n(priority)
-bridge --> inbound_node : RPUSH\n(re-route)
-sim --> inbound_node : BLPOP\n(via dispatcher)
-
-client --> resp : RPUSH\n(approval response)
-bridge --> resp : BLPOP\n(wait for approval)
-
-' Routing interactions
-bridge --> ws_owner : SET / GET / DEL
-client --> ws_owner : GET\n(route lookup)
-sim --> ws_owner : SET / DEL
-
-bridge --> node_hb : SET with EX\n(heartbeat)
-sim --> node_hb : SET with EX\n(heartbeat)
-console --> node_hb : SCAN + GET\n(discovery)
-client --> node_hb : SCAN + GET\n(list_nodes)
-
-' Pub/sub interactions
-bridge --> evt_global : PUBLISH
-bridge --> evt_ws : PUBLISH
-bridge --> evt_cluster : PUBLISH
-client --> evt_global : SUBSCRIBE
-client --> evt_ws : SUBSCRIBE
-sim --> evt_global : PUBLISH
-sim --> evt_ws : PUBLISH
-sim --> evt_cluster : PUBLISH
-console --> evt_cluster : SUBSCRIBE
-
-note bottom of inbound
-  **BLPOP priority**: Bridges call
-  BLPOP [per-node, shared] so the
-  per-node queue is always checked first.
-end note
-
-note bottom of resp
-  **Bypasses inbound queue**: Approval
-  responses go directly to the response
-  queue, not through the inbound queue.
-  Auto-cleaned after 600s TTL.
-end note
-
-note bottom of evt_cluster
-  **ClusterStateEvent** includes node_id,
-  tokens, and context_ratio — enriched
-  data not available on the global channel.
-end note
-
-@enduml

docs/diagrams/09-workstream-states.puml

@@ -64,7 +64,7 @@ note right of thinking
 
   **Propagation:**
   • WebUI → global SSE queue (ws_state)
-  • Bridge → PUBLISH to global + cluster channels
+  • Console → HTTP polling picks up state
   • CLI → WorkstreamManager.set_state()
 end note
 
@@ -72,27 +72,8 @@ note left of attention
   **Blocking mechanisms:**
   • TerminalUI: input() prompt
   • WebUI: threading.Event.wait()
-  • Bridge: BLPOP on response queue
+  • ChannelBot: SSE event + Discord button
   • NullUI: auto-approve (never reaches)
 end note
 
-state "SimWorkstream (simplified)" as sim_group {
-    state "sim_idle" as si <<idle>>
-    state "sim_thinking" as st <<thinking>>
-    state "sim_running" as sr <<running>>
-    state "sim_error" as se <<error>>
-
-    [*] --> si
-    si --> st : process_turn() called
-    st --> sr : Tool calls generated
-    sr --> st : More rounds
-    st --> si : No tools / max rounds
-    st --> se : Uncaught exception
-}
-
-note right of sim_group
-  SimWorkstream has no ATTENTION state —
-  tool approval is not simulated.
-end note
-
 @enduml

docs/diagrams/10-simulator-architecture.puml

@@ -1,113 +0,0 @@
-@startuml
-!theme plain
-title Turnstone — Simulator Architecture
-
-skinparam component {
-    BackgroundColor<<cluster>> #E1BEE7
-    BackgroundColor<<node>> #CE93D8
-    BackgroundColor<<engine>> #F3E5F5
-    BackgroundColor<<scenario>> #FFF3E0
-    BackgroundColor<<metrics>> #E8F5E9
-    BackgroundColor<<redis>> #FFCDD2
-}
-
-package "SimCluster" as cluster <<cluster>> {
-
-    component [**ThreadPoolExecutor**\nmax_workers=64\n(blocking Redis ops)] as executor <<cluster>>
-
-    component [**redis.ConnectionPool**\nmax_connections=64\ndecode_responses=True\n(shared across all nodes)] as pool <<redis>>
-
-    package "InboundDispatchers" {
-        component [**Dispatcher 0**\nnodes 0-49] as d0
-        component [**Dispatcher 1**\nnodes 50-99] as d1
-        component [**...**\n(ceil(N/50) total)] as dn
-
-        note bottom of d0
-            Each dispatcher calls BLPOP on a single Redis
-            connection for up to 50 node queues + shared queue.
-            Keys: [prefix:inbound:sim-0000, ..., prefix:inbound]
-            Per-node keys have BLPOP priority over shared.
-        end note
-    }
-
-    package "SimNodes (N instances)" {
-        component [**SimNode sim-0000**] as n0 <<node>>
-        component [**SimNode sim-0001**] as n1 <<node>>
-        component [**...**] as nn <<node>>
-
-        component [**SimEngine**\n(per node, seeded RNG)\n\nLLM simulation:\n  gaussian(μ=2s, σ=0.5s) latency\n  gaussian(μ=200, σ=50) tokens\n  random word content\n  P(tool_calls) = 0.6/0.3\n\nTool simulation:\n  gaussian(μ=0.5s, σ=0.2s) latency\n  P(failure) = 0.02] as engine <<engine>>
-
-        component [**SimWorkstream**\n(0..max_ws per node)\n\nState: idle→thinking→running→idle\nToken accounting: word_count × 3\nContent: 8-chunk streaming] as ws <<node>>
-    }
-
-    component [**MetricsCollector**\n(thread-safe, shared)\n\nTracks: turn latencies,\nthroughput, utilization,\nerrors, node kills] as metrics <<metrics>>
-}
-
-package "Scenarios (5 workload patterns)" <<scenario>> {
-    component [**SteadyState**\nConstant rate:\n1/mps interval\nfor duration secs] as steady <<scenario>>
-
-    component [**Burst**\nburst_size messages\nas fast as possible\nthen wait] as burst <<scenario>>
-
-    component [**NodeFailure**\nSteadyState + periodic\nnode kills (up to N/2)] as failure <<scenario>>
-
-    component [**Directed**\nMessages targeted to\nspecific nodes via\ntarget_node field] as directed <<scenario>>
-
-    component [**Lifecycle**\n3 phases:\n1. Create workstreams\n2. Send messages\n3. Close half] as lifecycle <<scenario>>
-}
-
-database "Redis" as redis <<redis>>
-
-' Scenario -> Redis
-steady --> redis : RPUSH prefix:inbound\n(SendMessage)
-burst --> redis : RPUSH prefix:inbound\n(burst)
-failure --> redis : RPUSH prefix:inbound
-directed --> redis : RPUSH prefix:inbound:{node}\n(directed)
-lifecycle --> redis : RPUSH prefix:inbound\n(Create/Send/Close)
-
-' Dispatchers -> Redis -> Nodes
-d0 --> redis : BLPOP [per-node..., shared]
-d1 --> redis : BLPOP [per-node..., shared]
-d0 --> n0 : handle_message(raw)
-d0 --> n1 : handle_message(raw)
-
-' Nodes internal
-n0 --> engine : simulate_llm_response()\nsimulate_tool_execution()
-n0 --> ws : process_turn()
-
-' Nodes -> Redis (events)
-n0 --> redis : PUBLISH prefix:events:global\n(StateChangeEvent)
-n0 --> redis : PUBLISH prefix:events:{ws_id}\n(ContentEvent, ToolResultEvent, ...)
-n0 --> redis : PUBLISH prefix:events:cluster\n(ClusterStateEvent)
-n0 --> redis : SET prefix:node:sim-0000\nEX 60 (heartbeat)
-n0 --> redis : SET prefix:ws:{ws_id}\n(ownership)
-
-' Shared pool
-n0 ..> pool : PooledBroker\n(shared connection)
-n1 ..> pool : PooledBroker
-d0 ..> pool
-d0 ..> executor : asyncio.to_thread()
-
-' Metrics
-ws --> metrics : record_turn(ws_id, node_id, latency)
-steady --> metrics : record_inject()
-burst --> metrics : record_inject()
-directed --> metrics : record_inject()
-lifecycle --> metrics : record_inject()
-cluster --> metrics : record_node_kill(node_id)
-cluster --> metrics : snapshot_utilization()\n(every metrics_interval)
-
-note bottom of cluster
-    **SimConfig** controls all simulation parameters:
-    num_nodes, max_ws_per_node, redis settings,
-    llm_latency_mean/stddev, tool_failure_rate,
-    scenario, duration, messages_per_second, seed
-end note
-
-note right of redis
-    Simulator uses **real Redis** —
-    not a mock. Console dashboard
-    can monitor a running simulation
-    via the same cluster channel.
-end note
-
-@enduml

docs/diagrams/11-console-data-flow.puml

@@ -7,110 +7,79 @@ skinparam sequenceArrowThickness 1.5
 participant "Browser" as Browser
 participant "Console\nStarlette App" as Server
 participant "ClusterCollector" as CC
-collections "Redis" as Redis
-participant "Node-A Bridge" as BridgeA
-participant "Node-A\n(real server)" as NodeA
-participant "Node-B\n(sim node)" as NodeB
+participant "Node-A\n(server)" as NodeA
+participant "Node-B\n(server)" as NodeB
 
-== Thread 1: Cluster Event Subscriber (real-time) ==
+== Thread 1: Node Discovery (every 60s) ==
 
-CC -> Redis : SUBSCRIBE turnstone:events:cluster
-activate CC #E1BEE7
-
-Redis --> CC : ClusterStateEvent\n{ws_id, state:"thinking",\nnode_id:"nodeA", tokens:500,\ncontext_ratio:0.05}
-CC -> CC : Update NodeSnapshot["nodeA"]\n.workstreams["ws123"].state = "thinking"
-CC -> CC : _fanout(event) → all SSE listeners
-
-Redis --> CC : {"type":"ws_created",\nws_id:"ws456", name:"task-1",\nnode_id:"sim-0003"}
-CC -> CC : Add workstream to\nNodeSnapshot["sim-0003"]
-CC -> CC : _fanout(event)
-
-Redis --> CC : ClusterStateEvent\n{ws_id:"ws456", state:"idle"}
-CC -> CC : Update workstream state
-
-note right of CC
-  Handles: cluster_state,
-  ws_created, ws_closed, ws_rename
-
-  Thread runs continuously.
-  All updates are thread-safe
-  via threading.Lock.
-end note
-
-deactivate CC
-
-== Thread 2: Node Discovery (every 15s) ==
-
-CC -> Redis : SCAN 0 MATCH turnstone:node:*
-activate CC #B2EBF2
-Redis --> CC : [turnstone:node:nodeA, turnstone:node:sim-0003, ...]
-
-loop for each discovered key
-    CC -> Redis : GET turnstone:node:{id}
-    Redis --> CC : JSON: {server_url, started, max_ws, sim:true/false}
-end
-
-CC -> CC : Create new NodeSnapshot\nfor newly discovered nodes
-CC -> CC : Remove NodeSnapshot\nfor disappeared nodes
-
-CC -> CC : _fanout({type: "node_joined", ...})\n_fanout({type: "node_lost", ...})
-
-deactivate CC
-
-== Thread 3: HTTP Polling (every 10s, real nodes only) ==
-
-CC -> CC : Filter nodes where\nserver_url.startswith("http")
+CC -> CC : list_services("server",\nmax_age_seconds=120)
 activate CC #C8E6C9
 
-note right of CC
-  sim:// nodes are SKIPPED.
-  Their data comes exclusively
-  from the cluster event channel.
-end note
-
-CC -> NodeA : GET /v1/api/dashboard
-activate NodeA
-NodeA --> CC : {workstreams: [...],\naggregate: {total_tokens, ...}}
-deactivate NodeA
-
-CC -> NodeA : GET /health
-activate NodeA
-NodeA --> CC : {status:"ok", version:"0.3.0",\nmodel:"...", workstreams:{...}}
-deactivate NodeA
-
-CC -> CC : Diff old vs new workstream IDs
-CC -> CC : Replace NodeSnapshot["nodeA"]\n.workstreams, .health, .aggregate
-CC -> CC : _fanout(ws_created) for\nnewly appeared workstreams
-CC -> CC : _fanout(ws_closed) for\nremoved workstreams
-
-note right of CC
-  Poll-diff fanout ensures
-  browser SSE clients learn
-  about workstreams that
-  appeared without a real-time
-  cluster event (e.g. bridge
-  startup recovery).
-end note
-
-CC -x NodeB : (SKIPPED: sim:// URL)
+CC -> CC : New node? → spawn SSE task\nLost node? → cancel SSE task
+CC -> CC : _fanout(node_joined)\n_fanout(node_lost)
 
 deactivate CC
 
+== Thread 2: SSE Manager (asyncio event loop) ==
+
+note over CC
+  Single asyncio event loop multiplexes
+  one persistent SSE connection per node.
+  Scales to 1000+ nodes.
+end note
+
+CC -> NodeA : GET /v1/api/events/global\n?expected_node_id=nodeA
+activate NodeA
+activate CC #BBDEFB
+
+NodeA --> CC : data: {"type":"node_snapshot",\n"node_id":"nodeA",\n"workstreams":[...],\n"health":{...},\n"aggregate":{...}}
+
+note right of CC
+  Snapshot populates NodeSnapshot
+  in-memory state. Reconciles
+  against stale data (emits
+  ws_created/ws_closed diffs).
+end note
+
+loop real-time delta events
+    NodeA --> CC : data: {"type":"ws_state",\n"ws_id":"ws1","state":"running"}
+    CC -> CC : Update NodeSnapshot\n_fanout(cluster_state)
+end
+
+alt health transition
+    NodeA --> CC : data: {"type":"health_changed",\n"circuit_state":"open"}
+    CC -> CC : Update node.health
+end
+
+alt periodic aggregate (every 10s)
+    NodeA --> CC : data: {"type":"aggregate",\n"total_tokens":50000}
+    CC -> CC : Update node.aggregate
+end
+
+deactivate CC
+deactivate NodeA
+
+alt SSE disconnect
+    CC -> CC : Mark node unreachable\nReconnect with backoff\n(1s → 30s cap)
+end
+
+alt identity mismatch (409 or snapshot node_id differs)
+    CC -> CC : Mark node unreachable\nStop reconnecting to this URL
+end
+
 == Browser SSE Stream ==
 
 Browser -> Server : GET /v1/api/cluster/events
 activate Server
 
-Server -> CC : get_snapshot()
+Server -> CC : get_snapshot_and_register(queue)
+note right : Atomic: snapshot + listener\nregistration under both locks\n→ no event gap
 CC --> Server : ClusterSnapshot\n(full current state)
 
-Server -> CC : register_listener(queue)
-note right : Per-client queue.Queue(maxsize=2000)\nSSE via EventSourceResponse + run_in_executor()
-
 Server -> Browser : data: {"type":"snapshot",...}\n(full state as first SSE event)
 
 loop continuous (incremental updates)
-    CC -> Server : event via listener queue\n(from any of the 3 threads)
+    CC -> Server : event via listener queue\n(from SSE manager thread)
     Server -> Browser : data: {"type":"cluster_state",...}\n\n
 end
 
@@ -133,20 +102,20 @@ Server --> Browser : JSON response
 
 Browser -> Server : GET /v1/api/cluster/overview
 Server -> CC : get_overview()
-CC --> Server : {nodes: 10, workstreams: 47,\nstates: {running:5, ...},\naggregate: {total_tokens: 50000},\nversion_drift: false, versions: ["0.3.0"]}
+CC --> Server : {nodes: 2, workstreams: 12,\nstates: {running:5, ...},\naggregate: {total_tokens: 50000},\nversion_drift: false, versions: ["0.9.7"]}
 Server --> Browser : JSON response
 
 Browser -> Server : GET /v1/api/cluster/nodes?sort=activity
 Server -> CC : get_nodes(sort_by="activity")
-CC --> Server : {nodes: [...], total: 10}
+CC --> Server : {nodes: [...], total: 2}
 Server --> Browser : JSON response
 
-Browser -> Server : GET /v1/api/cluster/workstreams\n?state=running&node=sim-0003
-Server -> CC : get_workstreams(state="running",\nnode="sim-0003")
+Browser -> Server : GET /v1/api/cluster/workstreams\n?state=running&node=nodeA
+Server -> CC : get_workstreams(state="running",\nnode="nodeA")
 CC --> Server : {workstreams: [...], total: 5,\npage: 1, per_page: 50, pages: 1}
 Server --> Browser : JSON response
 
-== Workstream Creation (via MQ) ==
+== Workstream Creation (via Console proxy) ==
 
 Browser -> Server : POST /v1/api/cluster/workstreams/new\n{node_id:"nodeA", name:"new-task"}
 activate Server #FFECB3
@@ -154,34 +123,22 @@ activate Server #FFECB3
 Server -> CC : _pick_best_node() or\nget_node_detail(node_id)
 CC --> Server : node validated
 
-Server -> Server : Build CreateWorkstreamMessage\n{target_node:"nodeA", name:"new-task",\nuser_id: from auth_result}
+Server -> NodeA : POST http://nodeA:8080/v1/api/workstreams/new\n{name:"new-task", user_id: from auth_result}
+activate NodeA
+NodeA --> Server : {ws_id:"ws789", name:"new-task",\nnode_url:"http://nodeA:8080"}
+deactivate NodeA
 
-Server -> Redis : RPUSH turnstone:inbound:nodeA\n(directed queue)
-Server --> Browser : {status:"ok", correlation_id:"abc",\ntarget_node:"nodeA"}
+Server --> Browser : {status:"ok", ws_id:"ws789",\nnode_url:"http://nodeA:8080"}
 deactivate Server
 
-note right of Redis
-  Bridge on Node-A picks up the
-  message from its directed queue,
-  POSTs to /v1/api/workstreams/new
-  (forwarding user_id in payload),
-  registers ownership, publishes
-  ws_created to cluster channel.
+note right of Server
+  Console proxies the create request
+  directly to the target node via HTTP.
+  The response includes node_url so the
+  client can establish a direct SSE
+  connection for the data plane.
 end note
 
-Redis --> BridgeA : BLPOP turnstone:inbound:nodeA
-activate BridgeA
-BridgeA -> NodeA : POST /v1/api/workstreams/new\n{name:"new-task"}
-NodeA --> BridgeA : {ws_id:"ws789", name:"new-task"}
-BridgeA -> Redis : SET turnstone:ws:ws789 = nodeA
-BridgeA -> Redis : PUBLISH turnstone:events:cluster\n{type:"ws_created", ws_id:"ws789",\nnode_id:"nodeA", name:"new-task"}
-deactivate BridgeA
-
-Redis --> CC : ws_created event
-CC -> CC : Add workstream to\nNodeSnapshot["nodeA"]
-CC -> CC : _fanout(event)
-Server -> Browser : SSE: data: {"type":"ws_created",...}
-
 == Reverse Proxy (server UI through console port) ==
 
 Browser -> Server : GET /node/nodeA/

docs/diagrams/12-deployment.puml

@@ -14,45 +14,25 @@ node "Docker Host" as host {
 
     frame "turnstone-net (bridge network)" as net {
 
-        node "redis" <<redis:7.4-alpine>> as redis_node {
-            component [Redis Server\nport 6379] as redis
-            note bottom of redis
-                Healthcheck: redis-cli ping
-                Volume: redis-data
-            end note
-        }
-
         node "server" <<turnstone image>> as server_node {
             component [turnstone-server\nport 8080] as server
             note bottom of server
                 Command: turnstone-server
                   --host 0.0.0.0
                   --port 8080
-                Depends: redis (healthy)
                 Volume: turnstone-data
                   (/data)
             end note
         }
 
-        node "bridge ×N" <<turnstone image>> as bridge_node {
-            component [turnstone-bridge] as bridge
-            note bottom of bridge
-                Command: turnstone-bridge
-                  --server-url http://server:8080
-                  --redis-host redis
-                Depends: server + redis
-                Scalable: --scale bridge=N
-                node_id: auto from hostname
-            end note
-        }
-
         node "console" <<turnstone image>> as console_node {
             component [turnstone-console\nport 8090] as console
             note bottom of console
                 Command: turnstone-console
-                  --redis-host redis
                   --port 8090
-                Depends: redis
+                Depends: server
+                Hash-ring router for
+                  multi-node clusters
             end note
         }
 
@@ -75,42 +55,21 @@ node "Docker Host" as host {
                 See docs/pgbouncer.md
             end note
         }
-
-        node "sim (profile: sim)" <<turnstone image>> as sim_node {
-            component [turnstone-sim] as sim
-            note bottom of sim
-                Command: turnstone-sim
-                  --redis-host redis
-                  --nodes 100
-                  --scenario steady
-                Depends: redis
-                Optional: only with
-                  --profile sim
-            end note
-        }
     }
 }
 
 actor "Browser\nUser" as browser
-actor "MQ Client" as mqclient
+actor "SDK /\nAPI Client" as apiclient
 
 ' External connections
 browser --> server : HTTP + SSE\nport 8080
 browser --> console : HTTP + SSE\nport 8090
-mqclient --> redis : Redis protocol\nport 6379
+apiclient --> server : HTTP + SSE\nport 8080
 
 ' Internal connections
-server --> redis : Redis protocol\n(6379)
 server --> llm_api : OpenAI API\n(HTTPS/HTTP)
 
-bridge --> server : HTTP REST\n(POST /v1/api/send, etc.)
-bridge <-- server : SSE\n(GET /v1/api/events)
-bridge --> redis : Redis protocol\n(queues + pubsub)
-
-console --> redis : Redis PUBSUB + LIST\n(cluster events,\nws creation commands)
-console --> server : HTTP polling + proxy\n(GET /v1/api/dashboard,\nproxy /node/{id}/*)
-
-sim --> redis : Redis protocol\n(queues + pubsub + keys)
+console --> server : HTTP proxy\n(hash-ring lookup,\nproxy /node/{id}/*)
 
 ' Database connections (production/cluster profiles)
 server ..> pgbouncer : PostgreSQL\n(pool_size=2)
@@ -120,20 +79,17 @@ pgbouncer --> postgres : transaction\npooling
 ' Environment variables
 note right of host
     **Environment Variables:**
-    • LLM_BASE_URL — LLM endpoint
-    • OPENAI_API_KEY — API key
-    • REDIS_PASSWORD — Redis auth
-    • TURNSTONE_AUTH_TOKEN — API auth
-    • TURNSTONE_DB_URL — PostgreSQL URL
-    • POSTGRES_PASSWORD — DB password
+    * LLM_BASE_URL -- LLM endpoint
+    * OPENAI_API_KEY -- API key
+    * TURNSTONE_AUTH_TOKEN -- API auth
+    * TURNSTONE_DB_URL -- PostgreSQL URL
+    * POSTGRES_PASSWORD -- DB password
 end note
 
 ' Volumes
-database "redis-data" as rv
 database "turnstone-data" as tv
 database "postgres-data" as pv
 
-redis_node --> rv
 server_node --> tv
 pg_node --> pv
 

docs/diagrams/16-channel-architecture.puml

@@ -5,8 +5,6 @@ title Turnstone — Channel Integration Architecture
 skinparam class {
     BackgroundColor<<platform>> #E1BEE7
     BackgroundColor<<service>> #E8EAF6
-    BackgroundColor<<mq>> #FFCDD2
-    BackgroundColor<<bridge>> #C8E6C9
     BackgroundColor<<server>> #FFE0B2
     BackgroundColor<<storage>> #B3E5FC
 }
@@ -63,53 +61,23 @@ class "DiscordBot" as Bot <<service>> {
     Renders approval buttons
     escape_mentions() on send
     --
-    _notify_ws_map: msg_id → (ws_id, user_id)
-    _notify_reply_channels: ws_id → (dm, user_id)
+    _notify_ws_map: msg_id -> (ws_id, user_id)
+    _notify_reply_channels: ws_id -> (dm, user_id)
 }
 
 class "ChannelRouter" as Router <<service>> {
     +resolve_route(platform, channel_id)
-        → ws_id | None
+        -> ws_id | None
     +register_route(channel_id, ws_id)
     +resolve_identity(platform, platform_user_id)
-        → user_id | None
+        -> user_id | None
     --
-    Maps channels → workstreams
-    Maps platform users → turnstone users
+    Maps channels -> workstreams
+    Maps platform users -> turnstone users
     Caches routes in memory
 }
 
-class "AsyncRedisBroker" as Broker <<service>> {
-    +push_inbound(msg)
-    +subscribe(ws_id) → AsyncIterator
-    +subscribe_global() → AsyncIterator
-    +push_response(correlation_id, msg)
-    --
-    redis.asyncio client
-    Pub/sub + queue operations
-}
-
-' -- Redis MQ --
-class "Redis MQ" as Redis <<mq>> {
-    turnstone:inbound (LIST)
-    turnstone:events:{ws_id} (PUBSUB)
-    turnstone:events:global (PUBSUB)
-    turnstone:resp:{corr_id} (LIST)
-    --
-    Shared message bus
-    Same queues as bridge protocol
-}
-
-' -- Bridge + Server --
-class "turnstone-bridge" as Bridge <<bridge>> {
-    BLPOP turnstone:inbound
-    Drive server via HTTP
-    Relay SSE → Redis pub/sub
-    --
-    Owns workstream lifecycle
-    Auto-approve / manual approve
-}
-
+' -- Server --
 class "turnstone-server" as Server <<server>> {
     POST /v1/api/send
     POST /v1/api/approve
@@ -128,7 +96,7 @@ class "channel_users" as CU <<storage>> {
     channel_user_id (PK)
     platform: "discord" | "slack"
     platform_user_id
-    user_id → users
+    user_id -> users
     linked_at
     --
     /link command creates row
@@ -161,18 +129,13 @@ class "services" as SVC <<storage>> {
 ' -- Relationships --
 Discord --> Bot : gateway\nevents
 Bot --> Router : on_message\non_interaction
-Router --> Broker : SendMessage\nApproveMessage
 Router --> CU : resolve identity
 Router --> CR : resolve / register route
-Broker --> Redis : RPUSH inbound\nRPUSH resp:{id}
 
-Redis --> Bridge : BLPOP inbound
-Bridge --> Server : HTTP API
-Server --> Bridge : SSE events
-Bridge --> Redis : PUBLISH events:{ws_id}\nPUBLISH events:global
+Router --> Server : POST /v1/api/send\nPOST /v1/api/approve\nPOST /v1/api/workstreams/new
+Bot --> Server : GET /v1/api/events?ws_id=\n(SSE via httpx-sse)
+Server --> Bot : SSE event stream
 
-Redis --> Broker : SUBSCRIBE events:{ws_id}
-Broker --> Bot : event stream
 Bot --> Discord : reply / embed\nbutton callback
 
 Slack .[hidden]. Discord
@@ -180,10 +143,9 @@ Teams .[hidden]. Slack
 
 ChannelService --> Bot : creates + runs
 ChannelService --> Router : creates
-ChannelService --> Broker : creates
 ChannelService --> SVC : register / heartbeat /\nderegister
 
-' -- Notification path (direct HTTP, bypasses MQ) --
+' -- Notification path (direct HTTP) --
 Server --> ChannelService : POST /v1/api/notify\n(JWT: aud=turnstone-channel)
 Server --> SVC : list_services("channel",\nmax_age_seconds=120)
 
@@ -192,38 +154,36 @@ note right of Bot
   **Inbound Flow**
   1. Discord message arrives via gateway
   2. Bot.on_message() fires
-  3. ChannelRouter resolves channel → ws_id
+  3. ChannelRouter resolves channel -> ws_id
      (or creates new workstream)
-  4. ChannelRouter resolves platform user → user_id
+  4. ChannelRouter resolves platform user -> user_id
      via channel_users table
-  5. Broker.push_inbound(SendMessage)
-  6. Bridge pops from Redis, drives server
+  5. Router sends POST /v1/api/send to server
 
   **Workstream Resume (evicted workstreams)**
-  1. Stale route detected (no MQ owner)
+  1. Stale route detected (no active SSE listener)
   2. Existing ws_id reused directly from route
-  3. CreateWorkstreamMessage sent with
+  3. POST /v1/api/workstreams/new with
      resume_ws=<ws_id>
   4. Server resumes atomically during creation
-  5. Bridge emits WorkstreamResumedEvent → thread
+  5. SSE emits WorkstreamResumedEvent -> thread
 end note
 
-note right of Broker
+note right of Server
   **Outbound Flow**
-  1. Server emits SSE events
-  2. Bridge relays to Redis events:{ws_id}
-  3. Broker.subscribe(ws_id) yields events
-  4. Bot formats and sends to Discord thread
+  1. Server emits SSE events on
+     GET /v1/api/events?ws_id=
+  2. Bot subscribes via httpx-sse
+  3. Bot formats and sends to Discord thread
 end note
 
 note bottom of CR
   **Approval Flow**
-  1. ApprovalRequestEvent arrives via events:{ws_id}
+  1. ApprovalRequestEvent arrives via SSE
   2. Bot renders Discord buttons (Approve / Deny)
-  3. User clicks button → on_interaction()
+  3. User clicks button -> on_interaction()
   4. Router builds ApproveMessage
-  5. Broker.push_response(correlation_id, msg)
-  6. Bridge pops from resp:{id}, calls POST /api/approve
+  5. Router sends POST /v1/api/approve to server
 end note
 
 note bottom of CU
@@ -238,17 +198,17 @@ note bottom of CU
 end note
 
 note bottom of SVC
-  **Notification Flow** (direct HTTP, bypasses MQ)
-  1. LLM calls notify tool → _prepare_notify()
+  **Notification Flow** (direct HTTP)
+  1. LLM calls notify tool -> _prepare_notify()
   2. _exec_notify() checks rate limit (5/turn)
   3. Queries services table for healthy gateways
   4. Mints JWT (aud: turnstone-channel) via
      ServiceTokenManager
   5. POSTs to first healthy gateway (incl. ws_id)
   6. Gateway validates JWT, resolves target
-  7. adapter.send_notification() → Discord API
-     (tracks msg_id → ws_id for reply routing)
-  8. On failure: retry up to 3× (1s, 3s backoff)
+  7. adapter.send_notification() -> Discord API
+     (tracks msg_id -> ws_id for reply routing)
+  8. On failure: retry up to 3x (1s, 3s backoff)
   9. SSRF: only http(s) URLs allowed
 
   **Bidirectional DM Replies**

docs/diagrams/23-memory-architecture.puml

@@ -61,7 +61,7 @@ end
 
 Session -> Session : _init_system_messages()\nevery conversation turn
 
-Session -> Session : _get_visible_memories(\nlimit=fetch_limit)
+Session -> Session : _list_visible_memories(\nlimit=fetch_limit)
 note right
   **Scope resolution:**
   1. global scope (always)

docs/diagrams/24-settings-architecture.puml

@@ -144,7 +144,7 @@ note over Server, Registry
   **CLI entry point:**
   CLI flag  >  config.toml  >  argparse default
 
-  **Bootstrap settings** (database, Redis, auth, server bind):
+  **Bootstrap settings** (database, auth, server bind):
   Always from config.toml / env vars — never in ConfigStore.
 end note
 

docs/diagrams/architecture-overview.svg

@@ -34,253 +34,214 @@
   <text x="600" y="54" text-anchor="middle" fill="#8b949e" font-size="11" letter-spacing="1">SYSTEM ARCHITECTURE</text>
 
   <!-- ==================== COLUMN HEADERS ==================== -->
-  <text x="90" y="86" text-anchor="middle" fill="#58a6ff" font-size="9" font-weight="600" letter-spacing="2">CLIENTS</text>
-  <text x="276" y="86" text-anchor="middle" fill="#3fb950" font-size="9" font-weight="600" letter-spacing="2">GATEWAYS</text>
-  <text x="480" y="86" text-anchor="middle" fill="#f0883e" font-size="9" font-weight="600" letter-spacing="2">MESSAGE QUEUE</text>
-  <text x="700" y="86" text-anchor="middle" fill="#f47067" font-size="9" font-weight="600" letter-spacing="2">CLUSTER NODES</text>
-  <text x="940" y="86" text-anchor="middle" fill="#f778ba" font-size="9" font-weight="600" letter-spacing="2">LLM PROVIDERS</text>
+  <text x="110" y="86" text-anchor="middle" fill="#58a6ff" font-size="9" font-weight="600" letter-spacing="2">CLIENTS</text>
+  <text x="380" y="86" text-anchor="middle" fill="#3fb950" font-size="9" font-weight="600" letter-spacing="2">CONSOLE ROUTER</text>
+  <text x="700" y="86" text-anchor="middle" fill="#f47067" font-size="9" font-weight="600" letter-spacing="2">SERVER NODES</text>
+  <text x="1010" y="86" text-anchor="middle" fill="#f778ba" font-size="9" font-weight="600" letter-spacing="2">LLM PROVIDERS</text>
 
   <!-- ==================== CLIENT BOXES ==================== -->
   <!-- CLI -->
   <g filter="url(#shadow)">
-    <rect x="30" y="108" width="120" height="46" rx="5" fill="#161b22" stroke="#30363d" stroke-width="1"/>
-    <rect x="30" y="108" width="120" height="5" rx="5" fill="#58a6ff"/>
-    <rect x="30" y="108" width="120" height="5" fill="#58a6ff"/>
-    <rect x="30" y="111" width="120" height="2" fill="#161b22"/>
-    <text x="90" y="130" text-anchor="middle" fill="#e6edf3" font-size="11" font-weight="600">CLI</text>
-    <text x="90" y="145" text-anchor="middle" fill="#8b949e" font-size="9">terminal REPL</text>
+    <rect x="40" y="108" width="140" height="46" rx="5" fill="#161b22" stroke="#30363d" stroke-width="1"/>
+    <rect x="40" y="108" width="140" height="5" rx="5" fill="#58a6ff"/>
+    <rect x="40" y="108" width="140" height="5" fill="#58a6ff"/>
+    <rect x="40" y="111" width="140" height="2" fill="#161b22"/>
+    <text x="110" y="130" text-anchor="middle" fill="#e6edf3" font-size="11" font-weight="600">CLI</text>
+    <text x="110" y="145" text-anchor="middle" fill="#8b949e" font-size="9">terminal REPL</text>
   </g>
 
   <!-- Browser UI -->
   <g filter="url(#shadow)">
-    <rect x="30" y="174" width="120" height="46" rx="5" fill="#161b22" stroke="#30363d" stroke-width="1"/>
-    <rect x="30" y="174" width="120" height="5" rx="5" fill="#58a6ff"/>
-    <rect x="30" y="174" width="120" height="5" fill="#58a6ff"/>
-    <rect x="30" y="177" width="120" height="2" fill="#161b22"/>
-    <text x="90" y="196" text-anchor="middle" fill="#e6edf3" font-size="11" font-weight="600">Browser UI</text>
-    <text x="90" y="211" text-anchor="middle" fill="#8b949e" font-size="9">HTTP + SSE</text>
+    <rect x="40" y="174" width="140" height="46" rx="5" fill="#161b22" stroke="#30363d" stroke-width="1"/>
+    <rect x="40" y="174" width="140" height="5" rx="5" fill="#58a6ff"/>
+    <rect x="40" y="174" width="140" height="5" fill="#58a6ff"/>
+    <rect x="40" y="177" width="140" height="2" fill="#161b22"/>
+    <text x="110" y="196" text-anchor="middle" fill="#e6edf3" font-size="11" font-weight="600">Browser UI</text>
+    <text x="110" y="211" text-anchor="middle" fill="#8b949e" font-size="9">HTTP + SSE</text>
   </g>
 
   <!-- SDK / API -->
   <g filter="url(#shadow)">
-    <rect x="30" y="244" width="120" height="46" rx="5" fill="#161b22" stroke="#30363d" stroke-width="1"/>
-    <rect x="30" y="244" width="120" height="5" rx="5" fill="#58a6ff"/>
-    <rect x="30" y="244" width="120" height="5" fill="#58a6ff"/>
-    <rect x="30" y="247" width="120" height="2" fill="#161b22"/>
-    <text x="90" y="266" text-anchor="middle" fill="#e6edf3" font-size="11" font-weight="600">SDK / API</text>
-    <text x="90" y="281" text-anchor="middle" fill="#8b949e" font-size="9">programmatic</text>
-  </g>
-
-  <!-- Discord / Slack -->
-  <g filter="url(#shadow)">
-    <rect x="30" y="314" width="120" height="46" rx="5" fill="#161b22" stroke="#30363d" stroke-width="1"/>
-    <rect x="30" y="314" width="120" height="5" rx="5" fill="#58a6ff"/>
-    <rect x="30" y="314" width="120" height="5" fill="#58a6ff"/>
-    <rect x="30" y="317" width="120" height="2" fill="#161b22"/>
-    <text x="90" y="336" text-anchor="middle" fill="#e6edf3" font-size="11" font-weight="600">Discord / Slack</text>
-    <text x="90" y="351" text-anchor="middle" fill="#8b949e" font-size="9">chat platforms</text>
-  </g>
-
-  <!-- ==================== GATEWAY BOXES ==================== -->
-  <!-- Console -->
-  <g filter="url(#shadow)">
-    <rect x="216" y="118" width="120" height="58" rx="5" fill="#161b22" stroke="#30363d" stroke-width="1"/>
-    <rect x="216" y="118" width="120" height="5" rx="5" fill="#3fb950"/>
-    <rect x="216" y="118" width="120" height="5" fill="#3fb950"/>
-    <rect x="216" y="121" width="120" height="2" fill="#161b22"/>
-    <text x="276" y="142" text-anchor="middle" fill="#e6edf3" font-size="11" font-weight="600">Console</text>
-    <text x="276" y="157" text-anchor="middle" fill="#8b949e" font-size="9">dashboard + proxy</text>
-    <text x="276" y="169" text-anchor="middle" fill="#8b949e" font-size="9">cluster management</text>
+    <rect x="40" y="244" width="140" height="46" rx="5" fill="#161b22" stroke="#30363d" stroke-width="1"/>
+    <rect x="40" y="244" width="140" height="5" rx="5" fill="#58a6ff"/>
+    <rect x="40" y="244" width="140" height="5" fill="#58a6ff"/>
+    <rect x="40" y="247" width="140" height="2" fill="#161b22"/>
+    <text x="110" y="266" text-anchor="middle" fill="#e6edf3" font-size="11" font-weight="600">SDK / API</text>
+    <text x="110" y="281" text-anchor="middle" fill="#8b949e" font-size="9">programmatic</text>
   </g>
 
   <!-- Channel Gateway -->
   <g filter="url(#shadow)">
-    <rect x="216" y="292" width="120" height="58" rx="5" fill="#161b22" stroke="#30363d" stroke-width="1"/>
-    <rect x="216" y="292" width="120" height="5" rx="5" fill="#3fb950"/>
-    <rect x="216" y="292" width="120" height="5" fill="#3fb950"/>
-    <rect x="216" y="295" width="120" height="2" fill="#161b22"/>
-    <text x="276" y="316" text-anchor="middle" fill="#e6edf3" font-size="11" font-weight="600">Channel Gateway</text>
-    <text x="276" y="331" text-anchor="middle" fill="#8b949e" font-size="9">platform adapter</text>
-    <text x="276" y="343" text-anchor="middle" fill="#8b949e" font-size="9">Discord, Slack, ...</text>
+    <rect x="40" y="314" width="140" height="46" rx="5" fill="#161b22" stroke="#30363d" stroke-width="1"/>
+    <rect x="40" y="314" width="140" height="5" rx="5" fill="#58a6ff"/>
+    <rect x="40" y="314" width="140" height="5" fill="#58a6ff"/>
+    <rect x="40" y="317" width="140" height="2" fill="#161b22"/>
+    <text x="110" y="336" text-anchor="middle" fill="#e6edf3" font-size="11" font-weight="600">Channel Gateway</text>
+    <text x="110" y="351" text-anchor="middle" fill="#8b949e" font-size="9">Discord, Slack, ...</text>
   </g>
 
-  <!-- ==================== REDIS MQ ==================== -->
+  <!-- ==================== CONSOLE ROUTER ==================== -->
   <g filter="url(#shadow)">
-    <rect x="420" y="168" width="120" height="132" rx="5" fill="#161b22" stroke="#30363d" stroke-width="1"/>
-    <rect x="420" y="168" width="120" height="5" rx="5" fill="#f0883e"/>
-    <rect x="420" y="168" width="120" height="5" fill="#f0883e"/>
-    <rect x="420" y="171" width="120" height="2" fill="#161b22"/>
-    <text x="480" y="198" text-anchor="middle" fill="#e6edf3" font-size="11" font-weight="600">Redis MQ</text>
-    <line x1="438" y1="210" x2="522" y2="210" stroke="#30363d" stroke-width="1"/>
-    <text x="480" y="228" text-anchor="middle" fill="#8b949e" font-size="9">inbound queues</text>
-    <text x="480" y="243" text-anchor="middle" fill="#8b949e" font-size="9">event pub/sub</text>
-    <text x="480" y="258" text-anchor="middle" fill="#8b949e" font-size="9">node heartbeats</text>
-    <text x="480" y="273" text-anchor="middle" fill="#8b949e" font-size="9">workstream routing</text>
-    <text x="480" y="288" text-anchor="middle" fill="#8b949e" font-size="9">cluster state</text>
+    <rect x="300" y="148" width="160" height="170" rx="5" fill="#161b22" stroke="#30363d" stroke-width="1"/>
+    <rect x="300" y="148" width="160" height="5" rx="5" fill="#3fb950"/>
+    <rect x="300" y="148" width="160" height="5" fill="#3fb950"/>
+    <rect x="300" y="151" width="160" height="2" fill="#161b22"/>
+    <text x="380" y="178" text-anchor="middle" fill="#e6edf3" font-size="11" font-weight="600">Console</text>
+    <line x1="318" y1="190" x2="442" y2="190" stroke="#30363d" stroke-width="1"/>
+    <text x="380" y="208" text-anchor="middle" fill="#8b949e" font-size="9">hash-ring router</text>
+    <text x="380" y="223" text-anchor="middle" fill="#8b949e" font-size="9">cluster dashboard</text>
+    <text x="380" y="238" text-anchor="middle" fill="#8b949e" font-size="9">reverse proxy</text>
+    <line x1="318" y1="250" x2="442" y2="250" stroke="#30363d" stroke-width="1"/>
+    <text x="380" y="268" text-anchor="middle" fill="#484f58" font-size="8">control plane:</text>
+    <text x="380" y="282" text-anchor="middle" fill="#484f58" font-size="8">create / send / approve</text>
+    <text x="380" y="296" text-anchor="middle" fill="#484f58" font-size="8">cancel / command / close</text>
+    <text x="380" y="310" text-anchor="middle" fill="#484f58" font-size="8">port 8090</text>
   </g>
 
-  <!-- ==================== CLUSTER NODES ==================== -->
+  <!-- ==================== SERVER NODES ==================== -->
   <!-- Cluster outline -->
-  <rect x="598" y="100" width="204" height="310" rx="8" fill="none" stroke="#30363d" stroke-width="1" stroke-dasharray="4,3"/>
+  <rect x="570" y="100" width="260" height="310" rx="8" fill="none" stroke="#30363d" stroke-width="1" stroke-dasharray="4,3"/>
   <text x="700" y="422" text-anchor="middle" fill="#30363d" font-size="9" letter-spacing="1">CLUSTER</text>
 
   <!-- Node A -->
   <g filter="url(#shadow)">
-    <rect x="614" y="118" width="170" height="100" rx="5" fill="#161b22" stroke="#30363d" stroke-width="1"/>
-    <rect x="614" y="118" width="170" height="5" rx="5" fill="#f47067"/>
-    <rect x="614" y="118" width="170" height="5" fill="#f47067"/>
-    <rect x="614" y="121" width="170" height="2" fill="#161b22"/>
-    <text x="699" y="142" text-anchor="middle" fill="#e6edf3" font-size="11" font-weight="600">Node A</text>
-    <line x1="632" y1="152" x2="766" y2="152" stroke="#30363d" stroke-width="1"/>
-    <!-- Bridge -->
-    <rect x="626" y="162" width="70" height="28" rx="3" fill="#1c2128" stroke="#30363d" stroke-width="1"/>
-    <text x="661" y="180" text-anchor="middle" fill="#8b949e" font-size="9">bridge</text>
-    <!-- Server -->
-    <rect x="704" y="162" width="70" height="28" rx="3" fill="#1c2128" stroke="#30363d" stroke-width="1"/>
-    <text x="739" y="180" text-anchor="middle" fill="#8b949e" font-size="9">server</text>
-    <!-- Arrow bridge to server -->
-    <line x1="696" y1="176" x2="702" y2="176" stroke="#484f58" stroke-width="1" marker-end="url(#arrow)"/>
+    <rect x="590" y="118" width="220" height="100" rx="5" fill="#161b22" stroke="#30363d" stroke-width="1"/>
+    <rect x="590" y="118" width="220" height="5" rx="5" fill="#f47067"/>
+    <rect x="590" y="118" width="220" height="5" fill="#f47067"/>
+    <rect x="590" y="121" width="220" height="2" fill="#161b22"/>
+    <text x="700" y="142" text-anchor="middle" fill="#e6edf3" font-size="11" font-weight="600">Server Node A</text>
+    <line x1="608" y1="152" x2="792" y2="152" stroke="#30363d" stroke-width="1"/>
+    <!-- Server process -->
+    <rect x="608" y="162" width="184" height="28" rx="3" fill="#1c2128" stroke="#30363d" stroke-width="1"/>
+    <text x="700" y="180" text-anchor="middle" fill="#8b949e" font-size="9">turnstone-server :8080</text>
     <!-- Tools label -->
-    <text x="699" y="206" text-anchor="middle" fill="#484f58" font-size="8">14 tools + MCP</text>
+    <text x="700" y="206" text-anchor="middle" fill="#484f58" font-size="8">19 tools + MCP</text>
   </g>
 
   <!-- Node B -->
   <g filter="url(#shadow)">
-    <rect x="614" y="238" width="170" height="100" rx="5" fill="#161b22" stroke="#30363d" stroke-width="1"/>
-    <rect x="614" y="238" width="170" height="5" rx="5" fill="#f47067"/>
-    <rect x="614" y="238" width="170" height="5" fill="#f47067"/>
-    <rect x="614" y="241" width="170" height="2" fill="#161b22"/>
-    <text x="699" y="262" text-anchor="middle" fill="#e6edf3" font-size="11" font-weight="600">Node B</text>
-    <line x1="632" y1="272" x2="766" y2="272" stroke="#30363d" stroke-width="1"/>
-    <!-- Bridge -->
-    <rect x="626" y="282" width="70" height="28" rx="3" fill="#1c2128" stroke="#30363d" stroke-width="1"/>
-    <text x="661" y="300" text-anchor="middle" fill="#8b949e" font-size="9">bridge</text>
-    <!-- Server -->
-    <rect x="704" y="282" width="70" height="28" rx="3" fill="#1c2128" stroke="#30363d" stroke-width="1"/>
-    <text x="739" y="300" text-anchor="middle" fill="#8b949e" font-size="9">server</text>
-    <!-- Arrow bridge to server -->
-    <line x1="696" y1="296" x2="702" y2="296" stroke="#484f58" stroke-width="1" marker-end="url(#arrow)"/>
+    <rect x="590" y="238" width="220" height="100" rx="5" fill="#161b22" stroke="#30363d" stroke-width="1"/>
+    <rect x="590" y="238" width="220" height="5" rx="5" fill="#f47067"/>
+    <rect x="590" y="238" width="220" height="5" fill="#f47067"/>
+    <rect x="590" y="241" width="220" height="2" fill="#161b22"/>
+    <text x="700" y="262" text-anchor="middle" fill="#e6edf3" font-size="11" font-weight="600">Server Node B</text>
+    <line x1="608" y1="272" x2="792" y2="272" stroke="#30363d" stroke-width="1"/>
+    <!-- Server process -->
+    <rect x="608" y="282" width="184" height="28" rx="3" fill="#1c2128" stroke="#30363d" stroke-width="1"/>
+    <text x="700" y="300" text-anchor="middle" fill="#8b949e" font-size="9">turnstone-server :8080</text>
     <!-- Tools label -->
-    <text x="699" y="326" text-anchor="middle" fill="#484f58" font-size="8">14 tools + MCP</text>
+    <text x="700" y="326" text-anchor="middle" fill="#484f58" font-size="8">19 tools + MCP</text>
   </g>
 
   <!-- ==================== LLM PROVIDERS ==================== -->
   <!-- OpenAI -->
   <g filter="url(#shadow)">
-    <rect x="870" y="130" width="140" height="46" rx="5" fill="#161b22" stroke="#30363d" stroke-width="1"/>
-    <rect x="870" y="130" width="140" height="5" rx="5" fill="#f778ba"/>
-    <rect x="870" y="130" width="140" height="5" fill="#f778ba"/>
-    <rect x="870" y="133" width="140" height="2" fill="#161b22"/>
-    <text x="940" y="153" text-anchor="middle" fill="#e6edf3" font-size="11" font-weight="600">OpenAI</text>
-    <text x="940" y="167" text-anchor="middle" fill="#8b949e" font-size="9">GPT-5, o-series</text>
+    <rect x="930" y="130" width="160" height="46" rx="5" fill="#161b22" stroke="#30363d" stroke-width="1"/>
+    <rect x="930" y="130" width="160" height="5" rx="5" fill="#f778ba"/>
+    <rect x="930" y="130" width="160" height="5" fill="#f778ba"/>
+    <rect x="930" y="133" width="160" height="2" fill="#161b22"/>
+    <text x="1010" y="153" text-anchor="middle" fill="#e6edf3" font-size="11" font-weight="600">OpenAI</text>
+    <text x="1010" y="167" text-anchor="middle" fill="#8b949e" font-size="9">GPT-5, o-series</text>
   </g>
 
   <!-- Anthropic -->
   <g filter="url(#shadow)">
-    <rect x="870" y="196" width="140" height="46" rx="5" fill="#161b22" stroke="#30363d" stroke-width="1"/>
-    <rect x="870" y="196" width="140" height="5" rx="5" fill="#f778ba"/>
-    <rect x="870" y="196" width="140" height="5" fill="#f778ba"/>
-    <rect x="870" y="199" width="140" height="2" fill="#161b22"/>
-    <text x="940" y="219" text-anchor="middle" fill="#e6edf3" font-size="11" font-weight="600">Anthropic</text>
-    <text x="940" y="233" text-anchor="middle" fill="#8b949e" font-size="9">Claude 4.5 / 4.6</text>
+    <rect x="930" y="196" width="160" height="46" rx="5" fill="#161b22" stroke="#30363d" stroke-width="1"/>
+    <rect x="930" y="196" width="160" height="5" rx="5" fill="#f778ba"/>
+    <rect x="930" y="196" width="160" height="5" fill="#f778ba"/>
+    <rect x="930" y="199" width="160" height="2" fill="#161b22"/>
+    <text x="1010" y="219" text-anchor="middle" fill="#e6edf3" font-size="11" font-weight="600">Anthropic</text>
+    <text x="1010" y="233" text-anchor="middle" fill="#8b949e" font-size="9">Claude 4.5 / 4.6</text>
   </g>
 
   <!-- Local / vLLM -->
   <g filter="url(#shadow)">
-    <rect x="870" y="262" width="140" height="46" rx="5" fill="#161b22" stroke="#30363d" stroke-width="1"/>
-    <rect x="870" y="262" width="140" height="5" rx="5" fill="#f778ba"/>
-    <rect x="870" y="262" width="140" height="5" fill="#f778ba"/>
-    <rect x="870" y="265" width="140" height="2" fill="#161b22"/>
-    <text x="940" y="285" text-anchor="middle" fill="#e6edf3" font-size="11" font-weight="600">Local / vLLM</text>
-    <text x="940" y="299" text-anchor="middle" fill="#8b949e" font-size="9">llama.cpp, NIM</text>
+    <rect x="930" y="262" width="160" height="46" rx="5" fill="#161b22" stroke="#30363d" stroke-width="1"/>
+    <rect x="930" y="262" width="160" height="5" rx="5" fill="#f778ba"/>
+    <rect x="930" y="262" width="160" height="5" fill="#f778ba"/>
+    <rect x="930" y="265" width="160" height="2" fill="#161b22"/>
+    <text x="1010" y="285" text-anchor="middle" fill="#e6edf3" font-size="11" font-weight="600">Local / vLLM</text>
+    <text x="1010" y="299" text-anchor="middle" fill="#8b949e" font-size="9">llama.cpp, NIM</text>
   </g>
 
   <!-- ==================== STORAGE ==================== -->
   <g filter="url(#shadow)">
-    <rect x="614" y="450" width="170" height="52" rx="5" fill="#161b22" stroke="#30363d" stroke-width="1"/>
-    <rect x="614" y="450" width="170" height="5" rx="5" fill="#bc8cff"/>
-    <rect x="614" y="450" width="170" height="5" fill="#bc8cff"/>
-    <rect x="614" y="453" width="170" height="2" fill="#161b22"/>
-    <text x="699" y="476" text-anchor="middle" fill="#e6edf3" font-size="11" font-weight="600">PostgreSQL / SQLite</text>
-    <text x="699" y="492" text-anchor="middle" fill="#8b949e" font-size="9">conversations, memory, auth</text>
+    <rect x="590" y="450" width="220" height="52" rx="5" fill="#161b22" stroke="#30363d" stroke-width="1"/>
+    <rect x="590" y="450" width="220" height="5" rx="5" fill="#bc8cff"/>
+    <rect x="590" y="450" width="220" height="5" fill="#bc8cff"/>
+    <rect x="590" y="453" width="220" height="2" fill="#161b22"/>
+    <text x="700" y="476" text-anchor="middle" fill="#e6edf3" font-size="11" font-weight="600">PostgreSQL / SQLite</text>
+    <text x="700" y="492" text-anchor="middle" fill="#8b949e" font-size="9">conversations, memory, auth</text>
   </g>
-  <text x="699" y="444" text-anchor="middle" fill="#bc8cff" font-size="9" font-weight="600" letter-spacing="2">STORAGE</text>
+  <text x="700" y="444" text-anchor="middle" fill="#bc8cff" font-size="9" font-weight="600" letter-spacing="2">STORAGE</text>
 
   <!-- ==================== CONNECTION LINES ==================== -->
 
-  <!-- CLIENT -> GATEWAY connections -->
+  <!-- CLIENT -> CONSOLE connections (control plane) -->
   <!-- Browser -> Console -->
-  <line x1="150" y1="197" x2="214" y2="155" stroke="#58a6ff" stroke-width="1.2" stroke-opacity="0.6" marker-end="url(#arrow-blue)"/>
-  <!-- Discord -> Channel -->
-  <line x1="150" y1="337" x2="214" y2="325" stroke="#58a6ff" stroke-width="1.2" stroke-opacity="0.6" marker-end="url(#arrow-blue)"/>
+  <line x1="180" y1="197" x2="298" y2="210" stroke="#58a6ff" stroke-width="1.2" stroke-opacity="0.6" marker-end="url(#arrow-blue)"/>
+  <!-- Channel -> Console -->
+  <line x1="180" y1="337" x2="298" y2="290" stroke="#58a6ff" stroke-width="1.2" stroke-opacity="0.6" marker-end="url(#arrow-blue)"/>
+  <!-- SDK -> Console -->
+  <line x1="180" y1="267" x2="298" y2="248" stroke="#58a6ff" stroke-width="1.2" stroke-opacity="0.6" marker-end="url(#arrow-blue)"/>
+  <text x="240" y="238" fill="#484f58" font-size="8" text-anchor="middle">HTTP</text>
 
-  <!-- CLI -> direct to Node A server (top path, curved) -->
-  <path d="M 150 131 C 200 131, 200 100, 400 100 L 400 100 C 500 100, 570 140, 612 168" stroke="#58a6ff" stroke-width="1.2" stroke-opacity="0.5" fill="none" stroke-dasharray="6,3" marker-end="url(#arrow-blue)"/>
-  <text x="370" y="96" fill="#484f58" font-size="8" text-anchor="middle">direct</text>
+  <!-- CLI -> direct to Node A (single-node mode, above everything) -->
+  <path d="M 180 120 L 588 120" stroke="#58a6ff" stroke-width="1.2" stroke-opacity="0.4" fill="none" stroke-dasharray="6,3" marker-end="url(#arrow-blue)"/>
+  <text x="390" y="114" fill="#484f58" font-size="8" text-anchor="middle">direct (single-node)</text>
 
-  <!-- SDK -> Redis (direct push) -->
-  <line x1="150" y1="267" x2="418" y2="240" stroke="#58a6ff" stroke-width="1.2" stroke-opacity="0.6" marker-end="url(#arrow-blue)"/>
+  <!-- CONSOLE -> NODE connections (proxy) -->
+  <!-- Console -> Node A -->
+  <line x1="460" y1="200" x2="588" y2="176" stroke="#3fb950" stroke-width="1.2" stroke-opacity="0.6" marker-end="url(#arrow-green)"/>
+  <!-- Console -> Node B -->
+  <line x1="460" y1="260" x2="588" y2="296" stroke="#3fb950" stroke-width="1.2" stroke-opacity="0.6" marker-end="url(#arrow-green)"/>
+  <text x="520" y="222" fill="#484f58" font-size="8" text-anchor="middle">proxy</text>
 
-  <!-- GATEWAY -> REDIS connections -->
-  <!-- Console -> Redis -->
-  <line x1="336" y1="160" x2="418" y2="200" stroke="#3fb950" stroke-width="1.2" stroke-opacity="0.6" marker-end="url(#arrow-green)"/>
-  <!-- Channel -> Redis -->
-  <line x1="336" y1="318" x2="418" y2="272" stroke="#3fb950" stroke-width="1.2" stroke-opacity="0.6" marker-end="url(#arrow-green)"/>
-
-  <!-- REDIS -> NODE connections -->
-  <!-- Redis -> Node A bridge -->
-  <line x1="540" y1="210" x2="624" y2="176" stroke="#f0883e" stroke-width="1.2" stroke-opacity="0.6" marker-end="url(#arrow-orange)"/>
-  <!-- Redis -> Node B bridge -->
-  <line x1="540" y1="260" x2="624" y2="296" stroke="#f0883e" stroke-width="1.2" stroke-opacity="0.6" marker-end="url(#arrow-orange)"/>
-
-  <!-- Console -> Node (proxy, dashed) -->
-  <path d="M 336 147 C 380 130, 500 108, 612 145" stroke="#3fb950" stroke-width="1" stroke-opacity="0.4" fill="none" stroke-dasharray="4,3" marker-end="url(#arrow-green)"/>
-  <text x="468" y="120" fill="#484f58" font-size="8" text-anchor="middle">proxy</text>
+  <!-- CLIENT -> NODE direct SSE (data plane, below console) -->
+  <!-- Browser -> Node A SSE (arc below console) -->
+  <path d="M 180 205 C 240 370, 450 380, 588 330" stroke="#58a6ff" stroke-width="1" stroke-opacity="0.3" fill="none" stroke-dasharray="4,3" marker-end="url(#arrow-blue)"/>
+  <text x="340" y="378" fill="#484f58" font-size="8" text-anchor="middle">SSE (data plane)</text>
 
   <!-- NODE -> LLM connections -->
   <!-- Node A -> LLM providers -->
-  <line x1="784" y1="168" x2="868" y2="155" stroke="#f47067" stroke-width="1.2" stroke-opacity="0.5" marker-end="url(#arrow-coral)"/>
-  <line x1="784" y1="176" x2="868" y2="219" stroke="#f47067" stroke-width="1.2" stroke-opacity="0.3"/>
-  <line x1="784" y1="180" x2="868" y2="282" stroke="#f47067" stroke-width="1.2" stroke-opacity="0.2"/>
+  <line x1="810" y1="168" x2="928" y2="155" stroke="#f47067" stroke-width="1.2" stroke-opacity="0.5" marker-end="url(#arrow-coral)"/>
+  <line x1="810" y1="176" x2="928" y2="219" stroke="#f47067" stroke-width="1.2" stroke-opacity="0.3"/>
+  <line x1="810" y1="180" x2="928" y2="282" stroke="#f47067" stroke-width="1.2" stroke-opacity="0.2"/>
 
   <!-- Node B -> LLM providers -->
-  <line x1="784" y1="288" x2="868" y2="163" stroke="#f47067" stroke-width="1.2" stroke-opacity="0.2"/>
-  <line x1="784" y1="296" x2="868" y2="222" stroke="#f47067" stroke-width="1.2" stroke-opacity="0.3"/>
-  <line x1="784" y1="300" x2="868" y2="288" stroke="#f47067" stroke-width="1.2" stroke-opacity="0.5" marker-end="url(#arrow-coral)"/>
+  <line x1="810" y1="288" x2="928" y2="163" stroke="#f47067" stroke-width="1.2" stroke-opacity="0.2"/>
+  <line x1="810" y1="296" x2="928" y2="222" stroke="#f47067" stroke-width="1.2" stroke-opacity="0.3"/>
+  <line x1="810" y1="300" x2="928" y2="288" stroke="#f47067" stroke-width="1.2" stroke-opacity="0.5" marker-end="url(#arrow-coral)"/>
 
   <!-- NODE -> STORAGE connections -->
   <line x1="680" y1="338" x2="680" y2="448" stroke="#bc8cff" stroke-width="1.2" stroke-opacity="0.4" stroke-dasharray="4,3" marker-end="url(#arrow-muted)"/>
   <line x1="718" y1="218" x2="718" y2="236" stroke="#484f58" stroke-width="1" stroke-opacity="0.3" stroke-dasharray="2,2"/>
 
   <!-- Extensibility hint -->
-  <text x="699" y="392" text-anchor="middle" fill="#30363d" font-size="10">...</text>
-
-  <!-- Event flow: Bridges -> Redis (dashed, bidirectional feel) -->
-  <line x1="624" y1="186" x2="542" y2="220" stroke="#f0883e" stroke-width="1" stroke-opacity="0.3" stroke-dasharray="3,3"/>
-  <line x1="624" y1="286" x2="542" y2="250" stroke="#f0883e" stroke-width="1" stroke-opacity="0.3" stroke-dasharray="3,3"/>
-  <text x="574" y="242" fill="#484f58" font-size="7" text-anchor="middle">events</text>
+  <text x="700" y="392" text-anchor="middle" fill="#30363d" font-size="10">...</text>
 
   <!-- ==================== FLOW LABELS ==================== -->
-  <!-- Interactive flow label -->
+  <!-- Direct / single-node flow label -->
   <rect x="30" y="395" width="10" height="10" rx="2" fill="none" stroke="#58a6ff" stroke-width="1.5" stroke-dasharray="3,2"/>
-  <text x="46" y="404" fill="#8b949e" font-size="9">interactive (direct)</text>
+  <text x="46" y="404" fill="#8b949e" font-size="9">direct (single-node / SSE)</text>
 
-  <!-- Queue flow label -->
-  <rect x="160" y="395" width="10" height="10" rx="2" fill="none" stroke="#f0883e" stroke-width="1.5"/>
-  <text x="176" y="404" fill="#8b949e" font-size="9">queue-driven</text>
+  <!-- Control plane label -->
+  <rect x="200" y="395" width="10" height="10" rx="2" fill="none" stroke="#58a6ff" stroke-width="1.5"/>
+  <text x="216" y="404" fill="#8b949e" font-size="9">control plane (HTTP)</text>
 
-  <!-- Proxy/event label -->
-  <rect x="275" y="395" width="10" height="10" rx="2" fill="none" stroke="#3fb950" stroke-width="1.5" stroke-dasharray="3,2"/>
-  <text x="291" y="404" fill="#8b949e" font-size="9">proxy / events</text>
+  <!-- Proxy label -->
+  <rect x="340" y="395" width="10" height="10" rx="2" fill="none" stroke="#3fb950" stroke-width="1.5"/>
+  <text x="356" y="404" fill="#8b949e" font-size="9">console proxy</text>
 
   <!-- ==================== BOTTOM DETAILS ==================== -->
   <line x1="30" y1="430" x2="1170" y2="430" stroke="#21262d" stroke-width="1"/>
 
   <!-- Routing rules at bottom, left-aligned -->
   <text x="44" y="456" fill="#30363d" font-size="9" font-weight="600" letter-spacing="1">ROUTING</text>
-  <circle cx="44" cy="474" r="3" fill="#f47067" opacity="0.6"/>
-  <text x="54" y="477" fill="#484f58" font-size="9">target_node set  &#x2192;  route to specific node queue</text>
-  <circle cx="44" cy="494" r="3" fill="#f0883e" opacity="0.6"/>
-  <text x="54" y="497" fill="#484f58" font-size="9">ws_id set  &#x2192;  route to owning node</text>
-  <circle cx="44" cy="514" r="3" fill="#58a6ff" opacity="0.6"/>
-  <text x="54" y="517" fill="#484f58" font-size="9">neither  &#x2192;  shared queue, any node picks up</text></svg>
+  <circle cx="44" cy="474" r="3" fill="#3fb950" opacity="0.6"/>
+  <text x="54" y="477" fill="#484f58" font-size="9">control plane: client &#x2192; console &#x2192; server node (hash-ring bucket lookup)</text>
+  <circle cx="44" cy="494" r="3" fill="#58a6ff" opacity="0.6"/>
+  <text x="54" y="497" fill="#484f58" font-size="9">data plane: client &#x2192; server node (direct SSE, node_url from create response)</text>
+  <circle cx="44" cy="514" r="3" fill="#f47067" opacity="0.6"/>
+  <text x="54" y="517" fill="#484f58" font-size="9">single-node: client &#x2192; server (direct HTTP + SSE, no console needed)</text>
+</svg>

docs/diagrams/png/01-system-context.png

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8ce6d2a43a991655c3f64a20b6e810fdb2f78eb767acc3d3d1b8d2c9f443181
-size 165011
+oid sha256:881a8b9bce67b5af9a52d5e50deaa72351cd99c76f18aad5caeb2b61131ca1af
+size 119798

docs/diagrams/png/02-package-structure.png

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b3ea69f852e93dc1bc7943db0c71d0cdd1afcbcf470a8737189ae56e85b3206
-size 310075
+oid sha256:75da80e6bd205e45b9fe48aa2f87197110c908f44e1d98c52eee69f956274711
+size 400402

docs/diagrams/png/06-mq-protocol.png

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d831c5e10266f0232262b6a29b0ea8e45b3cc63df75f716a80f18462b4f85e66
-size 319125

docs/diagrams/png/07-message-routing.png

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:09535722ba975e47cf0557a40b6c481f125ff2022c396f79715c3bba9f715871
-size 222032

docs/diagrams/png/08-redis-key-schema.png

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ed457b10b534b5fc2a5e190b281d7ded4dd1615da2229d67a373cf5dddccd059
-size 201601

docs/diagrams/png/09-workstream-states.png

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bf27afa267d5b8d6da38e83213ed1b8e87639d5105a0a1ccc2e5a4bf4d3b67e
-size 185282
+oid sha256:04d2069a9b5155ad1e7d842147fd78535ad9106d6856520439c33a9868a47499
+size 156694

docs/diagrams/png/10-simulator-architecture.png

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:35cf3a6942f62dabcbbe012ac2f9e6f155332c894692981b076de5a25c1f3330
-size 374055

docs/diagrams/png/11-console-data-flow.png

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3f1ad0fcd55eaca3b8ad9c5abc07432803641c54ede9fc93c79df144cf77d1c
-size 407761
+oid sha256:040f7d9ec7d676da40b9487e0825caf2c1574cbdd9f16d0998d90e0c2e4f8861
+size 360309

docs/diagrams/png/12-deployment.png

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09065fef028d05e6df425fd8abefaf5a2ca04b66802f2e3975f289fa597f63ed
-size 309656
+oid sha256:a872556d111185f4531d1b68ee892b4ce5042d7ccf277e2cad08beb6932c9803
+size 191144

docs/diagrams/png/16-channel-architecture.png

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fc99bb8d84d6e9f3dac9d5c12ac7f569a041b29431c57612c24b50f332982ed
-size 462992
+oid sha256:8a5957b71822656098cbe779ca619b7e56e9b11b0f1c4eac4fc880ed62b71a2a
+size 358670

docs/diagrams/png/24-settings-architecture.png

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83c0e6aad3eb19f6bc475a30a77215e801da3da5930f0462417fe7eb6eda6be2
-size 347144
+oid sha256:06fe076f0835a891e00afc804fd1805196ebde9fc0d34998c7873e87287f982b
+size 346887

docs/docker.md

@@ -1,6 +1,6 @@
 # Docker Deployment
 
-Docker Compose stack for running the full turnstone platform or the simulator.
+Docker Compose stack for running the full turnstone platform.
 
 ## Quick Start
 
@@ -10,9 +10,6 @@ cp .env.example .env
 
 # Full stack (needs an LLM API on the host)
 docker compose up
-
-# Simulator only (no LLM needed)
-docker compose --profile sim up redis console sim
 ```
 
 Console dashboard: http://localhost:8090
@@ -23,18 +20,14 @@ Console dashboard: http://localhost:8090
 
 | Service | Port | Profile | Description |
 |---------|------|---------|-------------|
-| `redis` | 6379 | default | Message broker, pub/sub, node registry |
 | `server` | 8080 | default | Web UI + chat workstreams + LLM |
-| `bridge` | — | default | Redis-to-HTTP bridge (multi-node routing) |
 | `console` | 8090 | default | Cluster dashboard |
 | `channel` | — | production | Channel gateway (Discord, Slack, etc.) |
 | `server-1`…`server-10` | — | cluster | 10-node server fleet (PostgreSQL required) |
-| `bridge-1`…`bridge-10` | — | cluster | Matching bridge fleet |
-| `sim` | — | sim | Multi-node cluster simulator |
 
 ## Profiles
 
-**Default** (no flag) — starts `redis`, `server`, `bridge`, `console`. Requires an OpenAI-compatible LLM API running on the host (default: `http://localhost:8000/v1`).
+**Default** (no flag) — starts `server` and `console`. Requires an OpenAI-compatible LLM API running on the host (default: `http://localhost:8000/v1`).
 
 ```bash
 docker compose up
@@ -46,22 +39,12 @@ docker compose up
 docker compose --profile production up
 ```
 
-**Cluster** — 10-node server/bridge fleet sharing PostgreSQL and Redis. Access all nodes via the console at `:8090`. Requires `POSTGRES_PASSWORD`:
+**Cluster** — 10-node server fleet sharing PostgreSQL. Access all nodes via the console at `:8090`. Requires `POSTGRES_PASSWORD`:
 
 ```bash
 docker compose --profile cluster up
 ```
 
-**Sim** — adds the simulator. Can run alongside the full stack or standalone with just Redis and the console:
-
-```bash
-# Sim + console (no LLM needed)
-docker compose --profile sim up redis console sim
-
-# Everything including sim
-docker compose --profile sim up
-```
-
 ## Configuration
 
 All configuration is via environment variables in `.env` (copy from `.env.example`):
@@ -74,13 +57,6 @@ All configuration is via environment variables in `.env` (copy from `.env.exampl
 | `OPENAI_API_KEY` | `dummy` | API key (`dummy` for local servers) |
 | `TAVILY_API_KEY` | — | Web search API key (only needed for local/vLLM models; Anthropic and OpenAI search models use native search) |
 
-### Redis
-
-| Variable | Default | Description |
-|----------|---------|-------------|
-| `REDIS_PASSWORD` | — | Redis auth password (empty = no auth) |
-| `REDIS_PORT` | `6379` | Host port mapping |
-
 ### Server
 
 | Variable | Default | Description |
@@ -93,15 +69,14 @@ All configuration is via environment variables in `.env` (copy from `.env.exampl
 | Variable | Default | Description |
 |----------|---------|-------------|
 | `CONSOLE_PORT` | `8090` | Host port mapping |
-| `CONSOLE_POLL_INTERVAL` | `10` | Node polling interval (seconds) |
 
 ### Auth
 
+Auth is always enabled. `TURNSTONE_JWT_SECRET` is required.
+
 | Variable | Default | Description |
 |----------|---------|-------------|
-| `TURNSTONE_AUTH_ENABLED` | — | Set to `1` to require authentication |
-| `TURNSTONE_AUTH_TOKEN` | — | Config-file token for server/bridge/console (backward compat, works alongside JWT) |
-| `TURNSTONE_JWT_SECRET` | — | Secret key for signing JWTs (required when using user identity / JWT auth) |
+| `TURNSTONE_JWT_SECRET` | — | Secret key for signing JWTs (required) |
 
 ### Database
 
@@ -130,29 +105,17 @@ The database stores workstream history, user accounts, and API tokens. When usin
 | `TURNSTONE_DISCORD_TOKEN` | — | Discord bot token (required to enable Discord adapter) |
 | `TURNSTONE_DISCORD_GUILD` | `0` | Restrict to a single Discord guild (0 = all guilds) |
 
-The channel service runs in the `production` profile. When `TURNSTONE_DISCORD_TOKEN` is set, the Discord adapter connects to the Discord Gateway and routes messages through Redis MQ to the bridge and server. See [Channel Integrations](channels.md) for full setup instructions including Discord application creation and user account linking.
-
-### Simulator
-
-| Variable | Default | Description |
-|----------|---------|-------------|
-| `SIM_NODES` | `100` | Number of simulated nodes |
-| `SIM_SCENARIO` | `steady` | Scenario: `steady`, `burst`, `node_failure`, `directed`, `lifecycle` |
-| `SIM_DURATION` | `60` | Duration in seconds |
-| `SIM_MPS` | `5.0` | Messages per second (steady scenario) |
-| `SIM_LOG_LEVEL` | `INFO` | Log verbosity |
-| `SIM_SEED` | — | Random seed for reproducibility |
-| `SIM_METRICS_FILE` | — | Write JSON report to file |
+The channel service runs in the `production` profile. When `TURNSTONE_DISCORD_TOKEN` is set, the Discord adapter connects to the Discord Gateway and routes messages to the server via HTTP. See [Channel Integrations](channels.md) for full setup instructions including Discord application creation and user account linking.
 
 ## Scaling
 
-For multi-node testing, use the `cluster` profile which provides 10 dedicated server+bridge pairs with unique node IDs (`node-1` through `node-10`), resource limits, and shared PostgreSQL:
+For multi-node testing, use the `cluster` profile which provides 10 server instances with unique node IDs (`node-1` through `node-10`), resource limits, and shared PostgreSQL:
 
 ```bash
 POSTGRES_PASSWORD=secret docker compose --profile cluster up
 ```
 
-The default `server` and `bridge` also run alongside the cluster nodes (11 total). All nodes are accessible via the console dashboard at `:8090`.
+The default `server` also runs alongside the cluster nodes (11 total). All nodes are accessible via the console dashboard at `:8090`.
 
 For production clusters beyond ~50 nodes, add PgBouncer between turnstone services and PostgreSQL. See [PgBouncer Connection Pooling](pgbouncer.md) for Docker Compose and Helm configuration.
 
@@ -160,7 +123,6 @@ For production clusters beyond ~50 nodes, add PgBouncer between turnstone servic
 
 | Volume | Mount | Purpose |
 |--------|-------|---------|
-| `redis-data` | `/data` | Redis persistence |
 | `turnstone-data` | `/data` | SQLite database (`.turnstone.db`) |
 
 ## Building
@@ -175,7 +137,7 @@ docker compose build
 docker compose build --no-cache
 ```
 
-All entry points are installed in a single image: `turnstone-server`, `turnstone-bridge`, `turnstone-console`, `turnstone-channel`, `turnstone-admin`, `turnstone-sim`, `turnstone-eval`.
+All entry points are installed in a single image: `turnstone-server`, `turnstone-console`, `turnstone-channel`, `turnstone-admin`, `turnstone-eval`.
 
 ## Cleanup
 

docs/judge.md

@@ -379,7 +379,7 @@ emitted to the frontend:
 ```
 
 The web UI renders this as an inline warning after the tool result. The CLI
-shows a colored terminal warning. The MQ bridge forwards it as an
+shows a colored terminal warning. The server forwards it as an
 `OutputWarningEvent` for console subscribers.
 
 Assessments are persisted to the `output_assessments` table for v2

docs/oidc.md

@@ -38,7 +38,7 @@ are set.
 | `TURNSTONE_OIDC_PROVIDER_NAME` | No | `SSO` | Display name for the login button (e.g. "Google", "Okta") |
 | `TURNSTONE_OIDC_ROLE_CLAIM` | No | — | ID token claim containing role/group values (see [Role Mapping](#role-mapping)) |
 | `TURNSTONE_OIDC_ROLE_MAP` | No | — | Mapping from claim values to Turnstone role IDs (see [Role Mapping](#role-mapping)) |
-| `TURNSTONE_OIDC_PASSWORD_ENABLED` | No | `true` | Set to `false` to hide the password form and block all username/password logins (including admin). API tokens and config-file tokens still work. |
+| `TURNSTONE_OIDC_PASSWORD_ENABLED` | No | `true` | Set to `false` to hide the password form and block all username/password logins (including admin). API tokens continue to work. |
 | `TURNSTONE_OIDC_REDIRECT_BASE` | No | — | Externally-reachable origin for the OIDC redirect URI (e.g. `https://app.example.com`). Recommended when running behind a reverse proxy. When unset, derived from the request Host header. |
 
 OIDC is enabled when all three required fields (issuer, client ID, client
@@ -246,10 +246,10 @@ password) before OIDC is enabled. The setup wizard always works
 regardless of this setting because it is only available when zero users
 exist in the database.
 
-API token login (`POST /v1/api/auth/login` with a `ts_` token) and
-config-file tokens (`Authorization: Bearer tok_xxx`) continue to work
-regardless of this setting. OIDC-only mode affects password-based
-authentication only.
+API token login (`POST /v1/api/auth/login` with a `ts_` token)
+continues to work regardless of this setting. JWTs and API tokens are
+the supported authentication methods. OIDC-only mode affects
+password-based authentication only.
 
 ---
 

docs/openshell.md

@@ -98,7 +98,6 @@ cannot bypass the proxy.
 | `skills_registry` | `skills.sh` | Skill discovery |
 | `github_api` | `api.github.com` (read-only L7), `raw.githubusercontent.com` | Skill fetch, GitHub API |
 | `mcp_registry` | `registry.modelcontextprotocol.io` (read-only L7) | MCP server discovery |
-| `redis` | `127.0.0.1:6379` | Message queue |
 | `web_fetch_common` | readthedocs, python docs, GitHub Pages, PyPI, npm, Stack Overflow, Wikipedia | Curated web_fetch domains |
 | `bash_network_tools` | Same as `web_fetch_common` | curl/wget from bash tool |
 | `package_registries` | `pypi.org`, `files.pythonhosted.org` | pip/uv package installs |
@@ -283,6 +282,5 @@ For production deployments:
 - [ ] Review and trim `web_fetch_common` domains to your actual needs
 - [ ] Remove `package_registries` policy if pip/uv installs are not needed
 - [ ] Add your OIDC provider endpoint if using SSO
-- [ ] Set Redis `allowed_ips` to your actual Redis host if not localhost
 - [ ] Consider removing `bash_network_tools` entirely if bash should not have
       network access

docs/pgbouncer.md

@@ -1,7 +1,7 @@
 # PgBouncer Connection Pooling
 
 Turnstone cluster deployments share a single PostgreSQL instance across
-all server nodes, bridge processes, and the console. Each process
+all server nodes and the console. Each process
 maintains a small connection pool (2 base + 3 overflow = 5 max). At
 scale this adds up — a 100-node cluster opens up to 500 connections,
 and a 1000-node cluster up to 5,000.

docs/releasing.md

@@ -0,0 +1,80 @@
+# Release Process
+
+Turnstone uses two parallel release tracks published from a single PyPI package.
+
+## Release Tracks
+
+| Track | Versions | Branch | Docker tags | PyPI install |
+|-------|----------|--------|-------------|--------------|
+| **Stable** | `1.0.0`, `1.0.1` | `stable/1.0` | `:1.0.1`, `:1.0`, `:stable`, `:latest` | `pip install turnstone` |
+| **Experimental** | `1.1.0a1`, `1.1.0a2` | `main` | `:1.1.0a1`, `:experimental` | `pip install turnstone --pre` |
+
+- **Stable** receives bugfixes only. Production-grade.
+- **Experimental** receives new features. May be rough around the edges.
+- When experimental matures, it is promoted to stable. The previous stable branch stops receiving patches.
+
+## Version Scheme
+
+[PEP 440](https://peps.python.org/pep-0440/) pre-release suffixes on a single package:
+
+- `1.0.0` — stable release
+- `1.1.0a1` — alpha (experimental)
+- `1.1.0b1` — beta (experimental, more stable)
+- `1.1.0rc1` — release candidate (experimental, nearly stable)
+- `1.1.0` — promoted to stable
+
+## Releasing an Experimental Version (from main)
+
+```bash
+scripts/release.sh 1.1.0a2 --push
+```
+
+This bumps `pyproject.toml` + `turnstone/__init__.py`, regenerates `uv.lock`, commits, tags `v1.1.0a2`, and pushes. CI runs, then publish + Docker workflows fire automatically.
+
+## Releasing a Stable Patch (from stable/X.Y)
+
+```bash
+git checkout stable/1.0
+git cherry-pick <commit-hash>    # bugfix from main
+scripts/release.sh 1.0.2 --push
+```
+
+## Promoting Experimental to Stable
+
+When `main` is ready for a stable release:
+
+```bash
+# 1. Tag the stable release on main
+scripts/release.sh 1.1.0 --push
+
+# 2. Create the stable maintenance branch from that tag
+git branch stable/1.1 v1.1.0
+git push origin stable/1.1
+
+# 3. Start the next experimental cycle on main
+scripts/release.sh 1.2.0a1 --push
+```
+
+The previous `stable/1.0` branch stops receiving patches at this point.
+
+## CI/CD Pipeline
+
+All releases are gated on CI success:
+
+1. `git push` with `v*` tag triggers **CI** (lint, typecheck, test, test-postgres, lock-check, security audit)
+2. On CI success, **Publish to PyPI** fires via `workflow_run`
+3. On CI success, **Publish Docker Image** fires via `workflow_run`
+
+Pre-release tags (`a`, `b`, `rc` suffixes) produce:
+- PyPI: pre-release version (not installed by default)
+- GitHub Release: marked as pre-release
+- Docker: `:experimental` alias + exact version tag
+
+Stable tags produce:
+- PyPI: stable version (default `pip install`)
+- GitHub Release: full release
+- Docker: `:stable`, `:latest`, `:X.Y`, `:X.Y.Z` tags
+
+## Dependency Updates
+
+Renovate targets `main` (experimental) only. Stable branches receive manual dependency updates via cherry-pick when security-relevant.

docs/sdk.md

@@ -332,6 +332,6 @@ client.login(token="ts_abc123...")
 - `client.logout()` clears the stored JWT from the client.
 - If a request returns 401, the SDK raises `TurnstoneAPIError` — the caller is responsible for re-authenticating.
 
-### Backward Compatibility
+### Token Types
 
-The config-file token (`TURNSTONE_AUTH_TOKEN`) still works as a simple Bearer token for environments that do not use the user/JWT system. When the server receives a non-JWT Bearer token, it falls back to the legacy token check.
+The SDK accepts any Bearer token — JWTs (from `ServiceTokenManager` or login) and API tokens (`ts_` prefix) are both supported. Use `token_factory` for auto-rotating JWTs or a static `token` for API tokens.

docs/security.md

@@ -8,23 +8,6 @@ credentials while individual server nodes validate JWTs locally.
 
 ## Token Types
 
-### Config-file tokens
-
-Static tokens defined in `config.toml` or the `TURNSTONE_AUTH_TOKEN`
-environment variable. Validated in-memory using `hmac.compare_digest`
-(timing-safe). Each token maps to a role that determines its scopes.
-
-```toml
-[[auth.tokens]]
-value = "tok_legacy"
-role = "full"     # full → {read, write, approve}
-```
-
-Role mappings: `"read"` → `{read}`, `"full"` → `{read, write, approve}`.
-
-Config tokens are sent directly as `Authorization: Bearer tok_legacy`
-on every request. No JWT exchange is needed.
-
 ### API tokens
 
 Database-backed tokens prefixed with `ts_`. Created via the admin CLI
@@ -149,15 +132,6 @@ The API token is hashed, looked up in the database, and exchanged for a
 JWT with the token's scopes. This is the recommended flow for SDKs and
 automated clients that need cookie-based sessions.
 
-### Config-file tokens (direct)
-
-Config tokens are validated per-request via `hmac.compare_digest`. No
-login exchange is needed — include the token as a `Bearer` header:
-
-```
-Authorization: Bearer tok_legacy
-```
-
 ### First-time setup
 
 When no users exist in the database:
@@ -276,7 +250,7 @@ Setting `TURNSTONE_OIDC_PASSWORD_ENABLED=false` hides the password
 form on the login page and blocks password-based login at the API
 level. The setup wizard always works regardless of this setting — the
 first admin user is created with a password before OIDC is relevant.
-API tokens and config-file tokens are unaffected by this setting.
+API tokens are unaffected by this setting.
 
 #### Known limitations
 
@@ -297,8 +271,6 @@ and classifies the token:
 
 1. **Contains `.`** → JWT → validate HS256 signature and expiry
 2. **Starts with `ts_`** → API token → SHA-256 hash, database lookup
-3. **Otherwise** → config-file token → `hmac.compare_digest` against
-   each configured token
 
 If a session cookie is present and no `Authorization` header is sent,
 the cookie value is treated as a JWT (step 1).
@@ -332,17 +304,10 @@ deployments.
 | Signing secret | `[auth] jwt_secret` | `TURNSTONE_JWT_SECRET` | Auto-generated ephemeral (warning logged) |
 | Expiry | `[auth] jwt_expiry_hours` | — | 24 hours |
 | Algorithm | — | — | HS256 (not configurable) |
-| Minimum secret length | — | — | 32 characters (warning if shorter) |
+| Minimum secret length | — | — | 32 characters (exits if shorter) |
 
-All service nodes that need to validate JWTs must share the same signing
-secret. If no secret is configured, an ephemeral key is generated at
-startup and a warning is logged — JWTs will not survive restarts or work
-across nodes.
-
-The bridge and console **require** `TURNSTONE_JWT_SECRET` when no
-`--auth-token` is provided. They exit with an error if the secret is
-missing, since ephemeral secrets would silently break inter-service
-communication.
+All services require `TURNSTONE_JWT_SECRET` and exit at startup if it is
+missing or shorter than 32 characters.
 
 ---
 
@@ -443,16 +408,15 @@ Console (cluster-wide)              Server (per-node)
 ┌──────────────────────┐           ┌──────────────────────┐
 │ User/Token CRUD (DB) │           │ JWT validation only  │
 │ Login: creds → JWT   │           │ (shared signing key) │
-│ Admin API endpoints  │           │ Config tokens: hmac  │
-│ Storage: users,      │           │ No auth DB needed    │
+│ Admin API endpoints  │           │ No auth DB needed    │
+│ Storage: users,      │           │                      │
 │   api_tokens tables  │           │                      │
 └──────────────────────┘           └──────────────────────┘
 ```
 
 The console owns the credential database and handles all user/token
 CRUD.  Individual server nodes only need the JWT signing secret to
-validate session tokens.  Config-file tokens are validated locally
-without any database.
+validate session tokens.
 
 ### Proxy auth forwarding
 
@@ -479,35 +443,30 @@ distinguish proxied requests from direct logins in audit logs.
 
 When no user context is available (auth disabled, or internal requests),
 the proxy falls back to a `ServiceTokenManager` with service identity
-`console-proxy` and full scopes.  If `--auth-token` is provided, that
-static token is used as a final fallback.
+`console-proxy` and full scopes.
 
 ### Service-to-service authentication
 
-The bridge and console collector use `ServiceTokenManager` for
-auto-rotating JWTs when communicating with server nodes:
+The console collector uses `ServiceTokenManager` for auto-rotating
+JWTs when communicating with server nodes:
 
 | Service | Identity | Scope | Audience | Purpose |
 |---------|----------|-------|----------|---------|
-| Bridge | `bridge` | `approve` | `turnstone-server` | Tool approval proxy, message relay |
 | Console collector | `console-collector` | `read` | `turnstone-server` | Node health polling |
 | Console proxy (fallback) | `console-proxy` | `approve` | `turnstone-server` | Proxied API calls when no user context |
 | Channel notify | `system` | `write` | `turnstone-channel` | Notification delivery to channel gateway |
 
 Service tokens use 1-hour expiry with automatic refresh via
-`ServiceTokenManager`.  The bridge injects auth headers per-request via
-httpx event hooks to ensure rotated tokens are picked up on SSE
-reconnects.
+`ServiceTokenManager`.
 
 ### User identity in MQ-dispatched workstreams
 
-When the console creates a workstream via MQ (the normal path), the
-authenticated user's `user_id` is embedded in the
-`CreateWorkstreamMessage`.  The bridge forwards this `user_id` in the
-HTTP payload when calling the server's `POST /v1/api/workstreams/new`.
-The server accepts a `user_id` from the request body **only when the
-caller is a trusted service** — identified by `token_source` matching
-`bridge`, `console-proxy`, or `console`.  Regular API callers cannot
+When the console creates a workstream (the normal path), the
+authenticated user's `user_id` is forwarded in the HTTP payload when
+calling the server's `POST /v1/api/workstreams/new`.  The server
+accepts a `user_id` from the request body **only when the caller is a
+trusted service** — identified by `token_source` matching
+`console-proxy` or `console`.  Regular API callers cannot
 override `user_id`; the server always uses their JWT identity.
 
 Note that the channel gateway uses a distinct JWT audience
@@ -523,22 +482,17 @@ channel gateway endpoint, and vice versa.
 
 ```toml
 [auth]
-enabled = true
 jwt_secret = "your-secret-key-here"
 jwt_expiry_hours = 24
-
-[[auth.tokens]]
-value = "tok_legacy"
-role = "full"
 ```
 
 ### Environment variables
 
+Auth is always enabled. `TURNSTONE_JWT_SECRET` is required.
+
 | Variable | Description |
 |----------|-------------|
-| `TURNSTONE_AUTH_ENABLED=1` | Enable authentication |
-| `TURNSTONE_AUTH_TOKEN=tok_xxx` | Register a config-file token with `full` access |
-| `TURNSTONE_JWT_SECRET=xxx` | JWT signing secret (must match across nodes) |
+| `TURNSTONE_JWT_SECRET=xxx` | JWT signing secret (required, must match across nodes) |
 | `TURNSTONE_CORS_ORIGINS=` | CORS allowed origins (comma-separated; empty = same-origin only) |
 
 ---
@@ -576,8 +530,6 @@ and browsers enforce same-origin policy.
 
 ## Security Properties
 
-- **Timing-safe comparison** for config-file tokens via
-  `hmac.compare_digest` — no timing side-channel.
 - **Hash-based lookup** for API tokens — the database stores only
   SHA-256 hashes, eliminating timing attacks on token comparison.
 - **Local JWT validation** — no network call or database query needed

docs/settings.md

@@ -27,7 +27,7 @@ Settings resolution differs between entry points:
 
 | Entry point | Chain |
 |-------------|-------|
-| **Server** (`turnstone-server`, `turnstone-bridge`) | CLI flag > ConfigStore > registry default |
+| **Server** (`turnstone-server`) | CLI flag > ConfigStore > registry default |
 | **CLI** (`turnstone`) | CLI flag > config.toml > argparse default |
 
 The server's `apply_config()` ignores config.toml sections that overlap with
@@ -46,9 +46,7 @@ connection, Redis, auth secrets, server bind address). These stay in
 |----------|---------|-------|
 | API credentials | `[api]` | config.toml / env |
 | Database | `[database]` | config.toml / env |
-| Redis | `[redis]` | config.toml / env |
 | Auth | `[auth]` | config.toml / env |
-| Bridge identity | `[bridge]` | config.toml / env |
 | Console bind | `[console]` | config.toml / env |
 
 **ConfigStore settings** (48 settings) are loaded from the database after

docs/simulator.md

@@ -1,204 +0,0 @@
-# Cluster Simulator
-
-The simulator (`turnstone-sim`) creates lightweight simulated nodes that talk to a real Redis instance using the standard turnstone protocol. External observers — `TurnstoneClient`, `turnstone-console`, real bridges — see identical behavior. No LLM backend is needed.
-
-## Quick Start
-
-```bash
-pip install turnstone[sim]
-
-# 10 nodes, steady load, 60 seconds
-turnstone-sim --nodes 10 --scenario steady --duration 60 --mps 5
-
-# 100 nodes via Docker
-docker compose --profile sim up redis console sim
-```
-
-## How It Works
-
-Each simulated node is an asyncio coroutine (not a thread or process), so 1000 nodes run efficiently on a single event loop. The simulator:
-
-1. Registers nodes via Redis heartbeats (same keys as real bridges)
-2. Accepts messages from per-node and shared inbound queues
-3. Simulates LLM responses with configurable latency and token generation
-4. Simulates tool execution with configurable latency and failure rates
-5. Publishes real protocol events (`ContentEvent`, `StateChangeEvent`, `TurnCompleteEvent`, etc.)
-6. Reports latency, throughput, and utilization metrics at completion
-
-```
-TurnstoneClient → Redis Queue → SimNode → Redis Pub/Sub → TurnstoneClient
-                                  ↓
-                            turnstone-console (cluster dashboard)
-```
-
-## Scenarios
-
-| Scenario | Description |
-|----------|-------------|
-| `steady` | Inject messages at a constant rate (`--mps`) for `--duration` seconds |
-| `burst` | Push `--burst-size` messages instantly, then wait for completion |
-| `node_failure` | Steady load + periodically kill nodes to test redistribution |
-| `directed` | Send messages to specific nodes via `target_node` routing |
-| `lifecycle` | Create, use, and close workstreams across nodes |
-
-## CLI Reference
-
-```
-turnstone-sim [options]
-```
-
-### Cluster
-
-| Flag | Default | Description |
-|------|---------|-------------|
-| `--nodes` | `10` | Number of simulated nodes |
-
-### Scenario
-
-| Flag | Default | Description |
-|------|---------|-------------|
-| `--scenario` | `steady` | Scenario name |
-| `--duration` | `60` | Duration in seconds |
-| `--mps` | `5.0` | Messages per second (steady) |
-| `--burst-size` | `100` | Messages to send (burst) |
-| `--node-kill-interval` | `15` | Seconds between kills (node_failure) |
-| `--node-kill-count` | `1` | Nodes per kill cycle |
-
-### Simulation
-
-| Flag | Default | Description |
-|------|---------|-------------|
-| `--llm-latency` | `2.0` | Mean LLM response latency (seconds) |
-| `--tool-latency` | `0.5` | Mean tool execution latency (seconds) |
-| `--tool-failure-rate` | `0.02` | Tool failure probability (0.0–1.0) |
-| `--seed` | — | Random seed for reproducibility |
-
-### Redis
-
-| Flag | Default | Description |
-|------|---------|-------------|
-| `--redis-host` | `localhost` | Redis host |
-| `--redis-port` | `6379` | Redis port |
-| `--redis-password` | — | Redis password |
-| `--prefix` | `turnstone` | Redis key prefix |
-
-### Output
-
-| Flag | Default | Description |
-|------|---------|-------------|
-| `--metrics-file` | — | Write JSON report to file |
-| `--log-level` | `INFO` | Log verbosity |
-
-## Example: Load Testing
-
-```bash
-# 100 nodes, high throughput, 2 minutes
-turnstone-sim --nodes 100 --scenario steady --duration 120 --mps 50
-
-# Burst of 500 messages across 50 nodes
-turnstone-sim --nodes 50 --scenario burst --burst-size 500 --duration 60
-
-# Node failure resilience (kill 2 nodes every 10 seconds)
-turnstone-sim --nodes 20 --scenario node_failure --duration 120 \
-  --node-kill-interval 10 --node-kill-count 2
-
-# Fast simulation (low latency, no failures)
-turnstone-sim --nodes 10 --scenario steady --duration 30 \
-  --llm-latency 0.1 --tool-latency 0.05 --tool-failure-rate 0 --mps 10
-```
-
-## Metrics Report
-
-The simulator prints a summary at completion:
-
-```
-============================================================
-  SIMULATION REPORT
-============================================================
-  Scenario:       steady
-  Nodes:          100
-  Duration:       60.2s
-  Total turns:    295
-  Total errors:   5
-  Node kills:     0
-------------------------------------------------------------
-  THROUGHPUT
-    Messages/sec: 4.97
-    Turns/sec:    4.89
-------------------------------------------------------------
-  LATENCY (seconds)
-    p50:          3.21
-    p90:          5.44
-    p99:          8.12
-    mean:         3.56
-    max:          12.1
-------------------------------------------------------------
-  UTILIZATION
-    Mean ws/node: 2.3
-    Max ws/node:  8
-    Idle nodes:   12
-============================================================
-```
-
-Use `--metrics-file report.json` to write the full report as JSON.
-
-## Console Integration
-
-The simulator's nodes appear in `turnstone-console` exactly like real nodes. Run them together to see the dashboard populate with simulated workstreams:
-
-```bash
-# Terminal 1: start Redis and console
-docker compose up redis console
-
-# Terminal 2: run simulator
-docker compose --profile sim up sim
-```
-
-Or all at once:
-
-```bash
-SIM_NODES=50 SIM_DURATION=120 docker compose --profile sim up redis console sim
-```
-
-Open http://localhost:8090 to see simulated nodes, workstream states, token counts, and load bars updating in real time.
-
-## Architecture
-
-> See also: [Simulator Architecture diagram](diagrams/png/10-simulator-architecture.png)
-
-```
-turnstone/sim/
-├── __init__.py     # Public API: SimCluster, SimConfig
-├── config.py       # SimConfig — all simulation parameters
-├── engine.py       # SimEngine — LLM + tool execution simulation
-├── node.py         # SimNode + SimWorkstream — protocol-compatible node
-├── cluster.py      # SimCluster + InboundDispatcher + PooledBroker
-├── scenario.py     # 5 scenario classes
-├── metrics.py      # MetricsCollector — latency, throughput, utilization
-└── cli.py          # CLI entry point
-```
-
-**Key design:** The `InboundDispatcher` batches ~50 node queues into a single Redis `BLPOP` call, keeping connection count bounded at ~20 regardless of node count. All nodes share a single `ConnectionPool(max_connections=64)`.
-
-## Programmatic Use
-
-```python
-import asyncio
-from turnstone.sim import SimCluster, SimConfig
-
-async def main():
-    config = SimConfig(
-        num_nodes=10,
-        scenario="steady",
-        duration=30,
-        messages_per_second=2.0,
-        llm_latency_mean=0.5,
-    )
-    cluster = SimCluster(config)
-    await cluster.start()
-    await cluster.run_scenario()
-    print(cluster.report())
-    await cluster.stop()
-
-asyncio.run(main())
-```

docs/tls.md

@@ -12,7 +12,7 @@ docker compose -f compose.yaml -f deploy/docker-compose.tls.yml up
 ```
 
 This:
-1. Bootstraps an internal CA and issues certs for Redis/PostgreSQL
+1. Bootstraps an internal CA and issues certs for PostgreSQL
 2. Starts the console with TLS enabled (internal CA + ACME server)
 3. Server nodes auto-provision certs via the console's ACME endpoint
 4. All inter-service communication uses mTLS
@@ -30,9 +30,9 @@ Console (CA + ACME Server)
                   | ACME protocol (auto-approve, no challenge validation)
       +-----------+-----------+
       |           |           |
-  Server(s)    Bridge    Channel GW
-  (auto-cert    (mTLS     (mTLS
-   + renewal)   client)    client)
+  Server(s)       Channel GW
+  (auto-cert       (mTLS
+   + renewal)       client)
 ```
 
 **Two cert paths on the console:**
@@ -57,12 +57,6 @@ Console (CA + ACME Server)
 These are needed before storage is available:
 
 ```toml
-[redis]
-tls = false
-tls_ca = ""      # path to CA cert
-tls_cert = ""    # path to client cert
-tls_key = ""     # path to client key
-
 [database]
 sslmode = "prefer"   # disable, allow, prefer, require, verify-full
 sslrootcert = ""     # path to CA cert
@@ -89,12 +83,11 @@ sslkey = ""          # path to client key
 Create a CA and infrastructure certs without a running console:
 
 ```bash
-# Bootstrap CA + Redis + PostgreSQL certs
-turnstone-admin tls-bootstrap --out /certs --issue redis --issue postgres
+# Bootstrap CA + PostgreSQL certs
+turnstone-admin tls-bootstrap --out /certs --issue postgres
 
 # Output:
 #   /certs/ca.pem              (CA root certificate)
-#   /certs/certs/redis/        (Redis cert + key)
 #   /certs/certs/postgres/     (PostgreSQL cert + key)
 ```
 
@@ -112,7 +105,7 @@ turnstone-admin tls-ca-cert --out ca.pem --console-url http://console:8080
 turnstone-admin tls-issue worker-1.internal --out /certs --console-url http://console:8080
 
 # List issued certs
-turnstone-admin tls-list --console-url http://console:8080 --auth-token $TOKEN
+turnstone-admin tls-list --console-url http://console:8080
 ```
 
 ### Console URL Discovery

docs/tools.md

@@ -593,7 +593,7 @@ current turn and letting it search for them on demand.
 Tool search uses the best available mechanism for each provider:
 
 1. **Anthropic (native)** -- Models that support it receive `defer_loading: true`
-   on deferred tool definitions plus the `tool_search_tool_bm25_20251119` server-side
+   on deferred tool definitions plus the `tool_search_tool_bm25` server-side
    search tool. Anthropic's API handles search and expansion transparently.
 
 2. **OpenAI GPT-5.4+ (native)** -- Models with hosted tool search receive
@@ -690,7 +690,7 @@ that external tools are read-only. However, global overrides such as
 `--skip-permissions` will auto-approve all tools, including MCP tools. The
 interactive "Always" button adds specific tool types to the per-tool auto-approve
 set. The web UI and server use `approval_label` for MCP tools, giving
-per-prompt/per-resource granularity. The CLI and bridge use `func_name`, which
+per-prompt/per-resource granularity. The CLI uses `func_name`, which
 gives per-tool-type granularity (e.g., all `use_prompt` calls).
 
 ### Sub-agent availability

examples/mcp-cluster-ops/README.md

@@ -1,10 +1,14 @@
 # MCP Cluster Ops
 
-An MCP server that exposes tools for executing commands across a [Turnstone](https://github.com/turnstonelabs/turnstone) cluster. Serves as a reference implementation for both MCP server patterns and Turnstone MQ client SDK usage.
+An MCP server that exposes tools for executing commands across a Turnstone cluster. Serves as a reference implementation for both MCP server patterns and Turnstone SDK usage.
 
 ## How it works
 
-This server uses Turnstone's MQ client (`TurnstoneClient`) to dispatch shell commands to specific nodes via Redis. Remote agents execute the command and the raw bash output is captured directly from the `ToolResultEvent` stream — bypassing the costly "agent reads output → re-generates output as completion tokens" round-trip.
+This server uses the Turnstone console SDK (`TurnstoneConsole`) for node discovery and routing, and `TurnstoneServer` for per-node SSE streaming. The dispatch flow for each command is:
+
+1. **Route** — `TurnstoneConsole.route_create_workstream(target_node=..., auto_approve=True)` creates a workstream pinned to the target node via the console's hash-ring routing proxy, returning `ws_id` and `node_url`.
+2. **Execute** — `TurnstoneServer(node_url, token=...)` connects directly to the node's SSE stream using the same `TURNSTONE_API_TOKEN`. `send_and_wait(prompt, ws_id)` runs the command and the raw bash output is captured from the `ToolResultEvent` — bypassing the costly "agent reads output then re-generates output as completion tokens" round-trip.
+3. **Cleanup** — `TurnstoneConsole.route_close(ws_id)` closes the workstream.
 
 Multi-node dispatches run in parallel via `asyncio.gather`, so total wall time is bounded by the slowest node rather than the sum.
 
@@ -19,8 +23,7 @@ Multi-node dispatches run in parallel via `asyncio.gather`, so total wall time i
 
 ## Prerequisites
 
-- A running Turnstone cluster (at least one `turnstone-server` + `turnstone-bridge`)
-- Redis accessible from wherever this MCP server runs
+- A running Turnstone cluster with at least one `turnstone-server` and a `turnstone-console`
 - Python 3.11+
 
 ## Installation
@@ -28,10 +31,6 @@ Multi-node dispatches run in parallel via `asyncio.gather`, so total wall time i
 ```bash
 # From the turnstone repo root:
 pip install -e ./examples/mcp-cluster-ops
-
-# Or install turnstone with MQ support first, then the example:
-pip install -e ".[mq]"
-pip install -e ./examples/mcp-cluster-ops
 ```
 
 ## Configuration
@@ -40,9 +39,8 @@ pip install -e ./examples/mcp-cluster-ops
 
 | Variable | Default | Description |
 |----------|---------|-------------|
-| `REDIS_HOST` | `localhost` | Redis host |
-| `REDIS_PORT` | `6379` | Redis port |
-| `REDIS_PASSWORD` | _(none)_ | Redis password (use env vars, not config files) |
+| `TURNSTONE_CONSOLE_URL` | `http://localhost:8090` | Console URL for node discovery and routing |
+| `TURNSTONE_API_TOKEN` | _(none)_ | API token / JWT for authentication |
 | `MCP_CLUSTER_OPS_TIMEOUT` | `120` | Default command timeout (seconds, clamped 5-3600) |
 | `MCP_CLUSTER_OPS_MAX_OUTPUT` | `8192` | Max output bytes per node (0 = unlimited) |
 | `MCP_CLUSTER_OPS_MAX_NODES` | `32` | Max concurrent node dispatches |
@@ -57,7 +55,7 @@ pip install -e ./examples/mcp-cluster-ops
 command = "mcp-cluster-ops"
 
 [mcp.servers.cluster-ops.env]
-REDIS_HOST = "redis.example.com"
+TURNSTONE_CONSOLE_URL = "http://console.example.com:8090"
 ```
 
 **JSON** (via `--mcp-config`):
@@ -68,7 +66,7 @@ REDIS_HOST = "redis.example.com"
     "cluster-ops": {
       "command": "mcp-cluster-ops",
       "env": {
-        "REDIS_HOST": "redis.example.com"
+        "TURNSTONE_CONSOLE_URL": "http://console.example.com:8090"
       }
     }
   }
@@ -90,10 +88,6 @@ node-2: /dev/sda1  500G  410G   90G  82%  /
 node-3: /dev/sda1  1.0T  200G  800G  20%  /
 ```
 
-## Why MQ client instead of HTTP SDK?
-
-The HTTP SDK (`TurnstoneServer`) talks to a single server instance. The MQ client (`TurnstoneClient`) routes through Redis with `target_node` support, which is the entire point of cross-node cluster operations.
-
 ## Security Considerations
 
 **This MCP server grants the calling agent shell access to cluster nodes.**
@@ -104,8 +98,8 @@ The HTTP SDK (`TurnstoneServer`) talks to a single server instance. The MQ clien
   is returned through the MCP tool result and becomes part of the LLM context.
 - The security boundary is at the MCP host layer -- use Turnstone's tool
   policy system to restrict which agents can invoke these tools.
-- Set `REDIS_PASSWORD` via your environment or a secrets manager -- avoid
-  hardcoding passwords in config files.
+- Set `TURNSTONE_API_TOKEN` via your environment or a secrets manager -- avoid
+  hardcoding tokens in config files.
 
 ## Development
 

examples/mcp-cluster-ops/mcp_cluster_ops/server.py

@@ -1,7 +1,8 @@
 """MCP server for Turnstone cluster operations.
 
 Exposes tools to execute commands on specific nodes in a Turnstone cluster.
-Uses the MQ client (``TurnstoneClient``) for direct node targeting via Redis.
+Uses the SDK console client (``TurnstoneConsole``) for node discovery and
+routing, and ``TurnstoneServer`` for per-node SSE streaming.
 
 Usage::
 
@@ -14,22 +15,20 @@ Configure in ``~/.config/turnstone/config.toml``::
     command = "mcp-cluster-ops"
 
     [mcp.servers.cluster-ops.env]
-    REDIS_HOST = "redis.example.com"
+    TURNSTONE_CONSOLE_URL = "http://localhost:8090"
 
 Environment variables
 ---------------------
-REDIS_HOST              Redis host (default: localhost)
-REDIS_PORT              Redis port (default: 6379)
-REDIS_PASSWORD          Redis password (default: none)
+TURNSTONE_CONSOLE_URL       Console URL (default: http://localhost:8090)
+TURNSTONE_API_TOKEN         API token / JWT for authentication (default: none)
 MCP_CLUSTER_OPS_TIMEOUT     Default command timeout in seconds (default: 120)
 MCP_CLUSTER_OPS_MAX_OUTPUT  Max output bytes per node (default: 8192, 0=unlimited)
 
 Performance notes
 -----------------
 Remote agents are told to reply with only "ok" or "failed" — the raw bash
-output is captured directly from the ToolResultEvent that already flows
-through Redis, bypassing the costly "agent reads output then re-generates
-output as completion tokens" round-trip.
+output is captured directly from the ToolResultEvent, bypassing the costly
+"agent reads output then re-generates output as completion tokens" round-trip.
 
 All multi-node dispatches run in parallel via ``asyncio.gather`` so total
 wall time is bounded by the slowest node, not the sum of all nodes.
@@ -45,7 +44,7 @@ from contextlib import asynccontextmanager
 from typing import TYPE_CHECKING, Any
 
 from mcp.server.fastmcp import Context, FastMCP
-from turnstone.mq.client import TurnResult, TurnstoneClient
+from turnstone.sdk import TurnResult, TurnstoneConsole, TurnstoneServer
 
 if TYPE_CHECKING:
     from collections.abc import AsyncIterator
@@ -68,20 +67,12 @@ _MAX_TIMEOUT = 3600
 # ---------------------------------------------------------------------------
 
 
-def _redis_kwargs() -> dict[str, Any]:
-    """Build Redis connection kwargs from environment variables.
-
-    Follows the same env var convention as ``turnstone.mq.broker.add_redis_args``:
-    ``REDIS_HOST``, ``REDIS_PORT``, ``REDIS_PASSWORD``.
-    """
-    kwargs: dict[str, Any] = {"host": os.environ.get("REDIS_HOST", "localhost")}
-    port = os.environ.get("REDIS_PORT")
-    if port is not None:
-        kwargs["port"] = int(port)
-    password = os.environ.get("REDIS_PASSWORD")
-    if password:
-        kwargs["password"] = password
-    return kwargs
+def _console_kwargs() -> dict[str, Any]:
+    """Build TurnstoneConsole connection kwargs from environment variables."""
+    return {
+        "base_url": os.environ.get("TURNSTONE_CONSOLE_URL", "http://localhost:8090"),
+        "token": os.environ.get("TURNSTONE_API_TOKEN", ""),
+    }
 
 
 def _exec_prompt(command: str) -> str:
@@ -148,6 +139,11 @@ def _validate_command(command: str) -> str | None:
     return None
 
 
+def _extract_node_ids(nodes: list[dict[str, Any]]) -> list[str]:
+    """Extract unique, non-empty node IDs from a list of node dicts."""
+    return list(dict.fromkeys(n["node_id"].strip() for n in nodes if n.get("node_id", "").strip()))
+
+
 def _format_node_result(
     node_id: str,
     result: TurnResult,
@@ -172,12 +168,12 @@ def _format_node_result(
 
 
 # ---------------------------------------------------------------------------
-# Core dispatch functions (testable with mocked TurnstoneClient)
+# Core dispatch functions (testable with mocked SDK clients)
 # ---------------------------------------------------------------------------
 
 
 def _exec_on_node_sync(
-    redis_kw: dict[str, Any],
+    console_kw: dict[str, Any],
     node_id: str,
     command: str,
     timeout: float,
@@ -185,22 +181,35 @@ def _exec_on_node_sync(
     """Dispatch *command* to *node_id* and block until complete.
 
     Runs inside ``asyncio.to_thread`` so it does not block the event loop.
-    Each call creates its own ``TurnstoneClient`` to avoid Redis pub/sub
-    subscription conflicts between concurrent dispatches.
+
+    Flow:
+      1. Create a workstream on the target node via the console routing proxy
+      2. Connect directly to the node's SSE stream to send + collect output
+      3. Close the workstream via the routing proxy
     """
     prompt = _exec_prompt(command)
-    with TurnstoneClient(**redis_kw) as client:
-        result = client.send_and_wait(
-            message=prompt,
-            target_node=node_id,
-            auto_approve=True,
-            timeout=timeout,
-        )
+    ws_id = ""
+    with TurnstoneConsole(**console_kw) as console:
+        try:
+            route_resp = console.route_create_workstream(
+                target_node=node_id,
+                auto_approve=True,
+            )
+            ws_id = route_resp["ws_id"]
+            node_url: str = route_resp["node_url"]
+            with TurnstoneServer(
+                base_url=node_url,
+                token=console_kw["token"],
+            ) as server:
+                result = server.send_and_wait(prompt, ws_id, timeout=timeout)
+        finally:
+            if ws_id:
+                console.route_close(ws_id)
     return node_id, result
 
 
 async def _dispatch_parallel(
-    redis_kw: dict[str, Any],
+    console_kw: dict[str, Any],
     node_ids: list[str],
     command: str,
     timeout: float,
@@ -211,7 +220,7 @@ async def _dispatch_parallel(
     Total wall time is bounded by the slowest node.
     """
     tasks = [
-        asyncio.to_thread(_exec_on_node_sync, redis_kw, nid, command, timeout) for nid in node_ids
+        asyncio.to_thread(_exec_on_node_sync, console_kw, nid, command, timeout) for nid in node_ids
     ]
     outcomes = await asyncio.gather(*tasks, return_exceptions=True)
 
@@ -227,16 +236,22 @@ async def _dispatch_parallel(
     return results
 
 
-def _list_nodes_sync(redis_kw: dict[str, Any]) -> list[dict[str, Any]]:
-    """List active cluster nodes (blocking)."""
-    with TurnstoneClient(**redis_kw) as client:
-        nodes: list[dict[str, Any]] = client.list_nodes()
-        return nodes
+def _list_nodes_sync(console_kw: dict[str, Any]) -> list[dict[str, Any]]:
+    """List active cluster nodes (blocking), paginating if needed."""
+    page_size = 100
+    nodes: list[dict[str, Any]] = []
+    with TurnstoneConsole(**console_kw) as console:
+        while True:
+            resp = console.nodes(limit=page_size, offset=len(nodes))
+            nodes.extend(n.model_dump() for n in resp.nodes)
+            if len(nodes) >= resp.total or not resp.nodes:
+                break
+    return nodes
 
 
-async def _list_nodes_impl(redis_kw: dict[str, Any]) -> list[dict[str, Any]]:
+async def _list_nodes_impl(console_kw: dict[str, Any]) -> list[dict[str, Any]]:
     """List active cluster nodes."""
-    return await asyncio.to_thread(_list_nodes_sync, redis_kw)
+    return await asyncio.to_thread(_list_nodes_sync, console_kw)
 
 
 # ---------------------------------------------------------------------------
@@ -246,9 +261,9 @@ async def _list_nodes_impl(redis_kw: dict[str, Any]) -> list[dict[str, Any]]:
 
 @asynccontextmanager
 async def _lifespan(server: FastMCP[dict[str, Any]]) -> AsyncIterator[dict[str, Any]]:
-    """Lifespan context — stores Redis kwargs for tool handlers."""
-    kw = _redis_kwargs()
-    yield {"redis_kwargs": kw}
+    """Lifespan context — stores console connection kwargs for tool handlers."""
+    kw = _console_kwargs()
+    yield {"console_kwargs": kw}
 
 
 mcp = FastMCP(
@@ -270,8 +285,8 @@ async def list_nodes(ctx: Context[Any, Any, Any]) -> str:
     Call this before dispatching work to discover available node IDs.
     Returns a JSON array of node metadata objects.
     """
-    redis_kw: dict[str, Any] = ctx.request_context.lifespan_context["redis_kwargs"]
-    nodes = await _list_nodes_impl(redis_kw)
+    console_kw: dict[str, Any] = ctx.request_context.lifespan_context["console_kwargs"]
+    nodes = await _list_nodes_impl(console_kw)
     return json.dumps(nodes, indent=2)
 
 
@@ -298,13 +313,16 @@ async def run_on_node(
     if cmd_err:
         return json.dumps({"error": cmd_err})
 
-    redis_kw: dict[str, Any] = ctx.request_context.lifespan_context["redis_kwargs"]
+    console_kw: dict[str, Any] = ctx.request_context.lifespan_context["console_kwargs"]
     max_output = _DEFAULT_MAX_OUTPUT
 
     log.info("run_on_node node=%s cmd=%r", node_id, command)
-    _, result = await asyncio.to_thread(
-        _exec_on_node_sync, redis_kw, node_id, command, _clamp_timeout(timeout)
-    )
+    try:
+        _, result = await asyncio.to_thread(
+            _exec_on_node_sync, console_kw, node_id, command, _clamp_timeout(timeout)
+        )
+    except Exception as exc:
+        return json.dumps({"node": node_id, "ok": False, "error": str(exc)}, indent=2)
     formatted = _format_node_result(node_id, result, max_output)
     return json.dumps(formatted, indent=2)
 
@@ -330,7 +348,7 @@ async def run_on_nodes(
     if cmd_err:
         return json.dumps({"error": cmd_err})
 
-    redis_kw: dict[str, Any] = ctx.request_context.lifespan_context["redis_kwargs"]
+    console_kw: dict[str, Any] = ctx.request_context.lifespan_context["console_kwargs"]
     max_output = _DEFAULT_MAX_OUTPUT
 
     clean_ids = list(dict.fromkeys(nid.strip() for nid in node_ids if nid.strip()))
@@ -343,7 +361,7 @@ async def run_on_nodes(
 
     log.info("run_on_nodes nodes=%s cmd=%r", clean_ids, command)
     results = await _dispatch_parallel(
-        redis_kw, clean_ids, command, _clamp_timeout(timeout), max_output
+        console_kw, clean_ids, command, _clamp_timeout(timeout), max_output
     )
     return json.dumps(results, indent=2)
 
@@ -368,18 +386,14 @@ async def run_on_all_nodes(
     if cmd_err:
         return json.dumps({"error": cmd_err})
 
-    redis_kw: dict[str, Any] = ctx.request_context.lifespan_context["redis_kwargs"]
+    console_kw: dict[str, Any] = ctx.request_context.lifespan_context["console_kwargs"]
     max_output = _DEFAULT_MAX_OUTPUT
 
-    nodes = await _list_nodes_impl(redis_kw)
+    nodes = await _list_nodes_impl(console_kw)
     if not nodes:
         return json.dumps({"error": "No active nodes found in cluster"})
 
-    node_ids = list(
-        dict.fromkeys(
-            nid.strip() for n in nodes if (nid := n.get("node_id") or n.get("id")) and nid.strip()
-        )
-    )
+    node_ids = _extract_node_ids(nodes)
     if not node_ids:
         return json.dumps({"error": "No nodes with identifiable IDs found"})
     if len(node_ids) > _MAX_CONCURRENT_NODES:
@@ -388,7 +402,7 @@ async def run_on_all_nodes(
         )
     log.info("run_on_all_nodes nodes=%s cmd=%r", node_ids, command)
     results = await _dispatch_parallel(
-        redis_kw, node_ids, command, _clamp_timeout(timeout), max_output
+        console_kw, node_ids, command, _clamp_timeout(timeout), max_output
     )
     return json.dumps(results, indent=2)
 

examples/mcp-cluster-ops/pyproject.toml

@@ -9,7 +9,7 @@ description = "MCP server for Turnstone cluster operations — reference impleme
 requires-python = ">=3.11"
 license = "BUSL-1.1"
 dependencies = [
-    "turnstone[mq]",
+    "turnstone",
     "mcp>=1.6",
 ]
 
@@ -18,7 +18,7 @@ mcp-cluster-ops = "mcp_cluster_ops.server:main"
 
 [project.optional-dependencies]
 test = ["pytest>=9.0"]
-dev = ["ruff>=0.9", "mypy>=1.14", "types-redis>=4.6"]
+dev = ["ruff>=0.9", "mypy>=1.14"]
 
 [tool.pytest.ini_options]
 testpaths = ["tests"]

examples/mcp-cluster-ops/tests/test_helpers.py

@@ -2,11 +2,12 @@
 
 from __future__ import annotations
 
-from turnstone.mq.client import TurnResult
+from turnstone.sdk import TurnResult
 
 from mcp_cluster_ops.server import (
     _clamp_timeout,
     _exec_prompt,
+    _extract_node_ids,
     _extract_output,
     _format_node_result,
     _truncate,
@@ -190,3 +191,53 @@ class TestClampTimeout:
 
     def test_negative(self):
         assert _clamp_timeout(-1) == 5.0
+
+
+# ---------------------------------------------------------------------------
+# _extract_node_ids
+# ---------------------------------------------------------------------------
+
+
+class TestExtractNodeIds:
+    def test_normal(self):
+        nodes = [
+            {"node_id": "a", "server_url": "http://a:8080"},
+            {"node_id": "b", "server_url": "http://b:8080"},
+        ]
+        assert _extract_node_ids(nodes) == ["a", "b"]
+
+    def test_deduplicates(self):
+        nodes = [
+            {"node_id": "a"},
+            {"node_id": "a"},
+            {"node_id": "b"},
+        ]
+        assert _extract_node_ids(nodes) == ["a", "b"]
+
+    def test_strips_whitespace(self):
+        nodes = [{"node_id": "  a  "}, {"node_id": "b "}]
+        assert _extract_node_ids(nodes) == ["a", "b"]
+
+    def test_skips_empty(self):
+        nodes = [
+            {"node_id": "a"},
+            {"node_id": ""},
+            {"node_id": "  "},
+            {"node_id": "b"},
+        ]
+        assert _extract_node_ids(nodes) == ["a", "b"]
+
+    def test_skips_missing_key(self):
+        nodes = [
+            {"node_id": "a"},
+            {"server_url": "http://orphan:8080"},
+            {"node_id": "b"},
+        ]
+        assert _extract_node_ids(nodes) == ["a", "b"]
+
+    def test_empty_list(self):
+        assert _extract_node_ids([]) == []
+
+    def test_all_empty_ids(self):
+        nodes = [{"node_id": ""}, {"node_id": "  "}]
+        assert _extract_node_ids(nodes) == []

examples/mcp-cluster-ops/tests/test_tools.py

@@ -1,12 +1,14 @@
-"""Tests for MCP tool handlers with mocked TurnstoneClient."""
+"""Tests for MCP tool handlers with mocked SDK clients."""
 
 from __future__ import annotations
 
 import asyncio
+import contextlib
 from typing import Any
 from unittest.mock import MagicMock, patch
 
-from turnstone.mq.client import TurnResult
+import pytest
+from turnstone.sdk import TurnResult
 
 from mcp_cluster_ops.server import (
     _dispatch_parallel,
@@ -14,6 +16,22 @@ from mcp_cluster_ops.server import (
     _list_nodes_impl,
 )
 
+_CONSOLE_KW: dict[str, Any] = {"base_url": "http://localhost:8090", "token": ""}
+_CONSOLE_KW_AUTH: dict[str, Any] = {"base_url": "http://localhost:8090", "token": "tok_test"}
+
+
+def _mock_console_ctx(mock_cls: MagicMock, mock_client: MagicMock) -> None:
+    """Wire up a TurnstoneConsole mock as a context manager."""
+    mock_cls.return_value.__enter__ = MagicMock(return_value=mock_client)
+    mock_cls.return_value.__exit__ = MagicMock(return_value=False)
+
+
+def _mock_server_ctx(mock_cls: MagicMock, mock_server: MagicMock) -> None:
+    """Wire up a TurnstoneServer mock as a context manager."""
+    mock_cls.return_value.__enter__ = MagicMock(return_value=mock_server)
+    mock_cls.return_value.__exit__ = MagicMock(return_value=False)
+
+
 # ---------------------------------------------------------------------------
 # _list_nodes_impl
 # ---------------------------------------------------------------------------
@@ -21,26 +39,71 @@ from mcp_cluster_ops.server import (
 
 class TestListNodesImpl:
     def test_returns_nodes(self):
-        nodes = [{"node_id": "a", "model": "gpt-5"}, {"node_id": "b", "model": "gpt-5"}]
-        with patch("mcp_cluster_ops.server.TurnstoneClient") as mock_cls:
-            mock_client = MagicMock()
-            mock_client.list_nodes.return_value = nodes
-            mock_cls.return_value.__enter__ = MagicMock(return_value=mock_client)
-            mock_cls.return_value.__exit__ = MagicMock(return_value=False)
+        mock_node_a = MagicMock()
+        mock_node_a.model_dump.return_value = {"node_id": "a", "server_url": "http://a:8080"}
+        mock_node_b = MagicMock()
+        mock_node_b.model_dump.return_value = {"node_id": "b", "server_url": "http://b:8080"}
 
-            result = asyncio.run(_list_nodes_impl({"host": "localhost"}))
-            assert result == nodes
+        mock_resp = MagicMock()
+        mock_resp.nodes = [mock_node_a, mock_node_b]
+        mock_resp.total = 2
+
+        with patch("mcp_cluster_ops.server.TurnstoneConsole") as mock_cls:
+            mock_client = MagicMock()
+            mock_client.nodes.return_value = mock_resp
+            _mock_console_ctx(mock_cls, mock_client)
+
+            result = asyncio.run(_list_nodes_impl(_CONSOLE_KW))
+            assert len(result) == 2
+            assert result[0]["node_id"] == "a"
+            assert result[1]["node_id"] == "b"
 
     def test_empty_cluster(self):
-        with patch("mcp_cluster_ops.server.TurnstoneClient") as mock_cls:
-            mock_client = MagicMock()
-            mock_client.list_nodes.return_value = []
-            mock_cls.return_value.__enter__ = MagicMock(return_value=mock_client)
-            mock_cls.return_value.__exit__ = MagicMock(return_value=False)
+        mock_resp = MagicMock()
+        mock_resp.nodes = []
+        mock_resp.total = 0
 
-            result = asyncio.run(_list_nodes_impl({"host": "localhost"}))
+        with patch("mcp_cluster_ops.server.TurnstoneConsole") as mock_cls:
+            mock_client = MagicMock()
+            mock_client.nodes.return_value = mock_resp
+            _mock_console_ctx(mock_cls, mock_client)
+
+            result = asyncio.run(_list_nodes_impl(_CONSOLE_KW))
             assert result == []
 
+    def test_paginates_large_clusters(self):
+        """Clusters with >100 nodes are fetched across multiple pages."""
+
+        def _make_node(nid: str) -> MagicMock:
+            m = MagicMock()
+            m.model_dump.return_value = {"node_id": nid}
+            return m
+
+        page1_nodes = [_make_node(f"n-{i}") for i in range(100)]
+        page2_nodes = [_make_node(f"n-{i}") for i in range(100, 150)]
+
+        page1_resp = MagicMock()
+        page1_resp.nodes = page1_nodes
+        page1_resp.total = 150
+
+        page2_resp = MagicMock()
+        page2_resp.nodes = page2_nodes
+        page2_resp.total = 150
+
+        with patch("mcp_cluster_ops.server.TurnstoneConsole") as mock_cls:
+            mock_client = MagicMock()
+            mock_client.nodes.side_effect = [page1_resp, page2_resp]
+            _mock_console_ctx(mock_cls, mock_client)
+
+            result = asyncio.run(_list_nodes_impl(_CONSOLE_KW))
+            assert len(result) == 150
+            assert result[0]["node_id"] == "n-0"
+            assert result[149]["node_id"] == "n-149"
+            assert mock_client.nodes.call_count == 2
+            # Verify offset was passed correctly
+            mock_client.nodes.assert_any_call(limit=100, offset=0)
+            mock_client.nodes.assert_any_call(limit=100, offset=100)
+
 
 # ---------------------------------------------------------------------------
 # _exec_on_node_sync
@@ -50,35 +113,111 @@ class TestListNodesImpl:
 class TestExecOnNodeSync:
     def test_success(self):
         turn_result = TurnResult(
+            ws_id="ws-123",
             tool_results=[("bash", "hello world")],
         )
-        with patch("mcp_cluster_ops.server.TurnstoneClient") as mock_cls:
-            mock_client = MagicMock()
-            mock_client.send_and_wait.return_value = turn_result
-            mock_cls.return_value.__enter__ = MagicMock(return_value=mock_client)
-            mock_cls.return_value.__exit__ = MagicMock(return_value=False)
+        with (
+            patch("mcp_cluster_ops.server.TurnstoneConsole") as mock_console_cls,
+            patch("mcp_cluster_ops.server.TurnstoneServer") as mock_server_cls,
+        ):
+            mock_console = MagicMock()
+            mock_console.route_create_workstream.return_value = {
+                "ws_id": "ws-123",
+                "node_url": "http://node-1:8080",
+                "node_id": "node-1",
+                "name": "ws-123",
+            }
+            _mock_console_ctx(mock_console_cls, mock_console)
 
-            node_id, result = _exec_on_node_sync(
-                {"host": "localhost"}, "node-1", "echo hello", 60.0
-            )
+            mock_server = MagicMock()
+            mock_server.send_and_wait.return_value = turn_result
+            _mock_server_ctx(mock_server_cls, mock_server)
+
+            node_id, result = _exec_on_node_sync(_CONSOLE_KW_AUTH, "node-1", "echo hello", 60.0)
             assert node_id == "node-1"
             assert result.ok
-            mock_client.send_and_wait.assert_called_once()
-            call_kwargs = mock_client.send_and_wait.call_args
-            assert call_kwargs.kwargs["target_node"] == "node-1"
-            assert call_kwargs.kwargs["auto_approve"] is True
+
+            # Verify console created ws on the right node
+            mock_console.route_create_workstream.assert_called_once_with(
+                target_node="node-1",
+                auto_approve=True,
+            )
+
+            # Verify server connected to the node URL with the token
+            mock_server_cls.assert_called_once_with(
+                base_url="http://node-1:8080",
+                token="tok_test",
+            )
+
+            # Verify send_and_wait got the right ws_id
+            call_kwargs = mock_server.send_and_wait.call_args
+            assert call_kwargs.args[1] == "ws-123"
+
+            # Verify workstream was closed
+            mock_console.route_close.assert_called_once_with("ws-123")
 
     def test_timeout(self):
-        turn_result = TurnResult(timed_out=True)
-        with patch("mcp_cluster_ops.server.TurnstoneClient") as mock_cls:
-            mock_client = MagicMock()
-            mock_client.send_and_wait.return_value = turn_result
-            mock_cls.return_value.__enter__ = MagicMock(return_value=mock_client)
-            mock_cls.return_value.__exit__ = MagicMock(return_value=False)
+        turn_result = TurnResult(ws_id="ws-456", timed_out=True)
+        with (
+            patch("mcp_cluster_ops.server.TurnstoneConsole") as mock_console_cls,
+            patch("mcp_cluster_ops.server.TurnstoneServer") as mock_server_cls,
+        ):
+            mock_console = MagicMock()
+            mock_console.route_create_workstream.return_value = {
+                "ws_id": "ws-456",
+                "node_url": "http://node-1:8080",
+                "node_id": "node-1",
+            }
+            _mock_console_ctx(mock_console_cls, mock_console)
 
-            _, result = _exec_on_node_sync({"host": "localhost"}, "node-1", "sleep 9999", 1.0)
+            mock_server = MagicMock()
+            mock_server.send_and_wait.return_value = turn_result
+            _mock_server_ctx(mock_server_cls, mock_server)
+
+            _, result = _exec_on_node_sync(_CONSOLE_KW, "node-1", "sleep 9999", 1.0)
             assert result.timed_out
             assert not result.ok
+            # Workstream still closed even on timeout
+            mock_console.route_close.assert_called_once_with("ws-456")
+
+    def test_send_failure_still_closes_workstream(self):
+        """Workstream must be closed even if send_and_wait raises."""
+        with (
+            patch("mcp_cluster_ops.server.TurnstoneConsole") as mock_console_cls,
+            patch("mcp_cluster_ops.server.TurnstoneServer") as mock_server_cls,
+        ):
+            mock_console = MagicMock()
+            mock_console.route_create_workstream.return_value = {
+                "ws_id": "ws-789",
+                "node_url": "http://node-1:8080",
+                "node_id": "node-1",
+            }
+            _mock_console_ctx(mock_console_cls, mock_console)
+
+            mock_server = MagicMock()
+            mock_server.send_and_wait.side_effect = ConnectionError("lost connection")
+            _mock_server_ctx(mock_server_cls, mock_server)
+
+            with contextlib.suppress(ConnectionError):
+                _exec_on_node_sync(_CONSOLE_KW, "node-1", "echo hi", 60.0)
+
+            mock_console.route_close.assert_called_once_with("ws-789")
+
+    def test_malformed_route_response_no_leak(self):
+        """If route response is missing ws_id, no route_close is attempted."""
+        with patch("mcp_cluster_ops.server.TurnstoneConsole") as mock_console_cls:
+            mock_console = MagicMock()
+            mock_console.route_create_workstream.return_value = {
+                # Missing "ws_id" and "node_url"
+                "node_id": "node-1",
+            }
+            _mock_console_ctx(mock_console_cls, mock_console)
+
+            with pytest.raises(KeyError):
+                _exec_on_node_sync(_CONSOLE_KW, "node-1", "echo hi", 60.0)
+
+            # route_close must NOT be called — ws_id was never assigned
+            mock_console.route_close.assert_not_called()
 
 
 # ---------------------------------------------------------------------------
@@ -88,61 +227,47 @@ class TestExecOnNodeSync:
 
 class TestDispatchParallel:
     def test_parallel_success(self):
-        def fake_exec(redis_kw: Any, node_id: str, command: str, timeout: float) -> Any:
-            return (node_id, TurnResult(tool_results=[("bash", f"output-{node_id}")]))
+        def fake_exec(console_kw: Any, node_id: str, command: str, timeout: float) -> Any:
+            return (
+                node_id,
+                TurnResult(tool_results=[("bash", f"output-{node_id}")]),
+            )
 
         with patch("mcp_cluster_ops.server._exec_on_node_sync", side_effect=fake_exec):
             results = asyncio.run(
-                _dispatch_parallel(
-                    {"host": "localhost"},
-                    ["a", "b", "c"],
-                    "echo hi",
-                    60.0,
-                    8192,
-                )
+                _dispatch_parallel(_CONSOLE_KW, ["a", "b", "c"], "echo hi", 60.0, 8192)
             )
             assert len(results) == 3
             assert all(r["ok"] for r in results)
             outputs = {r["node"]: r["output"] for r in results}
             assert outputs["a"] == "output-a"
             assert outputs["b"] == "output-b"
+            assert outputs["c"] == "output-c"
 
     def test_partial_failure(self):
-        def fake_exec(redis_kw: Any, node_id: str, command: str, timeout: float) -> Any:
+        def fake_exec(console_kw: Any, node_id: str, command: str, timeout: float) -> Any:
             if node_id == "bad":
-                raise ConnectionError("Redis down")
+                raise ConnectionError("connection refused")
             return (node_id, TurnResult(tool_results=[("bash", "ok")]))
 
         with patch("mcp_cluster_ops.server._exec_on_node_sync", side_effect=fake_exec):
             results = asyncio.run(
-                _dispatch_parallel(
-                    {"host": "localhost"},
-                    ["good", "bad"],
-                    "echo hi",
-                    60.0,
-                    8192,
-                )
+                _dispatch_parallel(_CONSOLE_KW, ["good", "bad"], "echo hi", 60.0, 8192)
             )
             assert len(results) == 2
             good = next(r for r in results if r["node"] == "good")
             bad = next(r for r in results if r["node"] == "bad")
             assert good["ok"] is True
             assert bad["ok"] is False
-            assert "Redis down" in bad["error"]
+            assert "connection refused" in bad["error"]
 
     def test_all_fail(self):
-        def fake_exec(redis_kw: Any, node_id: str, command: str, timeout: float) -> Any:
+        def fake_exec(console_kw: Any, node_id: str, command: str, timeout: float) -> Any:
             raise RuntimeError(f"fail-{node_id}")
 
         with patch("mcp_cluster_ops.server._exec_on_node_sync", side_effect=fake_exec):
             results = asyncio.run(
-                _dispatch_parallel(
-                    {"host": "localhost"},
-                    ["a", "b"],
-                    "echo hi",
-                    60.0,
-                    8192,
-                )
+                _dispatch_parallel(_CONSOLE_KW, ["a", "b"], "echo hi", 60.0, 8192)
             )
             assert all(not r["ok"] for r in results)
             assert "fail-a" in results[0]["error"]

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "turnstone"
-version = "0.9.5"
+version = "1.0.1"
 description = "Multi-node AI orchestration platform with tool use, agent routing, and cluster simulation."
 readme = "README.md"
 license = "BUSL-1.1"
@@ -12,7 +12,7 @@ requires-python = ">=3.11"
 authors = [{name = "Patrick Buckley", email = "buckleypm@gmail.com"}]
 keywords = ["ai", "chat", "llm", "agent", "tools", "openai"]
 classifiers = [
-    "Development Status :: 4 - Beta",
+    "Development Status :: 5 - Production/Stable",
     "Environment :: Console",
     "Intended Audience :: Developers",
     "Programming Language :: Python :: 3",
@@ -45,25 +45,21 @@ Issues = "https://github.com/turnstonelabs/turnstone/issues"
 
 [project.optional-dependencies]
 test = ["pytest>=9.0", "pytest-cov>=6.0", "croniter>=3.0"]
-dev = ["ruff>=0.9", "mypy>=1.14", "types-redis>=4.6"]
-mq = ["redis>=7.2"]
-console = ["redis>=7.2", "croniter>=3.0"]
-sim = ["redis>=7.2"]
+dev = ["ruff>=0.9", "mypy>=1.14"]
+console = ["croniter>=3.0"]
 anthropic = ["anthropic>=0.39"]
 postgres = ["psycopg[binary]>=3.2"]
 ddg = ["ddgs>=9.0"]
-discord = ["discord.py>=2.4", "redis>=7.2"]
+discord = ["discord.py>=2.4"]
 tls = ["lacme>=1.0.4"]
 sandbox = ["sympy>=1.13", "numpy>=2.0", "scipy>=1.14", "pytest>=9.0"]
-all = ["turnstone[mq,console,sim,anthropic,postgres,discord,ddg,tls,sandbox]"]
+all = ["turnstone[console,anthropic,postgres,discord,ddg,tls,sandbox]"]
 
 [project.scripts]
 turnstone = "turnstone.cli:main"
 turnstone-eval = "turnstone.eval:main"
 turnstone-server = "turnstone.server:main"
-turnstone-bridge = "turnstone.mq.bridge:main"
 turnstone-console = "turnstone.console.server:main"
-turnstone-sim = "turnstone.sim.cli:main"
 turnstone-admin = "turnstone.admin:main"
 turnstone-channel = "turnstone.channels.cli:main"
 turnstone-bootstrap = "turnstone.bootstrap:main"
@@ -82,7 +78,7 @@ include = [
   "turnstone/shared_static/*.js",
   "turnstone/shared_static/katex-0.16.44/**/*",
   "turnstone/shared_static/hljs-11.11.1/**/*",
-  "turnstone/shared_static/mermaid-11.13.0/**/*",
+  "turnstone/shared_static/mermaid-11.14.0/**/*",
   "turnstone/sdk/py.typed",
 ]
 

scripts/release.sh

@@ -0,0 +1,62 @@
+#!/usr/bin/env bash
+#
+# Bump version, regenerate lockfile, commit, and tag.
+#
+# Usage:
+#   scripts/release.sh 1.0.0          # stable release
+#   scripts/release.sh 1.1.0a1        # experimental pre-release
+#   scripts/release.sh 1.0.1 --push   # bump + push tag to origin
+#
+set -euo pipefail
+
+VERSION="${1:?Usage: scripts/release.sh VERSION [--push]}"
+PUSH="${2:-}"
+
+# Validate PEP 440 version
+if ! echo "$VERSION" | grep -qE '^[0-9]+\.[0-9]+\.[0-9]+(a[0-9]+|b[0-9]+|rc[0-9]+)?$'; then
+    echo "error: invalid PEP 440 version: $VERSION" >&2
+    echo "  examples: 1.0.0, 1.1.0a1, 1.0.1rc2" >&2
+    exit 1
+fi
+
+TAG="v${VERSION}"
+
+# Check for clean working tree
+if ! git diff --quiet || ! git diff --cached --quiet; then
+    echo "error: working tree is dirty — commit or stash first" >&2
+    exit 1
+fi
+
+# Check tag doesn't already exist
+if git rev-parse "$TAG" >/dev/null 2>&1; then
+    echo "error: tag $TAG already exists" >&2
+    exit 1
+fi
+
+# Detect current version
+CURRENT=$(grep -oP '(?<=^version = ")[^"]+' pyproject.toml)
+echo "Bumping $CURRENT → $VERSION"
+
+# Update version in both files
+sed -i "s/^version = \".*\"/version = \"$VERSION\"/" pyproject.toml
+sed -i "s/^__version__ = \".*\"/__version__ = \"$VERSION\"/" turnstone/__init__.py
+
+# Regenerate lockfile
+echo "Regenerating uv.lock..."
+uv lock
+
+# Commit and tag
+git add pyproject.toml turnstone/__init__.py uv.lock
+git commit -m "chore: bump version to $VERSION"
+git tag "$TAG"
+
+echo ""
+echo "Created commit and tag $TAG"
+
+if [ "$PUSH" = "--push" ]; then
+    BRANCH=$(git rev-parse --abbrev-ref HEAD)
+    echo "Pushing $BRANCH + $TAG to origin..."
+    git push origin "$BRANCH" "$TAG"
+else
+    echo "Run 'git push origin <branch> $TAG' to publish"
+fi

sdk/typescript/src/index.ts

@@ -7,7 +7,7 @@
  *
  * const client = new TurnstoneServer({
  *   baseUrl: "http://localhost:8080",
- *   token: "tok_xxx",
+ *   token: "ts_your_api_token",
  * });
  *
  * const ws = await client.createWorkstream({ name: "demo" });

tests/test_api_versioning.py

@@ -6,6 +6,37 @@ from unittest.mock import MagicMock
 
 import pytest
 
+# Shared test auth — JWT-based
+_TEST_JWT_SECRET = "test-jwt-secret-minimum-32-chars!"
+
+
+def _server_jwt() -> str:
+    from turnstone.core.auth import JWT_AUD_SERVER, create_jwt
+
+    return create_jwt(
+        user_id="test-versioning",
+        scopes=frozenset({"read", "write", "approve", "service"}),
+        source="test",
+        secret=_TEST_JWT_SECRET,
+        audience=JWT_AUD_SERVER,
+    )
+
+
+def _console_jwt() -> str:
+    from turnstone.core.auth import JWT_AUD_CONSOLE, create_jwt
+
+    return create_jwt(
+        user_id="test-versioning",
+        scopes=frozenset({"read", "write", "approve", "service"}),
+        source="test",
+        secret=_TEST_JWT_SECRET,
+        audience=JWT_AUD_CONSOLE,
+    )
+
+
+_SERVER_AUTH_HEADERS = {"Authorization": f"Bearer {_server_jwt()}"}
+_CONSOLE_AUTH_HEADERS = {"Authorization": f"Bearer {_console_jwt()}"}
+
 
 class TestServerVersioning:
     """Test /v1/ routes and OpenAPI endpoints on the server."""
@@ -14,7 +45,6 @@ class TestServerVersioning:
     def client(self):
         from starlette.testclient import TestClient
 
-        from turnstone.core.auth import AuthConfig
         from turnstone.server import create_app
 
         mock_mgr = MagicMock()
@@ -26,19 +56,19 @@ class TestServerVersioning:
             global_listeners=[],
             global_listeners_lock=threading.Lock(),
             skip_permissions=False,
-            auth_config=AuthConfig(),
+            jwt_secret=_TEST_JWT_SECRET,
         )
         client = TestClient(app, raise_server_exceptions=False)
         yield client
         client.close()
 
     def test_v1_workstreams(self, client):
-        resp = client.get("/v1/api/workstreams")
+        resp = client.get("/v1/api/workstreams", headers=_SERVER_AUTH_HEADERS)
         assert resp.status_code == 200
         assert "workstreams" in resp.json()
 
     def test_unversioned_api_404(self, client):
-        resp = client.get("/api/workstreams")
+        resp = client.get("/api/workstreams", headers=_SERVER_AUTH_HEADERS)
         assert resp.status_code == 404
 
     def test_openapi_json(self, client):
@@ -72,7 +102,6 @@ class TestConsoleVersioning:
 
         from turnstone.console.collector import ClusterCollector
         from turnstone.console.server import _load_static, create_app
-        from turnstone.core.auth import AuthConfig
 
         _load_static()
         collector = MagicMock(spec=ClusterCollector)
@@ -84,19 +113,18 @@ class TestConsoleVersioning:
         }
         app = create_app(
             collector=collector,
-            broker=MagicMock(),
-            auth_config=AuthConfig(),
+            jwt_secret=_TEST_JWT_SECRET,
         )
         client = TestClient(app, raise_server_exceptions=False)
         yield client
         client.close()
 
     def test_v1_cluster_overview(self, client):
-        resp = client.get("/v1/api/cluster/overview")
+        resp = client.get("/v1/api/cluster/overview", headers=_CONSOLE_AUTH_HEADERS)
         assert resp.status_code == 200
 
     def test_unversioned_api_404(self, client):
-        resp = client.get("/api/cluster/overview")
+        resp = client.get("/api/cluster/overview", headers=_CONSOLE_AUTH_HEADERS)
         assert resp.status_code == 404
 
     def test_openapi_json(self, client):

tests/test_async_broker.py

@@ -1,181 +0,0 @@
-"""Tests for turnstone.mq.async_broker.AsyncRedisBroker."""
-
-from __future__ import annotations
-
-import asyncio
-import contextlib
-from unittest.mock import AsyncMock, MagicMock, patch
-
-import pytest
-
-from turnstone.mq.async_broker import AsyncRedisBroker
-
-
-@pytest.fixture
-def broker() -> AsyncRedisBroker:
-    return AsyncRedisBroker(host="localhost", port=6379, db=0, prefix="test", response_ttl=120)
-
-
-@pytest.fixture
-def mock_redis() -> AsyncMock:
-    """Return a mock Redis client with common async methods."""
-    r = AsyncMock()
-    r.rpush = AsyncMock()
-    r.publish = AsyncMock()
-    r.expire = AsyncMock()
-    r.get = AsyncMock(return_value=None)
-    r.set = AsyncMock()
-    r.delete = AsyncMock()
-    r.blpop = AsyncMock(return_value=None)
-    ps = AsyncMock()
-    ps.subscribe = AsyncMock()
-    ps.unsubscribe = AsyncMock()
-    ps.close = AsyncMock()
-    ps.get_message = AsyncMock(return_value=None)
-    r.pubsub = MagicMock(return_value=ps)
-    return r
-
-
-def _inject_redis(broker: AsyncRedisBroker, mock_redis: AsyncMock) -> None:
-    """Inject a mock Redis client into the broker, simulating connect()."""
-    broker._redis = mock_redis
-    broker._pubsub = mock_redis.pubsub()
-
-
-class TestConstructor:
-    def test_stores_config(self) -> None:
-        b = AsyncRedisBroker(host="h", port=1234, db=2, prefix="pfx", password="pw")
-        assert b._host == "h"
-        assert b._port == 1234
-        assert b._db == 2
-        assert b._prefix == "pfx"
-        assert b._password == "pw"
-        assert b._redis is None
-
-    def test_defaults(self) -> None:
-        b = AsyncRedisBroker()
-        assert b._host == "localhost"
-        assert b._port == 6379
-        assert b._prefix == "turnstone"
-
-
-class TestConnect:
-    @pytest.mark.anyio
-    async def test_creates_connection(self) -> None:
-        b = AsyncRedisBroker()
-        mock_r = AsyncMock()
-        mock_r.pubsub = MagicMock(return_value=AsyncMock())
-        with patch("redis.asyncio.Redis", return_value=mock_r):
-            await b.connect()
-            assert b._redis is mock_r
-            assert b._pubsub is not None
-
-    @pytest.mark.anyio
-    async def test_connect_idempotent(
-        self, broker: AsyncRedisBroker, mock_redis: AsyncMock
-    ) -> None:
-        _inject_redis(broker, mock_redis)
-        old = broker._redis
-        await broker.connect()
-        assert broker._redis is old
-
-
-class TestPushInbound:
-    @pytest.mark.anyio
-    async def test_shared_queue(self, broker: AsyncRedisBroker, mock_redis: AsyncMock) -> None:
-        _inject_redis(broker, mock_redis)
-        await broker.push_inbound('{"type":"send"}')
-        mock_redis.rpush.assert_awaited_once_with("test:inbound", '{"type":"send"}')
-
-    @pytest.mark.anyio
-    async def test_per_node_queue(self, broker: AsyncRedisBroker, mock_redis: AsyncMock) -> None:
-        _inject_redis(broker, mock_redis)
-        await broker.push_inbound('{"type":"send"}', node_id="node-1")
-        mock_redis.rpush.assert_awaited_once_with("test:inbound:node-1", '{"type":"send"}')
-
-
-class TestPublishOutbound:
-    @pytest.mark.anyio
-    async def test_publishes(self, broker: AsyncRedisBroker, mock_redis: AsyncMock) -> None:
-        _inject_redis(broker, mock_redis)
-        await broker.publish_outbound("test:events:global", '{"event":"data"}')
-        mock_redis.publish.assert_awaited_once_with("test:events:global", '{"event":"data"}')
-
-
-class TestPushResponse:
-    @pytest.mark.anyio
-    async def test_rpush_and_expire(self, broker: AsyncRedisBroker, mock_redis: AsyncMock) -> None:
-        _inject_redis(broker, mock_redis)
-        await broker.push_response("req-123", '{"ok":true}')
-        mock_redis.rpush.assert_awaited_once_with("test:resp:req-123", '{"ok":true}')
-        mock_redis.expire.assert_awaited_once_with("test:resp:req-123", 120)
-
-
-class TestSubscribe:
-    @pytest.mark.anyio
-    async def test_creates_task(self, broker: AsyncRedisBroker, mock_redis: AsyncMock) -> None:
-        _inject_redis(broker, mock_redis)
-        await broker.subscribe("test:events:global", lambda msg: None)
-        assert "test:events:global" in broker._callbacks
-        assert broker._listener_task is not None
-        assert isinstance(broker._listener_task, asyncio.Task)
-        # Clean up.
-        broker._listener_task.cancel()
-        with contextlib.suppress(asyncio.CancelledError):
-            await broker._listener_task
-
-
-class TestUnsubscribe:
-    @pytest.mark.anyio
-    async def test_cancels_task(self, broker: AsyncRedisBroker, mock_redis: AsyncMock) -> None:
-        _inject_redis(broker, mock_redis)
-        await broker.subscribe("test:events:ch", lambda msg: None)
-        assert "test:events:ch" in broker._callbacks
-        await broker.unsubscribe("test:events:ch")
-        assert "test:events:ch" not in broker._callbacks
-
-
-class TestRoutingPrimitives:
-    @pytest.mark.anyio
-    async def test_get_ws_owner(self, broker: AsyncRedisBroker, mock_redis: AsyncMock) -> None:
-        _inject_redis(broker, mock_redis)
-        mock_redis.get.return_value = "node-1"
-        result = await broker.get_ws_owner("ws-abc")
-        mock_redis.get.assert_awaited_once_with("test:ws:ws-abc")
-        assert result == "node-1"
-
-    @pytest.mark.anyio
-    async def test_set_ws_owner(self, broker: AsyncRedisBroker, mock_redis: AsyncMock) -> None:
-        _inject_redis(broker, mock_redis)
-        await broker.set_ws_owner("ws-abc", "node-2")
-        mock_redis.set.assert_awaited_once_with("test:ws:ws-abc", "node-2")
-
-    @pytest.mark.anyio
-    async def test_set_ws_owner_with_ttl(
-        self, broker: AsyncRedisBroker, mock_redis: AsyncMock
-    ) -> None:
-        _inject_redis(broker, mock_redis)
-        await broker.set_ws_owner("ws-abc", "node-2", ttl=300)
-        mock_redis.set.assert_awaited_once_with("test:ws:ws-abc", "node-2", ex=300)
-
-    @pytest.mark.anyio
-    async def test_del_ws_owner(self, broker: AsyncRedisBroker, mock_redis: AsyncMock) -> None:
-        _inject_redis(broker, mock_redis)
-        await broker.del_ws_owner("ws-abc")
-        mock_redis.delete.assert_awaited_once_with("test:ws:ws-abc")
-
-
-class TestClose:
-    @pytest.mark.anyio
-    async def test_cancels_tasks_and_closes(
-        self, broker: AsyncRedisBroker, mock_redis: AsyncMock
-    ) -> None:
-        _inject_redis(broker, mock_redis)
-        await broker.subscribe("ch1", lambda m: None)
-        assert len(broker._callbacks) == 1
-        assert broker._listener_task is not None
-        await broker.close()
-        assert len(broker._callbacks) == 0
-        assert broker._listener_task is None
-        assert broker._redis is None
-        assert broker._pubsub is None

tests/test_auth.py

@@ -9,12 +9,11 @@ import pytest
 
 from turnstone.core.auth import (
     WRITE_PATHS,
-    AuthConfig,
     _extract_bearer,
     _extract_cookie,
     check_request,
+    create_jwt,
     is_public_path,
-    load_auth_config,
     make_clear_cookie,
     make_set_cookie,
     required_scope,
@@ -199,37 +198,6 @@ class TestRequiredScope:
         assert required_scope("GET", "/api/_internal/mcp-reload") == "read"
 
 
-# ---------------------------------------------------------------------------
-# TestAuthConfig
-# ---------------------------------------------------------------------------
-
-
-class TestAuthConfig:
-    def test_check_valid_full_token(self):
-        cfg = AuthConfig(enabled=True, tokens={"tok_full": "full", "tok_read": "read"})
-        assert cfg.check("tok_full") == "full"
-
-    def test_check_valid_read_token(self):
-        cfg = AuthConfig(enabled=True, tokens={"tok_full": "full", "tok_read": "read"})
-        assert cfg.check("tok_read") == "read"
-
-    def test_check_invalid_token(self):
-        cfg = AuthConfig(enabled=True, tokens={"tok_full": "full"})
-        assert cfg.check("wrong") is None
-
-    def test_check_none_token(self):
-        cfg = AuthConfig(enabled=True, tokens={"tok_full": "full"})
-        assert cfg.check(None) is None
-
-    def test_check_empty_token(self):
-        cfg = AuthConfig(enabled=True, tokens={"tok_full": "full"})
-        assert cfg.check("") is None
-
-    def test_check_no_tokens(self):
-        cfg = AuthConfig(enabled=True, tokens={})
-        assert cfg.check("anything") is None
-
-
 # ---------------------------------------------------------------------------
 # TestExtractBearer
 # ---------------------------------------------------------------------------
@@ -353,167 +321,157 @@ class TestMakeClearCookie:
 class TestCheckRequest:
     """Tests for the main check_request() entry point."""
 
-    @pytest.fixture()
-    def disabled(self):
-        return AuthConfig(enabled=False)
+    _SECRET = "test-jwt-secret-minimum-32-chars!"
 
     @pytest.fixture()
-    def enabled(self):
-        return AuthConfig(
-            enabled=True,
-            tokens={"tok_full": "full", "tok_read": "read"},
-        )
+    def read_jwt(self):
+        return f"Bearer {create_jwt('u1', frozenset({'read'}), 'test', self._SECRET)}"
 
-    def test_disabled_allows_all(self, disabled):
-        allowed, status, msg, _result = check_request(disabled, "POST", "/api/send", None)
+    @pytest.fixture()
+    def full_jwt(self):
+        return f"Bearer {create_jwt('u1', frozenset({'read', 'write', 'approve'}), 'test', self._SECRET)}"
+
+    def test_public_path_no_token_ok(self):
+        allowed, status, msg, _result = check_request("GET", "/health", None)
         assert allowed is True
         assert status == 200
 
-    def test_disabled_allows_no_header(self, disabled):
-        allowed, status, msg, _result = check_request(disabled, "GET", "/api/workstreams", None)
+    def test_public_root_no_token_ok(self):
+        allowed, status, msg, _result = check_request("GET", "/", None)
         assert allowed is True
 
-    def test_public_path_no_token_ok(self, enabled):
-        allowed, status, msg, _result = check_request(enabled, "GET", "/health", None)
-        assert allowed is True
-        assert status == 200
-
-    def test_public_root_no_token_ok(self, enabled):
-        allowed, status, msg, _result = check_request(enabled, "GET", "/", None)
+    def test_public_static_no_token_ok(self):
+        allowed, status, msg, _result = check_request("GET", "/static/style.css", None)
         assert allowed is True
 
-    def test_public_static_no_token_ok(self, enabled):
-        allowed, status, msg, _result = check_request(enabled, "GET", "/static/style.css", None)
-        assert allowed is True
-
-    def test_api_no_token_401(self, enabled):
-        allowed, status, msg, _result = check_request(enabled, "GET", "/api/workstreams", None)
+    def test_api_no_token_401(self):
+        allowed, status, msg, _result = check_request("GET", "/api/workstreams", None)
         assert allowed is False
         assert status == 401
         assert "Unauthorized" in msg
 
-    def test_api_invalid_token_401(self, enabled):
+    def test_api_invalid_token_401(self):
         allowed, status, msg, _result = check_request(
-            enabled, "GET", "/api/workstreams", "Bearer wrong_token"
+            "GET", "/api/workstreams", "Bearer wrong_token"
         )
         assert allowed is False
         assert status == 401
 
-    def test_api_read_token_ok(self, enabled):
+    def test_api_read_token_ok(self, read_jwt):
         allowed, status, msg, _result = check_request(
-            enabled, "GET", "/api/workstreams", "Bearer tok_read"
+            "GET", "/api/workstreams", read_jwt, jwt_secret=self._SECRET
         )
         assert allowed is True
         assert status == 200
 
-    def test_api_full_token_ok(self, enabled):
+    def test_api_full_token_ok(self, full_jwt):
         allowed, status, msg, _result = check_request(
-            enabled, "GET", "/api/workstreams", "Bearer tok_full"
+            "GET", "/api/workstreams", full_jwt, jwt_secret=self._SECRET
         )
         assert allowed is True
 
-    def test_write_read_token_403(self, enabled):
+    def test_write_read_token_403(self, read_jwt):
         allowed, status, msg, _result = check_request(
-            enabled, "POST", "/api/send", "Bearer tok_read"
+            "POST", "/api/send", read_jwt, jwt_secret=self._SECRET
         )
         assert allowed is False
         assert status == 403
         assert "Forbidden" in msg
 
-    def test_write_full_token_ok(self, enabled):
+    def test_write_full_token_ok(self, full_jwt):
         allowed, status, msg, _result = check_request(
-            enabled, "POST", "/api/send", "Bearer tok_full"
+            "POST", "/api/send", full_jwt, jwt_secret=self._SECRET
         )
         assert allowed is True
         assert status == 200
 
-    def test_approve_read_token_403(self, enabled):
+    def test_approve_read_token_403(self, read_jwt):
         allowed, status, msg, _result = check_request(
-            enabled, "POST", "/api/approve", "Bearer tok_read"
+            "POST", "/api/approve", read_jwt, jwt_secret=self._SECRET
         )
         assert allowed is False
         assert status == 403
 
-    def test_proxy_write_read_token_403(self, enabled):
+    def test_proxy_write_read_token_403(self, read_jwt):
         """Read tokens cannot escalate to write ops via proxy routes."""
         allowed, status, msg, _result = check_request(
-            enabled, "POST", "/node/node-a/api/send", "Bearer tok_read"
+            "POST", "/node/node-a/api/send", read_jwt, jwt_secret=self._SECRET
         )
         assert allowed is False
         assert status == 403
 
-    def test_proxy_write_trailing_slash_read_token_403(self, enabled):
+    def test_proxy_write_trailing_slash_read_token_403(self, read_jwt):
         """Trailing slash must not bypass write-role check on proxy routes."""
         allowed, status, msg, _result = check_request(
-            enabled, "POST", "/node/node-a/api/send/", "Bearer tok_read"
+            "POST", "/node/node-a/api/send/", read_jwt, jwt_secret=self._SECRET
         )
         assert allowed is False
         assert status == 403
 
-    def test_direct_write_trailing_slash_read_token_403(self, enabled):
+    def test_direct_write_trailing_slash_read_token_403(self, read_jwt):
         """Trailing slash must not bypass write-role check on direct routes."""
         allowed, status, msg, _result = check_request(
-            enabled, "POST", "/api/send/", "Bearer tok_read"
+            "POST", "/api/send/", read_jwt, jwt_secret=self._SECRET
         )
         assert allowed is False
         assert status == 403
 
-    def test_proxy_write_full_token_ok(self, enabled):
+    def test_proxy_write_full_token_ok(self, full_jwt):
         """Full tokens pass through proxy write routes."""
         allowed, status, msg, _result = check_request(
-            enabled, "POST", "/node/node-a/api/send", "Bearer tok_full"
+            "POST", "/node/node-a/api/send", full_jwt, jwt_secret=self._SECRET
         )
         assert allowed is True
 
-    def test_proxy_v1_write_read_token_403(self, enabled):
+    def test_proxy_v1_write_read_token_403(self, read_jwt):
         """Read tokens cannot escalate to write ops via v1 proxy routes."""
         allowed, status, msg, _result = check_request(
-            enabled, "POST", "/node/node-a/v1/api/send", "Bearer tok_read"
+            "POST", "/node/node-a/v1/api/send", read_jwt, jwt_secret=self._SECRET
         )
         assert allowed is False
         assert status == 403
 
-    def test_proxy_v1_write_full_token_ok(self, enabled):
+    def test_proxy_v1_write_full_token_ok(self, full_jwt):
         """Full tokens pass through v1 proxy write routes."""
         allowed, status, msg, _result = check_request(
-            enabled, "POST", "/node/node-a/v1/api/send", "Bearer tok_full"
+            "POST", "/node/node-a/v1/api/send", full_jwt, jwt_secret=self._SECRET
         )
         assert allowed is True
 
-    def test_proxy_v1_cluster_ws_new_read_403(self, enabled):
+    def test_proxy_v1_cluster_ws_new_read_403(self, read_jwt):
         """Read tokens cannot create workstreams via v1 proxy."""
         allowed, status, msg, _result = check_request(
-            enabled,
             "POST",
             "/node/node-a/v1/api/cluster/workstreams/new",
-            "Bearer tok_read",
+            read_jwt,
+            jwt_secret=self._SECRET,
         )
         assert allowed is False
         assert status == 403
 
-    def test_proxy_read_endpoint_read_token_ok(self, enabled):
+    def test_proxy_read_endpoint_read_token_ok(self, read_jwt):
         """Read tokens can access proxy read endpoints."""
         allowed, status, msg, _result = check_request(
-            enabled, "GET", "/node/node-a/api/workstreams", "Bearer tok_read"
+            "GET", "/node/node-a/api/workstreams", read_jwt, jwt_secret=self._SECRET
         )
         assert allowed is True
 
-    def test_console_create_ws_read_token_403(self, enabled):
+    def test_console_create_ws_read_token_403(self, read_jwt):
         """Read tokens cannot create workstreams."""
         allowed, status, msg, _result = check_request(
-            enabled, "POST", "/api/cluster/workstreams/new", "Bearer tok_read"
+            "POST", "/api/cluster/workstreams/new", read_jwt, jwt_secret=self._SECRET
         )
         assert allowed is False
         assert status == 403
 
-    def test_approve_full_token_ok(self, enabled):
+    def test_approve_full_token_ok(self, full_jwt):
         allowed, status, msg, _result = check_request(
-            enabled, "POST", "/api/approve", "Bearer tok_full"
+            "POST", "/api/approve", full_jwt, jwt_secret=self._SECRET
         )
         assert allowed is True
 
-    def test_no_auth_header_string(self, enabled):
-        allowed, status, msg, _result = check_request(enabled, "GET", "/api/dashboard", "")
+    def test_no_auth_header_string(self):
+        allowed, status, msg, _result = check_request("GET", "/api/dashboard", "")
         assert allowed is False
         assert status == 401
 
@@ -526,70 +484,71 @@ class TestCheckRequest:
 class TestCheckRequestWithCookie:
     """Tests for cookie-based auth fallback in check_request."""
 
-    @pytest.fixture()
-    def enabled(self):
-        return AuthConfig(
-            enabled=True,
-            tokens={"tok_full": "full", "tok_read": "read"},
-        )
+    _SECRET = "test-jwt-secret-minimum-32-chars!"
 
-    def test_cookie_fallback_when_no_bearer(self, enabled):
+    @pytest.fixture()
+    def read_jwt(self):
+        return create_jwt("u1", frozenset({"read"}), "test", self._SECRET)
+
+    @pytest.fixture()
+    def full_jwt(self):
+        return create_jwt("u1", frozenset({"read", "write", "approve"}), "test", self._SECRET)
+
+    def test_cookie_fallback_when_no_bearer(self, read_jwt):
         allowed, status, _, _r = check_request(
-            enabled,
             "GET",
             "/api/workstreams",
             None,
-            cookie_header="turnstone_auth=tok_read",
+            cookie_header=f"turnstone_auth={read_jwt}",
+            jwt_secret=self._SECRET,
         )
         assert allowed is True
         assert status == 200
 
-    def test_bearer_takes_precedence_over_cookie(self, enabled):
-        # Bearer is full, cookie is read — Bearer should win
+    def test_bearer_takes_precedence_over_cookie(self, read_jwt, full_jwt):
         allowed, status, _, _r = check_request(
-            enabled,
             "POST",
             "/api/send",
-            "Bearer tok_full",
-            cookie_header="turnstone_auth=tok_read",
+            f"Bearer {full_jwt}",
+            cookie_header=f"turnstone_auth={read_jwt}",
+            jwt_secret=self._SECRET,
         )
         assert allowed is True
 
-    def test_invalid_cookie_401(self, enabled):
+    def test_invalid_cookie_401(self):
         allowed, status, _, _r = check_request(
-            enabled,
             "GET",
             "/api/workstreams",
             None,
             cookie_header="turnstone_auth=wrong_token",
+            jwt_secret=self._SECRET,
         )
         assert allowed is False
         assert status == 401
 
-    def test_cookie_read_on_write_403(self, enabled):
+    def test_cookie_read_on_write_403(self, read_jwt):
         allowed, status, _, _r = check_request(
-            enabled,
             "POST",
             "/api/send",
             None,
-            cookie_header="turnstone_auth=tok_read",
+            cookie_header=f"turnstone_auth={read_jwt}",
+            jwt_secret=self._SECRET,
         )
         assert allowed is False
         assert status == 403
 
-    def test_cookie_full_on_write_ok(self, enabled):
+    def test_cookie_full_on_write_ok(self, full_jwt):
         allowed, status, _, _r = check_request(
-            enabled,
             "POST",
             "/api/send",
             None,
-            cookie_header="turnstone_auth=tok_full",
+            cookie_header=f"turnstone_auth={full_jwt}",
+            jwt_secret=self._SECRET,
         )
         assert allowed is True
 
-    def test_no_cookie_no_bearer_401(self, enabled):
+    def test_no_cookie_no_bearer_401(self):
         allowed, status, _, _r = check_request(
-            enabled,
             "GET",
             "/api/workstreams",
             None,
@@ -598,18 +557,16 @@ class TestCheckRequestWithCookie:
         assert allowed is False
         assert status == 401
 
-    def test_login_path_public(self, enabled):
+    def test_login_path_public(self):
         allowed, status, _, _r = check_request(
-            enabled,
             "POST",
             "/api/auth/login",
             None,
         )
         assert allowed is True
 
-    def test_logout_path_public(self, enabled):
+    def test_logout_path_public(self):
         allowed, status, _, _r = check_request(
-            enabled,
             "POST",
             "/api/auth/logout",
             None,
@@ -617,139 +574,6 @@ class TestCheckRequestWithCookie:
         assert allowed is True
 
 
-# ---------------------------------------------------------------------------
-# TestLoadAuthConfig
-# ---------------------------------------------------------------------------
-
-
-class TestLoadAuthConfig:
-    """Tests for load_auth_config with mocked config + env vars."""
-
-    def test_default_enabled(self):
-        with patch("turnstone.core.config.load_config", return_value={}):
-            cfg = load_auth_config()
-        assert cfg.enabled is True
-        assert cfg.tokens == {}
-
-    def test_explicit_disable(self):
-        with (
-            patch("turnstone.core.config.load_config", return_value={"enabled": False}),
-            patch.dict(os.environ, {}, clear=True),
-        ):
-            cfg = load_auth_config()
-        assert cfg.enabled is False
-
-    def test_env_disable(self):
-        with (
-            patch("turnstone.core.config.load_config", return_value={}),
-            patch.dict(os.environ, {"TURNSTONE_AUTH_ENABLED": "0"}, clear=True),
-        ):
-            cfg = load_auth_config()
-        assert cfg.enabled is False
-
-    def test_config_file_tokens(self):
-        mock_cfg = {
-            "enabled": True,
-            "tokens": [
-                {"value": "tok_a", "role": "full"},
-                {"value": "tok_b", "role": "read"},
-            ],
-        }
-        with (
-            patch("turnstone.core.config.load_config", return_value=mock_cfg),
-            patch.dict(os.environ, {}, clear=True),
-        ):
-            cfg = load_auth_config()
-        assert cfg.enabled is True
-        assert cfg.tokens == {"tok_a": "full", "tok_b": "read"}
-
-    def test_env_var_enabled(self):
-        with (
-            patch("turnstone.core.config.load_config", return_value={}),
-            patch.dict(os.environ, {"TURNSTONE_AUTH_ENABLED": "1"}, clear=False),
-        ):
-            cfg = load_auth_config()
-        assert cfg.enabled is True
-
-    def test_env_var_token(self):
-        with (
-            patch("turnstone.core.config.load_config", return_value={}),
-            patch.dict(os.environ, {"TURNSTONE_AUTH_TOKEN": "tok_env"}, clear=False),
-        ):
-            cfg = load_auth_config()
-        assert "tok_env" in cfg.tokens
-        assert cfg.tokens["tok_env"] == "full"
-
-    def test_config_plus_env_merge(self):
-        mock_cfg = {
-            "enabled": True,
-            "tokens": [{"value": "tok_cfg", "role": "read"}],
-        }
-        with (
-            patch("turnstone.core.config.load_config", return_value=mock_cfg),
-            patch.dict(os.environ, {"TURNSTONE_AUTH_TOKEN": "tok_env"}, clear=False),
-        ):
-            cfg = load_auth_config()
-        assert cfg.tokens["tok_cfg"] == "read"
-        assert cfg.tokens["tok_env"] == "full"
-
-    def test_invalid_role_skipped(self):
-        mock_cfg = {
-            "enabled": True,
-            "tokens": [
-                {"value": "tok_ok", "role": "full"},
-                {"value": "tok_bad", "role": "admin"},
-            ],
-        }
-        with (
-            patch("turnstone.core.config.load_config", return_value=mock_cfg),
-            patch.dict(os.environ, {}, clear=True),
-        ):
-            cfg = load_auth_config()
-        assert "tok_ok" in cfg.tokens
-        assert "tok_bad" not in cfg.tokens
-
-    def test_empty_value_skipped(self):
-        mock_cfg = {
-            "enabled": True,
-            "tokens": [{"value": "", "role": "full"}],
-        }
-        with (
-            patch("turnstone.core.config.load_config", return_value=mock_cfg),
-            patch.dict(os.environ, {}, clear=True),
-        ):
-            cfg = load_auth_config()
-        assert len(cfg.tokens) == 0
-
-    def test_non_dict_token_entry_skipped(self):
-        mock_cfg = {
-            "enabled": True,
-            "tokens": ["not_a_dict", {"value": "tok_ok", "role": "full"}],
-        }
-        with (
-            patch("turnstone.core.config.load_config", return_value=mock_cfg),
-            patch.dict(os.environ, {}, clear=True),
-        ):
-            cfg = load_auth_config()
-        assert cfg.tokens == {"tok_ok": "full"}
-
-    def test_env_enabled_true(self):
-        with (
-            patch("turnstone.core.config.load_config", return_value={}),
-            patch.dict(os.environ, {"TURNSTONE_AUTH_ENABLED": "true"}, clear=False),
-        ):
-            cfg = load_auth_config()
-        assert cfg.enabled is True
-
-    def test_env_enabled_yes(self):
-        with (
-            patch("turnstone.core.config.load_config", return_value={}),
-            patch.dict(os.environ, {"TURNSTONE_AUTH_ENABLED": "yes"}, clear=False),
-        ):
-            cfg = load_auth_config()
-        assert cfg.enabled is True
-
-
 # ---------------------------------------------------------------------------
 # Integration tests — actual HTTP server with auth enabled
 # ---------------------------------------------------------------------------
@@ -785,16 +609,22 @@ class TestServerAuth:
         mock_mgr.list_all.return_value = [mock_ws]
         mock_mgr.max_workstreams = 10
 
+        from turnstone.core.auth import JWT_AUD_SERVER
+
+        cls._jwt_secret = "test-jwt-secret-minimum-32-chars!"
+        cls._read_hdr = {
+            "Authorization": f"Bearer {create_jwt('u1', frozenset({'read'}), 'test', cls._jwt_secret, audience=JWT_AUD_SERVER)}"
+        }
+        cls._full_hdr = {
+            "Authorization": f"Bearer {create_jwt('u1', frozenset({'read', 'write', 'approve'}), 'test', cls._jwt_secret, audience=JWT_AUD_SERVER)}"
+        }
         app = srv_mod.create_app(
             workstreams=mock_mgr,
             global_queue=queue.Queue(),
             global_listeners=[],
             global_listeners_lock=threading.Lock(),
             skip_permissions=False,
-            auth_config=AuthConfig(
-                enabled=True,
-                tokens={"tok_full": "full", "tok_read": "read"},
-            ),
+            jwt_secret=cls._jwt_secret,
             cors_origins=["*"],
         )
         cls.client = TestClient(app, raise_server_exceptions=False)
@@ -809,7 +639,6 @@ class TestServerAuth:
 
     def test_metrics_no_token_passes_auth(self):
         resp = self.client.get("/metrics")
-        # Public path — should never be 401/403
         assert resp.status_code not in (401, 403)
 
     def test_root_no_token_200(self):
@@ -826,23 +655,17 @@ class TestServerAuth:
         assert "Unauthorized" in resp.json().get("error", "")
 
     def test_api_workstreams_read_token_200(self):
-        resp = self.client.get(
-            "/v1/api/workstreams",
-            headers={"Authorization": "Bearer tok_read"},
-        )
+        resp = self.client.get("/v1/api/workstreams", headers=self._read_hdr)
         assert resp.status_code == 200
 
     def test_api_workstreams_full_token_200(self):
-        resp = self.client.get(
-            "/v1/api/workstreams",
-            headers={"Authorization": "Bearer tok_full"},
-        )
+        resp = self.client.get("/v1/api/workstreams", headers=self._full_hdr)
         assert resp.status_code == 200
 
     def test_api_send_read_token_403(self):
         resp = self.client.post(
             "/v1/api/send",
-            headers={"Authorization": "Bearer tok_read"},
+            headers=self._read_hdr,
             json={"message": "hello", "ws_id": "x"},
         )
         assert resp.status_code == 403
@@ -851,10 +674,9 @@ class TestServerAuth:
     def test_api_send_full_token_passes_auth(self):
         resp = self.client.post(
             "/v1/api/send",
-            headers={"Authorization": "Bearer tok_full"},
+            headers=self._full_hdr,
             json={"message": "hello", "ws_id": "nonexistent"},
         )
-        # Should get 404 (unknown workstream), not 401/403
         assert resp.status_code not in (401, 403)
 
     def test_api_send_no_token_401(self):
@@ -921,13 +743,18 @@ class TestConsoleAuth:
             "aggregate": {"total_tokens": 100},
         }
 
+        from turnstone.core.auth import JWT_AUD_CONSOLE
+
+        cls._jwt_secret = "test-jwt-secret-minimum-32-chars!"
+        cls._read_hdr = {
+            "Authorization": f"Bearer {create_jwt('u1', frozenset({'read'}), 'test', cls._jwt_secret, audience=JWT_AUD_CONSOLE)}"
+        }
+        cls._full_hdr = {
+            "Authorization": f"Bearer {create_jwt('u1', frozenset({'read', 'write', 'approve'}), 'test', cls._jwt_secret, audience=JWT_AUD_CONSOLE)}"
+        }
         app = create_app(
             collector=mock_collector,
-            broker=MagicMock(),
-            auth_config=AuthConfig(
-                enabled=True,
-                tokens={"tok_full": "full", "tok_read": "read"},
-            ),
+            jwt_secret=cls._jwt_secret,
         )
         cls.test_client = TestClient(app, raise_server_exceptions=False)
 
@@ -948,17 +775,11 @@ class TestConsoleAuth:
         assert resp.status_code == 401
 
     def test_api_overview_read_token_200(self):
-        resp = self.test_client.get(
-            "/v1/api/cluster/overview",
-            headers={"Authorization": "Bearer tok_read"},
-        )
+        resp = self.test_client.get("/v1/api/cluster/overview", headers=self._read_hdr)
         assert resp.status_code == 200
 
     def test_api_overview_full_token_200(self):
-        resp = self.test_client.get(
-            "/v1/api/cluster/overview",
-            headers={"Authorization": "Bearer tok_full"},
-        )
+        resp = self.test_client.get("/v1/api/cluster/overview", headers=self._full_hdr)
         assert resp.status_code == 200
 
     def test_invalid_token_401(self):
@@ -1004,16 +825,33 @@ class TestServerLogin:
         mock_mgr.list_all.return_value = [mock_ws]
         mock_mgr.max_workstreams = 10
 
+        # Mock storage with a test user for password login
+        from turnstone.core.auth import hash_password
+
+        mock_storage = MagicMock()
+        mock_storage.get_user_by_username.side_effect = lambda u: (
+            {
+                "user_id": "uid_test",
+                "username": "testuser",
+                "password_hash": hash_password("testpass"),
+                "display_name": "Test",
+            }
+            if u == "testuser"
+            else None
+        )
+        mock_storage.list_user_roles.return_value = [
+            {"role_id": "builtin-admin", "scopes": "read,write,approve"}
+        ]
+
+        cls._jwt_secret = "test-jwt-secret-minimum-32-chars!"
         app = srv_mod.create_app(
             workstreams=mock_mgr,
             global_queue=queue.Queue(),
             global_listeners=[],
             global_listeners_lock=threading.Lock(),
             skip_permissions=False,
-            auth_config=AuthConfig(
-                enabled=True,
-                tokens={"tok_full": "full", "tok_read": "read"},
-            ),
+            jwt_secret=cls._jwt_secret,
+            auth_storage=mock_storage,
         )
         cls.test_client = TestClient(app, raise_server_exceptions=False)
 
@@ -1021,36 +859,36 @@ class TestServerLogin:
     def teardown_class(cls):
         cls.test_client.close()
 
-    def test_login_valid_token_sets_cookie(self):
+    def test_login_config_token_rejected(self):
+        """Config token exchange is no longer allowed."""
         resp = self.test_client.post(
             "/v1/api/auth/login",
             json={"token": "tok_full"},
         )
-        assert resp.status_code == 200
-        data = resp.json()
-        assert data["role"] == "full"
-        cookie = resp.headers.get("set-cookie", "")
-        assert "turnstone_auth=tok_full" in cookie
-        assert "HttpOnly" in cookie
+        assert resp.status_code == 401
 
-    def test_login_invalid_token_401(self):
+    def test_login_invalid_credentials_401(self):
         resp = self.test_client.post(
             "/v1/api/auth/login",
-            json={"token": "wrong"},
+            json={"username": "testuser", "password": "wrong"},
         )
         assert resp.status_code == 401
 
-    def test_login_no_auth_required(self):
-        # /v1/api/auth/login is public — shouldn't require auth itself
+    def test_login_password_ok(self):
         resp = self.test_client.post(
             "/v1/api/auth/login",
-            json={"token": "tok_read"},
+            json={"username": "testuser", "password": "testpass"},
         )
         assert resp.status_code == 200
+        data = resp.json()
+        assert "jwt" in data
 
     def test_cookie_auth_on_api(self):
         # Login to get cookie (TestClient tracks cookies automatically)
-        login_resp = self.test_client.post("/v1/api/auth/login", json={"token": "tok_read"})
+        login_resp = self.test_client.post(
+            "/v1/api/auth/login",
+            json={"username": "testuser", "password": "testpass"},
+        )
         assert login_resp.status_code == 200
 
         # Use cookie to access API — TestClient forwards cookies
@@ -1058,7 +896,10 @@ class TestServerLogin:
         assert resp.status_code == 200
 
     def test_logout_clears_cookie(self):
-        self.test_client.post("/v1/api/auth/login", json={"token": "tok_read"})
+        self.test_client.post(
+            "/v1/api/auth/login",
+            json={"username": "testuser", "password": "testpass"},
+        )
 
         # Logout
         logout_resp = self.test_client.post("/v1/api/auth/logout")
@@ -1082,6 +923,7 @@ class TestConsoleLogin:
 
         from turnstone.console.collector import ClusterCollector
         from turnstone.console.server import _load_static, create_app
+        from turnstone.core.auth import hash_password
 
         _load_static()
 
@@ -1093,13 +935,26 @@ class TestConsoleLogin:
             "aggregate": {"total_tokens": 100},
         }
 
+        mock_storage = MagicMock()
+        mock_storage.get_user_by_username.side_effect = lambda u: (
+            {
+                "user_id": "uid_test",
+                "username": "testuser",
+                "password_hash": hash_password("testpass"),
+                "display_name": "Test",
+            }
+            if u == "testuser"
+            else None
+        )
+        mock_storage.list_user_roles.return_value = [
+            {"role_id": "builtin-admin", "scopes": "read,write,approve"}
+        ]
+
+        cls._jwt_secret = "test-jwt-secret-minimum-32-chars!"
         app = create_app(
             collector=mock_collector,
-            broker=MagicMock(),
-            auth_config=AuthConfig(
-                enabled=True,
-                tokens={"tok_full": "full", "tok_read": "read"},
-            ),
+            jwt_secret=cls._jwt_secret,
+            auth_storage=mock_storage,
         )
         cls.test_client = TestClient(app, raise_server_exceptions=False)
 
@@ -1107,28 +962,34 @@ class TestConsoleLogin:
     def teardown_class(cls):
         cls.test_client.close()
 
-    def test_login_valid_token(self):
+    def test_login_config_token_rejected(self):
         resp = self.test_client.post(
             "/v1/api/auth/login",
             json={"token": "tok_read"},
         )
+        assert resp.status_code == 401
+
+    def test_login_password_ok(self):
+        resp = self.test_client.post(
+            "/v1/api/auth/login",
+            json={"username": "testuser", "password": "testpass"},
+        )
         assert resp.status_code == 200
         assert "turnstone_auth" in resp.headers.get("set-cookie", "")
 
-    def test_login_invalid_token(self):
-        resp = self.test_client.post(
-            "/v1/api/auth/login",
-            json={"token": "wrong"},
-        )
-        assert resp.status_code == 401
-
     def test_cookie_auth_on_api(self):
-        self.test_client.post("/v1/api/auth/login", json={"token": "tok_read"})
+        self.test_client.post(
+            "/v1/api/auth/login",
+            json={"username": "testuser", "password": "testpass"},
+        )
         resp = self.test_client.get("/v1/api/cluster/overview")
         assert resp.status_code == 200
 
     def test_logout_then_api_fails(self):
-        self.test_client.post("/v1/api/auth/login", json={"token": "tok_read"})
+        self.test_client.post(
+            "/v1/api/auth/login",
+            json={"username": "testuser", "password": "testpass"},
+        )
         self.test_client.post("/v1/api/auth/logout")
         resp = self.test_client.get("/v1/api/cluster/overview")
         assert resp.status_code == 401
@@ -1387,25 +1248,29 @@ class TestIsSecureRequest:
 
 
 class TestSecretStrength:
-    def test_short_secret_warns(self, caplog):
-        import logging
+    def test_short_secret_exits(self):
+        import turnstone.core.auth as auth_mod
 
-        from turnstone.core.auth import _MIN_SECRET_LENGTH
+        old = os.environ.get("TURNSTONE_JWT_SECRET", "")
+        os.environ["TURNSTONE_JWT_SECRET"] = "short"
+        try:
+            with pytest.raises(SystemExit):
+                auth_mod.load_jwt_secret()
+        finally:
+            if old:
+                os.environ["TURNSTONE_JWT_SECRET"] = old
+            else:
+                os.environ.pop("TURNSTONE_JWT_SECRET", None)
 
-        with caplog.at_level(logging.WARNING, logger="turnstone.core.auth"):
-            import turnstone.core.auth as auth_mod
+    def test_missing_secret_exits(self):
+        import turnstone.core.auth as auth_mod
 
-            old = os.environ.get("TURNSTONE_JWT_SECRET", "")
-            os.environ["TURNSTONE_JWT_SECRET"] = "short"
-            try:
-                secret = auth_mod.load_jwt_secret()
-                assert secret == "short"
-                assert any(str(_MIN_SECRET_LENGTH) in r.message for r in caplog.records)
-            finally:
-                if old:
-                    os.environ["TURNSTONE_JWT_SECRET"] = old
-                else:
-                    os.environ.pop("TURNSTONE_JWT_SECRET", None)
+        with (
+            patch("turnstone.core.config.load_config", return_value={}),
+            patch.dict(os.environ, {}, clear=True),
+            pytest.raises(SystemExit),
+        ):
+            auth_mod.load_jwt_secret()
 
 
 class TestCorsConfigurable:
@@ -1426,7 +1291,6 @@ class TestCorsConfigurable:
             global_listeners=[],
             global_listeners_lock=threading.Lock(),
             skip_permissions=False,
-            auth_config=AuthConfig(enabled=False),
         )
         client = TestClient(app)
         resp = client.get("/health", headers={"Origin": "http://evil.com"})
@@ -1448,7 +1312,6 @@ class TestCorsConfigurable:
             global_listeners=[],
             global_listeners_lock=threading.Lock(),
             skip_permissions=False,
-            auth_config=AuthConfig(enabled=False),
             cors_origins=["http://example.com"],
         )
         client = TestClient(app)
@@ -1504,3 +1367,69 @@ class TestOIDCPublicPaths:
     def test_oidc_callback_is_public(self):
         assert is_public_path("/api/auth/oidc/callback") is True
         assert is_public_path("/v1/api/auth/oidc/callback") is True
+
+
+# ---------------------------------------------------------------------------
+# TestRequirePermissionServiceScope — service scope bypasses permission checks
+# ---------------------------------------------------------------------------
+
+
+class TestRequirePermissionServiceScope:
+    """Verify require_permission() behaviour with the service scope."""
+
+    def _make_request(self, auth_result):
+        """Build a mock Starlette request with the given AuthResult on state."""
+        request = MagicMock()
+        request.state.auth_result = auth_result
+        return request
+
+    def test_service_scope_bypasses_permission(self):
+        """Service-scoped tokens bypass all permission checks (returns None)."""
+        from turnstone.core.auth import AuthResult, require_permission
+
+        auth = AuthResult(
+            user_id="svc-agent",
+            scopes=frozenset({"service"}),
+            token_source="jwt",
+        )
+        request = self._make_request(auth)
+        result = require_permission(request, "admin.users")
+        assert result is None  # bypass — no 403
+
+    def test_without_service_scope_and_without_permission_returns_403(self):
+        """Non-service tokens without the required permission get 403."""
+        from turnstone.core.auth import AuthResult, require_permission
+
+        auth = AuthResult(
+            user_id="regular-user",
+            scopes=frozenset({"read", "write"}),
+            token_source="jwt",
+        )
+        request = self._make_request(auth)
+        result = require_permission(request, "admin.users")
+        assert result is not None
+        assert result.status_code == 403
+
+    def test_without_service_scope_with_permission_returns_none(self):
+        """Non-service tokens with the required permission pass."""
+        from turnstone.core.auth import AuthResult, require_permission
+
+        auth = AuthResult(
+            user_id="admin-user",
+            scopes=frozenset({"read", "write", "approve"}),
+            token_source="jwt",
+            permissions=frozenset({"admin.users"}),
+        )
+        request = self._make_request(auth)
+        result = require_permission(request, "admin.users")
+        assert result is None  # granted — no 403
+
+    def test_no_auth_result_returns_401(self):
+        """Missing auth_result on request state returns 401."""
+        from turnstone.core.auth import require_permission
+
+        request = MagicMock()
+        del request.state.auth_result  # ensure attribute is absent
+        result = require_permission(request, "admin.users")
+        assert result is not None
+        assert result.status_code == 401

tests/test_auth_identity.py

@@ -7,7 +7,6 @@ import time
 import pytest
 
 from turnstone.core.auth import (
-    AuthConfig,
     AuthResult,
     _authenticate_token,
     check_request,
@@ -203,24 +202,10 @@ class TestRequiredScope:
 
 
 class TestAuthenticateToken:
-    def test_config_token_read(self):
-        cfg = AuthConfig(enabled=True, tokens={"tok_read": "read"})
-        result = _authenticate_token("tok_read", cfg)
-        assert result is not None
-        assert result.scopes == frozenset({"read"})
-        assert result.token_source == "config"
-
-    def test_config_token_full(self):
-        cfg = AuthConfig(enabled=True, tokens={"tok_full": "full"})
-        result = _authenticate_token("tok_full", cfg)
-        assert result is not None
-        assert result.scopes == frozenset({"read", "write", "approve"})
-
     def test_jwt_token(self):
         secret = "test-secret-key-for-jwt-min-32b!"
         jwt_tok = create_jwt("user1", frozenset({"read", "write"}), "db", secret)
-        cfg = AuthConfig(enabled=True)
-        result = _authenticate_token(jwt_tok, cfg, jwt_secret=secret)
+        result = _authenticate_token(jwt_tok, jwt_secret=secret)
         assert result is not None
         assert result.user_id == "user1"
         assert result.token_source == "db"
@@ -243,8 +228,7 @@ class TestAuthenticateToken:
                     }
                 return None
 
-        cfg = AuthConfig(enabled=True)
-        result = _authenticate_token(raw, cfg, storage=MockStorage())
+        result = _authenticate_token(raw, storage=MockStorage())
         assert result is not None
         assert result.user_id == "user1"
         assert result.has_scope("write")
@@ -266,13 +250,11 @@ class TestAuthenticateToken:
                     "expires": "2020-01-02T00:00:00",
                 }
 
-        cfg = AuthConfig(enabled=True)
-        result = _authenticate_token(raw, cfg, storage=MockStorage())
+        result = _authenticate_token(raw, storage=MockStorage())
         assert result is None
 
     def test_unknown_token(self):
-        cfg = AuthConfig(enabled=True, tokens={"tok": "full"})
-        result = _authenticate_token("unknown", cfg)
+        result = _authenticate_token("unknown")
         assert result is None
 
 
@@ -282,76 +264,74 @@ class TestAuthenticateToken:
 
 
 class TestCheckRequestScopes:
-    def test_config_read_on_write_403(self):
-        cfg = AuthConfig(enabled=True, tokens={"tok_read": "read"})
-        allowed, status, msg, _ = check_request(cfg, "POST", "/api/send", "Bearer tok_read")
+    _SECRET = "test-secret-key-for-jwt-min-32b!"
+
+    def test_jwt_read_on_write_403(self):
+        jwt_tok = create_jwt("u1", frozenset({"read"}), "test", self._SECRET)
+        allowed, status, msg, _ = check_request(
+            "POST",
+            "/api/send",
+            f"Bearer {jwt_tok}",
+            jwt_secret=self._SECRET,
+        )
         assert not allowed
         assert status == 403
         assert "write" in msg
 
-    def test_config_read_on_approve_403(self):
-        cfg = AuthConfig(enabled=True, tokens={"tok_read": "read"})
-        allowed, status, msg, _ = check_request(cfg, "POST", "/api/approve", "Bearer tok_read")
+    def test_jwt_read_on_approve_403(self):
+        jwt_tok = create_jwt("u1", frozenset({"read"}), "test", self._SECRET)
+        allowed, status, msg, _ = check_request(
+            "POST",
+            "/api/approve",
+            f"Bearer {jwt_tok}",
+            jwt_secret=self._SECRET,
+        )
         assert not allowed
         assert status == 403
         assert "approve" in msg
 
-    def test_config_full_on_approve_ok(self):
-        cfg = AuthConfig(enabled=True, tokens={"tok_full": "full"})
-        allowed, status, msg, result = check_request(cfg, "POST", "/api/approve", "Bearer tok_full")
+    def test_jwt_full_on_approve_ok(self):
+        jwt_tok = create_jwt("u1", frozenset({"read", "write", "approve"}), "test", self._SECRET)
+        allowed, status, msg, result = check_request(
+            "POST",
+            "/api/approve",
+            f"Bearer {jwt_tok}",
+            jwt_secret=self._SECRET,
+        )
         assert allowed
         assert result is not None
         assert result.has_scope("approve")
 
     def test_jwt_with_scopes(self):
-        secret = "test-secret-key-for-jwt-min-32b!"
-        jwt_tok = create_jwt("u1", frozenset({"read", "write"}), "db", secret)
-        cfg = AuthConfig(enabled=True)
+        jwt_tok = create_jwt("u1", frozenset({"read", "write"}), "db", self._SECRET)
         allowed, status, msg, result = check_request(
-            cfg,
             "POST",
             "/api/send",
             f"Bearer {jwt_tok}",
-            jwt_secret=secret,
+            jwt_secret=self._SECRET,
         )
         assert allowed
         assert result is not None
         assert result.user_id == "u1"
 
     def test_jwt_insufficient_scope(self):
-        secret = "test-secret-key-for-jwt-min-32b!"
-        jwt_tok = create_jwt("u1", frozenset({"read"}), "db", secret)
-        cfg = AuthConfig(enabled=True)
+        jwt_tok = create_jwt("u1", frozenset({"read"}), "db", self._SECRET)
         allowed, status, msg, _ = check_request(
-            cfg,
             "POST",
             "/api/send",
             f"Bearer {jwt_tok}",
-            jwt_secret=secret,
+            jwt_secret=self._SECRET,
         )
         assert not allowed
         assert status == 403
 
     def test_admin_path_requires_approve(self):
-        cfg = AuthConfig(enabled=True, tokens={"tok_read": "read"})
+        jwt_tok = create_jwt("u1", frozenset({"read"}), "test", self._SECRET)
         allowed, status, msg, _ = check_request(
-            cfg,
             "GET",
             "/v1/api/admin/users",
-            "Bearer tok_read",
+            f"Bearer {jwt_tok}",
+            jwt_secret=self._SECRET,
         )
         assert not allowed
         assert status == 403
-
-    def test_backward_compat_role_full(self):
-        """Config tokens with role='full' get all scopes."""
-        cfg = AuthConfig(enabled=True, tokens={"tok_full": "full"})
-        allowed, _, _, result = check_request(
-            cfg,
-            "GET",
-            "/v1/api/admin/users",
-            "Bearer tok_full",
-        )
-        assert allowed
-        assert result is not None
-        assert result.has_scope("approve")

tests/test_bridge_events.py

@@ -1,120 +0,0 @@
-"""Tests for bridge event publishing — TurnCompleteEvent on idle transitions."""
-
-from unittest.mock import MagicMock, patch
-
-from turnstone.mq.bridge import Bridge
-from turnstone.mq.protocol import ContentEvent, StateChangeEvent, TurnCompleteEvent
-
-
-def _make_bridge():
-    """Create a Bridge with a mock broker (no Redis or HTTP needed)."""
-    broker = MagicMock()
-    bridge = Bridge(server_url="http://localhost:8080", broker=broker, node_id="test-node")
-    return bridge
-
-
-class TestIdleTurnComplete:
-    """TurnCompleteEvent should be emitted on every idle transition."""
-
-    def test_idle_emits_turn_complete_with_correlation_id(self):
-        """Bridge-initiated turn: TurnCompleteEvent has the correlation_id."""
-        bridge = _make_bridge()
-        bridge._active_sends["ws-1"] = "cid-abc"
-
-        published = []
-        with patch.object(
-            bridge, "_publish_ws", side_effect=lambda ws, ev: published.append((ws, ev))
-        ):
-            bridge._handle_global_event({"type": "ws_state", "ws_id": "ws-1", "state": "idle"})
-
-        turn_completes = [(ws, ev) for ws, ev in published if isinstance(ev, TurnCompleteEvent)]
-        assert len(turn_completes) == 1
-        ws, ev = turn_completes[0]
-        assert ws == "ws-1"
-        assert ev.correlation_id == "cid-abc"
-        # correlation_id should be removed from _active_sends
-        assert "ws-1" not in bridge._active_sends
-
-    def test_idle_emits_turn_complete_without_correlation_id(self):
-        """Server-UI-initiated turn: TurnCompleteEvent has empty correlation_id."""
-        bridge = _make_bridge()
-        # No entry in _active_sends for this workstream
-
-        published = []
-        with patch.object(
-            bridge, "_publish_ws", side_effect=lambda ws, ev: published.append((ws, ev))
-        ):
-            bridge._handle_global_event({"type": "ws_state", "ws_id": "ws-2", "state": "idle"})
-
-        turn_completes = [(ws, ev) for ws, ev in published if isinstance(ev, TurnCompleteEvent)]
-        assert len(turn_completes) == 1
-        ws, ev = turn_completes[0]
-        assert ws == "ws-2"
-        assert ev.correlation_id == ""
-
-    def test_non_idle_state_does_not_emit_turn_complete(self):
-        """Non-idle state transitions should emit StateChangeEvent but not TurnCompleteEvent."""
-        bridge = _make_bridge()
-
-        published = []
-        with patch.object(
-            bridge, "_publish_ws", side_effect=lambda ws, ev: published.append((ws, ev))
-        ):
-            bridge._handle_global_event({"type": "ws_state", "ws_id": "ws-3", "state": "thinking"})
-
-        state_changes = [ev for _, ev in published if isinstance(ev, StateChangeEvent)]
-        turn_completes = [ev for _, ev in published if isinstance(ev, TurnCompleteEvent)]
-        assert len(state_changes) == 1
-        assert state_changes[0].state == "thinking"
-        assert len(turn_completes) == 0
-
-
-class TestContentPassthrough:
-    """Bridge should pass through content from the server's idle SSE event."""
-
-    def test_content_passed_through_in_turn_complete(self):
-        """Content from idle event should be included in TurnCompleteEvent."""
-        bridge = _make_bridge()
-
-        published = []
-        with patch.object(
-            bridge, "_publish_ws", side_effect=lambda ws, ev: published.append((ws, ev))
-        ):
-            bridge._handle_global_event(
-                {"type": "ws_state", "ws_id": "ws-1", "state": "idle", "content": "Hello world"}
-            )
-
-        turn_completes = [(ws, ev) for ws, ev in published if isinstance(ev, TurnCompleteEvent)]
-        assert len(turn_completes) == 1
-        _, ev = turn_completes[0]
-        assert ev.content == "Hello world"
-
-    def test_content_empty_when_not_in_event(self):
-        """TurnCompleteEvent.content should be empty when idle event has no content."""
-        bridge = _make_bridge()
-
-        published = []
-        with patch.object(
-            bridge, "_publish_ws", side_effect=lambda ws, ev: published.append((ws, ev))
-        ):
-            bridge._handle_global_event({"type": "ws_state", "ws_id": "ws-1", "state": "idle"})
-
-        turn_completes = [(ws, ev) for ws, ev in published if isinstance(ev, TurnCompleteEvent)]
-        assert len(turn_completes) == 1
-        _, ev = turn_completes[0]
-        assert ev.content == ""
-
-    def test_content_event_still_published(self):
-        """Content events should still be published to per-ws channel."""
-        bridge = _make_bridge()
-
-        published = []
-        with patch.object(
-            bridge, "_publish_ws", side_effect=lambda ws, ev: published.append((ws, ev))
-        ):
-            bridge._handle_ws_event("ws-1", {"type": "content", "text": "hello"})
-
-        content_events = [(ws, ev) for ws, ev in published if isinstance(ev, ContentEvent)]
-        assert len(content_events) == 1
-        _, ev = content_events[0]
-        assert ev.text == "hello"

tests/test_bridge_stress.py

@@ -1,357 +0,0 @@
-"""Stress tests for bridge.py threading — race conditions in approval,
-plan review, and workstream lifecycle.
-
-Each scenario is run many times (ITERATIONS) with threading.Barrier to
-maximize timing overlap.  Uses mock broker (no Redis) and no HTTP calls.
-
-Races tested:
-1. Duplicate approval on SSE reconnect (TOCTOU in _pending_approvals)
-2. Duplicate plan review on SSE reconnect (TOCTOU in _pending_plan_reviews)
-3. approve_set stale reference escape during concurrent update
-4. _running flag visibility across threads on shutdown
-5. Approval thread exits within bounded time after timeout
-6. Concurrent approval + workstream close leaves no orphaned state
-"""
-
-from __future__ import annotations
-
-import threading
-import time
-from collections import Counter
-from unittest.mock import MagicMock, patch
-
-from turnstone.mq.bridge import Bridge
-
-ITERATIONS = 100
-
-# ---------------------------------------------------------------------------
-# Helpers
-# ---------------------------------------------------------------------------
-
-
-def _make_bridge(**overrides) -> Bridge:
-    """Create a Bridge with a mock broker (no Redis or HTTP)."""
-    broker = MagicMock()
-    defaults = dict(
-        server_url="http://localhost:8080",
-        broker=broker,
-        node_id="test-node",
-        approval_timeout=1,
-    )
-    defaults.update(overrides)
-    bridge = Bridge(**defaults)
-    # Replace real httpx client with a mock so daemon threads spawned by
-    # _handle_approval / _handle_plan_review don't make real HTTP calls
-    # after the test's patch context exits.
-    bridge._http.close()
-    bridge._http = MagicMock()
-    return bridge
-
-
-def _approval_items(tool_name: str = "bash") -> list[dict]:
-    return [{"func_name": tool_name, "needs_approval": True, "approval_label": tool_name}]
-
-
-def _wait_pending_resolved(bridge: Bridge, key: str, attr: str, deadline_s: float = 3.0) -> bool:
-    """Poll until the pending entry is resolved (tombstone) or absent."""
-    deadline = time.monotonic() + deadline_s
-    while time.monotonic() < deadline:
-        with bridge._lock:
-            entries = getattr(bridge, attr)
-            if key not in entries:
-                return True
-            _, resolved_at = entries[key]
-            if resolved_at > 0:
-                return True
-        time.sleep(0.01)
-    return False
-
-
-# ---------------------------------------------------------------------------
-# Race 1: Duplicate approval on SSE reconnect
-# ---------------------------------------------------------------------------
-
-
-class TestDuplicateApproval:
-    """Two threads call _handle_approval for the same ws_id simultaneously.
-    Only one should create a pending entry; the other should be skipped."""
-
-    def test_no_duplicate_approvals(self):
-        sent_count = Counter()
-
-        for _ in range(ITERATIONS):
-            bridge = _make_bridge()
-            bridge._broker.pop_response.return_value = '{"type": "approve", "approved": true}'
-            barrier = threading.Barrier(2, timeout=5)
-
-            def _call_approval(bridge=bridge, barrier=barrier):
-                barrier.wait()
-                bridge._handle_approval("ws-1", {"items": _approval_items()})
-
-            t1 = threading.Thread(target=_call_approval)
-            t2 = threading.Thread(target=_call_approval)
-            with (
-                patch.object(bridge, "_api_approve") as mock_approve,
-                patch.object(bridge, "_publish_ws"),
-            ):
-                t1.start()
-                t2.start()
-                t1.join(timeout=5)
-                t2.join(timeout=5)
-                assert not t1.is_alive(), "Thread 1 hung"
-                assert not t2.is_alive(), "Thread 2 hung"
-
-                # Wait for spawned _wait_approval threads to resolve
-                _wait_pending_resolved(bridge, "ws-1", "_pending_approvals")
-
-                sent_count[mock_approve.call_count] += 1
-
-        # At most 1 approval should be forwarded per iteration
-        assert sent_count.get(2, 0) == 0, (
-            f"Duplicate approvals sent in {sent_count[2]}/{ITERATIONS} iterations"
-        )
-
-
-# ---------------------------------------------------------------------------
-# Race 2: Duplicate plan review on SSE reconnect
-# ---------------------------------------------------------------------------
-
-
-class TestDuplicatePlanReview:
-    """Two threads call _handle_plan_review simultaneously.
-    Only one should create a pending entry."""
-
-    def test_no_duplicate_plan_reviews(self):
-        sent_count = Counter()
-
-        for _ in range(ITERATIONS):
-            bridge = _make_bridge()
-            bridge._broker.pop_response.return_value = (
-                '{"type": "plan_feedback", "feedback": "looks good"}'
-            )
-            barrier = threading.Barrier(2, timeout=5)
-
-            def _call_plan(bridge=bridge, barrier=barrier):
-                barrier.wait()
-                bridge._handle_plan_review("ws-1", {"content": "plan text"})
-
-            t1 = threading.Thread(target=_call_plan)
-            t2 = threading.Thread(target=_call_plan)
-            with patch.object(bridge, "_publish_ws"), patch.object(bridge._http, "post"):
-                t1.start()
-                t2.start()
-                t1.join(timeout=5)
-                t2.join(timeout=5)
-                assert not t1.is_alive(), "Thread 1 hung"
-                assert not t2.is_alive(), "Thread 2 hung"
-
-                # Wait for spawned _wait_plan threads to resolve
-                _wait_pending_resolved(bridge, "ws-1", "_pending_plan_reviews")
-
-                sent_count[bridge._http.post.call_count] += 1
-
-        assert sent_count.get(2, 0) == 0, (
-            f"Duplicate plan reviews sent in {sent_count[2]}/{ITERATIONS} iterations"
-        )
-
-
-# ---------------------------------------------------------------------------
-# Race 3: approve_set stale reference during concurrent update
-# ---------------------------------------------------------------------------
-
-
-class TestApproveSetConsistency:
-    """One thread reads approve_set for auto-approve check while another
-    updates it via _wait_approval 'always' path.  The auto-approve
-    decision should be consistent (either all-approved or not)."""
-
-    def test_approve_set_never_partially_visible(self):
-        for _ in range(ITERATIONS):
-            bridge = _make_bridge()
-            with bridge._lock:
-                bridge._ws_approve_tools["ws-1"] = {"read_file", "search"}
-
-            barrier = threading.Barrier(2, timeout=5)
-            results = []
-
-            def _reader(bridge=bridge, barrier=barrier, results=results):
-                barrier.wait()
-                with bridge._lock:
-                    snap = bridge._ws_approve_tools.get("ws-1", set()).copy()
-                results.append(snap)
-
-            def _writer(bridge=bridge, barrier=barrier):
-                barrier.wait()
-                with bridge._lock:
-                    existing = bridge._ws_approve_tools.get("ws-1", set())
-                    bridge._ws_approve_tools["ws-1"] = existing | {"bash", "write_file"}
-
-            t1 = threading.Thread(target=_reader)
-            t2 = threading.Thread(target=_writer)
-            t1.start()
-            t2.start()
-            t1.join(timeout=5)
-            t2.join(timeout=5)
-            assert not t1.is_alive(), "Reader hung"
-            assert not t2.is_alive(), "Writer hung"
-
-            snap = results[0]
-            assert snap in (
-                {"read_file", "search"},
-                {"read_file", "search", "bash", "write_file"},
-            ), f"Partial set observed: {snap}"
-
-
-# ---------------------------------------------------------------------------
-# Race 4: _running flag visibility across threads
-# ---------------------------------------------------------------------------
-
-
-class TestRunningFlagVisibility:
-    """All threads reading _running should see False within a bounded time
-    after the main thread sets it."""
-
-    def test_all_threads_observe_shutdown(self):
-        bridge = _make_bridge()
-        observed_false = threading.Event()
-        threads_running = []
-
-        def _spin_checker():
-            while bridge._running:
-                time.sleep(0.001)
-            observed_false.set()
-
-        for _ in range(5):
-            t = threading.Thread(target=_spin_checker, daemon=True)
-            threads_running.append(t)
-            t.start()
-
-        time.sleep(0.01)
-        bridge._running = False
-
-        for t in threads_running:
-            t.join(timeout=1)
-            assert not t.is_alive(), "Thread did not observe _running=False"
-
-        assert observed_false.is_set()
-
-
-# ---------------------------------------------------------------------------
-# Race 5: Approval thread exits within bounded time
-# ---------------------------------------------------------------------------
-
-
-class TestApprovalThreadTimeout:
-    """An approval thread blocked on pop_response should exit within the
-    configured approval_timeout, not hang indefinitely."""
-
-    def test_approval_thread_exits_within_timeout(self):
-        for _ in range(10):
-            bridge = _make_bridge(approval_timeout=0.5)
-
-            def _slow_pop(queue_name, timeout=300):
-                time.sleep(min(timeout, 0.5))
-                return None
-
-            bridge._broker.pop_response.side_effect = _slow_pop
-
-            with patch.object(bridge, "_publish_ws"), patch.object(bridge, "_api_approve"):
-                bridge._handle_approval("ws-1", {"items": _approval_items()})
-
-            # The pending entry should be resolved within the timeout
-            resolved = _wait_pending_resolved(bridge, "ws-1", "_pending_approvals", deadline_s=3.0)
-            assert resolved, "Approval thread did not exit within expected timeout"
-
-
-# ---------------------------------------------------------------------------
-# Race 6: Concurrent approval + workstream close
-# ---------------------------------------------------------------------------
-
-
-class TestApprovalDuringClose:
-    """An approval arriving at the exact same time as a ws_closed event
-    should not leave orphaned state."""
-
-    def test_no_orphaned_pending_after_close(self):
-        for _ in range(ITERATIONS):
-            bridge = _make_bridge(approval_timeout=0.1)
-            bridge._broker.pop_response.return_value = None  # timeout
-
-            barrier = threading.Barrier(2, timeout=5)
-
-            def _send_approval(bridge=bridge, barrier=barrier):
-                barrier.wait()
-                with patch.object(bridge, "_publish_ws"), patch.object(bridge, "_api_approve"):
-                    bridge._handle_approval("ws-1", {"items": _approval_items()})
-
-            def _close_ws(bridge=bridge, barrier=barrier):
-                barrier.wait()
-                with (
-                    patch.object(bridge, "_publish_global"),
-                    patch.object(bridge, "_publish_cluster"),
-                ):
-                    bridge._handle_global_event({"type": "ws_closed", "ws_id": "ws-1"})
-
-            t1 = threading.Thread(target=_send_approval)
-            t2 = threading.Thread(target=_close_ws)
-            t1.start()
-            t2.start()
-            t1.join(timeout=5)
-            t2.join(timeout=5)
-            assert not t1.is_alive(), "Approval thread hung"
-            assert not t2.is_alive(), "Close thread hung"
-
-            # Wait for spawned _wait_approval thread to resolve (if close
-            # didn't remove the entry first)
-            resolved = _wait_pending_resolved(bridge, "ws-1", "_pending_approvals")
-            assert resolved, "Orphaned pending approval"
-
-
-# ---------------------------------------------------------------------------
-# Race 7: Plan review refinement loop (tombstone → cleanup → re-entry)
-# ---------------------------------------------------------------------------
-
-
-class TestPlanReviewRefinementLoop:
-    """After a plan review is resolved, a ws_state event should clean up the
-    tombstone so the refinement-loop plan_review event is handled correctly."""
-
-    def test_refinement_loop_allows_reentry(self):
-        for _ in range(ITERATIONS):
-            bridge = _make_bridge()
-            bridge._broker.pop_response.return_value = (
-                '{"type": "plan_feedback", "feedback": "refine this"}'
-            )
-
-            # Step 1: first plan review — creates pending entry, resolves it
-            with patch.object(bridge, "_publish_ws"), patch.object(bridge._http, "post"):
-                bridge._handle_plan_review("ws-1", {"content": "plan v1"})
-
-            _wait_pending_resolved(bridge, "ws-1", "_pending_plan_reviews")
-
-            # Verify tombstone is present (resolved_at > 0)
-            with bridge._lock:
-                assert "ws-1" in bridge._pending_plan_reviews
-                assert bridge._pending_plan_reviews["ws-1"][1] > 0
-
-            # Step 2: ws_state event cleans up the resolved tombstone
-            with (
-                patch.object(bridge, "_publish_ws"),
-                patch.object(bridge, "_publish_global"),
-                patch.object(bridge, "_publish_cluster"),
-            ):
-                bridge._handle_global_event(
-                    {"type": "ws_state", "ws_id": "ws-1", "state": "working"}
-                )
-
-            with bridge._lock:
-                assert "ws-1" not in bridge._pending_plan_reviews
-
-            # Step 3: refinement plan_review arrives — should create new entry
-            with patch.object(bridge, "_publish_ws"), patch.object(bridge._http, "post"):
-                bridge._handle_plan_review("ws-1", {"content": "plan v2"})
-
-            _wait_pending_resolved(bridge, "ws-1", "_pending_plan_reviews")
-
-            with bridge._lock:
-                assert "ws-1" in bridge._pending_plan_reviews

tests/test_channel_discord.py

@@ -76,8 +76,7 @@ class TestDiscordConfig:
         assert cfg.max_message_length == 2000
         assert cfg.streaming_edit_interval == 1.5
         # Inherited from ChannelConfig
-        assert cfg.redis_host == "localhost"
-        assert cfg.redis_port == 6379
+        assert cfg.server_url == "http://localhost:8080"
         assert cfg.model == ""
         assert cfg.auto_approve is False
 
@@ -230,13 +229,15 @@ class TestMessageCog:
 
         ts.router.send_message.assert_not_awaited()
 
-    def test_ignores_dms(self):
+    def test_dm_without_reference_sends_guidance(self):
         cog, ts, _bot = self._make_cog()
-        msg = _make_message(guild=False)
+        dm_channel = AsyncMock()
+        msg = _make_message(guild=False, channel=dm_channel)
 
         _run(cog._on_message(msg))
 
         ts.router.send_message.assert_not_awaited()
+        dm_channel.send.assert_awaited_once()
 
     def test_ignores_non_allowed_channels(self):
         cog, ts, _bot = self._make_cog()
@@ -316,12 +317,12 @@ class TestParseFooter:
 
 
 class TestWsEventFinalization:
-    """TurnCompleteEvent should finalize streaming messages in the Discord bot."""
+    """StreamEndEvent should finalize streaming messages in the Discord bot."""
 
-    def test_turn_complete_finalizes_streaming(self):
-        """ContentEvent + TurnCompleteEvent(correlation_id='') finalizes the message."""
+    def test_stream_end_finalizes_streaming(self):
+        """ContentEvent + StreamEndEvent finalizes the message."""
         from turnstone.channels.discord.bot import TurnstoneBot
-        from turnstone.mq.protocol import ContentEvent, TurnCompleteEvent
+        from turnstone.sdk.events import ContentEvent, StreamEndEvent
 
         bot = MagicMock(spec=TurnstoneBot)
         bot.config = MagicMock()
@@ -330,6 +331,8 @@ class TestWsEventFinalization:
         bot.config.auto_approve = False
         bot.config.auto_approve_tools = []
         bot._streaming = {}
+        bot._thinking_msgs = {}
+        bot._tool_info_msgs = {}
         bot._pending_approval_msgs = {}
         bot._notify_reply_channels = {}
 
@@ -339,34 +342,36 @@ class TestWsEventFinalization:
         thread = AsyncMock()
 
         # Feed content event
-        content_raw = ContentEvent(ws_id="ws-1", text="Hello world").to_json()
-        _run(bot._on_ws_event("ws-1", thread, content_raw))
+        content_event = ContentEvent(ws_id="ws-1", text="Hello world")
+        _run(bot._on_ws_event("ws-1", thread, content_event))
 
         # StreamingMessage should exist
         assert "ws-1" in bot._streaming
 
-        # Feed turn complete with empty correlation_id (server-UI-initiated)
-        complete_raw = TurnCompleteEvent(ws_id="ws-1", correlation_id="").to_json()
-        _run(bot._on_ws_event("ws-1", thread, complete_raw))
+        # Feed stream end
+        end_event = StreamEndEvent(ws_id="ws-1")
+        _run(bot._on_ws_event("ws-1", thread, end_event))
 
         # StreamingMessage should be removed and finalized
         assert "ws-1" not in bot._streaming
 
-    def test_turn_complete_no_streaming_is_noop(self):
-        """TurnCompleteEvent without prior content should not error."""
+    def test_stream_end_no_streaming_is_noop(self):
+        """StreamEndEvent without prior content should not error."""
         from turnstone.channels.discord.bot import TurnstoneBot
-        from turnstone.mq.protocol import TurnCompleteEvent
+        from turnstone.sdk.events import StreamEndEvent
 
         bot = MagicMock(spec=TurnstoneBot)
         bot._streaming = {}
+        bot._thinking_msgs = {}
+        bot._tool_info_msgs = {}
         bot._pending_approval_msgs = {}
         bot._notify_reply_channels = {}
         bot._on_ws_event = TurnstoneBot._on_ws_event.__get__(bot, TurnstoneBot)
 
         thread = AsyncMock()
 
-        complete_raw = TurnCompleteEvent(ws_id="ws-1", correlation_id="").to_json()
-        _run(bot._on_ws_event("ws-1", thread, complete_raw))
+        end_event = StreamEndEvent(ws_id="ws-1")
+        _run(bot._on_ws_event("ws-1", thread, end_event))
 
         # No error, no streaming message
         assert "ws-1" not in bot._streaming
@@ -392,6 +397,8 @@ class TestApprovalVerdictDisplay:
         bot.config.auto_approve_tools = []
         bot.storage = None
         bot._streaming = {}
+        bot._thinking_msgs = {}
+        bot._tool_info_msgs = {}
         bot._pending_approval_msgs = {}
         bot._notify_reply_channels = {}
         bot._should_auto_approve = MagicMock(return_value=False)
@@ -399,8 +406,8 @@ class TestApprovalVerdictDisplay:
         return bot
 
     def test_approval_with_heuristic_verdict(self):
-        """ApprovalRequestEvent items with verdict dicts add embed fields."""
-        from turnstone.mq.protocol import ApprovalRequestEvent
+        """ApproveRequestEvent items with verdict dicts add embed fields."""
+        from turnstone.sdk.events import ApproveRequestEvent
 
         bot = self._make_bot()
         thread = AsyncMock()
@@ -421,8 +428,8 @@ class TestApprovalVerdictDisplay:
                 },
             }
         ]
-        raw = ApprovalRequestEvent(ws_id="ws-1", correlation_id="corr-1", items=items).to_json()
-        _run(bot._on_ws_event("ws-1", thread, raw))
+        event = ApproveRequestEvent(ws_id="ws-1", items=items)
+        _run(bot._on_ws_event("ws-1", thread, event))
 
         # thread.send was called with an embed containing a verdict field
         thread.send.assert_awaited_once()
@@ -439,8 +446,8 @@ class TestApprovalVerdictDisplay:
         assert "ws-1" in bot._pending_approval_msgs
 
     def test_approval_without_verdict(self):
-        """ApprovalRequestEvent items without verdict still work normally."""
-        from turnstone.mq.protocol import ApprovalRequestEvent
+        """ApproveRequestEvent items without verdict still work normally."""
+        from turnstone.sdk.events import ApproveRequestEvent
 
         bot = self._make_bot()
         thread = AsyncMock()
@@ -448,8 +455,8 @@ class TestApprovalVerdictDisplay:
         thread.send = AsyncMock(return_value=sent_msg)
 
         items = [{"func_name": "read_file", "preview": "/etc/hosts", "needs_approval": True}]
-        raw = ApprovalRequestEvent(ws_id="ws-1", correlation_id="corr-1", items=items).to_json()
-        _run(bot._on_ws_event("ws-1", thread, raw))
+        event = ApproveRequestEvent(ws_id="ws-1", items=items)
+        _run(bot._on_ws_event("ws-1", thread, event))
 
         thread.send.assert_awaited_once()
         call_kwargs = thread.send.call_args[1]
@@ -459,7 +466,7 @@ class TestApprovalVerdictDisplay:
 
     def test_intent_verdict_event_updates_embed(self):
         """IntentVerdictEvent should update the pending approval embed."""
-        from turnstone.mq.protocol import IntentVerdictEvent
+        from turnstone.sdk.events import IntentVerdictEvent
 
         bot = self._make_bot()
         thread = AsyncMock()
@@ -471,7 +478,7 @@ class TestApprovalVerdictDisplay:
         msg.edit = AsyncMock()
         bot._pending_approval_msgs["ws-1"] = msg
 
-        raw = IntentVerdictEvent(
+        event = IntentVerdictEvent(
             ws_id="ws-1",
             func_name="bash",
             risk_level="high",
@@ -479,8 +486,8 @@ class TestApprovalVerdictDisplay:
             confidence=0.9,
             intent_summary="Dangerous operation",
             tier="llm",
-        ).to_json()
-        _run(bot._on_ws_event("ws-1", thread, raw))
+        )
+        _run(bot._on_ws_event("ws-1", thread, event))
 
         # Embed should be updated with the judge verdict field
         embed.add_field.assert_called_once()
@@ -494,35 +501,37 @@ class TestApprovalVerdictDisplay:
 
     def test_intent_verdict_without_pending_approval_is_noop(self):
         """IntentVerdictEvent without a pending approval message should not error."""
-        from turnstone.mq.protocol import IntentVerdictEvent
+        from turnstone.sdk.events import IntentVerdictEvent
 
         bot = self._make_bot()
         thread = AsyncMock()
 
-        raw = IntentVerdictEvent(ws_id="ws-1", func_name="bash", risk_level="low").to_json()
+        event = IntentVerdictEvent(ws_id="ws-1", func_name="bash", risk_level="low")
         # Should not raise
-        _run(bot._on_ws_event("ws-1", thread, raw))
+        _run(bot._on_ws_event("ws-1", thread, event))
 
-    def test_turn_complete_clears_pending_approval(self):
-        """TurnCompleteEvent should clean up the pending approval message tracking."""
+    def test_stream_end_clears_pending_approval(self):
+        """StreamEndEvent should clean up the pending approval message tracking."""
         from turnstone.channels.discord.bot import TurnstoneBot
-        from turnstone.mq.protocol import TurnCompleteEvent
+        from turnstone.sdk.events import StreamEndEvent
 
         bot = MagicMock(spec=TurnstoneBot)
         bot._streaming = {}
+        bot._thinking_msgs = {}
+        bot._tool_info_msgs = {}
         bot._pending_approval_msgs = {"ws-1": MagicMock()}
         bot._notify_reply_channels = {}
         bot._on_ws_event = TurnstoneBot._on_ws_event.__get__(bot, TurnstoneBot)
 
         thread = AsyncMock()
-        raw = TurnCompleteEvent(ws_id="ws-1", correlation_id="").to_json()
-        _run(bot._on_ws_event("ws-1", thread, raw))
+        event = StreamEndEvent(ws_id="ws-1")
+        _run(bot._on_ws_event("ws-1", thread, event))
 
         assert "ws-1" not in bot._pending_approval_msgs
 
 
-class TestContentCatchup:
-    """TurnCompleteEvent with content field provides catch-up for missed ContentEvents."""
+class TestStreamEndBehavior:
+    """StreamEndEvent finalizes streaming and cleans up state."""
 
     def _make_bot(self):
         from turnstone.channels.discord.bot import TurnstoneBot
@@ -534,56 +543,42 @@ class TestContentCatchup:
         bot.config.auto_approve = False
         bot.config.auto_approve_tools = []
         bot._streaming = {}
+        bot._thinking_msgs = {}
+        bot._tool_info_msgs = {}
         bot._pending_approval_msgs = {}
         bot._notify_reply_channels = {}
         bot._on_ws_event = TurnstoneBot._on_ws_event.__get__(bot, TurnstoneBot)
         return bot
 
-    def test_catchup_sends_content_when_no_streaming(self):
-        """TurnCompleteEvent with content but no SM sends catch-up message."""
-        from turnstone.mq.protocol import TurnCompleteEvent
+    def test_stream_end_no_streaming_no_send(self):
+        """StreamEndEvent without prior content should not send anything."""
+        from turnstone.sdk.events import StreamEndEvent
 
         bot = self._make_bot()
         thread = AsyncMock()
 
-        raw = TurnCompleteEvent(
-            ws_id="ws-1", correlation_id="", content="Caught up response"
-        ).to_json()
-        _run(bot._on_ws_event("ws-1", thread, raw))
+        event = StreamEndEvent(ws_id="ws-1")
+        _run(bot._on_ws_event("ws-1", thread, event))
 
-        thread.send.assert_awaited_once_with("Caught up response")
+        thread.send.assert_not_awaited()
 
-    def test_catchup_skipped_when_streaming_exists(self):
-        """TurnCompleteEvent with content and existing SM uses SM finalize, not catch-up."""
-        from turnstone.mq.protocol import ContentEvent, TurnCompleteEvent
+    def test_stream_end_finalizes_existing_streaming(self):
+        """StreamEndEvent with an existing StreamingMessage should finalize it."""
+        from turnstone.sdk.events import ContentEvent, StreamEndEvent
 
         bot = self._make_bot()
         thread = AsyncMock()
 
         # Feed content event to create SM
-        content_raw = ContentEvent(ws_id="ws-1", text="Streamed").to_json()
-        _run(bot._on_ws_event("ws-1", thread, content_raw))
+        content_event = ContentEvent(ws_id="ws-1", text="Streamed")
+        _run(bot._on_ws_event("ws-1", thread, content_event))
         assert "ws-1" in bot._streaming
 
-        # Now TurnCompleteEvent with content — SM should be finalized, not catch-up
-        complete_raw = TurnCompleteEvent(
-            ws_id="ws-1", correlation_id="", content="Streamed"
-        ).to_json()
-        _run(bot._on_ws_event("ws-1", thread, complete_raw))
+        # Now StreamEndEvent — SM should be finalized
+        end_event = StreamEndEvent(ws_id="ws-1")
+        _run(bot._on_ws_event("ws-1", thread, end_event))
         assert "ws-1" not in bot._streaming
 
-    def test_catchup_empty_content_no_message(self):
-        """TurnCompleteEvent with empty content and no SM sends nothing."""
-        from turnstone.mq.protocol import TurnCompleteEvent
-
-        bot = self._make_bot()
-        thread = AsyncMock()
-
-        raw = TurnCompleteEvent(ws_id="ws-1", correlation_id="", content="").to_json()
-        _run(bot._on_ws_event("ws-1", thread, raw))
-
-        thread.send.assert_not_awaited()
-
 
 class TestNotificationTracking:
     """Tests for notification message tracking and DM reply routing."""
@@ -719,8 +714,8 @@ class TestNotificationTracking:
         # Should send feedback to the DM channel
         dm_channel.send.assert_awaited_once_with("*This notification is no longer active.*")
 
-    def test_dm_without_reference_ignored(self):
-        """DM without a message reference should be ignored."""
+    def test_dm_without_reference_sends_guidance(self):
+        """DM without a message reference should reply with guidance."""
         from turnstone.channels.discord.cog import MessageCog
 
         bot = MagicMock()
@@ -735,11 +730,15 @@ class TestNotificationTracking:
         bot.turnstone = ts
 
         cog = MessageCog(bot)
-        msg = _make_message(guild=False)  # reference=None
+        dm_channel = AsyncMock()
+        msg = _make_message(guild=False, channel=dm_channel)  # reference=None
 
         _run(cog._on_message(msg))
 
         ts.router.send_message.assert_not_awaited()
+        dm_channel.send.assert_awaited_once()
+        sent_text = dm_channel.send.call_args[0][0]
+        assert "/ask" in sent_text
 
     def test_dm_reply_unlinked_user_ignored(self):
         """DM reply from an unlinked user should be ignored."""
@@ -767,15 +766,18 @@ class TestNotificationTracking:
 
         ts.router.send_message.assert_not_awaited()
 
-    def test_turn_complete_forwards_to_dm(self):
-        """TurnCompleteEvent should forward content to notification reply DM."""
+    def test_stream_end_forwards_accumulated_content_to_dm(self):
+        """StreamEndEvent should forward accumulated content to notification reply DM."""
         from turnstone.channels.discord.bot import TurnstoneBot
-        from turnstone.mq.protocol import TurnCompleteEvent
+        from turnstone.sdk.events import ContentEvent, StreamEndEvent
 
         bot = MagicMock(spec=TurnstoneBot)
         bot.config = MagicMock()
         bot.config.max_message_length = 2000
+        bot.config.streaming_edit_interval = 1.5
         bot._streaming = {}
+        bot._thinking_msgs = {}
+        bot._tool_info_msgs = {}
         bot._pending_approval_msgs = {}
         bot._notify_ws_map = {}
         bot._MAX_NOTIFY_TRACKING = 100
@@ -790,10 +792,13 @@ class TestNotificationTracking:
 
         thread = AsyncMock()
 
-        raw = TurnCompleteEvent(
-            ws_id="ws-1", correlation_id="", content="Here's the response"
-        ).to_json()
-        _run(bot._on_ws_event("ws-1", thread, raw))
+        # Feed content events to accumulate buffer
+        content_event = ContentEvent(ws_id="ws-1", text="Here's the response")
+        _run(bot._on_ws_event("ws-1", thread, content_event))
+
+        # Feed stream end — should finalize and forward to DM
+        end_event = StreamEndEvent(ws_id="ws-1")
+        _run(bot._on_ws_event("ws-1", thread, end_event))
 
         # Should send to DM channel
         dm_channel.send.assert_awaited_once_with("Here's the response")
@@ -803,13 +808,15 @@ class TestNotificationTracking:
         assert 88888 in bot._notify_ws_map
         assert bot._notify_ws_map[88888] == ("ws-1", "u123")
 
-    def test_turn_complete_cleans_up_dm_even_without_content(self):
-        """TurnCompleteEvent without content should still clean up DM tracking."""
+    def test_stream_end_cleans_up_dm_even_without_content(self):
+        """StreamEndEvent without prior content should still clean up DM tracking."""
         from turnstone.channels.discord.bot import TurnstoneBot
-        from turnstone.mq.protocol import TurnCompleteEvent
+        from turnstone.sdk.events import StreamEndEvent
 
         bot = MagicMock(spec=TurnstoneBot)
         bot._streaming = {}
+        bot._thinking_msgs = {}
+        bot._tool_info_msgs = {}
         bot._pending_approval_msgs = {}
         bot._notify_ws_map = {}
 
@@ -819,8 +826,8 @@ class TestNotificationTracking:
 
         thread = AsyncMock()
 
-        raw = TurnCompleteEvent(ws_id="ws-1", correlation_id="", content="").to_json()
-        _run(bot._on_ws_event("ws-1", thread, raw))
+        end_event = StreamEndEvent(ws_id="ws-1")
+        _run(bot._on_ws_event("ws-1", thread, end_event))
 
         # DM should not be sent to (no content)
         dm_channel.send.assert_not_awaited()
@@ -830,6 +837,482 @@ class TestNotificationTracking:
         assert len(bot._notify_ws_map) == 0
 
 
+# ---------------------------------------------------------------------------
+# Formatter: format_tool_result
+# ---------------------------------------------------------------------------
+
+
+class TestFormatToolResult:
+    """Tests for format_tool_result in _formatter.py."""
+
+    def test_basic_output(self):
+        from turnstone.channels._formatter import format_tool_result
+
+        result = format_tool_result("hello world")
+        assert "```" in result
+        assert "hello world" in result
+
+    def test_wraps_in_code_block(self):
+        from turnstone.channels._formatter import format_tool_result
+
+        result = format_tool_result("output text")
+        assert result.startswith("```\n")
+        assert result.endswith("\n```")
+
+    def test_truncates_long_output_by_lines(self):
+        from turnstone.channels._formatter import format_tool_result
+
+        output = "\n".join(f"line {i}" for i in range(20))
+        result = format_tool_result(output)
+        # Should have at most 10 content lines + ellipsis
+        inner = result.split("```")[1]
+        assert inner.strip().count("\n") <= 11
+
+    def test_truncates_long_output_by_chars(self):
+        from turnstone.channels._formatter import format_tool_result
+
+        output = "x" * 600
+        result = format_tool_result(output)
+        # Code block content should be <= 500 chars (497 + ellipsis)
+        inner = result.split("```")[1].strip()
+        assert len(inner) <= 501  # 497 + ellipsis char
+
+    def test_escapes_triple_backticks_in_output(self):
+        from turnstone.channels._formatter import format_tool_result
+
+        output = "before ``` after"
+        result = format_tool_result(output)
+        # Only the opening and closing code fences should remain as ```.
+        assert result.count("```") == 2
+
+
+# ---------------------------------------------------------------------------
+# Thinking indicator lifecycle
+# ---------------------------------------------------------------------------
+
+
+class TestThinkingIndicator:
+    """Tests for ThinkingStart/Stop event handling in the Discord bot."""
+
+    def _make_bot(self):
+        from turnstone.channels.discord.bot import TurnstoneBot
+
+        bot = MagicMock(spec=TurnstoneBot)
+        bot.config = MagicMock()
+        bot.config.max_message_length = 2000
+        bot.config.streaming_edit_interval = 1.5
+        bot.config.auto_approve = False
+        bot.config.auto_approve_tools = []
+        bot.storage = None
+        bot._streaming = {}
+        bot._thinking_msgs = {}
+        bot._tool_info_msgs = {}
+        bot._pending_approval_msgs = {}
+        bot._notify_reply_channels = {}
+        bot._should_auto_approve = MagicMock(return_value=False)
+        bot._on_ws_event = TurnstoneBot._on_ws_event.__get__(bot, TurnstoneBot)
+        return bot
+
+    def test_thinking_start_sends_message(self):
+        from turnstone.sdk.events import ThinkingStartEvent
+
+        bot = self._make_bot()
+        thread = AsyncMock()
+        sent_msg = MagicMock()
+        thread.send = AsyncMock(return_value=sent_msg)
+
+        event = ThinkingStartEvent(ws_id="ws-1")
+        _run(bot._on_ws_event("ws-1", thread, event))
+
+        thread.send.assert_awaited_once_with("*Thinking...*")
+        assert bot._thinking_msgs["ws-1"] is sent_msg
+
+    def test_thinking_stop_preserves_message_for_reuse(self):
+        from turnstone.sdk.events import ThinkingStopEvent
+
+        bot = self._make_bot()
+        thread = AsyncMock()
+        thinking_msg = MagicMock()
+        thinking_msg.delete = AsyncMock()
+        bot._thinking_msgs["ws-1"] = thinking_msg
+
+        event = ThinkingStopEvent(ws_id="ws-1")
+        _run(bot._on_ws_event("ws-1", thread, event))
+
+        # Message kept for next event to reuse via edit.
+        thinking_msg.delete.assert_not_awaited()
+        assert "ws-1" in bot._thinking_msgs
+
+    def test_thinking_stop_without_message_is_noop(self):
+        from turnstone.sdk.events import ThinkingStopEvent
+
+        bot = self._make_bot()
+        thread = AsyncMock()
+
+        event = ThinkingStopEvent(ws_id="ws-1")
+        _run(bot._on_ws_event("ws-1", thread, event))
+
+    def test_content_event_reuses_thinking_message(self):
+        from turnstone.sdk.events import ContentEvent
+
+        bot = self._make_bot()
+        thread = AsyncMock()
+        thinking_msg = MagicMock()
+        thinking_msg.edit = AsyncMock()
+        bot._thinking_msgs["ws-1"] = thinking_msg
+
+        event = ContentEvent(ws_id="ws-1", text="Hello")
+        _run(bot._on_ws_event("ws-1", thread, event))
+
+        # Thinking message becomes the StreamingMessage base — no delete.
+        assert "ws-1" not in bot._thinking_msgs
+        sm = bot._streaming["ws-1"]
+        assert sm._message is thinking_msg
+
+    def test_stream_end_clears_thinking_message(self):
+        from turnstone.sdk.events import StreamEndEvent
+
+        bot = self._make_bot()
+        thread = AsyncMock()
+        thinking_msg = MagicMock()
+        thinking_msg.delete = AsyncMock()
+        bot._thinking_msgs["ws-1"] = thinking_msg
+        bot._notify_reply_channels = {}
+
+        event = StreamEndEvent(ws_id="ws-1")
+        _run(bot._on_ws_event("ws-1", thread, event))
+
+        thinking_msg.delete.assert_awaited_once()
+        assert "ws-1" not in bot._thinking_msgs
+
+
+# ---------------------------------------------------------------------------
+# Tool info / result embeds
+# ---------------------------------------------------------------------------
+
+
+class TestToolInfoEvent:
+    """Tests for ToolInfoEvent handling in the Discord bot."""
+
+    def _make_bot(self):
+        from turnstone.channels.discord.bot import TurnstoneBot
+
+        bot = MagicMock(spec=TurnstoneBot)
+        bot.config = MagicMock()
+        bot.config.max_message_length = 2000
+        bot.config.streaming_edit_interval = 1.5
+        bot.config.auto_approve = False
+        bot.config.auto_approve_tools = []
+        bot.storage = None
+        bot._streaming = {}
+        bot._thinking_msgs = {}
+        bot._tool_info_msgs = {}
+        bot._pending_approval_msgs = {}
+        bot._notify_reply_channels = {}
+        bot._should_auto_approve = MagicMock(return_value=False)
+        bot._on_ws_event = TurnstoneBot._on_ws_event.__get__(bot, TurnstoneBot)
+        return bot
+
+    def test_sends_per_item_embed(self):
+        from turnstone.sdk.events import ToolInfoEvent
+
+        bot = self._make_bot()
+        thread = AsyncMock()
+        sent_msg = MagicMock()
+        thread.send = AsyncMock(return_value=sent_msg)
+
+        items = [{"func_name": "bash", "preview": "ls -la", "needs_approval": False}]
+        event = ToolInfoEvent(ws_id="ws-1", items=items)
+        _run(bot._on_ws_event("ws-1", thread, event))
+
+        thread.send.assert_awaited_once()
+        embed = thread.send.call_args[1]["embed"]
+        assert embed.title == "bash"
+        assert embed.description == "ls -la"
+        # Message tracked for later editing by ToolResultEvent.
+        assert bot._tool_info_msgs["ws-1"] == [("", "bash", "ls -la", sent_msg)]
+
+    def test_multiple_tools_send_multiple_embeds(self):
+        from turnstone.sdk.events import ToolInfoEvent
+
+        bot = self._make_bot()
+        thread = AsyncMock()
+
+        items = [
+            {"func_name": "bash", "preview": "ls", "needs_approval": False},
+            {"func_name": "read_file", "preview": "/etc", "needs_approval": False},
+        ]
+        event = ToolInfoEvent(ws_id="ws-1", items=items)
+        _run(bot._on_ws_event("ws-1", thread, event))
+
+        assert thread.send.await_count == 2
+        assert len(bot._tool_info_msgs["ws-1"]) == 2
+
+    def test_shows_all_items_regardless_of_approval(self):
+        from turnstone.sdk.events import ToolInfoEvent
+
+        bot = self._make_bot()
+        thread = AsyncMock()
+
+        items = [
+            {"func_name": "bash", "preview": "rm -rf /", "needs_approval": True},
+            {"func_name": "read_file", "preview": "/etc/hosts", "needs_approval": False},
+        ]
+        event = ToolInfoEvent(ws_id="ws-1", items=items)
+        _run(bot._on_ws_event("ws-1", thread, event))
+
+        # Both items shown — running indicator is separate from approval dialog.
+        assert thread.send.await_count == 2
+
+    def test_reuses_thinking_message_for_first_tool(self):
+        from turnstone.sdk.events import ToolInfoEvent
+
+        bot = self._make_bot()
+        thread = AsyncMock()
+        thinking_msg = MagicMock()
+        thinking_msg.edit = AsyncMock()
+        bot._thinking_msgs["ws-1"] = thinking_msg
+
+        items = [{"func_name": "bash", "preview": "ls -la", "needs_approval": False}]
+        event = ToolInfoEvent(ws_id="ws-1", items=items)
+        _run(bot._on_ws_event("ws-1", thread, event))
+
+        # Thinking message edited into tool embed, no new message sent.
+        thinking_msg.edit.assert_awaited_once()
+        thread.send.assert_not_awaited()
+        assert "ws-1" not in bot._thinking_msgs
+        # The reused message is tracked for ToolResultEvent editing.
+        assert bot._tool_info_msgs["ws-1"][0][3] is thinking_msg
+
+
+class TestToolResultEvent:
+    """Tests for ToolResultEvent handling in the Discord bot."""
+
+    def _make_bot(self):
+        from turnstone.channels.discord.bot import TurnstoneBot
+
+        bot = MagicMock(spec=TurnstoneBot)
+        bot.config = MagicMock()
+        bot.config.max_message_length = 2000
+        bot.config.streaming_edit_interval = 1.5
+        bot.config.auto_approve = False
+        bot.config.auto_approve_tools = []
+        bot.storage = None
+        bot._streaming = {}
+        bot._thinking_msgs = {}
+        bot._tool_info_msgs = {}
+        bot._pending_approval_msgs = {}
+        bot._notify_reply_channels = {}
+        bot._should_auto_approve = MagicMock(return_value=False)
+        bot._on_ws_event = TurnstoneBot._on_ws_event.__get__(bot, TurnstoneBot)
+        return bot
+
+    def test_marks_info_done_and_sends_result(self):
+        from turnstone.sdk.events import ToolResultEvent
+
+        bot = self._make_bot()
+        thread = AsyncMock()
+
+        # Pre-populate a tool info message (as ToolInfoEvent would).
+        info_msg = MagicMock()
+        info_msg.edit = AsyncMock()
+        bot._tool_info_msgs["ws-1"] = [("", "bash", "ls -la", info_msg)]
+
+        event = ToolResultEvent(ws_id="ws-1", name="bash", output="file1\nfile2")
+        _run(bot._on_ws_event("ws-1", thread, event))
+
+        # Info embed edited to "Done" status.
+        info_msg.edit.assert_awaited_once()
+        status_embed = info_msg.edit.call_args[1]["embed"]
+        assert "Done" in status_embed.title
+        assert status_embed.description == "ls -la"  # preview preserved
+        # Result sent as separate new message.
+        thread.send.assert_awaited_once()
+        result_embed = thread.send.call_args[1]["embed"]
+        assert result_embed.title == "bash"
+        assert "file1" in result_embed.description
+        # Entry consumed from tracking list.
+        assert bot._tool_info_msgs["ws-1"] == []
+
+    def test_result_sent_even_without_info_match(self):
+        from turnstone.sdk.events import ToolResultEvent
+
+        bot = self._make_bot()
+        thread = AsyncMock()
+
+        event = ToolResultEvent(ws_id="ws-1", name="bash", output="file1\nfile2")
+        _run(bot._on_ws_event("ws-1", thread, event))
+
+        thread.send.assert_awaited_once()
+        embed = thread.send.call_args[1]["embed"]
+        assert embed.title == "bash"
+        assert "file1" in embed.description
+
+    def test_error_result_uses_red_color(self):
+        from turnstone.sdk.events import ToolResultEvent
+
+        bot = self._make_bot()
+        thread = AsyncMock()
+
+        event = ToolResultEvent(
+            ws_id="ws-1", name="bash", output="command not found", is_error=True
+        )
+        _run(bot._on_ws_event("ws-1", thread, event))
+
+        embed = thread.send.call_args[1]["embed"]
+        assert embed.color == discord.Color.red()
+
+    def test_success_result_uses_dark_grey_color(self):
+        from turnstone.sdk.events import ToolResultEvent
+
+        bot = self._make_bot()
+        thread = AsyncMock()
+
+        event = ToolResultEvent(ws_id="ws-1", name="bash", output="ok")
+        _run(bot._on_ws_event("ws-1", thread, event))
+
+        embed = thread.send.call_args[1]["embed"]
+        assert embed.color == discord.Color.dark_grey()
+
+    def test_call_id_matching(self):
+        from turnstone.sdk.events import ToolResultEvent
+
+        bot = self._make_bot()
+        thread = AsyncMock()
+
+        first_msg = MagicMock()
+        first_msg.edit = AsyncMock()
+        second_msg = MagicMock()
+        second_msg.edit = AsyncMock()
+        bot._tool_info_msgs["ws-1"] = [
+            ("call-1", "bash", "", first_msg),
+            ("call-2", "bash", "", second_msg),
+        ]
+
+        # Result with call_id matches the correct message regardless of order.
+        event = ToolResultEvent(ws_id="ws-1", call_id="call-2", name="bash", output="result")
+        _run(bot._on_ws_event("ws-1", thread, event))
+        second_msg.edit.assert_awaited_once()
+        first_msg.edit.assert_not_awaited()
+
+    def test_fifo_fallback_when_no_call_id(self):
+        from turnstone.sdk.events import ToolResultEvent
+
+        bot = self._make_bot()
+        thread = AsyncMock()
+
+        first_msg = MagicMock()
+        first_msg.edit = AsyncMock()
+        second_msg = MagicMock()
+        second_msg.edit = AsyncMock()
+        bot._tool_info_msgs["ws-1"] = [("", "bash", "", first_msg), ("", "bash", "", second_msg)]
+
+        # No call_id — falls back to FIFO name match.
+        event1 = ToolResultEvent(ws_id="ws-1", name="bash", output="result1")
+        _run(bot._on_ws_event("ws-1", thread, event1))
+        first_msg.edit.assert_awaited_once()
+        second_msg.edit.assert_not_awaited()
+
+        event2 = ToolResultEvent(ws_id="ws-1", name="bash", output="result2")
+        _run(bot._on_ws_event("ws-1", thread, event2))
+        second_msg.edit.assert_awaited_once()
+
+    def test_edit_failure_falls_back_to_send(self):
+        from turnstone.sdk.events import ToolResultEvent
+
+        bot = self._make_bot()
+        thread = AsyncMock()
+
+        info_msg = MagicMock()
+        info_msg.edit = AsyncMock(side_effect=Exception("Discord API error"))
+        bot._tool_info_msgs["ws-1"] = [("", "bash", "ls -la", info_msg)]
+
+        event = ToolResultEvent(ws_id="ws-1", name="bash", output="ok")
+        _run(bot._on_ws_event("ws-1", thread, event))
+
+        # Edit failed, should fall back to send.
+        info_msg.edit.assert_awaited_once()
+        thread.send.assert_awaited_once()
+
+
+# ---------------------------------------------------------------------------
+# Approval resolved (timeout / external resolution)
+# ---------------------------------------------------------------------------
+
+
+class TestApprovalResolved:
+    """ApprovalResolvedEvent should disable buttons on the pending approval embed."""
+
+    def _make_bot(self):
+        from turnstone.channels.discord.bot import TurnstoneBot
+
+        bot = MagicMock(spec=TurnstoneBot)
+        bot.config = MagicMock()
+        bot.config.max_message_length = 2000
+        bot.config.streaming_edit_interval = 1.5
+        bot.config.auto_approve = False
+        bot.config.auto_approve_tools = []
+        bot.storage = None
+        bot._streaming = {}
+        bot._thinking_msgs = {}
+        bot._tool_info_msgs = {}
+        bot._pending_approval_msgs = {}
+        bot._notify_reply_channels = {}
+        bot._should_auto_approve = MagicMock(return_value=False)
+        bot._on_ws_event = TurnstoneBot._on_ws_event.__get__(bot, TurnstoneBot)
+        return bot
+
+    def test_disables_buttons_on_timeout(self):
+        from turnstone.sdk.events import ApprovalResolvedEvent
+
+        bot = self._make_bot()
+        thread = AsyncMock()
+
+        # Set up a pending approval message with components.
+        approval_msg = MagicMock()
+        approval_msg.embeds = [MagicMock()]
+        approval_msg.components = []
+        approval_msg.edit = AsyncMock()
+        bot._pending_approval_msgs["ws-1"] = approval_msg
+
+        event = ApprovalResolvedEvent(ws_id="ws-1", approved=False, feedback="timeout")
+        _run(bot._on_ws_event("ws-1", thread, event))
+
+        approval_msg.edit.assert_awaited_once()
+        # Pending approval message should be removed.
+        assert "ws-1" not in bot._pending_approval_msgs
+
+    def test_disables_buttons_on_approved(self):
+        from turnstone.sdk.events import ApprovalResolvedEvent
+
+        bot = self._make_bot()
+        thread = AsyncMock()
+
+        approval_msg = MagicMock()
+        approval_msg.embeds = [MagicMock()]
+        approval_msg.components = []
+        approval_msg.edit = AsyncMock()
+        bot._pending_approval_msgs["ws-1"] = approval_msg
+
+        event = ApprovalResolvedEvent(ws_id="ws-1", approved=True)
+        _run(bot._on_ws_event("ws-1", thread, event))
+
+        approval_msg.edit.assert_awaited_once()
+        # Check the embed title was updated with "Approved".
+        edited_embed = approval_msg.edit.call_args[1]["embed"]
+        assert "Approved" in edited_embed.title
+
+    def test_no_pending_approval_is_noop(self):
+        from turnstone.sdk.events import ApprovalResolvedEvent
+
+        bot = self._make_bot()
+        thread = AsyncMock()
+
+        event = ApprovalResolvedEvent(ws_id="ws-1", approved=False)
+        _run(bot._on_ws_event("ws-1", thread, event))
+        # No error, no state change.
+
+
 class TestChannelCLI:
     """Tests for the channel CLI entry point."""
 

tests/test_channel_routing.py

@@ -2,24 +2,12 @@
 
 from __future__ import annotations
 
-import json
 from unittest.mock import AsyncMock, MagicMock
 
 import pytest
 
 from turnstone.channels._routing import ChannelRouter
-
-
-@pytest.fixture
-def mock_broker() -> AsyncMock:
-    """Return a mock AsyncRedisBroker."""
-    broker = AsyncMock()
-    broker._prefix = "test"
-    broker.push_inbound = AsyncMock()
-    broker.push_response = AsyncMock()
-    broker.subscribe = AsyncMock()
-    broker.unsubscribe = AsyncMock()
-    return broker
+from turnstone.sdk._types import TurnstoneAPIError
 
 
 @pytest.fixture
@@ -35,8 +23,21 @@ def mock_storage() -> MagicMock:
 
 
 @pytest.fixture
-def router(mock_broker: AsyncMock, mock_storage: MagicMock) -> ChannelRouter:
-    return ChannelRouter(broker=mock_broker, storage=mock_storage)
+def router(mock_storage: MagicMock) -> ChannelRouter:
+    return ChannelRouter(
+        server_url="http://localhost:8080/v1",
+        storage=mock_storage,
+    )
+
+
+@pytest.fixture
+def console_router(mock_storage: MagicMock) -> ChannelRouter:
+    return ChannelRouter(
+        server_url="http://localhost:8080/v1",
+        storage=mock_storage,
+        console_url="http://localhost:8081/v1",
+        api_token="tok-test",
+    )
 
 
 class TestResolveUser:
@@ -56,46 +57,82 @@ class TestResolveUser:
 
 class TestSendMessage:
     @pytest.mark.anyio
-    async def test_pushes_send_message(self, router: ChannelRouter, mock_broker: AsyncMock) -> None:
-        cid = await router.send_message("ws-1", "hello world")
-        assert isinstance(cid, str)
-        assert len(cid) > 0
-        mock_broker.push_inbound.assert_awaited_once()
-        raw = mock_broker.push_inbound.call_args[0][0]
-        payload = json.loads(raw)
-        assert payload["type"] == "send"
-        assert payload["ws_id"] == "ws-1"
-        assert payload["message"] == "hello world"
-        assert payload["correlation_id"] == cid
+    async def test_calls_server_send(
+        self, router: ChannelRouter, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
+        assert router._server is not None
+        mock_send = AsyncMock()
+        monkeypatch.setattr(router._server, "send", mock_send)
+        await router.send_message("ws-1", "hello world")
+        mock_send.assert_awaited_once_with("hello world", "ws-1")
+
+    @pytest.mark.anyio
+    async def test_calls_console_route_send(
+        self, console_router: ChannelRouter, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
+        assert console_router._console is not None
+        mock_send = AsyncMock()
+        monkeypatch.setattr(console_router._console, "route_send", mock_send)
+        await console_router.send_message("ws-1", "hello world")
+        mock_send.assert_awaited_once_with("hello world", "ws-1")
 
 
 class TestSendApproval:
     @pytest.mark.anyio
-    async def test_pushes_to_response_queue(
-        self, router: ChannelRouter, mock_broker: AsyncMock
+    async def test_calls_server_approve(
+        self, router: ChannelRouter, monkeypatch: pytest.MonkeyPatch
     ) -> None:
+        assert router._server is not None
+        mock_approve = AsyncMock()
+        monkeypatch.setattr(router._server, "approve", mock_approve)
         await router.send_approval("ws-1", "corr-abc", approved=True, feedback="ok")
-        mock_broker.push_response.assert_awaited_once()
-        queue_name = mock_broker.push_response.call_args[0][0]
-        assert queue_name == "corr-abc"
-        raw = mock_broker.push_response.call_args[0][1]
-        payload = json.loads(raw)
-        assert payload["type"] == "approve"
-        assert payload["approved"] is True
-        assert payload["ws_id"] == "ws-1"
+        mock_approve.assert_awaited_once_with(
+            ws_id="ws-1", approved=True, feedback="ok", always=False
+        )
+
+    @pytest.mark.anyio
+    async def test_omits_empty_feedback(
+        self, router: ChannelRouter, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
+        assert router._server is not None
+        mock_approve = AsyncMock()
+        monkeypatch.setattr(router._server, "approve", mock_approve)
+        await router.send_approval("ws-1", "corr-abc", approved=False)
+        mock_approve.assert_awaited_once_with(
+            ws_id="ws-1", approved=False, feedback=None, always=False
+        )
+
+    @pytest.mark.anyio
+    async def test_calls_console_route_approve(
+        self, console_router: ChannelRouter, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
+        assert console_router._console is not None
+        mock_approve = AsyncMock()
+        monkeypatch.setattr(console_router._console, "route_approve", mock_approve)
+        await console_router.send_approval("ws-1", "corr-abc", approved=True, always=True)
+        mock_approve.assert_awaited_once_with(ws_id="ws-1", approved=True, feedback="", always=True)
 
 
 class TestSendPlanFeedback:
     @pytest.mark.anyio
-    async def test_pushes_to_response_queue(
-        self, router: ChannelRouter, mock_broker: AsyncMock
+    async def test_calls_server_plan_feedback(
+        self, router: ChannelRouter, monkeypatch: pytest.MonkeyPatch
     ) -> None:
+        assert router._server is not None
+        mock_plan = AsyncMock()
+        monkeypatch.setattr(router._server, "plan_feedback", mock_plan)
         await router.send_plan_feedback("ws-2", "corr-xyz", "looks good")
-        mock_broker.push_response.assert_awaited_once()
-        raw = mock_broker.push_response.call_args[0][1]
-        payload = json.loads(raw)
-        assert payload["type"] == "plan_feedback"
-        assert payload["feedback"] == "looks good"
+        mock_plan.assert_awaited_once_with(ws_id="ws-2", feedback="looks good")
+
+    @pytest.mark.anyio
+    async def test_calls_console_route_plan_feedback(
+        self, console_router: ChannelRouter, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
+        assert console_router._console is not None
+        mock_plan = AsyncMock()
+        monkeypatch.setattr(console_router._console, "route_plan_feedback", mock_plan)
+        await console_router.send_plan_feedback("ws-2", "corr-xyz", "looks good")
+        mock_plan.assert_awaited_once_with(ws_id="ws-2", feedback="looks good")
 
 
 class TestDeleteRoute:
@@ -105,3 +142,188 @@ class TestDeleteRoute:
     ) -> None:
         await router.delete_route("discord", "ch-123")
         mock_storage.delete_channel_route.assert_called_once_with("discord", "ch-123")
+
+
+class TestGetOrCreateWorkstream:
+    @pytest.mark.anyio
+    async def test_creates_new_workstream_via_server(
+        self,
+        router: ChannelRouter,
+        mock_storage: MagicMock,
+        monkeypatch: pytest.MonkeyPatch,
+    ) -> None:
+        assert router._server is not None
+        mock_create = AsyncMock()
+        mock_create.return_value = MagicMock(ws_id="ws-new", name="test")
+        monkeypatch.setattr(router._server, "create_workstream", mock_create)
+        ws_id, is_new = await router.get_or_create_workstream("discord", "ch-1", name="test")
+        assert ws_id == "ws-new"
+        assert is_new is True
+        mock_storage.create_channel_route.assert_called_once_with("discord", "ch-1", "ws-new")
+        mock_create.assert_awaited_once()
+
+    @pytest.mark.anyio
+    async def test_creates_new_workstream_via_console(
+        self,
+        console_router: ChannelRouter,
+        mock_storage: MagicMock,
+        monkeypatch: pytest.MonkeyPatch,
+    ) -> None:
+        assert console_router._console is not None
+        mock_create = AsyncMock(
+            return_value={"ws_id": "ws-new", "name": "test", "node_url": "http://node1:8080/v1"}
+        )
+        monkeypatch.setattr(console_router._console, "route_create_workstream", mock_create)
+        ws_id, is_new = await console_router.get_or_create_workstream(
+            "discord", "ch-1", name="test"
+        )
+        assert ws_id == "ws-new"
+        assert is_new is True
+        mock_storage.create_channel_route.assert_called_once_with("discord", "ch-1", "ws-new")
+        # Node URL should be cached.
+        assert console_router._node_urls["ws-new"] == "http://node1:8080/v1"
+
+    @pytest.mark.anyio
+    async def test_returns_existing_alive_workstream(
+        self,
+        router: ChannelRouter,
+        mock_storage: MagicMock,
+        monkeypatch: pytest.MonkeyPatch,
+    ) -> None:
+        mock_storage.get_channel_route.return_value = {
+            "ws_id": "ws-old",
+            "channel_type": "discord",
+            "channel_id": "ch-1",
+        }
+        monkeypatch.setattr(router, "_is_ws_alive", AsyncMock(return_value=True))
+        ws_id, is_new = await router.get_or_create_workstream("discord", "ch-1")
+        assert ws_id == "ws-old"
+        assert is_new is False
+
+    @pytest.mark.anyio
+    async def test_resumes_stale_workstream(
+        self,
+        router: ChannelRouter,
+        mock_storage: MagicMock,
+        monkeypatch: pytest.MonkeyPatch,
+    ) -> None:
+        mock_storage.get_channel_route.return_value = {
+            "ws_id": "ws-stale",
+            "channel_type": "discord",
+            "channel_id": "ch-1",
+        }
+        # Alive check returns False — ws is not alive.
+        monkeypatch.setattr(router, "_is_ws_alive", AsyncMock(return_value=False))
+        # Server create returns a resumed workstream.
+        assert router._server is not None
+        mock_create = AsyncMock()
+        mock_create.return_value = MagicMock(ws_id="ws-resumed", name="test")
+        monkeypatch.setattr(router._server, "create_workstream", mock_create)
+
+        ws_id, is_new = await router.get_or_create_workstream("discord", "ch-1", name="test")
+        assert ws_id == "ws-resumed"
+        assert is_new is True
+        # Should have deleted the stale route and created a new one.
+        mock_storage.delete_channel_route.assert_called_once_with("discord", "ch-1")
+        mock_storage.create_channel_route.assert_called_once_with("discord", "ch-1", "ws-resumed")
+        # The create call should include resume_ws pointing at the old ws.
+        mock_create.assert_awaited_once()
+        call_kwargs = mock_create.call_args[1]
+        assert call_kwargs["resume_ws"] == "ws-stale"
+
+    @pytest.mark.anyio
+    async def test_sends_initial_message_for_new_workstream(
+        self,
+        router: ChannelRouter,
+        mock_storage: MagicMock,
+        monkeypatch: pytest.MonkeyPatch,
+    ) -> None:
+        assert router._server is not None
+        mock_create = AsyncMock()
+        mock_create.return_value = MagicMock(ws_id="ws-new", name="test")
+        monkeypatch.setattr(router._server, "create_workstream", mock_create)
+        mock_send = AsyncMock()
+        monkeypatch.setattr(router._server, "send", mock_send)
+
+        await router.get_or_create_workstream("discord", "ch-1", name="test", initial_message="hi")
+        mock_send.assert_awaited_once_with("hi", "ws-new")
+
+
+class TestCloseWorkstream:
+    @pytest.mark.anyio
+    async def test_calls_server_close(
+        self, router: ChannelRouter, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
+        assert router._server is not None
+        mock_close = AsyncMock()
+        monkeypatch.setattr(router._server, "close_workstream", mock_close)
+        await router.close_workstream("ws-1")
+        mock_close.assert_awaited_once_with("ws-1")
+
+    @pytest.mark.anyio
+    async def test_catches_api_error(
+        self, router: ChannelRouter, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
+        assert router._server is not None
+        mock_close = AsyncMock(side_effect=TurnstoneAPIError(404, "not found"))
+        monkeypatch.setattr(router._server, "close_workstream", mock_close)
+        # Should not raise.
+        await router.close_workstream("ws-1")
+
+    @pytest.mark.anyio
+    async def test_calls_console_route_close(
+        self, console_router: ChannelRouter, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
+        assert console_router._console is not None
+        mock_close = AsyncMock()
+        monkeypatch.setattr(console_router._console, "route_close", mock_close)
+        await console_router.close_workstream("ws-1")
+        mock_close.assert_awaited_once_with("ws-1")
+
+
+class TestAclose:
+    @pytest.mark.anyio
+    async def test_closes_server_client(
+        self, router: ChannelRouter, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
+        assert router._server is not None
+        mock_close = AsyncMock()
+        monkeypatch.setattr(router._server, "aclose", mock_close)
+        await router.aclose()
+        mock_close.assert_awaited_once()
+
+    @pytest.mark.anyio
+    async def test_closes_console_client(
+        self, console_router: ChannelRouter, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
+        assert console_router._console is not None
+        mock_close = AsyncMock()
+        monkeypatch.setattr(console_router._console, "aclose", mock_close)
+        await console_router.aclose()
+        mock_close.assert_awaited_once()
+
+
+class TestGetNodeUrl:
+    @pytest.mark.anyio
+    async def test_returns_cached_url(self, router: ChannelRouter) -> None:
+        router._node_urls["ws-1"] = "http://node1:8080/v1"
+        url = await router.get_node_url("ws-1")
+        assert url == "http://node1:8080/v1"
+
+    @pytest.mark.anyio
+    async def test_falls_back_to_server_url(self, router: ChannelRouter) -> None:
+        url = await router.get_node_url("ws-unknown")
+        assert url == "http://localhost:8080/v1"
+
+    @pytest.mark.anyio
+    async def test_queries_console_route_lookup(
+        self, console_router: ChannelRouter, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
+        assert console_router._console is not None
+        mock_lookup = AsyncMock(return_value={"node_url": "http://node2:8080/v1", "node_id": "n2"})
+        monkeypatch.setattr(console_router._console, "route_lookup", mock_lookup)
+        url = await console_router.get_node_url("ws-1")
+        assert url == "http://node2:8080/v1"
+        mock_lookup.assert_awaited_once_with("ws-1")
+        # Should be cached now.
+        assert console_router._node_urls["ws-1"] == "http://node2:8080/v1"

tests/test_config.py

@@ -21,20 +21,20 @@ def test_load_config_missing_file(tmp_path):
 def test_load_config_valid_toml(tmp_path):
     _reset_cache()
     cfg = tmp_path / "config.toml"
-    cfg.write_text('[redis]\nhost = "10.0.0.1"\nport = 6380\npassword = "secret"\n')
+    cfg.write_text('[database]\nhost = "10.0.0.1"\nport = 5432\nname = "turnstone"\n')
     set_config_path(str(cfg))
     result = load_config()
-    assert result["redis"]["host"] == "10.0.0.1"
-    assert result["redis"]["port"] == 6380
-    assert result["redis"]["password"] == "secret"
+    assert result["database"]["host"] == "10.0.0.1"
+    assert result["database"]["port"] == 5432
+    assert result["database"]["name"] == "turnstone"
 
 
 def test_load_config_section(tmp_path):
     _reset_cache()
     cfg = tmp_path / "config.toml"
-    cfg.write_text('[api]\nbase_url = "http://x:8000/v1"\n[redis]\nhost = "y"\n')
+    cfg.write_text('[api]\nbase_url = "http://x:8000/v1"\n[database]\nhost = "y"\n')
     set_config_path(str(cfg))
-    assert load_config("redis") == {"host": "y"}
+    assert load_config("database") == {"host": "y"}
     assert load_config("api") == {"base_url": "http://x:8000/v1"}
     assert load_config("nonexistent") == {}
 
@@ -65,61 +65,56 @@ def test_apply_config_sets_defaults(tmp_path):
     _reset_cache()
     cfg = tmp_path / "config.toml"
     cfg.write_text(
-        '[redis]\nhost = "redis.local"\nport = 7777\npassword = "pw"\n'
-        '[bridge]\nserver_url = "http://bridge:9090"\n'
+        '[server]\nhost = "0.0.0.0"\nport = 9090\n[api]\nbase_url = "http://custom/v1"\n'
     )
     set_config_path(str(cfg))
 
     parser = argparse.ArgumentParser()
-    parser.add_argument("--redis-host", default="localhost")
-    parser.add_argument("--redis-port", type=int, default=6379)
-    parser.add_argument("--redis-password", default=None)
-    parser.add_argument("--server-url", default="http://localhost:8080")
+    parser.add_argument("--host", default="localhost")
+    parser.add_argument("--port", type=int, default=8080)
+    parser.add_argument("--base-url", default="http://localhost:11434/v1")
 
-    apply_config(parser, ["redis", "bridge"])
+    apply_config(parser, ["server", "api"])
     args = parser.parse_args([])
 
-    assert args.redis_host == "redis.local"
-    assert args.redis_port == 7777
-    assert args.redis_password == "pw"
-    assert args.server_url == "http://bridge:9090"
+    assert args.host == "0.0.0.0"
+    assert args.port == 9090
+    assert args.base_url == "http://custom/v1"
 
 
 def test_apply_config_cli_overrides(tmp_path):
     _reset_cache()
     cfg = tmp_path / "config.toml"
-    cfg.write_text('[redis]\nhost = "config-host"\nport = 7777\n')
+    cfg.write_text('[server]\nhost = "config-host"\nport = 7777\n')
     set_config_path(str(cfg))
 
     parser = argparse.ArgumentParser()
-    parser.add_argument("--redis-host", default="localhost")
-    parser.add_argument("--redis-port", type=int, default=6379)
+    parser.add_argument("--host", default="localhost")
+    parser.add_argument("--port", type=int, default=8080)
 
-    apply_config(parser, ["redis"])
+    apply_config(parser, ["server"])
     # CLI flag overrides config
-    args = parser.parse_args(["--redis-host", "cli-host"])
+    args = parser.parse_args(["--host", "cli-host"])
 
-    assert args.redis_host == "cli-host"  # CLI wins
-    assert args.redis_port == 7777  # config wins (no CLI override)
+    assert args.host == "cli-host"  # CLI wins
+    assert args.port == 7777  # config wins (no CLI override)
 
 
 def test_apply_config_missing_keys_keep_defaults(tmp_path):
     _reset_cache()
     cfg = tmp_path / "config.toml"
-    cfg.write_text('[redis]\nhost = "only-host"\n')  # no port, no password
+    cfg.write_text('[server]\nhost = "only-host"\n')  # no port
     set_config_path(str(cfg))
 
     parser = argparse.ArgumentParser()
-    parser.add_argument("--redis-host", default="localhost")
-    parser.add_argument("--redis-port", type=int, default=6379)
-    parser.add_argument("--redis-password", default=None)
+    parser.add_argument("--host", default="localhost")
+    parser.add_argument("--port", type=int, default=8080)
 
-    apply_config(parser, ["redis"])
+    apply_config(parser, ["server"])
     args = parser.parse_args([])
 
-    assert args.redis_host == "only-host"
-    assert args.redis_port == 6379  # original default kept
-    assert args.redis_password is None  # original default kept
+    assert args.host == "only-host"
+    assert args.port == 8080  # original default kept
 
 
 def test_apply_config_no_file(tmp_path):
@@ -127,11 +122,11 @@ def test_apply_config_no_file(tmp_path):
     set_config_path(str(tmp_path / "nope.toml"))
 
     parser = argparse.ArgumentParser()
-    parser.add_argument("--redis-host", default="localhost")
+    parser.add_argument("--host", default="localhost")
 
-    apply_config(parser, ["redis"])
+    apply_config(parser, ["server"])
     args = parser.parse_args([])
-    assert args.redis_host == "localhost"
+    assert args.host == "localhost"
 
 
 def test_apply_config_model_section(tmp_path):

tests/test_console_metrics.py

@@ -0,0 +1,148 @@
+"""Tests for turnstone.console.metrics."""
+
+from __future__ import annotations
+
+from turnstone.console.metrics import ConsoleMetrics
+
+
+class TestRecordRoute:
+    """Recording routed requests."""
+
+    def test_single_request(self) -> None:
+        m = ConsoleMetrics()
+        m.record_route("send", 200, 0.05)
+
+        text = m.generate_text()
+        assert 'turnstone_router_requests_total{method="send",status="2xx"} 1' in text
+
+    def test_multiple_methods(self) -> None:
+        m = ConsoleMetrics()
+        m.record_route("send", 200, 0.01)
+        m.record_route("create", 200, 0.02)
+        m.record_route("send", 502, 0.5)
+
+        text = m.generate_text()
+        assert 'turnstone_router_requests_total{method="send",status="2xx"} 1' in text
+        assert 'turnstone_router_requests_total{method="create",status="2xx"} 1' in text
+        assert 'turnstone_router_requests_total{method="send",status="5xx"} 1' in text
+
+    def test_duration_recorded(self) -> None:
+        m = ConsoleMetrics()
+        m.record_route("send", 200, 0.123)
+        m.record_route("send", 200, 0.456)
+
+        text = m.generate_text()
+        assert 'turnstone_router_request_duration_seconds_count{method="send"} 2' in text
+        # Sum should be 0.579
+        assert "turnstone_router_request_duration_seconds_sum" in text
+
+
+class TestRingInfo:
+    """Ring membership and version gauges."""
+
+    def test_defaults_zero(self) -> None:
+        m = ConsoleMetrics()
+        text = m.generate_text()
+        assert "turnstone_ring_membership_size 0" in text
+        assert "turnstone_ring_version 0" in text
+
+    def test_set_ring_info(self) -> None:
+        m = ConsoleMetrics()
+        m.set_ring_info(3, 7)
+
+        text = m.generate_text()
+        assert "turnstone_ring_membership_size 3" in text
+        assert "turnstone_ring_version 7" in text
+
+
+class TestRebalance:
+    """Rebalance and migration counters."""
+
+    def test_noop(self) -> None:
+        m = ConsoleMetrics()
+        m.record_rebalance("noop")
+
+        text = m.generate_text()
+        assert 'turnstone_ring_rebalance_total{result="noop"} 1' in text
+
+    def test_seeded(self) -> None:
+        m = ConsoleMetrics()
+        m.record_rebalance("seeded")
+
+        text = m.generate_text()
+        assert 'turnstone_ring_rebalance_total{result="seeded"} 1' in text
+
+    def test_rebalanced(self) -> None:
+        m = ConsoleMetrics()
+        m.record_rebalance("rebalanced")
+        m.record_rebalance("rebalanced")
+
+        text = m.generate_text()
+        assert 'turnstone_ring_rebalance_total{result="rebalanced"} 2' in text
+
+    def test_migrations(self) -> None:
+        m = ConsoleMetrics()
+        m.record_migrations(5)
+        m.record_migrations(3)
+
+        text = m.generate_text()
+        assert "turnstone_ring_migrations_total 8" in text
+
+    def test_migrations_default_zero(self) -> None:
+        m = ConsoleMetrics()
+        text = m.generate_text()
+        assert "turnstone_ring_migrations_total 0" in text
+
+
+class TestGenerateText:
+    """Output format validation."""
+
+    def test_contains_all_metric_names(self) -> None:
+        m = ConsoleMetrics()
+        text = m.generate_text()
+        expected = [
+            "turnstone_router_requests_total",
+            "turnstone_router_request_duration_seconds",
+            "turnstone_ring_membership_size",
+            "turnstone_ring_version",
+            "turnstone_ring_rebalance_total",
+            "turnstone_ring_migrations_total",
+        ]
+        for name in expected:
+            assert name in text, f"Missing metric: {name}"
+
+    def test_has_help_and_type(self) -> None:
+        m = ConsoleMetrics()
+        text = m.generate_text()
+        assert "# HELP turnstone_router_requests_total" in text
+        assert "# TYPE turnstone_router_requests_total counter" in text
+        assert "# HELP turnstone_ring_membership_size" in text
+        assert "# TYPE turnstone_ring_membership_size gauge" in text
+
+    def test_ends_with_newline(self) -> None:
+        m = ConsoleMetrics()
+        text = m.generate_text()
+        assert text.endswith("\n")
+
+    def test_combined_scenario(self) -> None:
+        """Full scenario: routes, ring info, rebalances, migrations."""
+        m = ConsoleMetrics()
+        m.record_route("create", 200, 0.1)
+        m.record_route("send", 200, 0.05)
+        m.record_route("send", 502, 1.2)
+        m.set_ring_info(3, 12)
+        m.record_rebalance("seeded")
+        m.record_rebalance("noop")
+        m.record_rebalance("rebalanced")
+        m.record_migrations(4)
+
+        text = m.generate_text()
+        assert 'turnstone_router_requests_total{method="create",status="2xx"} 1' in text
+        assert 'turnstone_router_requests_total{method="send",status="2xx"} 1' in text
+        assert 'turnstone_router_requests_total{method="send",status="5xx"} 1' in text
+        assert "turnstone_ring_membership_size 3" in text
+        assert "turnstone_ring_version 12" in text
+        assert 'turnstone_ring_rebalance_total{result="noop"} 1' in text
+        assert 'turnstone_ring_rebalance_total{result="rebalanced"} 1' in text
+        assert 'turnstone_ring_rebalance_total{result="seeded"} 1' in text
+        assert "turnstone_ring_migrations_total 4" in text

tests/test_console_router.py

@@ -0,0 +1,255 @@
+"""Tests for turnstone.console.router."""
+
+from __future__ import annotations
+
+from typing import Any
+
+import pytest
+
+from turnstone.console.router import ConsoleRouter, NodeRef
+from turnstone.core.hash_ring import RING_SIZE, NoAvailableNodeError
+
+# ---------------------------------------------------------------------------
+# Fake storage
+# ---------------------------------------------------------------------------
+
+
+class FakeStorage:
+    """Minimal storage mock for router tests."""
+
+    def __init__(self) -> None:
+        self.services: list[dict[str, str]] = []
+        self.buckets: list[dict[str, Any]] = []
+        self.overrides: list[dict[str, str]] = []
+        self.settings: dict[str, dict[str, Any]] = {}
+
+    def list_services(self, service_type: str, max_age_seconds: int = 120) -> list[dict[str, str]]:
+        return list(self.services)
+
+    def list_ring_buckets(self) -> list[dict[str, Any]]:
+        return list(self.buckets)
+
+    def list_workstream_overrides(self) -> list[dict[str, str]]:
+        return list(self.overrides)
+
+    def get_system_setting(self, key: str, node_id: str = "") -> dict[str, Any] | None:
+        return self.settings.get(key)
+
+
+# ---------------------------------------------------------------------------
+# Helpers
+# ---------------------------------------------------------------------------
+
+NODE_A = {"service_id": "node-a", "url": "http://a:8080", "metadata": "{}"}
+NODE_B = {"service_id": "node-b", "url": "http://b:8080", "metadata": "{}"}
+NODE_C = {"service_id": "node-c", "url": "http://c:8080", "metadata": "{}"}
+
+
+def _make_router(storage: FakeStorage | None = None) -> tuple[ConsoleRouter, FakeStorage]:
+    s = storage or FakeStorage()
+    return ConsoleRouter(s), s  # type: ignore[arg-type]
+
+
+def _ws_id_for_bucket(bucket: int) -> str:
+    """Build a 32-char hex ws_id whose first 4 chars encode *bucket*."""
+    return f"{bucket:04x}" + "0" * 28
+
+
+# ---------------------------------------------------------------------------
+# TestRouteBasic
+# ---------------------------------------------------------------------------
+
+
+class TestRouteBasic:
+    """Basic routing through the bucket cache."""
+
+    def test_route_returns_correct_node(self) -> None:
+        router, storage = _make_router()
+        storage.services = [NODE_A, NODE_B, NODE_C]
+        storage.buckets = [
+            {"bucket": 0x0000, "node_id": "node-a"},
+            {"bucket": 0x0001, "node_id": "node-b"},
+            {"bucket": 0x0002, "node_id": "node-c"},
+        ]
+        router.refresh_cache()
+
+        assert router.route(_ws_id_for_bucket(0x0000)) == NodeRef("node-a", "http://a:8080")
+        assert router.route(_ws_id_for_bucket(0x0001)) == NodeRef("node-b", "http://b:8080")
+        assert router.route(_ws_id_for_bucket(0x0002)) == NodeRef("node-c", "http://c:8080")
+
+    def test_route_override_priority(self) -> None:
+        router, storage = _make_router()
+        storage.services = [NODE_A, NODE_B]
+        storage.buckets = [{"bucket": 0x0000, "node_id": "node-a"}]
+        ws_id = _ws_id_for_bucket(0x0000)
+        storage.overrides = [{"ws_id": ws_id, "node_id": "node-b"}]
+        router.refresh_cache()
+
+        # Override wins over bucket assignment
+        assert router.route(ws_id) == NodeRef("node-b", "http://b:8080")
+
+    def test_route_empty_cache_raises(self) -> None:
+        router, _ = _make_router()
+
+        with pytest.raises(NoAvailableNodeError, match="not assigned"):
+            router.route(_ws_id_for_bucket(0x0000))
+
+    def test_route_url_convenience(self) -> None:
+        router, storage = _make_router()
+        storage.services = [NODE_A]
+        storage.buckets = [{"bucket": 0x0010, "node_id": "node-a"}]
+        router.refresh_cache()
+
+        assert router.route_url(_ws_id_for_bucket(0x0010)) == "http://a:8080"
+
+
+# ---------------------------------------------------------------------------
+# TestRefreshCache
+# ---------------------------------------------------------------------------
+
+
+class TestRefreshCache:
+    """Cache loading from storage."""
+
+    def test_refresh_loads_from_storage(self) -> None:
+        router, storage = _make_router()
+        storage.services = [NODE_A]
+        storage.buckets = [{"bucket": 100, "node_id": "node-a"}]
+        router.refresh_cache()
+
+        ref = router.route(_ws_id_for_bucket(100))
+        assert ref.node_id == "node-a"
+
+    def test_refresh_handles_dead_nodes(self) -> None:
+        router, storage = _make_router()
+        # node-b is in buckets but not in services (dead/expired)
+        storage.services = [NODE_A]
+        storage.buckets = [
+            {"bucket": 0x0000, "node_id": "node-a"},
+            {"bucket": 0x0001, "node_id": "node-b"},
+        ]
+        router.refresh_cache()
+
+        assert router.route(_ws_id_for_bucket(0x0000)).node_id == "node-a"
+        with pytest.raises(NoAvailableNodeError):
+            router.route(_ws_id_for_bucket(0x0001))
+
+    def test_refresh_returns_true_on_change(self) -> None:
+        router, storage = _make_router()
+        storage.services = [NODE_A]
+        storage.buckets = [{"bucket": 0, "node_id": "node-a"}]
+
+        assert router.refresh_cache() is True
+
+    def test_refresh_returns_false_on_no_change(self) -> None:
+        router, storage = _make_router()
+        storage.services = [NODE_A]
+        storage.buckets = [{"bucket": 0, "node_id": "node-a"}]
+
+        router.refresh_cache()
+        assert router.refresh_cache() is False
+
+
+# ---------------------------------------------------------------------------
+# TestCheckVersion
+# ---------------------------------------------------------------------------
+
+
+class TestCheckVersion:
+    """Version-gated refresh."""
+
+    def test_version_change_triggers_refresh(self) -> None:
+        router, storage = _make_router()
+        storage.services = [NODE_A]
+        storage.buckets = [{"bucket": 0, "node_id": "node-a"}]
+        storage.settings["rebalancer_version"] = {"value": "1"}
+
+        assert router.check_version() is True
+        assert router.is_ready()
+
+    def test_same_version_skips(self) -> None:
+        router, storage = _make_router()
+        # Default version is 0; setting absent also means 0
+        storage.services = [NODE_A]
+        storage.buckets = [{"bucket": 0, "node_id": "node-a"}]
+
+        # First call: version=0 matches self._version=0 -> no refresh
+        assert router.check_version() is False
+        assert not router.is_ready()  # cache was never loaded
+
+    def test_version_none_treated_as_zero(self) -> None:
+        router, storage = _make_router()
+        # settings dict is empty -> get_system_setting returns None
+        assert router.check_version() is False
+
+
+# ---------------------------------------------------------------------------
+# TestGenerateWsId
+# ---------------------------------------------------------------------------
+
+
+class TestGenerateWsId:
+    """Workstream ID generation targeting a specific node."""
+
+    def test_generates_routable_id(self) -> None:
+        router, storage = _make_router()
+        storage.services = [NODE_A, NODE_B]
+        storage.buckets = [
+            {"bucket": 0x00FF, "node_id": "node-a"},
+            {"bucket": 0x0100, "node_id": "node-b"},
+        ]
+        router.refresh_cache()
+
+        ws_id = router.generate_ws_id_for_node("node-a")
+        assert len(ws_id) == 32
+        assert router.route(ws_id).node_id == "node-a"
+
+    def test_unknown_node_raises(self) -> None:
+        router, storage = _make_router()
+        storage.services = [NODE_A]
+        storage.buckets = [{"bucket": 0, "node_id": "node-a"}]
+        router.refresh_cache()
+
+        with pytest.raises(NoAvailableNodeError, match="node-z"):
+            router.generate_ws_id_for_node("node-z")
+
+
+# ---------------------------------------------------------------------------
+# TestIsReady
+# ---------------------------------------------------------------------------
+
+
+class TestIsReady:
+    """Readiness checks."""
+
+    def test_false_when_empty(self) -> None:
+        router, _ = _make_router()
+        assert router.is_ready() is False
+
+    def test_true_after_refresh(self) -> None:
+        router, storage = _make_router()
+        storage.services = [NODE_A]
+        storage.buckets = [{"bucket": 0, "node_id": "node-a"}]
+        router.refresh_cache()
+
+        assert router.is_ready() is True
+
+
+# ---------------------------------------------------------------------------
+# TestNodeCount
+# ---------------------------------------------------------------------------
+
+
+class TestNodeCount:
+    """Distinct node counting."""
+
+    def test_count_distinct_nodes(self) -> None:
+        router, storage = _make_router()
+        storage.services = [NODE_A, NODE_B, NODE_C]
+        # Spread all 65536 buckets across 3 nodes
+        storage.buckets = [
+            {"bucket": b, "node_id": f"node-{['a', 'b', 'c'][b % 3]}"} for b in range(RING_SIZE)
+        ]
+        router.refresh_cache()
+
+        assert router.node_count() == 3

tests/test_console_routing_proxy.py

@@ -0,0 +1,433 @@
+"""Tests for console routing proxy endpoints (route_create, route_proxy, route_lookup)."""
+
+from __future__ import annotations
+
+from typing import Any
+from unittest.mock import MagicMock
+
+import httpx
+import pytest
+from starlette.testclient import TestClient
+
+from turnstone.console.collector import ClusterCollector
+from turnstone.console.router import ConsoleRouter, NodeRef
+from turnstone.core.hash_ring import NoAvailableNodeError
+
+# Shared test auth — JWT-based
+_TEST_JWT_SECRET = "test-jwt-secret-minimum-32-chars!"
+
+
+def _test_jwt() -> str:
+    from turnstone.core.auth import JWT_AUD_CONSOLE, create_jwt
+
+    return create_jwt(
+        user_id="test-routing",
+        scopes=frozenset({"read", "write", "approve", "service"}),
+        source="test",
+        secret=_TEST_JWT_SECRET,
+        audience=JWT_AUD_CONSOLE,
+    )
+
+
+_TEST_AUTH_HEADERS: dict[str, str] = {"Authorization": f"Bearer {_test_jwt()}"}
+
+# ---------------------------------------------------------------------------
+# Helpers
+# ---------------------------------------------------------------------------
+
+
+def _make_mock_collector() -> MagicMock:
+    collector = MagicMock(spec=ClusterCollector)
+    collector.get_overview.return_value = {
+        "nodes": 1,
+        "workstreams": 0,
+        "states": {"running": 0, "thinking": 0, "attention": 0, "idle": 0, "error": 0},
+        "aggregate": {"total_tokens": 0, "total_tool_calls": 0},
+    }
+    return collector
+
+
+def _make_mock_router(ready: bool = True) -> MagicMock:
+    router = MagicMock(spec=ConsoleRouter)
+    router.is_ready.return_value = ready
+    router.route.return_value = NodeRef("node-a", "http://a:8080")
+    router.generate_ws_id_for_node.return_value = "00ff" + "0" * 28
+    return router
+
+
+def _make_app(
+    collector: Any = None,
+    router: Any = None,
+) -> Any:
+    from turnstone.console.server import _load_static, create_app
+
+    _load_static()
+    return create_app(
+        collector=collector or _make_mock_collector(),
+        jwt_secret=_TEST_JWT_SECRET,
+        router=router,
+    )
+
+
+def _make_proxy_post(
+    status_code: int = 200,
+    json_data: dict[str, Any] | None = None,
+) -> MagicMock:
+    """Create a mock for httpx.AsyncClient.post that returns a fixed response."""
+    data = json_data or {"ws_id": "abc123", "name": "test"}
+
+    async def _mock_post(*args: Any, **kwargs: Any) -> httpx.Response:
+        return httpx.Response(
+            status_code,
+            json=data,
+            request=httpx.Request("POST", args[0] if args else "http://test"),
+        )
+
+    mock_post = MagicMock(side_effect=_mock_post)
+    return mock_post
+
+
+def _wire_proxy(app: Any, mock_post: MagicMock | None = None) -> None:
+    """Attach a mock proxy_client to the app (lifespan doesn't run in TestClient)."""
+    if mock_post is None:
+        mock_post = _make_proxy_post()
+    mock_proxy = MagicMock(spec=httpx.AsyncClient)
+    mock_proxy.post = mock_post
+    app.state.proxy_client = mock_proxy
+
+
+# ---------------------------------------------------------------------------
+# Tests — route_create
+# ---------------------------------------------------------------------------
+
+
+class TestRouteCreate:
+    """POST /v1/api/route/workstreams/new — create via hash-ring routing."""
+
+    @pytest.fixture()
+    def client(self):
+        router = _make_mock_router()
+        app = _make_app(router=router)
+        _wire_proxy(app, _make_proxy_post(json_data={"ws_id": "abc123", "name": "test"}))
+        client = TestClient(app, raise_server_exceptions=False)
+        yield client
+        client.close()
+
+    def test_route_create_proxies_to_node(self, client):
+        resp = client.post(
+            "/v1/api/route/workstreams/new",
+            json={"name": "test-ws"},
+            headers=_TEST_AUTH_HEADERS,
+        )
+        assert resp.status_code == 200
+        data = resp.json()
+        assert data["ws_id"] == "abc123"
+
+    def test_route_create_injects_node_url(self, client):
+        resp = client.post(
+            "/v1/api/route/workstreams/new",
+            json={"name": "test-ws"},
+            headers=_TEST_AUTH_HEADERS,
+        )
+        assert resp.status_code == 200
+        data = resp.json()
+        assert data["node_url"] == "http://a:8080"
+        assert data["node_id"] == "node-a"
+
+    def test_route_create_resume_ws(self):
+        """resume_ws should route to the node that owns the old workstream."""
+        router = _make_mock_router()
+        router.route.return_value = NodeRef("node-b", "http://b:8080")
+        app = _make_app(router=router)
+        _wire_proxy(app, _make_proxy_post(json_data={"ws_id": "old_ws_resumed", "name": "resumed"}))
+        client = TestClient(app, raise_server_exceptions=False)
+
+        resp = client.post(
+            "/v1/api/route/workstreams/new",
+            json={"resume_ws": "old_ws_id"},
+            headers=_TEST_AUTH_HEADERS,
+        )
+        assert resp.status_code == 200
+        data = resp.json()
+        assert data["node_url"] == "http://b:8080"
+        assert data["node_id"] == "node-b"
+        # route() should have been called with the old ws_id
+        router.route.assert_called_with("old_ws_id")
+        client.close()
+
+    def test_route_create_target_node(self):
+        """target_node should generate a ws_id that hashes to that node."""
+        router = _make_mock_router()
+        router.generate_ws_id_for_node.return_value = "00ff" + "0" * 28
+        router.route.return_value = NodeRef("node-c", "http://c:8080")
+        app = _make_app(router=router)
+        _wire_proxy(
+            app,
+            _make_proxy_post(json_data={"ws_id": "00ff" + "0" * 28, "name": "pinned"}),
+        )
+        client = TestClient(app, raise_server_exceptions=False)
+
+        resp = client.post(
+            "/v1/api/route/workstreams/new",
+            json={"target_node": "node-c"},
+            headers=_TEST_AUTH_HEADERS,
+        )
+        assert resp.status_code == 200
+        data = resp.json()
+        assert data["node_id"] == "node-c"
+        router.generate_ws_id_for_node.assert_called_with("node-c")
+        client.close()
+
+
+class TestRouteCreate503Retry:
+    """503 retry logic in route_create."""
+
+    def test_route_create_503_retries_on_different_node(self):
+        """If the first node returns 503, retry with a new ws_id targeting a different node."""
+        router = _make_mock_router()
+        call_count = 0
+
+        def side_effect_route(ws_id: str) -> NodeRef:
+            nonlocal call_count
+            call_count += 1
+            if call_count <= 1:
+                # First call returns node-a
+                return NodeRef("node-a", "http://a:8080")
+            # Subsequent calls return node-b (different node for retry)
+            return NodeRef("node-b", "http://b:8080")
+
+        router.route.side_effect = side_effect_route
+        app = _make_app(router=router)
+
+        post_count = 0
+
+        async def _mock_post(*args: Any, **kwargs: Any) -> httpx.Response:
+            nonlocal post_count
+            post_count += 1
+            if post_count == 1:
+                return httpx.Response(
+                    503,
+                    json={"error": "overloaded"},
+                    request=httpx.Request("POST", args[0] if args else "http://test"),
+                )
+            return httpx.Response(
+                200,
+                json={"ws_id": "retry_ws", "name": "retry"},
+                request=httpx.Request("POST", args[0] if args else "http://test"),
+            )
+
+        mock_proxy = MagicMock(spec=httpx.AsyncClient)
+        mock_proxy.post = MagicMock(side_effect=_mock_post)
+        app.state.proxy_client = mock_proxy
+        client = TestClient(app, raise_server_exceptions=False)
+
+        resp = client.post(
+            "/v1/api/route/workstreams/new",
+            json={"name": "test-ws"},
+            headers=_TEST_AUTH_HEADERS,
+        )
+        assert resp.status_code == 200
+        data = resp.json()
+        assert data["ws_id"] == "retry_ws"
+        assert data["node_id"] == "node-b"
+        assert post_count == 2
+        client.close()
+
+
+# ---------------------------------------------------------------------------
+# Tests — route_proxy
+# ---------------------------------------------------------------------------
+
+
+class TestRouteProxy:
+    """POST /v1/api/route/send (and other routed endpoints)."""
+
+    @pytest.fixture()
+    def client(self):
+        router = _make_mock_router()
+        app = _make_app(router=router)
+        _wire_proxy(app, _make_proxy_post(json_data={"status": "ok"}))
+        client = TestClient(app, raise_server_exceptions=False)
+        yield client
+        client.close()
+
+    def test_route_proxy_send(self, client):
+        resp = client.post(
+            "/v1/api/route/send",
+            json={"ws_id": "abc123", "message": "hello"},
+            headers=_TEST_AUTH_HEADERS,
+        )
+        assert resp.status_code == 200
+        # Verify upstream URL was /v1/api/send (not /v1/api/route/send)
+        mock_post = client.app.state.proxy_client.post
+        call_args = mock_post.call_args
+        assert "/v1/api/send" in call_args[0][0]
+        assert "/route/" not in call_args[0][0]
+
+    def test_route_proxy_approve(self, client):
+        resp = client.post(
+            "/v1/api/route/approve",
+            json={"ws_id": "abc123", "approved": True},
+            headers=_TEST_AUTH_HEADERS,
+        )
+        assert resp.status_code == 200
+
+    def test_route_proxy_cancel(self, client):
+        resp = client.post(
+            "/v1/api/route/cancel",
+            json={"ws_id": "abc123"},
+            headers=_TEST_AUTH_HEADERS,
+        )
+        assert resp.status_code == 200
+
+    def test_route_proxy_command(self, client):
+        resp = client.post(
+            "/v1/api/route/command",
+            json={"ws_id": "abc123", "command": "status"},
+            headers=_TEST_AUTH_HEADERS,
+        )
+        assert resp.status_code == 200
+
+    def test_route_proxy_close(self, client):
+        resp = client.post(
+            "/v1/api/route/workstreams/close",
+            json={"ws_id": "abc123"},
+            headers=_TEST_AUTH_HEADERS,
+        )
+        assert resp.status_code == 200
+
+
+# ---------------------------------------------------------------------------
+# Tests — route_lookup
+# ---------------------------------------------------------------------------
+
+
+class TestRouteLookup:
+    """GET /v1/api/route — look up which node owns a workstream."""
+
+    @pytest.fixture()
+    def client(self):
+        router = _make_mock_router()
+        app = _make_app(router=router)
+        app.state.proxy_client = MagicMock(spec=httpx.AsyncClient)
+        client = TestClient(app, raise_server_exceptions=False)
+        yield client
+        client.close()
+
+    def test_route_lookup(self, client):
+        resp = client.get("/v1/api/route?ws_id=abc123", headers=_TEST_AUTH_HEADERS)
+        assert resp.status_code == 200
+        data = resp.json()
+        assert data["node_url"] == "http://a:8080"
+        assert data["node_id"] == "node-a"
+
+    def test_route_lookup_missing_ws_id(self, client):
+        resp = client.get("/v1/api/route", headers=_TEST_AUTH_HEADERS)
+        assert resp.status_code == 400
+        assert "ws_id" in resp.json()["error"]
+
+
+# ---------------------------------------------------------------------------
+# Tests — not ready / no router -> 503
+# ---------------------------------------------------------------------------
+
+
+class TestRouteNotReady:
+    """When router is None or empty cache, all routing endpoints return 503."""
+
+    @pytest.fixture()
+    def client_no_router(self):
+        app = _make_app(router=None)
+        app.state.proxy_client = MagicMock(spec=httpx.AsyncClient)
+        client = TestClient(app, raise_server_exceptions=False)
+        yield client
+        client.close()
+
+    @pytest.fixture()
+    def client_empty_cache(self):
+        router = _make_mock_router(ready=False)
+        app = _make_app(router=router)
+        app.state.proxy_client = MagicMock(spec=httpx.AsyncClient)
+        client = TestClient(app, raise_server_exceptions=False)
+        yield client
+        client.close()
+
+    def test_route_create_no_router_503(self, client_no_router):
+        resp = client_no_router.post(
+            "/v1/api/route/workstreams/new",
+            json={"name": "test"},
+            headers=_TEST_AUTH_HEADERS,
+        )
+        assert resp.status_code == 503
+
+    def test_route_create_empty_cache_503(self, client_empty_cache):
+        resp = client_empty_cache.post(
+            "/v1/api/route/workstreams/new",
+            json={"name": "test"},
+            headers=_TEST_AUTH_HEADERS,
+        )
+        assert resp.status_code == 503
+
+    def test_route_proxy_no_router_503(self, client_no_router):
+        resp = client_no_router.post(
+            "/v1/api/route/send",
+            json={"ws_id": "abc", "message": "hello"},
+            headers=_TEST_AUTH_HEADERS,
+        )
+        assert resp.status_code == 503
+
+    def test_route_lookup_no_router_503(self, client_no_router):
+        resp = client_no_router.get("/v1/api/route?ws_id=abc", headers=_TEST_AUTH_HEADERS)
+        assert resp.status_code == 503
+
+    def test_route_proxy_empty_cache_503(self, client_empty_cache):
+        resp = client_empty_cache.post(
+            "/v1/api/route/send",
+            json={"ws_id": "abc", "message": "hello"},
+            headers=_TEST_AUTH_HEADERS,
+        )
+        assert resp.status_code == 503
+
+    def test_route_lookup_empty_cache_503(self, client_empty_cache):
+        resp = client_empty_cache.get("/v1/api/route?ws_id=abc", headers=_TEST_AUTH_HEADERS)
+        assert resp.status_code == 503
+
+
+# ---------------------------------------------------------------------------
+# Tests — NoAvailableNodeError handling
+# ---------------------------------------------------------------------------
+
+
+class TestRouteNoNode:
+    """When router.route() raises NoAvailableNodeError, endpoints return 503."""
+
+    @pytest.fixture()
+    def client(self):
+        router = _make_mock_router()
+        router.route.side_effect = NoAvailableNodeError("bucket 0 not assigned")
+        app = _make_app(router=router)
+        app.state.proxy_client = MagicMock(spec=httpx.AsyncClient)
+        client = TestClient(app, raise_server_exceptions=False)
+        yield client
+        client.close()
+
+    def test_route_create_no_node_503(self, client):
+        resp = client.post(
+            "/v1/api/route/workstreams/new",
+            json={"name": "test"},
+            headers=_TEST_AUTH_HEADERS,
+        )
+        assert resp.status_code == 503
+        assert "No available node" in resp.json()["error"]
+
+    def test_route_proxy_no_node_503(self, client):
+        resp = client.post(
+            "/v1/api/route/send",
+            json={"ws_id": "abc", "message": "hello"},
+            headers=_TEST_AUTH_HEADERS,
+        )
+        assert resp.status_code == 503
+
+    def test_route_lookup_no_node_503(self, client):
+        resp = client.get("/v1/api/route?ws_id=abc", headers=_TEST_AUTH_HEADERS)
+        assert resp.status_code == 503

tests/test_hash_ring.py

@@ -0,0 +1,15 @@
+"""Tests for turnstone.core.hash_ring."""
+
+from turnstone.core.hash_ring import bucket_of
+
+
+class TestBucketOf:
+    def test_known_vectors(self):
+        assert bucket_of("a3f1" + "0" * 28) == 0xA3F1
+        assert bucket_of("0000" + "a" * 28) == 0
+        assert bucket_of("ffff" + "b" * 28) == 65535
+
+    def test_hex_prefix(self):
+        # Only the first 4 hex chars matter — the rest is ignored.
+        assert bucket_of("abcd0000") == bucket_of("abcdffff")
+        assert bucket_of("abcd0000") == 0xABCD

tests/test_hash_ring_storage.py

@@ -0,0 +1,174 @@
+"""Tests for the hash ring routing storage methods."""
+
+from __future__ import annotations
+
+
+class TestHashRingBuckets:
+    def test_list_empty(self, storage):
+        assert storage.list_ring_buckets() == []
+
+    def test_seed_and_list(self, storage):
+        storage.seed_ring_buckets([(0, "node-a"), (1, "node-b"), (2, "node-a")])
+        rows = storage.list_ring_buckets()
+        assert len(rows) == 3
+        assert rows[0] == {"bucket": 0, "node_id": "node-a"}
+        assert rows[1] == {"bucket": 1, "node_id": "node-b"}
+        assert rows[2] == {"bucket": 2, "node_id": "node-a"}
+
+    def test_seed_idempotent(self, storage):
+        storage.seed_ring_buckets([(0, "node-a"), (1, "node-b")])
+        # Re-seed with conflicting assignment: should keep original
+        storage.seed_ring_buckets([(0, "node-x"), (2, "node-c")])
+        rows = storage.list_ring_buckets()
+        by_bucket = {r["bucket"]: r["node_id"] for r in rows}
+        assert by_bucket[0] == "node-a"  # original preserved
+        assert by_bucket[1] == "node-b"
+        assert by_bucket[2] == "node-c"  # new bucket added
+
+    def test_assign_buckets(self, storage):
+        storage.seed_ring_buckets([(0, "node-a"), (1, "node-a"), (2, "node-b")])
+        storage.assign_buckets([0, 1], "node-c")
+        rows = storage.list_ring_buckets()
+        by_bucket = {r["bucket"]: r["node_id"] for r in rows}
+        assert by_bucket[0] == "node-c"
+        assert by_bucket[1] == "node-c"
+        assert by_bucket[2] == "node-b"
+
+    def test_assign_returns_count(self, storage):
+        storage.seed_ring_buckets([(0, "node-a"), (1, "node-a")])
+        count = storage.assign_buckets([0, 1], "node-b")
+        assert count == 2
+        # Empty list returns 0
+        assert storage.assign_buckets([], "node-x") == 0
+
+    def test_assign_large_list_exceeds_chunk_size(self, storage):
+        """Regression: lists larger than chunk_size must not hit param limits."""
+        n = 1200  # exceeds SQLite chunk_size (500) and exercises multi-chunk path
+        storage.seed_ring_buckets([(i, "node-a") for i in range(n)])
+        count = storage.assign_buckets(list(range(n)), "node-b")
+        assert count == n
+        rows = storage.list_ring_buckets()
+        assert all(r["node_id"] == "node-b" for r in rows)
+
+    def test_assign_deduplicates_input(self, storage):
+        """Duplicates in the input list should not inflate rowcount."""
+        storage.seed_ring_buckets([(0, "node-a"), (1, "node-a")])
+        count = storage.assign_buckets([0, 1, 0, 1, 0], "node-b")
+        assert count == 2
+
+
+class TestBucketStats:
+    def test_increment_creates_row(self, storage):
+        storage.increment_bucket_count(42)
+        stats = storage.list_bucket_stats()
+        assert len(stats) == 1
+        assert stats[0]["bucket"] == 42
+        assert stats[0]["ws_count"] == 1
+        assert stats[0]["active_count"] == 0
+
+    def test_increment_active(self, storage):
+        storage.increment_bucket_count(10, active=True)
+        stats = storage.list_bucket_stats()
+        assert stats[0]["ws_count"] == 1
+        assert stats[0]["active_count"] == 1
+        # Increment again without active
+        storage.increment_bucket_count(10)
+        stats = storage.list_bucket_stats()
+        assert stats[0]["ws_count"] == 2
+        assert stats[0]["active_count"] == 1
+
+    def test_decrement(self, storage):
+        storage.increment_bucket_count(5, active=True)
+        storage.increment_bucket_count(5, active=True)
+        storage.decrement_bucket_count(5, active=True)
+        stats = storage.list_bucket_stats()
+        assert stats[0]["ws_count"] == 1
+        assert stats[0]["active_count"] == 1
+
+    def test_decrement_clamps_at_zero(self, storage):
+        storage.increment_bucket_count(7)
+        storage.decrement_bucket_count(7)
+        storage.decrement_bucket_count(7)  # already at 0
+        stats = storage.list_bucket_stats()
+        # ws_count is 0, so should not appear (filter ws_count > 0)
+        assert len(stats) == 0
+
+    def test_adjust_active_only(self, storage):
+        storage.increment_bucket_count(20, active=True)
+        storage.increment_bucket_count(20, active=True)
+        # Decrease active without changing ws_count
+        storage.adjust_bucket_active(20, -1)
+        stats = storage.list_bucket_stats()
+        assert stats[0]["ws_count"] == 2
+        assert stats[0]["active_count"] == 1
+        # Clamp at zero
+        storage.adjust_bucket_active(20, -5)
+        stats = storage.list_bucket_stats()
+        assert stats[0]["active_count"] == 0
+
+    def test_list_sparse(self, storage):
+        storage.increment_bucket_count(100)
+        storage.increment_bucket_count(200)
+        storage.increment_bucket_count(300)
+        # Decrement 200 to zero
+        storage.decrement_bucket_count(200)
+        stats = storage.list_bucket_stats()
+        buckets = [s["bucket"] for s in stats]
+        assert 100 in buckets
+        assert 200 not in buckets
+        assert 300 in buckets
+
+    def test_set_bucket_stat_creates(self, storage):
+        """set_bucket_stat upserts a new row."""
+        storage.set_bucket_stat(42, 5, 2)
+        stats = storage.list_bucket_stats()
+        row = next(s for s in stats if s["bucket"] == 42)
+        assert row["ws_count"] == 5
+        assert row["active_count"] == 2
+
+    def test_set_bucket_stat_overwrites(self, storage):
+        """set_bucket_stat overwrites existing values."""
+        storage.set_bucket_stat(42, 10, 3)
+        storage.set_bucket_stat(42, 2, 0)
+        stats = storage.list_bucket_stats()
+        row = next(s for s in stats if s["bucket"] == 42)
+        assert row["ws_count"] == 2
+        assert row["active_count"] == 0
+
+    def test_set_bucket_stat_zero_removes_from_sparse(self, storage):
+        """Setting ws_count=0 means list_bucket_stats excludes it (sparse)."""
+        storage.set_bucket_stat(42, 5, 1)
+        storage.set_bucket_stat(42, 0, 0)
+        stats = storage.list_bucket_stats()
+        assert not any(s["bucket"] == 42 for s in stats)
+
+
+class TestWorkstreamOverrides:
+    def test_set_and_list(self, storage):
+        storage.set_workstream_override("ws-001", "node-a", reason="affinity")
+        overrides = storage.list_workstream_overrides()
+        assert len(overrides) == 1
+        assert overrides[0]["ws_id"] == "ws-001"
+        assert overrides[0]["node_id"] == "node-a"
+        assert overrides[0]["reason"] == "affinity"
+
+    def test_upsert(self, storage):
+        storage.set_workstream_override("ws-002", "node-a")
+        storage.set_workstream_override("ws-002", "node-b", reason="migration")
+        overrides = storage.list_workstream_overrides()
+        assert len(overrides) == 1
+        assert overrides[0]["node_id"] == "node-b"
+        assert overrides[0]["reason"] == "migration"
+
+    def test_delete(self, storage):
+        storage.set_workstream_override("ws-003", "node-a")
+        result = storage.delete_workstream_override("ws-003")
+        assert result is True
+        assert storage.list_workstream_overrides() == []
+
+    def test_delete_nonexistent(self, storage):
+        result = storage.delete_workstream_override("ws-nope")
+        assert result is False
+
+    def test_list_empty(self, storage):
+        assert storage.list_workstream_overrides() == []

tests/test_load_skill.py

@@ -425,18 +425,23 @@ class TestSkillCatalogDisclosure:
         session._mcp_client = None
         session._notify_on_complete = "{}"
         session._tool_error_flags = {}
+        from turnstone.prompts import ClientType
+
+        session._tools = []
+        session._client_type = ClientType.CLI
+        session._username = ""
 
         # Memory stubs
         session._memory_config = MagicMock()
         session._memory_config.fetch_limit = 0
-        session._user_id = ""
+        session._user_id = "test-user"
 
         with (
             patch(
                 "turnstone.core.session.list_skills_by_activation",
                 return_value=search_skills or [],
             ),
-            patch.object(session, "_get_visible_memories", return_value=[]),
+            patch.object(session, "_list_visible_memories", return_value=[]),
         ):
             session._init_system_messages()
 

tests/test_model_probe.py

@@ -20,12 +20,15 @@ def _mock_model(
     *,
     owned_by: str = "test",
     meta: dict[str, Any] | None = None,
+    **kwargs: Any,
 ) -> MagicMock:
     m = MagicMock()
     m.id = model_id
     dumped: dict[str, Any] = {"owned_by": owned_by}
     if meta is not None:
         dumped["meta"] = meta
+    if kwargs.get("max_model_len") is not None:
+        dumped["max_model_len"] = kwargs["max_model_len"]
     m.model_dump.return_value = dumped
     return m
 
@@ -109,6 +112,27 @@ class TestProbeModelEndpoint:
         result = probe_model_endpoint("openai", "http://localhost:30000/v1", "key")
         assert result["server_type"] == "sglang"
 
+    @patch("turnstone.core.providers.create_client")
+    def test_vllm_max_model_len(self, mock_cc: MagicMock) -> None:
+        m = _mock_model("/models/nemotron", max_model_len=262144, owned_by="vllm")
+        mock_cc.return_value = _mock_client(m)
+
+        result = probe_model_endpoint("openai", "http://localhost:8000/v1", "key")
+        assert result["context_window"] == 262144
+        assert result["server_type"] == "vllm"
+
+    @patch("turnstone.core.providers.create_client")
+    def test_vllm_max_model_len_preferred_over_meta(self, mock_cc: MagicMock) -> None:
+        m = _mock_model(
+            "/models/test",
+            meta={"n_ctx_train": 8192},
+            max_model_len=131072,
+        )
+        mock_cc.return_value = _mock_client(m)
+
+        result = probe_model_endpoint("openai", "http://localhost:8000/v1", "key")
+        assert result["context_window"] == 131072
+
     @patch("turnstone.core.providers.create_client")
     def test_server_type_vllm(self, mock_cc: MagicMock) -> None:
         m = _mock_model("org/model-name")

tests/test_model_registry.py

@@ -840,32 +840,27 @@ class TestWorkstreamModelParam:
 
 
 # ---------------------------------------------------------------------------
-# Protocol
+# CreateWorkstreamRequest model field
 # ---------------------------------------------------------------------------
 
 
-class TestProtocolModel:
-    def test_create_workstream_message_has_model(self) -> None:
-        from turnstone.mq.protocol import CreateWorkstreamMessage
+class TestCreateWorkstreamRequestModel:
+    def test_request_has_model(self) -> None:
+        from turnstone.api.server_schemas import CreateWorkstreamRequest
 
-        msg = CreateWorkstreamMessage(name="test", model="openai")
-        assert msg.model == "openai"
+        req = CreateWorkstreamRequest(name="test", model="openai")
+        assert req.model == "openai"
 
-    def test_create_workstream_message_default(self) -> None:
-        from turnstone.mq.protocol import CreateWorkstreamMessage
+    def test_request_model_default(self) -> None:
+        from turnstone.api.server_schemas import CreateWorkstreamRequest
 
-        msg = CreateWorkstreamMessage(name="test")
-        assert msg.model == ""
+        req = CreateWorkstreamRequest(name="test")
+        assert req.model == ""
 
-    def test_round_trip(self) -> None:
-        from turnstone.mq.protocol import CreateWorkstreamMessage, InboundMessage
-
-        msg = CreateWorkstreamMessage(name="ws1", model="local")
-        raw = msg.to_json()
-        restored = InboundMessage.from_json(raw)
-        assert isinstance(restored, CreateWorkstreamMessage)
-        assert restored.model == "local"
-        assert restored.name == "ws1"
+    def test_json_payload_carries_model(self) -> None:
+        body = {"name": "ws1", "model": "local"}
+        assert body["model"] == "local"
+        assert body["name"] == "ws1"
 
 
 # ---------------------------------------------------------------------------
@@ -899,3 +894,125 @@ class TestDetectModelTimeout:
 
         result = detect_model(client, provider="openai", fatal=False)
         assert result == (None, None)
+
+    def test_vllm_max_model_len_detected(self) -> None:
+        """detect_model() reads max_model_len from vLLM model objects."""
+        mock_model = MagicMock()
+        mock_model.id = "/models/nemotron"
+        mock_model.model_dump.return_value = {
+            "owned_by": "vllm",
+            "max_model_len": 262144,
+        }
+
+        fast_client = MagicMock()
+        fast_client.models.list.return_value = MagicMock(data=[mock_model])
+
+        client = MagicMock()
+        client.with_options.return_value = fast_client
+
+        model_id, ctx = detect_model(client, provider="openai")
+        assert model_id == "/models/nemotron"
+        assert ctx == 262144
+
+
+class TestExtractContextWindow:
+    def test_vllm_max_model_len(self) -> None:
+        from turnstone.core.model_registry import _extract_context_window
+
+        m = MagicMock()
+        m.id = "/models/test"
+        m.model_dump.return_value = {"max_model_len": 131072}
+        assert _extract_context_window(m, "openai") == 131072
+
+    def test_llama_cpp_meta(self) -> None:
+        from turnstone.core.model_registry import _extract_context_window
+
+        m = MagicMock()
+        m.id = "test"
+        m.model_dump.return_value = {"meta": {"n_ctx_train": 8192}}
+        assert _extract_context_window(m, "openai") == 8192
+
+    def test_vllm_preferred_over_meta(self) -> None:
+        from turnstone.core.model_registry import _extract_context_window
+
+        m = MagicMock()
+        m.id = "test"
+        m.model_dump.return_value = {"max_model_len": 262144, "meta": {"n_ctx_train": 4096}}
+        assert _extract_context_window(m, "openai") == 262144
+
+    def test_no_metadata_returns_none(self) -> None:
+        from turnstone.core.model_registry import _extract_context_window
+
+        m = MagicMock()
+        m.id = "test"
+        m.model_dump.return_value = {}
+        assert _extract_context_window(m, "openai") is None
+
+
+class TestHealthMonitorModelChange:
+    def test_model_change_fires_callback(self) -> None:
+        from turnstone.core.healthcheck import BackendHealthMonitor
+
+        changes: list[tuple[str, int | None]] = []
+
+        def on_change(model_id: str, ctx: int | None) -> None:
+            changes.append((model_id, ctx))
+
+        client = MagicMock()
+        monitor = BackendHealthMonitor(
+            client=client,
+            provider="openai",
+            initial_model="model-a",
+            on_model_changed=on_change,
+        )
+
+        # Simulate probe returning a different model
+        resp = MagicMock()
+        m = MagicMock()
+        m.id = "model-b"
+        m.model_dump.return_value = {"max_model_len": 131072}
+        resp.data = [m]
+
+        monitor._check_model_change(resp)
+        assert len(changes) == 1
+        assert changes[0] == ("model-b", 131072)
+        assert monitor._last_detected_model == "model-b"
+
+    def test_same_model_no_callback(self) -> None:
+        from turnstone.core.healthcheck import BackendHealthMonitor
+
+        changes: list[tuple[str, int | None]] = []
+
+        def on_change(model_id: str, ctx: int | None) -> None:
+            changes.append((model_id, ctx))
+
+        client = MagicMock()
+        monitor = BackendHealthMonitor(
+            client=client,
+            provider="openai",
+            initial_model="model-a",
+            on_model_changed=on_change,
+        )
+
+        resp = MagicMock()
+        m = MagicMock()
+        m.id = "model-a"
+        m.model_dump.return_value = {}
+        resp.data = [m]
+
+        monitor._check_model_change(resp)
+        assert len(changes) == 0
+
+    def test_no_callback_configured(self) -> None:
+        from turnstone.core.healthcheck import BackendHealthMonitor
+
+        client = MagicMock()
+        monitor = BackendHealthMonitor(client=client, initial_model="model-a")
+
+        resp = MagicMock()
+        m = MagicMock()
+        m.id = "model-b"
+        resp.data = [m]
+
+        # Should not raise
+        monitor._check_model_change(resp)