From c58e16757ad05e6b75289b34745608e26d61a9f7 Mon Sep 17 00:00:00 2001
From: Teknium <127238744+teknium1@users.noreply.github.com>
Date: Tue, 7 Apr 2026 10:17:44 -0700
Subject: [PATCH] docs: fix 40+ discrepancies between documentation and
 codebase (#5818)

Comprehensive audit of all ~100 doc pages against the actual code, fixing:

Reference docs:
- HERMES_API_TIMEOUT default 900 -> 1800 (env-vars)
- TERMINAL_DOCKER_IMAGE default python:3.11 -> nikolaik/python-nodejs (env-vars)
- compression.summary_model default shown as gemini -> actually empty string (env-vars)
- Add missing GOOGLE_API_KEY, GEMINI_API_KEY, GEMINI_BASE_URL env vars (env-vars)
- Add missing /branch (/fork) slash command (slash-commands)
- Fix hermes-cli tool count 39 -> 38 (toolsets-reference)
- Fix hermes-api-server drop list to include text_to_speech (toolsets-reference)
- Fix total tool count 47 -> 48, standalone 14 -> 15 (tools-reference)

User guide:
- web_extract.timeout default 30 -> 360 (configuration)
- Remove display.theme_mode (not implemented in code) (configuration)
- Remove display.background_process_notifications (not in defaults) (configuration)
- Browser inactivity timeout 300/5min -> 120/2min (browser)
- Screenshot path browser_screenshots -> cache/screenshots (browser)
- batch_runner default model claude-sonnet-4-20250514 -> claude-sonnet-4.6
- Add minimax to TTS provider list (voice-mode)
- Remove credential_pool_strategies from auth.json example (credential-pools)
- Fix Slack token path platforms/slack/ -> root ~/.hermes/ (slack)
- Fix Matrix store path for new installs (matrix)
- Fix WhatsApp session path for new installs (whatsapp)
- Fix HomeAssistant config from gateway.json to config.yaml (homeassistant)
- Fix WeCom gateway start command (wecom)

Developer guide:
- Fix tool/toolset counts in architecture overview
- Update line counts: main.py ~5500, setup.py ~3100, run.py ~7500, mcp_tool ~2200
- Replace nonexistent agent/memory_store.py with memory_manager.py + memory_provider.py
- Update _discover_tools() list: remove honcho_tools, add skill_manager_tool
- Add session_search and delegate_task to intercepted tools list (agent-loop)
- Fix budget warning: two-tier system (70% caution, 90% warning) (agent-loop)
- Fix gateway auth order (per-platform first, global last) (gateway-internals)
- Fix email_adapter.py -> email.py, add webhook.py + api_server.py (gateway-internals)
- Add 7 missing providers to provider-runtime list

Other:
- Add Docker --cap-add entries to security doc
- Fix Python version 3.10+ -> 3.11+ (contributing)
- Fix AGENTS.md discovery claim (not hierarchical walk) (tips)
- Fix cron 'add' -> canonical 'create' (cron-internals)
- Add pre_api_request/post_api_request hooks to plugin guide
- Add Google/Gemini provider to providers page
- Clarify OPENAI_BASE_URL deprecation (providers)
---
 website/docs/developer-guide/agent-loop.md    |  8 +++--
 website/docs/developer-guide/architecture.md  | 15 +++++----
 website/docs/developer-guide/contributing.md  |  2 +-
 .../docs/developer-guide/cron-internals.md    |  2 +-
 .../docs/developer-guide/gateway-internals.md | 11 ++++---
 .../docs/developer-guide/provider-runtime.md  |  7 ++++
 website/docs/developer-guide/tools-runtime.md |  3 +-
 website/docs/guides/build-a-hermes-plugin.md  |  2 ++
 website/docs/guides/tips.md                   |  4 +--
 website/docs/integrations/providers.md        |  5 +--
 .../docs/reference/environment-variables.md   |  9 +++--
 website/docs/reference/slash-commands.md      |  1 +
 website/docs/reference/tools-reference.md     |  4 +--
 website/docs/reference/toolsets-reference.md  |  4 +--
 website/docs/user-guide/configuration.md      | 18 ++--------
 .../user-guide/features/batch-processing.md   |  8 ++---
 website/docs/user-guide/features/browser.md   |  8 ++---
 .../user-guide/features/credential-pools.md   |  3 --
 .../docs/user-guide/features/voice-mode.md    |  2 +-
 .../user-guide/messaging/homeassistant.md     | 33 ++++++++++---------
 website/docs/user-guide/messaging/matrix.md   |  4 +--
 website/docs/user-guide/messaging/slack.md    |  2 +-
 website/docs/user-guide/messaging/wecom.md    |  2 +-
 website/docs/user-guide/messaging/whatsapp.md |  8 ++---
 website/docs/user-guide/security.md           |  3 ++
 25 files changed, 90 insertions(+), 78 deletions(-)

diff --git a/website/docs/developer-guide/agent-loop.md b/website/docs/developer-guide/agent-loop.md
index 39a96df64..4728a634b 100644
--- a/website/docs/developer-guide/agent-loop.md
+++ b/website/docs/developer-guide/agent-loop.md
@@ -151,9 +151,11 @@ for each tool_call in response.tool_calls:
 Some tools are intercepted by `run_agent.py` *before* reaching `handle_function_call()`:
 
 | Tool | Why intercepted |
-|------|-----------------|
+|------|--------------------|
 | `todo` | Reads/writes agent-local task state |
 | `memory` | Writes to persistent memory files with character limits |
+| `session_search` | Queries session history via the agent's session DB |
+| `delegate_task` | Spawns subagent(s) with isolated context |
 
 These tools modify agent state directly and return synthetic tool results without going through the registry.
 
@@ -180,7 +182,9 @@ The agent tracks iterations via `IterationBudget`:
 
 - Default: 90 iterations (configurable via `agent.max_turns`)
 - Shared across parent and child agents — a subagent consumes from the parent's budget
-- At 70%+ usage, `_get_budget_warning()` appends a `[BUDGET WARNING: ...]` to the last tool result
+- Two-tier budget pressure via `_get_budget_warning()`:
+  - At 70%+ usage (caution tier): appends `[BUDGET: Iteration X/Y. N iterations left. Start consolidating your work.]` to the last tool result
+  - At 90%+ usage (warning tier): appends `[BUDGET WARNING: Iteration X/Y. Only N iteration(s) left. Provide your final response NOW.]`
 - At 100%, the agent stops and returns a summary of work done
 
 ### Fallback Model
diff --git a/website/docs/developer-guide/architecture.md b/website/docs/developer-guide/architecture.md
index ab143dc2a..c08161b32 100644
--- a/website/docs/developer-guide/architecture.md
+++ b/website/docs/developer-guide/architecture.md
@@ -32,8 +32,8 @@ This page is the top-level map of Hermes Agent internals. Use it to orient yours
 │  ┌──────┴───────┐ ┌──────┴───────┐ ┌──────┴───────┐                │
 │  │ Compression  │ │ 3 API Modes  │ │ Tool Registry│                │
 │  │ & Caching    │ │ chat_compl.  │ │ (registry.py)│                │
-│  │              │ │ codex_resp.  │ │ 47 tools     │                │
-│  │              │ │ anthropic    │ │ 37 toolsets   │                │
+│  │              │ │ codex_resp.  │ │ 48 tools     │                │
+│  │              │ │ anthropic    │ │ 40 toolsets   │                │
 │  └──────────────┘ └──────────────┘ └──────────────┘                │
 └─────────────────────────────────────────────────────────────────────┘
            │                                    │
@@ -70,18 +70,19 @@ hermes-agent/
 │   ├── anthropic_adapter.py  # Anthropic Messages API format conversion
 │   ├── display.py            # KawaiiSpinner, tool preview formatting
 │   ├── skill_commands.py     # Skill slash commands
-│   ├── memory_store.py       # Persistent memory read/write
+│   ├── memory_manager.py    # Memory manager orchestration
+│   ├── memory_provider.py   # Memory provider ABC
 │   └── trajectory.py         # Trajectory saving helpers
 │
 ├── hermes_cli/               # CLI subcommands and setup
-│   ├── main.py               # Entry point — all `hermes` subcommands (~4,200 lines)
+│   ├── main.py               # Entry point — all `hermes` subcommands (~5,500 lines)
 │   ├── config.py             # DEFAULT_CONFIG, OPTIONAL_ENV_VARS, migration
 │   ├── commands.py           # COMMAND_REGISTRY — central slash command definitions
 │   ├── auth.py               # PROVIDER_REGISTRY, credential resolution
 │   ├── runtime_provider.py   # Provider → api_mode + credentials
 │   ├── models.py             # Model catalog, provider model lists
 │   ├── model_switch.py       # /model command logic (CLI + gateway shared)
-│   ├── setup.py              # Interactive setup wizard (~3,500 lines)
+│   ├── setup.py              # Interactive setup wizard (~3,100 lines)
 │   ├── skin_engine.py        # CLI theming engine
 │   ├── skills_config.py      # hermes skills — enable/disable per platform
 │   ├── skills_hub.py         # /skills slash command
@@ -100,14 +101,14 @@ hermes-agent/
 │   ├── browser_tool.py       # 11 browser automation tools
 │   ├── code_execution_tool.py # execute_code sandbox
 │   ├── delegate_tool.py      # Subagent delegation
-│   ├── mcp_tool.py           # MCP client (~1,050 lines)
+│   ├── mcp_tool.py           # MCP client (~2,200 lines)
 │   ├── credential_files.py   # File-based credential passthrough
 │   ├── env_passthrough.py    # Env var passthrough for sandboxes
 │   ├── ansi_strip.py         # ANSI escape stripping
 │   └── environments/         # Terminal backends (local, docker, ssh, modal, daytona, singularity)
 │
 ├── gateway/                  # Messaging platform gateway
-│   ├── run.py                # GatewayRunner — message dispatch (~5,800 lines)
+│   ├── run.py                # GatewayRunner — message dispatch (~7,500 lines)
 │   ├── session.py            # SessionStore — conversation persistence
 │   ├── delivery.py           # Outbound message delivery
 │   ├── pairing.py            # DM pairing authorization
diff --git a/website/docs/developer-guide/contributing.md b/website/docs/developer-guide/contributing.md
index 603b416ac..f9b9e0ec5 100644
--- a/website/docs/developer-guide/contributing.md
+++ b/website/docs/developer-guide/contributing.md
@@ -33,7 +33,7 @@ We value contributions in this order:
 | Requirement | Notes |
 |-------------|-------|
 | **Git** | With `--recurse-submodules` support |
-| **Python 3.10+** | uv will install it if missing |
+| **Python 3.11+** | uv will install it if missing |
 | **uv** | Fast Python package manager ([install](https://docs.astral.sh/uv/)) |
 | **Node.js 18+** | Optional — needed for browser tools and WhatsApp bridge |
 
diff --git a/website/docs/developer-guide/cron-internals.md b/website/docs/developer-guide/cron-internals.md
index 060a8400f..cc8435dbe 100644
--- a/website/docs/developer-guide/cron-internals.md
+++ b/website/docs/developer-guide/cron-internals.md
@@ -185,7 +185,7 @@ The `hermes cron` CLI provides direct job management:
 
 ```bash
 hermes cron list                    # Show all jobs
-hermes cron add                     # Interactive job creation
+hermes cron create                  # Interactive job creation (alias: add)
 hermes cron edit <job_id>           # Edit job configuration
 hermes cron pause <job_id>          # Pause a running job
 hermes cron resume <job_id>         # Resume a paused job
diff --git a/website/docs/developer-guide/gateway-internals.md b/website/docs/developer-guide/gateway-internals.md
index f875c401f..1371bdd34 100644
--- a/website/docs/developer-guide/gateway-internals.md
+++ b/website/docs/developer-guide/gateway-internals.md
@@ -12,7 +12,7 @@ The messaging gateway is the long-running process that connects Hermes to 14+ ex
 
 | File | Purpose |
 |------|---------|
-| `gateway/run.py` | `GatewayRunner` — main loop, slash commands, message dispatch (~7,200 lines) |
+| `gateway/run.py` | `GatewayRunner` — main loop, slash commands, message dispatch (~7,500 lines) |
 | `gateway/session.py` | `SessionStore` — conversation persistence and session key construction |
 | `gateway/delivery.py` | Outbound message delivery to target platforms/channels |
 | `gateway/pairing.py` | DM pairing flow for user authorization |
@@ -91,10 +91,11 @@ Commands that must reach the runner while the agent is blocked (like `/approve`)
 
 The gateway uses a multi-layer authorization check, evaluated in order:
 
-1. **Gateway-wide allow-all** (`GATEWAY_ALLOW_ALL_USERS`) — if set, all users are authorized
+1. **Per-platform allow-all flag** (e.g., `TELEGRAM_ALLOW_ALL_USERS`) — if set, all users on that platform are authorized
 2. **Platform allowlist** (e.g., `TELEGRAM_ALLOWED_USERS`) — comma-separated user IDs
 3. **DM pairing** — authenticated users can pair new users via a pairing code
-4. **Admin escalation** — some commands require admin status beyond basic authorization
+4. **Global allow-all** (`GATEWAY_ALLOW_ALL_USERS`) — if set, all users across all platforms are authorized
+5. **Default: deny** — unauthorized users are rejected
 
 ### DM Pairing Flow
 
@@ -154,11 +155,13 @@ gateway/platforms/
 ├── signal.py            # Signal via signal-cli REST API
 ├── matrix.py            # Matrix via matrix-nio (optional E2EE)
 ├── mattermost.py        # Mattermost WebSocket API
-├── email_adapter.py     # Email via IMAP/SMTP
+├── email.py             # Email via IMAP/SMTP
 ├── sms.py               # SMS via Twilio
 ├── dingtalk.py          # DingTalk WebSocket
 ├── feishu.py            # Feishu/Lark WebSocket or webhook
 ├── wecom.py             # WeCom (WeChat Work) callback
+├── webhook.py           # Inbound/outbound webhook adapter
+├── api_server.py        # REST API server adapter
 └── homeassistant.py     # Home Assistant conversation integration
 ```
 
diff --git a/website/docs/developer-guide/provider-runtime.md b/website/docs/developer-guide/provider-runtime.md
index 007729595..bf9abe0ce 100644
--- a/website/docs/developer-guide/provider-runtime.md
+++ b/website/docs/developer-guide/provider-runtime.md
@@ -42,11 +42,18 @@ Current provider families include:
 - OpenRouter
 - Nous Portal
 - OpenAI Codex
+- Copilot / Copilot ACP
 - Anthropic (native)
+- Google / Gemini
+- Alibaba / DashScope
+- DeepSeek
 - Z.AI
 - Kimi / Moonshot
 - MiniMax
 - MiniMax China
+- Kilo Code
+- Hugging Face
+- OpenCode Zen / OpenCode Go
 - Custom (`provider: custom`) — first-class provider for any OpenAI-compatible endpoint
 - Named custom providers (`custom_providers` list in config.yaml)
 
diff --git a/website/docs/developer-guide/tools-runtime.md b/website/docs/developer-guide/tools-runtime.md
index f6fbc86de..8e349a505 100644
--- a/website/docs/developer-guide/tools-runtime.md
+++ b/website/docs/developer-guide/tools-runtime.md
@@ -55,6 +55,7 @@ _modules = [
     "tools.mixture_of_agents_tool",
     "tools.image_generation_tool",
     "tools.skills_tool",
+    "tools.skill_manager_tool",
     "tools.browser_tool",
     "tools.cronjob_tools",
     "tools.rl_training_tool",
@@ -67,7 +68,7 @@ _modules = [
     "tools.delegate_tool",
     "tools.process_registry",
     "tools.send_message_tool",
-    "tools.honcho_tools",
+    # "tools.honcho_tools",  # Removed — Honcho is now a memory provider plugin
     "tools.homeassistant_tool",
 ]
 ```
diff --git a/website/docs/guides/build-a-hermes-plugin.md b/website/docs/guides/build-a-hermes-plugin.md
index 91fb62f3a..85b1c8177 100644
--- a/website/docs/guides/build-a-hermes-plugin.md
+++ b/website/docs/guides/build-a-hermes-plugin.md
@@ -405,6 +405,8 @@ Each hook is documented in full on the **[Event Hooks reference](/docs/user-guid
 | [`post_llm_call`](/docs/user-guide/features/hooks#post_llm_call) | Once per turn, after the tool-calling loop (successful turns only) | `session_id: str, user_message: str, assistant_response: str, conversation_history: list, model: str, platform: str` | ignored |
 | [`on_session_start`](/docs/user-guide/features/hooks#on_session_start) | New session created (first turn only) | `session_id: str, model: str, platform: str` | ignored |
 | [`on_session_end`](/docs/user-guide/features/hooks#on_session_end) | End of every `run_conversation` call + CLI exit | `session_id: str, completed: bool, interrupted: bool, model: str, platform: str` | ignored |
+| [`pre_api_request`](/docs/user-guide/features/hooks#pre_api_request) | Before each HTTP request to the LLM provider | `method: str, url: str, headers: dict, body: dict` | ignored |
+| [`post_api_request`](/docs/user-guide/features/hooks#post_api_request) | After each HTTP response from the LLM provider | `method: str, url: str, status_code: int, response: dict` | ignored |
 
 Most hooks are fire-and-forget observers — their return values are ignored. The exception is `pre_llm_call`, which can inject context into the conversation.
 
diff --git a/website/docs/guides/tips.md b/website/docs/guides/tips.md
index 804e9046b..4d21b7357 100644
--- a/website/docs/guides/tips.md
+++ b/website/docs/guides/tips.md
@@ -95,9 +95,9 @@ Use `SOUL.md` for durable personality. Use `AGENTS.md` for project-specific inst
 
 Already have a `.cursorrules` or `.cursor/rules/*.mdc` file? Hermes reads those too. No need to duplicate your coding conventions — they're loaded automatically from the working directory.
 
-### Hierarchical Discovery
+### Discovery
 
-Hermes walks the directory tree and discovers **all** `AGENTS.md` files at every level. In a monorepo, put project-wide conventions at the root and team-specific ones in subdirectories — they're all concatenated together with path headers.
+Hermes loads the top-level `AGENTS.md` from the current working directory at session start. Subdirectory `AGENTS.md` files are discovered lazily during tool calls (via `subdirectory_hints.py`) and injected into tool results — they are not loaded upfront into the system prompt.
 
 :::tip
 Keep context files focused and concise. Every character counts against your token budget since they're injected into every single message.
diff --git a/website/docs/integrations/providers.md b/website/docs/integrations/providers.md
index ca6a0c511..e23924dc4 100644
--- a/website/docs/integrations/providers.md
+++ b/website/docs/integrations/providers.md
@@ -31,7 +31,8 @@ You need at least one way to connect to an LLM. Use `hermes model` to switch pro
 | **OpenCode Go** | `OPENCODE_GO_API_KEY` in `~/.hermes/.env` (provider: `opencode-go`) |
 | **DeepSeek** | `DEEPSEEK_API_KEY` in `~/.hermes/.env` (provider: `deepseek`) |
 | **Hugging Face** | `HF_TOKEN` in `~/.hermes/.env` (provider: `huggingface`, aliases: `hf`) |
-| **Custom Endpoint** | `hermes model` (saved in `config.yaml`) or `OPENAI_BASE_URL` + `OPENAI_API_KEY` in `~/.hermes/.env` |
+| **Google / Gemini** | `GOOGLE_API_KEY` (or `GEMINI_API_KEY`) in `~/.hermes/.env` (provider: `gemini`) |
+| **Custom Endpoint** | `hermes model` → choose "Custom endpoint" (saved in `config.yaml`) |
 
 :::tip Model key alias
 In the `model:` config section, you can use either `default:` or `model:` as the key name for your model ID. Both `model: { default: my-model }` and `model: { model: my-model }` work identically.
@@ -219,7 +220,7 @@ model:
 ```
 
 :::warning Legacy env vars
-`OPENAI_BASE_URL` and `LLM_MODEL` in `.env` are **deprecated**. The CLI ignores `LLM_MODEL` entirely (only the gateway reads it). Use `hermes model` or edit `config.yaml` directly — both persist correctly across restarts and Docker containers.
+`OPENAI_BASE_URL` and `LLM_MODEL` in `.env` are **deprecated**. `OPENAI_BASE_URL` is no longer consulted for endpoint resolution — `config.yaml` is the single source of truth. The CLI ignores `LLM_MODEL` entirely (only the gateway reads it as a fallback). Use `hermes model` or edit `config.yaml` directly — both persist correctly across restarts and Docker containers.
 :::
 
 Both approaches persist to `config.yaml`, which is the source of truth for model, provider, and base URL.
diff --git a/website/docs/reference/environment-variables.md b/website/docs/reference/environment-variables.md
index 899349325..7d40546c3 100644
--- a/website/docs/reference/environment-variables.md
+++ b/website/docs/reference/environment-variables.md
@@ -39,6 +39,9 @@ All variables go in `~/.hermes/.env`. You can also set them with `hermes config
 | `KILOCODE_BASE_URL` | Override Kilo Code base URL (default: `https://api.kilo.ai/api/gateway`) |
 | `HF_TOKEN` | Hugging Face token for Inference Providers ([huggingface.co/settings/tokens](https://huggingface.co/settings/tokens)) |
 | `HF_BASE_URL` | Override Hugging Face base URL (default: `https://router.huggingface.co/v1`) |
+| `GOOGLE_API_KEY` | Google AI Studio API key ([aistudio.google.com/app/apikey](https://aistudio.google.com/app/apikey)) |
+| `GEMINI_API_KEY` | Alias for `GOOGLE_API_KEY` |
+| `GEMINI_BASE_URL` | Override Google AI Studio base URL |
 | `ANTHROPIC_API_KEY` | Anthropic Console API key ([console.anthropic.com](https://console.anthropic.com/)) |
 | `ANTHROPIC_TOKEN` | Manual or legacy Anthropic OAuth/setup-token override |
 | `DASHSCOPE_API_KEY` | Alibaba Cloud DashScope API key for Qwen models ([modelstudio.console.alibabacloud.com](https://modelstudio.console.alibabacloud.com/)) |
@@ -108,7 +111,7 @@ For native Anthropic auth, Hermes prefers Claude Code's own credential files whe
 | Variable | Description |
 |----------|-------------|
 | `TERMINAL_ENV` | Backend: `local`, `docker`, `ssh`, `singularity`, `modal`, `daytona` |
-| `TERMINAL_DOCKER_IMAGE` | Docker image (default: `python:3.11`) |
+| `TERMINAL_DOCKER_IMAGE` | Docker image (default: `nikolaik/python-nodejs:python3.11-nodejs20`) |
 | `TERMINAL_DOCKER_FORWARD_ENV` | JSON array of env var names to explicitly forward into Docker terminal sessions. Note: skill-declared `required_environment_variables` are forwarded automatically — you only need this for vars not declared by any skill. |
 | `TERMINAL_DOCKER_VOLUMES` | Additional Docker volume mounts (comma-separated `host:container` pairs) |
 | `TERMINAL_DOCKER_MOUNT_CWD_TO_WORKSPACE` | Advanced opt-in: mount the launch cwd into Docker `/workspace` (`true`/`false`, default: `false`) |
@@ -262,7 +265,7 @@ For cloud sandbox backends, persistence is filesystem-oriented. `TERMINAL_LIFETI
 | `HERMES_HUMAN_DELAY_MIN_MS` | Custom delay range minimum (ms) |
 | `HERMES_HUMAN_DELAY_MAX_MS` | Custom delay range maximum (ms) |
 | `HERMES_QUIET` | Suppress non-essential output (`true`/`false`) |
-| `HERMES_API_TIMEOUT` | LLM API call timeout in seconds (default: `900`) |
+| `HERMES_API_TIMEOUT` | LLM API call timeout in seconds (default: `1800`) |
 | `HERMES_EXEC_ASK` | Enable execution approval prompts in gateway mode (`true`/`false`) |
 | `HERMES_ENABLE_PROJECT_PLUGINS` | Enable auto-discovery of repo-local plugins from `./.hermes/plugins/` (`true`/`false`, default: `false`) |
 | `HERMES_BACKGROUND_NOTIFICATIONS` | Background process notification mode in gateway: `all` (default), `result`, `error`, `off` |
@@ -283,7 +286,7 @@ Context compression is configured exclusively through the `compression` section
 compression:
   enabled: true
   threshold: 0.50
-  summary_model: google/gemini-3-flash-preview
+  summary_model: ""                            # empty = use main configured model
   summary_provider: auto
   summary_base_url: null  # Custom OpenAI-compatible endpoint for summaries
 ```
diff --git a/website/docs/reference/slash-commands.md b/website/docs/reference/slash-commands.md
index f750e7e7d..89a30c46b 100644
--- a/website/docs/reference/slash-commands.md
+++ b/website/docs/reference/slash-commands.md
@@ -37,6 +37,7 @@ Type `/` in the CLI to open the autocomplete menu. Built-in commands are case-in
 | `/background <prompt>` (alias: `/bg`) | Run a prompt in a separate background session. The agent processes your prompt independently — your current session stays free for other work. Results appear as a panel when the task finishes. See [CLI Background Sessions](/docs/user-guide/cli#background-sessions). |
 | `/btw <question>` | Ephemeral side question using session context (no tools, not persisted). Useful for quick clarifications without affecting the conversation history. |
 | `/plan [request]` | Load the bundled `plan` skill to write a markdown plan instead of executing the work. Plans are saved under `.hermes/plans/` relative to the active workspace/backend working directory. |
+| `/branch [name]` (alias: `/fork`) | Branch the current session (explore a different path) |
 
 ### Configuration
 
diff --git a/website/docs/reference/tools-reference.md b/website/docs/reference/tools-reference.md
index cd798697d..0728945da 100644
--- a/website/docs/reference/tools-reference.md
+++ b/website/docs/reference/tools-reference.md
@@ -6,9 +6,9 @@ description: "Authoritative reference for Hermes built-in tools, grouped by tool
 
 # Built-in Tools Reference
 
-This page documents all 47 built-in tools in the Hermes tool registry, grouped by toolset. Availability varies by platform, credentials, and enabled toolsets.
+This page documents all 48 built-in tools in the Hermes tool registry, grouped by toolset. Availability varies by platform, credentials, and enabled toolsets.
 
-**Quick counts:** 11 browser tools, 4 file tools, 10 RL tools, 4 Home Assistant tools, 2 terminal tools, 2 web tools, and 14 standalone tools across other toolsets.
+**Quick counts:** 11 browser tools, 4 file tools, 10 RL tools, 4 Home Assistant tools, 2 terminal tools, 2 web tools, and 15 standalone tools across other toolsets.
 
 :::tip MCP Tools
 In addition to built-in tools, Hermes can load tools dynamically from MCP servers. MCP tools appear with a server-name prefix (e.g., `github_create_issue` for the `github` MCP server). See [MCP Integration](/docs/user-guide/features/mcp) for configuration.
diff --git a/website/docs/reference/toolsets-reference.md b/website/docs/reference/toolsets-reference.md
index 7d566e602..1c225b233 100644
--- a/website/docs/reference/toolsets-reference.md
+++ b/website/docs/reference/toolsets-reference.md
@@ -88,9 +88,9 @@ Platform toolsets define the complete tool configuration for a deployment target
 
 | Toolset | Differences from `hermes-cli` |
 |---------|-------------------------------|
-| `hermes-cli` | Full toolset — all 39 tools including `clarify`. The default for interactive CLI sessions. |
+| `hermes-cli` | Full toolset — all 38 tools including `clarify`. The default for interactive CLI sessions. |
 | `hermes-acp` | Drops `clarify`, `cronjob`, `image_generate`, `mixture_of_agents`, `send_message`, `text_to_speech`, homeassistant tools. Focused on coding tasks in IDE context. |
-| `hermes-api-server` | Drops `clarify` and `send_message`. Adds everything else — suitable for programmatic access where user interaction isn't possible. |
+| `hermes-api-server` | Drops `clarify`, `send_message`, and `text_to_speech`. Adds everything else — suitable for programmatic access where user interaction isn't possible. |
 | `hermes-telegram` | Same as `hermes-cli`. |
 | `hermes-discord` | Same as `hermes-cli`. |
 | `hermes-slack` | Same as `hermes-cli`. |
diff --git a/website/docs/user-guide/configuration.md b/website/docs/user-guide/configuration.md
index 063329084..2e26a9f62 100644
--- a/website/docs/user-guide/configuration.md
+++ b/website/docs/user-guide/configuration.md
@@ -574,7 +574,7 @@ auxiliary:
     model: ""                  # e.g. "google/gemini-2.5-flash"
     base_url: ""
     api_key: ""
-    timeout: 30                # seconds
+    timeout: 360               # seconds (6min) — per-attempt LLM summarization
 
   # Dangerous command approval classifier
   approval:
@@ -622,7 +622,7 @@ auxiliary:
 ```
 
 :::tip
-Each auxiliary task has a configurable `timeout` (in seconds). Defaults: vision 30s, web_extract 30s, approval 30s, compression 120s. Increase these if you use slow local models for auxiliary tasks. Vision also has a separate `download_timeout` (default 30s) for the HTTP image download — increase this for slow connections or self-hosted image servers.
+Each auxiliary task has a configurable `timeout` (in seconds). Defaults: vision 30s, web_extract 360s, approval 30s, compression 120s. Increase these if you use slow local models for auxiliary tasks. Vision also has a separate `download_timeout` (default 30s) for the HTTP image download — increase this for slow connections or self-hosted image servers.
 :::
 
 :::info
@@ -804,30 +804,16 @@ display:
   tool_progress: all      # off | new | all | verbose
   tool_progress_command: false  # Enable /verbose slash command in messaging gateway
   skin: default           # Built-in or custom CLI skin (see user-guide/features/skins)
-  theme_mode: auto        # auto | light | dark — color scheme for skin-aware rendering
   personality: "kawaii"  # Legacy cosmetic field still surfaced in some summaries
   compact: false          # Compact output mode (less whitespace)
   resume_display: full    # full (show previous messages on resume) | minimal (one-liner only)
   bell_on_complete: false # Play terminal bell when agent finishes (great for long tasks)
   show_reasoning: false   # Show model reasoning/thinking above each response (toggle with /reasoning show|hide)
   streaming: false        # Stream tokens to terminal as they arrive (real-time output)
-  background_process_notifications: all  # all | result | error | off (gateway only)
   show_cost: false        # Show estimated $ cost in the CLI status bar
   tool_preview_length: 0  # Max chars for tool call previews (0 = no limit, show full paths/commands)
 ```
 
-### Theme mode
-
-The `theme_mode` setting controls whether skins render in light or dark mode:
-
-| Mode | Behavior |
-|------|----------|
-| `auto` (default) | Detects your terminal's background color automatically. Falls back to `dark` if detection fails. |
-| `light` | Forces light-mode skin colors. Skins that define a `colors_light` override use those colors instead of the default dark-mode palette. |
-| `dark` | Forces dark-mode skin colors. |
-
-This works with any skin — built-in or custom. Skin authors can provide `colors_light` in their skin definition for optimal light-terminal appearance.
-
 | Mode | What you see |
 |------|-------------|
 | `off` | Silent — just the final response |
diff --git a/website/docs/user-guide/features/batch-processing.md b/website/docs/user-guide/features/batch-processing.md
index 40df279c0..3cab1eba2 100644
--- a/website/docs/user-guide/features/batch-processing.md
+++ b/website/docs/user-guide/features/batch-processing.md
@@ -20,7 +20,7 @@ python batch_runner.py \
     --dataset_file=data/prompts.jsonl \
     --batch_size=10 \
     --run_name=my_first_run \
-    --model=anthropic/claude-sonnet-4-20250514 \
+    --model=anthropic/claude-sonnet-4.6 \
     --num_workers=4
 
 # Resume an interrupted run
@@ -56,7 +56,7 @@ Entries can optionally include:
 | `--batch_size` | (required) | Prompts per batch |
 | `--run_name` | (required) | Name for this run (used for output dir and checkpointing) |
 | `--distribution` | `"default"` | Toolset distribution to sample from |
-| `--model` | `claude-sonnet-4-20250514` | Model to use |
+| `--model` | `claude-sonnet-4.6` | Model to use |
 | `--base_url` | `https://openrouter.ai/api/v1` | API base URL |
 | `--api_key` | (env var) | API key for model |
 | `--max_turns` | `10` | Maximum tool-calling iterations per prompt |
@@ -127,7 +127,7 @@ Each line in `trajectories.jsonl` is a JSON object:
   "metadata": {
     "batch_num": 2,
     "timestamp": "2026-01-15T10:30:00",
-    "model": "anthropic/claude-sonnet-4-20250514"
+    "model": "anthropic/claude-sonnet-4.6"
   },
   "completed": true,
   "partial": false,
@@ -193,7 +193,7 @@ python batch_runner.py \
     --dataset_file=data/coding_prompts.jsonl \
     --batch_size=20 \
     --run_name=coding_v1 \
-    --model=anthropic/claude-sonnet-4-20250514 \
+    --model=anthropic/claude-sonnet-4.6 \
     --num_workers=8 \
     --distribution=default \
     --max_turns=15
diff --git a/website/docs/user-guide/features/browser.md b/website/docs/user-guide/features/browser.md
index 0dafec10b..bf7c61689 100644
--- a/website/docs/user-guide/features/browser.md
+++ b/website/docs/user-guide/features/browser.md
@@ -174,8 +174,8 @@ BROWSERBASE_KEEP_ALIVE=true
 # Examples: 600000 (10min), 1800000 (30min)
 BROWSERBASE_SESSION_TIMEOUT=600000
 
-# Inactivity timeout before auto-cleanup in seconds (default: 300)
-BROWSER_INACTIVITY_TIMEOUT=300
+# Inactivity timeout before auto-cleanup in seconds (default: 120)
+BROWSER_INACTIVITY_TIMEOUT=120
 ```
 
 ### Install agent-browser CLI
@@ -265,7 +265,7 @@ The screenshot is saved persistently and the file path is returned alongside the
 What does the chart on this page show?
 ```
 
-Screenshots are stored in `~/.hermes/browser_screenshots/` and automatically cleaned up after 24 hours.
+Screenshots are stored in `~/.hermes/cache/screenshots/` and automatically cleaned up after 24 hours.
 
 ### `browser_console`
 
@@ -333,7 +333,7 @@ If paid features aren't available on your plan, Hermes automatically falls back
 ## Session Management
 
 - Each task gets an isolated browser session via Browserbase
-- Sessions are automatically cleaned up after inactivity (default: 5 minutes)
+- Sessions are automatically cleaned up after inactivity (default: 2 minutes)
 - A background thread checks every 30 seconds for stale sessions
 - Emergency cleanup runs on process exit to prevent orphaned sessions
 - Sessions are released via the Browserbase API (`REQUEST_RELEASE` status)
diff --git a/website/docs/user-guide/features/credential-pools.md b/website/docs/user-guide/features/credential-pools.md
index 275e08a04..50eb8ca60 100644
--- a/website/docs/user-guide/features/credential-pools.md
+++ b/website/docs/user-guide/features/credential-pools.md
@@ -215,9 +215,6 @@ Pool state is stored in `~/.hermes/auth.json` under the `credential_pool` key:
       }
     ]
   },
-  "credential_pool_strategies": {
-    "openrouter": "round_robin"
-  }
 }
 ```
 
diff --git a/website/docs/user-guide/features/voice-mode.md b/website/docs/user-guide/features/voice-mode.md
index 31d6ea27d..2befd59e0 100644
--- a/website/docs/user-guide/features/voice-mode.md
+++ b/website/docs/user-guide/features/voice-mode.md
@@ -395,7 +395,7 @@ stt:
 
 # Text-to-Speech
 tts:
-  provider: "edge"                 # "edge" (free) | "elevenlabs" | "openai" | "neutts"
+  provider: "edge"                 # "edge" (free) | "elevenlabs" | "openai" | "neutts" | "minimax"
   edge:
     voice: "en-US-AriaNeural"      # 322 voices, 74 languages
   elevenlabs:
diff --git a/website/docs/user-guide/messaging/homeassistant.md b/website/docs/user-guide/messaging/homeassistant.md
index ec72383b8..f57b43977 100644
--- a/website/docs/user-guide/messaging/homeassistant.md
+++ b/website/docs/user-guide/messaging/homeassistant.md
@@ -130,22 +130,25 @@ The Home Assistant gateway adapter connects via WebSocket and subscribes to `sta
 By default, **no events are forwarded**. You must configure at least one of `watch_domains`, `watch_entities`, or `watch_all` to receive events. Without filters, a warning is logged at startup and all state changes are silently dropped.
 :::
 
-Configure which events the agent sees in `~/.hermes/gateway.json` under the Home Assistant platform's `extra` section:
+Configure which events the agent sees in `~/.hermes/config.yaml` under the Home Assistant platform's `extra` section:
 
-```json
-{
-  "platforms": {
-    "homeassistant": {
-      "enabled": true,
-      "extra": {
-        "watch_domains": ["climate", "binary_sensor", "alarm_control_panel", "light"],
-        "watch_entities": ["sensor.front_door_battery"],
-        "ignore_entities": ["sensor.uptime", "sensor.cpu_usage", "sensor.memory_usage"],
-        "cooldown_seconds": 30
-      }
-    }
-  }
-}
+```yaml
+platforms:
+  homeassistant:
+    enabled: true
+    extra:
+      watch_domains:
+        - climate
+        - binary_sensor
+        - alarm_control_panel
+        - light
+      watch_entities:
+        - sensor.front_door_battery
+      ignore_entities:
+        - sensor.uptime
+        - sensor.cpu_usage
+        - sensor.memory_usage
+      cooldown_seconds: 30
 ```
 
 | Setting | Default | Description |
diff --git a/website/docs/user-guide/messaging/matrix.md b/website/docs/user-guide/messaging/matrix.md
index 943751c12..6f4764055 100644
--- a/website/docs/user-guide/messaging/matrix.md
+++ b/website/docs/user-guide/messaging/matrix.md
@@ -265,13 +265,13 @@ MATRIX_ENCRYPTION=true
 
 When E2EE is enabled, Hermes:
 
-- Stores encryption keys in `~/.hermes/matrix/store/`
+- Stores encryption keys in `~/.hermes/platforms/matrix/store/` (legacy installs: `~/.hermes/matrix/store/`)
 - Uploads device keys on first connection
 - Decrypts incoming messages and encrypts outgoing messages automatically
 - Auto-joins encrypted rooms when invited
 
 :::warning
-If you delete the `~/.hermes/matrix/store/` directory, the bot loses its encryption keys. You'll need to verify the device again in your Matrix client. Back up this directory if you want to preserve encrypted sessions.
+If you delete the `~/.hermes/platforms/matrix/store/` directory, the bot loses its encryption keys. You'll need to verify the device again in your Matrix client. Back up this directory if you want to preserve encrypted sessions.
 :::
 
 :::info
diff --git a/website/docs/user-guide/messaging/slack.md b/website/docs/user-guide/messaging/slack.md
index 9b8edf0c3..7ce1b0352 100644
--- a/website/docs/user-guide/messaging/slack.md
+++ b/website/docs/user-guide/messaging/slack.md
@@ -384,7 +384,7 @@ platforms:
 In addition to tokens in the environment or config, Hermes also loads tokens from an **OAuth token file** at:
 
 ```
-~/.hermes/platforms/slack/slack_tokens.json
+~/.hermes/slack_tokens.json
 ```
 
 This file is a JSON object mapping team IDs to token entries:
diff --git a/website/docs/user-guide/messaging/wecom.md b/website/docs/user-guide/messaging/wecom.md
index 1a078a892..937872b9a 100644
--- a/website/docs/user-guide/messaging/wecom.md
+++ b/website/docs/user-guide/messaging/wecom.md
@@ -50,7 +50,7 @@ WECOM_HOME_CHANNEL=chat_id
 ### 3. Start the gateway
 
 ```bash
-hermes gateway start
+hermes gateway
 ```
 
 ## Features
diff --git a/website/docs/user-guide/messaging/whatsapp.md b/website/docs/user-guide/messaging/whatsapp.md
index 6011992ec..ac6c07b77 100644
--- a/website/docs/user-guide/messaging/whatsapp.md
+++ b/website/docs/user-guide/messaging/whatsapp.md
@@ -134,7 +134,7 @@ The gateway starts the WhatsApp bridge automatically using the saved session.
 
 ## Session Persistence
 
-The Baileys bridge saves its session under `~/.hermes/whatsapp/session`. This means:
+The Baileys bridge saves its session under `~/.hermes/platforms/whatsapp/session`. This means:
 
 - **Sessions survive restarts** — you don't need to re-scan the QR code every time
 - The session data includes encryption keys and device credentials
@@ -180,7 +180,7 @@ whatsapp:
 |---------|----------|
 | **QR code not scanning** | Ensure terminal is wide enough (60+ columns). Try a different terminal. Make sure you're scanning from the correct WhatsApp account (bot number, not personal). |
 | **QR code expires** | QR codes refresh every ~20 seconds. If it times out, restart `hermes whatsapp`. |
-| **Session not persisting** | Check that `~/.hermes/whatsapp/session` exists and is writable. If containerized, mount it as a persistent volume. |
+| **Session not persisting** | Check that `~/.hermes/platforms/whatsapp/session` exists and is writable. If containerized, mount it as a persistent volume. |
 | **Logged out unexpectedly** | WhatsApp unlinks devices after long inactivity. Keep the phone on and connected to the network, then re-pair with `hermes whatsapp` if needed. |
 | **Bridge crashes or reconnect loops** | Restart the gateway, update Hermes, and re-pair if the session was invalidated by a WhatsApp protocol change. |
 | **Bot stops working after WhatsApp update** | Update Hermes to get the latest bridge version, then re-pair. |
@@ -206,8 +206,8 @@ whatsapp:
   unauthorized_dm_behavior: ignore
 ```
 
-- The `~/.hermes/whatsapp/session` directory contains full session credentials — protect it like a password
-- Set file permissions: `chmod 700 ~/.hermes/whatsapp/session`
+- The `~/.hermes/platforms/whatsapp/session` directory contains full session credentials — protect it like a password
+- Set file permissions: `chmod 700 ~/.hermes/platforms/whatsapp/session`
 - Use a **dedicated phone number** for the bot to isolate risk from your personal account
 - If you suspect compromise, unlink the device from WhatsApp → Settings → Linked Devices
 - Phone numbers in logs are partially redacted, but review your log retention policy
diff --git a/website/docs/user-guide/security.md b/website/docs/user-guide/security.md
index 22e76b5a2..5554e896c 100644
--- a/website/docs/user-guide/security.md
+++ b/website/docs/user-guide/security.md
@@ -277,6 +277,9 @@ Every container runs with these flags (defined in `tools/environments/docker.py`
 ```python
 _SECURITY_ARGS = [
     "--cap-drop", "ALL",                          # Drop ALL Linux capabilities
+    "--cap-add", "DAC_OVERRIDE",                  # Root can write to bind-mounted dirs
+    "--cap-add", "CHOWN",                         # Package managers need file ownership
+    "--cap-add", "FOWNER",                        # Package managers need file ownership
     "--security-opt", "no-new-privileges",         # Block privilege escalation
     "--pids-limit", "256",                         # Limit process count
     "--tmpfs", "/tmp:rw,nosuid,size=512m",         # Size-limited /tmp