diff --git a/acp_adapter/tools.py b/acp_adapter/tools.py index 8756aa929..52313220b 100644 --- a/acp_adapter/tools.py +++ b/acp_adapter/tools.py @@ -39,7 +39,6 @@ TOOL_KIND_MAP: Dict[str, ToolKind] = { "browser_scroll": "execute", "browser_press": "execute", "browser_back": "execute", - "browser_close": "execute", "browser_get_images": "read", # Agent internals "delegate_task": "execute", diff --git a/agent/display.py b/agent/display.py index 94259fa80..5eac70a4b 100644 --- a/agent/display.py +++ b/agent/display.py @@ -890,8 +890,6 @@ def get_cute_tool_message( return _wrap(f"┊ ◀️ back {dur}") if tool_name == "browser_press": return _wrap(f"┊ ⌨️ press {args.get('key', '?')} {dur}") - if tool_name == "browser_close": - return _wrap(f"┊ 🚪 close browser {dur}") if tool_name == "browser_get_images": return _wrap(f"┊ 🖼️ images extracting {dur}") if tool_name == "browser_vision": diff --git a/agent/prompt_builder.py b/agent/prompt_builder.py index 0a2cbe374..d6c296f61 100644 --- a/agent/prompt_builder.py +++ b/agent/prompt_builder.py @@ -744,7 +744,6 @@ def build_nous_subscription_prompt(valid_tool_names: "set[str] | None" = None) - "browser_type", "browser_scroll", "browser_console", - "browser_close", "browser_press", "browser_get_images", "browser_vision", diff --git a/cli-config.yaml.example b/cli-config.yaml.example index e26ee920e..73bff981f 100644 --- a/cli-config.yaml.example +++ b/cli-config.yaml.example @@ -539,7 +539,7 @@ platform_toolsets: # terminal - terminal, process # file - read_file, write_file, patch, search # browser - browser_navigate, browser_snapshot, browser_click, browser_type, -# browser_scroll, browser_back, browser_press, browser_close, +# browser_scroll, browser_back, browser_press, # browser_get_images, browser_vision (requires BROWSERBASE_API_KEY) # vision - vision_analyze (requires OPENROUTER_API_KEY) # image_gen - image_generate (requires FAL_KEY) diff --git a/model_tools.py b/model_tools.py index da5ba7154..c37007c41 100644 --- a/model_tools.py +++ b/model_tools.py @@ -211,7 +211,7 @@ _LEGACY_TOOLSET_MAP = { "browser_tools": [ "browser_navigate", "browser_snapshot", "browser_click", "browser_type", "browser_scroll", "browser_back", - "browser_press", "browser_close", "browser_get_images", + "browser_press", "browser_get_images", "browser_vision", "browser_console" ], "cronjob_tools": ["cronjob"], diff --git a/skills/dogfood/SKILL.md b/skills/dogfood/SKILL.md index 81a4ebfde..b7ba36639 100644 --- a/skills/dogfood/SKILL.md +++ b/skills/dogfood/SKILL.md @@ -16,7 +16,7 @@ This skill guides you through systematic exploratory QA testing of web applicati ## Prerequisites -- Browser toolset must be available (`browser_navigate`, `browser_snapshot`, `browser_click`, `browser_type`, `browser_vision`, `browser_console`, `browser_scroll`, `browser_back`, `browser_press`, `browser_close`) +- Browser toolset must be available (`browser_navigate`, `browser_snapshot`, `browser_click`, `browser_type`, `browser_vision`, `browser_console`, `browser_scroll`, `browser_back`, `browser_press`) - A target URL and testing scope from the user ## Inputs @@ -148,7 +148,6 @@ Save the report to `{output_dir}/report.md`. | `browser_press` | Press a keyboard key | | `browser_vision` | Screenshot + AI analysis; use `annotate=true` for element labels | | `browser_console` | Get JS console output and errors | -| `browser_close` | Close the browser session | ## Tips diff --git a/tests/gateway/test_api_server_toolset.py b/tests/gateway/test_api_server_toolset.py index 3b4ff254d..943d867e6 100644 --- a/tests/gateway/test_api_server_toolset.py +++ b/tests/gateway/test_api_server_toolset.py @@ -39,7 +39,7 @@ class TestHermesApiServerToolset: tools = resolve_toolset("hermes-api-server") for tool in ["browser_navigate", "browser_snapshot", "browser_click", "browser_type", "browser_scroll", "browser_back", - "browser_press", "browser_close"]: + "browser_press"]: assert tool in tools, f"Missing browser tool: {tool}" def test_toolset_includes_homeassistant_tools(self): diff --git a/tests/tools/test_browser_cleanup.py b/tests/tools/test_browser_cleanup.py index 9dfabe640..df21f3a0e 100644 --- a/tests/tools/test_browser_cleanup.py +++ b/tests/tools/test_browser_cleanup.py @@ -65,18 +65,6 @@ class TestBrowserCleanup: mock_stop.assert_called_once_with("task-1") mock_run.assert_called_once_with("task-1", "close", [], timeout=10) - def test_browser_close_delegates_to_cleanup_browser(self): - import json - - browser_tool = self.browser_tool - browser_tool._active_sessions["task-2"] = {"session_name": "sess-2"} - - with patch("tools.browser_tool.cleanup_browser") as mock_cleanup: - result = json.loads(browser_tool.browser_close("task-2")) - - assert result == {"success": True, "closed": True} - mock_cleanup.assert_called_once_with("task-2") - def test_emergency_cleanup_clears_all_tracking_state(self): browser_tool = self.browser_tool browser_tool._cleanup_done = False diff --git a/tools/browser_camofox.py b/tools/browser_camofox.py index c2278f83e..91f8fa4fd 100644 --- a/tools/browser_camofox.py +++ b/tools/browser_camofox.py @@ -240,6 +240,25 @@ def camofox_navigate(url: str, task_id: Optional[str] = None) -> str: "Browser is visible via VNC. " "Share this link with the user so they can watch the browser live." ) + + # Auto-take a compact snapshot so the model can act immediately + try: + snap_data = _get( + f"/tabs/{session['tab_id']}/snapshot", + params={"userId": session["user_id"]}, + ) + snapshot_text = snap_data.get("snapshot", "") + from tools.browser_tool import ( + SNAPSHOT_SUMMARIZE_THRESHOLD, + _truncate_snapshot, + ) + if len(snapshot_text) > SNAPSHOT_SUMMARIZE_THRESHOLD: + snapshot_text = _truncate_snapshot(snapshot_text) + result["snapshot"] = snapshot_text + result["element_count"] = snap_data.get("refsCount", 0) + except Exception: + pass # Navigation succeeded; snapshot is a bonus + return json.dumps(result) except requests.HTTPError as e: return json.dumps({"success": False, "error": f"Navigation failed: {e}"}) diff --git a/tools/browser_tool.py b/tools/browser_tool.py index a6043e0bf..ba2f81cf4 100644 --- a/tools/browser_tool.py +++ b/tools/browser_tool.py @@ -518,7 +518,7 @@ atexit.register(_stop_browser_cleanup_thread) BROWSER_TOOL_SCHEMAS = [ { "name": "browser_navigate", - "description": "Navigate to a URL in the browser. Initializes the session and loads the page. Must be called before other browser tools. For simple information retrieval, prefer web_search or web_extract (faster, cheaper). Use browser tools when you need to interact with a page (click, fill forms, dynamic content).", + "description": "Navigate to a URL in the browser. Initializes the session and loads the page. Must be called before other browser tools. For simple information retrieval, prefer web_search or web_extract (faster, cheaper). Use browser tools when you need to interact with a page (click, fill forms, dynamic content). Returns a compact page snapshot with interactive elements and ref IDs — no need to call browser_snapshot separately after navigating.", "parameters": { "type": "object", "properties": { @@ -532,7 +532,7 @@ BROWSER_TOOL_SCHEMAS = [ }, { "name": "browser_snapshot", - "description": "Get a text-based snapshot of the current page's accessibility tree. Returns interactive elements with ref IDs (like @e1, @e2) for browser_click and browser_type. full=false (default): compact view with interactive elements. full=true: complete page content. Snapshots over 8000 chars are truncated or LLM-summarized. Requires browser_navigate first.", + "description": "Get a text-based snapshot of the current page's accessibility tree. Returns interactive elements with ref IDs (like @e1, @e2) for browser_click and browser_type. full=false (default): compact view with interactive elements. full=true: complete page content. Snapshots over 8000 chars are truncated or LLM-summarized. Requires browser_navigate first. Note: browser_navigate already returns a compact snapshot — use this to refresh after interactions that change the page, or with full=true for complete content.", "parameters": { "type": "object", "properties": { @@ -615,15 +615,7 @@ BROWSER_TOOL_SCHEMAS = [ "required": ["key"] } }, - { - "name": "browser_close", - "description": "Close the browser session and release resources. Call this when done with browser tasks to free up Browserbase session quota.", - "parameters": { - "type": "object", - "properties": {}, - "required": [] - } - }, + { "name": "browser_get_images", "description": "Get a list of all images on the current page with their URLs and alt text. Useful for finding images to analyze with the vision tool. Requires browser_navigate to be called first.", @@ -1229,7 +1221,22 @@ def browser_navigate(url: str, task_id: Optional[str] = None) -> str: "Consider upgrading Browserbase plan for proxy support." ) response["stealth_features"] = active_features - + + # Auto-take a compact snapshot so the model can act immediately + # without a separate browser_snapshot call. + try: + snap_result = _run_browser_command(effective_task_id, "snapshot", ["-c"]) + if snap_result.get("success"): + snap_data = snap_result.get("data", {}) + snapshot_text = snap_data.get("snapshot", "") + refs = snap_data.get("refs", {}) + if len(snapshot_text) > SNAPSHOT_SUMMARIZE_THRESHOLD: + snapshot_text = _truncate_snapshot(snapshot_text) + response["snapshot"] = snapshot_text + response["element_count"] = len(refs) if refs else 0 + except Exception as e: + logger.debug("Auto-snapshot after navigate failed: %s", e) + return json.dumps(response, ensure_ascii=False) else: return json.dumps({ @@ -1376,31 +1383,40 @@ def browser_scroll(direction: str, task_id: Optional[str] = None) -> str: Returns: JSON string with scroll result """ - if _is_camofox_mode(): - from tools.browser_camofox import camofox_scroll - return camofox_scroll(direction, task_id) - - effective_task_id = task_id or "default" - # Validate direction if direction not in ["up", "down"]: return json.dumps({ "success": False, "error": f"Invalid direction '{direction}'. Use 'up' or 'down'." }, ensure_ascii=False) - - result = _run_browser_command(effective_task_id, "scroll", [direction]) - - if result.get("success"): - return json.dumps({ - "success": True, - "scrolled": direction - }, ensure_ascii=False) - else: - return json.dumps({ - "success": False, - "error": result.get("error", f"Failed to scroll {direction}") - }, ensure_ascii=False) + + # Repeat the scroll 5 times to get meaningful page movement. + # Most backends scroll ~100px per call, which is barely visible. + # 5x gives roughly half a viewport of travel, backend-agnostic. + _SCROLL_REPEATS = 5 + + if _is_camofox_mode(): + from tools.browser_camofox import camofox_scroll + result = None + for _ in range(_SCROLL_REPEATS): + result = camofox_scroll(direction, task_id) + return result + + effective_task_id = task_id or "default" + + result = None + for _ in range(_SCROLL_REPEATS): + result = _run_browser_command(effective_task_id, "scroll", [direction]) + if not result.get("success"): + return json.dumps({ + "success": False, + "error": result.get("error", f"Failed to scroll {direction}") + }, ensure_ascii=False) + + return json.dumps({ + "success": True, + "scrolled": direction + }, ensure_ascii=False) def browser_back(task_id: Optional[str] = None) -> str: @@ -1463,33 +1479,7 @@ def browser_press(key: str, task_id: Optional[str] = None) -> str: }, ensure_ascii=False) -def browser_close(task_id: Optional[str] = None) -> str: - """ - Close the browser session. - Args: - task_id: Task identifier for session isolation - - Returns: - JSON string with close result - """ - if _is_camofox_mode(): - from tools.browser_camofox import camofox_close - return camofox_close(task_id) - - effective_task_id = task_id or "default" - with _cleanup_lock: - had_session = effective_task_id in _active_sessions - - cleanup_browser(effective_task_id) - - response = { - "success": True, - "closed": True, - } - if not had_session: - response["warning"] = "Session may not have been active" - return json.dumps(response, ensure_ascii=False) def browser_console(clear: bool = False, expression: Optional[str] = None, task_id: Optional[str] = None) -> str: @@ -1942,7 +1932,7 @@ def cleanup_browser(task_id: Optional[str] = None) -> None: Clean up browser session for a task. Called automatically when a task completes or when inactivity timeout is reached. - Closes both the agent-browser session and the Browserbase session. + Closes both the agent-browser/Browserbase session and Camofox sessions. Args: task_id: Task identifier to clean up @@ -1950,6 +1940,14 @@ def cleanup_browser(task_id: Optional[str] = None) -> None: if task_id is None: task_id = "default" + # Also clean up Camofox session if running in Camofox mode + if _is_camofox_mode(): + try: + from tools.browser_camofox import camofox_close + camofox_close(task_id) + except Exception as e: + logger.debug("Camofox cleanup for task %s: %s", task_id, e) + logger.debug("cleanup_browser called for task_id: %s", task_id) logger.debug("Active sessions: %s", list(_active_sessions.keys())) @@ -2168,14 +2166,7 @@ registry.register( check_fn=check_browser_requirements, emoji="⌨️", ) -registry.register( - name="browser_close", - toolset="browser", - schema=_BROWSER_SCHEMA_MAP["browser_close"], - handler=lambda args, **kw: browser_close(task_id=kw.get("task_id")), - check_fn=check_browser_requirements, - emoji="🚪", -) + registry.register( name="browser_get_images", toolset="browser", diff --git a/tools/cronjob_tools.py b/tools/cronjob_tools.py index eb13240b1..8dbcf7c3a 100644 --- a/tools/cronjob_tools.py +++ b/tools/cronjob_tools.py @@ -103,6 +103,32 @@ def _canonical_skills(skill: Optional[str] = None, skills: Optional[Any] = None) + +def _resolve_model_override(model_obj: Optional[Dict[str, Any]]) -> tuple: + """Resolve a model override object into (provider, model) for job storage. + + If provider is omitted, pins the current main provider from config so the + job doesn't drift when the user later changes their default via hermes model. + + Returns (provider_str_or_none, model_str_or_none). + """ + if not model_obj or not isinstance(model_obj, dict): + return (None, None) + model_name = (model_obj.get("model") or "").strip() or None + provider_name = (model_obj.get("provider") or "").strip() or None + if model_name and not provider_name: + # Pin to the current main provider so the job is stable + try: + from hermes_cli.config import load_config + cfg = load_config() + model_cfg = cfg.get("model", {}) + if isinstance(model_cfg, dict): + provider_name = model_cfg.get("provider") or None + except Exception: + pass # Best-effort; provider stays None + return (provider_name, model_name) + + def _normalize_optional_job_value(value: Optional[Any], *, strip_trailing_slash: bool = False) -> Optional[str]: if value is None: return None @@ -392,14 +418,9 @@ Use action='list' to inspect jobs. Use action='update', 'pause', 'resume', 'remove', or 'run' to manage an existing job. Jobs run in a fresh session with no current-chat context, so prompts must be self-contained. -If skill or skills are provided on create, the future cron run loads those skills in order, then follows the prompt as the task instruction. +If skills are provided on create, the future cron run loads those skills in order, then follows the prompt as the task instruction. On update, passing skills=[] clears attached skills. -If script is provided on create, the referenced Python script runs before each agent turn. -Its stdout is injected into the prompt as context. Use this for data collection and change -detection — the script handles gathering data, the agent analyzes and reports. -On update, pass script="" to clear an attached script. - NOTE: The agent's final response is auto-delivered to the target. Put the primary user-facing content in the final response. Cron jobs run autonomously with no user present — they cannot ask questions or request clarification. @@ -418,7 +439,7 @@ Important safety rule: cron-run sessions should not recursively schedule more cr }, "prompt": { "type": "string", - "description": "For create: the full self-contained prompt. If skill or skills are also provided, this becomes the task instruction paired with those skills." + "description": "For create: the full self-contained prompt. If skills are also provided, this becomes the task instruction paired with those skills." }, "schedule": { "type": "string", @@ -436,39 +457,30 @@ Important safety rule: cron-run sessions should not recursively schedule more cr "type": "string", "description": "Delivery target: origin, local, telegram, discord, slack, whatsapp, signal, matrix, mattermost, homeassistant, dingtalk, feishu, wecom, email, sms, or platform:chat_id or platform:chat_id:thread_id for Telegram topics. Examples: 'origin', 'local', 'telegram', 'telegram:-1001234567890:17585', 'discord:#engineering'" }, - "model": { - "type": "string", - "description": "Optional per-job model override used when the cron job runs" - }, - "provider": { - "type": "string", - "description": "Optional per-job provider override used when resolving runtime credentials" - }, - "base_url": { - "type": "string", - "description": "Optional per-job base URL override paired with provider/model routing" - }, - "include_disabled": { - "type": "boolean", - "description": "For list: include paused/completed jobs" - }, - "skill": { - "type": "string", - "description": "Optional single skill name to load before executing the cron prompt" - }, "skills": { "type": "array", "items": {"type": "string"}, - "description": "Optional ordered list of skills to load before executing the cron prompt. On update, pass an empty array to clear attached skills." + "description": "Optional ordered list of skill names to load before executing the cron prompt. On update, pass an empty array to clear attached skills." }, - "reason": { - "type": "string", - "description": "Optional pause reason" + "model": { + "type": "object", + "description": "Optional per-job model override. If provider is omitted, the current main provider is pinned at creation time so the job stays stable.", + "properties": { + "provider": { + "type": "string", + "description": "Provider name (e.g. 'openrouter', 'anthropic'). Omit to use and pin the current provider." + }, + "model": { + "type": "string", + "description": "Model name (e.g. 'anthropic/claude-sonnet-4', 'claude-sonnet-4')" + } + }, + "required": ["model"] }, "script": { "type": "string", "description": "Optional path to a Python script that runs before each cron job execution. Its stdout is injected into the prompt as context. Use for data collection and change detection. Relative paths resolve under ~/.hermes/scripts/. On update, pass empty string to clear." - } + }, }, "required": ["action"] } @@ -502,7 +514,7 @@ registry.register( name="cronjob", toolset="cronjob", schema=CRONJOB_SCHEMA, - handler=lambda args, **kw: cronjob( + handler=lambda args, **kw: (lambda _mo=_resolve_model_override(args.get("model")): cronjob( action=args.get("action", ""), job_id=args.get("job_id"), prompt=args.get("prompt"), @@ -510,16 +522,16 @@ registry.register( name=args.get("name"), repeat=args.get("repeat"), deliver=args.get("deliver"), - include_disabled=args.get("include_disabled", False), + include_disabled=args.get("include_disabled", True), skill=args.get("skill"), skills=args.get("skills"), - model=args.get("model"), - provider=args.get("provider"), + model=_mo[1], + provider=_mo[0] or args.get("provider"), base_url=args.get("base_url"), reason=args.get("reason"), script=args.get("script"), task_id=kw.get("task_id"), - ), + ))(), check_fn=check_cronjob_requirements, emoji="⏰", ) diff --git a/toolsets.py b/toolsets.py index 84c19637f..04e43b286 100644 --- a/toolsets.py +++ b/toolsets.py @@ -37,14 +37,12 @@ _HERMES_CORE_TOOLS = [ "read_file", "write_file", "patch", "search_files", # Vision + image generation "vision_analyze", "image_generate", - # MoA - "mixture_of_agents", # Skills "skills_list", "skill_view", "skill_manage", # Browser automation "browser_navigate", "browser_snapshot", "browser_click", "browser_type", "browser_scroll", "browser_back", - "browser_press", "browser_close", "browser_get_images", + "browser_press", "browser_get_images", "browser_vision", "browser_console", # Text-to-speech "text_to_speech", @@ -116,7 +114,7 @@ TOOLSETS = { "tools": [ "browser_navigate", "browser_snapshot", "browser_click", "browser_type", "browser_scroll", "browser_back", - "browser_press", "browser_close", "browser_get_images", + "browser_press", "browser_get_images", "browser_vision", "browser_console", "web_search" ], "includes": [] @@ -214,7 +212,7 @@ TOOLSETS = { "safe": { "description": "Safe toolkit without terminal access", - "tools": ["mixture_of_agents"], + "tools": [], "includes": ["web", "vision", "image_gen"] }, @@ -235,7 +233,7 @@ TOOLSETS = { "skills_list", "skill_view", "skill_manage", "browser_navigate", "browser_snapshot", "browser_click", "browser_type", "browser_scroll", "browser_back", - "browser_press", "browser_close", "browser_get_images", + "browser_press", "browser_get_images", "browser_vision", "browser_console", "todo", "memory", "session_search", @@ -255,14 +253,12 @@ TOOLSETS = { "read_file", "write_file", "patch", "search_files", # Vision + image generation "vision_analyze", "image_generate", - # MoA - "mixture_of_agents", # Skills "skills_list", "skill_view", "skill_manage", # Browser automation "browser_navigate", "browser_snapshot", "browser_click", "browser_type", "browser_scroll", "browser_back", - "browser_press", "browser_close", "browser_get_images", + "browser_press", "browser_get_images", "browser_vision", "browser_console", # Planning & memory "todo", "memory", diff --git a/website/docs/reference/tools-reference.md b/website/docs/reference/tools-reference.md index 5353ca5ff..cd798697d 100644 --- a/website/docs/reference/tools-reference.md +++ b/website/docs/reference/tools-reference.md @@ -20,7 +20,6 @@ In addition to built-in tools, Hermes can load tools dynamically from MCP server |------|-------------|----------------------| | `browser_back` | Navigate back to the previous page in browser history. Requires browser_navigate to be called first. | — | | `browser_click` | Click on an element identified by its ref ID from the snapshot (e.g., '@e5'). The ref IDs are shown in square brackets in the snapshot output. Requires browser_navigate and browser_snapshot to be called first. | — | -| `browser_close` | Close the browser session and release resources. Call this when done with browser tasks to free up Browserbase session quota. | — | | `browser_console` | Get browser console output and JavaScript errors from the current page. Returns console.log/warn/error/info messages and uncaught JS exceptions. Use this to detect silent JavaScript errors, failed API calls, and application warnings. Requi… | — | | `browser_get_images` | Get a list of all images on the current page with their URLs and alt text. Useful for finding images to analyze with the vision tool. Requires browser_navigate to be called first. | — | | `browser_navigate` | Navigate to a URL in the browser. Initializes the session and loads the page. Must be called before other browser tools. For simple information retrieval, prefer web_search or web_extract (faster, cheaper). Use browser tools when you need… | — | diff --git a/website/docs/reference/toolsets-reference.md b/website/docs/reference/toolsets-reference.md index 19ff00a3f..7d566e602 100644 --- a/website/docs/reference/toolsets-reference.md +++ b/website/docs/reference/toolsets-reference.md @@ -52,7 +52,7 @@ Or in-session: | Toolset | Tools | Purpose | |---------|-------|---------| -| `browser` | `browser_back`, `browser_click`, `browser_close`, `browser_console`, `browser_get_images`, `browser_navigate`, `browser_press`, `browser_scroll`, `browser_snapshot`, `browser_type`, `browser_vision`, `web_search` | Full browser automation. Includes `web_search` as a fallback for quick lookups. | +| `browser` | `browser_back`, `browser_click`, `browser_console`, `browser_get_images`, `browser_navigate`, `browser_press`, `browser_scroll`, `browser_snapshot`, `browser_type`, `browser_vision`, `web_search` | Full browser automation. Includes `web_search` as a fallback for quick lookups. | | `clarify` | `clarify` | Ask the user a question when the agent needs clarification. | | `code_execution` | `execute_code` | Run Python scripts that call Hermes tools programmatically. | | `cronjob` | `cronjob` | Schedule and manage recurring tasks. | diff --git a/website/docs/user-guide/features/browser.md b/website/docs/user-guide/features/browser.md index 8f9fc24eb..0dafec10b 100644 --- a/website/docs/user-guide/features/browser.md +++ b/website/docs/user-guide/features/browser.md @@ -277,10 +277,6 @@ Check the browser console for any JavaScript errors Use `clear=True` to clear the console after reading, so subsequent calls only show new messages. -### `browser_close` - -Close the browser session and release resources. Call this when done to free up Browserbase session quota. - ## Practical Examples ### Filling Out a Web Form @@ -295,7 +291,6 @@ Agent workflow: 4. browser_type(ref="@e5", text="SecurePass123") 5. browser_click(ref="@e8") → clicks "Create Account" 6. browser_snapshot() → confirms success -7. browser_close() ``` ### Researching Dynamic Content @@ -307,7 +302,6 @@ Agent workflow: 1. browser_navigate("https://github.com/trending") 2. browser_snapshot(full=true) → reads trending repo list 3. Returns formatted results -4. browser_close() ``` ## Session Recording @@ -349,5 +343,5 @@ If paid features aren't available on your plan, Hermes automatically falls back - **Text-based interaction** — relies on accessibility tree, not pixel coordinates - **Snapshot size** — large pages may be truncated or LLM-summarized at 8000 characters - **Session timeout** — cloud sessions expire based on your provider's plan settings -- **Cost** — cloud sessions consume provider credits; use `browser_close` when done. Use `/browser connect` for free local browsing. +- **Cost** — cloud sessions consume provider credits; sessions are automatically cleaned up when the conversation ends or after inactivity. Use `/browser connect` for free local browsing. - **No file downloads** — cannot download files from the browser