diff --git a/docs/agent.md b/docs/agent.md
index cbceaf6..dbe3944 100644
--- a/docs/agent.md
+++ b/docs/agent.md
@@ -10,13 +10,17 @@
 ### `run(session_id, user_message)` → `str`
 Non-streaming. Full tool-calling loop, returns final text. No planning phase.
 
-### `run_ephemeral(user_message, profile_id)` → `str`
-Non-persistent subagent. No DB reads/writes. Temporary in-memory context. Called by `SpawnAgentTool`.
+### `run_ephemeral(user_message, profile_id)` → `tuple[str, bool]`
+Non-persistent subagent. Temporary in-memory context. Called by `SpawnAgentTool`.
+
+Returns `(result_text, completed_normally)`. `completed_normally` is `False` if the subagent hit the iteration limit or timed out.
 
 `spawn_agent.profile_id` is optional. If omitted, `SpawnAgentTool` resolves the parent session's current profile. If provided, the subagent uses the selected profile's model, `subagent_system_prompt`, planning flags, and tool set. Its tools come from that profile's `subagent_tools`, falling back to `enabled_tools` when `subagent_tools` is empty.
 
 When spawned from a persistent parent session, session-aware tools run under the parent session id so file tools resolve the user's session directory rather than a `subagent_*` directory.
 
+`run_ephemeral` reads the parent session from the DB when `parent_session_id` is provided, so session-aware tools (filesystem, todo, scratchpad) operate on the parent's data.
+
 ---
 
 ## Planning phase (`_run_planning`)
diff --git a/docs/api.md b/docs/api.md
index fb64dc1..f30fed2 100644
--- a/docs/api.md
+++ b/docs/api.md
@@ -14,7 +14,27 @@
 
 **Response `200`**
 ```json
-{ "status": "ok" }
+{
+  "status": "ok",
+  "embed": {
+    "status": "ok",
+    "model": "nomic-embed-text",
+    "dimensions": 768
+  }
+}
+```
+
+#### `GET /health/embed`
+
+Embedding model health check. Returns the first vector of a test string to verify the embed backend is responsive.
+
+**Response `200`**
+```json
+{
+  "status": "ok",
+  "model": "nomic-embed-text",
+  "dimensions": 768
+}
 ```
 
 ---
@@ -27,6 +47,10 @@
 
 Redirect to gnexus-auth OAuth authorization endpoint. Sets PKCE + state internally.
 
+**Query params**
+- `return_to` — URL to redirect back to after login (default: `/`)
+- `platform` — `browser` (default) or `android` (affects redirect after callback)
+
 **Response `302`** → Location: gnexus-auth `/oauth/authorize`
 
 ---
@@ -45,6 +69,7 @@
 
 **Errors**
 - `400` — invalid state, PKCE failure, or token exchange failed
+- `503` — OAuth is not configured (missing `gnexus_auth_client_id` or `gnexus_auth_client_secret`)
 
 ---
 
@@ -80,6 +105,16 @@
   "id": "user-uuid",
   "email": "user@example.com",
   "display_name": "User Name",
+  "username": "username",
+  "first_name": "First",
+  "last_name": "Last",
+  "phone": "+1234567890",
+  "birth_date": "1990-01-01",
+  "country": "US",
+  "city": "New York",
+  "locale": "en-US",
+  "avatar_url": "https://...",
+  "profile_url": "https://...",
   "role": "admin",
   "permissions": ["navi.sessions.read_all", "navi.memory.read_all"]
 }
@@ -90,11 +125,22 @@
 
 ---
 
+#### `GET /auth/status`
+
+Check if the user is currently authenticated without returning full profile.
+
+**Response `200`**
+```json
+{ "authenticated": true }
+```
+
+---
+
 ### Profiles & Tools
 
 #### `GET /agents/profiles`
 
-List available agent profiles.
+List available agent profiles. Non-admin users do not see `is_admin_only` profiles.
 
 **Response `200`**
 ```json
@@ -105,7 +151,15 @@
     "description": "General-purpose assistant",
     "enabled_tools": ["todo", "web_search", "filesystem", "..."],
     "llm_backend": "ollama",
-    "model": "gemma4:31b-cloud"
+    "model": ["gemma4:31b-cloud", "gemma4:26b-a4b-it-q4_K_M"],
+    "temperature": 0.65,
+    "top_k": null,
+    "top_p": null,
+    "max_iterations": 10,
+    "iteration_budget_enabled": true,
+    "think_enabled": true,
+    "subagent_think_enabled": null,
+    "mcp_servers": {"gnexus-book": ["read", "write"]}
   }
 ]
 ```
@@ -117,19 +171,62 @@
 **Response `200`**
 ```json
 [
-  { "name": "web_search", "description": "Search the web using DuckDuckGo." },
-  { "name": "filesystem",  "description": "Read, write and list files." }
+  {
+    "name": "web_search",
+    "description": "Search the web using DuckDuckGo.",
+    "parameters": {"type": "object", "properties": {...}, "required": [...]}
+  },
+  {
+    "name": "filesystem",
+    "description": "Read, write and list files.",
+    "parameters": {"type": "object", "properties": {...}, "required": [...]}
+  }
 ]
 ```
 
 ---
 
+#### `GET /agents/prompts`
+
+Return the fully resolved system prompt for each profile (persona + profile system_prompt + context provider injections + MCP server instructions).
+
+**Response `200`**
+```json
+{
+  "secretary": "system prompt text...",
+  "server_admin": "system prompt text..."
+}
+```
+
+---
+
+#### `GET /agents/mcp_servers`
+
+Return all configured MCP servers with their resolved tools per profile.
+
+**Response `200`**
+```json
+{
+  "gnexus-book": {
+    "connected": true,
+    "tools": [
+      {"name": "gnexus-book_list_inventory", "description": "..."}
+    ],
+    "instructions": "MANDATORY: Before answering ANY question..."
+  }
+}
+```
+
+---
+
 ### Sessions
 
 #### `POST /sessions`
 
 Create a new session.
 
+**Auth**: requires authenticated user.
+
 **Request body**
 ```json
 { "profile_id": "secretary" }
@@ -145,6 +242,7 @@
 ```
 
 **Errors**
+- `401` — not authenticated
 - `404` — profile not found
 
 ---
@@ -153,7 +251,38 @@
 
 List all sessions sorted by activity (pinned first).
 
-**Response `200`**
+**Auth**: requires authenticated user.
+
+**Query params**
+| Param | Default | Description |
+|---|---|---|
+| `limit` | `50` | Page size |
+| `offset` | `0` | Items to skip |
+| `profile_id` | — | Filter by profile |
+
+**Response `200`** (when pagination params provided)
+```json
+{
+  "items": [
+    {
+      "session_id": "550e8400-...",
+      "profile_id": "secretary",
+      "name": "Research task",
+      "message_count": 12,
+      "preview": "Last 60 chars of the most recent message",
+      "pinned": false,
+      "created_at": "2026-04-10T15:00:00+00:00",
+      "last_active": "2026-04-10T18:00:00+00:00"
+    }
+  ],
+  "limit": 50,
+  "offset": 0,
+  "has_more": true,
+  "next_offset": 50
+}
+```
+
+**Response `200`** (plain list when no pagination params)
 ```json
 [
   {
@@ -177,6 +306,8 @@
 
 Full session with message history (display history — never compressed).
 
+**Auth**: requires authenticated user (or ownership of the session).
+
 **Response `200`**
 ```json
 {
@@ -290,6 +421,8 @@
 
 LLM context (what the model actually sees). May differ from `messages` — compressed history replaces old turns with a summary. Debug endpoint.
 
+**Auth**: requires `admin` role.
+
 **Response `200`**
 ```json
 {
@@ -301,17 +434,50 @@
 }
 ```
 
+**Errors**
+- `403` — not admin
+
 ---
 
 #### `GET /sessions/{session_id}/planning`
 
 All planning phase debug logs for the session. Each entry is one planning run.
 
+**Auth**: requires `admin` role.
+
 **Response `200`**
 ```json
 { "session_id": "...", "logs": [ { "phase": "...", "output": "..." }, ... ] }
 ```
 
+**Errors**
+- `403` — not admin
+
+---
+
+#### `GET /sessions/{session_id}/content`
+
+List published session content (artifacts registered via `content_publish` tool).
+
+**Response `200`**
+```json
+{
+  "content": [
+    {
+      "id": "...",
+      "filename": "report.html",
+      "path": "/abs/path/to/content/...",
+      "size": 102400,
+      "content_type": "text/html",
+      "created_at": "2026-04-10T18:00:00+00:00"
+    }
+  ]
+}
+```
+
+**Errors**
+- `404` — session not found
+
 ---
 
 #### `POST /sessions/{session_id}/files`
@@ -330,7 +496,7 @@
 {
   "name": "report.pdf",
   "size": 102400,
-  "path": "session_files/550e8400-.../report.pdf",
+  "path": "/abs/path/to/session_files/550e8400-.../report.pdf",
   "content_type": "application/pdf"
 }
 ```
@@ -344,7 +510,10 @@
 
 #### `GET /sessions/{session_id}/files/{filename}`
 
-Download or view an uploaded file. Images, PDFs and plain text are served inline; everything else as an attachment.
+Download or view an uploaded file. Images, PDFs, plain text and HTML are served inline; everything else as an attachment.
+
+**Query params**
+- `download` — force attachment download regardless of content type
 
 **Response `200`** — file bytes
 
@@ -795,6 +964,165 @@
 
 ---
 
+#### `GET /admin/sessions/{session_id}`
+
+Full session details including messages. Bypasses ownership check.
+
+**Response `200`**
+```json
+{
+  "session_id": "...",
+  "profile_id": "secretary",
+  "user_id": "user-uuid",
+  "name": "Research task",
+  "messages": [...],
+  "context_token_count": 4913,
+  "max_context_tokens": 65536,
+  "pinned": false,
+  "created_at": "...",
+  "last_active": "..."
+}
+```
+
+**Errors**
+- `404` — session not found
+
+---
+
+#### `DELETE /admin/sessions/{session_id}`
+
+Delete any session (bypasses ownership). Also deletes session files.
+
+**Response `204`** — no body
+
+**Errors**
+- `404` — session not found
+
+---
+
+#### `GET /admin/users/{user_id}`
+
+Single user details.
+
+**Response `200`**
+```json
+{
+  "id": "user-uuid",
+  "email": "user@example.com",
+  "display_name": "User Name",
+  "role": "admin",
+  "permissions": ["navi.sessions.read_all"],
+  "created_at": "...",
+  "updated_at": "..."
+}
+```
+
+**Errors**
+- `404` — user not found
+
+---
+
+#### `GET /admin/users/{user_id}/sessions`
+
+Sessions owned by a specific user.
+
+**Response `200`**
+```json
+[
+  {
+    "session_id": "...",
+    "profile_id": "secretary",
+    "name": "Research task",
+    "message_count": 12,
+    "pinned": false,
+    "created_at": "...",
+    "last_active": "..."
+  }
+]
+```
+
+---
+
+#### `POST /admin/ollama/clear-blacklists`
+
+Manually clear dead-server and dead-model blacklists for the Ollama fallback backend. Useful when a transient failure caused a 5-minute blacklist and you want immediate recovery.
+
+**Response `204`** — no body
+
+---
+
+#### `GET /admin/profiles/{profile_id}`
+
+Full profile configuration including system prompt.
+
+**Response `200`**
+```json
+{
+  "id": "secretary",
+  "name": "Personal Secretary",
+  "description": "General-purpose assistant",
+  "short_description": "...",
+  "full_description": {"specialization": "...", "when_to_use": "...", "key_tools": [...]},
+  "system_prompt": "...",
+  "subagent_system_prompt": "...",
+  "llm_backend": "ollama",
+  "model": ["gemma4:31b-cloud", "gemma4:26b-a4b-it-q4_K_M"],
+  "temperature": 0.65,
+  "top_k": null,
+  "top_p": null,
+  "num_thread": null,
+  "max_iterations": 10,
+  "planning_enabled": false,
+  "planning_mandatory": false,
+  "planning_phase1_enabled": true,
+  "planning_phase2_enabled": false,
+  "planning_phase3_enabled": true,
+  "think_enabled": true,
+  "iteration_budget_enabled": true,
+  "goal_anchoring_enabled": true,
+  "goal_anchoring_interval": 5,
+  "anti_stall_enabled": true,
+  "anti_stall_threshold": 8,
+  "step_validation_enabled": false,
+  "adaptive_replan_enabled": false,
+  "subagent_tools": [...],
+  "subagent_planning_enabled": false,
+  "subagent_think_enabled": null,
+  "enabled_tools": [...],
+  "context_providers": [],
+  "is_admin_only": false
+}
+```
+
+**Errors**
+- `404` — profile not found
+
+---
+
+#### `PUT /admin/profiles/{profile_id}`
+
+Update profile configuration on disk and in-memory. Accepts partial updates — only provided fields are modified.
+
+**Request body** (partial)
+```json
+{
+  "temperature": 0.5,
+  "max_iterations": 20,
+  "planning_enabled": true
+}
+```
+
+**Response `200`**
+```json
+{ "ok": true }
+```
+
+**Errors**
+- `400` — invalid profile data
+- `404` — profile not found
+
+---
+
 #### `PATCH /admin/users/{user_id}/role`
 
 Update cached role. Requires admin.
@@ -822,7 +1150,7 @@
 
 **Response `200`**
 ```json
-{ "ok": true, "note": "Profile availability is managed via profile config files" }
+{ "ok": true }
 ```
 
 ---
@@ -840,6 +1168,7 @@
 
 **Errors**
 - `400` — invalid payload
+- `503` — OAuth not configured
 
 ---
 
diff --git a/docs/config.md b/docs/config.md
index 01a2c9c..4631859 100644
--- a/docs/config.md
+++ b/docs/config.md
@@ -13,13 +13,24 @@
 | `OLLAMA_THINK` | bool | `true` | Enable extended reasoning (thinking) |
 | `OLLAMA_BACKENDS_FILE` | str | `""` | Path to JSON file with multi-server config (see below). When set, overrides `OLLAMA_HOST`/`OLLAMA_API_KEY`. |
 | `OLLAMA_REQUEST_TIMEOUT` | int | `30` | Seconds before Ollama request times out (affects fallback speed) |
+| `EMBEDDING_OLLAMA_HOST` | str | `""` | Ollama server for embedding model (falls back to `OLLAMA_HOST` if empty) |
+| `EMBEDDING_OLLAMA_API_KEY` | str | `""` | API key for embedding Ollama server |
+| `EMBEDDING_MODEL` | str | `nomic-embed-text:latest` | Embedding model for memory vector search |
+| `EMBEDDING_DIMENSIONS` | int | `768` | Vector dimensionality for embeddings |
 | `OPENAI_API_KEY` | str | `""` | OpenAI API key (if using OpenAI backend) |
 | `OPENAI_MODEL` | str | `"gpt-4"` | Default model for OpenAI backend |
-| `OPENAI_BASE_URL` | str | `None` | Custom base URL for OpenAI-compatible endpoints (e.g. vLLM, LM Studio) |
-| `ANTHROPIC_API_KEY` | str | `""` | Anthropic API key (if using Anthropic backend) |
+| `OPENAI_BASE_URL` | str \| None | `None` | Custom base URL for OpenAI-compatible endpoints (e.g. vLLM, LM Studio) |
+| `ANTHROPIC_API_KEY` | str | `""` | Reserved — no Anthropic backend implemented yet |
 
 For direct Ollama Cloud access without fallback: set `OLLAMA_HOST=https://ollama.com` and `OLLAMA_API_KEY=<key>`.
 
+## Web Search
+
+| Variable | Type | Default | Description |
+|---|---|---|---|
+| `BRAVE_SEARCH_API_KEY` | str | `""` | Brave Search API key (free tier: 2000 req/month). Used when DuckDuckGo returns no results. |
+| `SEARXNG_URL` | str | `""` | Self-hosted SearXNG meta-search URL, e.g. `http://localhost:8888` |
+
 ### Multi-server fallback (`OLLAMA_BACKENDS_FILE`)
 
 When `OLLAMA_BACKENDS_FILE` points to a JSON file, Navi uses `FallbackOllamaBackend` instead of the single-server backend. The file contains an ordered list of servers:
@@ -66,6 +77,12 @@
 
 `settings.fs_allowed_paths_list` and `settings.terminal_allowed_commands_list` are computed properties that parse the comma-separated strings into lists.
 
+| Variable | Type | Default | Description |
+|---|---|---|---|
+| `TERMINAL_USER_ALLOWED_COMMANDS` | str | long allowlist | Comma-separated allowed executables for non-admin users. Admin bypasses this restriction. |
+
+`settings.terminal_user_allowed_commands_list` — computed property parsed from the comma-separated string.
+
 ## Database
 
 | Variable | Type | Default | Description |
@@ -83,6 +100,7 @@
 | Variable | Type | Default | Description |
 |---|---|---|---|
 | `TOOLS_DIR` | str | `tools` | Directory for user-defined tools (auto-discovered at startup) |
+| `CONTEXT_PROVIDERS_DIR` | str | `context_providers` | Directory for user-defined context providers (auto-discovered at startup) |
 
 ## Session files
 
@@ -107,6 +125,7 @@
 | `CONTEXT_KEEP_RECENT` | int | `8` | Number of recent conversation turns to keep verbatim |
 | `CONTEXT_SUMMARY_TEMPERATURE` | float | `0.3` | Temperature for the summarization LLM call |
 | `CONTEXT_SUMMARY_MAX_TOKENS` | int | `3000` | Max output tokens for the summary LLM call |
+| `OUTPUT_RESERVE_TOKENS` | int | `2048` | Headroom reserved for model response in context size checks |
 
 ## Gmail
 
@@ -124,6 +143,8 @@
 | `GNAUTH_CLIENT_SECRET` | str | `""` | OAuth client secret |
 | `GNAUTH_REDIRECT_URI` | str | `http://localhost:8000/auth/callback` | Must match redirect URI registered in gnexus-auth |
 | `GNAUTH_ADMIN_ROLE_SLUG` | str | `navi_admin` | Role slug that maps to Navi `admin` role |
+| `GNAUTH_USER_ROLE_SLUG` | str | `navi_user` | Role slug that maps to Navi `user` role |
+| `GNAUTH_PROFILE_PATH` | str | `/account/profile` | Path appended to `gnauth_base_url` for profile links |
 | `NAVI_AUTH_ENCRYPTION_KEY` | str | `""` | **Fernet key** (base64, 32 bytes). Generate once with `python -c "from cryptography.fernet import Fernet; print(Fernet.generate_key().decode())"`. Never change after first launch. |
 | `NAVI_AUTH_COOKIE_NAME` | str | `navi_auth_session` | Session cookie name |
 | `NAVI_AUTH_COOKIE_SECURE` | bool | `False` | Set `True` behind HTTPS |
diff --git a/docs/memory.md b/docs/memory.md
index 265e581..b400040 100644
--- a/docs/memory.md
+++ b/docs/memory.md
@@ -83,16 +83,16 @@
 
 `user_id` references `navi_users(id)` with `ON DELETE CASCADE`. Facts and summaries are scoped per user. Admin with `navi.memory.read_all` can pass `user_id=None` for global search.
 
-`MemoryStore` is initialized synchronously (creates tables), all operations are async via asyncpg (PostgreSQL).
+`MemoryStore` lazily creates tables on first async operation via `_get_pool()`. All operations are async via asyncpg (PostgreSQL).
 
 ### Key operations
 
 | Method | Description |
 |---|---|
 | `upsert_fact(..., user_id=None)` | Insert or update a fact scoped to user |
-| `search_facts(query, limit=15, user_id=None)` | **Vector search first** (cosine distance, cutoff 0.3), then ILIKE fallback. `user_id=None` requires admin permission for global search. |
+| `search_facts(query, user_id=None, limit=15)` | **Vector search first** (cosine distance, cutoff 0.3), then ILIKE fallback. `user_id=None` requires admin permission for global search. |
 | `delete_fact(key, category=None, user_id=None)` | Delete by key, optionally filtered by category and user |
-| `get_all_facts(limit=None, offset=0, search=None, sort_by="category", sort_order="desc", user_id=None, all_users=False)` | All facts ordered by `sort_by`. Pass `all_users=True` for admin global view. |
+| `get_all_facts(user_id=None, all_users=False, limit=None, offset=0, search=None, sort_by="category", sort_order="desc")` | All facts ordered by `sort_by`. Pass `all_users=True` for admin global view. |
 | `get_summary(user_id=None)` | Current narrative summary text for user |
 | `set_summary(content, user_id=None)` | Replace the summary for user |
 | `mark_session_extracted(session_id)` | Record extraction timestamp |
diff --git a/docs/profiles.md b/docs/profiles.md
index ca55ffe..427eed2 100644
--- a/docs/profiles.md
+++ b/docs/profiles.md
@@ -30,14 +30,17 @@
 | `llm_backend` | str | `"ollama"` | Backend key: `"ollama"`, `"openai"` |
 | `model` | str or list[str] | `["gemma4:31b-cloud"]` | Model priority list — first available wins. String is accepted and auto-wrapped. |
 | `temperature` | float | `0.7` | Sampling temperature for main loop calls |
-| `max_iterations` | int | `20` | Hard cap on tool-calling iterations per turn |
+| `max_iterations` | int | `10` | Hard cap on tool-calling iterations per turn |
+| `top_k` | int \| None | `None` | Ollama sampling top_k |
+| `top_p` | float \| None | `None` | Ollama sampling top_p |
+| `num_thread` | int \| None | `None` | CPU threads for local inference. `None` = Ollama default |
 
 ### Tools
 
 | Key | Type | Default | Description |
 |---|---|---|---|
 | `enabled_tools` | list[str] | **required** | Tool names available in the main loop |
-| `subagent_tools` | list[str] | `[]` | Tools available to sub-agents spawned from this profile. Falls back to `enabled_tools` if empty. |
+| `subagent_tools` | list[str] | `[]` | Tools available to sub-agents spawned from this profile. Falls back to `enabled_tools` (full list) if empty. |
 
 `spawn_agent` may receive an optional `profile_id`. If omitted, the subagent uses the parent session's current profile. If provided, the subagent uses the selected profile's model, prompt, planning flags, and `subagent_tools`/`enabled_tools` fallback.
 
@@ -51,7 +54,7 @@
 | `goal_anchoring_interval` | int | `5` | N for goal anchoring. |
 | `anti_stall_enabled` | bool | `true` | Detect looping without todo progress and inject a hard warning. |
 | `anti_stall_threshold` | int | `8` | Consecutive iterations without progress before stall warning fires. |
-| `step_validation_enabled` | bool | `false` | After each todo step is marked done, run a lightweight LLM check: "did the result satisfy the goal?" Adds ~1 LLM call per step. |
+| `step_validation_enabled` | bool | `false` | Reserved flag — todo validation is unconditional in the current implementation. |
 | `adaptive_replan_enabled` | bool | `false` | When a todo step is marked failed, trigger a re-planning pass. Depends on `step_validation_enabled`. |
 
 ### Planning
@@ -74,7 +77,11 @@
 
 | Key | Type | Default | Description |
 |---|---|---|---|
+| `subagent_think_enabled` | bool \| None | `None` | Extended reasoning for sub-agents. `None` = inherit `think_enabled` from parent profile. |
 | `subagent_planning_enabled` | bool | `false` | Sub-agents spawned from this profile also run the planning pipeline before their tool loop. |
+| `context_providers` | list[str] | `[]` | Extra context providers to inject for this profile (by name). Global providers are always injected. |
+| `mcp_servers` | dict | `{}` | MCP servers referenced by this profile. Format: `{"server_name": ["group1", "group2"]}` or `{"server_name": ["*"]}` for all tools. |
+| `is_admin_only` | bool | `false` | If `true`, profile is hidden from non-admin users in the profile list. |
 
 ---
 
diff --git a/docs/sessions.md b/docs/sessions.md
index 7ddfbc4..5c5a18c 100644
--- a/docs/sessions.md
+++ b/docs/sessions.md
@@ -29,6 +29,7 @@
 | `is_compression: bool` | Marker message injected when context compression ran |
 | `is_summary: bool` | A summary message replacing compressed history in `session.context` |
 | `thinking: str \| None` | LLM reasoning captured during a tool-calling turn |
+| `metadata: dict` | Tool result metadata (e.g. `is_image`, `base64`) |
 
 ## Dual-buffer design
 
@@ -58,6 +59,7 @@
 - `count_all(user_id=None, is_admin=False, search=None)` → total matching sessions
 - `search_list(limit, offset, user_id=None, is_admin=False, search=None, sort_by="last_active", sort_order="desc")` → paginated, filtered, sorted sessions
 - `delete(session_id)` → `bool`
+- `list_page(user_id=None, is_admin=False, limit=50, offset=0)` → paginated list with `has_more` flag
 - `set_pinned(session_id, pinned)` → `bool`
 - `set_name(session_id, name)` → `bool`
 
@@ -80,7 +82,7 @@
 
 Config values (`settings`):
 - `context_compression_enabled: bool = True`
-- `context_compression_threshold: float = 0.80` — trigger at 80% of `ollama_num_ctx`
+- `context_compression_threshold: float = 0.70` — trigger at 70% of `ollama_num_ctx`
 - `context_keep_recent: int = 10` — keep last N conversational turns verbatim
 - `context_summary_temperature: float = 0.3`
 
diff --git a/docs/tools.md b/docs/tools.md
index 691327b..1da31f8 100644
--- a/docs/tools.md
+++ b/docs/tools.md
@@ -24,9 +24,7 @@
 | `WriteToolTool` | `write_tool` | Write a new user tool file and reload immediately |
 | `ListToolsTool` | `list_tools` | Return the live tool list from registry |
 | `ToolManualTool` | `tool_manual` | Return manuals/{name}.md or auto-generate from schema |
-| `MemorySaveTool` | `memory_save` | Save a fact to long-term memory |
-| `MemorySearchTool` | `memory_search` | Search long-term memory facts |
-| `MemoryForgetTool` | `memory_forget` | Delete a fact from long-term memory |
+| `MemoryTool` | `memory` | Unified memory tool: save, search, and forget facts |
 | `SpawnAgentTool` | `spawn_agent` | Spawn an isolated subagent (blocking). Optional `profile_id` selects another profile; omitted means parent profile |
 | `SwitchProfileTool` | `switch_profile` | Switch the active profile for a session |
 | `ListProfilesTool` | `list_profiles` | List all available profiles |
@@ -37,6 +35,7 @@
 | `Render3DTool` | `render_3d` | Render preview PNG images from an STL file (up to 3 views) |
 | `DeleteToolTool` | `delete_tool` | Delete a user tool file |
 | `TestToolTool` | `test_tool` | Run a user tool and verify its output |
+| `McpStatusTool` | `mcp_status` | Check connectivity and list tools for configured MCP servers |
 | `ReflectTool` | `reflect` | Self-reflection and analysis |
 
 ### User tools (`tools/*.py`)
diff --git a/docs/websocket.md b/docs/websocket.md
index 76a671e..723628e 100644
--- a/docs/websocket.md
+++ b/docs/websocket.md
@@ -39,7 +39,7 @@
 | Frame | When |
 |---|---|
 | `{"type": "stream_start"}` | Before any agent output begins |
-| `{"type": "stream_end", "content": "...", "context_tokens": N, "max_context_tokens": N, "elapsed_seconds": N, "tool_call_count": N, "token_count": N}` | After final text, before workers |
+| `{"type": "stream_end", "content": "...", "context_tokens": N, "max_context_tokens": N, "elapsed_seconds": N, "tool_call_count": N, "token_count": N, "message_index": N}` | After final text, before workers |
 | `{"type": "stream_stopped"}` | If the user stopped generation |
 | `{"type": "error", "message": "..."}` | On any unhandled error |
 
@@ -57,7 +57,7 @@
 
 | Frame | When |
 |---|---|
-| `{"type": "planning_status", "phase": "analysis\|reflect\|plan", "label": "...", "is_subagent": bool}` | During planning phase — progress label for UI |
+| `{"type": "planning_status", "phase": 1|2|3, "label": "...", "is_subagent": bool}` | During planning phase — progress label for UI. `phase`: 1=analysis, 2=reflect, 3=plan |
 | `{"type": "plan_ready", "plan": "...", "is_subagent": bool}` | Before tool-calling loop if `planning_enabled` and a plan was generated |
 
 `planning_status` frames arrive during each planning phase (analysis → optional reflect → plan). `is_subagent: true` means the planning is running inside a subagent — route it into the spawn_agent card, never into the top-level UI.
@@ -69,7 +69,7 @@
 | Frame | When |
 |---|---|
 | `{"type": "tool_started", "tool": "name", "args": {...}, "is_subagent": bool}` | Immediately when a tool call begins (before execution) |
-| `{"type": "tool_call", "tool": "name", "args": {...}, "result": "...", "success": bool, "is_subagent": bool}` | When the tool finishes |
+| `{"type": "tool_call", "tool": "name", "args": {...}, "result": "...", "success": bool, "is_subagent": bool, "metadata": {...}}` | When the tool finishes |
 
 `is_subagent: true` indicates the tool call was made by a nested subagent, not the top-level agent.
 
@@ -83,7 +83,7 @@
 
 | Frame | When |
 |---|---|
-| `{"type": "context_compressed", "messages_before": N, "messages_after": N, "summary": "..."}` | After context compression runs |
+| `{"type": "context_compressed", "messages_before": N, "messages_after": N, "summary": "...", "context_tokens": N, "max_context_tokens": N}` | After context compression runs |
 | `{"type": "profile_switched", "profile_id": "...", "profile_name": "..."}` | When `switch_profile` tool succeeds |
 | `{"type": "heartbeat"}` | Periodic keepalive during long silent operations (every 20 s) |
 | `{"type": "session_sync"}` | Client should reload session history from REST (`GET /sessions/{id}`) |