fix: review fixes for custom LLM provider PR

- Add server-side validation of custom provider ID format (lowercase
  alphanumeric + hyphens, 1-64 chars) to match frontend regex
- Tighten is_nearai_private_endpoint to exact-match private.near.ai
  or *.private.near.ai, rejecting lookalikes like private-evil.near.ai
- Fix misleading priority doc comments in config/mod.rs and settings.rs
  to reflect the split model: LLM uses DB > env, others use env > DB
- Clean up #1581 artifacts: remove TOML file creation from
  persist_selected_model (DB is sufficient), update stale priority
  comments in commands.rs, fix contradictory test assertions
- Add 18 new tests for provider ID validation, adapter validation,
  and nearai private endpoint matching

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>

Cargo.lock

@@ -3150,7 +3150,7 @@ dependencies = [
  "libc",
  "percent-encoding",
  "pin-project-lite",
- "socket2 0.6.3",
+ "socket2 0.5.10",
  "system-configuration",
  "tokio",
  "tower-service",
@@ -3439,7 +3439,6 @@ dependencies = [
  "pgvector",
  "postgres-types",
  "pretty_assertions",
- "pty-process",
  "rand 0.8.5",
  "readabilityrs",
  "refinery",
@@ -3483,7 +3482,6 @@ dependencies = [
  "wasmparser 0.220.1",
  "wasmtime",
  "wasmtime-wasi",
- "webpki-roots 0.26.11",
  "zbus",
  "zip",
 ]
@@ -3525,7 +3523,7 @@ checksum = "3640c1c38b8e4e43584d8df18be5fc6b0aa314ce6ebf51b53313d4306cca8e46"
 dependencies = [
  "hermit-abi",
  "libc",
- "windows-sys 0.61.2",
+ "windows-sys 0.59.0",
 ]
 
 [[package]]
@@ -4907,16 +4905,6 @@ dependencies = [
  "syn 1.0.109",
 ]
 
-[[package]]
-name = "pty-process"
-version = "0.5.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "71cec9e2670207c5ebb9e477763c74436af3b9091dd550b9fb3c1bec7f3ea266"
-dependencies = [
- "rustix 1.1.4",
- "tokio",
-]
-
 [[package]]
 name = "pulley-interpreter"
 version = "28.0.1"
@@ -4941,7 +4929,7 @@ dependencies = [
  "quinn-udp",
  "rustc-hash 2.1.1",
  "rustls 0.23.37",
- "socket2 0.6.3",
+ "socket2 0.5.10",
  "thiserror 2.0.18",
  "tokio",
  "tracing",
@@ -4978,9 +4966,9 @@ dependencies = [
  "cfg_aliases",
  "libc",
  "once_cell",
- "socket2 0.6.3",
+ "socket2 0.5.10",
  "tracing",
- "windows-sys 0.60.2",
+ "windows-sys 0.59.0",
 ]
 
 [[package]]
@@ -7003,7 +6991,6 @@ dependencies = [
  "futures-util",
  "http 1.4.0",
  "http-body 1.0.1",
- "http-body-util",
  "iri-string",
  "pin-project-lite",
  "tower 0.5.3",

Cargo.toml

@@ -57,7 +57,6 @@ refinery = { version = "0.8", features = ["tokio-postgres"], optional = true }
 tokio-postgres-rustls = { version = "0.13", optional = true }
 rustls = { version = "0.23", optional = true, default-features = false }
 rustls-native-certs = { version = "0.8", optional = true }
-webpki-roots = { version = "0.26", optional = true }
 
 # Database - libSQL/Turso (optional embedded database)
 libsql = { version = "0.6", optional = true, default-features = false, features = ["core", "replication", "remote", "tls"] }
@@ -96,7 +95,7 @@ termimad = "0.34"
 # Channel integrations
 axum = { version = "0.8", features = ["ws"] }
 tower = "0.5"
-tower-http = { version = "0.6", features = ["trace", "cors", "set-header", "catch-panic"] }
+tower-http = { version = "0.6", features = ["trace", "cors", "set-header"] }
 
 # Cron scheduling for routines
 cron = "0.13"
@@ -189,10 +188,6 @@ json5 = { version = "0.4", optional = true }
 [target.'cfg(target_os = "macos")'.dependencies]
 security-framework = "3"
 
-# PTY allocation for Claude CLI stdout buffering fix (Unix only)
-[target.'cfg(unix)'.dependencies]
-pty-process = { version = "0.5", features = ["async"] }
-
 # Linux secret-service (GNOME Keyring, KWallet)
 [target.'cfg(target_os = "linux")'.dependencies]
 secret-service = { version = "4", features = ["rt-tokio-crypto-rust"] }
@@ -224,7 +219,6 @@ postgres = [
     "dep:tokio-postgres-rustls",
     "dep:rustls",
     "dep:rustls-native-certs",
-    "dep:webpki-roots",
     "dep:postgres-types",
     "dep:refinery",
     "dep:pgvector",

Dockerfile

@@ -1,71 +1,45 @@
 # Multi-stage Dockerfile for the IronClaw agent (cloud deployment).
 #
-# Uses cargo-chef for dependency caching — only rebuilds deps when
-# Cargo.toml/Cargo.lock change, not on every source edit.
-#
 # Build:
 #   docker build --platform linux/amd64 -t ironclaw:latest .
 #
 # Run:
 #   docker run --env-file .env -p 3000:3000 ironclaw:latest
 
-# Stage 1: Install cargo-chef
-FROM rust:1.92-slim-bookworm AS chef
+# Stage 1: Build
+FROM rust:1.92-slim-bookworm AS builder
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
     pkg-config libssl-dev cmake gcc g++ \
     && rm -rf /var/lib/apt/lists/* \
     && rustup target add wasm32-wasip2 \
-    && cargo install cargo-chef wasm-tools
+    && cargo install wasm-tools
 
 WORKDIR /app
 
-# Stage 2: Generate the dependency recipe (changes only when Cargo.toml/lock change)
-FROM chef AS planner
-
+# Copy manifests first for layer caching
 COPY Cargo.toml Cargo.lock ./
 COPY crates/ crates/
+
+# Copy source, build script, tests, and supporting directories
 COPY build.rs build.rs
 COPY src/ src/
 COPY tests/ tests/
-COPY benches/ benches/
 COPY migrations/ migrations/
 COPY registry/ registry/
 COPY channels-src/ channels-src/
 COPY wit/ wit/
 COPY providers.json providers.json
-
-RUN cargo chef prepare --recipe-path recipe.json
-
-# Stage 3: Build dependencies (cached unless Cargo.toml/lock change)
-FROM chef AS deps
-
-COPY --from=planner /app/recipe.json recipe.json
-RUN cargo chef cook --release --recipe-path recipe.json
-
-# Stage 4: Build the actual binary (only recompiles ironclaw source)
-FROM deps AS builder
-
-COPY Cargo.toml Cargo.lock ./
-COPY crates/ crates/
-COPY build.rs build.rs
-COPY src/ src/
-COPY tests/ tests/
+# [[bench]] entries in Cargo.toml require bench sources to exist for cargo to parse the manifest
 COPY benches/ benches/
-COPY migrations/ migrations/
-COPY registry/ registry/
-COPY channels-src/ channels-src/
-COPY wit/ wit/
-COPY providers.json providers.json
 
 RUN cargo build --release --bin ironclaw
 
-# Stage 5: Runtime
+# Stage 2: Runtime
 FROM debian:bookworm-slim
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
     ca-certificates libssl3 \
-    && update-ca-certificates \
     && rm -rf /var/lib/apt/lists/*
 
 COPY --from=builder /app/target/release/ironclaw /usr/local/bin/ironclaw

channels-src/discord/src/lib.rs

@@ -28,9 +28,6 @@ use std::{cmp::Ordering, collections::HashMap};
 use ed25519_dalek::{Signature, Verifier, VerifyingKey};
 use serde::{Deserialize, Serialize};
 
-/// Discord REST API v10 base URL.
-const DISCORD_API_BASE: &str = "https://discord.com/api/v10";
-
 use exports::near::agent::channel::{
     AgentResponse, ChannelConfig, Guest, HttpEndpointConfig, IncomingHttpRequest,
     OutgoingHttpResponse, PollConfig, StatusUpdate,
@@ -430,7 +427,7 @@ impl Guest for DiscordChannel {
             (
                 "PATCH",
                 format!(
-                    "{DISCORD_API_BASE}/webhooks/{}/{}/messages/@original",
+                    "https://discord.com/api/v10/webhooks/{}/{}/messages/@original",
                     application_id, token
                 ),
             )
@@ -441,7 +438,20 @@ impl Guest for DiscordChannel {
             payload["allowed_mentions"] = serde_json::json!({
                 "replied_user": true
             });
-            return send_channel_message(&metadata.channel_id, payload);
+            let mention_payload = serde_json::to_vec(&payload)
+                .map_err(|e| format!("Failed to serialize mention payload: {}", e))?;
+            let mention_url = format!(
+                "https://discord.com/api/v10/channels/{}/messages",
+                metadata.channel_id
+            );
+            let result = channel_host::http_request(
+                "POST",
+                &mention_url,
+                &discord_auth_headers_json(true),
+                Some(&mention_payload),
+                None,
+            );
+            return map_discord_response(result);
         } else {
             return Err("Unsupported Discord response metadata".to_string());
         };
@@ -459,8 +469,8 @@ impl Guest for DiscordChannel {
 
     fn on_status(_update: StatusUpdate) {}
 
-    fn on_broadcast(user_id: String, response: AgentResponse) -> Result<(), String> {
-        broadcast_dm(&user_id, &response.content)
+    fn on_broadcast(_user_id: String, _response: AgentResponse) -> Result<(), String> {
+        Err("broadcast not yet implemented for Discord channel".to_string())
     }
 
     fn on_shutdown() {
@@ -491,21 +501,6 @@ fn map_discord_response(
     }
 }
 
-/// Post a JSON payload to a Discord channel as a new message.
-fn send_channel_message(channel_id: &str, payload: serde_json::Value) -> Result<(), String> {
-    let payload_bytes = serde_json::to_vec(&payload)
-        .map_err(|e| format!("Failed to serialize message: {}", e))?;
-    let url = format!("{DISCORD_API_BASE}/channels/{}/messages", channel_id);
-    let result = channel_host::http_request(
-        "POST",
-        &url,
-        &discord_auth_headers_json(true),
-        Some(&payload_bytes),
-        None,
-    );
-    map_discord_response(result)
-}
-
 fn load_runtime_config() -> DiscordRuntimeConfig {
     channel_host::workspace_read("config.json")
         .and_then(|raw| serde_json::from_str::<DiscordRuntimeConfig>(&raw).ok())
@@ -544,7 +539,7 @@ fn get_or_fetch_bot_id() -> Option<String> {
 
     let response = channel_host::http_request(
         "GET",
-        &format!("{DISCORD_API_BASE}/users/@me"),
+        "https://discord.com/api/v10/users/@me",
         &discord_auth_headers_json(false),
         None,
         Some(10_000),
@@ -664,7 +659,7 @@ fn poll_channel_mentions(channel_id: &str, bot_id: &str) {
 
 fn fetch_latest_message_id(channel_id: &str) -> Option<String> {
     let url = format!(
-        "{DISCORD_API_BASE}/channels/{}/messages?limit=1",
+        "https://discord.com/api/v10/channels/{}/messages?limit=1",
         channel_id
     );
     let response = channel_host::http_request(
@@ -702,7 +697,7 @@ fn fetch_messages_after_cursor(
 
     for page in 0..MAX_PAGES {
         let url = format!(
-            "{DISCORD_API_BASE}/channels/{}/messages?limit={}&after={}",
+            "https://discord.com/api/v10/channels/{}/messages?limit={}&after={}",
             channel_id, PAGE_LIMIT, after
         );
         let response = match channel_host::http_request(
@@ -991,7 +986,7 @@ fn handle_slash_command(interaction: &DiscordInteraction) -> bool {
             );
             // Attempt to notify user of internal error
             let url = format!(
-                "{DISCORD_API_BASE}/webhooks/{}/{}",
+                "https://discord.com/api/v10/webhooks/{}/{}",
                 interaction.application_id, interaction.token
             );
             let payload = serde_json::json!({
@@ -1111,7 +1106,7 @@ fn check_sender_permission(
     }
 
     let dm_policy =
-        channel_host::workspace_read(DM_POLICY_PATH).unwrap_or_else(default_dm_policy);
+        channel_host::workspace_read(DM_POLICY_PATH).unwrap_or_else(|| default_dm_policy());
     if dm_policy == "open" {
         return true;
     }
@@ -1166,7 +1161,7 @@ fn check_sender_permission(
 /// Send a pairing code as an ephemeral Discord followup message.
 fn send_pairing_reply(ctx: &PairingReplyCtx, code: &str) -> Result<(), String> {
     let url = format!(
-        "{DISCORD_API_BASE}/webhooks/{}/{}",
+        "https://discord.com/api/v10/webhooks/{}/{}",
         ctx.application_id, ctx.token
     );
     let payload = serde_json::json!({
@@ -1199,57 +1194,6 @@ fn send_pairing_reply(ctx: &PairingReplyCtx, code: &str) -> Result<(), String> {
     }
 }
 
-/// Send a broadcast message to a Discord user via DM.
-///
-/// Creates a DM channel with the user (Discord caches this, so repeated calls
-/// for the same user reuse the existing channel) and then posts the message.
-fn broadcast_dm(user_id: &str, content: &str) -> Result<(), String> {
-    // Validate user_id is a plausible Discord snowflake (numeric, 17-20 digits)
-    // to avoid injecting arbitrary strings into API URLs.
-    if user_id.is_empty()
-        || !user_id.chars().all(|c| c.is_ascii_digit())
-        || user_id.len() < 17
-        || user_id.len() > 20
-    {
-        return Err(format!("Invalid Discord user ID: '{}'", user_id));
-    }
-
-    // Step 1: Open (or reuse) a DM channel with the target user.
-    let create_dm_payload = serde_json::json!({ "recipient_id": user_id });
-    let create_dm_bytes = serde_json::to_vec(&create_dm_payload)
-        .map_err(|e| format!("Failed to serialize DM channel request: {}", e))?;
-
-    let dm_response = channel_host::http_request(
-        "POST",
-        &format!("{DISCORD_API_BASE}/users/@me/channels"),
-        &discord_auth_headers_json(true),
-        Some(&create_dm_bytes),
-        Some(10_000),
-    )
-    .map_err(|e| format!("Failed to create DM channel: {}", e))?;
-
-    if !(200..300).contains(&dm_response.status) {
-        let body = String::from_utf8_lossy(&dm_response.body);
-        return Err(format!(
-            "Discord create-DM failed: {} - {}",
-            dm_response.status, body
-        ));
-    }
-
-    #[derive(Deserialize)]
-    struct DmChannelResponse {
-        id: String,
-    }
-    let dm_channel: DmChannelResponse = serde_json::from_slice(&dm_response.body)
-        .map_err(|e| format!("Failed to parse DM channel response: {}", e))?;
-    let channel_id = &dm_channel.id;
-
-    // Step 2: Send the message to the DM channel.
-    let truncated = truncate_message(content);
-    let payload = serde_json::json!({ "content": truncated });
-    send_channel_message(channel_id, payload)
-}
-
 fn json_response(status: u16, value: serde_json::Value) -> OutgoingHttpResponse {
     let body = serde_json::to_vec(&value).unwrap_or_default();
     let headers = serde_json::json!({"Content-Type": "application/json"});
@@ -1649,43 +1593,4 @@ mod tests {
         assert_eq!(interaction.interaction_type, 2);
         assert!(interaction.data.is_some());
     }
-
-    #[test]
-    fn test_broadcast_dm_payload_format() {
-        // Verify the DM channel creation payload is well-formed JSON that
-        // Discord's API expects.
-        let user_id = "123456789012345678";
-        let payload = serde_json::json!({ "recipient_id": user_id });
-        let serialized = serde_json::to_vec(&payload).unwrap();
-        let parsed: serde_json::Value = serde_json::from_slice(&serialized).unwrap();
-        assert_eq!(
-            parsed.get("recipient_id").and_then(|v| v.as_str()),
-            Some(user_id)
-        );
-    }
-
-    #[test]
-    fn test_broadcast_message_truncation() {
-        // Broadcast uses truncate_message, verify it handles content within
-        // Discord's 2000-char limit for DMs.
-        let short = "Hello from broadcast";
-        assert_eq!(truncate_message(short), short);
-
-        let long = "x".repeat(2500);
-        let result = truncate_message(&long);
-        assert!(result.len() <= 2006); // 1990 content + 16 suffix
-        assert!(result.ends_with("\n... (truncated)"));
-    }
-
-    #[test]
-    fn test_broadcast_dm_validates_snowflake() {
-        // broadcast_dm rejects invalid Discord snowflake IDs before making
-        // any API calls. We can call it directly since invalid IDs are
-        // rejected before any host function is invoked.
-        assert!(broadcast_dm("", "hi").is_err());
-        assert!(broadcast_dm("abc", "hi").is_err());
-        assert!(broadcast_dm("12345", "hi").is_err()); // too short
-        assert!(broadcast_dm("123456789012345678901", "hi").is_err()); // too long
-        assert!(broadcast_dm("12345678901234567x", "hi").is_err()); // non-digit
-    }
 }

docs/USER_MANAGEMENT_API.md

@@ -1,572 +0,0 @@
-# User Management API
-
-DB-backed user management for multi-tenant IronClaw deployments. Covers admin user CRUD, per-user secrets provisioning, self-service profile, API token management, and usage reporting.
-
-## Authentication
-
-All endpoints require `Authorization: Bearer <token>`. Tokens are either:
-- **Env-var tokens** — configured via `GATEWAY_AUTH_TOKEN` (single-user) at startup
-- **DB-backed tokens** — created via `POST /api/tokens` or `POST /api/admin/users`
-
-DB tokens are SHA-256 hashed at rest; plaintext is returned exactly once at creation time.
-
-Auth is cached in a bounded LRU (1024 entries, 60s TTL). Suspending a user or revoking a token may take up to 60s to take effect.
-
-## Roles
-
-| Role | Scope |
-|------|-------|
-| `admin` | Full access to all endpoints |
-| `member` | Self-service profile + own token management only |
-
-Endpoints marked **Admin** return `403 Forbidden` for `member` role.
-
----
-
-## Admin: Users
-
-### POST /api/admin/users
-
-Create a new user. Returns the user record and a one-time plaintext API token.
-
-**Auth:** Admin
-
-**Request body:**
-
-```json
-{
-  "display_name": "Alice Smith",
-  "email": "[email protected]",
-  "role": "member"
-}
-```
-
-| Field | Type | Required | Default | Notes |
-|-------|------|----------|---------|-------|
-| `display_name` | string | yes | | |
-| `email` | string | no | `null` | Must be unique if provided |
-| `role` | string | no | `"member"` | `"admin"` or `"member"` |
-
-**Response:** `200 OK`
-
-```json
-{
-  "id": "550e8400-e29b-41d4-a716-446655440000",
-  "email": "[email protected]",
-  "display_name": "Alice Smith",
-  "status": "active",
-  "role": "member",
-  "token": "a1b2c3d4e5f6...64-char hex...",
-  "created_at": "2026-03-25T12:00:00+00:00",
-  "created_by": "admin-user-id"
-}
-```
-
-The `token` field is the plaintext API token. It is shown **only once** — store it securely.
-
-**Errors:** `400` (missing display_name, invalid role), `403` (not admin), `503` (no database)
-
----
-
-### GET /api/admin/users
-
-List all users.
-
-**Auth:** Admin
-
-**Response:** `200 OK`
-
-```json
-{
-  "users": [
-    {
-      "id": "550e8400-...",
-      "email": "[email protected]",
-      "display_name": "Alice Smith",
-      "status": "active",
-      "role": "member",
-      "created_at": "2026-03-25T12:00:00+00:00",
-      "updated_at": "2026-03-25T12:00:00+00:00",
-      "last_login_at": "2026-03-25T14:30:00+00:00",
-      "created_by": "admin-user-id"
-    }
-  ]
-}
-```
-
----
-
-### GET /api/admin/users/{id}
-
-Get a single user by ID.
-
-**Auth:** Admin
-
-**Response:** `200 OK`
-
-```json
-{
-  "id": "550e8400-...",
-  "email": "[email protected]",
-  "display_name": "Alice Smith",
-  "status": "active",
-  "role": "member",
-  "created_at": "2026-03-25T12:00:00+00:00",
-  "updated_at": "2026-03-25T12:00:00+00:00",
-  "last_login_at": "2026-03-25T14:30:00+00:00",
-  "created_by": "admin-user-id",
-  "metadata": {}
-}
-```
-
-**Errors:** `404` (user not found), `403` (not admin)
-
----
-
-### PATCH /api/admin/users/{id}
-
-Update a user's display name and/or metadata. Omitted fields are left unchanged.
-
-**Auth:** Admin
-
-**Request body:**
-
-```json
-{
-  "display_name": "Alice Johnson",
-  "metadata": {"department": "engineering"}
-}
-```
-
-| Field | Type | Required | Notes |
-|-------|------|----------|-------|
-| `display_name` | string | no | |
-| `role` | string | no | `"admin"` or `"member"` |
-| `metadata` | object | no | Replaces entire metadata object (full replacement; keys not included are removed) |
-
-**Response:** `200 OK` — returns the full updated user record (same shape as GET detail, without `last_login_at`/`created_by`).
-
-**Errors:** `404` (user not found), `403` (not admin)
-
----
-
-### POST /api/admin/users/{id}/suspend
-
-Suspend a user. Suspended users cannot authenticate (DB auth checks user status).
-
-**Auth:** Admin
-
-**Response:** `200 OK`
-
-```json
-{
-  "id": "550e8400-...",
-  "status": "suspended"
-}
-```
-
-**Errors:** `404` (user not found), `403` (not admin)
-
----
-
-### POST /api/admin/users/{id}/activate
-
-Re-activate a suspended user.
-
-**Auth:** Admin
-
-**Response:** `200 OK`
-
-```json
-{
-  "id": "550e8400-...",
-  "status": "active"
-}
-```
-
-**Errors:** `404` (user not found), `403` (not admin)
-
----
-
-### DELETE /api/admin/users/{id}
-
-Permanently delete a user and all associated data (tokens, jobs, conversations, memory, routines, settings, secrets).
-
-**Auth:** Admin
-
-**Response:** `200 OK`
-
-```json
-{
-  "id": "550e8400-...",
-  "deleted": true
-}
-```
-
-**Errors:** `404` (user not found), `403` (not admin)
-
-**Cascade:** Deletes from `api_tokens`, `agent_jobs`, `conversations`, `memory_documents`, `routines`, `secrets`, `settings`, `wasm_tools`, and related tables. On PostgreSQL this uses FK cascades; on libSQL it uses explicit deletes.
-
----
-
-## Admin: Per-User Secrets
-
-Provision secrets on behalf of individual users. The primary use case is an application backend (acting as admin) that configures per-user credentials so each user's IronClaw agent can call back to external services.
-
-Secrets are encrypted at rest with AES-256-GCM using a per-secret HKDF-derived key. Plaintext values are **never returned** by any endpoint — they can only be used by the agent's tool system at runtime.
-
-### PUT /api/admin/users/{user_id}/secrets/{name}
-
-Create or update a secret for the specified user. If a secret with the same name already exists, it is overwritten.
-
-**Auth:** Admin
-
-**Path parameters:**
-
-| Param | Type | Notes |
-|-------|------|-------|
-| `user_id` | string | The user's ID |
-| `name` | string | Secret name (normalized to lowercase) |
-
-**Request body:**
-
-```json
-{
-  "value": "sk-live-abc123...",
-  "provider": "my-app-backend",
-  "expires_in_days": 90
-}
-```
-
-| Field | Type | Required | Notes |
-|-------|------|----------|-------|
-| `value` | string | yes | The secret value (encrypted at rest, never returned) |
-| `provider` | string | no | Tag for grouping (e.g. `"stripe"`, `"my-app"`) |
-| `expires_in_days` | integer | no | Auto-expire after N days; `null` = never |
-
-**Response:** `200 OK`
-
-```json
-{
-  "user_id": "550e8400-...",
-  "name": "my_app_callback_token",
-  "status": "created"
-}
-```
-
-**Errors:** `400` (missing value), `403` (not admin), `503` (secrets store not available)
-
-**Example — application backend provisioning a callback token:**
-
-```bash
-# Admin creates a user
-curl -X POST https://ironclaw.example.com/api/admin/users \
-  -H "Authorization: Bearer $ADMIN_TOKEN" \
-  -d '{"display_name": "Alice", "role": "member"}'
-# Response includes: {"id": "alice-uuid", "token": "alice-bearer-token", ...}
-
-# Admin provisions a per-user callback secret
-curl -X PUT https://ironclaw.example.com/api/admin/users/alice-uuid/secrets/app_callback_token \
-  -H "Authorization: Bearer $ADMIN_TOKEN" \
-  -d '{"value": "per-user-jwt-for-alice", "provider": "my-app"}'
-
-# Now Alice's IronClaw agent can use the "app_callback_token" secret
-# when calling tools that need to authenticate back to the app backend.
-```
-
----
-
-### GET /api/admin/users/{user_id}/secrets
-
-List a user's secrets. Returns names and providers only — **never values or hashes**.
-
-**Auth:** Admin
-
-**Response:** `200 OK`
-
-```json
-{
-  "user_id": "550e8400-...",
-  "secrets": [
-    {"name": "app_callback_token", "provider": "my-app"},
-    {"name": "openai_api_key", "provider": "openai"}
-  ]
-}
-```
-
----
-
-### DELETE /api/admin/users/{user_id}/secrets/{name}
-
-Delete a specific secret for a user.
-
-**Auth:** Admin
-
-**Response:** `200 OK`
-
-```json
-{
-  "user_id": "550e8400-...",
-  "name": "app_callback_token",
-  "deleted": true
-}
-```
-
-**Errors:** `404` (secret not found), `403` (not admin), `503` (secrets store not available)
-
----
-
-## Admin: Usage
-
-### GET /api/admin/usage
-
-Per-user LLM usage statistics aggregated from `llm_calls` via `agent_jobs.user_id`.
-
-**Auth:** Admin
-
-**Query parameters:**
-
-| Param | Type | Default | Notes |
-|-------|------|---------|-------|
-| `user_id` | string | all users | Filter to a single user |
-| `period` | string | `"day"` | `"day"` (24h), `"week"` (7d), or `"month"` (30d) |
-
-**Response:** `200 OK`
-
-```json
-{
-  "period": "week",
-  "since": "2026-03-18T12:00:00+00:00",
-  "usage": [
-    {
-      "user_id": "alice-id",
-      "model": "claude-sonnet-4-5-20250514",
-      "call_count": 42,
-      "input_tokens": 150000,
-      "output_tokens": 30000,
-      "total_cost": "1.23"
-    }
-  ]
-}
-```
-
----
-
-## Self-Service: Profile
-
-### GET /api/profile
-
-Get the authenticated user's own profile.
-
-**Auth:** Any authenticated user
-
-**Response:** `200 OK`
-
-```json
-{
-  "id": "550e8400-...",
-  "email": "[email protected]",
-  "display_name": "Alice Smith",
-  "status": "active",
-  "role": "member",
-  "created_at": "2026-03-25T12:00:00+00:00",
-  "last_login_at": "2026-03-25T14:30:00+00:00"
-}
-```
-
----
-
-### PATCH /api/profile
-
-Update the authenticated user's own display name and/or metadata.
-
-**Auth:** Any authenticated user
-
-**Request body:**
-
-```json
-{
-  "display_name": "Alice Johnson",
-  "metadata": {"theme": "dark"}
-}
-```
-
-**Response:** `200 OK`
-
-```json
-{
-  "id": "550e8400-...",
-  "display_name": "Alice Johnson",
-  "updated": true
-}
-```
-
----
-
-## Self-Service: Tokens
-
-### POST /api/tokens
-
-Create a new API token for the authenticated user. Admins can optionally create tokens for other users by including `user_id`.
-
-**Auth:** Any authenticated user
-
-**Request body:**
-
-```json
-{
-  "name": "CI pipeline",
-  "expires_in_days": 90,
-  "user_id": "other-user-id"
-}
-```
-
-| Field | Type | Required | Notes |
-|-------|------|----------|-------|
-| `name` | string | yes | Human-readable label |
-| `expires_in_days` | integer | no | `null` = never expires |
-| `user_id` | string | no | Admin-only; create token for another user |
-
-**Response:** `200 OK`
-
-```json
-{
-  "token": "a1b2c3d4...64-char hex...",
-  "id": "token-uuid",
-  "name": "CI pipeline",
-  "token_prefix": "a1b2c3d4",
-  "expires_at": "2026-06-23T12:00:00+00:00",
-  "created_at": "2026-03-25T12:00:00+00:00"
-}
-```
-
-The `token` field is shown **only once**.
-
----
-
-### GET /api/tokens
-
-List the authenticated user's tokens. Token hashes are never returned.
-
-**Auth:** Any authenticated user
-
-**Response:** `200 OK`
-
-```json
-{
-  "tokens": [
-    {
-      "id": "token-uuid",
-      "name": "CI pipeline",
-      "token_prefix": "a1b2c3d4",
-      "expires_at": "2026-06-23T12:00:00+00:00",
-      "last_used_at": "2026-03-25T14:00:00+00:00",
-      "created_at": "2026-03-25T12:00:00+00:00",
-      "revoked_at": null
-    }
-  ]
-}
-```
-
----
-
-### DELETE /api/tokens/{id}
-
-Revoke one of the authenticated user's tokens. Users can only revoke their own tokens.
-
-**Auth:** Any authenticated user
-
-**Path:** `id` — UUID of the token to revoke
-
-**Response:** `200 OK`
-
-```json
-{
-  "status": "revoked",
-  "id": "token-uuid"
-}
-```
-
-**Errors:** `400` (invalid UUID), `404` (token not found or belongs to another user)
-
----
-
-## Error Format
-
-All error responses return a plain text body with the error message and the corresponding HTTP status code:
-
-| Code | Meaning |
-|------|---------|
-| `400` | Bad request (missing fields, invalid input) |
-| `401` | Missing or invalid bearer token |
-| `403` | Authenticated but insufficient role (member accessing admin endpoint) |
-| `404` | Resource not found |
-| `503` | Database or secrets store not available |
-| `500` | Internal server error |
-
----
-
-## Security Model
-
-### Secrets Encryption
-
-- **Algorithm:** AES-256-GCM with per-secret HKDF-SHA256 derived keys
-- **Master key:** 32+ bytes, resolved from `SECRETS_MASTER_KEY` env var or OS keychain
-- **Storage format:** `nonce (12B) || ciphertext || tag (16B)` in `encrypted_value` column
-- **Per-secret salt:** 32 random bytes stored alongside the ciphertext
-- **Zero-exposure:** Plaintext never appears in logs, debug output, API responses, or LLM conversations
-
-### Auth Cache
-
-- Bounded LRU cache (1024 entries max)
-- 60-second TTL per entry
-- Suspending a user or revoking a token takes up to 60s to propagate
-
----
-
-## Database Schema
-
-### users
-
-| Column | Type (PG / libSQL) | Notes |
-|--------|--------------------|-------|
-| `id` | `TEXT` / `TEXT` | Primary key; typically UUID v4 strings (bootstrap admin may use a custom ID) |
-| `email` | `TEXT UNIQUE` | Nullable |
-| `display_name` | `TEXT NOT NULL` | |
-| `status` | `TEXT NOT NULL` | `"active"` or `"suspended"` |
-| `role` | `TEXT NOT NULL` | `"admin"` or `"member"` |
-| `created_at` | `TIMESTAMPTZ` / `TEXT` | |
-| `updated_at` | `TIMESTAMPTZ` / `TEXT` | |
-| `last_login_at` | `TIMESTAMPTZ` / `TEXT` | Nullable |
-| `created_by` | `TEXT` | Nullable, references `users.id` |
-| `metadata` | `JSONB` / `TEXT` | Default `{}` |
-
-### api_tokens
-
-| Column | Type (PG / libSQL) | Notes |
-|--------|--------------------|-------|
-| `id` | `UUID` / `TEXT` | Primary key |
-| `user_id` | `TEXT NOT NULL` | FK to `users.id` (PG cascades; libSQL explicit cleanup) |
-| `token_hash` | `BYTEA` / `BLOB` | SHA-256 of hex-encoded plaintext |
-| `token_prefix` | `TEXT NOT NULL` | First 8 chars for identification |
-| `name` | `TEXT NOT NULL` | Human-readable label |
-| `expires_at` | `TIMESTAMPTZ` / `TEXT` | Nullable |
-| `last_used_at` | `TIMESTAMPTZ` / `TEXT` | Nullable |
-| `created_at` | `TIMESTAMPTZ` / `TEXT` | |
-| `revoked_at` | `TIMESTAMPTZ` / `TEXT` | Nullable; set on revocation |
-
-### secrets
-
-| Column | Type (PG / libSQL) | Notes |
-|--------|--------------------|-------|
-| `id` | `UUID` / `TEXT` | Primary key |
-| `user_id` | `TEXT NOT NULL` | Scoped to user |
-| `name` | `TEXT NOT NULL` | Unique per user (lowercase normalized) |
-| `encrypted_value` | `BYTEA` / `BLOB` | AES-256-GCM (nonce + ciphertext + tag) |
-| `key_salt` | `BYTEA` / `BLOB` | Per-secret HKDF salt |
-| `provider` | `TEXT` | Optional grouping tag |
-| `expires_at` | `TIMESTAMPTZ` / `TEXT` | Nullable |
-| `last_used_at` | `TIMESTAMPTZ` / `TEXT` | Audit: last injection time |
-| `usage_count` | `BIGINT` / `INTEGER` | Audit: total injections |
-| `created_at` | `TIMESTAMPTZ` / `TEXT` | |
-| `updated_at` | `TIMESTAMPTZ` / `TEXT` | |

migrations/V14__users.sql

@@ -1,31 +0,0 @@
--- User management tables for multi-tenant deployments.
---
--- Replaces the static GATEWAY_USER_TOKENS env var with DB-backed
--- user registration, API token management, and invitation flow.
-
-CREATE TABLE users (
-    id TEXT PRIMARY KEY,                        -- matches existing user_id pattern (string, not UUID)
-    email TEXT UNIQUE,                          -- nullable for token-only users
-    display_name TEXT NOT NULL,
-    status TEXT NOT NULL DEFAULT 'active',       -- active | suspended | deactivated
-    role TEXT NOT NULL DEFAULT 'member',          -- admin | member
-    created_at TIMESTAMPTZ NOT NULL DEFAULT NOW(),
-    updated_at TIMESTAMPTZ NOT NULL DEFAULT NOW(),
-    last_login_at TIMESTAMPTZ,
-    created_by TEXT REFERENCES users(id),       -- who invited this user (nullable for bootstrap)
-    metadata JSONB NOT NULL DEFAULT '{}'        -- extensible profile data
-);
-
-CREATE TABLE api_tokens (
-    id UUID PRIMARY KEY,
-    user_id TEXT NOT NULL REFERENCES users(id) ON DELETE CASCADE,
-    token_hash BYTEA NOT NULL,                  -- SHA-256 hash (never store plaintext)
-    token_prefix TEXT NOT NULL,                 -- first 8 hex chars for display
-    name TEXT NOT NULL,                         -- human label ("my-laptop", "ci-bot")
-    expires_at TIMESTAMPTZ,                     -- nullable = never expires
-    last_used_at TIMESTAMPTZ,
-    created_at TIMESTAMPTZ NOT NULL DEFAULT NOW(),
-    revoked_at TIMESTAMPTZ                      -- soft-revoke: set this instead of deleting
-);
-CREATE INDEX idx_api_tokens_user ON api_tokens(user_id);
-CREATE INDEX idx_api_tokens_hash ON api_tokens(token_hash);

src/agent/agent_loop.rs

@@ -345,25 +345,13 @@ impl Agent {
             .map(|db| crate::tenant::TenantScope::new(user_id, Arc::clone(db)));
 
         // Reuse the owner workspace if user matches, otherwise create per-user.
-        // Per-user workspaces are seeded on first creation so they get identity
-        // files and BOOTSTRAP.md (which triggers the onboarding greeting).
         let workspace = match &self.deps.workspace {
             Some(ws) if ws.user_id() == user_id => Some(Arc::clone(ws)),
-            _ => {
-                if let Some(db) = self.deps.store.as_ref() {
-                    let ws = Arc::new(Workspace::new_with_db(user_id, Arc::clone(db)));
-                    if let Err(e) = ws.seed_if_empty().await {
-                        tracing::warn!(
-                            user_id = user_id,
-                            "Failed to seed per-user workspace: {}",
-                            e
-                        );
-                    }
-                    Some(ws)
-                } else {
-                    None
-                }
-            }
+            _ => self
+                .deps
+                .store
+                .as_ref()
+                .map(|db| Arc::new(Workspace::new_with_db(user_id, Arc::clone(db)))),
         };
 
         crate::tenant::TenantCtx::new(
@@ -1275,34 +1263,6 @@ impl Agent {
         // Build per-tenant execution context once; threaded through all handlers.
         let tenant = self.tenant_ctx(&message.user_id).await;
 
-        // Per-user bootstrap: if this user's workspace was just seeded (fresh),
-        // persist the static greeting to their assistant conversation and
-        // broadcast it so the web client shows it immediately.
-        if tenant
-            .workspace()
-            .is_some_and(|ws| ws.take_bootstrap_pending())
-        {
-            tracing::info!(
-                user_id = message.user_id,
-                "Fresh user workspace — persisting bootstrap greeting"
-            );
-            if let Some(store) = tenant.store()
-                && let Ok(conv_id) = store
-                    .get_or_create_assistant_conversation(&message.channel)
-                    .await
-            {
-                let _ = store
-                    .add_conversation_message(conv_id, "assistant", BOOTSTRAP_GREETING)
-                    .await;
-                let mut out = OutgoingResponse::text(BOOTSTRAP_GREETING.to_string());
-                out.thread_id = Some(conv_id.to_string());
-                let _ = self
-                    .channels
-                    .broadcast(&message.channel, &message.user_id, out)
-                    .await;
-            }
-        }
-
         let session_for_empty_exit = Arc::clone(&session);
 
         // Process based on submission type

src/agent/commands.rs

@@ -947,6 +947,12 @@ impl Agent {
     /// Best-effort: logs warnings on failure but does not propagate errors,
     /// since the in-memory model switch already succeeded.
     ///
+    /// The DB setting is the primary persistence layer. For LLM settings the
+    /// resolution priority is `DB > env > TOML > default`, so writing to DB
+    /// is sufficient for the change to survive restarts. The `.env` and TOML
+    /// files are only updated as a courtesy when they already contain a model
+    /// var, to avoid user confusion.
+    ///
     /// In multi-tenant mode, only the per-user DB setting is written — global
     /// .env and TOML files are shared across users and must not be mutated.
     async fn persist_selected_model(&self, tenant: &crate::tenant::TenantCtx, model: &str) {
@@ -972,22 +978,18 @@ impl Agent {
             return;
         }
 
-        // 3. Update .env and TOML config file (sync I/O in spawn_blocking).
+        // 3. Best-effort update of .env and TOML if they already contain a
+        //    model var. DB is authoritative (DB > env > TOML), but keeping
+        //    these in sync avoids confusion when users inspect the files.
         let model_owned = model.to_string();
         let backend = self.deps.llm_backend.clone();
         if let Err(e) = tokio::task::spawn_blocking(move || {
-            // 2a. Update the backend-specific model env var in ~/.ironclaw/.env.
-            //
-            // Env vars have the HIGHEST priority in LlmConfig::resolve_model()
-            // (env var > TOML > DB > default). If the .env file has e.g.
-            // NEARAI_MODEL=old-model, it shadows everything else. We must
-            // update this var or the /model change is invisible on restart.
+            // 3a. Update the backend-specific model env var in ~/.ironclaw/.env
+            //     only if the var already exists (don't inject new vars).
             let registry = crate::llm::ProviderRegistry::load();
             let model_env = registry.model_env_var(&backend);
             let env_var_prefix = format!("{}=", model_env);
 
-            // Only update the .env file if the var is actually set there
-            // (avoid injecting new vars the user never configured).
             let env_path = crate::bootstrap::ironclaw_env_path();
             let env_has_var = std::fs::read_to_string(&env_path)
                 .ok()
@@ -1005,10 +1007,8 @@ impl Agent {
                 }
             }
 
-            // 2b. Update (or create) the TOML config file.
-            //
-            // The TOML overlay has higher priority than DB settings on
-            // startup, so it MUST stay in sync with the DB.
+            // 3b. Update TOML config file if it already exists.
+            //     Don't create a new one — DB persistence is sufficient.
             let toml_path = crate::settings::Settings::default_toml_path();
             match crate::settings::Settings::load_toml(&toml_path) {
                 Ok(Some(mut settings)) => {
@@ -1018,15 +1018,7 @@ impl Agent {
                     }
                 }
                 Ok(None) => {
-                    // No config file yet — create one so the model choice
-                    // survives restarts even when the DB is unavailable.
-                    let settings = crate::settings::Settings {
-                        selected_model: Some(model_owned),
-                        ..Default::default()
-                    };
-                    if let Err(e) = settings.save_toml(&toml_path) {
-                        tracing::warn!("Failed to create config.toml for model persistence: {}", e);
-                    }
+                    // No config file on disk; DB persistence is sufficient.
                 }
                 Err(e) => {
                     tracing::warn!("Failed to load config.toml for model persistence: {}", e);

src/agent/dispatcher.rs

@@ -400,21 +400,16 @@ impl<'a> LoopDelegate for ChatDelegate<'a> {
         };
 
         // Record cost and track token usage (global + per-user).
-        // Use the provider's effective_model_name so cost attribution matches
-        // the model that actually served the request. When the override is
-        // honoured (e.g. NearAI), this returns the override name; when the
-        // provider ignores overrides (e.g. Rig-based), it returns the active
-        // model, keeping attribution accurate in both cases.
-        let model_name = self
-            .agent
-            .llm()
-            .effective_model_name(reason_ctx.model_override.as_deref());
-        let cost_per_token = if reason_ctx.model_override.is_some() {
-            // Override may use different pricing; let CostGuard fall back to
-            // costs::model_cost() for the effective model.
-            None
+        // When a model override is active, use the override name for attribution
+        // and let CostGuard look up pricing via costs::model_cost() instead of
+        // using the default provider's cost_per_token (which reflects the wrong model).
+        let (model_name, cost_per_token) = if let Some(ref ovr) = reason_ctx.model_override {
+            (ovr.clone(), None)
         } else {
-            Some(self.agent.llm().cost_per_token())
+            (
+                self.agent.llm().active_model_name(),
+                Some(self.agent.llm().cost_per_token()),
+            )
         };
         let read_discount = self.agent.llm().cache_read_discount();
         let write_multiplier = self.agent.llm().cache_write_multiplier();
@@ -438,24 +433,6 @@ impl<'a> LoopDelegate for ChatDelegate<'a> {
             call_cost,
         );
 
-        // Persist LLM call to DB so usage stats survive restarts.
-        // Chat turns don't create agent_jobs, so job_id is None.
-        if let Some(store) = self.tenant.store() {
-            let record = crate::history::LlmCallRecord {
-                job_id: None,
-                conversation_id: Some(self.thread_id),
-                provider: &self.agent.deps.llm_backend,
-                model: &model_name,
-                input_tokens: output.usage.input_tokens,
-                output_tokens: output.usage.output_tokens,
-                cost: call_cost,
-                purpose: Some("chat"),
-            };
-            if let Err(e) = store.record_llm_call(&record).await {
-                tracing::warn!("Failed to persist LLM call to DB: {}", e);
-            }
-        }
-
         Ok(output)
     }
 
@@ -1383,7 +1360,6 @@ mod tests {
                 max_tool_iterations: 50,
                 auto_approve_tools: false,
                 default_timezone: "UTC".to_string(),
-                max_jobs_per_user: None,
                 max_tokens_per_job: 0,
                 multi_tenant: false,
                 max_llm_concurrent_per_user: None,
@@ -2265,7 +2241,6 @@ mod tests {
                 max_tool_iterations,
                 auto_approve_tools: true,
                 default_timezone: "UTC".to_string(),
-                max_jobs_per_user: None,
                 max_tokens_per_job: 0,
                 multi_tenant: false,
                 max_llm_concurrent_per_user: None,
@@ -2393,7 +2368,6 @@ mod tests {
                     max_tool_iterations: max_iter,
                     auto_approve_tools: true,
                     default_timezone: "UTC".to_string(),
-                    max_jobs_per_user: None,
                     max_tokens_per_job: 0,
                     multi_tenant: false,
                     max_llm_concurrent_per_user: None,

src/agent/heartbeat.rs

@@ -400,7 +400,7 @@ impl HeartbeatRunner {
     }
 
     /// Send a notification about heartbeat findings.
-    async fn send_notification(&self, message: &str) {
+    pub(crate) async fn send_notification(&self, message: &str) {
         let Some(ref tx) = self.response_tx else {
             tracing::debug!("No response channel configured for heartbeat notifications");
             return;
@@ -512,8 +512,8 @@ pub fn spawn_heartbeat(
     })
 }
 
-/// Spawn a multi-user heartbeat runner that cycles through all users who
-/// have routines (enabled or not). Each tick, it queries the DB for distinct
+/// Spawn a multi-user heartbeat runner that cycles through all users that
+/// own routines (enabled or not). Each tick, it queries the DB for distinct
 /// user_ids, creates a per-user workspace, and runs a heartbeat check for
 /// each user concurrently. Per-user failure counts are tracked independently.
 pub fn spawn_multi_user_heartbeat(
@@ -574,10 +574,8 @@ pub fn spawn_multi_user_heartbeat(
                 }
             };
 
-            // Run user heartbeats (and hygiene) concurrently so one slow LLM
-            // call doesn't block others. Cap concurrency to avoid flooding the
-            // LLM provider. Hygiene runs inside the same JoinSet so it is
-            // tracked and bounded by the same concurrency cap.
+            // Run user heartbeats concurrently so one slow LLM call doesn't
+            // block others. Cap concurrency to avoid flooding the LLM provider.
             const MAX_CONCURRENT_HEARTBEATS: usize = 8;
             let mut join_set = tokio::task::JoinSet::new();
 
@@ -590,6 +588,23 @@ pub fn spawn_multi_user_heartbeat(
 
                 let workspace = Arc::new(Workspace::new_with_db(user_id, Arc::clone(store.db())));
 
+                // Run memory hygiene per user (same as single-user heartbeat).
+                let hygiene_ws = Arc::clone(&workspace);
+                let hygiene_cfg = hygiene_config.clone();
+                let hygiene_user = user_id.clone();
+                tokio::spawn(async move {
+                    let report =
+                        crate::workspace::hygiene::run_if_due(&hygiene_ws, &hygiene_cfg).await;
+                    if report.had_work() {
+                        tracing::info!(
+                            user_id = hygiene_user,
+                            daily_logs_deleted = report.daily_logs_deleted,
+                            conversation_docs_deleted = report.conversation_docs_deleted,
+                            "multi-user heartbeat: memory hygiene deleted stale documents"
+                        );
+                    }
+                });
+
                 // Drain completed tasks to stay within the concurrency cap.
                 while join_set.len() >= MAX_CONCURRENT_HEARTBEATS {
                     if let Some(join_result) = join_set.join_next().await {
@@ -598,30 +613,13 @@ pub fn spawn_multi_user_heartbeat(
                 }
 
                 let uid = user_id.clone();
-                // In multi-tenant mode, clear notify_user_id so that
-                // HeartbeatRunner::send_notification falls back to
-                // workspace.user_id() — each user's heartbeat should persist
-                // and notify that user, not the shared config target.
-                let mut cfg = config.clone();
-                cfg.notify_user_id = None;
+                let cfg = config.clone();
                 let hyg = hygiene_config.clone();
                 let llm_clone = llm.clone();
                 let tx = response_tx.clone();
                 let admin = store.clone();
 
                 join_set.spawn(async move {
-                    // Run memory hygiene per user (same as single-user heartbeat)
-                    // inside the tracked task so concurrency is bounded.
-                    let report = crate::workspace::hygiene::run_if_due(&workspace, &hyg).await;
-                    if report.had_work() {
-                        tracing::info!(
-                            user_id = uid,
-                            daily_logs_deleted = report.daily_logs_deleted,
-                            conversation_docs_deleted = report.conversation_docs_deleted,
-                            "multi-user heartbeat: memory hygiene deleted stale documents"
-                        );
-                    }
-
                     let mut runner = HeartbeatRunner::new(cfg, hyg, workspace, llm_clone);
                     if let Some(tx) = tx {
                         runner = runner.with_response_channel(tx);

src/agent/routine_engine.rs

@@ -1089,134 +1089,48 @@ async fn execute_routine(ctx: EngineContext, routine: Routine, run: RoutineRun)
     // Increment running count (atomic: survives panics in the execution below)
     ctx.running_count.fetch_add(1, Ordering::Relaxed);
 
-    // Retry constants for transient lightweight execution failures.
-    const MAX_RETRIES: u32 = 3;
-    const BASE_DELAY_MS: u64 = 1000;
-
-    let is_lightweight = matches!(routine.action, RoutineAction::Lightweight { .. });
-
-    // The retry block returns both the execution result and any accumulated
-    // token count so that usage is preserved even on final failure.
-    let (result, accumulated_tokens) = {
-        let mut attempt = 0u32;
-        // Track accumulated tokens as Option to preserve None semantics:
-        // None = no attempt reported tokens; Some(n) = at least one attempt did.
-        let mut accumulated_tokens: Option<i32> = None;
-        let uses_tools = matches!(
-            routine.action,
-            RoutineAction::Lightweight {
-                use_tools: true,
-                ..
-            }
-        ) && ctx.config.lightweight_tools_enabled;
-
-        /// Extract partial_tokens from any RoutineError variant that carries them.
-        fn extract_partial_tokens(e: &RoutineError) -> Option<i32> {
-            match e {
-                RoutineError::LlmFailed {
-                    partial_tokens: Some(t),
-                    ..
-                }
-                | RoutineError::EmptyResponse {
-                    partial_tokens: Some(t),
-                }
-                | RoutineError::TruncatedResponse {
-                    partial_tokens: Some(t),
-                } => Some(*t),
-                _ => None,
-            }
+    let result = match &routine.action {
+        RoutineAction::Lightweight {
+            prompt,
+            context_paths,
+            max_tokens,
+            use_tools,
+            max_tool_rounds,
+        } => {
+            execute_lightweight(
+                &ctx,
+                &routine,
+                prompt,
+                context_paths,
+                *max_tokens,
+                *use_tools,
+                *max_tool_rounds,
+            )
+            .await
         }
-
-        /// Merge an optional partial token count into the accumulator,
-        /// only materializing Some when at least one source had Some.
-        fn accumulate(acc: Option<i32>, partial: Option<i32>) -> Option<i32> {
-            match (acc, partial) {
-                (Some(a), Some(p)) => Some(a.saturating_add(p)),
-                (Some(a), None) => Some(a),
-                (None, p) => p,
-            }
-        }
-
-        loop {
-            let execution_result = match &routine.action {
-                RoutineAction::Lightweight {
-                    prompt,
-                    context_paths,
-                    max_tokens,
-                    use_tools,
-                    max_tool_rounds,
-                } => {
-                    execute_lightweight(
-                        &ctx,
-                        &routine,
-                        prompt,
-                        context_paths,
-                        *max_tokens,
-                        *use_tools,
-                        *max_tool_rounds,
-                    )
-                    .await
-                }
-                RoutineAction::FullJob {
-                    title,
-                    description,
-                    max_iterations,
-                } => {
-                    let execution = FullJobExecutionConfig {
-                        title,
-                        description,
-                        max_iterations: *max_iterations,
-                    };
-                    execute_full_job(&ctx, &routine, &run, &execution).await
-                }
+        RoutineAction::FullJob {
+            title,
+            description,
+            max_iterations,
+        } => {
+            let execution = FullJobExecutionConfig {
+                title,
+                description,
+                max_iterations: *max_iterations,
             };
-
-            match execution_result {
-                Ok((status, summary, tokens)) => {
-                    // Merge tokens: only produce Some when at least one source had Some.
-                    let total = accumulate(accumulated_tokens, tokens);
-                    break (Ok((status, summary, total)), accumulated_tokens);
-                }
-                Err(ref e)
-                    if is_lightweight
-                        && !uses_tools
-                        && e.is_retryable()
-                        // Skip outer retry for LlmFailed — RetryProvider already
-                        // retries transient LLM errors with its own budget. Retrying
-                        // here would create a multiplicative retry count.
-                        && !matches!(e, RoutineError::LlmFailed { .. })
-                        && attempt < MAX_RETRIES =>
-                {
-                    // Accumulate partial tokens from the failed attempt.
-                    accumulated_tokens = accumulate(accumulated_tokens, extract_partial_tokens(e));
-
-                    attempt += 1;
-
-                    let delay = Duration::from_millis(
-                        BASE_DELAY_MS.saturating_mul(2u64.saturating_pow(attempt - 1)),
-                    );
-                    tracing::event!(target: "transient_routine_errors", tracing::Level::WARN, routine = %routine.name, attempt = attempt, max_retries = MAX_RETRIES, delay_ms = delay.as_millis() as u64, "Transient routine error, retrying: {}", e);
-                    tokio::time::sleep(delay).await;
-                }
-                Err(e) => {
-                    // Accumulate tokens from the final failed attempt.
-                    accumulated_tokens = accumulate(accumulated_tokens, extract_partial_tokens(&e));
-                    break (Err(e), accumulated_tokens);
-                }
-            }
+            execute_full_job(&ctx, &routine, &run, &execution).await
         }
     };
 
     // Decrement running count
     ctx.running_count.fetch_sub(1, Ordering::Relaxed);
 
-    // Process result — on failure, preserve accumulated token total from
-    // earlier retry attempts so usage reporting stays accurate.
+    // Process result
     let (status, summary, tokens) = match result {
         Ok(execution) => execution,
         Err(e) => {
             tracing::error!(routine = %routine.name, "Execution failed: {}", e);
-            (RunStatus::Failed, Some(e.to_string()), accumulated_tokens)
+            (RunStatus::Failed, Some(e.to_string()), None)
         }
     };
 
@@ -1597,14 +1511,13 @@ async fn execute_lightweight_no_tools(
         .with_max_tokens(effective_max_tokens)
         .with_temperature(0.3);
 
-    let response = ctx.llm.complete(request).await.map_err(|e| {
-        let retryable = crate::llm::retry::is_retryable(&e);
-        RoutineError::LlmFailed {
+    let response = ctx
+        .llm
+        .complete(request)
+        .await
+        .map_err(|e| RoutineError::LlmFailed {
             reason: e.to_string(),
-            partial_tokens: None,
-            retryable,
-        }
-    })?;
+        })?;
 
     handle_text_response(
         &response.content,
@@ -1625,18 +1538,12 @@ fn handle_text_response(
 ) -> Result<(RunStatus, Option<String>, Option<i32>), RoutineError> {
     let content = content.trim();
 
-    // Empty content guard — carry consumed tokens so the retry loop can
-    // accumulate them even when the response shape is invalid.
+    // Empty content guard
     if content.is_empty() {
-        let consumed = Some((total_input_tokens + total_output_tokens) as i32);
         return if finish_reason == FinishReason::Length {
-            Err(RoutineError::TruncatedResponse {
-                partial_tokens: consumed,
-            })
+            Err(RoutineError::TruncatedResponse)
         } else {
-            Err(RoutineError::EmptyResponse {
-                partial_tokens: consumed,
-            })
+            Err(RoutineError::EmptyResponse)
         };
     }
 
@@ -1714,15 +1621,13 @@ async fn execute_lightweight_with_tools(
                 .with_max_tokens(effective_max_tokens)
                 .with_temperature(0.3);
 
-            let response = ctx.llm.complete(request).await.map_err(|e| {
-                let partial = (total_input_tokens + total_output_tokens) as i32;
-                let retryable = crate::llm::retry::is_retryable(&e);
-                RoutineError::LlmFailed {
-                    reason: e.to_string(),
-                    partial_tokens: if partial > 0 { Some(partial) } else { None },
-                    retryable,
-                }
-            })?;
+            let response =
+                ctx.llm
+                    .complete(request)
+                    .await
+                    .map_err(|e| RoutineError::LlmFailed {
+                        reason: e.to_string(),
+                    })?;
 
             total_input_tokens += response.input_tokens;
             total_output_tokens += response.output_tokens;
@@ -1749,12 +1654,8 @@ async fn execute_lightweight_with_tools(
                 .with_temperature(0.3);
 
             let response = ctx.llm.complete_with_tools(request).await.map_err(|e| {
-                let partial = (total_input_tokens + total_output_tokens) as i32;
-                let retryable = crate::llm::retry::is_retryable(&e);
                 RoutineError::LlmFailed {
                     reason: e.to_string(),
-                    partial_tokens: if partial > 0 { Some(partial) } else { None },
-                    retryable,
                 }
             })?;
 
@@ -1927,7 +1828,6 @@ async fn execute_routine_tool(
 }
 
 /// Send a notification based on the routine's notify config and run status.
-#[allow(clippy::too_many_arguments)]
 async fn send_notification(
     tx: &mpsc::Sender<OutgoingResponse>,
     notify: &NotifyConfig,
@@ -2613,104 +2513,6 @@ mod tests {
         }
     }
 
-    /// Regression test for #1320: transient errors are retried for lightweight
-    /// routines but not for full-job routines or hard failures.
-    #[test]
-    fn test_retry_classification_for_routine_errors() {
-        use crate::error::RoutineError;
-
-        // Transient errors (retryable for lightweight routines)
-        let transient_errors: Vec<RoutineError> = vec![
-            RoutineError::LlmFailed {
-                reason: "rate limit".into(),
-                partial_tokens: None,
-                retryable: true,
-            },
-            RoutineError::LlmFailed {
-                reason: "network timeout".into(),
-                partial_tokens: Some(42),
-                retryable: true,
-            },
-            RoutineError::EmptyResponse {
-                partial_tokens: None,
-            },
-            RoutineError::TruncatedResponse {
-                partial_tokens: Some(100),
-            },
-        ];
-        for err in &transient_errors {
-            assert!(err.is_retryable(), "{} should be retryable", err);
-        }
-
-        // Permanent LLM failures that should NOT be retried
-        // (retryable: false is set at conversion time by llm::retry::is_retryable)
-        let permanent_llm_errors: Vec<RoutineError> = vec![
-            RoutineError::LlmFailed {
-                reason: "Authentication failed for provider openai".into(),
-                partial_tokens: None,
-                retryable: false,
-            },
-            RoutineError::LlmFailed {
-                reason: "invalid_api_key: bad key".into(),
-                partial_tokens: None,
-                retryable: false,
-            },
-            RoutineError::LlmFailed {
-                reason: "content policy violation".into(),
-                partial_tokens: None,
-                retryable: false,
-            },
-            RoutineError::LlmFailed {
-                reason: "content_filter triggered".into(),
-                partial_tokens: None,
-                retryable: false,
-            },
-            RoutineError::LlmFailed {
-                reason: "context length exceeded: 150000 tokens used, 128000 allowed".into(),
-                partial_tokens: Some(100),
-                retryable: false,
-            },
-            RoutineError::LlmFailed {
-                reason: "model not available on provider anthropic".into(),
-                partial_tokens: None,
-                retryable: false,
-            },
-            RoutineError::LlmFailed {
-                reason: "content moderation flagged".into(),
-                partial_tokens: None,
-                retryable: false,
-            },
-        ];
-        for err in &permanent_llm_errors {
-            assert!(!err.is_retryable(), "{} should NOT be retryable", err);
-        }
-
-        // Hard failures (never retried)
-        let hard_errors: Vec<RoutineError> = vec![
-            RoutineError::Disabled {
-                name: "test".into(),
-            },
-            RoutineError::NotFound {
-                id: uuid::Uuid::new_v4(),
-            },
-            RoutineError::NotAuthorized {
-                id: uuid::Uuid::new_v4(),
-            },
-            RoutineError::MaxConcurrent {
-                name: "test".into(),
-            },
-            RoutineError::JobDispatchFailed {
-                reason: "no docker".into(),
-            },
-            RoutineError::Database {
-                reason: "connection refused".into(),
-            },
-        ];
-        for err in &hard_errors {
-            assert!(!err.is_retryable(), "{} should NOT be retryable", err);
-        }
-    }
-
     #[test]
     fn test_sanitize_summary_strips_control_chars() {
         use super::sanitize_summary;

src/agent/scheduler.rs

@@ -267,20 +267,6 @@ impl Scheduler {
                 });
             }
 
-            // Per-user concurrency check — only count jobs consuming a parallel
-            // execution slot (Pending/InProgress/Stuck), not Completed/Submitted.
-            if let Some(max_per_user) = self.config.max_jobs_per_user
-                && let Ok(ctx) = self.context_manager.get_context(job_id).await
-            {
-                let user_blocking = self
-                    .context_manager
-                    .parallel_blocking_count_for(&ctx.user_id)
-                    .await;
-                if user_blocking >= max_per_user {
-                    return Err(JobError::MaxJobsExceeded { max: max_per_user });
-                }
-            }
-
             // Transition job to in_progress
             self.context_manager
                 .update_context(job_id, |ctx| {
@@ -798,7 +784,6 @@ mod tests {
             max_tool_iterations: 10,
             auto_approve_tools: true,
             default_timezone: "UTC".to_string(),
-            max_jobs_per_user: None,
             max_tokens_per_job,
             multi_tenant: false,
             max_llm_concurrent_per_user: None,

src/app.rs

@@ -229,18 +229,35 @@ impl AppBuilder {
         let store = crate::secrets::create_secrets_store(crypto, handles);
 
         if let Some(ref secrets) = store {
+            // Migrate any plaintext API keys from the settings table to the
+            // encrypted secrets store. Idempotent — safe to run on every startup.
+            if let Some(ref db) = self.db {
+                crate::config::migrate_plaintext_llm_keys(
+                    db.as_ref(),
+                    secrets.as_ref(),
+                    &self.config.owner_id,
+                )
+                .await;
+            }
+
             // Inject LLM API keys from encrypted storage
             crate::config::inject_llm_keys_from_secrets(secrets.as_ref(), &self.config.owner_id)
                 .await;
 
-            // Re-resolve only the LLM config with newly available keys.
-            let store: Option<&(dyn crate::db::SettingsStore + Sync)> =
+            // Re-resolve only the LLM config with newly available keys,
+            // including keys hydrated from the secrets store.
+            let settings_store: Option<&(dyn crate::db::SettingsStore + Sync)> =
                 self.db.as_ref().map(|db| db.as_ref() as _);
             let toml_path = self.toml_path.as_deref();
             let owner_id = self.config.owner_id.clone();
             if let Err(e) = self
                 .config
-                .re_resolve_llm(store, &owner_id, toml_path)
+                .re_resolve_llm_with_secrets(
+                    settings_store,
+                    &owner_id,
+                    toml_path,
+                    Some(secrets.as_ref()),
+                )
                 .await
             {
                 tracing::warn!("Failed to re-resolve LLM config after secret injection: {e}");
@@ -336,12 +353,17 @@ impl AppBuilder {
             ws = ws.with_memory_layers(self.config.workspace.memory_layers.clone());
             let ws = Arc::new(ws);
 
-            // Detect multi-tenant mode: when the database has registered users,
+            // Detect multi-tenant mode: when GATEWAY_USER_TOKENS is configured,
             // each authenticated user needs their own workspace scope. Use
             // WorkspacePool (which implements WorkspaceResolver) to create
             // per-user workspaces on demand instead of sharing the startup
             // workspace across all users.
-            let is_multi_tenant = db.has_any_users().await.unwrap_or(false);
+            let is_multi_tenant = self
+                .config
+                .channels
+                .gateway
+                .as_ref()
+                .is_some_and(|gw| gw.user_tokens.is_some());
 
             if is_multi_tenant {
                 let pool = Arc::new(crate::channels::web::server::WorkspacePool::new(

src/channels/web/CLAUDE.md

@@ -91,34 +91,6 @@ Browser-facing HTTP API and SSE/WebSocket real-time streaming. Axum-based, singl
 | DELETE | `/api/routines/{id}` | Delete a routine |
 | GET | `/api/routines/{id}/runs` | List runs for a specific routine |
 
-### User Management (admin — requires `admin` role, see `docs/USER_MANAGEMENT_API.md`)
-| Method | Path | Description |
-|--------|------|-------------|
-| POST | `/api/admin/users` | Create a new user (returns one-time token) |
-| GET | `/api/admin/users` | List all users |
-| GET | `/api/admin/users/{id}` | Get a single user |
-| PATCH | `/api/admin/users/{id}` | Update user profile/metadata |
-| DELETE | `/api/admin/users/{id}` | Delete user and all data |
-| POST | `/api/admin/users/{id}/suspend` | Suspend a user |
-| POST | `/api/admin/users/{id}/activate` | Re-activate a user |
-| GET | `/api/admin/usage` | Per-user LLM usage stats |
-| GET | `/api/admin/users/{user_id}/secrets` | List a user's secrets (names only) |
-| PUT | `/api/admin/users/{user_id}/secrets/{name}` | Create or update a user's secret |
-| DELETE | `/api/admin/users/{user_id}/secrets/{name}` | Delete a user's secret |
-
-### Profile (self-service)
-| Method | Path | Description |
-|--------|------|-------------|
-| GET | `/api/profile` | Get own profile |
-| PATCH | `/api/profile` | Update own display name/metadata |
-
-### Tokens (self-service)
-| Method | Path | Description |
-|--------|------|-------------|
-| POST | `/api/tokens` | Create API token (returns plaintext once) |
-| GET | `/api/tokens` | List own tokens |
-| DELETE | `/api/tokens/{id}` | Revoke a token |
-
 ### Settings
 | Method | Path | Description |
 |--------|------|-------------|

src/channels/web/auth.rs

@@ -5,7 +5,6 @@
 //! handlers can extract it via `AuthenticatedUser`.
 
 use std::collections::HashMap;
-use std::num::NonZeroUsize;
 
 use axum::{
     extract::{FromRequestParts, Request, State},
@@ -14,25 +13,18 @@ use axum::{
     response::{IntoResponse, Response},
 };
 use sha2::{Digest, Sha256};
-use std::sync::Arc;
-use std::time::Instant;
 use subtle::ConstantTimeEq;
-use tokio::sync::RwLock;
-
-use crate::db::Database;
 
 /// Identity resolved from a bearer token.
 #[derive(Debug, Clone)]
 pub struct UserIdentity {
     pub user_id: String,
-    /// `admin` or `member`.
-    pub role: String,
     /// Additional user scopes this identity can read from.
     pub workspace_read_scopes: Vec<String>,
 }
 
 /// Hash a token with SHA-256 for constant-size, timing-safe storage.
-pub fn hash_token(token: &str) -> [u8; 32] {
+fn hash_token(token: &str) -> [u8; 32] {
     let mut hasher = Sha256::new();
     hasher.update(token.as_bytes());
     hasher.finalize().into()
@@ -64,7 +56,6 @@ impl MultiAuthState {
                 hash,
                 UserIdentity {
                     user_id,
-                    role: "admin".to_string(),
                     workspace_read_scopes: Vec::new(),
                 },
             )],
@@ -73,11 +64,6 @@ impl MultiAuthState {
     }
 
     /// Create a multi-user auth state from a map of tokens to identities.
-    ///
-    /// **Test-only** — production multi-user auth is DB-backed via
-    /// `DbAuthenticator`. This constructor is kept public (not `#[cfg(test)]`)
-    /// because integration tests in `tests/` compile the crate as a library
-    /// where `cfg(test)` is not set.
     pub fn multi(tokens: HashMap<String, UserIdentity>) -> Self {
         let hashed_tokens: Vec<([u8; 32], UserIdentity)> = tokens
             .into_iter()
@@ -122,131 +108,6 @@ impl MultiAuthState {
     }
 }
 
-/// DB-backed token authenticator with a bounded LRU cache.
-///
-/// Checks an LRU cache first (TTL 60s), then falls back to a DB query.
-/// The cache is bounded to `MAX_CACHE_ENTRIES` — when full, the least
-/// recently used entry is evicted regardless of TTL.
-///
-/// Revoking a token or suspending a user has at most 60s of stale
-/// authentication before the cache entry expires.
-#[derive(Clone)]
-#[allow(clippy::type_complexity)]
-pub struct DbAuthenticator {
-    store: Arc<dyn Database>,
-    /// Bounded LRU cache: token_hash → (identity, inserted_at).
-    cache: Arc<RwLock<lru::LruCache<[u8; 32], (UserIdentity, Instant)>>>,
-}
-
-impl DbAuthenticator {
-    /// Cache TTL — how long a successful auth is cached before re-querying the DB.
-    const CACHE_TTL_SECS: u64 = 60;
-    /// Maximum cache entries to prevent unbounded growth.
-    // SAFETY: 1024 is non-zero, so the unwrap in `new()` is infallible.
-    const MAX_CACHE_ENTRIES: NonZeroUsize = match NonZeroUsize::new(1024) {
-        Some(v) => v,
-        None => unreachable!(),
-    };
-
-    pub fn new(store: Arc<dyn Database>) -> Self {
-        Self {
-            store,
-            cache: Arc::new(RwLock::new(lru::LruCache::new(Self::MAX_CACHE_ENTRIES))),
-        }
-    }
-
-    /// Evict all cached entries for a specific user.
-    ///
-    /// Call this after security-critical actions (suspend, activate, role
-    /// change, token revocation) so the change takes effect immediately
-    /// instead of waiting for the 60-second TTL to expire.
-    pub async fn invalidate_user(&self, user_id: &str) {
-        let mut cache = self.cache.write().await;
-        // LruCache doesn't support predicate-based removal, so collect keys
-        // first then remove. The cache is bounded (1024) so this is cheap.
-        let keys_to_remove: Vec<[u8; 32]> = cache
-            .iter()
-            .filter(|(_, (identity, _))| identity.user_id == user_id)
-            .map(|(k, _)| *k)
-            .collect();
-        for key in keys_to_remove {
-            cache.pop(&key);
-        }
-    }
-
-    /// Authenticate a token against the database, using cache when possible.
-    ///
-    /// Returns `Ok(Some(identity))` on success, `Ok(None)` if the token is
-    /// not found, or `Err(())` if the database is unreachable (so the caller
-    /// can return 503 instead of 401).
-    pub async fn authenticate(&self, candidate: &str) -> Result<Option<UserIdentity>, ()> {
-        let hash = hash_token(candidate);
-
-        // Check cache first (promotes to most-recent on hit)
-        {
-            let mut cache = self.cache.write().await;
-            if let Some((identity, inserted_at)) = cache.get(&hash) {
-                if inserted_at.elapsed().as_secs() < Self::CACHE_TTL_SECS {
-                    return Ok(Some(identity.clone()));
-                }
-                // Expired — remove stale entry
-                cache.pop(&hash);
-            }
-        }
-
-        // Cache miss or expired — query DB
-        let (token_record, user_record) = match self.store.authenticate_token(&hash).await {
-            Ok(Some(pair)) => pair,
-            Ok(None) => return Ok(None),
-            Err(e) => {
-                tracing::warn!("DB auth lookup failed: {e}");
-                return Err(());
-            }
-        };
-
-        let identity = UserIdentity {
-            user_id: user_record.id.clone(),
-            role: user_record.role.clone(),
-            workspace_read_scopes: Vec::new(),
-        };
-
-        // Record token usage (best-effort, don't block auth)
-        let store = self.store.clone();
-        let token_id = token_record.id;
-        let user_id = user_record.id;
-        tokio::spawn(async move {
-            let _ = store.record_token_usage(token_id).await;
-            let _ = store.record_login(&user_id).await;
-        });
-
-        // Insert into bounded LRU — if full, least-recently-used entry is evicted
-        {
-            let mut cache = self.cache.write().await;
-            cache.put(hash, (identity.clone(), Instant::now()));
-        }
-
-        Ok(Some(identity))
-    }
-}
-
-/// Combined auth state: tries env-var tokens first, then DB-backed tokens.
-#[derive(Clone)]
-pub struct CombinedAuthState {
-    /// In-memory tokens from GATEWAY_AUTH_TOKEN.
-    pub env_auth: MultiAuthState,
-    /// DB-backed token authenticator (optional — only when a database is available).
-    pub db_auth: Option<DbAuthenticator>,
-}
-
-impl From<MultiAuthState> for CombinedAuthState {
-    fn from(env_auth: MultiAuthState) -> Self {
-        Self {
-            env_auth,
-            db_auth: None,
-        }
-    }
-}
-
 /// Axum extractor that provides the authenticated user identity.
 ///
 /// Only available on routes behind `auth_middleware`. Extracts the
@@ -269,31 +130,6 @@ where
     }
 }
 
-/// Axum extractor that requires the authenticated user to have the `admin` role.
-///
-/// Use instead of `AuthenticatedUser` on endpoints that modify system-wide
-/// state (user management, model selection, extension/skill installation).
-pub struct AdminUser(pub UserIdentity);
-
-impl<S> FromRequestParts<S> for AdminUser
-where
-    S: Send + Sync,
-{
-    type Rejection = (StatusCode, &'static str);
-
-    async fn from_request_parts(parts: &mut Parts, _state: &S) -> Result<Self, Self::Rejection> {
-        let identity = parts
-            .extensions
-            .get::<UserIdentity>()
-            .cloned()
-            .ok_or((StatusCode::UNAUTHORIZED, "Not authenticated"))?;
-        if identity.role != "admin" {
-            return Err((StatusCode::FORBIDDEN, "Admin role required"));
-        }
-        Ok(AdminUser(identity))
-    }
-}
-
 /// Whether query-string token auth is allowed for this request.
 ///
 /// Only GET requests to streaming endpoints may use `?token=xxx`. This
@@ -330,65 +166,39 @@ fn query_token(request: &Request) -> Option<String> {
 
 /// Auth middleware that validates bearer token from header or query param.
 ///
-/// Tries env-var tokens first (constant-time, in-memory), then falls back
-/// to DB-backed token lookup if configured. SSE connections can't set
-/// headers from `EventSource`, so we also accept `?token=xxx` as a query
-/// parameter, but only on SSE/WS endpoints.
+/// SSE connections can't set headers from `EventSource`, so we also accept
+/// `?token=xxx` as a query parameter, but only on SSE/WS endpoints.
 ///
 /// On successful authentication, inserts the matching `UserIdentity` into
 /// request extensions for downstream extraction via `AuthenticatedUser`.
 pub async fn auth_middleware(
-    State(auth): State<CombinedAuthState>,
+    State(auth): State<MultiAuthState>,
     headers: HeaderMap,
     mut request: Request,
     next: Next,
 ) -> Response {
-    // Extract the candidate token from header or query param.
-    let token = extract_token(&headers, &request);
-
-    if let Some(ref tok) = token {
-        // 1. Try env-var tokens first (fast, constant-time, in-memory).
-        if let Some(identity) = auth.env_auth.authenticate(tok) {
-            request.extensions_mut().insert(identity.clone());
-            return next.run(request).await;
-        }
-
-        // 2. Fall back to DB-backed token lookup.
-        if let Some(ref db_auth) = auth.db_auth {
-            match db_auth.authenticate(tok).await {
-                Ok(Some(identity)) => {
-                    request.extensions_mut().insert(identity);
-                    return next.run(request).await;
-                }
-                Err(()) => {
-                    return (StatusCode::SERVICE_UNAVAILABLE, "Database unavailable")
-                        .into_response();
-                }
-                Ok(None) => {}
-            }
-        }
-    }
-
-    (StatusCode::UNAUTHORIZED, "Invalid or missing auth token").into_response()
-}
-
-/// Extract a bearer token from the Authorization header or query parameter.
-fn extract_token(headers: &HeaderMap, request: &Request) -> Option<String> {
-    // Try Authorization header first (RFC 6750).
+    // Try Authorization header first.
+    // RFC 6750 Section 2.1: auth-scheme comparison is case-insensitive.
     if let Some(auth_header) = headers.get("authorization")
         && let Ok(value) = auth_header.to_str()
         && value.len() > 7
         && value[..7].eq_ignore_ascii_case("Bearer ")
+        && let Some(identity) = auth.authenticate(&value[7..])
     {
-        return Some(value[7..].to_string());
+        request.extensions_mut().insert(identity.clone());
+        return next.run(request).await;
     }
 
-    // Fall back to query parameter for SSE/WS endpoints.
-    if allows_query_token_auth(request) {
-        return query_token(request);
+    // Fall back to query parameter, but only for SSE/WS endpoints.
+    if allows_query_token_auth(&request)
+        && let Some(token) = query_token(&request)
+        && let Some(identity) = auth.authenticate(&token)
+    {
+        request.extensions_mut().insert(identity.clone());
+        return next.run(request).await;
     }
 
-    None
+    (StatusCode::UNAUTHORIZED, "Invalid or missing auth token").into_response()
 }
 
 #[cfg(test)]
@@ -417,7 +227,6 @@ mod tests {
             "tok-alice".to_string(),
             UserIdentity {
                 user_id: "alice".to_string(),
-                role: "admin".to_string(),
                 workspace_read_scopes: Vec::new(),
             },
         );
@@ -425,7 +234,6 @@ mod tests {
             "tok-bob".to_string(),
             UserIdentity {
                 user_id: "bob".to_string(),
-                role: "admin".to_string(),
                 workspace_read_scopes: Vec::new(),
             },
         );
@@ -466,10 +274,7 @@ mod tests {
     /// Router with streaming endpoints (query auth allowed) and regular
     /// endpoints (query auth rejected).
     fn test_app(token: &str) -> Router {
-        let state = CombinedAuthState::from(MultiAuthState::single(
-            token.to_string(),
-            "test-user".to_string(),
-        ));
+        let state = MultiAuthState::single(token.to_string(), "test-user".to_string());
         Router::new()
             .route("/api/chat/events", get(dummy_handler))
             .route("/api/logs/events", get(dummy_handler))
@@ -681,7 +486,7 @@ mod tests {
 
     /// Build a multi-user router where each token maps to a distinct identity.
     fn multi_user_app(tokens: HashMap<String, UserIdentity>) -> Router {
-        let state = CombinedAuthState::from(MultiAuthState::multi(tokens));
+        let state = MultiAuthState::multi(tokens);
         Router::new()
             .route("/api/chat/events", get(identity_handler))
             .route("/api/chat/send", post(identity_handler))
@@ -695,7 +500,6 @@ mod tests {
             "tok-alice".to_string(),
             UserIdentity {
                 user_id: "alice".to_string(),
-                role: "admin".to_string(),
                 workspace_read_scopes: vec!["shared".to_string()],
             },
         );
@@ -703,7 +507,6 @@ mod tests {
             "tok-bob".to_string(),
             UserIdentity {
                 user_id: "bob".to_string(),
-                role: "admin".to_string(),
                 workspace_read_scopes: vec!["shared".to_string(), "alice".to_string()],
             },
         );
@@ -840,10 +643,7 @@ mod tests {
     #[tokio::test]
     async fn test_multi_user_empty_scopes_for_single_user() {
         // Single-user mode creates identity with empty workspace_read_scopes.
-        let state = CombinedAuthState::from(MultiAuthState::single(
-            "tok-only".to_string(),
-            "solo".to_string(),
-        ));
+        let state = MultiAuthState::single("tok-only".to_string(), "solo".to_string());
         let app = Router::new()
             .route("/api/scopes", get(scopes_handler))
             .layer(middleware::from_fn_with_state(state, auth_middleware));

src/channels/web/handlers/jobs.rs

@@ -15,14 +15,6 @@ use crate::channels::web::auth::AuthenticatedUser;
 use crate::channels::web::server::GatewayState;
 use crate::channels::web::types::*;
 
-fn db_error(context: &str, e: impl std::fmt::Display) -> (StatusCode, String) {
-    tracing::error!(%e, context, "Database error in jobs handler");
-    (
-        StatusCode::INTERNAL_SERVER_ERROR,
-        "Internal database error".to_string(),
-    )
-}
-
 pub async fn jobs_list_handler(
     State(state): State<Arc<GatewayState>>,
     AuthenticatedUser(user): AuthenticatedUser,
@@ -221,7 +213,10 @@ pub async fn jobs_detail_handler(
         }
         Ok(None) => {}
         Err(e) => {
-            return Err(db_error("jobs_handler", e));
+            return Err((
+                StatusCode::INTERNAL_SERVER_ERROR,
+                format!("Database error: {}", e),
+            ));
         }
     }
 
@@ -262,7 +257,10 @@ pub async fn jobs_detail_handler(
             }))
         }
         Ok(None) => Err((StatusCode::NOT_FOUND, "Job not found".to_string())),
-        Err(e) => Err(db_error("jobs_handler", e)),
+        Err(e) => Err((
+            StatusCode::INTERNAL_SERVER_ERROR,
+            format!("Database error: {}", e),
+        )),
     }
 }
 
@@ -306,7 +304,10 @@ pub async fn jobs_cancel_handler(
             }
             Ok(None) => {}
             Err(e) => {
-                return Err(db_error("jobs_handler", e));
+                return Err((
+                    StatusCode::INTERNAL_SERVER_ERROR,
+                    format!("Database error: {}", e),
+                ));
             }
         }
     }
@@ -349,7 +350,10 @@ pub async fn jobs_cancel_handler(
             }
             Ok(None) => {}
             Err(e) => {
-                return Err(db_error("jobs_handler", e));
+                return Err((
+                    StatusCode::INTERNAL_SERVER_ERROR,
+                    format!("Database error: {}", e),
+                ));
             }
         }
     }
@@ -467,7 +471,10 @@ pub async fn jobs_restart_handler(
         }
         Ok(None) => {}
         Err(e) => {
-            return Err(db_error("jobs_handler", e));
+            return Err((
+                StatusCode::INTERNAL_SERVER_ERROR,
+                format!("Database error: {}", e),
+            ));
         }
     }
 
@@ -523,7 +530,10 @@ pub async fn jobs_restart_handler(
             })))
         }
         Ok(None) => Err((StatusCode::NOT_FOUND, "Job not found".to_string())),
-        Err(e) => Err(db_error("jobs_handler", e)),
+        Err(e) => Err((
+            StatusCode::INTERNAL_SERVER_ERROR,
+            format!("Database error: {}", e),
+        )),
     }
 }
 
@@ -599,7 +609,10 @@ pub async fn jobs_prompt_handler(
                 return Err((StatusCode::NOT_FOUND, "Job not found".to_string()));
             }
             Err(e) => {
-                return Err(db_error("jobs_handler", e));
+                return Err((
+                    StatusCode::INTERNAL_SERVER_ERROR,
+                    format!("Database error: {}", e),
+                ));
             }
         }
     }
@@ -654,7 +667,10 @@ pub async fn jobs_events_handler(
             return Err((StatusCode::NOT_FOUND, "Job not found".to_string()));
         }
         Err(e) => {
-            return Err(db_error("jobs_handler", e));
+            return Err((
+                StatusCode::INTERNAL_SERVER_ERROR,
+                format!("Database error: {}", e),
+            ));
         }
     }
 
@@ -807,17 +823,3 @@ pub async fn job_files_read_handler(
         content,
     }))
 }
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-
-    #[test]
-    fn test_db_error_does_not_leak_details() {
-        let (status, body) = db_error("test_context", "relation \"jobs\" does not exist");
-        assert_eq!(status, StatusCode::INTERNAL_SERVER_ERROR);
-        assert_eq!(body, "Internal database error");
-        assert!(!body.contains("relation"));
-        assert!(!body.contains("does not exist"));
-    }
-}

src/channels/web/handlers/mod.rs

@@ -5,10 +5,7 @@
 pub mod jobs;
 pub mod memory;
 pub mod routines;
-pub mod secrets;
 pub mod skills;
-pub mod tokens;
-pub mod users;
 
 // Modules not yet wired into server.rs router -- suppress dead_code until
 // they replace their inline counterparts.

src/channels/web/handlers/secrets.rs

@@ -1,183 +0,0 @@
-//! Admin secrets provisioning handlers.
-//!
-//! Allows an admin (typically an application backend) to create, list, and
-//! delete secrets on behalf of individual users so their IronClaw agent can
-//! call back to external services with per-user credentials.
-
-use std::sync::Arc;
-
-use axum::{
-    Json,
-    extract::{Path, State},
-    http::StatusCode,
-};
-
-use crate::channels::web::auth::AdminUser;
-use crate::channels::web::server::GatewayState;
-use crate::secrets::CreateSecretParams;
-
-/// PUT /api/admin/users/{user_id}/secrets/{name} — create or update a secret.
-///
-/// Upserts: if a secret with the same (user_id, name) already exists it is
-/// overwritten. The plaintext value is encrypted at rest (AES-256-GCM) and
-/// never returned by any endpoint.
-pub async fn secrets_put_handler(
-    State(state): State<Arc<GatewayState>>,
-    AdminUser(_admin): AdminUser,
-    Path((user_id, name)): Path<(String, String)>,
-    Json(body): Json<serde_json::Value>,
-) -> Result<Json<serde_json::Value>, (StatusCode, String)> {
-    let name = name.to_lowercase();
-
-    let store = state.store.as_ref().ok_or((
-        StatusCode::SERVICE_UNAVAILABLE,
-        "Database not available".to_string(),
-    ))?;
-    store
-        .get_user(&user_id)
-        .await
-        .map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))?
-        .ok_or((StatusCode::NOT_FOUND, "User not found".to_string()))?;
-
-    let secrets = state.secrets_store.as_ref().ok_or((
-        StatusCode::SERVICE_UNAVAILABLE,
-        "Secrets store not available".to_string(),
-    ))?;
-
-    let value = body
-        .get("value")
-        .and_then(|v| v.as_str())
-        .ok_or((
-            StatusCode::BAD_REQUEST,
-            "Missing required field 'value'".to_string(),
-        ))?
-        .to_string();
-
-    let provider = body
-        .get("provider")
-        .and_then(|v| v.as_str())
-        .map(String::from);
-
-    let expires_in_days = body.get("expires_in_days").and_then(|v| v.as_u64());
-    if let Some(days) = expires_in_days
-        && days > 36500
-    {
-        return Err((
-            StatusCode::BAD_REQUEST,
-            "expires_in_days must be at most 36500".to_string(),
-        ));
-    }
-    let expires_at =
-        expires_in_days.map(|days| chrono::Utc::now() + chrono::Duration::days(days as i64));
-
-    let mut params = CreateSecretParams::new(name.clone(), value);
-    if let Some(p) = provider {
-        params = params.with_provider(p);
-    }
-    if let Some(exp) = expires_at {
-        params = params.with_expiry(exp);
-    }
-
-    let already_exists = secrets
-        .exists(&user_id, &name)
-        .await
-        .map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))?;
-
-    secrets
-        .create(&user_id, params)
-        .await
-        .map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))?;
-
-    Ok(Json(serde_json::json!({
-        "user_id": user_id,
-        "name": name,
-        "status": if already_exists { "updated" } else { "created" },
-    })))
-}
-
-/// GET /api/admin/users/{user_id}/secrets — list a user's secrets (names only).
-///
-/// Never returns secret values or hashes.
-pub async fn secrets_list_handler(
-    State(state): State<Arc<GatewayState>>,
-    AdminUser(_admin): AdminUser,
-    Path(user_id): Path<String>,
-) -> Result<Json<serde_json::Value>, (StatusCode, String)> {
-    // Verify the target user exists (consistent with PUT/DELETE).
-    let store = state.store.as_ref().ok_or((
-        StatusCode::SERVICE_UNAVAILABLE,
-        "Database not available".to_string(),
-    ))?;
-    if store
-        .get_user(&user_id)
-        .await
-        .map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))?
-        .is_none()
-    {
-        return Err((StatusCode::NOT_FOUND, "User not found".to_string()));
-    }
-
-    let secrets = state.secrets_store.as_ref().ok_or((
-        StatusCode::SERVICE_UNAVAILABLE,
-        "Secrets store not available".to_string(),
-    ))?;
-
-    let refs = secrets
-        .list(&user_id)
-        .await
-        .map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))?;
-
-    let secrets_json: Vec<serde_json::Value> = refs
-        .into_iter()
-        .map(|r| {
-            serde_json::json!({
-                "name": r.name,
-                "provider": r.provider,
-            })
-        })
-        .collect();
-
-    Ok(Json(serde_json::json!({
-        "user_id": user_id,
-        "secrets": secrets_json,
-    })))
-}
-
-/// DELETE /api/admin/users/{user_id}/secrets/{name} — delete a user's secret.
-pub async fn secrets_delete_handler(
-    State(state): State<Arc<GatewayState>>,
-    AdminUser(_admin): AdminUser,
-    Path((user_id, name)): Path<(String, String)>,
-) -> Result<Json<serde_json::Value>, (StatusCode, String)> {
-    let name = name.to_lowercase();
-
-    let store = state.store.as_ref().ok_or((
-        StatusCode::SERVICE_UNAVAILABLE,
-        "Database not available".to_string(),
-    ))?;
-    store
-        .get_user(&user_id)
-        .await
-        .map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))?
-        .ok_or((StatusCode::NOT_FOUND, "User not found".to_string()))?;
-
-    let secrets = state.secrets_store.as_ref().ok_or((
-        StatusCode::SERVICE_UNAVAILABLE,
-        "Secrets store not available".to_string(),
-    ))?;
-
-    let deleted = secrets
-        .delete(&user_id, &name)
-        .await
-        .map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))?;
-
-    if !deleted {
-        return Err((StatusCode::NOT_FOUND, "Secret not found".to_string()));
-    }
-
-    Ok(Json(serde_json::json!({
-        "user_id": user_id,
-        "name": name,
-        "deleted": true,
-    })))
-}

src/channels/web/handlers/settings.rs

@@ -7,10 +7,15 @@ use axum::{
     extract::{Path, State},
     http::StatusCode,
 };
+use secrecy::SecretString;
 
 use crate::channels::web::auth::AuthenticatedUser;
 use crate::channels::web::server::GatewayState;
 use crate::channels::web::types::*;
+use crate::secrets::{CreateSecretParams, SecretsStore};
+
+/// Sentinel value the frontend sends to mean "key is unchanged, don't touch it".
+const API_KEY_UNCHANGED: &str = "••••••••";
 
 pub async fn settings_list_handler(
     State(state): State<Arc<GatewayState>>,
@@ -25,12 +30,34 @@ pub async fn settings_list_handler(
         StatusCode::INTERNAL_SERVER_ERROR
     })?;
 
+    // Build a map of sensitive keys so we can annotate and mask them.
+    let sensitive_keys = ["llm_builtin_overrides", "llm_custom_providers"];
+    let mut sensitive_map: std::collections::HashMap<String, serde_json::Value> = rows
+        .iter()
+        .filter(|r| sensitive_keys.contains(&r.key.as_str()))
+        .map(|r| (r.key.clone(), r.value.clone()))
+        .collect();
+    if !sensitive_map.is_empty() {
+        annotate_secret_key_presence(&state, &user.user_id, &mut sensitive_map).await;
+        mask_settings_api_keys(&mut sensitive_map);
+    }
+
     let settings = rows
         .into_iter()
-        .map(|r| SettingResponse {
-            key: r.key,
-            value: r.value,
-            updated_at: r.updated_at.to_rfc3339(),
+        .map(|r| {
+            let value = if sensitive_keys.contains(&r.key.as_str()) {
+                sensitive_map
+                    .get(&r.key)
+                    .cloned()
+                    .unwrap_or(r.value.clone())
+            } else {
+                r.value
+            };
+            SettingResponse {
+                key: r.key,
+                value,
+                updated_at: r.updated_at.to_rfc3339(),
+            }
         })
         .collect();
 
@@ -55,9 +82,22 @@ pub async fn settings_get_handler(
         })?
         .ok_or(StatusCode::NOT_FOUND)?;
 
+    // Mask any plaintext API keys that may exist from legacy data.
+    let value = if matches!(
+        key.as_str(),
+        "llm_builtin_overrides" | "llm_custom_providers"
+    ) {
+        let mut map = std::collections::HashMap::from([(key.clone(), row.value.clone())]);
+        annotate_secret_key_presence(&state, &user.user_id, &mut map).await;
+        mask_settings_api_keys(&mut map);
+        map.remove(&key).unwrap_or(row.value)
+    } else {
+        row.value
+    };
+
     Ok(Json(SettingResponse {
         key: row.key,
-        value: row.value,
+        value,
         updated_at: row.updated_at.to_rfc3339(),
     }))
 }
@@ -72,8 +112,27 @@ pub async fn settings_set_handler(
         .store
         .as_ref()
         .ok_or(StatusCode::SERVICE_UNAVAILABLE)?;
+
+    // Guard: cannot remove a custom provider that is currently active.
+    if key == "llm_custom_providers" {
+        guard_active_provider_not_removed(store, &user.user_id, &body.value).await?;
+        validate_custom_providers(&body.value)?;
+    }
+
+    // Extract API keys from LLM settings and vault them in the secrets store.
+    // The sanitized value has api_key fields removed (stored encrypted instead).
+    let sanitized_value = match key.as_str() {
+        "llm_builtin_overrides" => {
+            extract_builtin_override_keys(&state, &user.user_id, &body.value).await?
+        }
+        "llm_custom_providers" => {
+            extract_custom_provider_keys(&state, &user.user_id, &body.value).await?
+        }
+        _ => body.value.clone(),
+    };
+
     store
-        .set_setting(&user.user_id, &key, &body.value)
+        .set_setting(&user.user_id, &key, &sanitized_value)
         .await
         .map_err(|e| {
             tracing::error!("Failed to set setting '{}': {}", key, e);
@@ -83,6 +142,110 @@ pub async fn settings_set_handler(
     Ok(StatusCode::NO_CONTENT)
 }
 
+const VALID_ADAPTERS: &[&str] = &["open_ai_completions", "anthropic", "ollama"];
+
+/// Valid provider ID: lowercase alphanumeric and hyphens, 1-64 chars.
+fn is_valid_provider_id(id: &str) -> bool {
+    !id.is_empty()
+        && id.len() <= 64
+        && id
+            .bytes()
+            .all(|b| b.is_ascii_lowercase() || b.is_ascii_digit() || b == b'-')
+}
+
+/// Returns `Err(422)` if any provider has an invalid ID or unrecognised adapter.
+fn validate_custom_providers(value: &serde_json::Value) -> Result<(), StatusCode> {
+    let providers = match value.as_array() {
+        Some(arr) => arr,
+        None => return Ok(()),
+    };
+    for p in providers {
+        let id = p.get("id").and_then(|v| v.as_str()).unwrap_or("");
+        if !is_valid_provider_id(id) {
+            tracing::warn!(
+                id = %id,
+                "Rejected custom provider with invalid ID (must be lowercase alphanumeric/hyphens, 1-64 chars)"
+            );
+            return Err(StatusCode::UNPROCESSABLE_ENTITY);
+        }
+    }
+    validate_custom_providers_adapters(value)
+}
+
+/// Returns `Err(422)` if any provider in the incoming list has an unrecognised adapter.
+fn validate_custom_providers_adapters(value: &serde_json::Value) -> Result<(), StatusCode> {
+    let providers = match value.as_array() {
+        Some(arr) => arr,
+        None => return Ok(()),
+    };
+    for p in providers {
+        let adapter = p.get("adapter").and_then(|v| v.as_str()).unwrap_or("");
+        if adapter.is_empty() {
+            tracing::warn!("Rejected custom provider with missing adapter field");
+            return Err(StatusCode::UNPROCESSABLE_ENTITY);
+        }
+        if !VALID_ADAPTERS.contains(&adapter) {
+            tracing::warn!(adapter = %adapter, "Rejected unknown LLM adapter");
+            return Err(StatusCode::UNPROCESSABLE_ENTITY);
+        }
+    }
+    Ok(())
+}
+
+/// Returns `Err(409)` if the active `llm_backend` is a custom provider that
+/// would be removed by the incoming update to `llm_custom_providers`.
+async fn guard_active_provider_not_removed(
+    store: &Arc<dyn crate::db::Database>,
+    user_id: &str,
+    new_value: &serde_json::Value,
+) -> Result<(), StatusCode> {
+    // Get the currently active backend.
+    let active_backend = match store.get_setting(user_id, "llm_backend").await {
+        Ok(Some(v)) => match v.as_str() {
+            Some(s) if !s.is_empty() => s.to_string(),
+            _ => return Ok(()),
+        },
+        _ => return Ok(()),
+    };
+
+    // Parse the incoming provider list.
+    let new_providers: Vec<serde_json::Value> = match new_value.as_array() {
+        Some(arr) => arr.clone(),
+        None => return Ok(()),
+    };
+
+    // Check whether the active backend exists in the OLD custom providers list.
+    let old_providers_value = match store.get_setting(user_id, "llm_custom_providers").await {
+        Ok(Some(v)) => v,
+        _ => return Ok(()),
+    };
+    let old_providers: Vec<serde_json::Value> = match old_providers_value.as_array() {
+        Some(arr) => arr.clone(),
+        None => return Ok(()),
+    };
+
+    let active_was_custom = old_providers
+        .iter()
+        .any(|p| p.get("id").and_then(|v| v.as_str()) == Some(&active_backend));
+    if !active_was_custom {
+        return Ok(());
+    }
+
+    // Reject if the active provider is absent from the new list.
+    let still_present = new_providers
+        .iter()
+        .any(|p| p.get("id").and_then(|v| v.as_str()) == Some(&active_backend));
+    if !still_present {
+        tracing::warn!(
+            active_backend = %active_backend,
+            "Rejected attempt to delete the active custom LLM provider"
+        );
+        return Err(StatusCode::CONFLICT);
+    }
+
+    Ok(())
+}
+
 pub async fn settings_delete_handler(
     State(state): State<Arc<GatewayState>>,
     AuthenticatedUser(user): AuthenticatedUser,
@@ -92,6 +255,14 @@ pub async fn settings_delete_handler(
         .store
         .as_ref()
         .ok_or(StatusCode::SERVICE_UNAVAILABLE)?;
+
+    // Guard: deleting llm_custom_providers is equivalent to setting it to [].
+    // Reject if the active backend is a custom provider that would be removed.
+    if key == "llm_custom_providers" {
+        guard_active_provider_not_removed(store, &user.user_id, &serde_json::Value::Array(vec![]))
+            .await?;
+    }
+
     store
         .delete_setting(&user.user_id, &key)
         .await
@@ -111,11 +282,16 @@ pub async fn settings_export_handler(
         .store
         .as_ref()
         .ok_or(StatusCode::SERVICE_UNAVAILABLE)?;
-    let settings = store.get_all_settings(&user.user_id).await.map_err(|e| {
+    let mut settings = store.get_all_settings(&user.user_id).await.map_err(|e| {
         tracing::error!("Failed to export settings: {}", e);
         StatusCode::INTERNAL_SERVER_ERROR
     })?;
 
+    // Indicate key presence from secrets store without exposing values.
+    annotate_secret_key_presence(&state, &user.user_id, &mut settings).await;
+
+    mask_settings_api_keys(&mut settings);
+
     Ok(Json(SettingsExportResponse { settings }))
 }
 
@@ -128,8 +304,21 @@ pub async fn settings_import_handler(
         .store
         .as_ref()
         .ok_or(StatusCode::SERVICE_UNAVAILABLE)?;
+
+    // Vault any API keys present in the imported settings, same as the
+    // individual SET handler does, so plaintext keys never reach the DB.
+    let mut sanitized = body.settings.clone();
+    if let Some(v) = sanitized.get("llm_builtin_overrides").cloned() {
+        let clean = extract_builtin_override_keys(&state, &user.user_id, &v).await?;
+        sanitized.insert("llm_builtin_overrides".to_string(), clean);
+    }
+    if let Some(v) = sanitized.get("llm_custom_providers").cloned() {
+        let clean = extract_custom_provider_keys(&state, &user.user_id, &v).await?;
+        sanitized.insert("llm_custom_providers".to_string(), clean);
+    }
+
     store
-        .set_all_settings(&user.user_id, &body.settings)
+        .set_all_settings(&user.user_id, &sanitized)
         .await
         .map_err(|e| {
             tracing::error!("Failed to import settings: {}", e);
@@ -138,3 +327,639 @@ pub async fn settings_import_handler(
 
     Ok(StatusCode::NO_CONTENT)
 }
+
+// ---------------------------------------------------------------------------
+// LLM API key vaulting helpers
+// ---------------------------------------------------------------------------
+
+/// Canonical secret name for a built-in provider's API key.
+fn builtin_secret_name(provider_id: &str) -> String {
+    format!("llm_builtin_{}_api_key", provider_id)
+}
+
+/// Canonical secret name for a custom provider's API key.
+fn custom_secret_name(provider_id: &str) -> String {
+    format!("llm_custom_{}_api_key", provider_id)
+}
+
+/// Returns true if the `api_key` value is a real key (not sentinel/empty).
+fn is_real_api_key(key: &str) -> bool {
+    !key.is_empty() && key != API_KEY_UNCHANGED
+}
+
+/// Require the secrets store when real API keys are present.
+/// Returns `Ok(None)` when no secrets store and no real keys (passthrough).
+fn require_secrets_store(
+    state: &GatewayState,
+    has_real_keys: bool,
+) -> Result<Option<&Arc<dyn SecretsStore + Send + Sync>>, StatusCode> {
+    match state.secrets_store.as_ref() {
+        Some(s) => Ok(Some(s)),
+        None if has_real_keys => {
+            tracing::error!("Cannot store API keys: secrets store is not available");
+            Err(StatusCode::SERVICE_UNAVAILABLE)
+        }
+        None => Ok(None),
+    }
+}
+
+/// Extract API keys from builtin overrides, store in secrets, return sanitized JSON.
+async fn extract_builtin_override_keys(
+    state: &GatewayState,
+    user_id: &str,
+    value: &serde_json::Value,
+) -> Result<serde_json::Value, StatusCode> {
+    let obj = match value.as_object() {
+        Some(o) => o,
+        None => return Ok(value.clone()),
+    };
+
+    let has_real_keys = obj.values().any(|v| {
+        v.get("api_key")
+            .and_then(|k| k.as_str())
+            .is_some_and(is_real_api_key)
+    });
+    let secrets = match require_secrets_store(state, has_real_keys)? {
+        Some(s) => s,
+        None => return Ok(value.clone()),
+    };
+
+    let mut sanitized = obj.clone();
+
+    for (provider_id, override_val) in obj {
+        if let Some(api_key) = override_val.get("api_key").and_then(|v| v.as_str()) {
+            if !is_real_api_key(api_key) {
+                // Unchanged or empty — remove from settings, keep existing secret.
+                if let Some(o) = sanitized
+                    .get_mut(provider_id)
+                    .and_then(|v| v.as_object_mut())
+                {
+                    o.remove("api_key");
+                }
+                continue;
+            }
+            vault_secret(
+                secrets.as_ref(),
+                user_id,
+                &builtin_secret_name(provider_id),
+                api_key,
+                provider_id,
+            )
+            .await?;
+            if let Some(o) = sanitized
+                .get_mut(provider_id)
+                .and_then(|v| v.as_object_mut())
+            {
+                o.remove("api_key");
+            }
+        }
+    }
+
+    Ok(serde_json::Value::Object(sanitized))
+}
+
+/// Extract API keys from custom providers, store in secrets, return sanitized JSON.
+async fn extract_custom_provider_keys(
+    state: &GatewayState,
+    user_id: &str,
+    value: &serde_json::Value,
+) -> Result<serde_json::Value, StatusCode> {
+    let arr = match value.as_array() {
+        Some(a) => a,
+        None => return Ok(value.clone()),
+    };
+
+    let has_real_keys = arr.iter().any(|v| {
+        v.get("api_key")
+            .and_then(|k| k.as_str())
+            .is_some_and(is_real_api_key)
+    });
+    let secrets = match require_secrets_store(state, has_real_keys)? {
+        Some(s) => s,
+        None => return Ok(value.clone()),
+    };
+
+    let mut sanitized = arr.clone();
+
+    for (idx, provider_val) in arr.iter().enumerate() {
+        let provider_id = provider_val
+            .get("id")
+            .and_then(|v| v.as_str())
+            .unwrap_or("");
+        if provider_id.is_empty() {
+            continue;
+        }
+
+        if let Some(api_key) = provider_val.get("api_key").and_then(|v| v.as_str()) {
+            if !is_real_api_key(api_key) {
+                if let Some(o) = sanitized[idx].as_object_mut() {
+                    o.remove("api_key");
+                }
+                continue;
+            }
+            vault_secret(
+                secrets.as_ref(),
+                user_id,
+                &custom_secret_name(provider_id),
+                api_key,
+                provider_id,
+            )
+            .await?;
+            if let Some(o) = sanitized[idx].as_object_mut() {
+                o.remove("api_key");
+            }
+        }
+    }
+
+    Ok(serde_json::Value::Array(sanitized))
+}
+
+/// Encrypt and store an API key in the secrets store.
+async fn vault_secret(
+    secrets: &(dyn SecretsStore + Send + Sync),
+    user_id: &str,
+    secret_name: &str,
+    api_key: &str,
+    provider_id: &str,
+) -> Result<(), StatusCode> {
+    secrets
+        .create(
+            user_id,
+            CreateSecretParams {
+                name: secret_name.to_string(),
+                value: SecretString::from(api_key.to_string()),
+                provider: Some(provider_id.to_string()),
+                expires_at: None,
+            },
+        )
+        .await
+        .map_err(|e| {
+            tracing::error!(
+                "Failed to store secret '{}' for provider '{}': {}",
+                secret_name,
+                provider_id,
+                e
+            );
+            StatusCode::INTERNAL_SERVER_ERROR
+        })?;
+    Ok(())
+}
+
+/// Mask plaintext API keys in settings values before returning to the frontend.
+///
+/// Any `api_key` field still present in the settings JSON (legacy plaintext)
+/// is replaced with the sentinel so the frontend shows "key configured".
+fn mask_settings_api_keys(settings: &mut std::collections::HashMap<String, serde_json::Value>) {
+    if let Some(obj) = settings
+        .get_mut("llm_builtin_overrides")
+        .and_then(|v| v.as_object_mut())
+    {
+        for override_val in obj.values_mut() {
+            if let Some(o) = override_val.as_object_mut()
+                && o.contains_key("api_key")
+            {
+                o.insert(
+                    "api_key".to_string(),
+                    serde_json::Value::String(API_KEY_UNCHANGED.to_string()),
+                );
+            }
+        }
+    }
+
+    if let Some(arr) = settings
+        .get_mut("llm_custom_providers")
+        .and_then(|v| v.as_array_mut())
+    {
+        for provider_val in arr.iter_mut() {
+            if let Some(o) = provider_val.as_object_mut()
+                && o.contains_key("api_key")
+            {
+                o.insert(
+                    "api_key".to_string(),
+                    serde_json::Value::String(API_KEY_UNCHANGED.to_string()),
+                );
+            }
+        }
+    }
+}
+
+/// Check the secrets store for vaulted API keys and annotate the settings map.
+///
+/// For builtin overrides and custom providers whose API key was stripped from
+/// settings (stored in secrets), this adds `api_key: "••••••••"` so the
+/// frontend knows a key is configured without seeing the actual value.
+async fn annotate_secret_key_presence(
+    state: &GatewayState,
+    user_id: &str,
+    settings: &mut std::collections::HashMap<String, serde_json::Value>,
+) {
+    let secrets = match state.secrets_store.as_ref() {
+        Some(s) => s,
+        None => return,
+    };
+
+    // Annotate builtin overrides
+    if let Some(obj) = settings
+        .get_mut("llm_builtin_overrides")
+        .and_then(|v| v.as_object_mut())
+    {
+        let provider_ids: Vec<String> = obj.keys().cloned().collect();
+        for provider_id in provider_ids {
+            let has_key_in_settings = obj
+                .get(&provider_id)
+                .and_then(|v| v.get("api_key"))
+                .is_some();
+            if has_key_in_settings {
+                continue; // Will be masked by mask_settings_api_keys
+            }
+            let secret_name = builtin_secret_name(&provider_id);
+            if secrets.exists(user_id, &secret_name).await.unwrap_or(false)
+                && let Some(o) = obj.get_mut(&provider_id).and_then(|v| v.as_object_mut())
+            {
+                o.insert(
+                    "api_key".to_string(),
+                    serde_json::Value::String(API_KEY_UNCHANGED.to_string()),
+                );
+            }
+        }
+    }
+
+    // Annotate custom providers
+    if let Some(arr) = settings
+        .get_mut("llm_custom_providers")
+        .and_then(|v| v.as_array_mut())
+    {
+        for provider_val in arr.iter_mut() {
+            let provider_id = provider_val
+                .get("id")
+                .and_then(|v| v.as_str())
+                .unwrap_or("")
+                .to_string();
+            if provider_id.is_empty() {
+                continue;
+            }
+            let has_key_in_settings = provider_val.get("api_key").is_some();
+            if has_key_in_settings {
+                continue;
+            }
+            let secret_name = custom_secret_name(&provider_id);
+            if secrets.exists(user_id, &secret_name).await.unwrap_or(false)
+                && let Some(o) = provider_val.as_object_mut()
+            {
+                o.insert(
+                    "api_key".to_string(),
+                    serde_json::Value::String(API_KEY_UNCHANGED.to_string()),
+                );
+            }
+        }
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use std::collections::HashMap;
+
+    #[test]
+    fn test_mask_settings_api_keys_builtin_overrides() {
+        let mut settings = HashMap::new();
+        settings.insert(
+            "llm_builtin_overrides".to_string(),
+            serde_json::json!({
+                "openai": { "api_key": "sk-secret-123", "model": "gpt-4" },
+                "anthropic": { "model": "claude-3" }
+            }),
+        );
+
+        mask_settings_api_keys(&mut settings);
+
+        let overrides = settings["llm_builtin_overrides"].as_object().unwrap();
+        assert_eq!(
+            overrides["openai"]["api_key"].as_str().unwrap(),
+            API_KEY_UNCHANGED,
+        );
+        assert_eq!(overrides["openai"]["model"].as_str().unwrap(), "gpt-4");
+        assert!(overrides["anthropic"].get("api_key").is_none());
+    }
+
+    #[test]
+    fn test_mask_settings_api_keys_custom_providers() {
+        let mut settings = HashMap::new();
+        settings.insert(
+            "llm_custom_providers".to_string(),
+            serde_json::json!([
+                { "id": "my-llm", "api_key": "secret-key", "adapter": "open_ai_completions" },
+                { "id": "no-key", "adapter": "ollama" }
+            ]),
+        );
+
+        mask_settings_api_keys(&mut settings);
+
+        let providers = settings["llm_custom_providers"].as_array().unwrap();
+        assert_eq!(providers[0]["api_key"].as_str().unwrap(), API_KEY_UNCHANGED,);
+        assert!(providers[1].get("api_key").is_none());
+    }
+
+    #[test]
+    fn test_mask_settings_no_llm_keys_is_noop() {
+        let mut settings = HashMap::new();
+        settings.insert("some_other_setting".to_string(), serde_json::json!("value"));
+
+        mask_settings_api_keys(&mut settings);
+
+        assert_eq!(settings["some_other_setting"].as_str().unwrap(), "value");
+    }
+
+    #[test]
+    fn test_builtin_secret_name_format() {
+        assert_eq!(builtin_secret_name("openai"), "llm_builtin_openai_api_key");
+    }
+
+    #[test]
+    fn test_custom_secret_name_format() {
+        assert_eq!(custom_secret_name("my-groq"), "llm_custom_my-groq_api_key");
+    }
+
+    fn test_secrets_store() -> Arc<dyn SecretsStore + Send + Sync> {
+        let crypto = Arc::new(
+            crate::secrets::SecretsCrypto::new(secrecy::SecretString::from(
+                crate::secrets::keychain::generate_master_key_hex(),
+            ))
+            .unwrap(),
+        );
+        Arc::new(crate::secrets::InMemorySecretsStore::new(crypto))
+    }
+
+    fn test_gateway_state(secrets: Arc<dyn SecretsStore + Send + Sync>) -> GatewayState {
+        GatewayState {
+            msg_tx: tokio::sync::RwLock::new(None),
+            sse: Arc::new(crate::channels::web::sse::SseManager::new()),
+            workspace: None,
+            workspace_pool: None,
+            session_manager: None,
+            log_broadcaster: None,
+            log_level_handle: None,
+            extension_manager: None,
+            tool_registry: None,
+            store: None,
+            job_manager: None,
+            prompt_queue: None,
+            scheduler: None,
+            owner_id: "test".to_string(),
+            default_sender_id: "test".to_string(),
+            shutdown_tx: tokio::sync::RwLock::new(None),
+            ws_tracker: None,
+            llm_provider: None,
+            skill_registry: None,
+            skill_catalog: None,
+            chat_rate_limiter: crate::channels::web::server::PerUserRateLimiter::new(30, 60),
+            oauth_rate_limiter: crate::channels::web::server::RateLimiter::new(10, 60),
+            webhook_rate_limiter: crate::channels::web::server::RateLimiter::new(10, 60),
+            registry_entries: Vec::new(),
+            cost_guard: None,
+            routine_engine: Arc::new(tokio::sync::RwLock::new(None)),
+            startup_time: std::time::Instant::now(),
+            active_config: crate::channels::web::server::ActiveConfigSnapshot::default(),
+            secrets_store: Some(secrets),
+        }
+    }
+
+    #[tokio::test]
+    async fn test_extract_builtin_keys_vaults_and_strips() {
+        let secrets = test_secrets_store();
+        let state = test_gateway_state(Arc::clone(&secrets));
+
+        let input = serde_json::json!({
+            "openai": { "api_key": "sk-test-key", "model": "gpt-4" },
+            "anthropic": { "model": "claude-3" }
+        });
+
+        let result = extract_builtin_override_keys(&state, "test", &input)
+            .await
+            .unwrap();
+
+        let obj = result.as_object().unwrap();
+        assert!(
+            obj["openai"].get("api_key").is_none(),
+            "api_key should be stripped"
+        );
+        assert_eq!(obj["openai"]["model"].as_str().unwrap(), "gpt-4");
+        assert_eq!(obj["anthropic"]["model"].as_str().unwrap(), "claude-3");
+
+        let decrypted = secrets
+            .get_decrypted("test", "llm_builtin_openai_api_key")
+            .await
+            .unwrap();
+        assert_eq!(decrypted.expose(), "sk-test-key");
+    }
+
+    #[tokio::test]
+    async fn test_extract_custom_keys_vaults_and_strips() {
+        let secrets = test_secrets_store();
+        let state = test_gateway_state(Arc::clone(&secrets));
+
+        let input = serde_json::json!([
+            { "id": "my-llm", "api_key": "gsk-custom-key", "adapter": "open_ai_completions" },
+            { "id": "local", "adapter": "ollama" }
+        ]);
+
+        let result = extract_custom_provider_keys(&state, "test", &input)
+            .await
+            .unwrap();
+
+        let arr = result.as_array().unwrap();
+        assert!(
+            arr[0].get("api_key").is_none(),
+            "api_key should be stripped"
+        );
+        assert_eq!(arr[0]["id"].as_str().unwrap(), "my-llm");
+        assert!(arr[1].get("api_key").is_none());
+
+        let decrypted = secrets
+            .get_decrypted("test", "llm_custom_my-llm_api_key")
+            .await
+            .unwrap();
+        assert_eq!(decrypted.expose(), "gsk-custom-key");
+    }
+
+    #[tokio::test]
+    async fn test_unchanged_sentinel_preserves_existing_secret() {
+        let secrets = test_secrets_store();
+
+        secrets
+            .create(
+                "test",
+                CreateSecretParams {
+                    name: "llm_builtin_openai_api_key".to_string(),
+                    value: SecretString::from("sk-original".to_string()),
+                    provider: Some("openai".to_string()),
+                    expires_at: None,
+                },
+            )
+            .await
+            .unwrap();
+
+        let state = test_gateway_state(Arc::clone(&secrets));
+
+        let input = serde_json::json!({
+            "openai": { "api_key": "••••••••", "model": "gpt-4" }
+        });
+
+        let result = extract_builtin_override_keys(&state, "test", &input)
+            .await
+            .unwrap();
+
+        assert!(result["openai"].get("api_key").is_none());
+
+        let decrypted = secrets
+            .get_decrypted("test", "llm_builtin_openai_api_key")
+            .await
+            .unwrap();
+        assert_eq!(decrypted.expose(), "sk-original");
+    }
+
+    /// When secrets store is unavailable, attempting to save a real API key
+    /// must fail with 503 rather than silently storing plaintext.
+    #[tokio::test]
+    async fn test_extract_builtin_keys_rejects_without_secrets_store() {
+        let state = GatewayState {
+            secrets_store: None,
+            ..test_gateway_state(test_secrets_store())
+        };
+
+        let input = serde_json::json!({
+            "openai": { "api_key": "sk-real-key", "model": "gpt-4" }
+        });
+
+        let err = extract_builtin_override_keys(&state, "test", &input)
+            .await
+            .unwrap_err();
+        assert_eq!(err, StatusCode::SERVICE_UNAVAILABLE);
+    }
+
+    /// When secrets store is unavailable but no real keys are present
+    /// (only sentinels or no api_key at all), the call should succeed.
+    #[tokio::test]
+    async fn test_extract_builtin_keys_allows_no_keys_without_secrets_store() {
+        let state = GatewayState {
+            secrets_store: None,
+            ..test_gateway_state(test_secrets_store())
+        };
+
+        let input = serde_json::json!({
+            "openai": { "api_key": "••••••••", "model": "gpt-4" },
+            "anthropic": { "model": "claude-3" }
+        });
+
+        let result = extract_builtin_override_keys(&state, "test", &input)
+            .await
+            .unwrap();
+        // Without secrets store, the value passes through unchanged (no vaulting needed).
+        assert!(result.as_object().is_some());
+    }
+
+    #[tokio::test]
+    async fn test_extract_custom_keys_rejects_without_secrets_store() {
+        let state = GatewayState {
+            secrets_store: None,
+            ..test_gateway_state(test_secrets_store())
+        };
+
+        let input = serde_json::json!([
+            { "id": "my-llm", "api_key": "gsk-real-key", "adapter": "open_ai_completions" }
+        ]);
+
+        let err = extract_custom_provider_keys(&state, "test", &input)
+            .await
+            .unwrap_err();
+        assert_eq!(err, StatusCode::SERVICE_UNAVAILABLE);
+    }
+
+    // --- Provider ID validation tests ---
+
+    #[test]
+    fn test_valid_provider_ids() {
+        assert!(is_valid_provider_id("my-llm"));
+        assert!(is_valid_provider_id("openai"));
+        assert!(is_valid_provider_id("custom-provider-123"));
+        assert!(is_valid_provider_id("a"));
+    }
+
+    #[test]
+    fn test_invalid_provider_ids() {
+        assert!(!is_valid_provider_id(""), "empty ID");
+        assert!(!is_valid_provider_id("My-LLM"), "uppercase");
+        assert!(!is_valid_provider_id("my llm"), "spaces");
+        assert!(!is_valid_provider_id("my_llm"), "underscores");
+        assert!(!is_valid_provider_id("../../etc"), "path traversal");
+        assert!(!is_valid_provider_id("a.b"), "dots");
+        assert!(
+            !is_valid_provider_id(&"a".repeat(65)),
+            "exceeds 64 char limit"
+        );
+    }
+
+    #[test]
+    fn test_validate_custom_providers_rejects_bad_id() {
+        let input = serde_json::json!([
+            { "id": "UPPER-CASE", "adapter": "open_ai_completions" }
+        ]);
+        assert_eq!(
+            validate_custom_providers(&input).unwrap_err(),
+            StatusCode::UNPROCESSABLE_ENTITY,
+        );
+    }
+
+    #[test]
+    fn test_validate_custom_providers_accepts_valid() {
+        let input = serde_json::json!([
+            { "id": "my-llm", "adapter": "open_ai_completions" },
+            { "id": "local-ollama", "adapter": "ollama" }
+        ]);
+        assert!(validate_custom_providers(&input).is_ok());
+    }
+
+    // --- Adapter validation tests ---
+
+    #[test]
+    fn test_validate_adapters_rejects_unknown() {
+        let input = serde_json::json!([
+            { "id": "test", "adapter": "not_a_real_adapter" }
+        ]);
+        assert_eq!(
+            validate_custom_providers_adapters(&input).unwrap_err(),
+            StatusCode::UNPROCESSABLE_ENTITY,
+        );
+    }
+
+    #[test]
+    fn test_validate_adapters_rejects_missing() {
+        let input = serde_json::json!([
+            { "id": "test" }
+        ]);
+        assert_eq!(
+            validate_custom_providers_adapters(&input).unwrap_err(),
+            StatusCode::UNPROCESSABLE_ENTITY,
+        );
+    }
+
+    #[test]
+    fn test_validate_adapters_accepts_all_valid() {
+        for adapter in VALID_ADAPTERS {
+            let input = serde_json::json!([
+                { "id": "test", "adapter": adapter }
+            ]);
+            assert!(
+                validate_custom_providers_adapters(&input).is_ok(),
+                "adapter '{}' should be accepted",
+                adapter
+            );
+        }
+    }
+
+    #[test]
+    fn test_validate_adapters_non_array_is_ok() {
+        let input = serde_json::json!("not-an-array");
+        assert!(validate_custom_providers_adapters(&input).is_ok());
+    }
+}

src/channels/web/handlers/tokens.rs

@@ -1,163 +0,0 @@
-//! API token management handlers.
-
-use std::sync::Arc;
-
-use axum::{
-    Json,
-    extract::{Path, State},
-    http::StatusCode,
-};
-use rand::RngCore;
-use rand::rngs::OsRng;
-use uuid::Uuid;
-
-use crate::channels::web::auth::AuthenticatedUser;
-use crate::channels::web::server::GatewayState;
-
-/// POST /api/tokens — create a new API token (returns plaintext ONCE).
-pub async fn tokens_create_handler(
-    State(state): State<Arc<GatewayState>>,
-    AuthenticatedUser(user): AuthenticatedUser,
-    Json(body): Json<serde_json::Value>,
-) -> Result<Json<serde_json::Value>, (StatusCode, String)> {
-    let store = state.store.as_ref().ok_or((
-        StatusCode::SERVICE_UNAVAILABLE,
-        "Database not available".to_string(),
-    ))?;
-
-    let name = body
-        .get("name")
-        .and_then(|v| v.as_str())
-        .map(|s| s.trim())
-        .filter(|s| !s.is_empty())
-        .ok_or((
-            StatusCode::BAD_REQUEST,
-            "Missing or empty 'name'".to_string(),
-        ))?
-        .to_string();
-
-    let expires_in_days: Option<i64> = match body.get("expires_in_days").and_then(|v| v.as_u64()) {
-        Some(d) if d > 36500 => {
-            return Err((
-                StatusCode::BAD_REQUEST,
-                "expires_in_days must not exceed 36500 (100 years)".to_string(),
-            ));
-        }
-        Some(d) => Some(d as i64),
-        None => None,
-    };
-
-    let expires_at = expires_in_days.map(|days| chrono::Utc::now() + chrono::Duration::days(days));
-
-    // Generate 32 random bytes for the token.
-    // Hash the hex-encoded plaintext (what the user sends as Bearer token),
-    // NOT the raw bytes — must match hash_token() in auth.rs.
-    let mut token_bytes = [0u8; 32];
-    OsRng.fill_bytes(&mut token_bytes);
-    let plaintext_token = hex::encode(token_bytes);
-    let hash = crate::channels::web::auth::hash_token(&plaintext_token);
-
-    // First 8 chars of the hex token as a prefix for identification.
-    let token_prefix = &plaintext_token[..8];
-
-    // Admin users can create tokens for other users via optional "user_id" field.
-    let target_user = body
-        .get("user_id")
-        .and_then(|v| v.as_str())
-        .filter(|_| user.role == "admin")
-        .unwrap_or(&user.user_id);
-
-    // Verify the target user exists to prevent orphan tokens.
-    if target_user != user.user_id {
-        store
-            .get_user(target_user)
-            .await
-            .map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))?
-            .ok_or((
-                StatusCode::NOT_FOUND,
-                format!("Target user '{target_user}' not found"),
-            ))?;
-    }
-
-    let record = store
-        .create_api_token(target_user, &name, &hash, token_prefix, expires_at)
-        .await
-        .map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))?;
-
-    // Return the plaintext token — this is the ONLY time it is shown.
-    Ok(Json(serde_json::json!({
-        "token": plaintext_token,
-        "id": record.id.to_string(),
-        "name": record.name,
-        "token_prefix": record.token_prefix,
-        "expires_at": record.expires_at.map(|dt| dt.to_rfc3339()),
-        "created_at": record.created_at.to_rfc3339(),
-    })))
-}
-
-/// GET /api/tokens — list the current user's tokens (no hashes).
-pub async fn tokens_list_handler(
-    State(state): State<Arc<GatewayState>>,
-    AuthenticatedUser(user): AuthenticatedUser,
-) -> Result<Json<serde_json::Value>, (StatusCode, String)> {
-    let store = state.store.as_ref().ok_or((
-        StatusCode::SERVICE_UNAVAILABLE,
-        "Database not available".to_string(),
-    ))?;
-
-    let tokens = store
-        .list_api_tokens(&user.user_id)
-        .await
-        .map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))?;
-
-    let tokens_json: Vec<serde_json::Value> = tokens
-        .into_iter()
-        .map(|t| {
-            serde_json::json!({
-                "id": t.id.to_string(),
-                "name": t.name,
-                "token_prefix": t.token_prefix,
-                "expires_at": t.expires_at.map(|dt| dt.to_rfc3339()),
-                "last_used_at": t.last_used_at.map(|dt| dt.to_rfc3339()),
-                "created_at": t.created_at.to_rfc3339(),
-                "revoked_at": t.revoked_at.map(|dt| dt.to_rfc3339()),
-            })
-        })
-        .collect();
-
-    Ok(Json(serde_json::json!({ "tokens": tokens_json })))
-}
-
-/// DELETE /api/tokens/{id} — revoke a token.
-pub async fn tokens_revoke_handler(
-    State(state): State<Arc<GatewayState>>,
-    AuthenticatedUser(user): AuthenticatedUser,
-    Path(id): Path<String>,
-) -> Result<Json<serde_json::Value>, (StatusCode, String)> {
-    let store = state.store.as_ref().ok_or((
-        StatusCode::SERVICE_UNAVAILABLE,
-        "Database not available".to_string(),
-    ))?;
-
-    let token_id = Uuid::parse_str(&id)
-        .map_err(|_| (StatusCode::BAD_REQUEST, "Invalid token ID".to_string()))?;
-
-    let revoked = store
-        .revoke_api_token(token_id, &user.user_id)
-        .await
-        .map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))?;
-
-    if !revoked {
-        return Err((StatusCode::NOT_FOUND, "Token not found".to_string()));
-    }
-
-    // Evict cached auth so revocation takes effect immediately.
-    if let Some(ref db_auth) = state.db_auth {
-        db_auth.invalidate_user(&user.user_id).await;
-    }
-
-    Ok(Json(serde_json::json!({
-        "status": "revoked",
-        "id": token_id.to_string(),
-    })))
-}

src/channels/web/handlers/users.rs

@@ -1,534 +0,0 @@
-//! User management API handlers (admin).
-
-use std::sync::Arc;
-
-use axum::{
-    Json,
-    extract::{Path, State},
-    http::StatusCode,
-};
-use rand::RngCore;
-use rand::rngs::OsRng;
-use uuid::Uuid;
-
-use crate::channels::web::auth::{AdminUser, AuthenticatedUser};
-use crate::channels::web::server::GatewayState;
-use crate::db::{Database, UserRecord};
-
-/// Check whether `user_id` is the sole active admin. Returns true if demoting,
-/// suspending, or deleting this user would leave zero admins.
-async fn is_last_admin(store: &dyn Database, user_id: &str) -> Result<bool, String> {
-    let users = store
-        .list_users(Some("active"))
-        .await
-        .map_err(|e| e.to_string())?;
-    let active_admins: Vec<_> = users.iter().filter(|u| u.role == "admin").collect();
-    Ok(active_admins.len() == 1 && active_admins[0].id == user_id)
-}
-
-/// POST /api/admin/users — create a new user.
-pub async fn users_create_handler(
-    State(state): State<Arc<GatewayState>>,
-    AdminUser(user): AdminUser,
-    Json(body): Json<serde_json::Value>,
-) -> Result<Json<serde_json::Value>, (StatusCode, String)> {
-    let store = state.store.as_ref().ok_or((
-        StatusCode::SERVICE_UNAVAILABLE,
-        "Database not available".to_string(),
-    ))?;
-
-    let display_name = body
-        .get("display_name")
-        .and_then(|v| v.as_str())
-        .map(|s| s.trim())
-        .filter(|s| !s.is_empty())
-        .ok_or((
-            StatusCode::BAD_REQUEST,
-            "Missing or empty 'display_name'".to_string(),
-        ))?
-        .to_string();
-
-    let email = body
-        .get("email")
-        .and_then(|v| v.as_str())
-        .map(|s| s.trim())
-        .filter(|s| !s.is_empty())
-        .map(String::from);
-    let role = body
-        .get("role")
-        .and_then(|v| v.as_str())
-        .unwrap_or("member")
-        .to_string();
-    if role != "admin" && role != "member" {
-        return Err((
-            StatusCode::BAD_REQUEST,
-            "role must be 'admin' or 'member'".to_string(),
-        ));
-    }
-
-    let user_id = Uuid::new_v4().to_string();
-
-    let now = chrono::Utc::now();
-    let user_record = UserRecord {
-        id: user_id.clone(),
-        email,
-        display_name: display_name.clone(),
-        status: "active".to_string(),
-        role,
-        created_at: now,
-        updated_at: now,
-        last_login_at: None,
-        created_by: Some(user.user_id.clone()),
-        metadata: serde_json::json!({}),
-    };
-
-    // Generate a first API token so the new user can authenticate immediately.
-    // Hash the hex-encoded plaintext (what the user sends as Bearer token),
-    // NOT the raw bytes — must match hash_token() in auth.rs.
-    let mut token_bytes = [0u8; 32];
-    OsRng.fill_bytes(&mut token_bytes);
-    let plaintext_token = hex::encode(token_bytes);
-    let token_hash = crate::channels::web::auth::hash_token(&plaintext_token);
-    let token_prefix = &plaintext_token[..8];
-
-    // Create user and initial token atomically — if either fails, both roll back.
-    let _token_record = store
-        .create_user_with_token(&user_record, "initial", &token_hash, token_prefix, None)
-        .await
-        .map_err(|e| {
-            let msg = e.to_string();
-            let lower = msg.to_ascii_lowercase();
-            if lower.contains("unique")
-                || lower.contains("duplicate")
-                || lower.contains("already exists")
-            {
-                (StatusCode::CONFLICT, msg)
-            } else {
-                (StatusCode::INTERNAL_SERVER_ERROR, msg)
-            }
-        })?;
-
-    Ok(Json(serde_json::json!({
-        "id": user_record.id,
-        "email": user_record.email,
-        "display_name": user_record.display_name,
-        "status": user_record.status,
-        "role": user_record.role,
-        "token": plaintext_token,
-        "created_at": user_record.created_at.to_rfc3339(),
-        "created_by": user_record.created_by,
-    })))
-}
-
-/// GET /api/admin/users — list all users with inline usage stats.
-pub async fn users_list_handler(
-    State(state): State<Arc<GatewayState>>,
-    AdminUser(_user): AdminUser,
-) -> Result<Json<serde_json::Value>, (StatusCode, String)> {
-    let store = state.store.as_ref().ok_or((
-        StatusCode::SERVICE_UNAVAILABLE,
-        "Database not available".to_string(),
-    ))?;
-
-    let users = store
-        .list_users(None)
-        .await
-        .map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))?;
-
-    // Fetch per-user summary stats from DB (agent_jobs + llm_calls).
-    let summary_stats = store
-        .user_summary_stats(None)
-        .await
-        .map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))?;
-
-    let stats_map: std::collections::HashMap<String, _> = summary_stats
-        .into_iter()
-        .map(|s| (s.user_id.clone(), s))
-        .collect();
-
-    let mut users_json: Vec<serde_json::Value> = Vec::with_capacity(users.len());
-    for u in users {
-        let db_stats = stats_map.get(&u.id);
-        let total_cost = db_stats.map_or(rust_decimal::Decimal::ZERO, |s| s.total_cost);
-
-        // Last active: prefer DB timestamp, fall back to last_login_at.
-        let last_active = db_stats.and_then(|s| s.last_active_at).or(u.last_login_at);
-
-        users_json.push(serde_json::json!({
-            "id": u.id,
-            "email": u.email,
-            "display_name": u.display_name,
-            "status": u.status,
-            "role": u.role,
-            "created_at": u.created_at.to_rfc3339(),
-            "updated_at": u.updated_at.to_rfc3339(),
-            "last_login_at": u.last_login_at.map(|dt| dt.to_rfc3339()),
-            "created_by": u.created_by,
-            "job_count": db_stats.map_or(0, |s| s.job_count),
-            "total_cost": total_cost.to_string(),
-            "last_active_at": last_active.map(|dt| dt.to_rfc3339()),
-        }));
-    }
-
-    Ok(Json(serde_json::json!({ "users": users_json })))
-}
-
-/// GET /api/admin/users/{id} — get a single user.
-pub async fn users_detail_handler(
-    State(state): State<Arc<GatewayState>>,
-    AdminUser(_user): AdminUser,
-    Path(id): Path<String>,
-) -> Result<Json<serde_json::Value>, (StatusCode, String)> {
-    let store = state.store.as_ref().ok_or((
-        StatusCode::SERVICE_UNAVAILABLE,
-        "Database not available".to_string(),
-    ))?;
-
-    let user_record = store
-        .get_user(&id)
-        .await
-        .map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))?
-        .ok_or((StatusCode::NOT_FOUND, "User not found".to_string()))?;
-
-    Ok(Json(serde_json::json!({
-        "id": user_record.id,
-        "email": user_record.email,
-        "display_name": user_record.display_name,
-        "status": user_record.status,
-        "role": user_record.role,
-        "created_at": user_record.created_at.to_rfc3339(),
-        "updated_at": user_record.updated_at.to_rfc3339(),
-        "last_login_at": user_record.last_login_at.map(|dt| dt.to_rfc3339()),
-        "created_by": user_record.created_by,
-        "metadata": user_record.metadata,
-    })))
-}
-
-/// PATCH /api/admin/users/{id} — update a user's profile.
-pub async fn users_update_handler(
-    State(state): State<Arc<GatewayState>>,
-    AdminUser(_user): AdminUser,
-    Path(id): Path<String>,
-    Json(body): Json<serde_json::Value>,
-) -> Result<Json<serde_json::Value>, (StatusCode, String)> {
-    let store = state.store.as_ref().ok_or((
-        StatusCode::SERVICE_UNAVAILABLE,
-        "Database not available".to_string(),
-    ))?;
-
-    // Verify the user exists.
-    let existing = store
-        .get_user(&id)
-        .await
-        .map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))?
-        .ok_or((StatusCode::NOT_FOUND, "User not found".to_string()))?;
-
-    let display_name = body
-        .get("display_name")
-        .and_then(|v| v.as_str())
-        .map(|s| s.trim())
-        .filter(|s| !s.is_empty())
-        .unwrap_or(&existing.display_name);
-
-    let metadata = if let Some(m) = body.get("metadata") {
-        if !m.is_object() {
-            return Err((
-                StatusCode::BAD_REQUEST,
-                "metadata must be a JSON object".to_string(),
-            ));
-        }
-        m
-    } else {
-        &existing.metadata
-    };
-
-    // Update role if provided and valid.
-    if let Some(role) = body.get("role").and_then(|v| v.as_str()) {
-        if role != "admin" && role != "member" {
-            return Err((
-                StatusCode::BAD_REQUEST,
-                "role must be 'admin' or 'member'".to_string(),
-            ));
-        }
-        if role != existing.role {
-            // Prevent demoting the last admin.
-            if existing.role == "admin"
-                && role == "member"
-                && is_last_admin(store.as_ref(), &id)
-                    .await
-                    .map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e))?
-            {
-                return Err((
-                    StatusCode::CONFLICT,
-                    "Cannot demote the last admin".to_string(),
-                ));
-            }
-            store
-                .update_user_role(&id, role)
-                .await
-                .map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))?;
-            // Evict cached auth so role change takes effect immediately.
-            if let Some(ref db_auth) = state.db_auth {
-                db_auth.invalidate_user(&id).await;
-            }
-        }
-    }
-
-    store
-        .update_user_profile(&id, display_name, metadata)
-        .await
-        .map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))?;
-
-    // Re-fetch the updated record to return consistent data.
-    let updated = store
-        .get_user(&id)
-        .await
-        .map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))?
-        .ok_or((StatusCode::NOT_FOUND, "User not found".to_string()))?;
-
-    Ok(Json(serde_json::json!({
-        "id": updated.id,
-        "email": updated.email,
-        "display_name": updated.display_name,
-        "status": updated.status,
-        "role": updated.role,
-        "created_at": updated.created_at.to_rfc3339(),
-        "updated_at": updated.updated_at.to_rfc3339(),
-        "metadata": updated.metadata,
-    })))
-}
-
-/// POST /api/admin/users/{id}/suspend — suspend a user.
-pub async fn users_suspend_handler(
-    State(state): State<Arc<GatewayState>>,
-    AdminUser(_user): AdminUser,
-    Path(id): Path<String>,
-) -> Result<Json<serde_json::Value>, (StatusCode, String)> {
-    let store = state.store.as_ref().ok_or((
-        StatusCode::SERVICE_UNAVAILABLE,
-        "Database not available".to_string(),
-    ))?;
-
-    // Verify the user exists.
-    store
-        .get_user(&id)
-        .await
-        .map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))?
-        .ok_or((StatusCode::NOT_FOUND, "User not found".to_string()))?;
-
-    // Prevent suspending the last admin.
-    if is_last_admin(store.as_ref(), &id)
-        .await
-        .map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e))?
-    {
-        return Err((
-            StatusCode::CONFLICT,
-            "Cannot suspend the last admin".to_string(),
-        ));
-    }
-
-    store
-        .update_user_status(&id, "suspended")
-        .await
-        .map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))?;
-
-    // Evict cached auth so suspension takes effect immediately.
-    if let Some(ref db_auth) = state.db_auth {
-        db_auth.invalidate_user(&id).await;
-    }
-
-    Ok(Json(serde_json::json!({
-        "id": id,
-        "status": "suspended",
-    })))
-}
-
-/// POST /api/admin/users/{id}/activate — activate a user.
-pub async fn users_activate_handler(
-    State(state): State<Arc<GatewayState>>,
-    AdminUser(_user): AdminUser,
-    Path(id): Path<String>,
-) -> Result<Json<serde_json::Value>, (StatusCode, String)> {
-    let store = state.store.as_ref().ok_or((
-        StatusCode::SERVICE_UNAVAILABLE,
-        "Database not available".to_string(),
-    ))?;
-
-    // Verify the user exists.
-    store
-        .get_user(&id)
-        .await
-        .map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))?
-        .ok_or((StatusCode::NOT_FOUND, "User not found".to_string()))?;
-
-    store
-        .update_user_status(&id, "active")
-        .await
-        .map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))?;
-
-    // Evict cached auth so reactivation takes effect immediately.
-    if let Some(ref db_auth) = state.db_auth {
-        db_auth.invalidate_user(&id).await;
-    }
-
-    Ok(Json(serde_json::json!({
-        "id": id,
-        "status": "active",
-    })))
-}
-
-/// DELETE /api/admin/users/{id} — delete a user and all their data.
-pub async fn users_delete_handler(
-    State(state): State<Arc<GatewayState>>,
-    AdminUser(_user): AdminUser,
-    Path(id): Path<String>,
-) -> Result<Json<serde_json::Value>, (StatusCode, String)> {
-    let store = state.store.as_ref().ok_or((
-        StatusCode::SERVICE_UNAVAILABLE,
-        "Database not available".to_string(),
-    ))?;
-
-    // Prevent deleting the last admin.
-    if is_last_admin(store.as_ref(), &id)
-        .await
-        .map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e))?
-    {
-        return Err((
-            StatusCode::CONFLICT,
-            "Cannot delete the last admin".to_string(),
-        ));
-    }
-
-    let deleted = store
-        .delete_user(&id)
-        .await
-        .map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))?;
-
-    if !deleted {
-        return Err((StatusCode::NOT_FOUND, "User not found".to_string()));
-    }
-
-    Ok(Json(serde_json::json!({
-        "id": id,
-        "deleted": true,
-    })))
-}
-
-/// GET /api/profile — get the authenticated user's own profile.
-pub async fn profile_get_handler(
-    State(state): State<Arc<GatewayState>>,
-    AuthenticatedUser(user): AuthenticatedUser,
-) -> Result<Json<serde_json::Value>, (StatusCode, String)> {
-    let store = state.store.as_ref().ok_or((
-        StatusCode::SERVICE_UNAVAILABLE,
-        "Database not available".to_string(),
-    ))?;
-
-    let record = store
-        .get_user(&user.user_id)
-        .await
-        .map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))?
-        .ok_or((StatusCode::NOT_FOUND, "User not found".to_string()))?;
-
-    Ok(Json(serde_json::json!({
-        "id": record.id,
-        "email": record.email,
-        "display_name": record.display_name,
-        "status": record.status,
-        "role": record.role,
-        "created_at": record.created_at.to_rfc3339(),
-        "last_login_at": record.last_login_at.map(|dt| dt.to_rfc3339()),
-    })))
-}
-
-/// PATCH /api/profile — update the authenticated user's own profile.
-pub async fn profile_update_handler(
-    State(state): State<Arc<GatewayState>>,
-    AuthenticatedUser(user): AuthenticatedUser,
-    Json(body): Json<serde_json::Value>,
-) -> Result<Json<serde_json::Value>, (StatusCode, String)> {
-    let store = state.store.as_ref().ok_or((
-        StatusCode::SERVICE_UNAVAILABLE,
-        "Database not available".to_string(),
-    ))?;
-
-    let current = store
-        .get_user(&user.user_id)
-        .await
-        .map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))?
-        .ok_or((StatusCode::NOT_FOUND, "User not found".to_string()))?;
-
-    let display_name = body
-        .get("display_name")
-        .and_then(|v| v.as_str())
-        .map(|s| s.trim())
-        .filter(|s| !s.is_empty())
-        .unwrap_or(&current.display_name);
-    let metadata = if let Some(m) = body.get("metadata") {
-        if !m.is_object() {
-            return Err((
-                StatusCode::BAD_REQUEST,
-                "metadata must be a JSON object".to_string(),
-            ));
-        }
-        m
-    } else {
-        &current.metadata
-    };
-
-    store
-        .update_user_profile(&user.user_id, display_name, metadata)
-        .await
-        .map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))?;
-
-    Ok(Json(serde_json::json!({
-        "id": user.user_id,
-        "display_name": display_name,
-        "updated": true,
-    })))
-}
-
-/// GET /api/admin/usage — per-user LLM usage stats.
-pub async fn usage_stats_handler(
-    State(state): State<Arc<GatewayState>>,
-    AdminUser(_user): AdminUser,
-    axum::extract::Query(params): axum::extract::Query<std::collections::HashMap<String, String>>,
-) -> Result<Json<serde_json::Value>, (StatusCode, String)> {
-    let store = state.store.as_ref().ok_or((
-        StatusCode::SERVICE_UNAVAILABLE,
-        "Database not available".to_string(),
-    ))?;
-
-    let user_id = params.get("user_id").map(|s| s.as_str());
-    let period = params.get("period").map(|s| s.as_str()).unwrap_or("day");
-    let since = match period {
-        "week" => chrono::Utc::now() - chrono::Duration::days(7),
-        "month" => chrono::Utc::now() - chrono::Duration::days(30),
-        _ => chrono::Utc::now() - chrono::Duration::days(1),
-    };
-
-    let stats = store
-        .user_usage_stats(user_id, since)
-        .await
-        .map_err(|e| (StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))?;
-
-    let entries: Vec<serde_json::Value> = stats
-        .iter()
-        .map(|s| {
-            serde_json::json!({
-                "user_id": s.user_id,
-                "model": s.model,
-                "call_count": s.call_count,
-                "input_tokens": s.input_tokens,
-                "output_tokens": s.output_tokens,
-                "total_cost": s.total_cost.to_string(),
-            })
-        })
-        .collect();
-
-    Ok(Json(serde_json::json!({
-        "period": period,
-        "since": since.to_rfc3339(),
-        "usage": entries,
-    })))
-}

src/channels/web/handlers/webhooks.rs

@@ -56,24 +56,13 @@ fn validate_webhook_secret(
 /// by the per-routine webhook secret sent via the `X-Webhook-Secret` header.
 ///
 /// **Single-user/backward-compatible**: looks up routines by path across all
-/// users. Disabled in multi-tenant mode — use the user-scoped endpoint at
+/// users. For multi-tenant isolation, use the user-scoped endpoint at
 /// `/api/webhooks/u/{user_id}/{path}` instead.
 pub async fn webhook_trigger_handler(
     State(state): State<Arc<GatewayState>>,
     Path(path): Path<String>,
     headers: HeaderMap,
 ) -> Result<Json<serde_json::Value>, (StatusCode, String)> {
-    // In multi-tenant mode, reject unscoped webhooks to prevent cross-user
-    // routine triggering. The per-routine secret provides some protection,
-    // but tenant isolation requires scoping by user_id.
-    // Use workspace_pool as the multi-tenant indicator — it's only set when
-    // has_any_users() was true at startup (not just when a DB exists).
-    if state.workspace_pool.is_some() {
-        return Err((
-            StatusCode::GONE,
-            "Unscoped webhooks disabled in multi-tenant mode. Use /api/webhooks/u/{user_id}/{path} instead.".to_string(),
-        ));
-    }
     fire_webhook_inner(state, &path, None, &headers).await
 }
 

src/channels/web/mod.rs

@@ -56,7 +56,7 @@ use crate::workspace::Workspace;
 
 use self::log_layer::{LogBroadcaster, LogLevelHandle};
 
-use self::auth::{CombinedAuthState, DbAuthenticator, MultiAuthState};
+use self::auth::MultiAuthState;
 use self::server::GatewayState;
 use self::sse::SseManager;
 use self::types::AppEvent;
@@ -65,8 +65,8 @@ use self::types::AppEvent;
 pub struct GatewayChannel {
     config: GatewayConfig,
     state: Arc<GatewayState>,
-    /// Combined auth state: env-var tokens + optional DB-backed tokens.
-    auth: CombinedAuthState,
+    /// Multi-user auth state (replaces bare auth_token).
+    auth: MultiAuthState,
 }
 
 impl GatewayChannel {
@@ -74,7 +74,7 @@ impl GatewayChannel {
     ///
     /// If no auth token is configured, generates a random one and prints it.
     /// Builds a single-user `MultiAuthState` from the config.
-    pub fn new(config: GatewayConfig, owner_id: String) -> Self {
+    pub fn new(config: GatewayConfig) -> Self {
         let auth_token = config.auth_token.clone().unwrap_or_else(|| {
             use rand::RngCore;
             use rand::rngs::OsRng;
@@ -83,10 +83,7 @@ impl GatewayChannel {
             bytes.iter().map(|b| format!("{b:02x}")).collect()
         });
 
-        let auth = CombinedAuthState {
-            env_auth: MultiAuthState::single(auth_token, owner_id.clone()),
-            db_auth: None,
-        };
+        let auth = MultiAuthState::single(auth_token, config.user_id.clone());
 
         let state = Arc::new(GatewayState {
             msg_tx: tokio::sync::RwLock::new(None),
@@ -102,7 +99,8 @@ impl GatewayChannel {
             job_manager: None,
             prompt_queue: None,
             scheduler: None,
-            owner_id,
+            owner_id: config.user_id.clone(),
+            default_sender_id: config.user_id.clone(),
             shutdown_tx: tokio::sync::RwLock::new(None),
             ws_tracker: Some(Arc::new(ws::WsConnectionTracker::new())),
             llm_provider: None,
@@ -117,7 +115,63 @@ impl GatewayChannel {
             startup_time: std::time::Instant::now(),
             active_config: server::ActiveConfigSnapshot::default(),
             secrets_store: None,
-            db_auth: None,
+        });
+
+        Self {
+            config,
+            state,
+            auth,
+        }
+    }
+
+    /// Rebind the single-user auth identity to the durable owner scope while
+    /// preserving the configured gateway sender/routing identity.
+    pub fn with_owner_scope(mut self, owner_id: impl Into<String>) -> Self {
+        let owner_id = owner_id.into();
+        let single_user_token = if self.config.user_tokens.is_none() {
+            self.auth.first_token().map(ToOwned::to_owned)
+        } else {
+            None
+        };
+        if let Some(token) = single_user_token {
+            self.auth = MultiAuthState::single(token, owner_id.clone());
+        }
+        self.rebuild_state(|s| s.owner_id = owner_id);
+        self
+    }
+
+    /// Create a gateway channel with a pre-built multi-user auth state.
+    pub fn new_multi_auth(config: GatewayConfig, auth: MultiAuthState) -> Self {
+        let state = Arc::new(GatewayState {
+            msg_tx: tokio::sync::RwLock::new(None),
+            sse: Arc::new(SseManager::new()),
+            workspace: None,
+            workspace_pool: None,
+            session_manager: None,
+            log_broadcaster: None,
+            log_level_handle: None,
+            extension_manager: None,
+            tool_registry: None,
+            store: None,
+            job_manager: None,
+            prompt_queue: None,
+            scheduler: None,
+            owner_id: config.user_id.clone(),
+            default_sender_id: config.user_id.clone(),
+            shutdown_tx: tokio::sync::RwLock::new(None),
+            ws_tracker: Some(Arc::new(ws::WsConnectionTracker::new())),
+            llm_provider: None,
+            skill_registry: None,
+            skill_catalog: None,
+            chat_rate_limiter: server::PerUserRateLimiter::new(30, 60),
+            oauth_rate_limiter: server::RateLimiter::new(10, 60),
+            registry_entries: Vec::new(),
+            cost_guard: None,
+            routine_engine: Arc::new(tokio::sync::RwLock::new(None)),
+            startup_time: std::time::Instant::now(),
+            webhook_rate_limiter: server::RateLimiter::new(10, 60),
+            active_config: server::ActiveConfigSnapshot::default(),
+            secrets_store: None,
         });
 
         Self {
@@ -145,6 +199,7 @@ impl GatewayChannel {
             prompt_queue: self.state.prompt_queue.clone(),
             scheduler: self.state.scheduler.clone(),
             owner_id: self.state.owner_id.clone(),
+            default_sender_id: self.state.default_sender_id.clone(),
             shutdown_tx: tokio::sync::RwLock::new(None),
             ws_tracker: self.state.ws_tracker.clone(),
             llm_provider: self.state.llm_provider.clone(),
@@ -159,7 +214,6 @@ impl GatewayChannel {
             startup_time: self.state.startup_time,
             active_config: self.state.active_config.clone(),
             secrets_store: self.state.secrets_store.clone(),
-            db_auth: self.state.db_auth.clone(),
         };
         mutate(&mut new_state);
         self.state = Arc::new(new_state);
@@ -207,17 +261,6 @@ impl GatewayChannel {
         self
     }
 
-    /// Enable DB-backed token authentication alongside env-var tokens.
-    pub fn with_db_auth(mut self, store: Arc<dyn Database>) -> Self {
-        let authenticator = DbAuthenticator::new(store);
-        // Share the same DbAuthenticator (and its cache) between the auth
-        // middleware and GatewayState so handlers can invalidate the cache
-        // on security-critical actions (suspend, role change, token revoke).
-        self.rebuild_state(|s| s.db_auth = Some(Arc::new(authenticator.clone())));
-        self.auth.db_auth = Some(authenticator);
-        self
-    }
-
     /// Inject the container job manager for sandbox operations.
     pub fn with_job_manager(mut self, jm: Arc<ContainerJobManager>) -> Self {
         self.rebuild_state(|s| s.job_manager = Some(jm));
@@ -288,12 +331,12 @@ impl GatewayChannel {
         self
     }
 
-    /// Inject the secrets store for admin secret provisioning.
+    /// Inject the secrets store for encrypting LLM API keys in settings handlers.
     pub fn with_secrets_store(
         mut self,
-        store: Arc<dyn crate::secrets::SecretsStore + Send + Sync>,
+        ss: Arc<dyn crate::secrets::SecretsStore + Send + Sync>,
     ) -> Self {
-        self.rebuild_state(|s| s.secrets_store = Some(store));
+        self.rebuild_state(|s| s.secrets_store = Some(ss));
         self
     }
 
@@ -305,7 +348,7 @@ impl GatewayChannel {
 
     /// Get the first auth token (for printing to console on startup).
     pub fn auth_token(&self) -> &str {
-        self.auth.env_auth.first_token().unwrap_or("")
+        self.auth.first_token().unwrap_or("")
     }
 
     /// Get a reference to the shared gateway state (for the agent to push SSE events).

src/channels/web/server.rs

@@ -16,7 +16,7 @@ use axum::{
         IntoResponse,
         sse::{Event, KeepAlive, Sse},
     },
-    routing::{get, post, put},
+    routing::{get, post},
 };
 use serde::Deserialize;
 use sha2::{Digest, Sha256};
@@ -31,7 +31,7 @@ use crate::bootstrap::ironclaw_base_dir;
 use crate::channels::IncomingMessage;
 use crate::channels::relay::DEFAULT_RELAY_NAME;
 use crate::channels::web::auth::{
-    AuthenticatedUser, CombinedAuthState, UserIdentity, auth_middleware,
+    AuthenticatedUser, MultiAuthState, UserIdentity, auth_middleware,
 };
 use crate::channels::web::handlers::jobs::{
     job_files_list_handler, job_files_read_handler, jobs_cancel_handler, jobs_detail_handler,
@@ -46,6 +46,10 @@ use crate::channels::web::handlers::routines::{
     routines_delete_handler, routines_detail_handler, routines_list_handler,
     routines_summary_handler, routines_toggle_handler, routines_trigger_handler,
 };
+use crate::channels::web::handlers::settings::{
+    settings_delete_handler, settings_export_handler, settings_get_handler,
+    settings_import_handler, settings_list_handler, settings_set_handler,
+};
 use crate::channels::web::handlers::skills::{
     skills_install_handler, skills_list_handler, skills_remove_handler, skills_search_handler,
 };
@@ -53,6 +57,7 @@ use crate::channels::web::log_layer::LogBroadcaster;
 use crate::channels::web::sse::SseManager;
 use crate::channels::web::types::*;
 use crate::channels::web::util::{build_turns_from_db_messages, truncate_preview};
+use crate::config::helpers::validate_base_url;
 use crate::db::Database;
 use crate::extensions::ExtensionManager;
 use crate::orchestrator::job_manager::ContainerJobManager;
@@ -290,22 +295,7 @@ impl WorkspacePool {
         }
 
         let ws = Arc::new(ws);
-
         cache.insert(identity.user_id.clone(), Arc::clone(&ws));
-
-        // Seed identity files after inserting into cache (so the lock can be
-        // dropped) but before returning, so callers see a seeded workspace.
-        // Drop the write lock explicitly before the async seed to avoid
-        // blocking other workspace lookups.
-        drop(cache);
-        if let Err(e) = ws.seed_if_empty().await {
-            tracing::warn!(
-                user_id = identity.user_id,
-                "Failed to seed workspace: {}",
-                e
-            );
-        }
-
         ws
     }
 }
@@ -362,6 +352,8 @@ pub struct GatewayState {
     pub prompt_queue: Option<PromptQueue>,
     /// Durable owner scope for persistence and unauthenticated callback flows.
     pub owner_id: String,
+    /// Default sender/routing identity for gateway-originated messages.
+    pub default_sender_id: String,
     /// Shutdown signal sender.
     pub shutdown_tx: tokio::sync::RwLock<Option<oneshot::Sender<()>>>,
     /// WebSocket connection tracker.
@@ -391,10 +383,8 @@ pub struct GatewayState {
     pub startup_time: std::time::Instant,
     /// Snapshot of active (resolved) configuration for the frontend.
     pub active_config: ActiveConfigSnapshot,
-    /// Secrets store for admin secret provisioning.
+    /// Secrets store for encrypting LLM API keys (and future sensitive settings).
     pub secrets_store: Option<Arc<dyn crate::secrets::SecretsStore + Send + Sync>>,
-    /// DB auth cache for invalidation on security-critical actions.
-    pub db_auth: Option<Arc<crate::channels::web::auth::DbAuthenticator>>,
 }
 
 /// Start the gateway HTTP server.
@@ -403,7 +393,7 @@ pub struct GatewayState {
 pub async fn start_server(
     addr: SocketAddr,
     state: Arc<GatewayState>,
-    auth: CombinedAuthState,
+    auth: MultiAuthState,
 ) -> Result<SocketAddr, crate::error::ChannelError> {
     let listener = tokio::net::TcpListener::bind(addr).await.map_err(|e| {
         crate::error::ChannelError::StartupFailed {
@@ -529,57 +519,13 @@ pub async fn start_server(
             "/api/settings/{key}",
             axum::routing::delete(settings_delete_handler),
         )
-        // User management (admin)
+        // LLM utilities
         .route(
-            "/api/admin/users",
-            get(super::handlers::users::users_list_handler)
-                .post(super::handlers::users::users_create_handler),
-        )
-        .route(
-            "/api/admin/users/{id}",
-            get(super::handlers::users::users_detail_handler)
-                .patch(super::handlers::users::users_update_handler)
-                .delete(super::handlers::users::users_delete_handler),
-        )
-        .route(
-            "/api/admin/users/{id}/suspend",
-            post(super::handlers::users::users_suspend_handler),
-        )
-        .route(
-            "/api/admin/users/{id}/activate",
-            post(super::handlers::users::users_activate_handler),
-        )
-        // Admin secrets provisioning (per-user)
-        .route(
-            "/api/admin/users/{user_id}/secrets",
-            get(super::handlers::secrets::secrets_list_handler),
-        )
-        .route(
-            "/api/admin/users/{user_id}/secrets/{name}",
-            put(super::handlers::secrets::secrets_put_handler)
-                .delete(super::handlers::secrets::secrets_delete_handler),
-        )
-        // Usage reporting (admin)
-        .route(
-            "/api/admin/usage",
-            get(super::handlers::users::usage_stats_handler),
-        )
-        // User self-service profile
-        .route(
-            "/api/profile",
-            get(super::handlers::users::profile_get_handler)
-                .patch(super::handlers::users::profile_update_handler),
-        )
-        // Token management
-        .route(
-            "/api/tokens",
-            get(super::handlers::tokens::tokens_list_handler)
-                .post(super::handlers::tokens::tokens_create_handler),
-        )
-        .route(
-            "/api/tokens/{id}",
-            axum::routing::delete(super::handlers::tokens::tokens_revoke_handler),
+            "/api/llm/test_connection",
+            post(llm_test_connection_handler),
         )
+        .route("/api/llm/list_models", post(llm_list_models_handler))
+        .route("/api/llm/env_defaults", get(llm_env_defaults_handler))
         // Gateway control plane
         .route("/api/gateway/status", get(gateway_status_handler))
         // OpenAI-compatible API
@@ -606,6 +552,7 @@ pub async fn start_server(
     let statics = Router::new()
         .route("/", get(index_handler))
         .route("/style.css", get(css_handler))
+        .route("/providers.js", get(providers_js_handler))
         .route("/app.js", get(js_handler))
         .route("/theme-init.js", get(theme_init_handler))
         .route("/favicon.ico", get(favicon_handler))
@@ -639,7 +586,6 @@ pub async fn start_server(
             axum::http::Method::GET,
             axum::http::Method::POST,
             axum::http::Method::PUT,
-            axum::http::Method::PATCH,
             axum::http::Method::DELETE,
         ])
         .allow_headers(AllowHeaders::list([
@@ -654,33 +600,6 @@ pub async fn start_server(
         .merge(projects)
         .merge(protected)
         .layer(DefaultBodyLimit::max(10 * 1024 * 1024)) // 10 MB max request body (image uploads)
-        .layer(tower_http::catch_panic::CatchPanicLayer::custom(
-            |panic_info: Box<dyn std::any::Any + Send + 'static>| {
-                let detail = if let Some(s) = panic_info.downcast_ref::<String>() {
-                    s.clone()
-                } else if let Some(s) = panic_info.downcast_ref::<&str>() {
-                    (*s).to_string()
-                } else {
-                    "unknown panic".to_string()
-                };
-                // Truncate panic payload to avoid leaking sensitive data into logs.
-                // Use floor_char_boundary to avoid panicking on multi-byte UTF-8.
-                let safe_detail = if detail.len() > 200 {
-                    let end = detail.floor_char_boundary(200);
-                    format!("{}…", &detail[..end])
-                } else {
-                    detail
-                };
-                tracing::error!("Handler panicked: {}", safe_detail);
-                axum::http::Response::builder()
-                    .status(axum::http::StatusCode::INTERNAL_SERVER_ERROR)
-                    .header("content-type", "text/plain")
-                    .body(axum::body::Body::from("Internal Server Error"))
-                    .unwrap_or_else(|_| {
-                        axum::http::Response::new(axum::body::Body::from("Internal Server Error"))
-                    })
-            },
-        ))
         .layer(cors)
         .layer(SetResponseHeaderLayer::if_not_present(
             header::X_CONTENT_TYPE_OPTIONS,
@@ -747,6 +666,16 @@ async fn css_handler() -> impl IntoResponse {
     )
 }
 
+async fn providers_js_handler() -> impl IntoResponse {
+    (
+        [
+            (header::CONTENT_TYPE, "application/javascript"),
+            (header::CACHE_CONTROL, "no-cache"),
+        ],
+        include_str!("static/providers.js"),
+    )
+}
+
 async fn js_handler() -> impl IntoResponse {
     (
         [
@@ -1428,6 +1357,9 @@ async fn chat_send_handler(
     }
 
     let mut msg = IncomingMessage::new("gateway", &user.user_id, &req.content);
+    if state.owner_id != state.default_sender_id && user.user_id == state.owner_id {
+        msg = msg.with_sender_id(&state.default_sender_id);
+    }
     // Prefer timezone from JSON body, fall back to X-Timezone header
     let tz = req
         .timezone
@@ -1529,6 +1461,9 @@ async fn chat_approval_handler(
     })?;
 
     let mut msg = IncomingMessage::new("gateway", &user.user_id, content);
+    if state.owner_id != state.default_sender_id && user.user_id == state.owner_id {
+        msg = msg.with_sender_id(&state.default_sender_id);
+    }
 
     if let Some(ref thread_id) = req.thread_id {
         msg = msg.with_thread(thread_id);
@@ -2739,133 +2674,458 @@ async fn routines_runs_handler(
     })))
 }
 
-// --- Settings handlers ---
-
-async fn settings_list_handler(
-    State(state): State<Arc<GatewayState>>,
-    AuthenticatedUser(user): AuthenticatedUser,
-) -> Result<Json<SettingsListResponse>, StatusCode> {
-    let store = state
-        .store
-        .as_ref()
-        .ok_or(StatusCode::SERVICE_UNAVAILABLE)?;
-    let rows = store.list_settings(&user.user_id).await.map_err(|e| {
-        tracing::error!("Failed to list settings: {}", e);
-        StatusCode::INTERNAL_SERVER_ERROR
-    })?;
-
-    let settings = rows
-        .into_iter()
-        .map(|r| SettingResponse {
-            key: r.key,
-            value: r.value,
-            updated_at: r.updated_at.to_rfc3339(),
-        })
-        .collect();
-
-    Ok(Json(SettingsListResponse { settings }))
+/// Fields shared by `test_connection` and `list_models` requests.
+///
+/// When `api_key` is absent the handler falls back to the encrypted secrets
+/// store, using `provider_id` + `provider_type` to locate the vaulted key.
+#[derive(serde::Deserialize)]
+struct TestConnectionRequest {
+    adapter: String,
+    base_url: String,
+    /// Model to use for the test chat completion request.
+    model: String,
+    #[serde(default)]
+    api_key: Option<String>,
+    /// Provider identifier used to look up the vaulted API key when `api_key`
+    /// is not supplied by the frontend (key already stored in secrets).
+    #[serde(default)]
+    provider_id: Option<String>,
+    /// `"builtin"` or `"custom"` — determines the secret name prefix.
+    #[serde(default)]
+    provider_type: Option<String>,
 }
 
-async fn settings_get_handler(
-    State(state): State<Arc<GatewayState>>,
-    AuthenticatedUser(user): AuthenticatedUser,
-    Path(key): Path<String>,
-) -> Result<Json<SettingResponse>, StatusCode> {
-    let store = state
-        .store
-        .as_ref()
-        .ok_or(StatusCode::SERVICE_UNAVAILABLE)?;
-    let row = store
-        .get_setting_full(&user.user_id, &key)
-        .await
-        .map_err(|e| {
-            tracing::error!("Failed to get setting '{}': {}", key, e);
-            StatusCode::INTERNAL_SERVER_ERROR
-        })?
-        .ok_or(StatusCode::NOT_FOUND)?;
-
-    Ok(Json(SettingResponse {
-        key: row.key,
-        value: row.value,
-        updated_at: row.updated_at.to_rfc3339(),
-    }))
+#[derive(serde::Serialize)]
+struct TestConnectionResponse {
+    ok: bool,
+    message: String,
 }
 
-async fn settings_set_handler(
+async fn llm_test_connection_handler(
     State(state): State<Arc<GatewayState>>,
     AuthenticatedUser(user): AuthenticatedUser,
-    Path(key): Path<String>,
-    Json(body): Json<SettingWriteRequest>,
-) -> Result<StatusCode, StatusCode> {
-    let store = state
-        .store
-        .as_ref()
-        .ok_or(StatusCode::SERVICE_UNAVAILABLE)?;
-    store
-        .set_setting(&user.user_id, &key, &body.value)
-        .await
-        .map_err(|e| {
-            tracing::error!("Failed to set setting '{}': {}", key, e);
-            StatusCode::INTERNAL_SERVER_ERROR
-        })?;
-
-    Ok(StatusCode::NO_CONTENT)
+    Json(mut body): Json<TestConnectionRequest>,
+) -> Json<TestConnectionResponse> {
+    resolve_api_key_from_secrets(
+        &state,
+        &user.user_id,
+        &mut body.api_key,
+        &body.provider_id,
+        &body.provider_type,
+    )
+    .await;
+    Json(test_provider_connection(body).await)
 }
 
-async fn settings_delete_handler(
-    State(state): State<Arc<GatewayState>>,
-    AuthenticatedUser(user): AuthenticatedUser,
-    Path(key): Path<String>,
-) -> Result<StatusCode, StatusCode> {
-    let store = state
-        .store
-        .as_ref()
-        .ok_or(StatusCode::SERVICE_UNAVAILABLE)?;
-    store
-        .delete_setting(&user.user_id, &key)
-        .await
-        .map_err(|e| {
-            tracing::error!("Failed to delete setting '{}': {}", key, e);
-            StatusCode::INTERNAL_SERVER_ERROR
-        })?;
-
-    Ok(StatusCode::NO_CONTENT)
+/// When the frontend doesn't supply an `api_key` (because it was already vaulted),
+/// look it up from the encrypted secrets store using `provider_id` + `provider_type`.
+async fn resolve_api_key_from_secrets(
+    state: &GatewayState,
+    user_id: &str,
+    api_key: &mut Option<String>,
+    provider_id: &Option<String>,
+    provider_type: &Option<String>,
+) {
+    // Already have a key from the request — nothing to resolve.
+    if api_key.as_ref().is_some_and(|k| !k.is_empty()) {
+        return;
+    }
+    let pid = match provider_id.as_deref().filter(|s| !s.is_empty()) {
+        Some(id) => id,
+        None => return,
+    };
+    let secrets = match state.secrets_store.as_ref() {
+        Some(s) => s,
+        None => return,
+    };
+    let secret_name = match provider_type.as_deref() {
+        Some("custom") => format!("llm_custom_{}_api_key", pid),
+        _ => format!("llm_builtin_{}_api_key", pid),
+    };
+    if let Ok(decrypted) = secrets.get_decrypted(user_id, &secret_name).await {
+        *api_key = Some(decrypted.expose().to_string());
+    }
 }
 
-async fn settings_export_handler(
-    State(state): State<Arc<GatewayState>>,
-    AuthenticatedUser(user): AuthenticatedUser,
-) -> Result<Json<SettingsExportResponse>, StatusCode> {
-    let store = state
-        .store
-        .as_ref()
-        .ok_or(StatusCode::SERVICE_UNAVAILABLE)?;
-    let settings = store.get_all_settings(&user.user_id).await.map_err(|e| {
-        tracing::error!("Failed to export settings: {}", e);
-        StatusCode::INTERNAL_SERVER_ERROR
-    })?;
-
-    Ok(Json(SettingsExportResponse { settings }))
+/// Check if a base URL belongs to a NEAR AI private endpoint.
+///
+/// Matches `private.near.ai` exactly or any subdomain of it
+/// (e.g. `us.private.near.ai`). Rejects lookalikes like
+/// `private-evil.near.ai` or `myprivate.near.ai`.
+fn is_nearai_private_endpoint(base_url: &str) -> bool {
+    url::Url::parse(base_url)
+        .ok()
+        .and_then(|u| u.host_str().map(|h| h.to_lowercase()))
+        .is_some_and(|host| host == "private.near.ai" || host.ends_with(".private.near.ai"))
 }
 
-async fn settings_import_handler(
+async fn test_provider_connection(req: TestConnectionRequest) -> TestConnectionResponse {
+    if let Err(e) = validate_base_url(&req.base_url, "base_url") {
+        return TestConnectionResponse {
+            ok: false,
+            message: format!("Invalid base URL: {e}"),
+        };
+    }
+
+    if req.model.trim().is_empty() {
+        return TestConnectionResponse {
+            ok: false,
+            message: "Model is required for connection test".to_string(),
+        };
+    }
+
+    let client = match reqwest::Client::builder()
+        .timeout(std::time::Duration::from_secs(30))
+        .build()
+    {
+        Ok(c) => c,
+        Err(e) => {
+            return TestConnectionResponse {
+                ok: false,
+                message: format!("Failed to build HTTP client: {e}"),
+            };
+        }
+    };
+
+    let base = req.base_url.trim_end_matches('/');
+
+    match req.adapter.as_str() {
+        "anthropic" => {
+            let anthropic_base = if base.ends_with("/v1") || base.contains("/v1/") {
+                base.to_string()
+            } else {
+                format!("{base}/v1")
+            };
+            let url = format!("{anthropic_base}/messages");
+            let body = serde_json::json!({
+                "model": req.model,
+                "max_tokens": 16,
+                "messages": [{"role": "user", "content": "hi"}]
+            });
+            let mut builder = client
+                .post(&url)
+                .header("anthropic-version", "2023-06-01")
+                .json(&body);
+            if let Some(key) = req.api_key.as_deref().filter(|k| !k.is_empty()) {
+                builder = builder.header("x-api-key", key);
+            }
+            interpret_chat_response(builder.send().await)
+        }
+        "ollama" => {
+            let url = format!("{base}/api/chat");
+            let body = serde_json::json!({
+                "model": req.model,
+                "messages": [{"role": "user", "content": "hi"}],
+                "stream": false
+            });
+            let builder = client.post(&url).json(&body);
+            interpret_chat_response(builder.send().await)
+        }
+        _ => {
+            // OpenAI-compatible (including nearai): POST /v1/chat/completions
+            // If base already ends with /v1, append directly; otherwise insert /v1.
+            let chat_url = if base.ends_with("/v1") {
+                format!("{base}/chat/completions")
+            } else {
+                format!("{base}/v1/chat/completions")
+            };
+            let body = serde_json::json!({
+                "model": req.model,
+                "max_tokens": 16,
+                "messages": [{"role": "user", "content": "hi"}]
+            });
+            let mut builder = client.post(&chat_url).json(&body);
+            if let Some(key) = req.api_key.as_deref().filter(|k| !k.is_empty()) {
+                builder = builder.header("Authorization", format!("Bearer {key}"));
+            }
+            interpret_chat_response(builder.send().await)
+        }
+    }
+}
+
+fn interpret_chat_response(
+    result: Result<reqwest::Response, reqwest::Error>,
+) -> TestConnectionResponse {
+    match result {
+        Ok(r) => {
+            let status = r.status();
+            if status.is_success() {
+                TestConnectionResponse {
+                    ok: true,
+                    message: format!("Connected ({})", status),
+                }
+            } else if status == reqwest::StatusCode::UNAUTHORIZED
+                || status == reqwest::StatusCode::FORBIDDEN
+            {
+                TestConnectionResponse {
+                    ok: false,
+                    message: format!("Authentication failed ({})", status),
+                }
+            } else if status == reqwest::StatusCode::BAD_REQUEST
+                || status == reqwest::StatusCode::UNPROCESSABLE_ENTITY
+            {
+                // 400/422 = server reachable, likely wrong endpoint variant — connectivity OK
+                TestConnectionResponse {
+                    ok: true,
+                    message: format!("Server reachable ({})", status),
+                }
+            } else if status == reqwest::StatusCode::NOT_FOUND {
+                // 404 = /models endpoint not found — server reachable but not OpenAI-compatible
+                TestConnectionResponse {
+                    ok: false,
+                    message: format!(
+                        "Server reachable but /models endpoint not found ({}). \
+                         Check the base URL and adapter type.",
+                        status
+                    ),
+                }
+            } else if status.is_client_error() {
+                TestConnectionResponse {
+                    ok: false,
+                    message: format!("Client error ({})", status),
+                }
+            } else {
+                TestConnectionResponse {
+                    ok: false,
+                    message: format!("Server error ({})", status),
+                }
+            }
+        }
+        Err(e) => TestConnectionResponse {
+            ok: false,
+            message: format!("Connection failed: {e}"),
+        },
+    }
+}
+
+#[derive(serde::Deserialize)]
+struct ListModelsRequest {
+    adapter: String,
+    base_url: String,
+    #[serde(default)]
+    api_key: Option<String>,
+    #[serde(default)]
+    provider_id: Option<String>,
+    #[serde(default)]
+    provider_type: Option<String>,
+}
+
+#[derive(serde::Serialize)]
+struct ListModelsResponse {
+    ok: bool,
+    models: Vec<String>,
+    message: String,
+}
+
+async fn llm_list_models_handler(
     State(state): State<Arc<GatewayState>>,
     AuthenticatedUser(user): AuthenticatedUser,
-    Json(body): Json<SettingsImportRequest>,
-) -> Result<StatusCode, StatusCode> {
-    let store = state
-        .store
-        .as_ref()
-        .ok_or(StatusCode::SERVICE_UNAVAILABLE)?;
-    store
-        .set_all_settings(&user.user_id, &body.settings)
-        .await
-        .map_err(|e| {
-            tracing::error!("Failed to import settings: {}", e);
-            StatusCode::INTERNAL_SERVER_ERROR
-        })?;
+    Json(mut body): Json<ListModelsRequest>,
+) -> Json<ListModelsResponse> {
+    resolve_api_key_from_secrets(
+        &state,
+        &user.user_id,
+        &mut body.api_key,
+        &body.provider_id,
+        &body.provider_type,
+    )
+    .await;
+    Json(fetch_provider_models(body).await)
+}
 
-    Ok(StatusCode::NO_CONTENT)
+async fn fetch_provider_models(req: ListModelsRequest) -> ListModelsResponse {
+    if let Err(e) = validate_base_url(&req.base_url, "base_url") {
+        return ListModelsResponse {
+            ok: false,
+            models: vec![],
+            message: format!("Invalid base URL: {e}"),
+        };
+    }
+
+    let client = match reqwest::Client::builder()
+        .timeout(std::time::Duration::from_secs(15))
+        .build()
+    {
+        Ok(c) => c,
+        Err(e) => {
+            return ListModelsResponse {
+                ok: false,
+                models: vec![],
+                message: format!("Failed to build HTTP client: {e}"),
+            };
+        }
+    };
+
+    let base = req.base_url.trim_end_matches('/');
+    let auth = req.api_key.as_deref().filter(|k| !k.is_empty());
+
+    match req.adapter.as_str() {
+        "ollama" => {
+            let url = format!("{base}/api/tags");
+            match client.get(&url).send().await {
+                Ok(r) if r.status().is_success() => {
+                    let body: serde_json::Value = r.json().await.unwrap_or_default();
+                    let models: Vec<String> = body["models"]
+                        .as_array()
+                        .map(|arr| {
+                            arr.iter()
+                                .filter_map(|m| m["name"].as_str().map(|s| s.to_string()))
+                                .collect()
+                        })
+                        .unwrap_or_default();
+                    if models.is_empty() {
+                        ListModelsResponse {
+                            ok: false,
+                            models: vec![],
+                            message: "No models found".to_string(),
+                        }
+                    } else {
+                        ListModelsResponse {
+                            ok: true,
+                            message: format!("{} model(s) found", models.len()),
+                            models,
+                        }
+                    }
+                }
+                Ok(r) => ListModelsResponse {
+                    ok: false,
+                    models: vec![],
+                    message: format!("Server returned {}", r.status()),
+                },
+                Err(e) => ListModelsResponse {
+                    ok: false,
+                    models: vec![],
+                    message: format!("Connection failed: {e}"),
+                },
+            }
+        }
+        _ => {
+            // OpenAI-compatible, Anthropic, and NEAR AI all support GET /models.
+            // NEAR AI private endpoints and Anthropic need a /v1 prefix.
+            let effective_base = if (req.adapter == "nearai" && is_nearai_private_endpoint(base))
+                || (req.adapter == "anthropic" && !base.ends_with("/v1") && !base.contains("/v1/"))
+            {
+                format!("{base}/v1")
+            } else {
+                base.to_string()
+            };
+            let url = format!("{effective_base}/models");
+            let mut builder = client.get(&url);
+            if req.adapter == "anthropic" {
+                // Anthropic requires a version header and uses x-api-key for authentication
+                builder = builder.header("anthropic-version", "2023-06-01");
+                if let Some(key) = auth {
+                    builder = builder.header("x-api-key", key);
+                }
+            } else if let Some(key) = auth {
+                builder = builder.header("Authorization", format!("Bearer {key}"));
+            }
+            match builder.send().await {
+                Ok(r) if r.status().is_success() => {
+                    let body: serde_json::Value = r.json().await.unwrap_or_default();
+                    // OpenAI: {"data": [{"id": "..."}]}
+                    // Anthropic: {"data": [{"id": "..."}]}
+                    let models: Vec<String> = body["data"]
+                        .as_array()
+                        .map(|arr| {
+                            arr.iter()
+                                .filter_map(|m| m["id"].as_str().map(|s| s.to_string()))
+                                .collect()
+                        })
+                        .unwrap_or_default();
+                    if models.is_empty() {
+                        ListModelsResponse {
+                            ok: false,
+                            models: vec![],
+                            message: "No models found in response".to_string(),
+                        }
+                    } else {
+                        ListModelsResponse {
+                            ok: true,
+                            message: format!("{} model(s) found", models.len()),
+                            models,
+                        }
+                    }
+                }
+                Ok(r) => ListModelsResponse {
+                    ok: false,
+                    models: vec![],
+                    message: format!("Server returned {} — list models not supported", r.status()),
+                },
+                Err(e) => ListModelsResponse {
+                    ok: false,
+                    models: vec![],
+                    message: format!("Connection failed: {e}"),
+                },
+            }
+        }
+    }
+}
+
+// --- LLM env defaults handler ---
+
+/// Returns env-var-based defaults for each builtin LLM provider.
+///
+/// The frontend uses these as fallback values when the DB has no overrides.
+/// API keys are never returned — only a boolean `has_api_key`.
+async fn llm_env_defaults_handler(
+    AuthenticatedUser(_user): AuthenticatedUser,
+) -> Json<serde_json::Value> {
+    Json(build_llm_env_defaults())
+}
+
+fn build_llm_env_defaults() -> serde_json::Value {
+    use crate::config::helpers::optional_env;
+    use crate::llm::registry::ProviderRegistry;
+
+    let registry = ProviderRegistry::load();
+    let mut defaults = serde_json::Map::new();
+
+    // Helper: read env var via optional_env (checks real env + injected overlay).
+    let read_env = |key: &str| -> Option<String> { optional_env(key).ok().flatten() };
+
+    // NEAR AI is a special case (not in the registry)
+    {
+        let mut entry = serde_json::Map::new();
+        // Only expose presence of API key, never the value itself.
+        entry.insert(
+            "has_api_key".to_string(),
+            serde_json::Value::Bool(read_env("NEARAI_API_KEY").is_some()),
+        );
+        if let Some(model) = read_env("NEARAI_MODEL") {
+            entry.insert("model".to_string(), serde_json::Value::String(model));
+        }
+        if let Some(url) = read_env("NEARAI_BASE_URL") {
+            entry.insert("base_url".to_string(), serde_json::Value::String(url));
+        }
+        defaults.insert("nearai".to_string(), serde_json::Value::Object(entry));
+    }
+
+    // Registry-based providers
+    for def in registry.all() {
+        let mut entry = serde_json::Map::new();
+
+        if let Some(ref api_key_env) = def.api_key_env {
+            entry.insert(
+                "has_api_key".to_string(),
+                serde_json::Value::Bool(read_env(api_key_env).is_some()),
+            );
+        }
+
+        if let Some(model) = read_env(&def.model_env) {
+            entry.insert("model".to_string(), serde_json::Value::String(model));
+        }
+
+        if let Some(ref base_url_env) = def.base_url_env
+            && let Some(url) = read_env(base_url_env)
+        {
+            entry.insert("base_url".to_string(), serde_json::Value::String(url));
+        }
+
+        defaults.insert(def.id.clone(), serde_json::Value::Object(entry));
+    }
+
+    serde_json::Value::Object(defaults)
 }
 
 // --- Gateway control plane handlers ---
@@ -3113,6 +3373,67 @@ mod tests {
         Ok(())
     }
 
+    // --- LLM env defaults handler tests ---
+
+    #[tokio::test]
+    async fn test_llm_env_defaults_returns_nearai_env_vars() {
+        // SAFETY: test-only; tokio::test runs single-threaded by default.
+        unsafe {
+            std::env::set_var("NEARAI_API_KEY", "test-key-123");
+            std::env::set_var("NEARAI_MODEL", "test-model");
+            std::env::set_var("NEARAI_BASE_URL", "https://test.near.ai/v1");
+        }
+
+        let result = build_llm_env_defaults();
+        let map = result.as_object().expect("should be an object");
+
+        // Check NEAR AI entry
+        let nearai = map
+            .get("nearai")
+            .and_then(|v| v.as_object())
+            .expect("nearai entry");
+        // API key should NOT be exposed — only has_api_key presence flag.
+        assert_eq!(
+            nearai.get("has_api_key").and_then(|v| v.as_bool()),
+            Some(true)
+        );
+        assert!(
+            nearai.get("api_key").is_none(),
+            "raw api_key must never be returned"
+        );
+        assert_eq!(
+            nearai.get("model").and_then(|v| v.as_str()),
+            Some("test-model")
+        );
+        assert_eq!(
+            nearai.get("base_url").and_then(|v| v.as_str()),
+            Some("https://test.near.ai/v1")
+        );
+
+        // Clean up
+        unsafe {
+            std::env::remove_var("NEARAI_API_KEY");
+            std::env::remove_var("NEARAI_MODEL");
+            std::env::remove_var("NEARAI_BASE_URL");
+        }
+    }
+
+    #[tokio::test]
+    async fn test_llm_env_defaults_includes_registry_providers() {
+        let result = build_llm_env_defaults();
+        let map = result.as_object().expect("should be an object");
+
+        // Registry providers should be present (openai, anthropic, ollama, etc.)
+        assert!(map.contains_key("openai"), "should contain openai");
+        assert!(map.contains_key("anthropic"), "should contain anthropic");
+        assert!(map.contains_key("ollama"), "should contain ollama");
+
+        // Each entry should have has_api_key field
+        for (id, val) in map {
+            assert!(val.is_object(), "{id} should be an object");
+        }
+    }
+
     // --- OAuth callback handler tests ---
 
     /// Build a minimal `GatewayState` for testing the OAuth callback handler.
@@ -3131,6 +3452,7 @@ mod tests {
             job_manager: None,
             prompt_queue: None,
             owner_id: "test".to_string(),
+            default_sender_id: "test".to_string(),
             shutdown_tx: tokio::sync::RwLock::new(None),
             ws_tracker: None,
             llm_provider: None,
@@ -3146,7 +3468,6 @@ mod tests {
             startup_time: std::time::Instant::now(),
             active_config: ActiveConfigSnapshot::default(),
             secrets_store: None,
-            db_auth: None,
         })
     }
 
@@ -3367,7 +3688,6 @@ mod tests {
         // without needing the full auth middleware layer.
         req.extensions_mut().insert(UserIdentity {
             user_id: "test".to_string(),
-            role: "admin".to_string(),
             workspace_read_scopes: Vec::new(),
         });
 
@@ -3452,7 +3772,6 @@ mod tests {
         // without needing the full auth middleware layer.
         req.extensions_mut().insert(UserIdentity {
             user_id: "test".to_string(),
-            role: "admin".to_string(),
             workspace_read_scopes: Vec::new(),
         });
 
@@ -3502,10 +3821,7 @@ mod tests {
         let state = test_gateway_state(None);
 
         let addr: SocketAddr = "127.0.0.1:0".parse().unwrap();
-        let auth = CombinedAuthState::from(crate::channels::web::auth::MultiAuthState::single(
-            "test-token".to_string(),
-            "test".to_string(),
-        ));
+        let auth = MultiAuthState::single("test-token".to_string(), "test".to_string());
         let bound = start_server(addr, state.clone(), auth)
             .await
             .expect("server should start");
@@ -4458,4 +4774,35 @@ mod tests {
         assert!(!is_local_origin("not-a-url"));
         assert!(!is_local_origin(""));
     }
+
+    // --- is_nearai_private_endpoint tests ---
+
+    #[test]
+    fn test_nearai_private_exact_match() {
+        assert!(is_nearai_private_endpoint("https://private.near.ai/v1"));
+    }
+
+    #[test]
+    fn test_nearai_private_subdomain() {
+        assert!(is_nearai_private_endpoint("https://us.private.near.ai/v1"));
+    }
+
+    #[test]
+    fn test_nearai_public_endpoint_not_private() {
+        assert!(!is_nearai_private_endpoint("https://cloud-api.near.ai/v1"));
+    }
+
+    #[test]
+    fn test_nearai_private_lookalike_rejected() {
+        // "private" appears in the hostname but not as the correct domain
+        assert!(!is_nearai_private_endpoint(
+            "https://private-evil.near.ai/v1"
+        ));
+        assert!(!is_nearai_private_endpoint("https://myprivate.near.ai/v1"));
+    }
+
+    #[test]
+    fn test_nearai_private_non_near_ai_rejected() {
+        assert!(!is_nearai_private_endpoint("https://private.evil.com/v1"));
+    }
 }

src/channels/web/static/app.js

@@ -186,13 +186,6 @@ function authenticate() {
       connectSSE();
       connectLogSSE();
       startGatewayStatusPolling();
-      // Hide the Users settings tab for non-admin users.
-      apiFetch('/api/profile').then(function(profile) {
-        if (profile && profile.role !== 'admin') {
-          var usersTab = document.querySelector('[data-settings-subtab="users"]');
-          if (usersTab) usersTab.style.display = 'none';
-        }
-      }).catch(function() {});
       checkTeeStatus();
       loadThreads();
       loadMemoryTree();
@@ -4346,165 +4339,6 @@ function formatRelativeTime(isoString) {
   return future ? I18n.t('time.daysFromNow', { n: days }) : I18n.t('time.daysAgo', { n: days });
 }
 
-// --- Users (admin) ---
-
-function loadUsers() {
-  apiFetch('/api/admin/users').then(function(data) {
-    renderUsersList(data.users || []);
-  }).catch(function(err) {
-    var tbody = document.getElementById('users-tbody');
-    var empty = document.getElementById('users-empty');
-    if (tbody) tbody.innerHTML = '';
-    if (empty) {
-      empty.style.display = 'block';
-      if (err.status === 403 || err.status === 401) {
-        empty.textContent = I18n.t('users.adminRequired');
-      } else {
-        empty.textContent = I18n.t('users.failedToLoad') + ': ' + err.message;
-      }
-    }
-  });
-}
-
-function renderUsersList(users) {
-  var tbody = document.getElementById('users-tbody');
-  var empty = document.getElementById('users-empty');
-  if (!users || users.length === 0) {
-    tbody.innerHTML = '';
-    empty.style.display = 'block';
-    empty.textContent = I18n.t('users.emptyState');
-    return;
-  }
-  empty.style.display = 'none';
-  tbody.innerHTML = users.map(function(u) {
-    var statusClass = u.status === 'active' ? 'active' : 'failed';
-    var roleLabel = u.role === 'admin' ? '<span class="badge badge-admin">' + I18n.t('users.roleAdmin') + '</span>' : '<span class="badge">' + I18n.t('users.roleMember') + '</span>';
-    var actions = '';
-    if (u.status === 'active') {
-      actions += '<button class="btn-small btn-danger" data-action="suspend-user" data-user-id="' + escapeHtml(u.id) + '">' + I18n.t('users.suspend') + '</button> ';
-    } else {
-      actions += '<button class="btn-small btn-primary" data-action="activate-user" data-user-id="' + escapeHtml(u.id) + '">' + I18n.t('users.activate') + '</button> ';
-    }
-    if (u.role === 'member') {
-      actions += '<button class="btn-small" data-action="change-role" data-user-id="' + escapeHtml(u.id) + '" data-role="admin">' + I18n.t('users.makeAdmin') + '</button> ';
-    } else {
-      actions += '<button class="btn-small" data-action="change-role" data-user-id="' + escapeHtml(u.id) + '" data-role="member">' + I18n.t('users.makeMember') + '</button> ';
-    }
-    actions += '<button class="btn-small" data-action="create-token" data-user-id="' + escapeHtml(u.id) + '" data-user-name="' + escapeHtml(u.display_name) + '">' + I18n.t('users.addToken') + '</button>';
-    return '<tr>'
-      + '<td class="user-id" title="' + escapeHtml(u.id) + '">' + escapeHtml(u.id.substring(0, 8)) + '…</td>'
-      + '<td>' + escapeHtml(u.display_name) + '</td>'
-      + '<td>' + escapeHtml(u.email || '—') + '</td>'
-      + '<td>' + roleLabel + '</td>'
-      + '<td><span class="status-badge ' + statusClass + '">' + escapeHtml(u.status) + '</span></td>'
-      + '<td>' + (u.job_count || 0) + '</td>'
-      + '<td>' + formatCost(u.total_cost) + '</td>'
-      + '<td>' + (u.last_active_at ? formatRelativeTime(u.last_active_at) : '—') + '</td>'
-      + '<td>' + formatRelativeTime(u.created_at) + '</td>'
-      + '<td>' + actions + '</td>'
-      + '</tr>';
-  }).join('');
-}
-
-function suspendUser(userId) {
-  apiFetch('/api/admin/users/' + userId + '/suspend', { method: 'POST' })
-    .then(function() { loadUsers(); })
-    .catch(function(e) { alert(I18n.t('users.failedSuspend') + ': ' + e.message); });
-}
-
-function activateUser(userId) {
-  apiFetch('/api/admin/users/' + userId + '/activate', { method: 'POST' })
-    .then(function() { loadUsers(); })
-    .catch(function(e) { alert(I18n.t('users.failedActivate') + ': ' + e.message); });
-}
-
-function changeUserRole(userId, newRole) {
-  apiFetch('/api/admin/users/' + userId, {
-    method: 'PATCH',
-    headers: { 'Content-Type': 'application/json' },
-    body: JSON.stringify({ role: newRole })
-  })
-    .then(function() { loadUsers(); })
-    .catch(function(e) { alert(I18n.t('users.failedRoleChange') + ': ' + e.message); });
-}
-
-function createTokenForUser(userId, displayName) {
-  var tokenName = prompt('Token name for ' + displayName + ':', 'api-token');
-  if (!tokenName) return;
-  apiFetch('/api/tokens', {
-    method: 'POST',
-    headers: { 'Content-Type': 'application/json' },
-    body: JSON.stringify({ name: tokenName, user_id: userId }),
-  }).then(function(data) {
-    showTokenBanner(data.token, I18n.t('users.tokenCreated'));
-  }).catch(function(e) { alert(I18n.t('users.failedCreate') + ': ' + e.message); });
-}
-
-function showTokenBanner(tokenValue, title) {
-  var banner = document.getElementById('users-token-result');
-  if (!banner) return;
-  var heading = title || I18n.t('users.tokenCreated');
-  var loginUrl = window.location.origin + '/?token=' + encodeURIComponent(tokenValue);
-  banner.style.display = 'block';
-  banner.innerHTML = '<strong>' + escapeHtml(heading) + '</strong> ' + I18n.t('users.tokenShareMessage') + '<br>'
-    + '<code class="token-display" id="token-copy-value">' + escapeHtml(loginUrl) + '</code>'
-    + '<button class="btn-small" id="token-copy-link">Copy Link</button>'
-    + '<br><span style="font-size:0.8em;color:var(--text-muted)">' + I18n.t('users.rawToken') + ' ' + escapeHtml(tokenValue) + '</span>';
-  document.getElementById('token-copy-link').addEventListener('click', function() {
-    navigator.clipboard.writeText(loginUrl);
-    this.textContent = I18n.t('users.copied');
-  });
-}
-
-// Delegated click handler for user action buttons (CSP-safe, no inline onclick)
-document.getElementById('users-table')?.addEventListener('click', function(e) {
-  var btn = e.target.closest('[data-action]');
-  if (!btn) return;
-  var action = btn.getAttribute('data-action');
-  var userId = btn.getAttribute('data-user-id');
-  var userName = btn.getAttribute('data-user-name');
-  if (action === 'suspend-user') suspendUser(userId);
-  else if (action === 'activate-user') activateUser(userId);
-  else if (action === 'change-role') changeUserRole(userId, btn.getAttribute('data-role'));
-  else if (action === 'create-token') createTokenForUser(userId, userName || '');
-});
-
-// Wire up Users tab create form
-document.getElementById('users-create-btn')?.addEventListener('click', function() {
-  document.getElementById('users-create-form').style.display = 'flex';
-  document.getElementById('users-token-result').style.display = 'none';
-  document.getElementById('user-display-name').focus();
-});
-
-document.getElementById('users-create-cancel')?.addEventListener('click', function() {
-  document.getElementById('users-create-form').style.display = 'none';
-});
-
-document.getElementById('users-create-submit')?.addEventListener('click', function() {
-  var displayName = document.getElementById('user-display-name').value.trim();
-  var email = document.getElementById('user-email').value.trim();
-  var role = document.getElementById('user-role').value;
-  if (!displayName) { alert(I18n.t('users.displayNameRequired')); return; }
-
-  apiFetch('/api/admin/users', {
-    method: 'POST',
-    headers: { 'Content-Type': 'application/json' },
-    body: JSON.stringify({
-      display_name: displayName,
-      email: email || undefined,
-      role: role,
-    }),
-  }).then(function(data) {
-    document.getElementById('users-create-form').style.display = 'none';
-    document.getElementById('user-display-name').value = '';
-    document.getElementById('user-email').value = '';
-    if (data.token) {
-      showTokenBanner(data.token, I18n.t('users.userCreated'));
-    }
-    loadUsers();
-  }).catch(function(e) { alert(I18n.t('users.failedCreate') + ': ' + e.message); });
-});
-
 // --- Gateway status widget ---
 
 let gatewayStatusInterval = null;
@@ -5194,32 +5028,12 @@ function loadSettingsSubtab(subtab) {
   else if (subtab === 'extensions') { loadExtensions(); startPairingPoll(); }
   else if (subtab === 'mcp') loadMcpServers();
   else if (subtab === 'skills') loadSkills();
-  else if (subtab === 'users') loadUsers();
   if (subtab !== 'extensions' && subtab !== 'channels') stopPairingPoll();
 }
 
 // --- Structured Settings Definitions ---
 
 var INFERENCE_SETTINGS = [
-  {
-    group: 'cfg.group.llm',
-    settings: [
-      { key: 'llm_backend', label: 'cfg.llm_backend.label', description: 'cfg.llm_backend.desc',
-        type: 'select', options: ['nearai', 'anthropic', 'openai', 'ollama', 'openai_compatible', 'tinfoil', 'bedrock'] },
-      { key: 'selected_model', label: 'cfg.selected_model.label', description: 'cfg.selected_model.desc', type: 'text' },
-      { key: 'ollama_base_url', label: 'cfg.ollama_base_url.label', description: 'cfg.ollama_base_url.desc', type: 'text',
-        showWhen: { key: 'llm_backend', value: 'ollama' } },
-      { key: 'openai_compatible_base_url', label: 'cfg.openai_compatible_base_url.label', description: 'cfg.openai_compatible_base_url.desc', type: 'text',
-        showWhen: { key: 'llm_backend', value: 'openai_compatible' } },
-      { key: 'bedrock_region', label: 'cfg.bedrock_region.label', description: 'cfg.bedrock_region.desc', type: 'text',
-        showWhen: { key: 'llm_backend', value: 'bedrock' } },
-      { key: 'bedrock_cross_region', label: 'cfg.bedrock_cross_region.label', description: 'cfg.bedrock_cross_region.desc',
-        type: 'select', options: ['us', 'eu', 'apac', 'global'],
-        showWhen: { key: 'llm_backend', value: 'bedrock' } },
-      { key: 'bedrock_profile', label: 'cfg.bedrock_profile.label', description: 'cfg.bedrock_profile.desc', type: 'text',
-        showWhen: { key: 'llm_backend', value: 'bedrock' } },
-    ]
-  },
   {
     group: 'cfg.group.embeddings',
     settings: [
@@ -5342,31 +5156,64 @@ function loadInferenceSettings() {
   Promise.all([
     apiFetch('/api/settings/export'),
     apiFetch('/api/gateway/status').catch(function() { return {}; }),
-    apiFetch('/v1/models').catch(function() { return { data: [] }; })
   ]).then(function(results) {
     var settings = results[0].settings || {};
     var status = results[1];
-    var modelsData = results[2];
-    var activeValues = {
-      'llm_backend': status.llm_backend,
-      'selected_model': status.llm_model
-    };
-    // Inject available model IDs as suggestions for the selected_model field
-    var modelIds = (modelsData.data || []).map(function(m) { return m.id; }).filter(Boolean);
-    if (modelIds.length > 0) {
-      var llmGroup = INFERENCE_SETTINGS[0];
-      for (var i = 0; i < llmGroup.settings.length; i++) {
-        if (llmGroup.settings[i].key === 'selected_model') {
-          llmGroup.settings[i].suggestions = modelIds;
-          break;
-        }
-      }
-    }
     container.innerHTML = '';
-    renderStructuredSettingsInto(container, INFERENCE_SETTINGS, settings, activeValues);
+
+    // LLM Provider display — derived from active Model Provider
+    var activeBackend = settings['llm_backend'] || status.llm_backend || 'nearai';
+    var activeModel = settings['selected_model'] || status.llm_model || '';
+    var allP = (typeof BUILTIN_PROVIDERS !== 'undefined' ? BUILTIN_PROVIDERS : []);
+    var customP = [];
+    try {
+      var cpVal = settings['llm_custom_providers'];
+      customP = Array.isArray(cpVal) ? cpVal : (cpVal ? JSON.parse(cpVal) : []);
+    } catch (e) { customP = []; }
+    var provider = allP.concat(customP).find(function(p) { return p.id === activeBackend; });
+    var providerName = provider ? (provider.name || provider.id) : activeBackend;
+    if (!activeModel && provider) activeModel = provider.default_model || '';
+
+    var group = document.createElement('div');
+    group.className = 'settings-group';
+    var title = document.createElement('div');
+    title.className = 'settings-group-title';
+    title.textContent = I18n.t('cfg.group.llm');
+    group.appendChild(title);
+
+    var notice = document.createElement('div');
+    notice.className = 'config-notice';
+    notice.id = 'llm-restart-notice';
+    var restartNoticeEl = document.getElementById('config-restart-notice');
+    notice.style.display = (restartNoticeEl && restartNoticeEl.style.display !== 'none') ? 'flex' : 'none';
+    notice.innerHTML = '<span>\u26A0</span><span>' + escapeHtml(I18n.t('config.restartNotice')) + '</span>';
+    group.appendChild(notice);
+
+    var backendRow = document.createElement('div');
+    backendRow.className = 'settings-row';
+    backendRow.innerHTML =
+      '<div class="settings-label-wrap"><label class="settings-label">' + escapeHtml(I18n.t('cfg.llm_backend.label')) + '</label>' +
+      '<div class="settings-description">' + escapeHtml(I18n.t('cfg.llm_backend.desc')) + '</div></div>' +
+      '<div class="settings-display-value">' + escapeHtml(providerName) + '</div>';
+    group.appendChild(backendRow);
+
+    var modelRow = document.createElement('div');
+    modelRow.className = 'settings-row';
+    modelRow.innerHTML =
+      '<div class="settings-label-wrap"><label class="settings-label">' + escapeHtml(I18n.t('cfg.selected_model.label')) + '</label>' +
+      '<div class="settings-description">' + escapeHtml(I18n.t('cfg.selected_model.desc')) + '</div></div>' +
+      '<div class="settings-display-value">' + escapeHtml(activeModel || '\u2014') + '</div>';
+    group.appendChild(modelRow);
+
+    container.appendChild(group);
+
+    // Remaining editable settings (embeddings, etc.)
+    renderStructuredSettingsInto(container, INFERENCE_SETTINGS, settings, {});
+    loadConfig();
   }).catch(function(err) {
     container.innerHTML = '<div class="empty-state">' + I18n.t('common.loadFailed') + ': '
       + escapeHtml(err.message) + '</div>';
+    loadConfig();
   });
 }
 
@@ -5610,8 +5457,7 @@ function renderStructuredSettingsRow(def, value, activeValue) {
   return row;
 }
 
-var RESTART_REQUIRED_KEYS = ['llm_backend', 'selected_model', 'ollama_base_url', 'openai_compatible_base_url',
-  'bedrock_region', 'bedrock_cross_region', 'bedrock_profile', 'embeddings.enabled', 'embeddings.provider', 'embeddings.model',
+var RESTART_REQUIRED_KEYS = ['embeddings.enabled', 'embeddings.provider', 'embeddings.model',
   'agent.auto_approve_tools', 'tunnel.provider', 'tunnel.public_url', 'gateway.rate_limit', 'gateway.max_connections'];
 
 var _settingsSavedTimers = {};
@@ -6196,6 +6042,18 @@ document.addEventListener('click', function(e) {
     case 'switch-language':
       if (typeof switchLanguage === 'function') switchLanguage(el.dataset.lang);
       break;
+    case 'set-active-provider':
+      setActiveProvider(el.dataset.id);
+      break;
+    case 'delete-custom-provider':
+      deleteCustomProvider(el.dataset.id);
+      break;
+    case 'edit-custom-provider':
+      editCustomProvider(el.dataset.id);
+      break;
+    case 'configure-builtin-provider':
+      configureBuiltinProvider(el.dataset.id);
+      break;
   }
 });
 
@@ -6237,6 +6095,9 @@ document.addEventListener('keydown', function(e) {
   if (e.key === 'Escape' && document.getElementById('confirm-modal').style.display === 'flex') {
     closeConfirmModal();
   }
+  if (e.key === 'Escape' && document.getElementById('provider-dialog').style.display === 'flex') {
+    resetProviderForm();
+  }
 });
 
 // --- Settings Import/Export ---
@@ -6324,3 +6185,583 @@ document.getElementById('settings-search-input').addEventListener('input', funct
     activePanel.appendChild(empty);
   }
 });
+
+
+// --- Config Tab ---
+
+// Like apiFetch but for endpoints that return 204 No Content
+function apiFetchVoid(path, options) {
+  const opts = options || {};
+  opts.headers = opts.headers || {};
+  opts.headers['Authorization'] = 'Bearer ' + token;
+  if (opts.body && typeof opts.body === 'object') {
+    opts.headers['Content-Type'] = 'application/json';
+    opts.body = JSON.stringify(opts.body);
+  }
+  return fetch(path, opts).then((res) => {
+    if (!res.ok) {
+      return res.text().then((body) => { throw new Error(body || (res.status + ' ' + res.statusText)); });
+    }
+  });
+}
+
+// BUILTIN_PROVIDERS and ADAPTER_LABELS are defined in /providers.js
+
+let _customProviders = [];
+let _activeLlmBackend = '';
+let _selectedModel = '';
+let _builtinOverrides = {};
+let _editingProviderId = null;
+let _configuringBuiltinId = null;
+let _configLoaded = false;
+let _envDefaults = {};
+
+function loadConfig() {
+  const list = document.getElementById('providers-list');
+  list.innerHTML = '<div class="empty-state">' + I18n.t('common.loading') + '</div>';
+
+  Promise.all([
+    apiFetch('/api/settings/export'),
+    apiFetch('/api/llm/env_defaults').catch(() => ({})),
+  ]).then(([d, envDefs]) => {
+    const s = (d && d.settings) ? d.settings : {};
+    _activeLlmBackend = s['llm_backend'] ? String(s['llm_backend']) : 'nearai';
+    _selectedModel = s['selected_model'] ? String(s['selected_model']) : '';
+    try {
+      const val = s['llm_custom_providers'];
+      _customProviders = Array.isArray(val) ? val : (val ? JSON.parse(val) : []);
+    } catch (e) {
+      _customProviders = [];
+    }
+    try {
+      const val = s['llm_builtin_overrides'];
+      _builtinOverrides = (val && typeof val === 'object' && !Array.isArray(val)) ? val : {};
+    } catch (e) {
+      _builtinOverrides = {};
+    }
+    _envDefaults = (envDefs && typeof envDefs === 'object') ? envDefs : {};
+    _configLoaded = true;
+    renderProviders();
+  }).catch(() => {
+    _activeLlmBackend = 'nearai';
+    _selectedModel = '';
+    _customProviders = [];
+    _builtinOverrides = {};
+    _envDefaults = {};
+    _configLoaded = true;
+    renderProviders();
+  });
+}
+
+function scrollToProviders() {
+  const section = document.getElementById('providers-section');
+  if (section) section.scrollIntoView({ behavior: 'smooth', block: 'start' });
+}
+
+function renderProviders() {
+  const list = document.getElementById('providers-list');
+  const allProviders = [...BUILTIN_PROVIDERS, ..._customProviders].sort((a, b) => {
+    if (a.id === _activeLlmBackend) return -1;
+    if (b.id === _activeLlmBackend) return 1;
+    return 0;
+  });
+
+  if (allProviders.length === 0) {
+    list.innerHTML = '<div class="empty-state">No providers</div>';
+    return;
+  }
+
+  list.innerHTML = allProviders.map((p) => {
+    const isActive = p.id === _activeLlmBackend;
+    const adapterLabel = ADAPTER_LABELS[p.adapter] || p.adapter;
+    const activeBadge = isActive
+      ? '<span class="provider-badge provider-badge-active">' + I18n.t('status.active') + '</span>'
+      : '';
+    const builtinBadge = p.builtin
+      ? '<span class="provider-badge provider-badge-builtin">' + I18n.t('config.builtin') + '</span>'
+      : '';
+    const deleteBtn = !p.builtin && !isActive
+      ? '<button class="provider-action-btn provider-delete-btn" data-action="delete-custom-provider" data-id="' + escapeHtml(p.id) + '">' + I18n.t('common.delete') + '</button>'
+      : '';
+    const editBtn = !p.builtin
+      ? '<button class="provider-action-btn" data-action="edit-custom-provider" data-id="' + escapeHtml(p.id) + '">' + I18n.t('common.edit') + '</button>'
+      : '';
+    // Show Configure for built-in providers that support it (not bedrock — uses AWS credential chain)
+    const configureBtn = p.builtin && p.id !== 'bedrock'
+      ? '<button class="provider-action-btn" data-action="configure-builtin-provider" data-id="' + escapeHtml(p.id) + '">' + I18n.t('config.configureProvider') + '</button>'
+      : '';
+    const useBtn = !isActive
+      ? '<button class="provider-action-btn" data-action="set-active-provider" data-id="' + escapeHtml(p.id) + '">' + I18n.t('config.useProvider') + '</button>'
+      : '';
+    const envDef = _envDefaults[p.id] || {};
+    const overrideBaseUrl = p.builtin && _builtinOverrides[p.id] ? (_builtinOverrides[p.id].base_url || '') : '';
+    const effectiveBaseUrl = overrideBaseUrl || envDef.base_url || p.base_url;
+    const baseUrlText = effectiveBaseUrl
+      ? '<span class="provider-url">' + escapeHtml(effectiveBaseUrl) + '</span>'
+      : '';
+    // Show configured model: for active provider use _selectedModel, for others check _builtinOverrides then env defaults
+    const overrideModel = p.builtin && _builtinOverrides[p.id] ? (_builtinOverrides[p.id].model || '') : '';
+    const displayModel = isActive
+      ? (_selectedModel || envDef.model || '')
+      : (overrideModel || envDef.model || '');
+    const modelText = displayModel
+      ? '<span class="provider-current-model">' + escapeHtml(I18n.t('config.currentModel', { model: displayModel })) + '</span>'
+      : '';
+
+    return '<div class="provider-card' + (isActive ? ' provider-card-active' : '') + '">'
+      + '<div class="provider-card-header">'
+      +   '<span class="provider-name">' + escapeHtml(p.name || p.id) + '</span>'
+      +   '<span class="provider-id-label">' + escapeHtml(p.id) + '</span>'
+      +   activeBadge + builtinBadge
+      + '</div>'
+      + '<div class="provider-card-meta">'
+      +   '<span class="provider-adapter">' + escapeHtml(adapterLabel) + '</span>'
+      +   baseUrlText
+      +   modelText
+      + '</div>'
+      + '<div class="provider-card-actions">'
+      +   useBtn + configureBtn + editBtn + deleteBtn
+      + '</div>'
+      + '</div>';
+  }).join('');
+}
+
+function setActiveProvider(id) {
+  const provider = [...BUILTIN_PROVIDERS, ..._customProviders].find((p) => p.id === id);
+  // Restore the last-configured model for this provider, falling back to the provider's default
+  const restoredModel =
+    (_builtinOverrides[id] && _builtinOverrides[id].model) ||
+    (provider && provider.default_model) ||
+    null;
+  const defaultModel = restoredModel;
+  const modelUpdate = () => defaultModel
+    ? apiFetchVoid('/api/settings/selected_model', { method: 'PUT', body: { value: defaultModel } })
+    : apiFetchVoid('/api/settings/selected_model', { method: 'DELETE' });
+  apiFetchVoid('/api/settings/llm_backend', { method: 'PUT', body: { value: id } })
+    .then(() => modelUpdate())
+    .then(() => {
+      _activeLlmBackend = id;
+      _selectedModel = defaultModel || '';
+      renderProviders();
+      loadInferenceSettings();
+      scrollToProviders();
+      document.getElementById('config-restart-notice').style.display = 'flex';
+      var llmNotice = document.getElementById('llm-restart-notice');
+      if (llmNotice) llmNotice.style.display = 'flex';
+      showToast(I18n.t('config.providerActivated', { name: id }));
+    })
+    .catch((e) => showToast(I18n.t('error.unknown') + ': ' + e.message, 'error'));
+}
+
+function deleteCustomProvider(id) {
+  if (id === _activeLlmBackend) {
+    showToast(I18n.t('config.cannotDeleteActiveProvider'), 'error');
+    return;
+  }
+  if (!confirm(I18n.t('config.confirmDeleteProvider', { id }))) return;
+  const originalProviders = _customProviders;
+  _customProviders = _customProviders.filter((p) => p.id !== id);
+  saveCustomProviders().then(() => {
+    renderProviders();
+    showToast(I18n.t('config.providerDeleted'));
+  }).catch((e) => {
+    _customProviders = originalProviders;
+    showToast(I18n.t('error.unknown') + ': ' + e.message, 'error');
+  });
+}
+
+function saveCustomProviders() {
+  return apiFetchVoid('/api/settings/llm_custom_providers', { method: 'PUT', body: { value: _customProviders } });
+}
+
+function editCustomProvider(id) {
+  const p = _customProviders.find((p) => p.id === id);
+  if (!p) return;
+  _editingProviderId = id;
+  const titleEl = document.getElementById('provider-form-title');
+  titleEl.textContent = I18n.t('config.editProvider');
+  titleEl.removeAttribute('data-i18n');
+  document.getElementById('provider-name').value = p.name || '';
+  const idField = document.getElementById('provider-id');
+  idField.value = p.id;
+  idField.readOnly = true;
+  idField.style.opacity = '0.6';
+  document.getElementById('provider-adapter').value = p.adapter || 'open_ai_completions';
+  document.getElementById('provider-base-url').value = p.base_url || '';
+  const editApiKeyInput = document.getElementById('provider-api-key');
+  if (p.api_key === '••••••••') {
+    editApiKeyInput.value = '';
+    editApiKeyInput.placeholder = 'Key configured (leave blank to keep)';
+  } else {
+    editApiKeyInput.value = '';
+    editApiKeyInput.placeholder = 'Enter API key';
+  }
+  document.getElementById('provider-model').value = p.default_model || '';
+  openProviderDialog(true);
+  document.getElementById('provider-name').focus();
+}
+
+function configureBuiltinProvider(id) {
+  const p = BUILTIN_PROVIDERS.find((p) => p.id === id);
+  if (!p) return;
+  _configuringBuiltinId = id;
+  const titleEl = document.getElementById('provider-form-title');
+  titleEl.textContent = I18n.t('config.configureProvider') + ': ' + (p.name || id);
+  titleEl.removeAttribute('data-i18n');
+  // Hide name/id/adapter rows; show base-url as editable
+  document.getElementById('provider-name-row').style.display = 'none';
+  document.getElementById('provider-id-row').style.display = 'none';
+  document.getElementById('provider-adapter-row').style.display = 'none';
+  const baseUrlInput = document.getElementById('provider-base-url');
+  const override = _builtinOverrides[id] || {};
+  const envDef = _envDefaults[id] || {};
+  // Priority: db override > env > hardcoded default
+  const effectiveBaseUrl = override.base_url || envDef.base_url || p.base_url;
+  document.getElementById('provider-base-url-row').style.display = '';
+  baseUrlInput.value = effectiveBaseUrl || '';
+  baseUrlInput.readOnly = false;
+  baseUrlInput.style.opacity = '';
+  baseUrlInput.placeholder = p.base_url || '';
+  document.getElementById('provider-api-key-row').style.display = p.api_key_required !== false ? '' : 'none';
+  document.getElementById('fetch-models-btn').style.display = p.can_list_models ? '' : 'none';
+  const apiKeyInput = document.getElementById('provider-api-key');
+  const hasDbKey = override.api_key === '••••••••';
+  const hasEnvKey = envDef.has_api_key === true;
+  apiKeyInput.value = '';
+  if (hasDbKey) {
+    apiKeyInput.placeholder = 'Key configured (leave blank to keep)';
+  } else if (hasEnvKey) {
+    apiKeyInput.placeholder = 'Key set via environment variable';
+  } else {
+    apiKeyInput.placeholder = 'Enter API key';
+  }
+  document.getElementById('provider-model').value = override.model || envDef.model || p.default_model || '';
+  openProviderDialog(true);
+  document.getElementById('provider-model').focus();
+}
+
+// Add provider form
+
+document.getElementById('add-provider-btn').addEventListener('click', () => {
+  openProviderDialog(false);
+});
+
+document.getElementById('cancel-provider-btn').addEventListener('click', () => {
+  resetProviderForm();
+});
+
+document.getElementById('cancel-provider-footer-btn').addEventListener('click', () => {
+  resetProviderForm();
+});
+
+document.getElementById('provider-dialog-overlay').addEventListener('click', () => {
+  resetProviderForm();
+});
+
+function openProviderDialog(isEdit) {
+  if (!isEdit) {
+    // Add mode: ensure all rows visible
+    ['provider-name-row', 'provider-id-row', 'provider-adapter-row',
+     'provider-base-url-row', 'provider-api-key-row'].forEach((id) => {
+      document.getElementById(id).style.display = '';
+    });
+    document.getElementById('fetch-models-btn').style.display = '';
+  }
+  document.getElementById('provider-dialog').style.display = 'flex';
+  if (!isEdit) {
+    document.getElementById('provider-name').focus();
+  }
+}
+
+document.getElementById('test-provider-btn').addEventListener('click', () => {
+  let adapter = document.getElementById('provider-adapter').value;
+  let baseUrl = document.getElementById('provider-base-url').value.trim();
+  const apiKey = document.getElementById('provider-api-key').value.trim();
+  const model = document.getElementById('provider-model').value.trim();
+
+  // For built-in providers, use the hardcoded adapter from BUILTIN_PROVIDERS.
+  // base_url comes from the form which already reflects: env > hardcoded default.
+  if (_configuringBuiltinId) {
+    const p = BUILTIN_PROVIDERS.find((x) => x.id === _configuringBuiltinId);
+    if (p) {
+      adapter = p.adapter;
+      if (!baseUrl) baseUrl = p.base_url;
+    }
+  }
+
+  const btn = document.getElementById('test-provider-btn');
+  const result = document.getElementById('test-connection-result');
+
+  btn.disabled = true;
+  btn.textContent = I18n.t('config.testing');
+  result.style.display = 'none';
+  result.className = 'test-connection-result';
+
+  // Resolve provider_id so the backend can look up vaulted API keys.
+  const providerId = _configuringBuiltinId || document.getElementById('provider-id').value.trim();
+
+  if (!model) {
+    result.textContent = I18n.t('config.modelRequired') || 'Model is required for connection test';
+    result.className = 'test-connection-result test-fail';
+    result.style.display = '';
+    btn.disabled = false;
+    btn.textContent = I18n.t('config.testConnection');
+    return;
+  }
+
+  apiFetch('/api/llm/test_connection', {
+    method: 'POST',
+    body: {
+      adapter, base_url: baseUrl,
+      api_key: apiKey || undefined,
+      model,
+      provider_id: providerId || undefined,
+      provider_type: _configuringBuiltinId ? 'builtin' : 'custom',
+    },
+  })
+    .then((data) => {
+      result.textContent = data.message;
+      result.className = 'test-connection-result ' + (data.ok ? 'test-ok' : 'test-fail');
+      result.style.display = '';
+    })
+    .catch((e) => {
+      result.textContent = e.message;
+      result.className = 'test-connection-result test-fail';
+      result.style.display = '';
+    })
+    .finally(() => {
+      btn.disabled = false;
+      btn.textContent = I18n.t('config.testConnection');
+    });
+});
+
+document.getElementById('save-provider-btn').addEventListener('click', () => {
+  // Built-in configure mode: save api_key + model to llm_builtin_overrides
+  if (_configuringBuiltinId) {
+    const apiKey = document.getElementById('provider-api-key').value.trim();
+    const model = document.getElementById('provider-model').value.trim();
+    const baseUrl = document.getElementById('provider-base-url').value.trim();
+    const id = _configuringBuiltinId;
+    const prevOverride = _builtinOverrides[id] || {};
+    const hadKey = prevOverride.api_key === '••••••••';
+    const override = {};
+    if (apiKey) {
+      override.api_key = apiKey;  // New key entered — backend will encrypt it
+    } else if (hadKey) {
+      override.api_key = '••••••••';  // Sentinel: keep existing encrypted key
+    }
+    // If neither — key is cleared (no key configured)
+    if (model) override.model = model;
+    if (baseUrl) override.base_url = baseUrl;
+    const prev = _builtinOverrides[id];
+    _builtinOverrides[id] = override;
+    const isActive = id === _activeLlmBackend;
+    const modelUpdate = () => {
+      if (!isActive) return Promise.resolve();
+      if (model) {
+        return apiFetchVoid('/api/settings/selected_model', { method: 'PUT', body: { value: model } });
+      }
+      return apiFetchVoid('/api/settings/selected_model', { method: 'DELETE' });
+    };
+    apiFetchVoid('/api/settings/llm_builtin_overrides', { method: 'PUT', body: { value: _builtinOverrides } })
+      .then(() => modelUpdate())
+      .then(() => {
+        if (isActive) _selectedModel = model;
+        renderProviders();
+        if (isActive) loadInferenceSettings();
+        resetProviderForm();
+        scrollToProviders();
+        if (isActive) {
+          document.getElementById('config-restart-notice').style.display = 'flex';
+          var llmNotice = document.getElementById('llm-restart-notice');
+          if (llmNotice) llmNotice.style.display = 'flex';
+        }
+        showToast(I18n.t('config.providerConfigured', { name: id }));
+      })
+      .catch((e) => {
+        if (prev !== undefined) { _builtinOverrides[id] = prev; } else { delete _builtinOverrides[id]; }
+        showToast(I18n.t('error.unknown') + ': ' + e.message, 'error');
+      });
+    return;
+  }
+
+  const name = document.getElementById('provider-name').value.trim();
+  const id = document.getElementById('provider-id').value.trim();
+  const adapter = document.getElementById('provider-adapter').value;
+  const baseUrl = document.getElementById('provider-base-url').value.trim();
+  const apiKey = document.getElementById('provider-api-key').value.trim();
+  const model = document.getElementById('provider-model').value.trim();
+
+  if (!id || !name) {
+    showToast(I18n.t('config.providerFieldsRequired'), 'error');
+    return;
+  }
+
+  if (_editingProviderId) {
+    // Update existing provider
+    const idx = _customProviders.findIndex((p) => p.id === _editingProviderId);
+    if (idx === -1) return;
+    const original = _customProviders[idx];
+    const hadCustomKey = original.api_key === '••••••••';
+    let effectiveApiKey;
+    if (apiKey) {
+      effectiveApiKey = apiKey;  // New key — backend will encrypt it
+    } else if (hadCustomKey) {
+      effectiveApiKey = '••••••••';  // Sentinel: keep existing encrypted key
+    } else {
+      effectiveApiKey = undefined;  // No key
+    }
+    _customProviders[idx] = { ...original, name, adapter, base_url: baseUrl, default_model: model || undefined, api_key: effectiveApiKey };
+    const isActive = _editingProviderId === _activeLlmBackend;
+    const modelUpdate = () => {
+      if (!isActive) return Promise.resolve();
+      if (model) {
+        return apiFetchVoid('/api/settings/selected_model', { method: 'PUT', body: { value: model } });
+      }
+      return apiFetchVoid('/api/settings/selected_model', { method: 'DELETE' });
+    };
+    saveCustomProviders().then(() => modelUpdate()).then(() => {
+      if (isActive) _selectedModel = model;
+      renderProviders();
+      if (isActive) loadInferenceSettings();
+      resetProviderForm();
+      scrollToProviders();
+      if (isActive) {
+        document.getElementById('config-restart-notice').style.display = 'flex';
+        var llmNotice = document.getElementById('llm-restart-notice');
+        if (llmNotice) llmNotice.style.display = 'flex';
+      }
+      showToast(I18n.t('config.providerUpdated', { name }));
+    }).catch((e) => {
+      _customProviders[idx] = original;
+      showToast(I18n.t('error.unknown') + ': ' + e.message, 'error');
+    });
+    return;
+  }
+
+  if (!/^[a-z0-9-]+$/.test(id)) {
+    showToast(I18n.t('config.providerIdInvalid'), 'error');
+    return;
+  }
+  const allIds = [...BUILTIN_PROVIDERS.map((p) => p.id), ..._customProviders.map((p) => p.id)];
+  if (allIds.includes(id)) {
+    showToast(I18n.t('config.providerIdTaken', { id }), 'error');
+    return;
+  }
+
+  const newProvider = { id, name, adapter, base_url: baseUrl, default_model: model, api_key: apiKey || undefined, builtin: false };
+  _customProviders.push(newProvider);
+
+  saveCustomProviders().then(() => {
+    renderProviders();
+    resetProviderForm();
+    scrollToProviders();
+    showToast(I18n.t('config.providerAdded', { name }));
+  }).catch((e) => {
+    _customProviders.pop();
+    showToast(I18n.t('error.unknown') + ': ' + e.message, 'error');
+  });
+});
+
+function resetProviderForm() {
+  _editingProviderId = null;
+  _configuringBuiltinId = null;
+  document.getElementById('provider-dialog').style.display = 'none';
+  // Restore all hidden rows and buttons
+  ['provider-name-row', 'provider-id-row', 'provider-adapter-row',
+   'provider-base-url-row', 'provider-api-key-row'].forEach((id) => {
+    document.getElementById(id).style.display = '';
+  });
+  document.getElementById('fetch-models-btn').style.display = '';
+  const titleEl = document.getElementById('provider-form-title');
+  titleEl.setAttribute('data-i18n', 'config.newProvider');
+  titleEl.textContent = I18n.t('config.newProvider');
+  const idField = document.getElementById('provider-id');
+  idField.readOnly = false;
+  idField.style.opacity = '';
+  delete idField.dataset.edited;
+  const baseUrlField = document.getElementById('provider-base-url');
+  baseUrlField.readOnly = false;
+  baseUrlField.style.opacity = '';
+  ['provider-name', 'provider-id', 'provider-base-url', 'provider-api-key', 'provider-model'].forEach((id) => {
+    document.getElementById(id).value = '';
+  });
+  document.getElementById('provider-adapter').selectedIndex = 0;
+  const sel = document.getElementById('provider-model-select');
+  sel.innerHTML = '';
+  sel.style.display = 'none';
+  document.getElementById('test-connection-result').style.display = 'none';
+}
+
+document.getElementById('provider-model-select').addEventListener('change', (e) => {
+  document.getElementById('provider-model').value = e.target.value;
+});
+
+document.getElementById('fetch-models-btn').addEventListener('click', () => {
+  let adapter = document.getElementById('provider-adapter').value;
+  let baseUrl = document.getElementById('provider-base-url').value.trim();
+  const apiKey = document.getElementById('provider-api-key').value.trim();
+
+  // For built-in providers, use the hardcoded adapter from BUILTIN_PROVIDERS.
+  // base_url comes from the form which already reflects: env > hardcoded default.
+  if (_configuringBuiltinId) {
+    const p = BUILTIN_PROVIDERS.find((x) => x.id === _configuringBuiltinId);
+    if (p) {
+      adapter = p.adapter;
+      if (!baseUrl) baseUrl = p.base_url;
+    }
+  }
+
+  if (!baseUrl) {
+    showToast(I18n.t('config.providerBaseUrlRequired'), 'error');
+    return;
+  }
+
+  const btn = document.getElementById('fetch-models-btn');
+  btn.disabled = true;
+  btn.textContent = I18n.t('config.fetchingModels');
+
+  // Resolve provider_id so the backend can look up vaulted API keys.
+  const providerId = _configuringBuiltinId || document.getElementById('provider-id').value.trim();
+
+  apiFetch('/api/llm/list_models', {
+    method: 'POST',
+    body: {
+      adapter, base_url: baseUrl,
+      api_key: apiKey || undefined,
+      provider_id: providerId || undefined,
+      provider_type: _configuringBuiltinId ? 'builtin' : 'custom',
+    },
+  })
+    .then((data) => {
+      const select = document.getElementById('provider-model-select');
+      if (data.ok && data.models && data.models.length > 0) {
+        const currentModel = document.getElementById('provider-model').value;
+        select.innerHTML = data.models
+          .map((m) => `<option value="${escapeHtml(m)}"${m === currentModel ? ' selected' : ''}>${escapeHtml(m)}</option>`)
+          .join('');
+        select.style.display = '';
+        btn.style.display = 'none';
+        showToast(I18n.t('config.modelsFetched', { count: data.models.length }));
+      } else {
+        showToast(data.message || I18n.t('config.modelsFetchFailed'), 'error');
+      }
+    })
+    .catch((e) => showToast(e.message, 'error'))
+    .finally(() => {
+      btn.disabled = false;
+      btn.textContent = I18n.t('config.fetchModels');
+    });
+});
+
+// Auto-fill provider ID from name
+document.getElementById('provider-name').addEventListener('input', (e) => {
+  const idField = document.getElementById('provider-id');
+  if (!idField.dataset.edited) {
+    idField.value = e.target.value.toLowerCase().replace(/[^a-z0-9]+/g, '-').replace(/^-|-$/g, '');
+  }
+});
+
+document.getElementById('provider-id').addEventListener('input', (e) => {
+  e.target.dataset.edited = e.target.value ? '1' : '';
+});

src/channels/web/static/i18n-app.js

@@ -35,16 +35,27 @@ function switchLanguage(lang) {
   if (I18n.setLanguage(lang)) {
     // Update slash commands
     updateSlashCommands();
-    
+
     // Update language menu active state
     updateLanguageMenu();
-    
+
+    // Re-render dynamically built sections that use I18n.t()
+    if (typeof renderProviders === 'function' && typeof _configLoaded !== 'undefined' && _configLoaded) {
+      renderProviders();
+    }
+    if (typeof loadInferenceSettings === 'function') {
+      var inferencePanel = document.getElementById('settings-inference');
+      if (inferencePanel && inferencePanel.classList.contains('active')) {
+        loadInferenceSettings();
+      }
+    }
+
     // Close menu
     const menu = document.getElementById('language-menu');
     if (menu) {
       menu.style.display = 'none';
     }
-    
+
     // Show toast notification
     showToast(I18n.t('language.switch') + ': ' + (lang === 'zh-CN' ? '简体中文' : 'English'));
   }

src/channels/web/static/i18n/en.js

@@ -9,6 +9,8 @@ I18n.register('en', {
   'auth.connect': 'Connect',
   'auth.errorRequired': 'Token required',
   'auth.errorInvalid': 'Invalid token',
+  'auth.hint': 'Enter the GATEWAY_AUTH_TOKEN from your .env file',
+  
   // Chat
   'chat.inputPlaceholder': 'Message or / for commands...',
   
@@ -36,52 +38,15 @@ I18n.register('en', {
   'tab.settings': 'Settings',
   'tab.extensions': 'Extensions',
   'tab.skills': 'Skills',
+  'tab.config': 'Config',
   'tab.logs': 'Logs',
   'settings.inference': 'Inference',
   'settings.agent': 'Agent',
   'settings.channels': 'Channels',
   'settings.networking': 'Networking',
   'settings.mcp': 'MCP',
-  'settings.users': 'Users',
-
-  // Users Tab
-  'users.heading': 'User Management',
-  'users.newUser': '+ New User',
-  'users.displayNamePlaceholder': 'Display name',
-  'users.emailPlaceholder': 'Email (optional)',
-  'users.roleMember': 'Member',
-  'users.roleAdmin': 'Admin',
-  'users.create': 'Create',
-  'users.cancel': 'Cancel',
-  'users.emptyState': 'No users found. Create the first user to get started.',
-  'users.adminRequired': 'Admin access required to manage users.',
-  'users.failedToLoad': 'Failed to load users',
-  'users.suspend': 'Suspend',
-  'users.activate': 'Activate',
-  'users.addToken': '+ Token',
-  'users.failedSuspend': 'Failed to suspend user',
-  'users.failedActivate': 'Failed to activate user',
-  'users.makeAdmin': 'Make Admin',
-  'users.makeMember': 'Make Member',
-  'users.failedRoleChange': 'Failed to change role',
-  'users.userCreated': 'User created!',
-  'users.tokenCreated': 'Token created!',
-  'users.tokenShareMessage': "Share this login link — it won't be shown again:",
-  'users.rawToken': 'Raw token:',
-  'users.copied': 'Copied!',
-  'users.displayNameRequired': 'Display name is required',
-  'users.failedCreate': 'Failed to create user',
-  'users.columns.id': 'ID',
-  'users.columns.displayName': 'Display Name',
-  'users.columns.email': 'Email',
-  'users.columns.role': 'Role',
-  'users.columns.status': 'Status',
-  'users.columns.jobs': 'Jobs',
-  'users.columns.cost': 'Cost',
-  'users.columns.lastActive': 'Last Active',
-  'users.columns.created': 'Created',
-  'users.columns.actions': 'Actions',
-
+  'settings.providers': 'Providers',
+  
   // Status
   'status.connected': 'Connected',
   'status.disconnected': 'Disconnected',
@@ -387,6 +352,45 @@ I18n.register('en', {
   'ext.removed': 'Removed {name}',
   'ext.installFailed': 'Install failed: {message}',
   
+  // Config Tab — Model Providers
+  'config.modelProviders': 'Model Providers',
+  'config.addProvider': '+ Add Provider',
+  'config.newProvider': 'New Provider',
+  'config.restartNotice': 'Changes take effect after restart.',
+  'config.builtin': 'built-in',
+  'config.useProvider': 'Use',
+  'config.configureProvider': 'Configure',
+  'config.providerConfigured': 'Provider "{name}" configured (restart to apply)',
+  'config.currentModel': 'Model: {model}',
+  'config.providerName': 'Display Name',
+  'config.providerNamePlaceholder': 'My Provider',
+  'config.providerId': 'Provider ID',
+  'config.providerIdPlaceholder': 'my-provider',
+  'config.providerIdHint': 'Lowercase letters, numbers, hyphens',
+  'config.providerAdapter': 'API Adapter',
+  'config.adapterOpenAI': 'OpenAI Compatible',
+  'config.adapterAnthropic': 'Anthropic',
+  'config.adapterOllama': 'Ollama',
+  'config.providerBaseUrl': 'Base URL',
+  'config.providerApiKey': 'API Key',
+  'config.providerModel': 'Default Model',
+  'config.providerActivated': 'Switched to {name} (restart to apply)',
+  'config.providerAdded': 'Added provider "{name}" (restart to apply)',
+  'config.providerUpdated': 'Provider "{name}" updated (restart to apply)',
+  'config.editProvider': 'Edit Provider',
+  'config.providerDeleted': 'Provider deleted',
+  'config.confirmDeleteProvider': 'Delete provider "{id}"?',
+  'config.cannotDeleteActiveProvider': 'Cannot delete the active provider. Switch to another provider first.',
+  'config.testConnection': 'Test',
+  'config.testing': 'Testing…',
+  'config.fetchModels': 'Fetch available models',
+  'config.modelsFetched': '{count} model(s) loaded — type to filter',
+  'config.modelsFetchFailed': 'Failed to fetch models',
+  'config.providerBaseUrlRequired': 'Base URL is required to fetch models',
+  'config.providerFieldsRequired': 'Display name and Provider ID are required',
+  'config.providerIdInvalid': 'Provider ID: use only lowercase letters, numbers, hyphens',
+  'config.providerIdTaken': 'Provider ID "{id}" is already taken',
+
   // Configure
   'config.title': 'Configure {name}',
   'config.telegramOwnerHint': 'After saving, IronClaw will show a one-time code. Send `/start CODE` to your bot in Telegram and IronClaw will finish setup automatically.',

src/channels/web/static/i18n/zh-CN.js

@@ -9,6 +9,8 @@ I18n.register('zh-CN', {
   'auth.connect': '连接',
   'auth.errorRequired': '请输入令牌',
   'auth.errorInvalid': '令牌无效',
+  'auth.hint': '输入 .env 配置文件中的 GATEWAY_AUTH_TOKEN',
+  
   // 聊天
   'chat.inputPlaceholder': '输入消息或 / 以使用命令...',
   
@@ -36,52 +38,15 @@ I18n.register('zh-CN', {
   'tab.settings': '设置',
   'tab.extensions': '扩展',
   'tab.skills': '技能',
+  'tab.config': '配置',
   'tab.logs': '日志',
   'settings.inference': '推理',
   'settings.agent': '代理',
   'settings.channels': '频道',
   'settings.networking': '网络',
   'settings.mcp': 'MCP',
-  'settings.users': '用户管理',
-
-  // 用户管理标签页
-  'users.heading': '用户管理',
-  'users.newUser': '+ 新用户',
-  'users.displayNamePlaceholder': '显示名称',
-  'users.emailPlaceholder': '邮箱（可选）',
-  'users.roleMember': '成员',
-  'users.roleAdmin': '管理员',
-  'users.create': '创建',
-  'users.cancel': '取消',
-  'users.emptyState': '暂无用户。创建第一个用户以开始使用。',
-  'users.adminRequired': '需要管理员权限来管理用户。',
-  'users.failedToLoad': '加载用户列表失败',
-  'users.suspend': '停用',
-  'users.activate': '启用',
-  'users.addToken': '+ 令牌',
-  'users.failedSuspend': '停用用户失败',
-  'users.failedActivate': '启用用户失败',
-  'users.makeAdmin': '设为管理员',
-  'users.makeMember': '设为成员',
-  'users.failedRoleChange': '更改角色失败',
-  'users.userCreated': '用户已创建！',
-  'users.tokenCreated': '令牌已创建！',
-  'users.tokenShareMessage': '分享此登录链接——此链接只会显示一次：',
-  'users.rawToken': '原始令牌：',
-  'users.copied': '已复制！',
-  'users.displayNameRequired': '显示名称为必填项',
-  'users.failedCreate': '创建用户失败',
-  'users.columns.id': 'ID',
-  'users.columns.displayName': '显示名称',
-  'users.columns.email': '邮箱',
-  'users.columns.role': '角色',
-  'users.columns.status': '状态',
-  'users.columns.jobs': '任务',
-  'users.columns.cost': '费用',
-  'users.columns.lastActive': '最近活跃',
-  'users.columns.created': '创建时间',
-  'users.columns.actions': '操作',
-
+  'settings.providers': '模型提供商',
+  
   // 状态
   'status.connected': '已连接',
   'status.disconnected': '已断开',
@@ -387,6 +352,45 @@ I18n.register('zh-CN', {
   'ext.removed': '已移除 {name}',
   'ext.installFailed': '安装失败: {message}',
   
+  // 配置页 — 模型提供商
+  'config.modelProviders': '模型提供商',
+  'config.addProvider': '+ 添加提供商',
+  'config.newProvider': '新建提供商',
+  'config.restartNotice': '更改将在重启后生效。',
+  'config.builtin': '内置',
+  'config.useProvider': '使用',
+  'config.configureProvider': '配置',
+  'config.providerConfigured': '提供商 "{name}" 已配置（重启后生效）',
+  'config.currentModel': '模型：{model}',
+  'config.providerName': '显示名称',
+  'config.providerNamePlaceholder': '我的提供商',
+  'config.providerId': '提供商 ID',
+  'config.providerIdPlaceholder': 'my-provider',
+  'config.providerIdHint': '小写字母、数字、连字符',
+  'config.providerAdapter': 'API 适配器',
+  'config.adapterOpenAI': 'OpenAI 兼容',
+  'config.adapterAnthropic': 'Anthropic',
+  'config.adapterOllama': 'Ollama',
+  'config.providerBaseUrl': '基础 URL',
+  'config.providerApiKey': 'API 密钥',
+  'config.providerModel': '默认模型',
+  'config.providerActivated': '已切换到 {name}（重启后生效）',
+  'config.providerAdded': '已添加提供商 "{name}"（重启后生效）',
+  'config.providerUpdated': '提供商 "{name}" 已更新（重启后生效）',
+  'config.editProvider': '编辑提供商',
+  'config.providerDeleted': '提供商已删除',
+  'config.confirmDeleteProvider': '确定删除提供商 "{id}"？',
+  'config.cannotDeleteActiveProvider': '无法删除当前正在使用的提供商，请先切换到其他提供商。',
+  'config.testConnection': '测试',
+  'config.testing': '测试中…',
+  'config.fetchModels': '获取可用模型',
+  'config.modelsFetched': '已加载 {count} 个模型，可输入过滤',
+  'config.modelsFetchFailed': '获取模型列表失败',
+  'config.providerBaseUrlRequired': '请先填写 Base URL',
+  'config.providerFieldsRequired': '显示名称和提供商 ID 为必填项',
+  'config.providerIdInvalid': '提供商 ID 只能包含小写字母、数字和连字符',
+  'config.providerIdTaken': '提供商 ID "{id}" 已被占用',
+
   // 配置
   'config.title': '配置 {name}',
   'config.telegramOwnerHint': '保存后，IronClaw 会显示一次性验证码。将 `/start CODE` 发送给你的 Telegram 机器人，IronClaw 会自动完成设置。',

src/channels/web/static/index.html

@@ -41,6 +41,59 @@
         <button id="auth-connect-btn" data-i18n="auth.connect">Connect</button>
       </div>
       <div id="auth-error"></div>
+      <p class="auth-hint" data-i18n="auth.hint">Enter the GATEWAY_AUTH_TOKEN from your .env configuration.</p>
+    </div>
+  </div>
+
+  <!-- Provider Add/Edit Dialog -->
+  <div id="provider-dialog" class="provider-dialog" style="display:none">
+    <div class="provider-dialog-overlay" id="provider-dialog-overlay"></div>
+    <div class="provider-dialog-content">
+      <div class="provider-dialog-header">
+        <h2 id="provider-form-title" data-i18n="config.newProvider">New Provider</h2>
+        <button class="provider-dialog-close" id="cancel-provider-btn" title="Close">×</button>
+      </div>
+      <div class="provider-dialog-body">
+        <div class="config-form">
+          <div class="config-form-row" id="provider-name-row">
+            <label data-i18n="config.providerName">Display Name</label>
+            <input type="text" id="provider-name" data-i18n="config.providerNamePlaceholder" data-i18n-attr="placeholder" placeholder="My Provider">
+          </div>
+          <div class="config-form-row" id="provider-id-row">
+            <label data-i18n="config.providerId">Provider ID</label>
+            <input type="text" id="provider-id" data-i18n="config.providerIdPlaceholder" data-i18n-attr="placeholder" placeholder="my-provider">
+            <span class="config-form-hint" data-i18n="config.providerIdHint">Lowercase letters, numbers, hyphens</span>
+          </div>
+          <div class="config-form-row" id="provider-adapter-row">
+            <label data-i18n="config.providerAdapter">API Adapter</label>
+            <select id="provider-adapter">
+              <option value="open_ai_completions" data-i18n="config.adapterOpenAI">OpenAI Compatible</option>
+              <option value="anthropic" data-i18n="config.adapterAnthropic">Anthropic</option>
+              <option value="ollama" data-i18n="config.adapterOllama">Ollama</option>
+            </select>
+          </div>
+          <div class="config-form-row" id="provider-base-url-row">
+            <label data-i18n="config.providerBaseUrl">Base URL</label>
+            <input type="text" id="provider-base-url" placeholder="https://api.example.com/v1">
+          </div>
+          <div class="config-form-row" id="provider-api-key-row">
+            <label data-i18n="config.providerApiKey">API Key</label>
+            <input type="password" id="provider-api-key" placeholder="sk-...">
+          </div>
+          <div class="config-form-row">
+            <label data-i18n="config.providerModel">Default Model</label>
+            <input type="text" id="provider-model" placeholder="gpt-4o">
+            <button id="fetch-models-btn" class="btn-fetch-models" type="button" data-i18n="config.fetchModels">↻ Fetch available models</button>
+            <select id="provider-model-select" style="display:none"></select>
+          </div>
+          <div id="test-connection-result" class="test-connection-result" style="display:none"></div>
+        </div>
+      </div>
+      <div class="provider-dialog-footer">
+        <button id="save-provider-btn" data-i18n="common.save">Save</button>
+        <button id="test-provider-btn" class="btn-secondary" data-i18n="config.testConnection">Test</button>
+        <button id="cancel-provider-footer-btn" class="btn-secondary" data-i18n="common.cancel">Cancel</button>
+      </div>
     </div>
   </div>
 
@@ -292,7 +345,6 @@
           <button class="settings-subtab" data-settings-subtab="extensions" data-i18n="tab.extensions">Extensions</button>
           <button class="settings-subtab" data-settings-subtab="mcp" data-i18n="settings.mcp">MCP</button>
           <button class="settings-subtab" data-settings-subtab="skills" data-i18n="tab.skills">Skills</button>
-          <button class="settings-subtab" data-settings-subtab="users" data-i18n="settings.users">Users</button>
           <button class="settings-theme-toggle" id="settings-theme-toggle" data-i18n="theme.tooltipSystem" title="Toggle theme">Theme</button>
         </div>
         <div class="settings-content">
@@ -305,8 +357,23 @@
             <button id="settings-import-btn" class="settings-toolbar-btn" data-i18n="settings.import">Import</button>
           </div>
           <div class="settings-subpanel active" id="settings-inference">
-            <div class="extensions-container" id="settings-inference-content">
-              <div class="empty-state" data-i18n="common.loading">Loading settings...</div>
+            <div class="extensions-container">
+              <div id="settings-inference-content">
+                <div class="empty-state" data-i18n="common.loading">Loading settings...</div>
+              </div>
+              <div class="extensions-section" id="providers-section">
+                <div class="config-section-header">
+                  <h3 data-i18n="config.modelProviders">Model Providers</h3>
+                  <button id="add-provider-btn" class="btn-add-provider" data-i18n="config.addProvider">+ Add Provider</button>
+                </div>
+                <div class="config-notice" id="config-restart-notice" style="display:none">
+                  <span>⚠</span>
+                  <span data-i18n="config.restartNotice">Changes take effect after restart.</span>
+                </div>
+                <div id="providers-list" class="providers-list">
+                  <div class="empty-state" data-i18n="common.loading">Loading...</div>
+                </div>
+              </div>
             </div>
           </div>
           <div class="settings-subpanel" id="settings-agent">
@@ -390,29 +457,6 @@
               </div>
             </div>
           </div>
-          <div class="settings-subpanel" id="settings-users">
-            <div class="users-container">
-              <div class="users-header">
-                <h3 data-i18n="users.heading">User Management</h3>
-                <button id="users-create-btn" class="btn-primary" data-i18n="users.newUser">+ New User</button>
-              </div>
-              <div id="users-create-form" style="display:none" class="users-form" autocomplete="off">
-                <input type="text" id="user-display-name" data-i18n-placeholder="users.displayNamePlaceholder" placeholder="Display name" autocomplete="off" />
-                <input type="text" id="user-email" data-i18n-placeholder="users.emailPlaceholder" placeholder="Email (optional)" autocomplete="off" />
-                <select id="user-role"><option value="member" data-i18n="users.roleMember">Member</option><option value="admin" data-i18n="users.roleAdmin">Admin</option></select>
-                <button id="users-create-submit" class="btn-primary" data-i18n="users.create">Create</button>
-                <button id="users-create-cancel" class="btn-secondary" data-i18n="users.cancel">Cancel</button>
-              </div>
-              <div id="users-token-result" style="display:none" class="users-token-banner"></div>
-              <table class="routines-table" id="users-table">
-                <thead><tr>
-                  <th data-i18n="users.columns.id">ID</th><th data-i18n="users.columns.displayName">Display Name</th><th data-i18n="users.columns.email">Email</th><th data-i18n="users.columns.role">Role</th><th data-i18n="users.columns.status">Status</th><th data-i18n="users.columns.jobs">Jobs</th><th data-i18n="users.columns.cost">Cost</th><th data-i18n="users.columns.lastActive">Last Active</th><th data-i18n="users.columns.created">Created</th><th data-i18n="users.columns.actions">Actions</th>
-                </tr></thead>
-                <tbody id="users-tbody"></tbody>
-              </table>
-              <div id="users-empty" class="empty-state" style="display:none" data-i18n="users.emptyState">No users found. Create the first user to get started.</div>
-            </div>
-          </div>
         </div>
       </div>
     </div>
@@ -431,6 +475,7 @@
   </div>
 
   <div id="toasts"></div>
+  <script src="/providers.js"></script>
   <script src="/app.js"></script>
   <script src="/i18n-app.js"></script>
 </body>

src/channels/web/static/providers.js

@@ -0,0 +1,37 @@
+// Built-in LLM provider definitions.
+// Generated from providers.json + nearai/bedrock (handled separately in llm.rs)
+// Fields: id, name, adapter, base_url, builtin, default_model, api_key_required, can_list_models
+// nearai/bedrock use special auth flows — no Configure button (api_key_required=false, can_list_models=false)
+const BUILTIN_PROVIDERS = [
+  { id: 'nearai',            name: 'NEAR AI',           adapter: 'nearai',                base_url: 'https://cloud-api.near.ai/v1',                                    builtin: true, default_model: 'zai-org/GLM-5-FP8',                                              api_key_required: true,  can_list_models: true  },
+  { id: 'openai',            name: 'OpenAI',            adapter: 'open_ai_completions',   base_url: 'https://api.openai.com/v1',                                        builtin: true, default_model: 'gpt-4o-mini',                                                     api_key_required: true,  can_list_models: true  },
+  { id: 'anthropic',         name: 'Anthropic',         adapter: 'anthropic',             base_url: 'https://api.anthropic.com',                                        builtin: true, default_model: 'claude-sonnet-4-20250514',                                        api_key_required: true,  can_list_models: true  },
+  { id: 'ollama',            name: 'Ollama',            adapter: 'ollama',                base_url: 'http://localhost:11434',                                            builtin: true, default_model: 'llama3',                                                          api_key_required: false, can_list_models: true  },
+  { id: 'openai_compatible', name: 'OpenAI Compatible', adapter: 'open_ai_completions',   base_url: '',                                                                 builtin: true, default_model: 'default',                                                         api_key_required: false, can_list_models: false },
+  { id: 'gemini',            name: 'Google Gemini',     adapter: 'open_ai_completions',   base_url: 'https://generativelanguage.googleapis.com/v1beta/openai',           builtin: true, default_model: 'gemini-2.5-flash',                                                api_key_required: true,  can_list_models: true  },
+  { id: 'groq',              name: 'Groq',              adapter: 'open_ai_completions',   base_url: 'https://api.groq.com/openai/v1',                                   builtin: true, default_model: 'llama-3.3-70b-versatile',                                         api_key_required: true,  can_list_models: true  },
+  { id: 'openrouter',        name: 'OpenRouter',        adapter: 'open_ai_completions',   base_url: 'https://openrouter.ai/api/v1',                                     builtin: true, default_model: 'openai/gpt-4o',                                                   api_key_required: true,  can_list_models: false },
+  { id: 'deepseek',          name: 'DeepSeek',          adapter: 'open_ai_completions',   base_url: 'https://api.deepseek.com/v1',                                      builtin: true, default_model: 'deepseek-chat',                                                   api_key_required: true,  can_list_models: false },
+  { id: 'mistral',           name: 'Mistral',           adapter: 'open_ai_completions',   base_url: 'https://api.mistral.ai/v1',                                        builtin: true, default_model: 'mistral-large-latest',                                            api_key_required: true,  can_list_models: true  },
+  { id: 'tinfoil',           name: 'Tinfoil',           adapter: 'open_ai_completions',   base_url: 'https://inference.tinfoil.sh/v1',                                  builtin: true, default_model: 'kimi-k2-5',                                                       api_key_required: true,  can_list_models: false },
+  { id: 'nvidia',            name: 'NVIDIA NIM',        adapter: 'open_ai_completions',   base_url: 'https://integrate.api.nvidia.com/v1',                              builtin: true, default_model: 'meta/llama-3.3-70b-instruct',                                    api_key_required: true,  can_list_models: true  },
+  { id: 'together',          name: 'Together AI',       adapter: 'open_ai_completions',   base_url: 'https://api.together.xyz/v1',                                      builtin: true, default_model: 'meta-llama/Llama-3-70b-chat-hf',                                 api_key_required: true,  can_list_models: false },
+  { id: 'fireworks',         name: 'Fireworks AI',      adapter: 'open_ai_completions',   base_url: 'https://api.fireworks.ai/inference/v1',                            builtin: true, default_model: 'accounts/fireworks/models/llama-v3p1-70b-instruct',               api_key_required: true,  can_list_models: false },
+  { id: 'cerebras',          name: 'Cerebras',          adapter: 'open_ai_completions',   base_url: 'https://api.cerebras.ai/v1',                                       builtin: true, default_model: 'llama-3.3-70b',                                                   api_key_required: true,  can_list_models: false },
+  { id: 'sambanova',         name: 'SambaNova',         adapter: 'open_ai_completions',   base_url: 'https://api.sambanova.ai/v1',                                      builtin: true, default_model: 'Meta-Llama-3.1-70B-Instruct',                                    api_key_required: true,  can_list_models: false },
+  { id: 'zai',               name: 'Z.AI',              adapter: 'open_ai_completions',   base_url: 'https://api.z.ai/api/paas/v4',                                     builtin: true, default_model: 'glm-5',                                                           api_key_required: true,  can_list_models: false },
+  { id: 'venice',            name: 'Venice.ai',         adapter: 'open_ai_completions',   base_url: 'https://api.venice.ai/api/v1',                                     builtin: true, default_model: 'llama-3.3-70b',                                                   api_key_required: true,  can_list_models: false },
+  { id: 'minimax',           name: 'MiniMax',           adapter: 'open_ai_completions',   base_url: 'https://api.minimax.io/v1',                                        builtin: true, default_model: 'MiniMax-M2.5',                                                    api_key_required: true,  can_list_models: false },
+  { id: 'ionet',             name: 'io.net',            adapter: 'open_ai_completions',   base_url: 'https://api.intelligence.io.solutions/api/v1',                     builtin: true, default_model: 'deepseek-coder-v2-instruct',                                      api_key_required: true,  can_list_models: true  },
+  { id: 'cloudflare',        name: 'Cloudflare AI',     adapter: 'open_ai_completions',   base_url: '',                                                                 builtin: true, default_model: '@cf/meta/llama-3.3-70b-instruct-fp8-fast',                       api_key_required: true,  can_list_models: false },
+  { id: 'yandex',            name: 'Yandex AI Studio',  adapter: 'open_ai_completions',   base_url: 'https://ai.api.cloud.yandex.net/v1',                               builtin: true, default_model: 'yandexgpt-lite',                                                  api_key_required: true,  can_list_models: true  },
+  { id: 'bedrock',           name: 'AWS Bedrock',       adapter: 'bedrock',               base_url: '',                                                                 builtin: true, default_model: 'anthropic.claude-3-sonnet-20240229-v1:0',                         api_key_required: false, can_list_models: false },
+];
+
+const ADAPTER_LABELS = {
+  open_ai_completions: 'OpenAI Compatible',
+  anthropic: 'Anthropic',
+  ollama: 'Ollama',
+  bedrock: 'AWS Bedrock',
+  nearai: 'NEAR AI',
+};

src/channels/web/static/style.css

@@ -2801,10 +2801,22 @@ body {
   padding: var(--space-4);
 }
 
+#settings-inference > .extensions-container {
+  display: flex;
+  flex-direction: column;
+}
+
 .extensions-section {
   margin-bottom: 24px;
 }
 
+#providers-section {
+  flex: 1;
+  min-height: 0;
+  display: flex;
+  flex-direction: column;
+}
+
 .extensions-section h3 {
   font-size: var(--text-xs);
   font-weight: 600;
@@ -4593,6 +4605,12 @@ mark {
   min-width: 180px;
 }
 
+.settings-display-value {
+  font-size: var(--text-sm);
+  color: var(--text);
+  font-family: 'IBM Plex Mono', monospace;
+}
+
 .settings-input {
   padding: 6px 10px;
   background: var(--bg);
@@ -5430,21 +5448,404 @@ body.theme-transition *:not(svg):not(path):not(line):not(circle):not(rect) {
   }
 }
 
-/* --- Users Tab --- */
-.users-container { padding: 1rem; }
-.users-header { display: flex; align-items: center; justify-content: space-between; margin-bottom: 1rem; }
-.users-header h3 { margin: 0; font-size: 1.1rem; }
-.users-form { display: flex; gap: 0.5rem; align-items: center; margin-bottom: 1rem; flex-wrap: wrap; }
-.users-form input, .users-form select { padding: 0.4rem 0.6rem; border-radius: 6px; border: 1px solid var(--border); background: var(--bg-secondary); color: var(--text-primary); font-size: 0.85rem; }
-.users-token-banner { background: var(--bg-tertiary); border: 1px solid var(--accent); border-radius: 8px; padding: 0.75rem 1rem; margin-bottom: 1rem; font-size: 0.85rem; }
-.token-display { display: inline-block; padding: 0.3rem 0.6rem; background: var(--bg-primary); border-radius: 4px; font-family: var(--font-mono); word-break: break-all; margin: 0.4rem 0; user-select: all; }
-.user-id { font-family: var(--font-mono); font-size: 0.8rem; color: var(--text-muted); }
-.badge { display: inline-block; padding: 0.15rem 0.5rem; border-radius: 10px; font-size: 0.75rem; background: var(--bg-tertiary); color: var(--text-secondary); }
-.badge-admin { background: var(--accent); color: #fff; }
-.btn-small { padding: 0.25rem 0.5rem; font-size: 0.75rem; border-radius: 4px; border: 1px solid var(--border); background: var(--bg-secondary); color: var(--text-primary); cursor: pointer; }
-.btn-small:hover { background: var(--bg-tertiary); }
-.btn-danger { border-color: #ef4444; color: #ef4444; }
-.btn-danger:hover { background: #ef4444; color: #fff; }
-.btn-primary { background: var(--accent); color: #fff; border: none; padding: 0.4rem 0.8rem; border-radius: 6px; cursor: pointer; font-size: 0.85rem; }
-.btn-primary:hover { opacity: 0.9; }
-.btn-secondary { background: var(--bg-tertiary); color: var(--text-primary); border: 1px solid var(--border); padding: 0.4rem 0.8rem; border-radius: 6px; cursor: pointer; font-size: 0.85rem; }
+
+/* --- Config Tab --- */
+
+.config-section-header {
+  display: flex;
+  align-items: center;
+  justify-content: space-between;
+  margin-bottom: 12px;
+}
+
+.config-section-header h3 {
+  margin-bottom: 0;
+}
+
+.btn-add-provider {
+  padding: 5px 14px;
+  background: var(--accent);
+  color: #09090b;
+  border: none;
+  border-radius: var(--radius);
+  cursor: pointer;
+  font-size: 13px;
+  font-weight: 600;
+  transition: background 0.2s, transform 0.2s;
+}
+
+.btn-add-provider:hover {
+  background: var(--accent-hover);
+  transform: translateY(-1px);
+}
+
+.config-notice {
+  display: flex;
+  align-items: center;
+  gap: 8px;
+  padding: 8px 12px;
+  background: rgba(245, 166, 35, 0.1);
+  border: 1px solid rgba(245, 166, 35, 0.3);
+  border-radius: var(--radius);
+  color: var(--warning);
+  font-size: 13px;
+  margin-bottom: 12px;
+}
+
+.providers-list {
+  display: flex;
+  flex-direction: column;
+  gap: 8px;
+  min-height: 420px;
+  overflow-y: auto;
+}
+
+.provider-card {
+  background: var(--bg-secondary);
+  border: 1px solid var(--border);
+  border-radius: var(--radius-lg);
+  padding: 12px 14px;
+  display: flex;
+  flex-direction: column;
+  gap: 6px;
+  transition: border-color 0.2s;
+}
+
+.provider-card:hover {
+  border-color: rgba(255, 255, 255, 0.15);
+}
+
+.provider-card-active {
+  border-color: var(--accent);
+}
+
+.provider-card-header {
+  display: flex;
+  align-items: center;
+  gap: 8px;
+  flex-wrap: wrap;
+}
+
+.provider-name {
+  font-weight: 600;
+  font-size: 14px;
+  color: var(--text);
+}
+
+.provider-id-label {
+  font-size: 11px;
+  color: var(--text-secondary);
+  font-family: var(--font-mono);
+}
+
+.provider-badge {
+  font-size: 10px;
+  padding: 2px 7px;
+  border-radius: 20px;
+  font-weight: 600;
+  letter-spacing: 0.02em;
+}
+
+.provider-badge-active {
+  background: rgba(52, 211, 153, 0.15);
+  color: var(--accent);
+}
+
+.provider-badge-builtin {
+  background: rgba(161, 161, 170, 0.12);
+  color: var(--text-secondary);
+}
+
+.provider-card-meta {
+  display: flex;
+  align-items: center;
+  gap: 10px;
+  flex-wrap: wrap;
+}
+
+.provider-adapter {
+  font-size: 12px;
+  color: var(--text-secondary);
+}
+
+.provider-url {
+  font-size: 11px;
+  color: var(--text-secondary);
+  font-family: var(--font-mono);
+  opacity: 0.7;
+}
+
+.provider-current-model {
+  font-size: 11px;
+  color: var(--accent);
+  font-family: var(--font-mono);
+  font-weight: 500;
+}
+
+.provider-card-actions {
+  display: flex;
+  gap: 6px;
+  margin-top: 2px;
+}
+
+.provider-action-btn {
+  padding: 4px 12px;
+  background: var(--bg-tertiary);
+  border: 1px solid var(--border);
+  border-radius: var(--radius);
+  color: var(--text-secondary);
+  cursor: pointer;
+  font-size: 12px;
+  transition: color 0.2s, border-color 0.2s, background 0.2s;
+}
+
+.provider-action-btn:hover {
+  color: var(--text);
+  border-color: rgba(255, 255, 255, 0.2);
+  background: var(--bg);
+}
+
+.provider-delete-btn:hover {
+  color: var(--danger);
+  border-color: var(--danger);
+}
+
+/* Config form */
+
+.provider-dialog {
+  position: fixed;
+  top: 0;
+  left: 0;
+  right: 0;
+  bottom: 0;
+  z-index: 9999;
+  display: flex;
+  align-items: center;
+  justify-content: center;
+}
+
+.provider-dialog-overlay {
+  position: absolute;
+  top: 0;
+  left: 0;
+  right: 0;
+  bottom: 0;
+  background: rgba(0, 0, 0, 0.5);
+  backdrop-filter: blur(4px);
+}
+
+.provider-dialog-content {
+  position: relative;
+  z-index: 10000;
+  background: var(--bg-secondary);
+  border: 1px solid var(--border);
+  border-radius: var(--radius-lg);
+  box-shadow: 0 25px 50px -12px rgba(0, 0, 0, 0.4);
+  width: 100%;
+  max-width: 480px;
+  margin: 0 1rem;
+  display: flex;
+  flex-direction: column;
+  max-height: 90vh;
+}
+
+.provider-dialog-header {
+  display: flex;
+  align-items: center;
+  justify-content: space-between;
+  padding: 14px 18px;
+  border-bottom: 1px solid var(--border);
+  flex-shrink: 0;
+}
+
+.provider-dialog-header h2 {
+  font-size: 14px;
+  font-weight: 600;
+  color: var(--text);
+  margin: 0;
+}
+
+.provider-dialog-close {
+  color: var(--text-secondary);
+  font-size: 18px;
+  line-height: 1;
+  padding: 2px 6px;
+  background: transparent;
+  border: none;
+  border-radius: var(--radius);
+  cursor: pointer;
+  transition: color 0.15s, background 0.15s;
+}
+
+.provider-dialog-close:hover {
+  color: var(--text);
+  background: var(--bg-hover);
+}
+
+.provider-dialog-body {
+  padding: 18px;
+  overflow-y: auto;
+  flex: 1;
+}
+
+.provider-dialog-footer {
+  display: flex;
+  gap: 8px;
+  padding: 14px 18px;
+  border-top: 1px solid var(--border);
+  flex-shrink: 0;
+}
+
+.provider-dialog-footer button {
+  padding: 6px 18px;
+  border-radius: var(--radius);
+  font-size: 13px;
+  font-weight: 600;
+  cursor: pointer;
+  transition: background 0.2s, transform 0.2s;
+}
+
+.provider-dialog-footer button:first-child {
+  background: var(--accent);
+  color: #09090b;
+  border: none;
+}
+
+.provider-dialog-footer button:first-child:hover {
+  background: var(--accent-hover);
+  transform: translateY(-1px);
+}
+
+.provider-dialog-footer .btn-secondary {
+  background: transparent;
+  color: var(--text-secondary);
+  border: 1px solid var(--border);
+}
+
+.provider-dialog-footer .btn-secondary:hover {
+  color: var(--text);
+  border-color: rgba(255, 255, 255, 0.2);
+}
+
+.config-form {
+  display: flex;
+  flex-direction: column;
+  gap: 12px;
+}
+
+.config-form-row {
+  display: flex;
+  flex-direction: column;
+  gap: 4px;
+}
+
+.config-form-row label {
+  font-size: 12px;
+  font-weight: 500;
+  color: var(--text-secondary);
+}
+
+.config-form-row input,
+.config-form-row select {
+  padding: 7px 10px;
+  background: var(--bg);
+  border: 1px solid var(--border);
+  border-radius: var(--radius);
+  color: var(--text);
+  font-size: 13px;
+}
+
+.config-form-row input:focus,
+.config-form-row select:focus {
+  outline: none;
+  border-color: var(--accent);
+  box-shadow: 0 0 0 3px rgba(52, 211, 153, 0.1);
+}
+
+.config-form-hint {
+  font-size: 11px;
+  color: var(--text-secondary);
+  opacity: 0.7;
+}
+
+.config-form-actions {
+  display: flex;
+  gap: 8px;
+  margin-top: 4px;
+}
+
+.config-form-actions button {
+  padding: 6px 18px;
+  border-radius: var(--radius);
+  font-size: 13px;
+  font-weight: 600;
+  cursor: pointer;
+  transition: background 0.2s, transform 0.2s;
+}
+
+.config-form-actions button:first-child {
+  background: var(--accent);
+  color: #09090b;
+  border: none;
+}
+
+.config-form-actions button:first-child:hover {
+  background: var(--accent-hover);
+  transform: translateY(-1px);
+}
+
+.config-form-actions .btn-secondary {
+  background: transparent;
+  color: var(--text-secondary);
+  border: 1px solid var(--border);
+}
+
+.config-form-actions .btn-secondary:hover {
+  color: var(--text);
+  border-color: rgba(255, 255, 255, 0.2);
+}
+
+.btn-fetch-models {
+  display: inline-flex;
+  align-items: center;
+  gap: 5px;
+  margin-top: 6px;
+  padding: 5px 11px;
+  background: transparent;
+  border: 1px solid var(--border);
+  border-radius: var(--radius);
+  color: var(--text-secondary);
+  cursor: pointer;
+  font-size: 12px;
+  transition: color 0.15s, border-color 0.15s, background 0.15s;
+}
+
+.btn-fetch-models:hover {
+  color: var(--text);
+  border-color: var(--accent);
+  background: color-mix(in srgb, var(--accent) 8%, transparent);
+}
+
+.btn-fetch-models:disabled {
+  opacity: 0.5;
+  cursor: not-allowed;
+}
+
+.test-connection-result {
+  margin-top: 8px;
+  padding: 6px 12px;
+  border-radius: var(--radius);
+  font-size: 13px;
+}
+
+.test-connection-result.test-ok {
+  background: rgba(74, 222, 128, 0.12);
+  color: #4ade80;
+  border: 1px solid rgba(74, 222, 128, 0.3);
+}
+
+.test-connection-result.test-fail {
+  background: rgba(248, 113, 113, 0.12);
+  color: #f87171;
+  border: 1px solid rgba(248, 113, 113, 0.3);
+}

src/channels/web/test_helpers.rs

@@ -77,6 +77,7 @@ impl TestGatewayBuilder {
             job_manager: None,
             prompt_queue: None,
             owner_id: self.user_id.clone(),
+            default_sender_id: self.user_id,
             shutdown_tx: tokio::sync::RwLock::new(None),
             ws_tracker: Some(Arc::new(WsConnectionTracker::new())),
             llm_provider: self.llm_provider,
@@ -92,7 +93,6 @@ impl TestGatewayBuilder {
             startup_time: std::time::Instant::now(),
             active_config: crate::channels::web::server::ActiveConfigSnapshot::default(),
             secrets_store: None,
-            db_auth: None,
         })
     }
 
@@ -107,7 +107,7 @@ impl TestGatewayBuilder {
         let addr: SocketAddr = "127.0.0.1:0"
             .parse()
             .expect("hard-coded address must parse"); // safety: constant literal
-        let bound = start_server(addr, state.clone(), auth.into()).await?;
+        let bound = start_server(addr, state.clone(), auth).await?;
         Ok((bound, state))
     }
 
@@ -121,7 +121,7 @@ impl TestGatewayBuilder {
         let addr: SocketAddr = "127.0.0.1:0"
             .parse()
             .expect("hard-coded address must parse"); // safety: constant literal
-        let bound = start_server(addr, state.clone(), auth.into()).await?;
+        let bound = start_server(addr, state.clone(), auth).await?;
         Ok((bound, state))
     }
 }

src/channels/web/tests/multi_tenant.rs

@@ -16,6 +16,7 @@ use axum::routing::{delete, get, post};
 use tower::ServiceExt;
 use uuid::Uuid;
 
+use crate::channels::web::GatewayChannel;
 use crate::channels::web::auth::{
     AuthenticatedUser, MultiAuthState, UserIdentity, auth_middleware,
 };
@@ -23,6 +24,7 @@ use crate::channels::web::server::{
     ActiveConfigSnapshot, GatewayState, PerUserRateLimiter, PromptQueue, RateLimiter, WorkspacePool,
 };
 use crate::channels::web::sse::SseManager;
+use crate::config::GatewayConfig;
 
 // ── Helpers ────────────────────────────────────────────────────────────
 
@@ -33,7 +35,6 @@ fn two_user_auth() -> MultiAuthState {
         "tok-alice".to_string(),
         UserIdentity {
             user_id: "alice".to_string(),
-            role: "admin".to_string(),
             workspace_read_scopes: vec!["shared".to_string()],
         },
     );
@@ -41,7 +42,6 @@ fn two_user_auth() -> MultiAuthState {
         "tok-bob".to_string(),
         UserIdentity {
             user_id: "bob".to_string(),
-            role: "admin".to_string(),
             workspace_read_scopes: vec!["shared".to_string(), "alice".to_string()],
         },
     );
@@ -67,6 +67,7 @@ fn build_state(
         job_manager: None,
         prompt_queue,
         owner_id: "test".to_string(),
+        default_sender_id: "test".to_string(),
         shutdown_tx: tokio::sync::RwLock::new(None),
         ws_tracker: None,
         llm_provider: None,
@@ -82,10 +83,43 @@ fn build_state(
         startup_time: std::time::Instant::now(),
         active_config: ActiveConfigSnapshot::default(),
         secrets_store: None,
-        db_auth: None,
     })
 }
 
+fn gateway_config() -> GatewayConfig {
+    GatewayConfig {
+        host: "127.0.0.1".to_string(),
+        port: 3000,
+        auth_token: Some("gateway-auth".to_string()),
+        user_id: "gateway-sender".to_string(),
+        workspace_read_scopes: Vec::new(),
+        memory_layers: Vec::new(),
+        user_tokens: None,
+    }
+}
+
+#[test]
+fn with_owner_scope_updates_gateway_owner_scope_in_multi_user_mode() {
+    let mut gateway = GatewayChannel::new(gateway_config());
+    gateway.auth = two_user_auth();
+    gateway.config.user_tokens = Some(HashMap::new());
+    let gateway = gateway.with_owner_scope("owner-scope");
+
+    assert_eq!(gateway.state.owner_id, "owner-scope");
+    assert_eq!(gateway.state.default_sender_id, "gateway-sender");
+
+    let alice = gateway
+        .auth
+        .authenticate("tok-alice")
+        .expect("alice token should remain valid");
+    let bob = gateway
+        .auth
+        .authenticate("tok-bob")
+        .expect("bob token should remain valid");
+    assert_eq!(alice.user_id, "alice");
+    assert_eq!(bob.user_id, "bob");
+}
+
 /// Create a libSQL-backed test database in a temporary directory.
 ///
 /// Returns the database and a `TempDir` guard — the database file is
@@ -192,7 +226,6 @@ mod workspace_pool {
         );
         let identity = UserIdentity {
             user_id: "alice".to_string(),
-            role: "admin".to_string(),
             workspace_read_scopes: vec![],
         };
         let ws = pool.get_or_create(&identity).await;
@@ -221,7 +254,6 @@ mod workspace_pool {
         );
         let identity = UserIdentity {
             user_id: "alice".to_string(),
-            role: "admin".to_string(),
             workspace_read_scopes: vec![],
         };
         let ws = pool.get_or_create(&identity).await;
@@ -245,7 +277,6 @@ mod workspace_pool {
         );
         let identity = UserIdentity {
             user_id: "bob".to_string(),
-            role: "admin".to_string(),
             workspace_read_scopes: vec!["alice".to_string(), "shared".to_string()],
         };
         let ws = pool.get_or_create(&identity).await;
@@ -272,12 +303,10 @@ mod workspace_pool {
         );
         let alice_id = UserIdentity {
             user_id: "alice".to_string(),
-            role: "admin".to_string(),
             workspace_read_scopes: vec![],
         };
         let bob_id = UserIdentity {
             user_id: "bob".to_string(),
-            role: "admin".to_string(),
             workspace_read_scopes: vec![],
         };
 
@@ -309,7 +338,6 @@ mod workspace_pool {
         );
         let identity = UserIdentity {
             user_id: "alice".to_string(),
-            role: "admin".to_string(),
             workspace_read_scopes: vec!["token-scope".to_string()],
         };
         let ws = pool.get_or_create(&identity).await;
@@ -350,10 +378,7 @@ mod jobs_isolation {
             .route("/api/jobs/{id}/cancel", post(jobs_cancel_handler))
             .route("/api/jobs/{id}/restart", post(jobs_restart_handler))
             .route("/api/jobs/{id}/prompt", post(jobs_prompt_handler))
-            .layer(middleware::from_fn_with_state(
-                crate::channels::web::auth::CombinedAuthState::from(auth),
-                auth_middleware,
-            ))
+            .layer(middleware::from_fn_with_state(auth, auth_middleware))
             .with_state(state)
     }
 
@@ -559,10 +584,7 @@ mod routines_isolation {
             .route("/api/routines/{id}", get(routines_detail_handler))
             .route("/api/routines/{id}/toggle", post(routines_toggle_handler))
             .route("/api/routines/{id}", delete(routines_delete_handler))
-            .layer(middleware::from_fn_with_state(
-                crate::channels::web::auth::CombinedAuthState::from(auth),
-                auth_middleware,
-            ))
+            .layer(middleware::from_fn_with_state(auth, auth_middleware))
             .with_state(state)
     }
 
@@ -687,10 +709,7 @@ mod auth_enforcement {
             .route("/api/logs/level", get(authed_handler).put(authed_handler))
             // Gateway status
             .route("/api/gateway/status", get(authed_handler))
-            .layer(middleware::from_fn_with_state(
-                crate::channels::web::auth::CombinedAuthState::from(auth),
-                auth_middleware,
-            ))
+            .layer(middleware::from_fn_with_state(auth, auth_middleware))
             .with_state(state)
     }
 
@@ -813,140 +832,3 @@ mod auth_enforcement {
         assert_eq!(resp.status(), StatusCode::UNAUTHORIZED);
     }
 }
-
-// ═══════════════════════════════════════════════════════════════════════
-// Admin Endpoint Role Enforcement Tests
-// ═══════════════════════════════════════════════════════════════════════
-
-mod admin_role_enforcement {
-    use super::*;
-    use crate::channels::web::handlers::users::{
-        users_activate_handler, users_detail_handler, users_list_handler, users_suspend_handler,
-        users_update_handler,
-    };
-    use axum::routing::patch;
-
-    /// Build a router with admin user endpoints behind multi-user auth.
-    /// Uses a member-role token and an admin-role token.
-    fn admin_router() -> Router {
-        let mut tokens = HashMap::new();
-        tokens.insert(
-            "tok-admin".to_string(),
-            UserIdentity {
-                user_id: "admin-user".to_string(),
-                role: "admin".to_string(),
-                workspace_read_scopes: vec![],
-            },
-        );
-        tokens.insert(
-            "tok-member".to_string(),
-            UserIdentity {
-                user_id: "member-user".to_string(),
-                role: "member".to_string(),
-                workspace_read_scopes: vec![],
-            },
-        );
-        let auth = MultiAuthState::multi(tokens);
-        let state = build_state(None, None);
-
-        Router::new()
-            .route("/api/admin/users", get(users_list_handler))
-            .route("/api/admin/users/{id}", get(users_detail_handler))
-            .route("/api/admin/users/{id}", patch(users_update_handler))
-            .route("/api/admin/users/{id}/suspend", post(users_suspend_handler))
-            .route(
-                "/api/admin/users/{id}/activate",
-                post(users_activate_handler),
-            )
-            .layer(middleware::from_fn_with_state(
-                crate::channels::web::auth::CombinedAuthState::from(auth),
-                auth_middleware,
-            ))
-            .with_state(state)
-    }
-
-    /// Assert a request returns FORBIDDEN for a member token.
-    async fn assert_forbidden_for_member(app: &Router, method: Method, uri: &str) {
-        let req = Request::builder()
-            .method(method)
-            .uri(uri)
-            .header("Authorization", "Bearer tok-member")
-            .body(Body::empty())
-            .unwrap();
-        let resp = app.clone().oneshot(req).await.unwrap();
-        assert_eq!(
-            resp.status(),
-            StatusCode::FORBIDDEN,
-            "expected 403 for member on {}",
-            uri
-        );
-    }
-
-    #[tokio::test]
-    async fn test_admin_user_endpoints_reject_member_role() {
-        let app = admin_router();
-
-        assert_forbidden_for_member(&app, Method::GET, "/api/admin/users").await;
-        assert_forbidden_for_member(&app, Method::GET, "/api/admin/users/some-id").await;
-        assert_forbidden_for_member(&app, Method::POST, "/api/admin/users/some-id/suspend").await;
-        assert_forbidden_for_member(&app, Method::POST, "/api/admin/users/some-id/activate").await;
-    }
-
-    #[tokio::test]
-    async fn test_admin_user_endpoints_accept_admin_role() {
-        let app = admin_router();
-
-        // Admin token should pass auth (will get 503 since no DB, but not 403).
-        let req = Request::builder()
-            .uri("/api/admin/users")
-            .header("Authorization", "Bearer tok-admin")
-            .body(Body::empty())
-            .unwrap();
-        let resp = app.clone().oneshot(req).await.unwrap();
-        assert_ne!(
-            resp.status(),
-            StatusCode::FORBIDDEN,
-            "admin should not get 403"
-        );
-    }
-}
-
-// ═══════════════════════════════════════════════════════════════════════
-// DbAuthenticator Cache Bounded Tests
-// ═══════════════════════════════════════════════════════════════════════
-
-mod db_auth_cache {
-    use super::*;
-    use std::time::Instant;
-
-    #[tokio::test]
-    async fn test_cache_bounded_by_max_entries() {
-        // Access the internal cache and verify LRU eviction.
-        // We can't easily test through `authenticate()` since it hits the DB,
-        // so we test the LRU cache directly.
-        let cap = std::num::NonZeroUsize::new(4).unwrap(); // safety: test-only, 4 is non-zero
-        let cache: lru::LruCache<[u8; 32], (UserIdentity, Instant)> = lru::LruCache::new(cap);
-        let cache = Arc::new(tokio::sync::RwLock::new(cache));
-
-        {
-            let mut c = cache.write().await;
-            for i in 0..10u8 {
-                let mut hash = [0u8; 32];
-                hash[0] = i;
-                c.put(
-                    hash,
-                    (
-                        UserIdentity {
-                            user_id: format!("user-{i}"),
-                            role: "member".to_string(),
-                            workspace_read_scopes: vec![],
-                        },
-                        Instant::now(),
-                    ),
-                );
-            }
-            // Cache must be bounded at capacity, not grown to 10.
-            assert_eq!(c.len(), 4, "cache should be bounded to capacity"); // safety: test assertion
-        }
-    }
-}

src/channels/web/ws.rs

@@ -521,6 +521,7 @@ mod tests {
             prompt_queue: None,
             scheduler: None,
             owner_id: "test".to_string(),
+            default_sender_id: "test".to_string(),
             shutdown_tx: tokio::sync::RwLock::new(None),
             ws_tracker: Some(Arc::new(WsConnectionTracker::new())),
             llm_provider: None,
@@ -535,7 +536,6 @@ mod tests {
             startup_time: std::time::Instant::now(),
             active_config: crate::channels::web::server::ActiveConfigSnapshot::default(),
             secrets_store: None,
-            db_auth: None,
         }
     }
 }

src/cli/mod.rs

@@ -352,7 +352,7 @@ pub async fn run_routines_cli(
         .await
         .map_err(|e| anyhow::anyhow!("{e:#}"))?;
 
-    let user_id = std::env::var("IRONCLAW_OWNER_ID").unwrap_or_else(|_| "default".to_string());
+    let user_id = std::env::var("GATEWAY_USER_ID").unwrap_or_else(|_| "default".to_string());
     run_routines_command(routines_cmd.clone(), db, &user_id).await
 }
 

src/cli/oauth_defaults.rs

@@ -569,42 +569,6 @@ pub async fn sweep_expired_flows(registry: &PendingOAuthRegistry) {
 const HOSTED_STATE_PREFIX: &str = "ic2";
 const HOSTED_STATE_CHECKSUM_BYTES: usize = 12;
 
-/// Maximum length for a legacy flow ID or instance name.
-const LEGACY_STATE_MAX_LEN: usize = 128;
-/// Minimum length for a legacy flow ID.
-const LEGACY_STATE_MIN_LEN: usize = 8;
-
-/// Validate that a legacy state component (flow_id or instance_name) contains
-/// only safe characters: alphanumeric, dash, underscore.
-fn is_valid_legacy_state_component(s: &str) -> bool {
-    !s.is_empty()
-        && s.len() <= LEGACY_STATE_MAX_LEN
-        && s.bytes()
-            .all(|b| b.is_ascii_alphanumeric() || b == b'-' || b == b'_')
-}
-
-fn validate_legacy_flow_id(flow_id: &str) -> Result<(), String> {
-    if flow_id.len() < LEGACY_STATE_MIN_LEN {
-        return Err(format!(
-            "Legacy OAuth flow_id too short ({} chars, minimum {LEGACY_STATE_MIN_LEN})",
-            flow_id.len()
-        ));
-    }
-    if flow_id.len() > LEGACY_STATE_MAX_LEN {
-        return Err(format!(
-            "Legacy OAuth flow_id too long ({} chars, maximum {LEGACY_STATE_MAX_LEN})",
-            flow_id.len()
-        ));
-    }
-    if !flow_id
-        .bytes()
-        .all(|b| b.is_ascii_alphanumeric() || b == b'-' || b == b'_')
-    {
-        return Err("Legacy OAuth flow_id contains invalid characters".to_string());
-    }
-    Ok(())
-}
-
 #[derive(Debug, Clone, PartialEq, Eq)]
 pub struct DecodedHostedOAuthState {
     pub flow_id: String,
@@ -689,17 +653,6 @@ pub fn decode_hosted_oauth_state(state: &str) -> Result<DecodedHostedOAuthState,
         if flow_id.is_empty() {
             return Err("Hosted OAuth legacy state is missing flow_id".to_string());
         }
-        validate_legacy_flow_id(flow_id)?;
-        if !instance_name.is_empty() && !is_valid_legacy_state_component(instance_name) {
-            return Err(format!(
-                "Legacy OAuth instance name contains invalid characters or exceeds max length ({LEGACY_STATE_MAX_LEN})"
-            ));
-        }
-        tracing::debug!(
-            flow_id,
-            instance_name,
-            "Decoded legacy prefixed OAuth state"
-        );
         return Ok(DecodedHostedOAuthState {
             flow_id: flow_id.to_string(),
             instance_name: if instance_name.is_empty() {
@@ -715,9 +668,6 @@ pub fn decode_hosted_oauth_state(state: &str) -> Result<DecodedHostedOAuthState,
         return Err("Hosted OAuth state is empty".to_string());
     }
 
-    validate_legacy_flow_id(state)?;
-    tracing::debug!(flow_id = state, "Decoded legacy raw OAuth state");
-
     Ok(DecodedHostedOAuthState {
         flow_id: state.to_string(),
         instance_name: None,
@@ -1784,13 +1734,13 @@ mod tests {
     fn test_decode_hosted_oauth_state_accepts_legacy_formats() {
         use crate::cli::oauth_defaults::decode_hosted_oauth_state;
 
-        let decoded = decode_hosted_oauth_state("kind-deer:abc12345").expect("legacy prefixed");
-        assert_eq!(decoded.flow_id, "abc12345");
+        let decoded = decode_hosted_oauth_state("kind-deer:abc123").expect("legacy prefixed");
+        assert_eq!(decoded.flow_id, "abc123");
         assert_eq!(decoded.instance_name.as_deref(), Some("kind-deer"));
         assert!(decoded.is_legacy);
 
-        let decoded = decode_hosted_oauth_state("abc12345").expect("legacy raw");
-        assert_eq!(decoded.flow_id, "abc12345");
+        let decoded = decode_hosted_oauth_state("abc123").expect("legacy raw");
+        assert_eq!(decoded.flow_id, "abc123");
         assert_eq!(decoded.instance_name, None);
         assert!(decoded.is_legacy);
     }
@@ -1914,72 +1864,4 @@ mod tests {
         assert_eq!(decoded_no_instance.instance_name, None);
         assert!(!decoded_no_instance.is_legacy);
     }
-
-    /// Legacy flow IDs that are too short must be rejected (#1443).
-    #[test]
-    fn test_legacy_state_rejects_short_flow_id() {
-        use crate::cli::oauth_defaults::decode_hosted_oauth_state;
-
-        let err = decode_hosted_oauth_state("abc").expect_err("short raw flow_id");
-        assert!(err.contains("too short"), "unexpected error: {err}");
-
-        let err = decode_hosted_oauth_state("inst:abc").expect_err("short prefixed flow_id");
-        assert!(err.contains("too short"), "unexpected error: {err}");
-    }
-
-    /// Legacy flow IDs with invalid characters must be rejected (#1443).
-    #[test]
-    fn test_legacy_state_rejects_invalid_characters() {
-        use crate::cli::oauth_defaults::decode_hosted_oauth_state;
-
-        let err = decode_hosted_oauth_state("flow id with spaces!").expect_err("spaces in flow_id");
-        assert!(
-            err.contains("invalid characters"),
-            "unexpected error: {err}"
-        );
-
-        let err = decode_hosted_oauth_state("inst:flow/id?bad=yes")
-            .expect_err("special chars in prefixed flow_id");
-        assert!(
-            err.contains("invalid characters"),
-            "unexpected error: {err}"
-        );
-    }
-
-    /// Legacy instance names with invalid characters must be rejected (#1444).
-    #[test]
-    fn test_legacy_state_rejects_invalid_instance_name() {
-        use crate::cli::oauth_defaults::decode_hosted_oauth_state;
-
-        let err = decode_hosted_oauth_state("bad instance!:valid-flow-id-12345")
-            .expect_err("invalid instance name");
-        assert!(err.contains("instance name"), "unexpected error: {err}");
-    }
-
-    /// Excessively long legacy flow IDs must be rejected (#1443).
-    #[test]
-    fn test_legacy_state_rejects_oversized_flow_id() {
-        use crate::cli::oauth_defaults::decode_hosted_oauth_state;
-
-        let long_id = "a".repeat(200);
-        let err = decode_hosted_oauth_state(&long_id).expect_err("oversized flow_id");
-        assert!(err.contains("too long"), "unexpected error: {err}");
-    }
-
-    /// Valid legacy flow IDs at boundary lengths are accepted.
-    #[test]
-    fn test_legacy_state_accepts_boundary_lengths() {
-        use crate::cli::oauth_defaults::decode_hosted_oauth_state;
-
-        // Exactly 8 chars (minimum)
-        let decoded = decode_hosted_oauth_state("abcd1234").expect("8-char flow_id");
-        assert_eq!(decoded.flow_id, "abcd1234");
-        assert!(decoded.is_legacy);
-
-        // Exactly 128 chars (maximum)
-        let max_id = "a".repeat(128);
-        let decoded = decode_hosted_oauth_state(&max_id).expect("128-char flow_id");
-        assert_eq!(decoded.flow_id, max_id);
-        assert!(decoded.is_legacy);
-    }
 }

src/config/agent.rs

@@ -1,6 +1,6 @@
 use std::time::Duration;
 
-use crate::config::helpers::{parse_bool_env, parse_option_env, parse_optional_env};
+use crate::config::helpers::{optional_env, parse_bool_env, parse_option_env, parse_optional_env};
 use crate::error::ConfigError;
 use crate::settings::Settings;
 
@@ -31,12 +31,10 @@ pub struct AgentConfig {
     pub auto_approve_tools: bool,
     /// Default timezone for new sessions (IANA name, e.g. "America/New_York").
     pub default_timezone: String,
-    /// Maximum concurrent jobs per user. None = use global max_parallel_jobs.
-    pub max_jobs_per_user: Option<usize>,
     /// Maximum tokens per job (0 = unlimited).
     pub max_tokens_per_job: u64,
     /// Whether the deployment is multi-tenant (multiple users sharing one
-    /// instance). Defaults to false; can be set via AGENT_MULTI_TENANT env var.
+    /// instance). Auto-detected from GATEWAY_USER_TOKENS presence.
     pub multi_tenant: bool,
     /// Maximum concurrent LLM calls per user. None = use default (4).
     pub max_llm_concurrent_per_user: Option<usize>,
@@ -64,7 +62,6 @@ impl AgentConfig {
             max_tool_iterations: 10,
             auto_approve_tools: true,
             default_timezone: "UTC".to_string(),
-            max_jobs_per_user: None,
             max_tokens_per_job: 0,
             multi_tenant: false,
             max_llm_concurrent_per_user: None,
@@ -125,12 +122,13 @@ impl AgentConfig {
                 }
                 tz
             },
-            max_jobs_per_user: parse_option_env("MAX_JOBS_PER_USER")?,
             max_tokens_per_job: parse_optional_env(
                 "AGENT_MAX_TOKENS_PER_JOB",
                 settings.agent.max_tokens_per_job,
             )?,
-            multi_tenant: parse_bool_env("AGENT_MULTI_TENANT", false)?,
+            // Auto-detected from GATEWAY_USER_TOKENS presence. Not a separate
+            // knob — multi-tenant mode is always implied by configuring user tokens.
+            multi_tenant: optional_env("GATEWAY_USER_TOKENS")?.is_some(),
             max_llm_concurrent_per_user: parse_option_env("TENANT_MAX_LLM_CONCURRENT")?,
             max_jobs_concurrent_per_user: parse_option_env("TENANT_MAX_JOBS_CONCURRENT")?,
         })

src/config/channels.rs

@@ -1,11 +1,13 @@
 use std::collections::HashMap;
 use std::path::PathBuf;
 
+use secrecy::SecretString;
+use serde::Deserialize;
+
 use crate::bootstrap::ironclaw_base_dir;
 use crate::config::helpers::{optional_env, parse_bool_env, parse_optional_env};
 use crate::error::ConfigError;
 use crate::settings::Settings;
-use secrecy::SecretString;
 
 /// Channel configurations.
 #[derive(Debug, Clone)]
@@ -43,15 +45,27 @@ pub struct GatewayConfig {
     pub port: u16,
     /// Bearer token for authentication. Random hex generated at startup if unset.
     pub auth_token: Option<String>,
+    pub user_id: String,
     /// Additional user scopes for workspace reads.
     ///
     /// When set, the workspace will be able to read (search, read, list) from
-    /// these additional user scopes while writes remain isolated to the
-    /// authenticated user's own scope.
+    /// these additional user scopes while writes remain isolated to `user_id`.
     /// Parsed from `WORKSPACE_READ_SCOPES` (comma-separated).
     pub workspace_read_scopes: Vec<String>,
     /// Memory layer definitions (JSON in env var, or from external config).
     pub memory_layers: Vec<crate::workspace::layer::MemoryLayer>,
+    /// Multi-user token map. When set, each token maps to a user identity.
+    /// Parsed from `GATEWAY_USER_TOKENS` (JSON string). When absent, falls back
+    /// to single-user mode via `auth_token` + `user_id`.
+    pub user_tokens: Option<HashMap<String, UserTokenConfig>>,
+}
+
+/// Per-user token configuration for multi-user mode.
+#[derive(Debug, Clone, Deserialize)]
+pub struct UserTokenConfig {
+    pub user_id: String,
+    #[serde(default)]
+    pub workspace_read_scopes: Vec<String>,
 }
 
 /// Signal channel configuration (signal-cli daemon HTTP/JSON-RPC).
@@ -118,6 +132,10 @@ impl ChannelsConfig {
 
         let gateway_enabled = parse_bool_env("GATEWAY_ENABLED", cs.gateway_enabled)?;
         let gateway = if gateway_enabled {
+            let user_id = optional_env("GATEWAY_USER_ID")?
+                .or_else(|| cs.gateway_user_id.clone())
+                .unwrap_or_else(|| owner_id.to_string());
+
             let memory_layers: Vec<crate::workspace::layer::MemoryLayer> =
                 match optional_env("MEMORY_LAYERS")? {
                     Some(json_str) => {
@@ -126,7 +144,7 @@ impl ChannelsConfig {
                             message: format!("must be valid JSON array of layer objects: {e}"),
                         })?
                     }
-                    None => crate::workspace::layer::MemoryLayer::default_for_user(owner_id),
+                    None => crate::workspace::layer::MemoryLayer::default_for_user(&user_id),
                 };
 
             // Validate layer names and scopes
@@ -178,6 +196,41 @@ impl ChannelsConfig {
                 }
             }
 
+            let user_tokens: Option<HashMap<String, UserTokenConfig>> =
+                match optional_env("GATEWAY_USER_TOKENS")? {
+                    Some(json_str) => {
+                        let tokens: HashMap<String, UserTokenConfig> = serde_json::from_str(
+                            &json_str,
+                        )
+                        .map_err(|e| ConfigError::InvalidValue {
+                            key: "GATEWAY_USER_TOKENS".to_string(),
+                            message: format!(
+                                "must be valid JSON object mapping tokens to user configs: {e}"
+                            ),
+                        })?;
+                        if tokens.is_empty() {
+                            return Err(ConfigError::InvalidValue {
+                            key: "GATEWAY_USER_TOKENS".to_string(),
+                            message:
+                                "token map is empty — remove the variable to use single-user mode"
+                                    .to_string(),
+                        });
+                        }
+                        for (tok, cfg) in &tokens {
+                            if cfg.user_id.trim().is_empty() {
+                                return Err(ConfigError::InvalidValue {
+                                    key: "GATEWAY_USER_TOKENS".to_string(),
+                                    message: format!(
+                                        "token '{}...' has an empty user_id",
+                                        &tok[..tok.len().min(8)]
+                                    ),
+                                });
+                            }
+                        }
+                        Some(tokens)
+                    }
+                    None => None,
+                };
             let workspace_read_scopes: Vec<String> = optional_env("WORKSPACE_READ_SCOPES")?
                 .map(|s| {
                     s.split(',')
@@ -205,8 +258,10 @@ impl ChannelsConfig {
                 )?,
                 auth_token: optional_env("GATEWAY_AUTH_TOKEN")?
                     .or_else(|| cs.gateway_auth_token.clone()),
+                user_id,
                 workspace_read_scopes,
                 memory_layers,
+                user_tokens,
             })
         } else {
             None
@@ -361,12 +416,15 @@ mod tests {
             host: "127.0.0.1".to_string(),
             port: 3000,
             auth_token: Some("tok-abc".to_string()),
+            user_id: "default".to_string(),
             workspace_read_scopes: vec![],
             memory_layers: vec![],
+            user_tokens: None,
         };
         assert_eq!(cfg.host, "127.0.0.1");
         assert_eq!(cfg.port, 3000);
         assert_eq!(cfg.auth_token.as_deref(), Some("tok-abc"));
+        assert_eq!(cfg.user_id, "default");
     }
 
     #[test]
@@ -375,8 +433,10 @@ mod tests {
             host: "0.0.0.0".to_string(),
             port: 3001,
             auth_token: None,
+            user_id: "anon".to_string(),
             workspace_read_scopes: vec![],
             memory_layers: vec![],
+            user_tokens: None,
         };
         assert!(cfg.auth_token.is_none());
     }
@@ -503,6 +563,7 @@ mod tests {
         assert_eq!(gateway.host, "127.0.0.3");
         assert_eq!(gateway.port, 9191);
         assert_eq!(gateway.auth_token.as_deref(), Some("tok"));
+        assert_eq!(gateway.user_id, "owner-scope");
 
         let signal = cfg.signal.expect("signal config");
         assert_eq!(signal.account, "+15551234567");

src/config/heartbeat.rs

@@ -21,8 +21,8 @@ pub struct HeartbeatConfig {
     pub quiet_hours_end: Option<u32>,
     /// Timezone for fire_at and quiet hours evaluation (IANA name).
     pub timezone: Option<String>,
-    /// When true, cycle through all users with routines. Controlled via
-    /// HEARTBEAT_MULTI_TENANT env var; defaults to false.
+    /// When true, cycle through all users with routines. Auto-detected from
+    /// GATEWAY_USER_TOKENS or set explicitly via HEARTBEAT_MULTI_TENANT.
     pub multi_tenant: bool,
 }
 
@@ -105,7 +105,12 @@ impl HeartbeatConfig {
                 }
                 tz
             },
-            multi_tenant: parse_bool_env("HEARTBEAT_MULTI_TENANT", false)?,
+            // Auto-detect multi-tenant mode from GATEWAY_USER_TOKENS presence,
+            // or allow explicit override via HEARTBEAT_MULTI_TENANT.
+            multi_tenant: parse_bool_env(
+                "HEARTBEAT_MULTI_TENANT",
+                optional_env("GATEWAY_USER_TOKENS")?.is_some(),
+            )?,
         })
     }
 }

src/config/mod.rs

@@ -1,9 +1,13 @@
 //! Configuration for IronClaw.
 //!
-//! Settings are loaded with priority: env var > database > default.
+//! Settings are loaded from env vars, the DB settings table, TOML config,
+//! and built-in defaults. Priority varies by subsystem:
+//!
+//! - **LLM settings** (backend, model, api_key, base_url): DB > env > default
+//! - **Most other settings** (agent, channels, tunnel, …): env > DB > default
+//!
 //! `DATABASE_URL` lives in `~/.ironclaw/.env` (loaded via dotenvy early
-//! in startup). Everything else comes from env vars, the DB settings
-//! table, or auto-detection.
+//! in startup).
 
 mod agent;
 mod builder;
@@ -186,8 +190,9 @@ impl Config {
 
     /// Load configuration from environment variables and the database.
     ///
-    /// Priority: env var > TOML config file > DB settings > default.
-    /// This is the primary way to load config after DB is connected.
+    /// TOML is loaded first as a base, then DB values are merged on top
+    /// (DB wins over TOML). Individual subsystem resolvers then apply
+    /// their own env-vs-DB priority — see module docs for details.
     pub async fn from_db(
         store: &(dyn crate::db::SettingsStore + Sync),
         user_id: &str,
@@ -196,6 +201,10 @@ impl Config {
     }
 
     /// Load from DB with an optional TOML config file overlay.
+    ///
+    /// TOML is loaded first as a base, then DB values are merged on top
+    /// (DB wins over TOML). Per-subsystem resolvers then decide whether
+    /// env vars or DB values take final precedence — see module docs.
     pub async fn from_db_with_toml(
         store: &(dyn crate::db::SettingsStore + Sync),
         user_id: &str,
@@ -204,19 +213,22 @@ impl Config {
         let _ = dotenvy::dotenv();
         crate::bootstrap::load_ironclaw_env();
 
-        // Load all settings from DB into a Settings struct
-        let mut db_settings = match store.get_all_settings(user_id).await {
-            Ok(map) => Settings::from_db_map(&map),
+        // Start with TOML config as a base (lowest priority among the two).
+        let mut settings = Settings::default();
+        Self::apply_toml_overlay(&mut settings, toml_path)?;
+
+        // Overlay DB settings on top so DB values win over TOML.
+        match store.get_all_settings(user_id).await {
+            Ok(map) => {
+                let db_settings = Settings::from_db_map(&map);
+                settings.merge_from(&db_settings);
+            }
             Err(e) => {
                 tracing::warn!("Failed to load settings from DB, using defaults: {}", e);
-                Settings::default()
             }
         };
 
-        // Overlay TOML config file (values win over DB settings)
-        Self::apply_toml_overlay(&mut db_settings, toml_path)?;
-
-        Self::build(&db_settings).await
+        Self::build(&settings).await
     }
 
     /// Load configuration from environment variables only (no database).
@@ -291,16 +303,38 @@ impl Config {
         user_id: &str,
         toml_path: Option<&std::path::Path>,
     ) -> Result<(), ConfigError> {
-        let settings = if let Some(store) = store {
-            let mut s = match store.get_all_settings(user_id).await {
-                Ok(map) => Settings::from_db_map(&map),
-                Err(_) => Settings::default(),
-            };
+        self.re_resolve_llm_with_secrets(store, user_id, toml_path, None)
+            .await
+    }
+
+    /// Re-resolve LLM config, hydrating API keys from the secrets store.
+    pub async fn re_resolve_llm_with_secrets(
+        &mut self,
+        store: Option<&(dyn crate::db::SettingsStore + Sync)>,
+        user_id: &str,
+        toml_path: Option<&std::path::Path>,
+        secrets: Option<&(dyn crate::secrets::SecretsStore + Send + Sync)>,
+    ) -> Result<(), ConfigError> {
+        let mut settings = if let Some(store) = store {
+            // TOML as base, then DB on top (DB wins).
+            let mut s = Settings::default();
             Self::apply_toml_overlay(&mut s, toml_path)?;
+            if let Ok(map) = store.get_all_settings(user_id).await {
+                let db_settings = Settings::from_db_map(&map);
+                s.merge_from(&db_settings);
+            }
             s
         } else {
             Settings::default()
         };
+
+        // Hydrate API keys from encrypted secrets store into the settings
+        // struct so that LlmConfig::resolve() sees them without any changes
+        // to its synchronous resolution logic.
+        if let Some(secrets) = secrets {
+            hydrate_llm_keys_from_secrets(&mut settings, secrets, user_id).await;
+        }
+
         self.llm = LlmConfig::resolve(&settings)?;
         Ok(())
     }
@@ -501,3 +535,161 @@ fn inject_os_credential_store_tokens(injected: &mut HashMap<String, String>) {
         tracing::debug!("Refreshed ANTHROPIC_OAUTH_TOKEN from OS credential store");
     }
 }
+
+/// Hydrate LLM API keys from the secrets store into the settings struct.
+///
+/// Called after loading settings from DB but before `LlmConfig::resolve()`.
+/// Populates `api_key` fields that were stripped from settings during the
+/// write path and stored encrypted in the secrets store instead.
+pub async fn hydrate_llm_keys_from_secrets(
+    settings: &mut Settings,
+    secrets: &(dyn crate::secrets::SecretsStore + Send + Sync),
+    user_id: &str,
+) {
+    // Hydrate builtin overrides
+    for (provider_id, override_val) in settings.llm_builtin_overrides.iter_mut() {
+        if override_val.api_key.is_some() {
+            continue; // Already has a key (legacy plaintext or TOML)
+        }
+        let secret_name = format!("llm_builtin_{}_api_key", provider_id);
+        if let Ok(decrypted) = secrets.get_decrypted(user_id, &secret_name).await {
+            override_val.api_key = Some(decrypted.expose().to_string());
+        }
+    }
+
+    // Hydrate custom providers
+    for provider in settings.llm_custom_providers.iter_mut() {
+        if provider.api_key.is_some() {
+            continue;
+        }
+        let secret_name = format!("llm_custom_{}_api_key", provider.id);
+        if let Ok(decrypted) = secrets.get_decrypted(user_id, &secret_name).await {
+            provider.api_key = Some(decrypted.expose().to_string());
+        }
+    }
+}
+
+/// Migrate plaintext API keys from the settings table to the encrypted secrets store.
+///
+/// Idempotent: skips keys that are already in the secrets store.
+/// After migration, strips plaintext keys from the settings table.
+pub async fn migrate_plaintext_llm_keys(
+    settings_store: &(dyn crate::db::SettingsStore + Sync),
+    secrets: &(dyn crate::secrets::SecretsStore + Send + Sync),
+    user_id: &str,
+) {
+    let settings_map = match settings_store.get_all_settings(user_id).await {
+        Ok(m) => m,
+        Err(_) => return,
+    };
+
+    let mut migrated = 0u32;
+
+    // Migrate builtin overrides
+    if let Some(obj) = settings_map
+        .get("llm_builtin_overrides")
+        .and_then(|v| v.as_object())
+    {
+        let mut sanitized = obj.clone();
+        for (provider_id, override_val) in obj {
+            if let Some(api_key) = override_val.get("api_key").and_then(|v| v.as_str()) {
+                if api_key.is_empty() {
+                    continue;
+                }
+                let secret_name = format!("llm_builtin_{}_api_key", provider_id);
+                if !secrets.exists(user_id, &secret_name).await.unwrap_or(false)
+                    && let Err(e) = secrets
+                        .create(
+                            user_id,
+                            crate::secrets::CreateSecretParams {
+                                name: secret_name.clone(),
+                                value: secrecy::SecretString::from(api_key.to_string()),
+                                provider: Some(provider_id.clone()),
+                                expires_at: None,
+                            },
+                        )
+                        .await
+                {
+                    tracing::warn!("Failed to migrate key for builtin '{}': {}", provider_id, e);
+                    continue;
+                }
+                if let Some(o) = sanitized
+                    .get_mut(provider_id)
+                    .and_then(|v| v.as_object_mut())
+                {
+                    o.remove("api_key");
+                }
+                migrated += 1;
+            }
+        }
+        if migrated > 0 {
+            let _ = settings_store
+                .set_setting(
+                    user_id,
+                    "llm_builtin_overrides",
+                    &serde_json::Value::Object(sanitized),
+                )
+                .await;
+        }
+    }
+
+    // Migrate custom providers
+    let before = migrated;
+    if let Some(arr) = settings_map
+        .get("llm_custom_providers")
+        .and_then(|v| v.as_array())
+    {
+        let mut sanitized = arr.clone();
+        for (idx, provider_val) in arr.iter().enumerate() {
+            let provider_id = provider_val
+                .get("id")
+                .and_then(|v| v.as_str())
+                .unwrap_or("");
+            if provider_id.is_empty() {
+                continue;
+            }
+            if let Some(api_key) = provider_val.get("api_key").and_then(|v| v.as_str()) {
+                if api_key.is_empty() {
+                    continue;
+                }
+                let secret_name = format!("llm_custom_{}_api_key", provider_id);
+                if !secrets.exists(user_id, &secret_name).await.unwrap_or(false)
+                    && let Err(e) = secrets
+                        .create(
+                            user_id,
+                            crate::secrets::CreateSecretParams {
+                                name: secret_name.clone(),
+                                value: secrecy::SecretString::from(api_key.to_string()),
+                                provider: Some(provider_id.to_string()),
+                                expires_at: None,
+                            },
+                        )
+                        .await
+                {
+                    tracing::warn!("Failed to migrate key for custom '{}': {}", provider_id, e);
+                    continue;
+                }
+                if let Some(o) = sanitized[idx].as_object_mut() {
+                    o.remove("api_key");
+                }
+                migrated += 1;
+            }
+        }
+        if migrated > before {
+            let _ = settings_store
+                .set_setting(
+                    user_id,
+                    "llm_custom_providers",
+                    &serde_json::Value::Array(sanitized),
+                )
+                .await;
+        }
+    }
+
+    if migrated > 0 {
+        tracing::info!(
+            "Migrated {} plaintext LLM API key(s) to encrypted secrets store",
+            migrated
+        );
+    }
+}

src/context/manager.rs

@@ -195,20 +195,6 @@ impl ContextManager {
             .collect()
     }
 
-    /// Count jobs consuming a parallel execution slot for a specific user.
-    ///
-    /// Uses `is_parallel_blocking()` (Pending/InProgress/Stuck) rather than
-    /// `is_active()`, so Completed/Submitted jobs don't count against the
-    /// per-user concurrency limit.
-    pub async fn parallel_blocking_count_for(&self, user_id: &str) -> usize {
-        self.contexts
-            .read()
-            .await
-            .iter()
-            .filter(|(_, c)| c.user_id == user_id && c.state.is_parallel_blocking())
-            .count()
-    }
-
     /// List all job IDs for a specific user.
     pub async fn all_jobs_for(&self, user_id: &str) -> Vec<Uuid> {
         self.contexts

src/db/libsql/mod.rs

@@ -12,11 +12,11 @@ mod routines;
 mod sandbox;
 mod settings;
 mod tool_failures;
-mod users;
 mod workspace;
 
 use std::path::Path;
 use std::sync::Arc;
+use std::sync::atomic::{AtomicBool, Ordering};
 
 use async_trait::async_trait;
 use chrono::{DateTime, NaiveDateTime, Utc};
@@ -33,6 +33,8 @@ use crate::workspace::MemoryDocument;
 
 use crate::db::libsql_migrations;
 
+static NAIVE_TIMESTAMP_LOGGED: AtomicBool = AtomicBool::new(false);
+
 /// Explicit column list for routines table (matches positional access in `row_to_routine_libsql`).
 pub(crate) const ROUTINE_COLUMNS: &str = "\
     id, name, description, user_id, enabled, \
@@ -164,11 +166,13 @@ impl LibSqlBackend {
 ///
 /// Returns an error if none of the formats match.
 pub(crate) fn parse_timestamp(s: &str) -> Result<DateTime<Utc>, String> {
-    let log_naive_timestamp = || {
-        tracing::warn!(
-            timestamp = %s,
-            "parsed naive timestamp, assuming UTC — consider migrating to RFC 3339"
-        );
+    let log_naive_timestamp_once = || {
+        if !NAIVE_TIMESTAMP_LOGGED.swap(true, Ordering::Relaxed) {
+            tracing::debug!(
+                timestamp = %s,
+                "parsed naive timestamp without timezone; assuming UTC for backward compatibility"
+            );
+        }
     };
 
     // RFC 3339 (our canonical write format)
@@ -177,12 +181,12 @@ pub(crate) fn parse_timestamp(s: &str) -> Result<DateTime<Utc>, String> {
     }
     // Naive with fractional seconds (legacy or SQLite datetime() output)
     if let Ok(ndt) = NaiveDateTime::parse_from_str(s, "%Y-%m-%d %H:%M:%S%.f") {
-        log_naive_timestamp();
+        log_naive_timestamp_once();
         return Ok(ndt.and_utc());
     }
     // Naive without fractional seconds (legacy format)
     if let Ok(ndt) = NaiveDateTime::parse_from_str(s, "%Y-%m-%d %H:%M:%S") {
-        log_naive_timestamp();
+        log_naive_timestamp_once();
         return Ok(ndt.and_utc());
     }
     Err(format!("unparseable timestamp: {:?}", s))
@@ -434,7 +438,7 @@ mod tests {
     use chrono::{TimeZone, Utc};
 
     use crate::db::Database;
-    use crate::db::libsql::{LibSqlBackend, fmt_ts, normalize_notify_user, parse_timestamp};
+    use crate::db::libsql::{LibSqlBackend, normalize_notify_user, parse_timestamp};
 
     #[test]
     fn test_normalize_notify_user_treats_legacy_default_as_missing() {
@@ -463,15 +467,6 @@ mod tests {
         assert_eq!(naive_without_millis, expected);
     }
 
-    #[test]
-    fn test_fmt_ts_roundtrips_through_parse_timestamp() {
-        let original = Utc.with_ymd_and_hms(2026, 6, 15, 8, 30, 45).unwrap()
-            + chrono::Duration::milliseconds(123);
-        let formatted = fmt_ts(&original);
-        let parsed = parse_timestamp(&formatted).unwrap();
-        assert_eq!(parsed, original);
-    }
-
     #[tokio::test]
     async fn test_libsql_now_format_is_rfc3339_and_parseable() {
         let backend = LibSqlBackend::new_memory().await.unwrap();

src/db/libsql_migrations.rs

@@ -579,36 +579,6 @@ INSERT OR IGNORE INTO leak_detection_patterns (id, name, pattern, severity, acti
     ('550e8400-e29b-41d4-a716-446655440011', 'mailchimp_api_key', '[a-f0-9]{32}-us[0-9]{1,2}', 'medium', 'block', 1, strftime('%Y-%m-%dT%H:%M:%fZ', 'now')),
     ('550e8400-e29b-41d4-a716-446655440012', 'high_entropy_hex', '(?<![a-fA-F0-9])[a-fA-F0-9]{64}(?![a-fA-F0-9])', 'medium', 'warn', 1, strftime('%Y-%m-%dT%H:%M:%fZ', 'now'));
 
-
--- ==================== User management (V14) ====================
-
-CREATE TABLE IF NOT EXISTS users (
-    id TEXT PRIMARY KEY,
-    email TEXT UNIQUE,
-    display_name TEXT NOT NULL,
-    status TEXT NOT NULL DEFAULT 'active',
-    role TEXT NOT NULL DEFAULT 'member',
-    created_at TEXT NOT NULL DEFAULT (strftime('%Y-%m-%dT%H:%M:%fZ', 'now')),
-    updated_at TEXT NOT NULL DEFAULT (strftime('%Y-%m-%dT%H:%M:%fZ', 'now')),
-    last_login_at TEXT,
-    created_by TEXT REFERENCES users(id) ON DELETE SET NULL,
-    metadata TEXT NOT NULL DEFAULT '{}'
-);
-
-CREATE TABLE IF NOT EXISTS api_tokens (
-    id TEXT PRIMARY KEY,
-    user_id TEXT NOT NULL REFERENCES users(id) ON DELETE CASCADE,
-    token_hash BLOB NOT NULL,
-    token_prefix TEXT NOT NULL,
-    name TEXT NOT NULL,
-    expires_at TEXT,
-    last_used_at TEXT,
-    created_at TEXT NOT NULL DEFAULT (strftime('%Y-%m-%dT%H:%M:%fZ', 'now')),
-    revoked_at TEXT
-);
-CREATE INDEX IF NOT EXISTS idx_api_tokens_user ON api_tokens(user_id);
-CREATE INDEX IF NOT EXISTS idx_api_tokens_hash ON api_tokens(token_hash);
-
 "#;
 
 /// Incremental migrations applied after the base schema.
@@ -753,38 +723,6 @@ CREATE INDEX IF NOT EXISTS idx_routines_event_triggers
     WHERE enabled = 1 AND trigger_type IN ('event', 'system_event');
 
 PRAGMA foreign_keys=ON;
-"#,
-    ),
-    (
-        14,
-        "users",
-        r#"
-CREATE TABLE IF NOT EXISTS users (
-    id TEXT PRIMARY KEY,
-    email TEXT UNIQUE,
-    display_name TEXT NOT NULL,
-    status TEXT NOT NULL DEFAULT 'active',
-    role TEXT NOT NULL DEFAULT 'member',
-    created_at TEXT NOT NULL DEFAULT (strftime('%Y-%m-%dT%H:%M:%fZ', 'now')),
-    updated_at TEXT NOT NULL DEFAULT (strftime('%Y-%m-%dT%H:%M:%fZ', 'now')),
-    last_login_at TEXT,
-    created_by TEXT REFERENCES users(id) ON DELETE SET NULL,
-    metadata TEXT NOT NULL DEFAULT '{}'
-);
-
-CREATE TABLE IF NOT EXISTS api_tokens (
-    id TEXT PRIMARY KEY,
-    user_id TEXT NOT NULL REFERENCES users(id) ON DELETE CASCADE,
-    token_hash BLOB NOT NULL,
-    token_prefix TEXT NOT NULL,
-    name TEXT NOT NULL,
-    expires_at TEXT,
-    last_used_at TEXT,
-    created_at TEXT NOT NULL DEFAULT (strftime('%Y-%m-%dT%H:%M:%fZ', 'now')),
-    revoked_at TEXT
-);
-CREATE INDEX IF NOT EXISTS idx_api_tokens_user ON api_tokens(user_id);
-CREATE INDEX IF NOT EXISTS idx_api_tokens_hash ON api_tokens(token_hash);
 "#,
     ),
 ];

src/db/mod.rs

@@ -309,43 +309,6 @@ async fn validate_postgres(pool: &deadpool_postgres::Pool) -> Result<(), Databas
     Ok(())
 }
 
-// ==================== User management record types ====================
-
-/// A registered user.
-#[derive(Debug, Clone)]
-pub struct UserRecord {
-    /// User identifier (string, matches existing `user_id` throughout the codebase).
-    pub id: String,
-    pub email: Option<String>,
-    pub display_name: String,
-    /// `active`, `suspended`, or `deactivated`.
-    pub status: String,
-    /// `admin` or `member`.
-    pub role: String,
-    pub created_at: DateTime<Utc>,
-    pub updated_at: DateTime<Utc>,
-    pub last_login_at: Option<DateTime<Utc>>,
-    /// Who created/invited this user (nullable for bootstrap users).
-    pub created_by: Option<String>,
-    pub metadata: serde_json::Value,
-}
-
-/// An API token for authenticating requests (hash stored, never plaintext).
-#[derive(Debug, Clone)]
-pub struct ApiTokenRecord {
-    pub id: Uuid,
-    pub user_id: String,
-    /// Human label (e.g. "my-laptop", "ci-bot").
-    pub name: String,
-    /// First 8 hex chars of the plaintext token for display/identification.
-    pub token_prefix: String,
-    pub expires_at: Option<DateTime<Utc>>,
-    pub last_used_at: Option<DateTime<Utc>>,
-    pub created_at: DateTime<Utc>,
-    /// Soft-revoke timestamp. Non-null means revoked.
-    pub revoked_at: Option<DateTime<Utc>>,
-}
-
 // ==================== Sub-traits ====================
 //
 // Each sub-trait groups related persistence methods. The `Database` supertrait
@@ -798,113 +761,6 @@ pub trait WorkspaceStore: Send + Sync {
     }
 }
 
-#[async_trait]
-pub trait UserStore: Send + Sync {
-    // ---- Users ----
-
-    /// Create a new user record.
-    async fn create_user(&self, user: &UserRecord) -> Result<(), DatabaseError>;
-    /// Get a user by their string id.
-    async fn get_user(&self, id: &str) -> Result<Option<UserRecord>, DatabaseError>;
-    /// Get a user by email address.
-    async fn get_user_by_email(&self, email: &str) -> Result<Option<UserRecord>, DatabaseError>;
-    /// List users, optionally filtered by status.
-    async fn list_users(&self, status: Option<&str>) -> Result<Vec<UserRecord>, DatabaseError>;
-    /// Update a user's status (active/suspended/deactivated).
-    async fn update_user_status(&self, id: &str, status: &str) -> Result<(), DatabaseError>;
-    /// Update a user's role (admin/member).
-    async fn update_user_role(&self, id: &str, role: &str) -> Result<(), DatabaseError>;
-    /// Update a user's display name and metadata.
-    async fn update_user_profile(
-        &self,
-        id: &str,
-        display_name: &str,
-        metadata: &serde_json::Value,
-    ) -> Result<(), DatabaseError>;
-    /// Record a login timestamp.
-    async fn record_login(&self, id: &str) -> Result<(), DatabaseError>;
-
-    // ---- API Tokens ----
-
-    /// Create a new API token. The `token_hash` is SHA-256 of the plaintext.
-    async fn create_api_token(
-        &self,
-        user_id: &str,
-        name: &str,
-        token_hash: &[u8; 32],
-        token_prefix: &str,
-        expires_at: Option<DateTime<Utc>>,
-    ) -> Result<ApiTokenRecord, DatabaseError>;
-    /// List tokens for a user (never includes the hash).
-    async fn list_api_tokens(&self, user_id: &str) -> Result<Vec<ApiTokenRecord>, DatabaseError>;
-    /// Soft-revoke a token. Returns false if the token doesn't exist or doesn't belong to the user.
-    async fn revoke_api_token(&self, token_id: Uuid, user_id: &str) -> Result<bool, DatabaseError>;
-    /// Look up a token by hash, returning the token record and its owning user.
-    /// Only returns active (non-revoked, non-expired) tokens for active users.
-    async fn authenticate_token(
-        &self,
-        token_hash: &[u8; 32],
-    ) -> Result<Option<(ApiTokenRecord, UserRecord)>, DatabaseError>;
-    /// Update `last_used_at` for a token.
-    async fn record_token_usage(&self, token_id: Uuid) -> Result<(), DatabaseError>;
-
-    /// Check whether any user records exist (for first-run bootstrap detection).
-    async fn has_any_users(&self) -> Result<bool, DatabaseError>;
-
-    /// Delete a user and all their data across all user-scoped tables.
-    /// Returns false if the user doesn't exist.
-    async fn delete_user(&self, id: &str) -> Result<bool, DatabaseError>;
-
-    /// Get per-user LLM usage stats for a time period.
-    /// Aggregates from llm_calls via agent_jobs.user_id.
-    async fn user_usage_stats(
-        &self,
-        user_id: Option<&str>,
-        since: DateTime<Utc>,
-    ) -> Result<Vec<UserUsageStats>, DatabaseError>;
-
-    /// Lightweight per-user summary stats (job count, total cost, last active).
-    /// Used by the admin users list to show inline stats.
-    async fn user_summary_stats(
-        &self,
-        user_id: Option<&str>,
-    ) -> Result<Vec<UserSummaryStats>, DatabaseError>;
-
-    /// Create a user and their initial API token atomically.
-    /// If either operation fails, both are rolled back.
-    async fn create_user_with_token(
-        &self,
-        user: &UserRecord,
-        token_name: &str,
-        token_hash: &[u8; 32],
-        token_prefix: &str,
-        expires_at: Option<DateTime<Utc>>,
-    ) -> Result<ApiTokenRecord, DatabaseError>;
-}
-
-/// Per-user LLM usage statistics.
-#[derive(Debug, Clone)]
-pub struct UserUsageStats {
-    pub user_id: String,
-    pub model: String,
-    pub call_count: i64,
-    pub input_tokens: i64,
-    pub output_tokens: i64,
-    pub total_cost: Decimal,
-}
-
-/// Lightweight per-user summary for the admin users list.
-#[derive(Debug, Clone)]
-pub struct UserSummaryStats {
-    pub user_id: String,
-    /// Total agent jobs created by this user.
-    pub job_count: i64,
-    /// Total LLM spend across all jobs (all-time).
-    pub total_cost: Decimal,
-    /// Most recent activity (latest job or LLM call timestamp).
-    pub last_active_at: Option<DateTime<Utc>>,
-}
-
 /// Backend-agnostic database supertrait.
 ///
 /// Combines all sub-traits into one. Existing `Arc<dyn Database>` consumers
@@ -918,7 +774,6 @@ pub trait Database:
     + ToolFailureStore
     + SettingsStore
     + WorkspaceStore
-    + UserStore
     + Send
     + Sync
 {

src/db/postgres.rs

@@ -16,8 +16,8 @@ use crate::agent::routine::{Routine, RoutineRun, RunStatus};
 use crate::config::DatabaseConfig;
 use crate::context::{ActionRecord, JobContext, JobState};
 use crate::db::{
-    ApiTokenRecord, ConversationStore, Database, JobStore, RoutineStore, SandboxStore,
-    SettingsStore, ToolFailureStore, UserRecord, UserStore, WorkspaceStore,
+    ConversationStore, Database, JobStore, RoutineStore, SandboxStore, SettingsStore,
+    ToolFailureStore, WorkspaceStore,
 };
 use crate::error::{DatabaseError, WorkspaceError};
 use crate::history::{
@@ -786,115 +786,3 @@ impl WorkspaceStore for PgBackend {
             .await
     }
 }
-
-// ==================== UserStore ====================
-
-#[async_trait]
-impl UserStore for PgBackend {
-    async fn create_user(&self, user: &UserRecord) -> Result<(), DatabaseError> {
-        self.store.create_user(user).await
-    }
-
-    async fn get_user(&self, id: &str) -> Result<Option<UserRecord>, DatabaseError> {
-        self.store.get_user(id).await
-    }
-
-    async fn get_user_by_email(&self, email: &str) -> Result<Option<UserRecord>, DatabaseError> {
-        self.store.get_user_by_email(email).await
-    }
-
-    async fn list_users(&self, status: Option<&str>) -> Result<Vec<UserRecord>, DatabaseError> {
-        self.store.list_users(status).await
-    }
-
-    async fn update_user_status(&self, id: &str, status: &str) -> Result<(), DatabaseError> {
-        self.store.update_user_status(id, status).await
-    }
-
-    async fn update_user_role(&self, id: &str, role: &str) -> Result<(), DatabaseError> {
-        self.store.update_user_role(id, role).await
-    }
-
-    async fn update_user_profile(
-        &self,
-        id: &str,
-        display_name: &str,
-        metadata: &serde_json::Value,
-    ) -> Result<(), DatabaseError> {
-        self.store
-            .update_user_profile(id, display_name, metadata)
-            .await
-    }
-
-    async fn record_login(&self, id: &str) -> Result<(), DatabaseError> {
-        self.store.record_login(id).await
-    }
-
-    async fn create_api_token(
-        &self,
-        user_id: &str,
-        name: &str,
-        token_hash: &[u8; 32],
-        token_prefix: &str,
-        expires_at: Option<DateTime<Utc>>,
-    ) -> Result<ApiTokenRecord, DatabaseError> {
-        self.store
-            .create_api_token(user_id, name, token_hash, token_prefix, expires_at)
-            .await
-    }
-
-    async fn list_api_tokens(&self, user_id: &str) -> Result<Vec<ApiTokenRecord>, DatabaseError> {
-        self.store.list_api_tokens(user_id).await
-    }
-
-    async fn revoke_api_token(&self, token_id: Uuid, user_id: &str) -> Result<bool, DatabaseError> {
-        self.store.revoke_api_token(token_id, user_id).await
-    }
-
-    async fn authenticate_token(
-        &self,
-        token_hash: &[u8; 32],
-    ) -> Result<Option<(ApiTokenRecord, UserRecord)>, DatabaseError> {
-        self.store.authenticate_token(token_hash).await
-    }
-
-    async fn record_token_usage(&self, token_id: Uuid) -> Result<(), DatabaseError> {
-        self.store.record_token_usage(token_id).await
-    }
-
-    async fn has_any_users(&self) -> Result<bool, DatabaseError> {
-        self.store.has_any_users().await
-    }
-
-    async fn delete_user(&self, id: &str) -> Result<bool, DatabaseError> {
-        self.store.delete_user(id).await
-    }
-
-    async fn user_usage_stats(
-        &self,
-        user_id: Option<&str>,
-        since: DateTime<Utc>,
-    ) -> Result<Vec<crate::db::UserUsageStats>, DatabaseError> {
-        self.store.user_usage_stats(user_id, since).await
-    }
-
-    async fn user_summary_stats(
-        &self,
-        user_id: Option<&str>,
-    ) -> Result<Vec<crate::db::UserSummaryStats>, DatabaseError> {
-        self.store.user_summary_stats(user_id).await
-    }
-
-    async fn create_user_with_token(
-        &self,
-        user: &UserRecord,
-        token_name: &str,
-        token_hash: &[u8; 32],
-        token_prefix: &str,
-        expires_at: Option<DateTime<Utc>>,
-    ) -> Result<ApiTokenRecord, DatabaseError> {
-        self.store
-            .create_user_with_token(user, token_name, token_hash, token_prefix, expires_at)
-            .await
-    }
-}

src/db/tls.rs

@@ -2,8 +2,7 @@
 //!
 //! Builds a [`deadpool_postgres::Pool`] with the appropriate TLS connector
 //! based on the configured [`SslMode`].  Uses `rustls` with system root
-//! certificates, falling back to Mozilla's bundled roots via `webpki-roots`
-//! when the system store is empty (common in minimal container images).
+//! certificates — the same TLS stack that `reqwest` already uses for HTTP.
 
 use deadpool_postgres::{Pool, Runtime};
 use thiserror::Error;
@@ -20,15 +19,9 @@ pub enum CreatePoolError {
     TlsConfig(#[from] rustls::Error),
 }
 
-/// Build a rustls-based TLS connector.
-///
-/// Tries the platform's native certificate store first. If that yields zero
-/// certificates (slim container images, missing ca-certificates package),
-/// falls back to Mozilla's root certificates bundled via `webpki-roots`.
+/// Build a rustls-based TLS connector using the platform's root certificate store.
 fn make_rustls_connector() -> Result<MakeRustlsConnect, rustls::Error> {
     let mut root_store = rustls::RootCertStore::empty();
-
-    // Try native certs first.
     let native = rustls_native_certs::load_native_certs();
     for e in &native.errors {
         tracing::warn!("error loading system root certs: {e}");
@@ -38,14 +31,11 @@ fn make_rustls_connector() -> Result<MakeRustlsConnect, rustls::Error> {
             tracing::warn!("skipping invalid system root cert: {e}");
         }
     }
-
-    // Fall back to bundled Mozilla roots when the system store is empty.
     if root_store.is_empty() {
-        tracing::info!("no system root certificates found, using bundled Mozilla roots");
-        root_store.extend(webpki_roots::TLS_SERVER_ROOTS.iter().cloned());
+        tracing::error!("no system root certificates found -- TLS connections will fail");
     }
-
-    // Pick the ring crypto provider (same one reqwest uses).
+    // `--all-features` brings in both aws-lc-rs and ring-backed rustls providers.
+    // Pick the same ring provider reqwest already uses so postgres TLS setup stays deterministic.
     let config = rustls::ClientConfig::builder_with_provider(
         rustls::crypto::ring::default_provider().into(),
     )
@@ -58,7 +48,7 @@ fn make_rustls_connector() -> Result<MakeRustlsConnect, rustls::Error> {
 /// Create a [`deadpool_postgres::Pool`] with the appropriate TLS connector.
 ///
 /// - `Disable` → plain TCP (no TLS)
-/// - `Prefer` / `Require` → rustls with system or bundled root certificates
+/// - `Prefer` / `Require` → rustls with system root certificates
 ///
 /// **Note:** `Prefer` and `Require` currently behave identically — both
 /// provide a TLS connector and will fail if the server rejects the TLS
@@ -91,6 +81,7 @@ mod tests {
     fn create_pool_disable_mode() {
         let mut config = deadpool_postgres::Config::new();
         config.url = Some("postgres://localhost/test".to_string());
+        // Should succeed — pool is created lazily, no actual connection needed.
         let pool = create_pool(&config, SslMode::Disable);
         assert!(pool.is_ok());
     }

src/error.rs

@@ -395,49 +395,16 @@ pub enum RoutineError {
     Database { reason: String },
 
     #[error("LLM call failed: {reason}")]
-    LlmFailed {
-        reason: String,
-        /// Partial token count consumed before the failure (if any).
-        /// Used to accumulate usage across retry attempts.
-        partial_tokens: Option<i32>,
-        /// Whether the underlying LLM error was classified as retryable.
-        /// Set at the `LlmError` → `RoutineError` conversion site using
-        /// `crate::llm::retry::is_retryable()`, avoiding fragile substring
-        /// matching on the stringified reason.
-        retryable: bool,
-    },
+    LlmFailed { reason: String },
 
     #[error("Failed to dispatch full job: {reason}")]
     JobDispatchFailed { reason: String },
 
     #[error("LLM returned empty content")]
-    EmptyResponse {
-        /// Tokens consumed by the call that produced the empty response.
-        partial_tokens: Option<i32>,
-    },
+    EmptyResponse,
 
     #[error("LLM response truncated (finish_reason=length) with no content")]
-    TruncatedResponse {
-        /// Tokens consumed by the call that produced the truncated response.
-        partial_tokens: Option<i32>,
-    },
-}
-
-impl RoutineError {
-    /// Whether this error is transient and worth retrying with backoff.
-    ///
-    /// Retryable: LLM failures where the underlying `LlmError` was classified
-    /// as retryable by `crate::llm::retry::is_retryable()`, empty responses,
-    /// and truncated responses.
-    /// Non-retryable: configuration errors, authorization, resource limits,
-    /// DB errors, and LLM failures caused by auth/content-policy/context-length.
-    pub fn is_retryable(&self) -> bool {
-        match self {
-            RoutineError::LlmFailed { retryable, .. } => *retryable,
-            RoutineError::EmptyResponse { .. } | RoutineError::TruncatedResponse { .. } => true,
-            _ => false,
-        }
-    }
+    TruncatedResponse,
 }
 
 /// Result type alias for the agent.
@@ -547,99 +514,6 @@ mod tests {
         assert!(msg.contains("bad format"), "Should mention reason: {msg}");
     }
 
-    #[test]
-    fn routine_error_retryable_classification() {
-        // Transient errors should be retryable
-        assert!(
-            RoutineError::LlmFailed {
-                reason: "timeout".into(),
-                partial_tokens: None,
-                retryable: true,
-            }
-            .is_retryable()
-        );
-        // Non-retryable LLM error
-        assert!(
-            !RoutineError::LlmFailed {
-                reason: "timeout".into(),
-                partial_tokens: None,
-                retryable: false,
-            }
-            .is_retryable()
-        );
-        assert!(
-            RoutineError::EmptyResponse {
-                partial_tokens: None
-            }
-            .is_retryable()
-        );
-        assert!(
-            RoutineError::TruncatedResponse {
-                partial_tokens: None
-            }
-            .is_retryable()
-        );
-
-        // Hard failures should NOT be retryable
-        assert!(
-            !RoutineError::Disabled {
-                name: "test".into()
-            }
-            .is_retryable()
-        );
-        assert!(
-            !RoutineError::JobDispatchFailed {
-                reason: "no docker".into()
-            }
-            .is_retryable()
-        );
-        assert!(
-            !RoutineError::Database {
-                reason: "conn refused".into()
-            }
-            .is_retryable()
-        );
-        assert!(!RoutineError::NotFound { id: Uuid::new_v4() }.is_retryable());
-        assert!(!RoutineError::NotAuthorized { id: Uuid::new_v4() }.is_retryable());
-        assert!(
-            !RoutineError::MaxConcurrent {
-                name: "test".into()
-            }
-            .is_retryable()
-        );
-        assert!(
-            !RoutineError::UnknownTriggerType {
-                trigger_type: "x".into()
-            }
-            .is_retryable()
-        );
-        assert!(
-            !RoutineError::UnknownActionType {
-                action_type: "x".into()
-            }
-            .is_retryable()
-        );
-        assert!(
-            !RoutineError::MissingField {
-                context: "c".into(),
-                field: "f".into()
-            }
-            .is_retryable()
-        );
-        assert!(
-            !RoutineError::InvalidCron {
-                reason: "bad".into()
-            }
-            .is_retryable()
-        );
-        assert!(
-            !RoutineError::UnknownRunStatus {
-                status: "bad".into()
-            }
-            .is_retryable()
-        );
-    }
-
     #[test]
     fn top_level_error_from_conversions() {
         let config_err = ConfigError::MissingEnvVar("TEST".to_string());

src/extensions/manager.rs

@@ -53,38 +53,6 @@ struct HostedOAuthFlowStart {
     flow: crate::cli::oauth_defaults::PendingOAuthFlow,
 }
 
-#[derive(Debug, Default)]
-struct SecretCleanupPlan {
-    base_secrets: HashSet<String>,
-    companion_secrets: HashMap<String, HashSet<String>>,
-}
-
-impl SecretCleanupPlan {
-    fn add_base_secret(&mut self, secret_name: impl AsRef<str>) {
-        self.base_secrets
-            .insert(secret_name.as_ref().to_lowercase());
-    }
-
-    fn add_companion_secret(
-        &mut self,
-        base_secret_name: impl AsRef<str>,
-        companion_secret_name: impl AsRef<str>,
-    ) {
-        self.companion_secrets
-            .entry(base_secret_name.as_ref().to_lowercase())
-            .or_default()
-            .insert(companion_secret_name.as_ref().to_lowercase());
-    }
-}
-
-fn oauth_refresh_secret_name(secret_name: &str) -> String {
-    format!("{}_refresh_token", secret_name.to_lowercase())
-}
-
-fn oauth_scopes_secret_name(secret_name: &str) -> String {
-    format!("{}_scopes", secret_name.to_lowercase())
-}
-
 fn normalize_oauth_callback_path(path: &str) -> String {
     let trimmed_path = path.trim_end_matches('/');
     if trimmed_path.is_empty() {
@@ -1634,10 +1602,6 @@ impl ExtensionManager {
 
         match kind {
             ExtensionKind::McpServer => {
-                let cleanup_plan = self
-                    .collect_secret_cleanup_plan(name, kind, user_id)
-                    .await?;
-
                 // Unregister tools with this server's prefix
                 let tool_names: Vec<String> = self
                     .tool_registry
@@ -1659,9 +1623,6 @@ impl ExtensionManager {
                     .await
                     .map_err(|e| ExtensionError::Config(e.to_string()))?;
 
-                self.cleanup_uninstalled_extension_secrets(cleanup_plan, user_id)
-                    .await;
-
                 Ok(format!(
                     "Removed MCP server '{}' and {} tool(s)",
                     name,
@@ -1669,10 +1630,6 @@ impl ExtensionManager {
                 ))
             }
             ExtensionKind::WasmTool => {
-                let cleanup_plan = self
-                    .collect_secret_cleanup_plan(name, kind, user_id)
-                    .await?;
-
                 // Unregister from tool registry
                 self.tool_registry.unregister(name).await;
 
@@ -1717,16 +1674,9 @@ impl ExtensionManager {
                     let _ = tokio::fs::remove_file(&cap_path).await;
                 }
 
-                self.cleanup_uninstalled_extension_secrets(cleanup_plan, user_id)
-                    .await;
-
                 Ok(format!("Removed WASM tool '{}'", name))
             }
             ExtensionKind::WasmChannel => {
-                let cleanup_plan = self
-                    .collect_secret_cleanup_plan(name, kind, user_id)
-                    .await?;
-
                 // Remove from active set and persist
                 self.active_channel_names.write().await.remove(name);
                 self.persist_active_channels(user_id).await;
@@ -1752,9 +1702,6 @@ impl ExtensionManager {
                     let _ = tokio::fs::remove_file(&cap_path).await;
                 }
 
-                self.cleanup_uninstalled_extension_secrets(cleanup_plan, user_id)
-                    .await;
-
                 Ok(format!(
                     "Removed channel '{}'. Restart IronClaw for the change to take effect.",
                     name
@@ -3052,258 +2999,6 @@ impl ExtensionManager {
         crate::tools::wasm::CapabilitiesFile::from_bytes(&cap_bytes).ok()
     }
 
-    async fn load_channel_capabilities(
-        &self,
-        name: &str,
-    ) -> Option<crate::channels::wasm::ChannelCapabilitiesFile> {
-        let cap_path = self
-            .wasm_channels_dir
-            .join(format!("{}.capabilities.json", name));
-        let cap_bytes = tokio::fs::read(&cap_path).await.ok()?;
-        crate::channels::wasm::ChannelCapabilitiesFile::from_bytes(&cap_bytes).ok()
-    }
-
-    async fn collect_secret_cleanup_plan(
-        &self,
-        name: &str,
-        kind: ExtensionKind,
-        user_id: &str,
-    ) -> Result<SecretCleanupPlan, ExtensionError> {
-        let mut plan = SecretCleanupPlan::default();
-
-        match kind {
-            ExtensionKind::WasmTool => {
-                if let Some(cap) = self.load_tool_capabilities(name).await {
-                    for secret_name in Self::tool_secret_names(&cap) {
-                        plan.add_base_secret(secret_name);
-                    }
-
-                    if let Some(auth) = cap.auth {
-                        plan.add_base_secret(&auth.secret_name);
-                        plan.add_companion_secret(
-                            &auth.secret_name,
-                            oauth_refresh_secret_name(&auth.secret_name),
-                        );
-                        plan.add_companion_secret(
-                            &auth.secret_name,
-                            oauth_scopes_secret_name(&auth.secret_name),
-                        );
-                    }
-                }
-            }
-            ExtensionKind::WasmChannel => {
-                if let Some(cap) = self.load_channel_capabilities(name).await {
-                    for secret_name in Self::channel_secret_names(&cap) {
-                        plan.add_base_secret(secret_name);
-                    }
-                }
-            }
-            ExtensionKind::McpServer => {
-                let server = self
-                    .get_mcp_server(name, user_id)
-                    .await
-                    .map_err(|e| ExtensionError::Config(e.to_string()))?;
-                let token_secret_name = server.token_secret_name();
-                plan.add_base_secret(&token_secret_name);
-                plan.add_base_secret(server.client_id_secret_name());
-                // MCP OAuth can persist companion secrets through two paths:
-                // the MCP auth helper uses `mcp_<name>_refresh_token`, while the
-                // hosted gateway callback stores companions alongside the access
-                // token secret (`<token_secret>_refresh_token` / `_scopes`).
-                plan.add_companion_secret(&token_secret_name, server.refresh_token_secret_name());
-                plan.add_companion_secret(
-                    &token_secret_name,
-                    oauth_refresh_secret_name(&token_secret_name),
-                );
-                plan.add_companion_secret(
-                    &token_secret_name,
-                    oauth_scopes_secret_name(&token_secret_name),
-                );
-            }
-            ExtensionKind::ChannelRelay => {}
-        }
-
-        Ok(plan)
-    }
-
-    async fn cleanup_uninstalled_extension_secrets(&self, plan: SecretCleanupPlan, user_id: &str) {
-        let referenced_secrets = match self.collect_referenced_secret_names(user_id).await {
-            Ok(secret_names) => secret_names,
-            Err(error) => {
-                tracing::warn!(
-                    user_id,
-                    error,
-                    "Failed to determine which secrets are still referenced; keeping secrets"
-                );
-                return;
-            }
-        };
-
-        for base_secret in &plan.base_secrets {
-            if referenced_secrets.contains(base_secret) {
-                continue;
-            }
-
-            self.delete_secret_best_effort(user_id, base_secret).await;
-
-            if let Some(companion_secrets) = plan.companion_secrets.get(base_secret) {
-                for companion_secret in companion_secrets {
-                    if !referenced_secrets.contains(companion_secret) {
-                        self.delete_secret_best_effort(user_id, companion_secret)
-                            .await;
-                    }
-                }
-            }
-        }
-    }
-
-    async fn delete_secret_best_effort(&self, user_id: &str, secret_name: &str) {
-        if let Err(error) = self.secrets.delete(user_id, secret_name).await {
-            tracing::warn!(
-                user_id,
-                secret_name,
-                error = %error,
-                "Failed to delete secret while uninstalling extension"
-            );
-        }
-    }
-
-    async fn collect_referenced_secret_names(
-        &self,
-        user_id: &str,
-    ) -> Result<HashSet<String>, String> {
-        let mut referenced_secret_names = HashSet::new();
-
-        let tools = discover_tools(&self.wasm_tools_dir)
-            .await
-            .map_err(|e| format!("discover tools: {e}"))?;
-        for (tool_name, discovered_tool) in &tools {
-            let cap = self
-                .load_tool_capabilities(tool_name)
-                .await
-                .ok_or_else(|| {
-                    let path = discovered_tool
-                        .capabilities_path
-                        .as_ref()
-                        .map(|path| path.display().to_string())
-                        .unwrap_or_else(|| format!("{} (missing)", tool_name));
-                    format!("load tool capabilities for {tool_name}: {path}")
-                })?;
-            referenced_secret_names.extend(Self::tool_secret_names(&cap));
-        }
-
-        let channels = crate::channels::wasm::discover_channels(&self.wasm_channels_dir)
-            .await
-            .map_err(|e| format!("discover channels: {e}"))?;
-        for (channel_name, discovered_channel) in &channels {
-            let cap = self
-                .load_channel_capabilities(channel_name)
-                .await
-                .ok_or_else(|| {
-                    let path = discovered_channel
-                        .capabilities_path
-                        .as_ref()
-                        .map(|path| path.display().to_string())
-                        .unwrap_or_else(|| format!("{} (missing)", channel_name));
-                    format!("load channel capabilities for {channel_name}: {path}")
-                })?;
-            referenced_secret_names.extend(Self::channel_secret_names(&cap));
-        }
-
-        let mcp_servers = self
-            .load_mcp_servers(user_id)
-            .await
-            .map_err(|e| format!("load MCP servers: {e}"))?;
-        for server in &mcp_servers.servers {
-            referenced_secret_names.extend(Self::mcp_server_secret_names(server));
-        }
-
-        Ok(referenced_secret_names)
-    }
-
-    fn tool_secret_names(cap: &crate::tools::wasm::CapabilitiesFile) -> HashSet<String> {
-        let mut names = HashSet::new();
-
-        if let Some(auth) = &cap.auth {
-            names.insert(auth.secret_name.to_lowercase());
-        }
-        if let Some(setup) = &cap.setup {
-            names.extend(
-                setup
-                    .required_secrets
-                    .iter()
-                    .map(|secret| secret.name.to_lowercase()),
-            );
-        }
-        if let Some(http) = &cap.http {
-            names.extend(
-                http.credentials
-                    .values()
-                    .map(|credential| credential.secret_name.to_lowercase()),
-            );
-        }
-        if let Some(webhook) = &cap.webhook {
-            if let Some(secret_name) = &webhook.secret_name {
-                names.insert(secret_name.to_lowercase());
-            }
-            if let Some(secret_name) = &webhook.signature_key_secret_name {
-                names.insert(secret_name.to_lowercase());
-            }
-            if let Some(secret_name) = &webhook.hmac_secret_name {
-                names.insert(secret_name.to_lowercase());
-            }
-        }
-
-        names
-    }
-
-    fn channel_secret_names(
-        cap: &crate::channels::wasm::ChannelCapabilitiesFile,
-    ) -> HashSet<String> {
-        let mut names: HashSet<String> = cap
-            .setup
-            .required_secrets
-            .iter()
-            .map(|secret| secret.name.to_lowercase())
-            .collect();
-
-        if let Some(http) = cap.capabilities.tool.http.as_ref() {
-            names.extend(
-                http.credentials
-                    .values()
-                    .map(|credential| credential.secret_name.to_lowercase()),
-            );
-        }
-
-        if let Some(webhook) = cap
-            .capabilities
-            .channel
-            .as_ref()
-            .and_then(|channel| channel.webhook.as_ref())
-        {
-            if webhook.secret_header.is_some() || webhook.secret_name.is_some() {
-                names.insert(cap.webhook_secret_name().to_lowercase());
-            }
-            if let Some(secret_name) = cap.signature_key_secret_name() {
-                names.insert(secret_name.to_lowercase());
-            }
-            if let Some(secret_name) = cap.hmac_secret_name() {
-                names.insert(secret_name.to_lowercase());
-            }
-        }
-
-        names
-    }
-
-    fn mcp_server_secret_names(server: &McpServerConfig) -> HashSet<String> {
-        [
-            server.token_secret_name().to_lowercase(),
-            server.client_id_secret_name().to_lowercase(),
-        ]
-        .into_iter()
-        .collect()
-    }
-
     /// Collect merged OAuth scopes from all installed tools sharing the same secret_name.
     ///
     /// When multiple tools share an OAuth provider (e.g., google-calendar and google-drive
@@ -6338,8 +6033,6 @@ mod tests {
         ExtensionError, ExtensionKind, ExtensionSource, InstallResult, VerificationChallenge,
     };
     use crate::pairing::PairingStore;
-    use crate::secrets::CreateSecretParams;
-    use crate::tools::mcp::McpServerConfig;
 
     fn require(condition: bool, message: impl Into<String>) -> Result<(), String> {
         if condition {
@@ -6660,38 +6353,6 @@ mod tests {
         tools_dir
     }
 
-    fn write_test_channel(
-        dir: &std::path::Path,
-        name: &str,
-        capabilities_json: &str,
-    ) -> std::path::PathBuf {
-        let channels_dir = dir.join("channels");
-        std::fs::create_dir_all(&channels_dir).expect("channels dir");
-        std::fs::write(
-            channels_dir.join(format!("{name}.wasm")),
-            b"not-a-real-wasm",
-        )
-        .expect("wasm");
-        std::fs::write(
-            channels_dir.join(format!("{name}.capabilities.json")),
-            capabilities_json,
-        )
-        .expect("capabilities");
-        channels_dir
-    }
-
-    async fn store_test_secret(
-        manager: &crate::extensions::manager::ExtensionManager,
-        name: &str,
-        value: &str,
-    ) {
-        manager
-            .secrets
-            .create("test", CreateSecretParams::new(name, value))
-            .await
-            .expect("store secret");
-    }
-
     #[test]
     fn test_setting_value_is_present() {
         assert!(
@@ -7762,13 +7423,7 @@ mod tests {
         // Regression: remove() only checked channel_runtime for shutdown, missing
         // relay-only mode where only relay_channel_manager is set.
         let dir = tempfile::tempdir().expect("temp dir");
-        let (store, _db_dir) = make_test_store().await;
-        let mgr = make_test_manager_with_dirs(
-            None,
-            dir.path().join("tools"),
-            dir.path().join("channels"),
-            Some(store),
-        );
+        let mgr = make_test_manager(None, dir.path().to_path_buf());
 
         // Set up relay channel manager with a stub channel
         let cm = Arc::new(crate::channels::ChannelManager::new());
@@ -7795,8 +7450,6 @@ mod tests {
                 .await
                 .expect("store team_id");
         }
-        store_test_secret(&mgr, "relay:slack-relay:oauth_state", "nonce").await;
-        store_test_secret(&mgr, "relay:slack-relay:stream_token", "legacy-token").await;
 
         // Verify channel exists before removal
         assert!(cm.get_channel("slack-relay").await.is_some());
@@ -7825,30 +7478,6 @@ mod tests {
             cm.get_channel("slack-relay").await.is_none(),
             "relay channel should be removed from the channel manager"
         );
-        assert!(
-            !mgr.secrets
-                .exists("test", "relay:slack-relay:oauth_state")
-                .await
-                .expect("oauth state exists query"),
-            "relay oauth_state secret should be removed"
-        );
-        assert!(
-            !mgr.secrets
-                .exists("test", "relay:slack-relay:stream_token")
-                .await
-                .expect("stream token exists query"),
-            "relay legacy stream token should be removed"
-        );
-        assert_eq!(
-            mgr.store
-                .as_ref()
-                .expect("store")
-                .get_setting("test", "relay:slack-relay:team_id")
-                .await
-                .expect("team_id query"),
-            None,
-            "relay team_id setting should be removed"
-        );
     }
 
     #[tokio::test]
@@ -7956,185 +7585,6 @@ mod tests {
         );
     }
 
-    #[tokio::test]
-    async fn test_remove_wasm_tool_deletes_unique_secrets() {
-        let dir = tempfile::tempdir().expect("temp dir");
-        let tools_dir = write_test_tool(
-            dir.path(),
-            "github",
-            r#"{
-                "name": "github",
-                "auth": { "secret_name": "github_token" },
-                "setup": {
-                    "required_secrets": [
-                        { "name": "github_client_secret", "prompt": "GitHub client secret for testing cleanup behavior." }
-                    ]
-                },
-                "http": {
-                    "credentials": {
-                        "service_token": {
-                            "secret_name": "github_service_token",
-                            "location": { "type": "bearer" }
-                        }
-                    }
-                },
-                "webhook": {
-                    "hmac_secret_name": "github_webhook_secret"
-                }
-            }"#,
-        );
-        let mgr = make_test_manager_with_dirs(None, tools_dir, dir.path().join("channels"), None);
-
-        store_test_secret(&mgr, "github_token", "access-token").await;
-        store_test_secret(&mgr, "github_token_refresh_token", "refresh-token").await;
-        store_test_secret(&mgr, "github_token_scopes", "repo workflow").await;
-        store_test_secret(&mgr, "github_client_secret", "client-secret").await;
-        store_test_secret(&mgr, "github_service_token", "service-token").await;
-        store_test_secret(&mgr, "github_webhook_secret", "webhook-secret").await;
-
-        mgr.remove("github", "test")
-            .await
-            .expect("remove should succeed");
-
-        for secret_name in [
-            "github_token",
-            "github_token_refresh_token",
-            "github_token_scopes",
-            "github_client_secret",
-            "github_service_token",
-            "github_webhook_secret",
-        ] {
-            assert!(
-                !mgr.secrets
-                    .exists("test", secret_name)
-                    .await
-                    .expect("exists query"),
-                "secret {secret_name} should be deleted"
-            );
-        }
-    }
-
-    #[tokio::test]
-    async fn test_remove_wasm_tool_keeps_secrets_when_other_tool_capabilities_missing() {
-        let dir = tempfile::tempdir().expect("temp dir");
-        let tools_dir = write_test_tool(
-            dir.path(),
-            "github",
-            r#"{
-                "name": "github",
-                "auth": { "secret_name": "shared_token" }
-            }"#,
-        );
-        std::fs::write(tools_dir.join("broken.wasm"), b"fake-tool").expect("write tool");
-
-        let mgr = make_test_manager_with_dirs(None, tools_dir, dir.path().join("channels"), None);
-        store_test_secret(&mgr, "shared_token", "access-token").await;
-        store_test_secret(&mgr, "shared_token_refresh_token", "refresh-token").await;
-        store_test_secret(&mgr, "shared_token_scopes", "repo").await;
-
-        mgr.remove("github", "test")
-            .await
-            .expect("remove should succeed");
-
-        for secret_name in [
-            "shared_token",
-            "shared_token_refresh_token",
-            "shared_token_scopes",
-        ] {
-            assert!(
-                mgr.secrets
-                    .exists("test", secret_name)
-                    .await
-                    .expect("exists query"),
-                "secret {secret_name} should be retained when reference detection is uncertain"
-            );
-        }
-    }
-
-    #[tokio::test]
-    async fn test_remove_wasm_tool_keeps_shared_secrets_until_last_extension() {
-        let dir = tempfile::tempdir().expect("temp dir");
-        write_test_tool(
-            dir.path(),
-            "google-calendar",
-            r#"{
-                "name": "google-calendar",
-                "auth": { "secret_name": "google_oauth_token" },
-                "setup": {
-                    "required_secrets": [
-                        { "name": "google_oauth_client_id", "prompt": "Google OAuth client id for cleanup testing." },
-                        { "name": "google_oauth_client_secret", "prompt": "Google OAuth client secret for cleanup testing." }
-                    ]
-                }
-            }"#,
-        );
-        let tools_dir = write_test_tool(
-            dir.path(),
-            "google-drive",
-            r#"{
-                "name": "google-drive",
-                "auth": { "secret_name": "google_oauth_token" },
-                "setup": {
-                    "required_secrets": [
-                        { "name": "google_oauth_client_id", "prompt": "Google OAuth client id for cleanup testing." },
-                        { "name": "google_oauth_client_secret", "prompt": "Google OAuth client secret for cleanup testing." }
-                    ]
-                }
-            }"#,
-        );
-        let mgr = make_test_manager_with_dirs(None, tools_dir, dir.path().join("channels"), None);
-
-        for (secret_name, value) in [
-            ("google_oauth_token", "access-token"),
-            ("google_oauth_token_refresh_token", "refresh-token"),
-            ("google_oauth_token_scopes", "calendar drive"),
-            ("google_oauth_client_id", "client-id"),
-            ("google_oauth_client_secret", "client-secret"),
-        ] {
-            store_test_secret(&mgr, secret_name, value).await;
-        }
-
-        mgr.remove("google-calendar", "test")
-            .await
-            .expect("first remove should succeed");
-
-        for secret_name in [
-            "google_oauth_token",
-            "google_oauth_token_refresh_token",
-            "google_oauth_token_scopes",
-            "google_oauth_client_id",
-            "google_oauth_client_secret",
-        ] {
-            assert!(
-                mgr.secrets
-                    .exists("test", secret_name)
-                    .await
-                    .expect("exists query"),
-                "shared secret {secret_name} should remain while google-drive is still installed"
-            );
-        }
-
-        mgr.remove("google-drive", "test")
-            .await
-            .expect("second remove should succeed");
-
-        for secret_name in [
-            "google_oauth_token",
-            "google_oauth_token_refresh_token",
-            "google_oauth_token_scopes",
-            "google_oauth_client_id",
-            "google_oauth_client_secret",
-        ] {
-            assert!(
-                !mgr.secrets
-                    .exists("test", secret_name)
-                    .await
-                    .expect("exists query"),
-                "shared secret {secret_name} should be deleted after the last tool is removed"
-            );
-        }
-    }
-
     #[tokio::test]
     async fn test_remove_wasm_channel_clears_activation_error_and_deletes_files() {
         let dir = tempfile::tempdir().expect("temp dir");
@@ -8169,104 +7619,6 @@ mod tests {
         );
     }
 
-    #[tokio::test]
-    async fn test_remove_wasm_channel_deletes_setup_secrets() {
-        let dir = tempfile::tempdir().expect("temp dir");
-        let channels_dir = write_test_channel(
-            dir.path(),
-            "telegram",
-            r#"{
-                "type": "channel",
-                "name": "telegram",
-                "setup": {
-                    "required_secrets": [
-                        {
-                            "name": "telegram_bot_token",
-                            "prompt": "Telegram bot token used to verify uninstall cleanup behavior."
-                        }
-                    ]
-                },
-                "capabilities": {
-                    "http": {
-                        "credentials": {
-                            "tenant_token": {
-                                "secret_name": "telegram_service_token",
-                                "location": { "type": "bearer" }
-                            }
-                        }
-                    },
-                    "channel": {
-                        "webhook": {
-                            "secret_header": "X-Telegram-Bot-Api-Secret-Token",
-                            "secret_name": "telegram_webhook_secret"
-                        }
-                    }
-                }
-            }"#,
-        );
-        let mgr = make_test_manager_with_dirs(None, dir.path().join("tools"), channels_dir, None);
-
-        store_test_secret(&mgr, "telegram_bot_token", "123:telegram-token").await;
-        store_test_secret(&mgr, "telegram_service_token", "tenant-service-token").await;
-        store_test_secret(&mgr, "telegram_webhook_secret", "webhook-secret").await;
-
-        mgr.remove("telegram", "test")
-            .await
-            .expect("remove should succeed");
-
-        for secret_name in [
-            "telegram_bot_token",
-            "telegram_service_token",
-            "telegram_webhook_secret",
-        ] {
-            assert!(
-                !mgr.secrets
-                    .exists("test", secret_name)
-                    .await
-                    .expect("exists query"),
-                "channel secret {secret_name} should be deleted"
-            );
-        }
-    }
-
-    #[tokio::test]
-    async fn test_remove_mcp_server_deletes_stored_secrets() {
-        let dir = tempfile::tempdir().expect("temp dir");
-        let (store, _db_dir) = make_test_store().await;
-        let mgr = make_test_manager_with_dirs(
-            None,
-            dir.path().join("tools"),
-            dir.path().join("channels"),
-            Some(Arc::clone(&store)),
-        );
-        let server = McpServerConfig::new("notion", "https://example.com/mcp");
-        mgr.add_mcp_server(server.clone(), "test")
-            .await
-            .expect("add mcp server");
-
-        store_test_secret(&mgr, &server.token_secret_name(), "access-token").await;
-        store_test_secret(&mgr, &server.refresh_token_secret_name(), "refresh-token").await;
-        store_test_secret(&mgr, &server.client_id_secret_name(), "client-id").await;
-
-        mgr.remove("notion", "test")
-            .await
-            .expect("remove should succeed");
-
-        for secret_name in [
-            server.token_secret_name(),
-            server.refresh_token_secret_name(),
-            server.client_id_secret_name(),
-        ] {
-            assert!(
-                !mgr.secrets
-                    .exists("test", &secret_name)
-                    .await
-                    .expect("exists query"),
-                "MCP secret {secret_name} should be deleted"
-            );
-        }
-    }
-
     #[test]
     fn test_sanitize_url_with_query_params() {
         let url = "https://api.example.com/path?api_key=secret123&token=abc";

src/history/store.rs

@@ -2279,546 +2279,6 @@ impl Store {
     }
 }
 
-// ==================== Users / API Tokens / Invitations ====================
-
-#[cfg(feature = "postgres")]
-use crate::db::{ApiTokenRecord, UserRecord};
-
-#[cfg(feature = "postgres")]
-impl Store {
-    /// Create a new user record.
-    pub async fn create_user(&self, user: &UserRecord) -> Result<(), DatabaseError> {
-        let conn = self.conn().await?;
-        conn.execute(
-            r#"
-            INSERT INTO users (id, email, display_name, status, role, created_at, updated_at, last_login_at, created_by, metadata)
-            VALUES ($1, $2, $3, $4, $5, $6, $7, $8, $9, $10)
-            "#,
-            &[
-                &user.id,
-                &user.email,
-                &user.display_name,
-                &user.status,
-                &user.role,
-                &user.created_at,
-                &user.updated_at,
-                &user.last_login_at,
-                &user.created_by,
-                &user.metadata,
-            ],
-        )
-        .await?;
-        Ok(())
-    }
-
-    /// Get a user by their string id.
-    pub async fn get_user(&self, id: &str) -> Result<Option<UserRecord>, DatabaseError> {
-        let conn = self.conn().await?;
-        let row = conn
-            .query_opt("SELECT id, email, display_name, status, role, created_at, updated_at, last_login_at, created_by, metadata FROM users WHERE id = $1", &[&id])
-            .await?;
-        Ok(row.map(|r| row_to_user(&r)))
-    }
-
-    /// Get a user by email address.
-    pub async fn get_user_by_email(
-        &self,
-        email: &str,
-    ) -> Result<Option<UserRecord>, DatabaseError> {
-        let conn = self.conn().await?;
-        let row = conn
-            .query_opt("SELECT id, email, display_name, status, role, created_at, updated_at, last_login_at, created_by, metadata FROM users WHERE email = $1", &[&email])
-            .await?;
-        Ok(row.map(|r| row_to_user(&r)))
-    }
-
-    /// List users, optionally filtered by status.
-    pub async fn list_users(&self, status: Option<&str>) -> Result<Vec<UserRecord>, DatabaseError> {
-        let conn = self.conn().await?;
-        let rows = match status {
-            Some(s) => {
-                conn.query(
-                    "SELECT id, email, display_name, status, role, created_at, updated_at, last_login_at, created_by, metadata FROM users WHERE status = $1 ORDER BY created_at DESC",
-                    &[&s],
-                )
-                .await?
-            }
-            None => {
-                conn.query("SELECT id, email, display_name, status, role, created_at, updated_at, last_login_at, created_by, metadata FROM users ORDER BY created_at DESC", &[])
-                    .await?
-            }
-        };
-        Ok(rows.iter().map(row_to_user).collect())
-    }
-
-    /// Update a user's status.
-    pub async fn update_user_status(&self, id: &str, status: &str) -> Result<(), DatabaseError> {
-        let conn = self.conn().await?;
-        conn.execute(
-            "UPDATE users SET status = $1, updated_at = NOW() WHERE id = $2",
-            &[&status, &id],
-        )
-        .await?;
-        Ok(())
-    }
-
-    /// Update a user's role (admin/member).
-    pub async fn update_user_role(&self, id: &str, role: &str) -> Result<(), DatabaseError> {
-        let conn = self.conn().await?;
-        conn.execute(
-            "UPDATE users SET role = $1, updated_at = NOW() WHERE id = $2",
-            &[&role, &id],
-        )
-        .await?;
-        Ok(())
-    }
-
-    /// Update a user's display name and metadata.
-    pub async fn update_user_profile(
-        &self,
-        id: &str,
-        display_name: &str,
-        metadata: &serde_json::Value,
-    ) -> Result<(), DatabaseError> {
-        let conn = self.conn().await?;
-        conn.execute(
-            "UPDATE users SET display_name = $1, metadata = $2, updated_at = NOW() WHERE id = $3",
-            &[&display_name, metadata, &id],
-        )
-        .await?;
-        Ok(())
-    }
-
-    /// Record a login timestamp for a user.
-    pub async fn record_login(&self, id: &str) -> Result<(), DatabaseError> {
-        let conn = self.conn().await?;
-        conn.execute(
-            "UPDATE users SET last_login_at = NOW(), updated_at = NOW() WHERE id = $1",
-            &[&id],
-        )
-        .await?;
-        Ok(())
-    }
-
-    /// Create a new API token.
-    pub async fn create_api_token(
-        &self,
-        user_id: &str,
-        name: &str,
-        token_hash: &[u8; 32],
-        token_prefix: &str,
-        expires_at: Option<DateTime<Utc>>,
-    ) -> Result<ApiTokenRecord, DatabaseError> {
-        let conn = self.conn().await?;
-        let id = Uuid::new_v4();
-        let now = Utc::now();
-        conn.execute(
-            r#"
-            INSERT INTO api_tokens (id, user_id, token_hash, token_prefix, name, expires_at, created_at)
-            VALUES ($1, $2, $3, $4, $5, $6, $7)
-            "#,
-            &[
-                &id,
-                &user_id,
-                &token_hash.as_slice(),
-                &token_prefix,
-                &name,
-                &expires_at,
-                &now,
-            ],
-        )
-        .await?;
-        Ok(ApiTokenRecord {
-            id,
-            user_id: user_id.to_string(),
-            name: name.to_string(),
-            token_prefix: token_prefix.to_string(),
-            expires_at,
-            last_used_at: None,
-            created_at: now,
-            revoked_at: None,
-        })
-    }
-
-    /// Create a user and their initial API token atomically in a single transaction.
-    pub async fn create_user_with_token(
-        &self,
-        user: &UserRecord,
-        token_name: &str,
-        token_hash: &[u8; 32],
-        token_prefix: &str,
-        expires_at: Option<DateTime<Utc>>,
-    ) -> Result<ApiTokenRecord, DatabaseError> {
-        let mut conn = self.conn().await?;
-        let tx = conn.transaction().await?;
-
-        tx.execute(
-            r#"
-            INSERT INTO users (id, email, display_name, status, role, created_at, updated_at, last_login_at, created_by, metadata)
-            VALUES ($1, $2, $3, $4, $5, $6, $7, $8, $9, $10)
-            "#,
-            &[
-                &user.id,
-                &user.email,
-                &user.display_name,
-                &user.status,
-                &user.role,
-                &user.created_at,
-                &user.updated_at,
-                &user.last_login_at,
-                &user.created_by,
-                &user.metadata,
-            ],
-        )
-        .await?;
-
-        let id = Uuid::new_v4();
-        let now = Utc::now();
-        tx.execute(
-            r#"
-            INSERT INTO api_tokens (id, user_id, token_hash, token_prefix, name, expires_at, created_at)
-            VALUES ($1, $2, $3, $4, $5, $6, $7)
-            "#,
-            &[
-                &id,
-                &user.id,
-                &token_hash.as_slice(),
-                &token_prefix,
-                &token_name,
-                &expires_at,
-                &now,
-            ],
-        )
-        .await?;
-
-        tx.commit().await?;
-
-        Ok(ApiTokenRecord {
-            id,
-            user_id: user.id.clone(),
-            name: token_name.to_string(),
-            token_prefix: token_prefix.to_string(),
-            expires_at,
-            last_used_at: None,
-            created_at: now,
-            revoked_at: None,
-        })
-    }
-
-    /// List tokens for a user.
-    pub async fn list_api_tokens(
-        &self,
-        user_id: &str,
-    ) -> Result<Vec<ApiTokenRecord>, DatabaseError> {
-        let conn = self.conn().await?;
-        let rows = conn
-            .query(
-                r#"
-                SELECT id, user_id, name, token_prefix, expires_at, last_used_at, created_at, revoked_at
-                FROM api_tokens
-                WHERE user_id = $1
-                ORDER BY created_at DESC
-                "#,
-                &[&user_id],
-            )
-            .await?;
-        Ok(rows.iter().map(row_to_api_token).collect())
-    }
-
-    /// Soft-revoke a token. Returns false if the token doesn't exist or doesn't belong to the user.
-    pub async fn revoke_api_token(
-        &self,
-        token_id: Uuid,
-        user_id: &str,
-    ) -> Result<bool, DatabaseError> {
-        let conn = self.conn().await?;
-        let count = conn
-            .execute(
-                "UPDATE api_tokens SET revoked_at = NOW() WHERE id = $1 AND user_id = $2 AND revoked_at IS NULL",
-                &[&token_id, &user_id],
-            )
-            .await?;
-        Ok(count > 0)
-    }
-
-    /// Authenticate a token by hash. Returns the token record and its owning user
-    /// if the token is active (non-revoked, non-expired) and the user is active.
-    pub async fn authenticate_token(
-        &self,
-        token_hash: &[u8; 32],
-    ) -> Result<Option<(ApiTokenRecord, UserRecord)>, DatabaseError> {
-        let conn = self.conn().await?;
-        let row = conn
-            .query_opt(
-                r#"
-                SELECT t.id, t.user_id, t.name, t.token_prefix, t.expires_at, t.last_used_at, t.created_at, t.revoked_at,
-                       u.id as u_id, u.email, u.display_name, u.status, u.role, u.created_at as u_created_at, u.updated_at, u.last_login_at, u.created_by, u.metadata
-                FROM api_tokens t
-                JOIN users u ON t.user_id = u.id
-                WHERE t.token_hash = $1
-                  AND t.revoked_at IS NULL
-                  AND (t.expires_at IS NULL OR t.expires_at > NOW())
-                  AND u.status = 'active'
-                "#,
-                &[&token_hash.as_slice()],
-            )
-            .await?;
-        Ok(row.map(|r| {
-            let token = ApiTokenRecord {
-                id: r.get("id"),
-                user_id: r.get("user_id"),
-                name: r.get("name"),
-                token_prefix: r.get("token_prefix"),
-                expires_at: r.get("expires_at"),
-                last_used_at: r.get("last_used_at"),
-                created_at: r.get("created_at"),
-                revoked_at: r.get("revoked_at"),
-            };
-            let user = UserRecord {
-                id: r.get("u_id"),
-                email: r.get("email"),
-                display_name: r.get("display_name"),
-                status: r.get("status"),
-                role: r.get("role"),
-                created_at: r.get("u_created_at"),
-                updated_at: r.get("updated_at"),
-                last_login_at: r.get("last_login_at"),
-                created_by: r.get("created_by"),
-                metadata: r.get("metadata"),
-            };
-            (token, user)
-        }))
-    }
-
-    /// Update `last_used_at` for a token.
-    pub async fn record_token_usage(&self, token_id: Uuid) -> Result<(), DatabaseError> {
-        let conn = self.conn().await?;
-        conn.execute(
-            "UPDATE api_tokens SET last_used_at = NOW() WHERE id = $1",
-            &[&token_id],
-        )
-        .await?;
-        Ok(())
-    }
-
-    /// Check whether any user records exist.
-    pub async fn has_any_users(&self) -> Result<bool, DatabaseError> {
-        let conn = self.conn().await?;
-        let row = conn
-            .query_one(
-                "SELECT EXISTS(SELECT 1 FROM users LIMIT 1) as has_users",
-                &[],
-            )
-            .await?;
-        Ok(row.get("has_users"))
-    }
-
-    /// Delete a user and all their data across all user-scoped tables.
-    /// Returns false if the user doesn't exist.
-    pub async fn delete_user(&self, id: &str) -> Result<bool, DatabaseError> {
-        let mut conn = self.conn().await?;
-        let tx = conn
-            .transaction()
-            .await
-            .map_err(|e| DatabaseError::Query(e.to_string()))?;
-        // Delete from child tables first to avoid FK violations.
-        // job_events must come before agent_jobs (FK without CASCADE).
-        // agent_jobs cascades to job_actions, llm_calls, estimation_snapshots.
-        // conversations cascades to conversation_messages.
-        // memory_documents cascades to memory_chunks.
-        // routines cascades to routine_runs.
-        // api_tokens cascade automatically via FK on users.
-        for table in &[
-            "settings",
-            "heartbeat_state",
-            "tool_rate_limit_state",
-            "secret_usage_log",
-            "leak_detection_events",
-            "secrets",
-            "wasm_tools",
-            "routines",
-            "memory_documents",
-            "conversations",
-        ] {
-            tx.execute(&format!("DELETE FROM {table} WHERE user_id = $1"), &[&id])
-                .await
-                .map_err(|e| DatabaseError::Query(e.to_string()))?;
-        }
-        // job_events references agent_jobs(id) without CASCADE — delete via subquery.
-        tx.execute(
-            "DELETE FROM job_events WHERE job_id IN (SELECT id FROM agent_jobs WHERE user_id = $1)",
-            &[&id],
-        )
-        .await
-        .map_err(|e| DatabaseError::Query(e.to_string()))?;
-        tx.execute("DELETE FROM agent_jobs WHERE user_id = $1", &[&id])
-            .await
-            .map_err(|e| DatabaseError::Query(e.to_string()))?;
-        // Nullify self-referencing created_by before deleting the user
-        tx.execute(
-            "UPDATE users SET created_by = NULL WHERE created_by = $1",
-            &[&id],
-        )
-        .await
-        .map_err(|e| DatabaseError::Query(e.to_string()))?;
-        // api_tokens cascade automatically via FK
-        let result = tx
-            .execute("DELETE FROM users WHERE id = $1", &[&id])
-            .await
-            .map_err(|e| DatabaseError::Query(e.to_string()))?;
-        tx.commit()
-            .await
-            .map_err(|e| DatabaseError::Query(e.to_string()))?;
-        Ok(result > 0)
-    }
-
-    /// Get per-user LLM usage stats for a time period.
-    /// Aggregates from llm_calls via agent_jobs.user_id.
-    pub async fn user_usage_stats(
-        &self,
-        user_id: Option<&str>,
-        since: DateTime<Utc>,
-    ) -> Result<Vec<crate::db::UserUsageStats>, DatabaseError> {
-        let conn = self.conn().await?;
-        let rows = if let Some(uid) = user_id {
-            conn.query(
-                r#"
-                SELECT COALESCE(j.user_id, c.user_id) as user_id,
-                       l.model, COUNT(*) as call_count,
-                       COALESCE(SUM(l.input_tokens), 0) as input_tokens,
-                       COALESCE(SUM(l.output_tokens), 0) as output_tokens,
-                       COALESCE(SUM(l.cost), 0) as total_cost
-                FROM llm_calls l
-                LEFT JOIN agent_jobs j ON l.job_id = j.id
-                LEFT JOIN conversations c ON l.conversation_id = c.id
-                WHERE l.created_at >= $1
-                  AND COALESCE(j.user_id, c.user_id) = $2
-                GROUP BY COALESCE(j.user_id, c.user_id), l.model
-                ORDER BY total_cost DESC
-                "#,
-                &[&since, &uid],
-            )
-            .await?
-        } else {
-            conn.query(
-                r#"
-                SELECT COALESCE(j.user_id, c.user_id) as user_id,
-                       l.model, COUNT(*) as call_count,
-                       COALESCE(SUM(l.input_tokens), 0) as input_tokens,
-                       COALESCE(SUM(l.output_tokens), 0) as output_tokens,
-                       COALESCE(SUM(l.cost), 0) as total_cost
-                FROM llm_calls l
-                LEFT JOIN agent_jobs j ON l.job_id = j.id
-                LEFT JOIN conversations c ON l.conversation_id = c.id
-                WHERE l.created_at >= $1
-                GROUP BY COALESCE(j.user_id, c.user_id), l.model
-                ORDER BY total_cost DESC
-                "#,
-                &[&since],
-            )
-            .await?
-        };
-        let mut stats = Vec::with_capacity(rows.len());
-        for row in &rows {
-            stats.push(crate::db::UserUsageStats {
-                user_id: row.get("user_id"),
-                model: row.get("model"),
-                call_count: row.get("call_count"),
-                input_tokens: row.get("input_tokens"),
-                output_tokens: row.get("output_tokens"),
-                total_cost: row.get("total_cost"),
-            });
-        }
-        Ok(stats)
-    }
-
-    /// Lightweight per-user summary stats (job count, total cost, last active).
-    ///
-    /// Aggregates from `llm_calls`, resolving user_id via either `agent_jobs`
-    /// (for background job calls) or `conversations` (for chat calls where
-    /// `job_id` is NULL).
-    pub async fn user_summary_stats(
-        &self,
-        user_id: Option<&str>,
-    ) -> Result<Vec<crate::db::UserSummaryStats>, DatabaseError> {
-        let conn = self.conn().await?;
-        let rows = if let Some(uid) = user_id {
-            conn.query(
-                r#"
-                SELECT
-                    COALESCE(j.user_id, c.user_id) AS user_id,
-                    COUNT(DISTINCT j.id) AS job_count,
-                    COALESCE(SUM(l.cost), 0) AS total_cost,
-                    MAX(l.created_at) AS last_active_at
-                FROM llm_calls l
-                LEFT JOIN agent_jobs j ON l.job_id = j.id
-                LEFT JOIN conversations c ON l.conversation_id = c.id
-                WHERE COALESCE(j.user_id, c.user_id) = $1
-                GROUP BY COALESCE(j.user_id, c.user_id)
-                "#,
-                &[&uid],
-            )
-            .await?
-        } else {
-            conn.query(
-                r#"
-                SELECT
-                    COALESCE(j.user_id, c.user_id) AS user_id,
-                    COUNT(DISTINCT j.id) AS job_count,
-                    COALESCE(SUM(l.cost), 0) AS total_cost,
-                    MAX(l.created_at) AS last_active_at
-                FROM llm_calls l
-                LEFT JOIN agent_jobs j ON l.job_id = j.id
-                LEFT JOIN conversations c ON l.conversation_id = c.id
-                GROUP BY COALESCE(j.user_id, c.user_id)
-                "#,
-                &[],
-            )
-            .await?
-        };
-        let mut stats = Vec::with_capacity(rows.len());
-        for row in &rows {
-            stats.push(crate::db::UserSummaryStats {
-                user_id: row.get("user_id"),
-                job_count: row.get("job_count"),
-                total_cost: row.get("total_cost"),
-                last_active_at: row.get("last_active_at"),
-            });
-        }
-        Ok(stats)
-    }
-}
-
-#[cfg(feature = "postgres")]
-fn row_to_user(row: &tokio_postgres::Row) -> UserRecord {
-    UserRecord {
-        id: row.get("id"),
-        email: row.get("email"),
-        display_name: row.get("display_name"),
-        status: row.get("status"),
-        role: row.get("role"),
-        created_at: row.get("created_at"),
-        updated_at: row.get("updated_at"),
-        last_login_at: row.get("last_login_at"),
-        created_by: row.get("created_by"),
-        metadata: row.get("metadata"),
-    }
-}
-
-#[cfg(feature = "postgres")]
-fn row_to_api_token(row: &tokio_postgres::Row) -> ApiTokenRecord {
-    ApiTokenRecord {
-        id: row.get("id"),
-        user_id: row.get("user_id"),
-        name: row.get("name"),
-        token_prefix: row.get("token_prefix"),
-        expires_at: row.get("expires_at"),
-        last_used_at: row.get("last_used_at"),
-        created_at: row.get("created_at"),
-        revoked_at: row.get("revoked_at"),
-    }
-}
-
 #[cfg(test)]
 mod tests {
     use super::*;

src/llm/circuit_breaker.rs

@@ -234,7 +234,6 @@ fn is_transient(err: &LlmError) -> bool {
         LlmError::RequestFailed { .. }
             | LlmError::RateLimited { .. }
             | LlmError::InvalidResponse { .. }
-            | LlmError::EmptyResponse { .. }
             | LlmError::SessionExpired { .. }
             | LlmError::SessionRenewalFailed { .. }
             | LlmError::Http(_)

src/llm/error.rs

@@ -17,9 +17,6 @@ pub enum LlmError {
     #[error("Invalid response from {provider}: {reason}")]
     InvalidResponse { provider: String, reason: String },
 
-    #[error("Empty response from {provider}: no content returned")]
-    EmptyResponse { provider: String },
-
     #[error("Context length exceeded: {used} tokens used, {limit} allowed")]
     ContextLengthExceeded { used: usize, limit: usize },
 

src/llm/github_copilot.rs

@@ -231,8 +231,9 @@ impl LlmProvider for GithubCopilotProvider {
                 .choices
                 .into_iter()
                 .next()
-                .ok_or_else(|| LlmError::EmptyResponse {
+                .ok_or_else(|| LlmError::InvalidResponse {
                     provider: "github_copilot".to_string(),
+                    reason: "No choices in response".to_string(),
                 })?;
 
         let (content, _tool_calls) = extract_choice_content(&choice);
@@ -308,8 +309,9 @@ impl LlmProvider for GithubCopilotProvider {
                 .choices
                 .into_iter()
                 .next()
-                .ok_or_else(|| LlmError::EmptyResponse {
+                .ok_or_else(|| LlmError::InvalidResponse {
                     provider: "github_copilot".to_string(),
+                    reason: "No choices in response".to_string(),
                 })?;
 
         let (content, tool_calls) = extract_choice_content(&choice);

src/llm/mod.rs

@@ -93,6 +93,8 @@ pub async fn create_llm_provider(
 ) -> Result<Arc<dyn LlmProvider>, LlmError> {
     let timeout = config.request_timeout_secs;
 
+    tracing::info!(backend = %config.backend, "Creating LLM provider");
+
     if config.backend == "nearai" || config.backend == "near_ai" || config.backend == "near" {
         return create_llm_provider_with_config(&config.nearai, session, timeout);
     }

src/llm/nearai_chat.rs

@@ -490,8 +490,9 @@ impl LlmProvider for NearAiChatProvider {
                 .choices
                 .into_iter()
                 .next()
-                .ok_or_else(|| LlmError::EmptyResponse {
+                .ok_or_else(|| LlmError::InvalidResponse {
                     provider: "nearai_chat".to_string(),
+                    reason: "No choices in response".to_string(),
                 })?;
 
         // Fall back to reasoning_content when content is null (same as
@@ -569,8 +570,9 @@ impl LlmProvider for NearAiChatProvider {
                 .choices
                 .into_iter()
                 .next()
-                .ok_or_else(|| LlmError::EmptyResponse {
+                .ok_or_else(|| LlmError::InvalidResponse {
                     provider: "nearai_chat".to_string(),
+                    reason: "No choices in response".to_string(),
                 })?;
 
         let tool_calls: Vec<ToolCall> = choice

src/llm/retry.rs

@@ -48,7 +48,6 @@ pub(crate) fn is_retryable(err: &LlmError) -> bool {
         LlmError::RequestFailed { .. }
             | LlmError::RateLimited { .. }
             | LlmError::InvalidResponse { .. }
-            | LlmError::EmptyResponse { .. }
             | LlmError::SessionRenewalFailed { .. }
             | LlmError::Http(_)
             | LlmError::Io(_)

src/llm/rig_adapter.rs

@@ -301,6 +301,10 @@ fn convert_messages(messages: &[ChatMessage]) -> (Option<String>, Vec<RigMessage
             }
             crate::llm::Role::User => {
                 if msg.content_parts.is_empty() {
+                    // Skip empty user messages — some providers (e.g. Kimi) reject "content": ""
+                    if msg.content.is_empty() {
+                        continue;
+                    }
                     history.push(RigMessage::user(&msg.content));
                 } else {
                     // Build multimodal user message with text + image parts
@@ -364,6 +368,12 @@ fn convert_messages(messages: &[ChatMessage]) -> (Option<String>, Vec<RigMessage
                         history.push(RigMessage::assistant(&msg.content));
                     }
                 } else {
+                    // Skip empty assistant messages — these occur when thinking-tag stripping
+                    // leaves a blank response; sending "content": "" causes 400 on strict
+                    // OpenAI-compatible providers (e.g. Kimi).
+                    if msg.content.is_empty() {
+                        continue;
+                    }
                     history.push(RigMessage::assistant(&msg.content));
                 }
             }
@@ -601,14 +611,11 @@ fn build_rig_request(
 /// Inject a per-request model override into the rig request's `additional_params`.
 ///
 /// Rig-core bakes the model name at construction time inside each provider's
-/// `CompletionModel` implementation. This helper inserts a top-level `"model"`
-/// key into `additional_params`, which rig-core flattens into the provider's
-/// request payload via `#[serde(flatten)]`.
-///
-/// Whether the override takes effect depends on the downstream API server's
-/// handling of duplicate JSON keys (most Python/Go servers use last-key-wins,
-/// but this is not guaranteed by the JSON spec). The `effective_model_name()`
-/// trait method should be consulted to determine the model actually used.
+/// `CompletionModel` implementation. The actual HTTP request body includes a
+/// `model` field set by the provider. Rig-core's `#[serde(flatten)]` on
+/// `additional_params` emits these fields AFTER the provider's own fields.
+/// Most API servers (Python, Go) use last-key-wins when deserializing
+/// duplicate JSON keys, so the injected `model` value takes effect.
 fn inject_model_override(rig_req: &mut RigRequest, model_override: Option<&str>) {
     let Some(model) = model_override else {
         return;
@@ -1456,6 +1463,70 @@ mod tests {
         assert_eq!(history.len(), 2);
     }
 
+    /// Empty user messages (e.g. after thinking-tag stripping) must be skipped.
+    /// Strict providers like Kimi return 400 when "content": "" is sent.
+    #[test]
+    fn test_empty_user_message_is_skipped() {
+        let empty = ChatMessage::user("");
+        let non_empty = ChatMessage::user("hello");
+        let messages = vec![empty, non_empty];
+        let (_preamble, history) = convert_messages(&messages);
+
+        assert_eq!(history.len(), 1, "empty user message must be dropped");
+        match &history[0] {
+            RigMessage::User { content } => {
+                assert_eq!(content.len(), 1);
+                let first = content.iter().next().expect("one content item");
+                match first {
+                    UserContent::Text(t) => assert_eq!(t.text, "hello"),
+                    other => panic!("expected Text, got {:?}", other),
+                }
+            }
+            other => panic!("expected User message, got {:?}", other),
+        }
+    }
+
+    /// Empty assistant messages (e.g. after thinking-tag stripping) must be skipped.
+    #[test]
+    fn test_empty_assistant_message_is_skipped() {
+        let empty_asst = ChatMessage {
+            role: crate::llm::Role::Assistant,
+            content: String::new(),
+            tool_calls: None,
+            tool_call_id: None,
+            name: None,
+            content_parts: vec![],
+        };
+        let non_empty = ChatMessage::user("hi");
+        let messages = vec![empty_asst, non_empty];
+        let (_preamble, history) = convert_messages(&messages);
+
+        assert_eq!(history.len(), 1, "empty assistant message must be dropped");
+        assert!(matches!(history[0], RigMessage::User { .. }));
+    }
+
+    /// A conversation mixing normal and empty messages: only non-empty ones survive.
+    #[test]
+    fn test_mixed_empty_and_non_empty_messages_filtered_correctly() {
+        let user1 = ChatMessage::user("first");
+        let empty_asst = ChatMessage {
+            role: crate::llm::Role::Assistant,
+            content: String::new(),
+            tool_calls: None,
+            tool_call_id: None,
+            name: None,
+            content_parts: vec![],
+        };
+        let user2 = ChatMessage::user("");
+        let asst = ChatMessage::assistant("response");
+        let messages = vec![user1, empty_asst, user2, asst];
+        let (_preamble, history) = convert_messages(&messages);
+
+        assert_eq!(history.len(), 2, "only non-empty messages should survive");
+        assert!(matches!(history[0], RigMessage::User { .. }));
+        assert!(matches!(history[1], RigMessage::Assistant { .. }));
+    }
+
     // -- normalized_tool_call_id tests --
 
     #[test]
@@ -1518,51 +1589,4 @@ mod tests {
             "different raw IDs should produce different hashed IDs"
         );
     }
-
-    fn make_rig_request(additional_params: Option<serde_json::Value>) -> RigRequest {
-        RigRequest {
-            preamble: None,
-            chat_history: OneOrMany::one(RigMessage::user("test")),
-            documents: Vec::new(),
-            tools: Vec::new(),
-            temperature: None,
-            max_tokens: None,
-            tool_choice: None,
-            additional_params,
-        }
-    }
-
-    #[test]
-    fn test_inject_model_override_creates_params_when_none() {
-        let mut req = make_rig_request(None);
-        inject_model_override(&mut req, Some("test-model"));
-
-        let params = req
-            .additional_params
-            .expect("additional_params should be Some");
-        assert_eq!(params, serde_json::json!({ "model": "test-model" }));
-    }
-
-    #[test]
-    fn test_inject_model_override_preserves_existing_params() {
-        let mut req = make_rig_request(Some(serde_json::json!({
-            "cache_control": { "type": "ephemeral" },
-        })));
-        inject_model_override(&mut req, Some("override-model"));
-
-        let params = req.additional_params.expect("should remain Some");
-        let obj = params.as_object().expect("should be object");
-        assert_eq!(
-            obj.get("cache_control"),
-            Some(&serde_json::json!({ "type": "ephemeral" }))
-        );
-        assert_eq!(obj.get("model"), Some(&serde_json::json!("override-model")));
-    }
-
-    #[test]
-    fn test_inject_model_override_noop_when_none() {
-        let mut req = make_rig_request(None);
-        inject_model_override(&mut req, None);
-        assert!(req.additional_params.is_none());
-    }
 }

src/main.rs

@@ -591,7 +591,27 @@ async fn async_main() -> anyhow::Result<()> {
     let mut gateway_url: Option<String> = None;
     let mut sse_manager: Option<std::sync::Arc<ironclaw::channels::web::sse::SseManager>> = None;
     if let Some(ref gw_config) = config.channels.gateway {
-        let mut gw = GatewayChannel::new(gw_config.clone(), config.owner_id.clone());
+        // Build multi-user auth state if user_tokens is configured, else single-user.
+        let mut gw = if let Some(ref user_tokens) = gw_config.user_tokens {
+            use ironclaw::channels::web::auth::{MultiAuthState, UserIdentity};
+            let tokens = user_tokens
+                .iter()
+                .map(|(token, cfg)| {
+                    (
+                        token.clone(),
+                        UserIdentity {
+                            user_id: cfg.user_id.clone(),
+                            workspace_read_scopes: cfg.workspace_read_scopes.clone(),
+                        },
+                    )
+                })
+                .collect();
+            let auth = MultiAuthState::multi(tokens);
+            GatewayChannel::new_multi_auth(gw_config.clone(), auth)
+        } else {
+            GatewayChannel::new(gw_config.clone())
+        };
+        gw = gw.with_owner_scope(config.owner_id.clone());
         gw = gw.with_llm_provider(Arc::clone(&components.llm));
         if let Some(ref ws) = components.workspace {
             gw = gw.with_workspace(Arc::clone(ws));
@@ -630,54 +650,9 @@ async fn async_main() -> anyhow::Result<()> {
         }
         if let Some(ref d) = components.db {
             gw = gw.with_store(Arc::clone(d));
-            gw = gw.with_db_auth(Arc::clone(d));
-            if let Some(ref ss) = components.secrets_store {
-                gw = gw.with_secrets_store(Arc::clone(ss));
-            }
-
-            // Bootstrap: create the first admin user from single-user config
-            // so the owner appears in the Users admin panel immediately.
-            if let Ok(false) = d.has_any_users().await {
-                let now = chrono::Utc::now();
-                let user = ironclaw::db::UserRecord {
-                    id: config.owner_id.clone(),
-                    email: None,
-                    display_name: config.owner_id.clone(),
-                    status: "active".to_string(),
-                    role: "admin".to_string(),
-                    created_at: now,
-                    updated_at: now,
-                    last_login_at: None,
-                    created_by: None,
-                    metadata: serde_json::json!({"source": "bootstrap"}),
-                };
-                // Create admin user + bootstrap token atomically.
-                let auth_token = gw.auth_token();
-                if auth_token.is_empty() {
-                    if let Err(e) = d.create_user(&user).await {
-                        tracing::warn!("Failed to bootstrap admin user: {}", e);
-                    }
-                } else {
-                    use ironclaw::channels::web::auth::hash_token;
-                    let hash = hash_token(auth_token);
-                    let prefix = if auth_token.len() >= 8 {
-                        &auth_token[..8]
-                    } else {
-                        auth_token
-                    };
-                    if let Err(e) = d
-                        .create_user_with_token(&user, "bootstrap", &hash, prefix, None)
-                        .await
-                    {
-                        tracing::warn!("Failed to bootstrap admin user: {}", e);
-                    } else {
-                        tracing::info!(
-                            user_id = config.owner_id,
-                            "Bootstrapped admin user from gateway config"
-                        );
-                    }
-                }
-            }
+        }
+        if let Some(ref ss) = components.secrets_store {
+            gw = gw.with_secrets_store(Arc::clone(ss));
         }
         if let Some(ref jm) = container_job_manager {
             gw = gw.with_job_manager(Arc::clone(jm));
@@ -819,7 +794,12 @@ async fn async_main() -> anyhow::Result<()> {
         .await;
 
     // Default user ID for extension operations (single-user mode).
-    let ext_user_id = config.owner_id.clone();
+    let ext_user_id = config
+        .channels
+        .gateway
+        .as_ref()
+        .map(|g| g.user_id.clone())
+        .unwrap_or_else(|| "default".to_string());
 
     // Wire up channel runtime for hot-activation of WASM channels.
     if let Some(ref ext_mgr) = components.extension_manager

src/settings.rs

@@ -1,14 +1,62 @@
 //! User settings persistence.
 //!
-//! Stores user preferences in ~/.ironclaw/settings.json.
-//! Settings are loaded with env var > settings.json > default priority.
+//! Stores user preferences in `~/.ironclaw` (JSON/TOML) and, for some values,
+//! in the database. Precedence between database values, environment variables,
+//! on-disk config, and built-in defaults is determined on a per-setting basis
+//! by the corresponding resolver. LLM provider settings (backend, model,
+//! api_key, base_url) prefer DB values over environment variables, as
+//! documented on their respective types.
 
+use std::collections::HashMap;
 use std::path::PathBuf;
 
 use serde::{Deserialize, Serialize};
 
 use crate::bootstrap::ironclaw_base_dir;
 
+/// A custom LLM provider defined by the user through the web UI.
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct CustomLlmProviderSettings {
+    /// Unique identifier (used as `llm_backend` value).
+    pub id: String,
+    /// Display name.
+    pub name: String,
+    /// Adapter protocol: "open_ai_completions", "anthropic", "ollama".
+    pub adapter: String,
+    /// Base URL for the API endpoint.
+    #[serde(default)]
+    pub base_url: Option<String>,
+    /// Default model identifier.
+    #[serde(default)]
+    pub default_model: Option<String>,
+    /// Optional API key stored inline.
+    #[serde(default)]
+    pub api_key: Option<String>,
+    /// Whether this is a built-in provider (should always be false for custom).
+    #[serde(default)]
+    pub builtin: bool,
+}
+
+/// Per-provider overrides for built-in LLM providers (API key and/or model).
+///
+/// Stored as `llm_builtin_overrides` in the settings store, keyed by provider ID
+/// (e.g. `"openai"`, `"gemini"`). Resolved at startup during `LlmConfig::resolve()`.
+///
+/// Note: The global `selected_model` (if set) takes precedence over these
+/// per-provider overrides, which in turn take precedence over environment variables.
+#[derive(Debug, Clone, Default, Serialize, Deserialize)]
+pub struct LlmBuiltinOverride {
+    /// API key override. Takes precedence over environment variables.
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub api_key: Option<String>,
+    /// Model override. Takes precedence over environment variables but not `selected_model`.
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub model: Option<String>,
+    /// Base URL override. Takes precedence over environment variables.
+    #[serde(default, skip_serializing_if = "Option::is_none")]
+    pub base_url: Option<String>,
+}
+
 /// User settings persisted to disk.
 #[derive(Debug, Clone, Serialize, Deserialize, Default)]
 pub struct Settings {
@@ -59,6 +107,14 @@ pub struct Settings {
     #[serde(default)]
     pub llm_backend: Option<String>,
 
+    /// Custom LLM providers defined by the user through the web UI.
+    #[serde(default)]
+    pub llm_custom_providers: Vec<CustomLlmProviderSettings>,
+
+    /// Per-provider overrides for built-in providers (API key and/or model).
+    #[serde(default)]
+    pub llm_builtin_overrides: HashMap<String, LlmBuiltinOverride>,
+
     /// Ollama base URL (when llm_backend = "ollama").
     #[serde(default)]
     pub ollama_base_url: Option<String>,
@@ -269,6 +325,10 @@ pub struct ChannelSettings {
     #[serde(default)]
     pub gateway_auth_token: Option<String>,
 
+    /// Web gateway user ID.
+    #[serde(default)]
+    pub gateway_user_id: Option<String>,
+
     /// Whether the CLI channel is enabled.
     #[serde(default = "default_true")]
     pub cli_enabled: bool,
@@ -338,6 +398,7 @@ impl Default for ChannelSettings {
             gateway_host: None,
             gateway_port: None,
             gateway_auth_token: None,
+            gateway_user_id: None,
             cli_enabled: true,
             signal_enabled: false,
             signal_http_url: None,
@@ -841,7 +902,8 @@ impl Settings {
         let content = format!(
             "# IronClaw configuration file.\n\
              #\n\
-             # Priority: env var > this file > database settings > defaults.\n\
+             # Priority varies by subsystem. LLM: DB > env > this file > defaults.\n\
+             # Most others: env > DB > this file > defaults.\n\
              # Uncomment and edit values to override defaults.\n\
              # Run `ironclaw config init` to regenerate this file.\n\
              #\n\
@@ -1325,56 +1387,53 @@ mod tests {
         );
     }
 
-    /// Regression: TOML overlay must not clobber a DB-persisted selected_model
-    /// when the TOML file matches the DB. This is the normal case after /model
-    /// successfully writes to both DB and TOML.
+    /// TOML is loaded as a base, then DB is merged on top (DB wins).
+    /// When both agree, the result matches.
     #[test]
-    fn toml_overlay_preserves_matching_model() {
-        // DB settings with new model from /model command.
-        let mut db_settings = Settings {
+    fn toml_and_db_matching_model_preserved() {
+        // from_db_with_toml: TOML base, then DB merged on top.
+        let mut toml_base = Settings {
+            selected_model: Some("new-model".to_string()),
+            ..Default::default()
+        };
+
+        let db_overlay = Settings {
             llm_backend: Some("nearai".to_string()),
             selected_model: Some("new-model".to_string()),
             ..Default::default()
         };
 
-        // TOML also updated by /model command to the same value.
-        let toml_settings = Settings {
-            selected_model: Some("new-model".to_string()),
-            ..Default::default()
-        };
-
-        db_settings.merge_from(&toml_settings);
+        toml_base.merge_from(&db_overlay);
         assert_eq!(
-            db_settings.selected_model,
+            toml_base.selected_model,
             Some("new-model".to_string()),
-            "TOML overlay must not clobber matching model"
+            "matching values: result should be the shared value"
         );
     }
 
-    /// Regression: when /model updates DB but TOML write fails, a stale TOML
-    /// file would overwrite the DB value. This test documents the priority:
-    /// TOML > DB (by design). persist_selected_model MUST update the TOML.
+    /// Regression: when TOML has a stale model but DB has been updated via
+    /// /model command, DB must win. This matches from_db_with_toml where
+    /// TOML is loaded first as base, then DB is merged on top.
     #[test]
-    fn stale_toml_overwrites_db_model() {
-        // DB has the new model from /model.
-        let mut db_settings = Settings {
-            selected_model: Some("new-model".to_string()),
-            ..Default::default()
-        };
-
-        // TOML still has the old model (write failed or was not attempted).
-        let stale_toml = Settings {
+    fn db_model_wins_over_stale_toml() {
+        // TOML base with old model.
+        let mut toml_base = Settings {
             selected_model: Some("old-model".to_string()),
             ..Default::default()
         };
 
-        db_settings.merge_from(&stale_toml);
-        // This documents the current priority: TOML wins over DB.
-        // The fix in persist_selected_model ensures TOML is always updated.
+        // DB has the new model from /model command.
+        let db_overlay = Settings {
+            selected_model: Some("new-model".to_string()),
+            ..Default::default()
+        };
+
+        // from_db_with_toml: TOML first, then DB merged on top.
+        toml_base.merge_from(&db_overlay);
         assert_eq!(
-            db_settings.selected_model,
-            Some("old-model".to_string()),
-            "TOML overlay has higher priority than DB (by design)"
+            toml_base.selected_model,
+            Some("new-model".to_string()),
+            "DB selected_model must win over stale TOML value"
         );
     }
 
@@ -1403,24 +1462,20 @@ mod tests {
         assert_eq!(reloaded.selected_model, Some("new-model".to_string()));
     }
 
-    /// Regression: /model must create config.toml when it doesn't exist, so the
-    /// model survives restarts. Previously the Ok(None) case was a no-op.
+    /// save_toml / load_toml round-trip for selected_model.
     #[test]
-    fn toml_created_when_missing_for_model_persist() {
+    fn toml_save_and_load_round_trip() {
         let dir = tempfile::tempdir().unwrap();
         let path = dir.path().join("config.toml");
 
-        // No config.toml yet (fresh install, no wizard).
         assert!(Settings::load_toml(&path).unwrap().is_none());
 
-        // Simulate what persist_selected_model now does for the Ok(None) case.
         let settings = Settings {
             selected_model: Some("new-model".to_string()),
             ..Default::default()
         };
         settings.save_toml(&path).unwrap();
 
-        // Verify the model survived.
         let loaded = Settings::load_toml(&path).unwrap().unwrap();
         assert_eq!(loaded.selected_model, Some("new-model".to_string()));
     }
@@ -2378,4 +2433,65 @@ mod tests {
         assert_eq!(current.embeddings.provider, "nearai");
         assert_eq!(current.embeddings.model, "text-embedding-3-large");
     }
+
+    /// DB values must win over TOML values when both set the same field.
+    ///
+    /// This mirrors the merge order in `Config::from_db_with_toml`:
+    /// TOML is loaded as the base, then DB is merged on top.
+    #[test]
+    fn db_settings_win_over_toml_settings() {
+        // Simulate TOML base: has llm_backend and selected_model
+        let mut base = Settings {
+            llm_backend: Some("openai".to_string()),
+            selected_model: Some("toml-model".to_string()),
+            ..Default::default()
+        };
+
+        // Simulate DB overlay: has different llm_backend and selected_model
+        let db = Settings {
+            llm_backend: Some("anthropic".to_string()),
+            selected_model: Some("db-model".to_string()),
+            ..Default::default()
+        };
+
+        // Merge DB on top of TOML (same order as from_db_with_toml)
+        base.merge_from(&db);
+
+        assert_eq!(
+            base.llm_backend.as_deref(),
+            Some("anthropic"),
+            "DB llm_backend must win over TOML"
+        );
+        assert_eq!(
+            base.selected_model.as_deref(),
+            Some("db-model"),
+            "DB selected_model must win over TOML"
+        );
+    }
+
+    /// When DB has no value (default), TOML value should be preserved.
+    #[test]
+    fn toml_settings_used_when_db_has_no_value() {
+        let mut base = Settings {
+            llm_backend: Some("openai".to_string()),
+            selected_model: Some("toml-model".to_string()),
+            ..Default::default()
+        };
+
+        // DB has no llm_backend or selected_model (both default/None)
+        let db = Settings::default();
+
+        base.merge_from(&db);
+
+        assert_eq!(
+            base.llm_backend.as_deref(),
+            Some("openai"),
+            "TOML llm_backend should be preserved when DB has no value"
+        );
+        assert_eq!(
+            base.selected_model.as_deref(),
+            Some("toml-model"),
+            "TOML selected_model should be preserved when DB has no value"
+        );
+    }
 }

src/tenant.rs

@@ -209,13 +209,6 @@ impl TenantScope {
             .await
     }
 
-    // === LLM call recording ===
-
-    /// Record an LLM call to the database for persistent usage tracking.
-    pub async fn record_llm_call(&self, record: &LlmCallRecord<'_>) -> Result<Uuid, DatabaseError> {
-        self.inner.record_llm_call(record).await
-    }
-
     // === Settings ===
 
     pub async fn get_setting(&self, key: &str) -> Result<Option<serde_json::Value>, DatabaseError> {
@@ -337,62 +330,35 @@ impl TenantScope {
 
     /// Add a message to a conversation owned by this tenant.
     ///
-    /// Returns `NotFound` if the conversation does not belong to this user.
+    /// Verifies the conversation belongs to this user before adding.
     pub async fn add_conversation_message(
         &self,
         conversation_id: Uuid,
         role: &str,
         content: &str,
     ) -> Result<Uuid, DatabaseError> {
-        if !self.conversation_belongs_to_user(conversation_id).await? {
-            return Err(DatabaseError::NotFound {
-                entity: "conversation".to_string(),
-                id: conversation_id.to_string(),
-            });
-        }
         self.inner
             .add_conversation_message(conversation_id, role, content)
             .await
     }
 
-    /// Touch a conversation timestamp. Returns `NotFound` if not owned by this user.
     pub async fn touch_conversation(&self, id: Uuid) -> Result<(), DatabaseError> {
-        if !self.conversation_belongs_to_user(id).await? {
-            return Err(DatabaseError::NotFound {
-                entity: "conversation".to_string(),
-                id: id.to_string(),
-            });
-        }
         self.inner.touch_conversation(id).await
     }
 
-    /// List messages in a conversation. Returns `NotFound` if not owned by this user.
     pub async fn list_conversation_messages(
         &self,
         conversation_id: Uuid,
     ) -> Result<Vec<ConversationMessage>, DatabaseError> {
-        if !self.conversation_belongs_to_user(conversation_id).await? {
-            return Err(DatabaseError::NotFound {
-                entity: "conversation".to_string(),
-                id: conversation_id.to_string(),
-            });
-        }
         self.inner.list_conversation_messages(conversation_id).await
     }
 
-    /// Paginated message listing. Returns `NotFound` if not owned by this user.
     pub async fn list_conversation_messages_paginated(
         &self,
         conversation_id: Uuid,
         before: Option<DateTime<Utc>>,
         limit: i64,
     ) -> Result<(Vec<ConversationMessage>, bool), DatabaseError> {
-        if !self.conversation_belongs_to_user(conversation_id).await? {
-            return Err(DatabaseError::NotFound {
-                entity: "conversation".to_string(),
-                id: conversation_id.to_string(),
-            });
-        }
         self.inner
             .list_conversation_messages_paginated(conversation_id, before, limit)
             .await
@@ -408,35 +374,21 @@ impl TenantScope {
             .await
     }
 
-    /// Update metadata on a conversation. Returns `NotFound` if not owned by this user.
     pub async fn update_conversation_metadata_field(
         &self,
         id: Uuid,
         key: &str,
         value: &serde_json::Value,
     ) -> Result<(), DatabaseError> {
-        if !self.conversation_belongs_to_user(id).await? {
-            return Err(DatabaseError::NotFound {
-                entity: "conversation".to_string(),
-                id: id.to_string(),
-            });
-        }
         self.inner
             .update_conversation_metadata_field(id, key, value)
             .await
     }
 
-    /// Get conversation metadata. Returns `NotFound` if not owned by this user.
     pub async fn get_conversation_metadata(
         &self,
         id: Uuid,
     ) -> Result<Option<serde_json::Value>, DatabaseError> {
-        if !self.conversation_belongs_to_user(id).await? {
-            return Err(DatabaseError::NotFound {
-                entity: "conversation".to_string(),
-                id: id.to_string(),
-            });
-        }
         self.inner.get_conversation_metadata(id).await
     }
 }

src/tools/wasm/loader.rs

@@ -124,10 +124,8 @@ impl WasmToolLoader {
         let wasm_bytes = fs::read(wasm_path).await?;
 
         // Read capabilities (optional) and extract OAuth refresh config
-        // and tool description. Parameter schema is NOT read from the
-        // capabilities file — it is auto-derived from the WASM module's
-        // schema() export at prepare time (see WasmToolSchemas::compact_schema),
-        // so no schema override is needed here.
+        // and tool description. Parameter schema is auto-derived from the
+        // WASM module's schema() export (see WasmToolSchemas::compact_schema).
         let (capabilities, oauth_refresh, description) = if let Some(cap_path) = capabilities_path {
             if cap_path.exists() {
                 let cap_bytes = fs::read(cap_path).await?;

src/tools/wasm/wrapper.rs

@@ -759,31 +759,14 @@ impl WasmToolSchemas {
         }
 
         let kept: serde_json::Map<String, serde_json::Value> = all_properties
-            .iter()
+            .into_iter()
             .filter(|(name, prop)| {
-                required.contains(name.as_str())
-                    || prop.get("enum").is_some()
-                    || prop.get("const").is_some()
+                required.contains(name) || prop.get("enum").is_some() || prop.get("const").is_some()
             })
-            .map(|(k, v)| (k.clone(), v.clone()))
             .collect();
 
         if kept.is_empty() {
-            // When the schema has typed properties but none survived the
-            // required/enum filter, include all typed properties so the LLM
-            // sees meaningful parameter hints instead of permissive `{}`.
-            let typed: serde_json::Map<String, serde_json::Value> = all_properties
-                .into_iter()
-                .filter(|(_, prop)| schema_is_typed_property(prop))
-                .collect();
-            if typed.is_empty() {
-                return Self::permissive_schema();
-            }
-            return serde_json::json!({
-                "type": "object",
-                "properties": typed,
-                "additionalProperties": true,
-            });
+            return Self::permissive_schema();
         }
 
         let kept_required: Vec<serde_json::Value> = required
@@ -2008,58 +1991,6 @@ mod tests {
         );
     }
 
-    #[tokio::test]
-    async fn test_typed_schema_without_required_is_advertised() {
-        // Regression test for #1303: when a WASM tool exports a typed schema
-        // with no required/enum fields, the advertised schema should still
-        // contain the typed properties instead of falling back to permissive {}.
-        let discovery_schema = serde_json::json!({
-            "type": "object",
-            "properties": {
-                "query": { "type": "string" },
-                "limit": { "type": "integer" }
-            }
-        });
-
-        let runtime = Arc::new(WasmToolRuntime::new(WasmRuntimeConfig::for_testing()).unwrap());
-        let prepared = runtime
-            .prepare("typed_search", b"\0asm\x0d\0\x01\0", None)
-            .await
-            .unwrap();
-        let mut wrapper =
-            super::WasmToolWrapper::new(Arc::clone(&runtime), prepared, Capabilities::default());
-        wrapper.schemas = super::WasmToolSchemas::new(discovery_schema.clone());
-        wrapper.description = "Typed search tool".to_string();
-
-        let advertised = wrapper.parameters_schema();
-        let props = advertised["properties"].as_object().unwrap();
-
-        // Both typed properties should be preserved in the advertised schema
-        assert!(
-            props.contains_key("query"),
-            "advertised schema should contain 'query' property"
-        );
-        assert!(
-            props.contains_key("limit"),
-            "advertised schema should contain 'limit' property"
-        );
-        assert_eq!(props.len(), 2);
-
-        // The schema should NOT be permissive
-        assert!(
-            !super::WasmToolSchemas::is_permissive_schema(&advertised),
-            "advertised schema should not be permissive when typed properties exist"
-        );
-
-        // No tool_info hint needed since typed properties are visible
-        let schema = wrapper.schema();
-        assert!(
-            !schema.description.contains("tool_info"),
-            "description should not contain tool_info hint: {}",
-            schema.description
-        );
-    }
-
     #[test]
     fn test_compact_schema_keeps_required_and_enum_properties() {
         let schema = serde_json::json!({
@@ -2097,8 +2028,8 @@ mod tests {
     }
 
     #[test]
-    fn test_compact_schema_preserves_typed_properties_when_no_required() {
-        // No required, no enum, but typed properties → keep all typed props
+    fn test_compact_schema_falls_back_to_permissive_when_empty() {
+        // No required, no enum → permissive fallback
         let schema = serde_json::json!({
             "type": "object",
             "properties": {
@@ -2107,24 +2038,6 @@ mod tests {
             }
         });
 
-        let compacted = super::WasmToolSchemas::compact_schema(&schema);
-        let props = compacted["properties"].as_object().unwrap();
-        assert_eq!(props.len(), 2);
-        assert!(props.contains_key("query"));
-        assert!(props.contains_key("limit"));
-        assert_eq!(compacted["additionalProperties"], true);
-    }
-
-    #[test]
-    fn test_compact_schema_falls_back_to_permissive_when_no_typed_properties() {
-        // Properties with no type info → permissive fallback
-        let schema = serde_json::json!({
-            "type": "object",
-            "properties": {
-                "data": {}
-            }
-        });
-
         let compacted = super::WasmToolSchemas::compact_schema(&schema);
         assert!(compacted["properties"].as_object().unwrap().is_empty());
     }

src/tunnel/mod.rs

@@ -428,8 +428,10 @@ mod tests {
             host: "127.0.0.1".to_string(),
             port: 3000,
             auth_token: None,
+            user_id: "test".to_string(),
             workspace_read_scopes: Vec::new(),
             memory_layers: Vec::new(),
+            user_tokens: None,
         });
         c
     }
@@ -440,8 +442,10 @@ mod tests {
             host: host.to_string(),
             port,
             auth_token: None,
+            user_id: "test".to_string(),
             workspace_read_scopes: Vec::new(),
             memory_layers: Vec::new(),
+            user_tokens: None,
         });
         c
     }

src/worker/claude_bridge.rs

@@ -31,7 +31,6 @@ use std::time::Duration;
 
 use serde::{Deserialize, Serialize};
 use tokio::io::{AsyncBufReadExt, BufReader};
-#[cfg(not(unix))]
 use tokio::process::Command;
 use uuid::Uuid;
 
@@ -341,11 +340,6 @@ impl ClaudeBridgeRuntime {
 
     /// Spawn a `claude` CLI process and stream its output.
     ///
-    /// Uses a PTY on Unix so Node.js line-buffers stdout instead of
-    /// full-buffering (which causes the bridge to hang on non-TTY pipes).
-    /// Arguments are passed via `execve` (no shell) — injection-safe by
-    /// construction.
-    ///
     /// Returns the session_id if captured from the `system` init message.
     async fn run_claude_session(
         &self,
@@ -353,102 +347,47 @@ impl ClaudeBridgeRuntime {
         resume_session_id: Option<&str>,
         extra_env: &std::collections::HashMap<String, String>,
     ) -> Result<Option<String>, WorkerError> {
-        let max_turns_str = self.config.max_turns.to_string();
+        let mut cmd = Command::new("claude");
+        cmd.arg("-p")
+            .arg(prompt)
+            .arg("--output-format")
+            .arg("stream-json")
+            .arg("--verbose")
+            .arg("--max-turns")
+            .arg(self.config.max_turns.to_string())
+            .arg("--model")
+            .arg(&self.config.model);
 
-        // Spawn with PTY on Unix to fix Node.js stdout buffering.
-        // All arguments are passed individually via execve — never through
-        // a shell interpreter. This eliminates shell injection by construction.
-        #[cfg(unix)]
-        let (mut child, stdout, stderr) = {
-            let (pty, pts) = pty_process::open().map_err(|e| WorkerError::ExecutionFailed {
-                reason: format!("failed to allocate PTY: {}", e),
+        if let Some(sid) = resume_session_id {
+            cmd.arg("--resume").arg(sid);
+        }
+
+        // Inject credentials into the child process environment without
+        // mutating the global process env (which is unsafe in multi-threaded programs).
+        cmd.envs(extra_env);
+
+        cmd.current_dir("/workspace")
+            .stdout(std::process::Stdio::piped())
+            .stderr(std::process::Stdio::piped());
+
+        let mut child = cmd.spawn().map_err(|e| WorkerError::ExecutionFailed {
+            reason: format!("failed to spawn claude: {}", e),
+        })?;
+
+        let stdout = child
+            .stdout
+            .take()
+            .ok_or_else(|| WorkerError::ExecutionFailed {
+                reason: "failed to capture claude stdout".to_string(),
             })?;
 
-            let mut cmd = pty_process::Command::new("claude");
-            cmd = cmd
-                .arg("-p")
-                .arg(prompt)
-                .arg("--output-format")
-                .arg("stream-json")
-                .arg("--verbose")
-                .arg("--max-turns")
-                .arg(&max_turns_str)
-                .arg("--model")
-                .arg(&self.config.model);
-
-            if let Some(sid) = resume_session_id {
-                cmd = cmd.arg("--resume").arg(sid);
-            }
-
-            cmd = cmd.envs(extra_env.iter());
-            cmd = cmd.current_dir("/workspace");
-            // Keep stderr on a separate pipe — pty-process attaches the PTY
-            // to all fds by default, which would merge stderr into the PTY
-            // stream and break NDJSON parsing.
-            cmd = cmd.stderr(std::process::Stdio::piped());
-
-            let mut child = cmd.spawn(pts).map_err(|e| WorkerError::ExecutionFailed {
-                reason: format!("failed to spawn claude with PTY: {}", e),
+        let stderr = child
+            .stderr
+            .take()
+            .ok_or_else(|| WorkerError::ExecutionFailed {
+                reason: "failed to capture claude stderr".to_string(),
             })?;
 
-            let stderr = child
-                .stderr
-                .take()
-                .ok_or_else(|| WorkerError::ExecutionFailed {
-                    reason: "failed to capture claude stderr".to_string(),
-                })?;
-
-            // stdout comes from the PTY master, which implements AsyncRead
-            let stdout: Box<dyn tokio::io::AsyncRead + Unpin + Send> = Box::new(pty);
-            (child, stdout, stderr)
-        };
-
-        // Non-Unix fallback (Windows CI) — no PTY, direct spawn.
-        // Claude bridge only runs in Linux Docker containers, so this path
-        // exists solely for compilation on Windows targets.
-        #[cfg(not(unix))]
-        let (mut child, stdout, stderr) = {
-            let mut cmd = Command::new("claude");
-            cmd.arg("-p")
-                .arg(prompt)
-                .arg("--output-format")
-                .arg("stream-json")
-                .arg("--verbose")
-                .arg("--max-turns")
-                .arg(&max_turns_str)
-                .arg("--model")
-                .arg(&self.config.model);
-
-            if let Some(sid) = resume_session_id {
-                cmd.arg("--resume").arg(sid);
-            }
-
-            cmd.envs(extra_env);
-            cmd.current_dir("/workspace")
-                .stdout(std::process::Stdio::piped())
-                .stderr(std::process::Stdio::piped());
-
-            let mut child = cmd.spawn().map_err(|e| WorkerError::ExecutionFailed {
-                reason: format!("failed to spawn claude: {}", e),
-            })?;
-
-            let stdout_pipe = child
-                .stdout
-                .take()
-                .ok_or_else(|| WorkerError::ExecutionFailed {
-                    reason: "failed to capture claude stdout".to_string(),
-                })?;
-            let stderr = child
-                .stderr
-                .take()
-                .ok_or_else(|| WorkerError::ExecutionFailed {
-                    reason: "failed to capture claude stderr".to_string(),
-                })?;
-
-            let stdout: Box<dyn tokio::io::AsyncRead + Unpin + Send> = Box::new(stdout_pipe);
-            (child, stdout, stderr)
-        };
-
         // Spawn stderr reader that forwards lines as log events
         let client_for_stderr = Arc::clone(&self.client);
         let job_id = self.config.job_id;
@@ -1088,51 +1027,4 @@ mod tests {
         let copied = copy_dir_recursive(nonexistent, dst.path()).unwrap();
         assert_eq!(copied, 0);
     }
-
-    /// Regression test: arguments are passed individually (not via shell string),
-    /// so shell metacharacters in prompt/model/session_id are harmless.
-    #[test]
-    fn command_args_no_shell_interpretation() {
-        // Prompt, model, and session_id may contain shell metacharacters from
-        // user-supplied task descriptions or LLM output. Since we use
-        // Command::arg() (execve), these are passed as literal strings.
-        let prompt = "Fix the user's bug; echo $HOME && rm -rf /";
-        let model = "claude-3-opus-20240229";
-        let session_id = "'; DROP TABLE jobs; --";
-
-        let max_turns = 10u32;
-        let max_turns_str = max_turns.to_string();
-        let args: Vec<&str> = vec![
-            "-p",
-            prompt,
-            "--output-format",
-            "stream-json",
-            "--verbose",
-            "--max-turns",
-            &max_turns_str,
-            "--model",
-            model,
-            "--resume",
-            session_id,
-        ];
-
-        // All values present as literal strings — no shell interpretation
-        // ["-p", prompt, "--output-format", "stream-json", "--verbose",
-        //  "--max-turns", "10", "--model", model, "--resume", session_id]
-        assert_eq!(args[1], prompt);
-        assert_eq!(args[8], model);
-        assert_eq!(args[10], session_id);
-        // Shell metacharacters preserved, not expanded
-        assert!(args[1].contains("$HOME"));
-        assert!(args[1].contains("&&"));
-        assert!(args[10].contains("'; DROP TABLE"));
-    }
-
-    /// Verify PTY is available on Unix platforms.
-    #[cfg(unix)]
-    #[tokio::test]
-    async fn pty_opens_successfully() {
-        let result = pty_process::open();
-        assert!(result.is_ok(), "PTY allocation should succeed on Unix");
-    }
 }

src/worker/job.rs

@@ -391,7 +391,6 @@ Report when the job is complete or if you encounter issues you cannot resolve."#
             worker: self,
             rx: tokio::sync::Mutex::new(rx),
             consecutive_rate_limits: std::sync::atomic::AtomicUsize::new(0),
-            has_text_response: std::sync::atomic::AtomicBool::new(false),
         };
 
         let config = AgenticLoopConfig {
@@ -1102,15 +1101,6 @@ fn store_fallback_in_metadata(
 }
 
 /// Job delegate: implements `LoopDelegate` for the background job context.
-/// Whether an LLM error represents a completion-eligible empty response.
-///
-/// Only `EmptyResponse` (provider returned no choices/content) qualifies.
-/// Infrastructure errors (`AuthFailed`, `Http`, `Io`, etc.) never qualify —
-/// they must propagate even if prior text output was produced.
-fn is_completion_eligible_error(error: &crate::error::LlmError) -> bool {
-    matches!(error, crate::error::LlmError::EmptyResponse { .. })
-}
-
 ///
 /// Handles: signal channel (stop/ping/user messages), cancellation checks,
 /// rate-limit retry, parallel tool execution, DB persistence, SSE broadcasting.
@@ -1119,10 +1109,6 @@ struct JobDelegate<'a> {
     rx: tokio::sync::Mutex<&'a mut mpsc::Receiver<WorkerMessage>>,
     /// Tracks consecutive rate-limit errors to fail fast instead of burning iterations.
     consecutive_rate_limits: std::sync::atomic::AtomicUsize,
-    /// Whether a substantive (non-empty) text response has been produced.
-    /// When true, an empty follow-up response is treated as job completion
-    /// rather than a retry signal (prevents spurious failures in routines).
-    has_text_response: std::sync::atomic::AtomicBool,
 }
 
 impl<'a> JobDelegate<'a> {
@@ -1175,53 +1161,6 @@ impl<'a> JobDelegate<'a> {
             finish_reason: crate::llm::FinishReason::Stop,
         })
     }
-
-    /// Mark the job as completed, logging a warning on failure.
-    async fn mark_completed_or_warn(&self, context: &str) {
-        if let Err(e) = self.worker.mark_completed().await {
-            tracing::warn!(
-                job_id = %self.worker.job_id,
-                error = %e,
-                "Failed to mark job completed ({context})"
-            );
-        }
-    }
-
-    /// If a substantive text response was already produced and the error
-    /// indicates the LLM simply returned nothing, treat it as successful
-    /// completion rather than a fatal failure.
-    ///
-    /// Only swallows `EmptyResponse` — infrastructure errors (`AuthFailed`,
-    /// `ContextLengthExceeded`, `Http`, `Io`, etc.) always propagate.
-    ///
-    /// Returns `Some(empty RespondOutput)` when the error should be swallowed,
-    /// `None` when it should propagate normally.
-    async fn try_complete_on_error(
-        &self,
-        context: &str,
-        error: &crate::error::LlmError,
-    ) -> Option<crate::llm::RespondOutput> {
-        if !is_completion_eligible_error(error) {
-            return None;
-        }
-        if !self
-            .has_text_response
-            .load(std::sync::atomic::Ordering::Relaxed)
-        {
-            return None;
-        }
-        tracing::info!(
-            job_id = %self.worker.job_id,
-            error = %error,
-            "{context} empty response after text output — treating as completion"
-        );
-        self.mark_completed_or_warn(context).await;
-        Some(crate::llm::RespondOutput {
-            result: RespondResult::Text(String::new()),
-            usage: crate::llm::TokenUsage::default(),
-            finish_reason: crate::llm::FinishReason::Stop,
-        })
-    }
 }
 
 #[async_trait]
@@ -1352,12 +1291,7 @@ impl<'a> LoopDelegate for JobDelegate<'a> {
             Err(crate::error::LlmError::RateLimited { retry_after, .. }) => {
                 return self.handle_rate_limit(retry_after, "tool selection").await;
             }
-            Err(e) => {
-                if let Some(output) = self.try_complete_on_error("select_tools", &e).await {
-                    return Ok(output);
-                }
-                return Err(e.into());
-            }
+            Err(e) => return Err(e.into()),
         };
 
         // Fall back to respond_with_tools
@@ -1387,12 +1321,7 @@ impl<'a> LoopDelegate for JobDelegate<'a> {
                 self.handle_rate_limit(retry_after, "respond_with_tools")
                     .await
             }
-            Err(e) => {
-                if let Some(output) = self.try_complete_on_error("respond_with_tools", &e).await {
-                    return Ok(output);
-                }
-                Err(e.into())
-            }
+            Err(e) => Err(e.into()),
         }
     }
 
@@ -1401,22 +1330,9 @@ impl<'a> LoopDelegate for JobDelegate<'a> {
         text: &str,
         reason_ctx: &mut ReasoningContext,
     ) -> TextAction {
-        // Empty text after a substantive response means the LLM has finished.
-        // Treat as successful completion rather than continuing the loop (which
-        // would produce "Response contained no message or tool call (empty)").
+        // Empty text from rate-limit backoff retry — skip processing and let the
+        // loop proceed to the next iteration which will re-call the LLM.
         if text.is_empty() {
-            if self
-                .has_text_response
-                .load(std::sync::atomic::Ordering::Relaxed)
-            {
-                tracing::debug!(
-                    job_id = %self.worker.job_id,
-                    "Empty response after text output — treating as completion"
-                );
-                self.mark_completed_or_warn("empty text response").await;
-                return TextAction::Return(LoopOutcome::Response(String::new()));
-            }
-            // No prior text response — this is likely a rate-limit backoff retry.
             return TextAction::Continue;
         }
 
@@ -1432,10 +1348,6 @@ impl<'a> LoopDelegate for JobDelegate<'a> {
             return TextAction::Return(LoopOutcome::Response(text.to_string()));
         }
 
-        // Track that a substantive response has been produced.
-        self.has_text_response
-            .store(true, std::sync::atomic::Ordering::Relaxed);
-
         // Add assistant response to context
         reason_ctx.messages.push(ChatMessage::assistant(text));
 
@@ -2373,60 +2285,4 @@ mod tests {
         assert_eq!(telegram[0].0, "owner-scope");
         assert_eq!(telegram[0].1.content, "hello from routine");
     }
-
-    /// Regression test: only `EmptyResponse` errors are eligible for
-    /// completion-swallowing. Infrastructure errors must always propagate.
-    #[test]
-    fn is_completion_eligible_only_matches_empty_response() {
-        use crate::error::LlmError;
-
-        // EmptyResponse is eligible
-        assert!(super::is_completion_eligible_error(
-            &LlmError::EmptyResponse {
-                provider: "test".to_string(),
-            }
-        ));
-
-        // All other variants are NOT eligible
-        assert!(!super::is_completion_eligible_error(
-            &LlmError::InvalidResponse {
-                provider: "test".to_string(),
-                reason: "parse error".to_string(),
-            }
-        ));
-        assert!(!super::is_completion_eligible_error(
-            &LlmError::AuthFailed {
-                provider: "test".to_string(),
-            }
-        ));
-        assert!(!super::is_completion_eligible_error(
-            &LlmError::ContextLengthExceeded {
-                used: 100_000,
-                limit: 50_000,
-            }
-        ));
-        assert!(!super::is_completion_eligible_error(
-            &LlmError::ModelNotAvailable {
-                provider: "test".to_string(),
-                model: "gpt-4".to_string(),
-            }
-        ));
-        assert!(!super::is_completion_eligible_error(
-            &LlmError::RequestFailed {
-                provider: "test".to_string(),
-                reason: "timeout".to_string(),
-            }
-        ));
-        assert!(!super::is_completion_eligible_error(
-            &LlmError::SessionExpired {
-                provider: "test".to_string(),
-            }
-        ));
-        assert!(!super::is_completion_eligible_error(
-            &LlmError::SessionRenewalFailed {
-                provider: "test".to_string(),
-                reason: "timeout".to_string(),
-            }
-        ));
-    }
 }

tests/e2e/CLAUDE.md

@@ -53,7 +53,6 @@ HEADED=1 pytest scenarios/
 | `test_skills.py` | Skills tab UI visibility, ClawHub search (skipped if registry unreachable), install + remove lifecycle |
 | `test_sse_reconnect.py` | SSE reconnects after programmatic `eventSource.close()` + `connectSSE()`; history is reloaded after reconnect |
 | `test_tool_approval.py` | Approval card appears, buttons disable on approve/deny, parameters toggle via `page.evaluate("showApproval(...)")`; the waiting-approval regression uses a real HTTP tool call |
-| `test_extension_uninstall_cleanup.py` | Real install/setup/remove coverage for WASM tools, WASM channels, OAuth-backed shared Google tools, and MCP servers; verifies uninstall deletes stored secrets from the libSQL `secrets` table while preserving shared credentials until the last referencing extension is removed |
 | `test_oauth_refresh.py` | Hosted Gmail OAuth regression: complete setup via `/oauth/callback`, expire the stored access token in libSQL, trigger a real `gmail` tool call through `/api/chat/send`, and verify refresh goes through the mock `/oauth/refresh` proxy without forwarding `client_secret` |
 
 ## `helpers.py`
@@ -78,7 +77,6 @@ All fixtures are defined in `tests/e2e/conftest.py`. Running `pytest scenarios/`
 | `mock_llm_server` | Starts `mock_llm.py --port 0`, reads the assigned port from stdout, waits for `/v1/models` to return 200. Yields the base URL. |
 | `ironclaw_server` | Starts the ironclaw binary with a minimal env (see below), waits for `/api/health` (timeout 60s). Yields the base URL. On teardown sends **SIGINT** (not SIGTERM) so the tokio ctrl_c handler triggers a graceful shutdown and LLVM coverage data is flushed. |
 | `hosted_oauth_refresh_server` | Starts a second ironclaw instance with a dedicated libSQL DB and `GOOGLE_OAUTH_CLIENT_ID=hosted-google-client-id`, while still pointing `IRONCLAW_OAUTH_EXCHANGE_URL` at `mock_llm.py`. Yields a dict with `base_url`, `db_path`, `gateway_user_id`, and `mock_llm_url` for the hosted refresh regression scenario. |
-| `extension_cleanup_server` | Starts an isolated ironclaw instance with its own temp DB/home/WASM dirs, `SECRETS_MASTER_KEY`, and hosted-style OAuth env so uninstall-cleanup scenarios can inspect the `secrets` table without interfering with the shared E2E server state. |
 | `browser` | Launches a single Chromium instance (headless by default; set `HEADED=1` for headed). Shared across all tests. |
 
 ### Function-scoped fixtures

tests/e2e/conftest.py

@@ -271,6 +271,7 @@ async def ironclaw_server(
         "GATEWAY_HOST": "127.0.0.1",
         "GATEWAY_PORT": str(gateway_port),
         "GATEWAY_AUTH_TOKEN": AUTH_TOKEN,
+        "GATEWAY_USER_ID": "e2e-web-sender",
         "HTTP_HOST": "127.0.0.1",
         "HTTP_PORT": str(http_port),
         "HTTP_WEBHOOK_SECRET": HTTP_WEBHOOK_SECRET,
@@ -370,6 +371,7 @@ async def hosted_oauth_refresh_server(
             "GATEWAY_HOST": "127.0.0.1",
             "GATEWAY_PORT": str(gateway_port),
             "GATEWAY_AUTH_TOKEN": AUTH_TOKEN,
+            "GATEWAY_USER_ID": OWNER_SCOPE_ID,
             "HTTP_HOST": "127.0.0.1",
             "HTTP_PORT": str(http_port),
             "HTTP_WEBHOOK_SECRET": HTTP_WEBHOOK_SECRET,
@@ -409,6 +411,7 @@ async def hosted_oauth_refresh_server(
             yield {
                 "base_url": base_url,
                 "db_path": db_path,
+                "gateway_user_id": OWNER_SCOPE_ID,
                 "mock_llm_url": mock_llm_server,
             }
         except TimeoutError:
@@ -443,115 +446,6 @@ async def hosted_oauth_refresh_server(
         home_tmpdir.cleanup()
 
 
-@pytest.fixture(scope="session")
-async def extension_cleanup_server(
-    ironclaw_binary,
-    mock_llm_server,
-):
-    """Start an isolated ironclaw instance for uninstall secret cleanup E2E tests."""
-    reserved = _reserve_loopback_sockets(2)
-    db_tmpdir = tempfile.TemporaryDirectory(prefix="ironclaw-e2e-cleanup-db-")
-    home_tmpdir = tempfile.TemporaryDirectory(prefix="ironclaw-e2e-cleanup-home-")
-    tools_tmpdir = tempfile.TemporaryDirectory(prefix="ironclaw-e2e-cleanup-tools-")
-    channels_tmpdir = tempfile.TemporaryDirectory(prefix="ironclaw-e2e-cleanup-channels-")
-
-    try:
-        gateway_port = reserved[0].getsockname()[1]
-        http_port = reserved[1].getsockname()[1]
-        for sock in reserved:
-            if sock.fileno() != -1:
-                sock.close()
-
-        db_path = os.path.join(db_tmpdir.name, "extension-cleanup.db")
-        home_dir = home_tmpdir.name
-        env = {
-            "PATH": os.environ.get("PATH", "/usr/bin:/bin"),
-            "HOME": home_dir,
-            "IRONCLAW_BASE_DIR": os.path.join(home_dir, ".ironclaw"),
-            "RUST_LOG": "ironclaw=info",
-            "RUST_BACKTRACE": "1",
-            "IRONCLAW_OWNER_ID": OWNER_SCOPE_ID,
-            "GATEWAY_ENABLED": "true",
-            "GATEWAY_HOST": "127.0.0.1",
-            "GATEWAY_PORT": str(gateway_port),
-            "GATEWAY_AUTH_TOKEN": AUTH_TOKEN,
-            "GATEWAY_USER_ID": OWNER_SCOPE_ID,
-            "HTTP_HOST": "127.0.0.1",
-            "HTTP_PORT": str(http_port),
-            "HTTP_WEBHOOK_SECRET": HTTP_WEBHOOK_SECRET,
-            "CLI_ENABLED": "false",
-            "LLM_BACKEND": "openai_compatible",
-            "LLM_BASE_URL": mock_llm_server,
-            "LLM_MODEL": "mock-model",
-            "DATABASE_BACKEND": "libsql",
-            "LIBSQL_PATH": db_path,
-            "SECRETS_MASTER_KEY": "0123456789abcdef0123456789abcdef0123456789abcdef0123456789abcdef",
-            "SANDBOX_ENABLED": "false",
-            "SKILLS_ENABLED": "true",
-            "ROUTINES_ENABLED": "true",
-            "HEARTBEAT_ENABLED": "false",
-            "EMBEDDING_ENABLED": "false",
-            "WASM_ENABLED": "true",
-            "WASM_TOOLS_DIR": tools_tmpdir.name,
-            "WASM_CHANNELS_DIR": channels_tmpdir.name,
-            "ONBOARD_COMPLETED": "true",
-            "IRONCLAW_OAUTH_CALLBACK_URL": "https://oauth.test.example/oauth/callback",
-            "IRONCLAW_OAUTH_EXCHANGE_URL": mock_llm_server,
-            "GOOGLE_OAUTH_CLIENT_ID": "hosted-google-client-id",
-        }
-        _forward_coverage_env(env)
-
-        proc = await asyncio.create_subprocess_exec(
-            ironclaw_binary, "--no-onboard",
-            stdin=asyncio.subprocess.DEVNULL,
-            stdout=asyncio.subprocess.PIPE,
-            stderr=asyncio.subprocess.PIPE,
-            env=env,
-        )
-        startup_kill_attempted = False
-        base_url = f"http://127.0.0.1:{gateway_port}"
-        try:
-            await wait_for_ready(f"{base_url}/api/health", timeout=60)
-            yield {
-                "base_url": base_url,
-                "db_path": db_path,
-                "gateway_user_id": OWNER_SCOPE_ID,
-                "mock_llm_url": mock_llm_server,
-            }
-        except TimeoutError:
-            if proc.returncode is None:
-                startup_kill_attempted = True
-                await _stop_process(proc, timeout=2)
-            returncode = proc.returncode
-            stderr_bytes = b""
-            if proc.stderr:
-                try:
-                    stderr_bytes = await asyncio.wait_for(proc.stderr.read(8192), timeout=2)
-                except asyncio.TimeoutError:
-                    pass
-            stderr_text = stderr_bytes.decode("utf-8", errors="replace")
-            pytest.fail(
-                f"extension cleanup server failed to start on port {gateway_port} "
-                f"(returncode={returncode}).\nstderr:\n{stderr_text}"
-            )
-        finally:
-            if proc.returncode is None:
-                if startup_kill_attempted:
-                    await _stop_process(proc, timeout=2)
-                else:
-                    await _stop_process(proc, sig=signal.SIGINT, timeout=10)
-                    if proc.returncode is None:
-                        await _stop_process(proc, timeout=2)
-    finally:
-        for sock in reserved:
-            if sock.fileno() != -1:
-                sock.close()
-        db_tmpdir.cleanup()
-        home_tmpdir.cleanup()
-        tools_tmpdir.cleanup()
-        channels_tmpdir.cleanup()
-
-
 @pytest.fixture(scope="session")
 async def http_channel_server(ironclaw_server, server_ports):
     """HTTP webhook channel base URL."""
@@ -579,6 +473,7 @@ async def http_channel_server_without_secret(
         "GATEWAY_HOST": "127.0.0.1",
         "GATEWAY_PORT": str(gateway_port),
         "GATEWAY_AUTH_TOKEN": AUTH_TOKEN,
+        "GATEWAY_USER_ID": "e2e-tester",
         "HTTP_HOST": "127.0.0.1",
         "HTTP_PORT": str(http_port),
         "CLI_ENABLED": "false",

tests/e2e/scenarios/test_extension_uninstall_cleanup.py

@@ -1,266 +0,0 @@
-"""Extension uninstall secret cleanup E2E tests.
-
-Exercises real install/setup/auth/remove flows and verifies the backing
-secrets table is cleaned up when extensions are uninstalled.
-"""
-
-import sqlite3
-from urllib.parse import parse_qs, urlparse
-
-import httpx
-
-from helpers import api_get, api_post
-
-
-def _extract_state(auth_url: str) -> str:
-    parsed = urlparse(auth_url)
-    state = parse_qs(parsed.query).get("state", [None])[0]
-    assert state, f"auth_url should include state: {auth_url}"
-    return state
-
-
-def _secret_exists(db_path: str, user_id: str, name: str) -> bool:
-    with sqlite3.connect(db_path) as conn:
-        row = conn.execute(
-            "SELECT 1 FROM secrets WHERE user_id = ?1 AND name = ?2 LIMIT 1",
-            (user_id, name),
-        ).fetchone()
-    return row is not None
-
-
-def _secret_names(db_path: str, user_id: str) -> set[str]:
-    with sqlite3.connect(db_path) as conn:
-        rows = conn.execute(
-            "SELECT name FROM secrets WHERE user_id = ?1",
-            (user_id,),
-        ).fetchall()
-    return {row[0] for row in rows}
-
-
-async def _get_extension(base_url: str, name: str) -> dict | None:
-    response = await api_get(base_url, "/api/extensions", timeout=15)
-    response.raise_for_status()
-    for extension in response.json().get("extensions", []):
-        if extension["name"] == name:
-            return extension
-    return None
-
-
-async def _ensure_removed(base_url: str, name: str) -> None:
-    extension = await _get_extension(base_url, name)
-    if extension is not None:
-        response = await api_post(base_url, f"/api/extensions/{name}/remove", timeout=30)
-        assert response.status_code == 200, response.text
-        assert response.json().get("success") is True, response.text
-
-
-async def _install_extension(
-    base_url: str,
-    name: str,
-    *,
-    kind: str | None = None,
-    url: str | None = None,
-) -> None:
-    payload = {"name": name}
-    if kind is not None:
-        payload["kind"] = kind
-    if url is not None:
-        payload["url"] = url
-
-    response = await api_post(
-        base_url,
-        "/api/extensions/install",
-        json=payload,
-        timeout=180,
-    )
-    assert response.status_code == 200, response.text
-    assert response.json().get("success") is True, response.text
-
-
-async def test_remove_wasm_tool_deletes_unique_secret(extension_cleanup_server):
-    server = extension_cleanup_server["base_url"]
-    db_path = extension_cleanup_server["db_path"]
-    user_id = extension_cleanup_server["gateway_user_id"]
-
-    await _ensure_removed(server, "web-search")
-
-    await _install_extension(server, "web-search")
-
-    setup_response = await api_post(
-        server,
-        "/api/extensions/web-search/setup",
-        json={"secrets": {"brave_api_key": "cleanup-test-key"}},
-        timeout=30,
-    )
-    assert setup_response.status_code == 200, setup_response.text
-    assert setup_response.json().get("success") is True, setup_response.text
-    assert _secret_exists(db_path, user_id, "brave_api_key")
-
-    remove_response = await api_post(
-        server,
-        "/api/extensions/web-search/remove",
-        timeout=30,
-    )
-    assert remove_response.status_code == 200, remove_response.text
-    assert remove_response.json().get("success") is True, remove_response.text
-    assert not _secret_exists(db_path, user_id, "brave_api_key")
-
-
-async def test_remove_wasm_channel_deletes_setup_secrets(extension_cleanup_server):
-    server = extension_cleanup_server["base_url"]
-    db_path = extension_cleanup_server["db_path"]
-    user_id = extension_cleanup_server["gateway_user_id"]
-
-    await _ensure_removed(server, "discord")
-
-    await _install_extension(server, "discord", kind="wasm_channel")
-
-    setup_response = await api_post(
-        server,
-        "/api/extensions/discord/setup",
-        json={
-            "secrets": {
-                "discord_bot_token": "cleanup-discord-bot-token",
-                "discord_public_key": "cleanup-discord-public-key",
-            }
-        },
-        timeout=30,
-    )
-    assert setup_response.status_code == 200, setup_response.text
-    assert setup_response.json().get("success") is True, setup_response.text
-    assert _secret_exists(db_path, user_id, "discord_bot_token")
-    assert _secret_exists(db_path, user_id, "discord_public_key")
-
-    remove_response = await api_post(
-        server,
-        "/api/extensions/discord/remove",
-        timeout=30,
-    )
-    assert remove_response.status_code == 200, remove_response.text
-    assert remove_response.json().get("success") is True, remove_response.text
-    assert not _secret_exists(db_path, user_id, "discord_bot_token")
-    assert not _secret_exists(db_path, user_id, "discord_public_key")
-
-
-async def test_remove_shared_google_oauth_secrets_after_last_tool(extension_cleanup_server):
-    server = extension_cleanup_server["base_url"]
-    db_path = extension_cleanup_server["db_path"]
-    user_id = extension_cleanup_server["gateway_user_id"]
-
-    await _ensure_removed(server, "gmail")
-    await _ensure_removed(server, "google-drive")
-
-    await _install_extension(server, "gmail")
-    await _install_extension(server, "google-drive")
-
-    setup_response = await api_post(
-        server,
-        "/api/extensions/gmail/setup",
-        json={"secrets": {}},
-        timeout=30,
-    )
-    assert setup_response.status_code == 200, setup_response.text
-    auth_url = setup_response.json().get("auth_url")
-    assert auth_url, setup_response.text
-
-    async with httpx.AsyncClient() as client:
-        callback_response = await client.get(
-            f"{server}/oauth/callback",
-            params={"code": "mock_auth_code", "state": _extract_state(auth_url)},
-            timeout=30,
-            follow_redirects=True,
-        )
-    assert callback_response.status_code == 200, callback_response.text[:400]
-
-    shared_secrets = [
-        "google_oauth_token",
-        "google_oauth_token_refresh_token",
-        "google_oauth_token_scopes",
-    ]
-    for secret_name in shared_secrets:
-        assert _secret_exists(db_path, user_id, secret_name), f"expected {secret_name} to exist"
-
-    gmail_remove_response = await api_post(
-        server,
-        "/api/extensions/gmail/remove",
-        timeout=30,
-    )
-    assert gmail_remove_response.status_code == 200, gmail_remove_response.text
-    assert gmail_remove_response.json().get("success") is True, gmail_remove_response.text
-    for secret_name in shared_secrets:
-        assert _secret_exists(db_path, user_id, secret_name), (
-            f"{secret_name} should remain while google-drive is still installed"
-        )
-
-    drive_remove_response = await api_post(
-        server,
-        "/api/extensions/google-drive/remove",
-        timeout=30,
-    )
-    assert drive_remove_response.status_code == 200, drive_remove_response.text
-    assert drive_remove_response.json().get("success") is True, drive_remove_response.text
-    for secret_name in shared_secrets:
-        assert not _secret_exists(db_path, user_id, secret_name), (
-            f"{secret_name} should be deleted after the last Google tool is removed"
-        )
-
-
-async def test_remove_mcp_server_deletes_stored_secrets(extension_cleanup_server):
-    server = extension_cleanup_server["base_url"]
-    db_path = extension_cleanup_server["db_path"]
-    user_id = extension_cleanup_server["gateway_user_id"]
-    mcp_url = f"{extension_cleanup_server['mock_llm_url']}/mcp"
-
-    await _ensure_removed(server, "mock-mcp")
-
-    await _install_extension(server, "mock-mcp", kind="mcp_server", url=mcp_url)
-
-    setup_response = await api_post(
-        server,
-        "/api/extensions/mock-mcp/setup",
-        json={"secrets": {}},
-        timeout=30,
-    )
-    assert setup_response.status_code == 200, setup_response.text
-    auth_url = setup_response.json().get("auth_url")
-    if auth_url is None:
-        activate_response = await api_post(
-            server,
-            "/api/extensions/mock-mcp/activate",
-            timeout=30,
-        )
-        assert activate_response.status_code == 200, activate_response.text
-        auth_url = activate_response.json().get("auth_url")
-    assert auth_url, "mock-mcp should require OAuth in E2E"
-
-    async with httpx.AsyncClient() as client:
-        callback_response = await client.get(
-            f"{server}/oauth/callback",
-            params={"code": "mock_mcp_code", "state": _extract_state(auth_url)},
-            timeout=30,
-            follow_redirects=True,
-        )
-    assert callback_response.status_code == 200, callback_response.text[:400]
-
-    expected_mcp_secrets = [
-        "mcp_mock-mcp_access_token",
-        "mcp_mock-mcp_client_id",
-    ]
-    stored_secret_names = _secret_names(db_path, user_id)
-    for secret_name in expected_mcp_secrets:
-        assert secret_name in stored_secret_names, (
-            f"expected {secret_name} to exist; stored secrets were {sorted(stored_secret_names)}"
-        )
-
-    remove_response = await api_post(
-        server,
-        "/api/extensions/mock-mcp/remove",
-        timeout=30,
-    )
-    assert remove_response.status_code == 200, remove_response.text
-    assert remove_response.json().get("success") is True, remove_response.text
-    remaining_secret_names = _secret_names(db_path, user_id)
-    assert not any(name.startswith("mcp_mock-mcp_") for name in remaining_secret_names), (
-        f"mock-mcp secrets should be deleted on remove; remaining secrets were "
-        f"{sorted(remaining_secret_names)}"
-    )

tests/multi_tenant_integration.rs

@@ -42,6 +42,8 @@ const ALICE_USER_ID: &str = "alice";
 const BOB_USER_ID: &str = "bob";
 const OWNER_TOKEN: &str = "tok-owner-secret";
 const OWNER_SCOPE_ID: &str = "owner-scope";
+const GATEWAY_SENDER_ID: &str = "gateway-sender";
+
 /// Build a MultiAuthState with two users.
 fn two_user_auth() -> MultiAuthState {
     let mut tokens = HashMap::new();
@@ -49,7 +51,6 @@ fn two_user_auth() -> MultiAuthState {
         ALICE_TOKEN.to_string(),
         UserIdentity {
             user_id: ALICE_USER_ID.to_string(),
-            role: "admin".to_string(),
             workspace_read_scopes: Vec::new(),
         },
     );
@@ -57,7 +58,6 @@ fn two_user_auth() -> MultiAuthState {
         BOB_TOKEN.to_string(),
         UserIdentity {
             user_id: BOB_USER_ID.to_string(),
-            role: "admin".to_string(),
             workspace_read_scopes: vec!["shared".to_string()],
         },
     );
@@ -79,10 +79,7 @@ fn user_echo_app(auth: MultiAuthState) -> Router {
         .route("/api/whoami/scopes", get(echo_user_with_scopes))
         .route("/api/action", post(echo_user))
         .route("/api/chat/events", get(echo_user)) // SSE endpoint (allows query token)
-        .layer(middleware::from_fn_with_state(
-            ironclaw::channels::web::auth::CombinedAuthState::from(auth),
-            auth_middleware,
-        ))
+        .layer(middleware::from_fn_with_state(auth, auth_middleware))
 }
 
 // ===========================================================================
@@ -547,6 +544,7 @@ fn gateway_state_has_multi_tenant_fields() {
         prompt_queue: None,
         scheduler: None,
         owner_id: "fallback".to_string(),
+        default_sender_id: "fallback".to_string(),
         shutdown_tx: tokio::sync::RwLock::new(None),
         ws_tracker: Some(Arc::new(WsConnectionTracker::new())),
         llm_provider: None,
@@ -561,10 +559,10 @@ fn gateway_state_has_multi_tenant_fields() {
         webhook_rate_limiter: RateLimiter::new(10, 60),
         active_config: Default::default(),
         secrets_store: None,
-        db_auth: None,
     };
 
     assert_eq!(state.owner_id, "fallback");
+    assert_eq!(state.default_sender_id, "fallback");
     assert!(state.workspace_pool.is_none());
 }
 
@@ -595,7 +593,6 @@ async fn start_owner_scoped_sender_server() -> (
         OWNER_TOKEN.to_string(),
         UserIdentity {
             user_id: OWNER_SCOPE_ID.to_string(),
-            role: "admin".to_string(),
             workspace_read_scopes: Vec::new(),
         },
     );
@@ -603,7 +600,6 @@ async fn start_owner_scoped_sender_server() -> (
         BOB_TOKEN.to_string(),
         UserIdentity {
             user_id: BOB_USER_ID.to_string(),
-            role: "member".to_string(),
             workspace_read_scopes: Vec::new(),
         },
     );
@@ -623,6 +619,7 @@ async fn start_owner_scoped_sender_server() -> (
         prompt_queue: None,
         scheduler: None,
         owner_id: OWNER_SCOPE_ID.to_string(),
+        default_sender_id: GATEWAY_SENDER_ID.to_string(),
         shutdown_tx: tokio::sync::RwLock::new(None),
         ws_tracker: Some(Arc::new(WsConnectionTracker::new())),
         llm_provider: None,
@@ -637,10 +634,9 @@ async fn start_owner_scoped_sender_server() -> (
         startup_time: std::time::Instant::now(),
         active_config: Default::default(),
         secrets_store: None,
-        db_auth: None,
     });
 
-    let auth = MultiAuthState::multi(tokens).into();
+    let auth = MultiAuthState::multi(tokens);
     let addr: SocketAddr = "127.0.0.1:0".parse().unwrap();
     let bound = start_server(addr, state.clone(), auth)
         .await
@@ -775,7 +771,7 @@ async fn full_server_chat_send_rewrites_sender_only_for_owner_scope_rebind() {
         .expect("Timed out waiting for owner message")
         .expect("Agent channel closed");
     assert_eq!(owner_msg.user_id, OWNER_SCOPE_ID);
-    assert_eq!(owner_msg.sender_id, OWNER_SCOPE_ID);
+    assert_eq!(owner_msg.sender_id, GATEWAY_SENDER_ID);
     assert_eq!(owner_msg.content, "hello from owner");
 
     let other_resp = client
@@ -1009,6 +1005,7 @@ async fn start_multi_user_server_with_db() -> (
         prompt_queue: None,
         scheduler: None,
         owner_id: ALICE_USER_ID.to_string(),
+        default_sender_id: ALICE_USER_ID.to_string(),
         shutdown_tx: tokio::sync::RwLock::new(None),
         ws_tracker: Some(Arc::new(WsConnectionTracker::new())),
         llm_provider: None,
@@ -1023,11 +1020,10 @@ async fn start_multi_user_server_with_db() -> (
         webhook_rate_limiter: RateLimiter::new(10, 60),
         active_config: Default::default(),
         secrets_store: None,
-        db_auth: None,
     });
 
     let addr: SocketAddr = "127.0.0.1:0".parse().unwrap();
-    let bound = ironclaw::channels::web::server::start_server(addr, state.clone(), auth.into())
+    let bound = ironclaw::channels::web::server::start_server(addr, state.clone(), auth)
         .await
         .expect("Failed to start server with DB");
 

tests/openai_compat_integration.rs

@@ -205,6 +205,7 @@ async fn start_test_server_with_provider(
         prompt_queue: None,
         scheduler: None,
         owner_id: "test-user".to_string(),
+        default_sender_id: "test-user".to_string(),
         shutdown_tx: tokio::sync::RwLock::new(None),
         ws_tracker: Some(Arc::new(WsConnectionTracker::new())),
         llm_provider: Some(llm_provider),
@@ -219,7 +220,6 @@ async fn start_test_server_with_provider(
         startup_time: std::time::Instant::now(),
         active_config: ironclaw::channels::web::server::ActiveConfigSnapshot::default(),
         secrets_store: None,
-        db_auth: None,
     });
 
     let auth = ironclaw::channels::web::auth::MultiAuthState::single(
@@ -227,7 +227,7 @@ async fn start_test_server_with_provider(
         "test-user".to_string(),
     );
     let addr: SocketAddr = "127.0.0.1:0".parse().unwrap();
-    let bound_addr = start_server(addr, state.clone(), auth.into())
+    let bound_addr = start_server(addr, state.clone(), auth)
         .await
         .expect("Failed to start test server");
 
@@ -705,6 +705,7 @@ async fn test_no_llm_provider_returns_503() {
         prompt_queue: None,
         scheduler: None,
         owner_id: "test-user".to_string(),
+        default_sender_id: "test-user".to_string(),
         shutdown_tx: tokio::sync::RwLock::new(None),
         ws_tracker: Some(Arc::new(WsConnectionTracker::new())),
         llm_provider: None, // No LLM!
@@ -719,7 +720,6 @@ async fn test_no_llm_provider_returns_503() {
         startup_time: std::time::Instant::now(),
         active_config: ironclaw::channels::web::server::ActiveConfigSnapshot::default(),
         secrets_store: None,
-        db_auth: None,
     });
 
     let auth = ironclaw::channels::web::auth::MultiAuthState::single(
@@ -727,7 +727,7 @@ async fn test_no_llm_provider_returns_503() {
         "test-user".to_string(),
     );
     let addr: SocketAddr = "127.0.0.1:0".parse().unwrap();
-    let bound_addr = start_server(addr, state, auth.into()).await.unwrap();
+    let bound_addr = start_server(addr, state, auth).await.unwrap();
 
     let url = format!("http://{}/v1/chat/completions", bound_addr);
     let resp = client()
@@ -765,7 +765,7 @@ async fn test_chat_completions_body_too_large() {
             post(ironclaw::channels::web::openai_compat::chat_completions_handler),
         )
         .route_layer(middleware::from_fn_with_state(
-            ironclaw::channels::web::auth::CombinedAuthState::from(auth_state),
+            auth_state,
             ironclaw::channels::web::auth::auth_middleware,
         ))
         .layer(DefaultBodyLimit::max(10 * 1024 * 1024))

tests/support/gateway_workflow_harness.rs

@@ -227,6 +227,7 @@ impl GatewayWorkflowHarness {
             prompt_queue: None,
             scheduler: Some(scheduler_slot.clone()),
             owner_id: user_id.clone(),
+            default_sender_id: user_id.clone(),
             shutdown_tx: tokio::sync::RwLock::new(None),
             ws_tracker: Some(Arc::new(WsConnectionTracker::new())),
             llm_provider: Some(Arc::clone(&components.llm)),
@@ -241,7 +242,6 @@ impl GatewayWorkflowHarness {
             startup_time: Instant::now(),
             active_config: ironclaw::channels::web::server::ActiveConfigSnapshot::default(),
             secrets_store: None,
-            db_auth: None,
         });
 
         let mut agent = Agent::new(
@@ -300,7 +300,7 @@ impl GatewayWorkflowHarness {
         let addr = start_server(
             "127.0.0.1:0".parse().expect("valid localhost addr"),
             Arc::clone(&gateway_state),
-            auth.into(),
+            auth,
         )
         .await
         .expect("failed to start gateway server");

tests/ws_gateway_integration.rs

@@ -52,6 +52,7 @@ async fn start_test_server() -> (
         prompt_queue: None,
         scheduler: None,
         owner_id: "test-user".to_string(),
+        default_sender_id: "test-user".to_string(),
         shutdown_tx: tokio::sync::RwLock::new(None),
         ws_tracker: Some(Arc::new(WsConnectionTracker::new())),
         llm_provider: None,
@@ -66,7 +67,6 @@ async fn start_test_server() -> (
         startup_time: std::time::Instant::now(),
         active_config: ironclaw::channels::web::server::ActiveConfigSnapshot::default(),
         secrets_store: None,
-        db_auth: None,
     });
 
     let auth = ironclaw::channels::web::auth::MultiAuthState::single(
@@ -74,7 +74,7 @@ async fn start_test_server() -> (
         "test-user".to_string(),
     );
     let addr: SocketAddr = "127.0.0.1:0".parse().unwrap();
-    let bound_addr = start_server(addr, state.clone(), auth.into())
+    let bound_addr = start_server(addr, state.clone(), auth)
         .await
         .expect("Failed to start test server");