stagent 0.6.3 → 0.8.0

package/docs/journeys/developer.md

@@ -4,9 +4,9 @@ category: "user-journey"
 persona: "developer"
 difficulty: "advanced"
 estimatedTime: "30 minutes"
-sections: ["settings", "environment", "chat", "monitoring", "profiles", "workflows", "schedules", "delivery-channels"]
-tags: ["advanced", "developer", "settings", "environment", "cli", "api", "monitoring", "profiles", "ollama", "channels", "handoffs", "memory"]
-lastUpdated: "2026-03-31"
+sections: ["settings", "environment", "chat", "monitoring", "profiles", "workflows", "tables", "schedules", "delivery-channels"]
+tags: ["advanced", "developer", "settings", "environment", "cli", "api", "monitoring", "profiles", "ollama", "channels", "handoffs", "memory", "tables"]
+lastUpdated: "2026-04-03"
 ---
 
 # Developer Guide
@@ -41,7 +41,7 @@ Riley starts at the Settings page. The first priority is getting authentication
 
 Riley sets up Ollama as the fifth runtime adapter for private, zero-cost execution.
 
-![Ollama section with local models listed](../screengrabs/settings-ollama-connected.png)
+![Settings Providers and Runtimes section with authentication and runtime config](../screengrabs/settings-auth.png)
 
 1. Install Ollama from [ollama.com](https://ollama.com) and pull models: `ollama pull llama3 && ollama pull qwen3`
 2. Scroll to the **Ollama** section in Settings
@@ -55,21 +55,15 @@ Riley sets up Ollama as the fifth runtime adapter for private, zero-cost executi
 
 Riley sets up Slack and Telegram as delivery channels for schedule notifications and bidirectional chat.
 
-![Delivery channels with Slack configuration form](../screengrabs/settings-channels-add-form.png)
+![Settings data management section](../screengrabs/settings-data.png)
 
 1. Scroll to **Delivery Channels** in Settings
 2. Click **+ Add Channel** and select **Slack**
 3. Enter the webhook URL, bot token (xoxb-), signing secret, and channel ID
 4. Click **Create Channel** then **Test** to verify delivery
 5. Toggle **Chat** on for bidirectional mode
-
-![Telegram channel configuration](../screengrabs/settings-channels-telegram-form.png)
-
 6. Add a second channel for **Telegram** with bot token and chat ID
 7. Test and enable Chat mode
-
-![Webhook channel configuration](../screengrabs/settings-channels-webhook-form.png)
-
 8. Add a **Webhook** channel for custom integrations (outbound only)
 
 > **Tip:** The channel gateway architecture is straightforward: for local development, Stagent includes a built-in poller that checks Slack (`conversations.history` API) and Telegram (`getUpdates` API) every 5 seconds. No public URL or webhook registration needed. The poller only polls channels with both Chat and Active toggles on. Channel conversations flow through the same chat engine as web conversations, including tool access and permission handling.
@@ -122,7 +116,7 @@ Riley switches to the Environment page to understand the control plane.
 
 Riley traces the request lifecycle from input to streamed response across both web and channel interfaces.
 
-![Active chat conversation with streamed response](../screengrabs/chat-conversation.png)
+![Chat interface with conversation thread and streamed response](../screengrabs/chat-detail.png)
 
 1. Open **Chat** and start a conversation
 2. Trace the API flow: `POST /api/chat` (SSE stream), `GET/POST/DELETE /api/chat/conversations`, `GET /api/models`
@@ -172,9 +166,25 @@ Riley reviews the episodic memory system that gives agents persistent knowledge.
 3. Review total duration and aggregate token usage
 4. Note handoff steps where one agent delegated to another mid-workflow
 
-### Step 12: Review Schedule Configuration
+### Step 12: Explore the Tables API and Agent Tools
+
+Riley reviews the tables subsystem -- 12 agent tools that let AI agents create, query, and mutate structured data via chat or task execution.
+
+1. Review the tables API routes:
+   - `GET/POST /api/tables` -- list and create tables
+   - `GET/PATCH/DELETE /api/tables/[id]` -- single table CRUD
+   - `GET/POST /api/tables/[id]/charts` -- chart management per table
+   - `GET/POST /api/tables/[id]/triggers` -- workflow triggers attached to table events
+2. Inspect the 12 agent tools registered for tables: `create_table`, `list_tables`, `get_table`, `update_table`, `delete_table`, `add_row`, `update_row`, `delete_row`, `query_table`, `add_column`, `create_chart`, `create_trigger`
+3. Test from Chat: ask "Create a table called Deploy Log with columns: service, version, status, deployed_at" and verify the agent calls the `create_table` tool
+4. Verify that table mutations from agent tools appear in the web UI in real time
+5. Check that workflow triggers fire correctly when an agent adds or updates a row via tool call
+
+> **Tip:** The tables agent tools enable a powerful pattern: agents can build and populate structured datasets during task execution, then other agents or workflows can query those tables for downstream decisions. This turns tables into a shared knowledge layer between agents.
+
+### Step 13: Review Schedule Configuration
 
-![Schedule detail sheet showing configuration and firing history](../screengrabs/schedules-detail.png)
+![Schedules list showing active and configured schedules](../screengrabs/schedules-list.png)
 
 1. Select a schedule to open its detail sheet
 2. Review configuration: prompt, interval, heartbeat checklist, delivery channels
@@ -183,7 +193,7 @@ Riley reviews the episodic memory system that gives agents persistent knowledge.
 
 > **Tip:** The scheduler engine runs via the Next.js `instrumentation.ts` register hook. The interval parser supports both natural language and standard cron expressions.
 
-### Step 13: Build and Test the CLI
+### Step 14: Build and Test the CLI
 
 Riley builds the CLI for scripted operations and CI/CD integration.
 
@@ -194,7 +204,7 @@ Riley builds the CLI for scripted operations and CI/CD integration.
 3. Test CRUD operations: `node dist/cli.js projects list`, `node dist/cli.js tasks create --title "CLI test"`
 4. Verify CLI-created entities appear in the web UI (shared SQLite database)
 
-### Step 14: Verify Platform Health
+### Step 15: Verify Platform Health
 
 Riley performs a final platform health check.
 

package/docs/journeys/personal-use.md

@@ -4,9 +4,9 @@ category: "user-journey"
 persona: "personal"
 difficulty: "beginner"
 estimatedTime: "30 minutes"
-sections: ["home-workspace", "dashboard-kanban", "projects", "chat", "schedules", "user-guide"]
-tags: ["beginner", "solo", "tasks", "kanban", "chat", "schedules", "delivery-channels"]
-lastUpdated: "2026-03-31"
+sections: ["home-workspace", "dashboard-kanban", "projects", "chat", "tables", "schedules", "user-guide"]
+tags: ["beginner", "solo", "tasks", "kanban", "chat", "tables", "schedules", "delivery-channels"]
+lastUpdated: "2026-04-03"
 ---
 
 # Personal Use Guide
@@ -141,14 +141,28 @@ Alex uses the quick-edit dialog for a fast priority change.
 
 Alex clicks on a task card to open the full detail sheet.
 
-![Task detail sheet showing full task information](../screengrabs/dashboard-card-detail.png)
+![Task edit dialog opened from a kanban card](../screengrabs/dashboard-card-edit.png)
 
 1. Click on any **task card** in the kanban board (not the edit icon -- the card itself)
 2. The **detail sheet** slides in from the right side of the screen
 3. Review the full **Description**, **Priority**, **Status**, **Project** assignment, and timestamps
 4. Press **Escape** or click outside the sheet to close it
 
-### Step 11: Set Up a Heartbeat Schedule
+### Step 11: Track Content in a Table
+
+Alex wants to keep a structured list of portfolio pages, their status, and target launch dates. A table is perfect for this kind of lightweight tracking.
+
+![Tables list view showing structured data tables](../screengrabs/tables-list.png)
+
+1. Click **Tables** in the sidebar under the **Work** group
+2. Click **Create Table** and enter a name: "Portfolio Pages"
+3. Add columns: **Page Name** (text), **Status** (select: Draft / In Progress / Done), **Target Date** (date)
+4. Start adding rows directly in the inline spreadsheet editor -- type into cells just like a regular spreadsheet
+5. Use the table to track which pages are done and which still need work
+
+> **Tip:** Tables are great for any structured tracking that does not need a full project board. Content calendars, feature lists, contact directories -- anything you would put in a spreadsheet fits naturally here.
+
+### Step 12: Set Up a Heartbeat Schedule
 
 Alex wants Stagent to proactively check on the portfolio project every morning. A heartbeat schedule evaluates conditions before deciding whether to act -- it only creates tasks when something meaningful needs attention.
 
@@ -163,11 +177,11 @@ Alex wants Stagent to proactively check on the portfolio project every morning.
 
 > **Tip:** Heartbeat schedules are smarter than clock-driven ones -- they suppress no-op runs. If your portfolio project has no stale tasks, the heartbeat stays quiet and costs nothing.
 
-### Step 12: Connect Telegram for Notifications
+### Step 13: Connect Telegram for Notifications
 
 Alex wants to receive schedule results on the go. Setting up a Telegram delivery channel takes less than two minutes.
 
-![Settings delivery channels section](../screengrabs/settings-channels.png)
+![Settings page showing provider and runtime configuration](../screengrabs/settings-auth.png)
 
 1. Open **Settings** from the sidebar under **Configure**
 2. Scroll to the **Delivery Channels** section
@@ -180,7 +194,7 @@ Alex wants to receive schedule results on the go. Setting up a Telegram delivery
 
 > **Tip:** With Chat mode enabled, you can ask Stagent questions directly from Telegram. "What's the status of my portfolio project?" works just like the web chat.
 
-### Step 13: Browse the User Guide
+### Step 14: Browse the User Guide
 
 Alex discovers the built-in documentation hub.
 
@@ -191,7 +205,7 @@ Alex discovers the built-in documentation hub.
 3. Check the **guided journeys** for your current skill level
 4. Use the feature grid to discover areas you have not tried yet
 
-### Step 14: What's Next
+### Step 15: What's Next
 
 Alex now has a solid foundation: a project, organized tasks on a kanban board, a heartbeat schedule for proactive monitoring, and Telegram notifications for staying connected on the go. Here is where to go from here:
 

package/docs/journeys/power-user.md

@@ -4,9 +4,9 @@ category: "user-journey"
 persona: "power-user"
 difficulty: "advanced"
 estimatedTime: "30 minutes"
-sections: ["dashboard-kanban", "profiles", "chat", "workflows", "schedules", "monitoring", "settings"]
-tags: ["advanced", "automation", "workflows", "profiles", "schedules", "monitoring", "bulk-operations", "ollama", "episodic-memory", "nlp-scheduling"]
-lastUpdated: "2026-03-31"
+sections: ["dashboard-kanban", "profiles", "chat", "workflows", "tables", "schedules", "monitoring", "settings"]
+tags: ["advanced", "automation", "workflows", "profiles", "tables", "schedules", "monitoring", "bulk-operations", "ollama", "episodic-memory", "nlp-scheduling"]
+lastUpdated: "2026-04-03"
 ---
 
 # Power User Guide
@@ -63,7 +63,7 @@ Before building any automation, Sam reviews the available agent profiles. The ca
 
 Sam wants to run privacy-sensitive tasks on local models with zero API cost.
 
-![Ollama connected with local models](../screengrabs/settings-ollama-connected.png)
+![Settings Providers and Runtimes section with runtime configuration](../screengrabs/settings-auth.png)
 
 1. Install Ollama from [ollama.com](https://ollama.com) and pull a model: `ollama pull llama3`
 2. Open **Settings** and scroll to the **Ollama** section
@@ -74,7 +74,7 @@ Sam wants to run privacy-sensitive tasks on local models with zero API cost.
 
 ### Step 5: Optimize Chat with Model Selection
 
-![Chat model selector dropdown showing available models with cost tier indicators](../screengrabs/chat-model-selector.png)
+![Chat interface showing model selection and conversation controls](../screengrabs/chat-list.png)
 
 1. Navigate to **Chat** and click the **model selector** in the input area
 2. Review models with cost tier indicators ($ to $$$)
@@ -120,7 +120,33 @@ Sam customizes a workflow for a "Deploy & Verify" pipeline with specialized prof
 4. Click completed steps to read their full output
 5. Use the **Run Workflow** button to trigger a new execution
 
-### Step 9: Batch-Manage Tasks on the Kanban
+### Step 9: Add Formula Columns and Charts to Tables
+
+Sam tracks deployment metrics in a table and wants computed columns and visual dashboards without leaving Stagent.
+
+![Tables detail view with charts tab showing data visualizations](../screengrabs/tables-detail-charts.png)
+
+1. Open a table from the **Tables** page
+2. Click **Add Column** and select **Formula** as the column type
+3. Write a formula referencing other columns (e.g., `duration_hours / deploy_count` for average deploy time)
+4. Switch to the **Charts** tab to add visualizations -- bar, line, or pie charts built from the table data
+5. Configure chart axes and filters to highlight the metrics that matter
+
+> **Tip:** Formula columns recalculate automatically when source data changes. Combined with workflow triggers, a table can fire a workflow step whenever a metric crosses a threshold -- for example, triggering a rollback review when error rate exceeds 5%.
+
+### Step 10: Attach Workflow Triggers to Table Events
+
+Sam connects a table to the workflow engine so that row changes automatically kick off automation.
+
+1. Open a table and navigate to the **Triggers** tab
+2. Click **Add Trigger** and select the event type: row created, row updated, or column value changed
+3. Map the trigger to an existing workflow
+4. Configure field mappings so the workflow receives the changed row data as context
+5. Save the trigger -- new rows or edits now fire the connected workflow automatically
+
+> **Tip:** Table triggers turn spreadsheets into event-driven automation surfaces. Sam uses them to auto-run incident postmortems whenever an incident row status changes to "Resolved."
+
+### Step 11: Batch-Manage Tasks on the Kanban
 
 Sam cleans up the task board using bulk select mode.
 
@@ -134,9 +160,9 @@ Sam cleans up the task board using bulk select mode.
 
 > **Tip:** After a weekend of autonomous heartbeat runs, Sam's first Monday task is always a bulk cleanup.
 
-### Step 10: Schedule Automated Prompt Loops
+### Step 12: Schedule Automated Prompt Loops
 
-![Schedule detail sheet showing configuration and firing history](../screengrabs/schedules-detail.png)
+![Schedules list showing active schedules and firing status](../screengrabs/schedules-list.png)
 
 1. Click on a schedule to open its detail sheet
 2. Review the **firing history** with timestamps and outcomes (including suppressed heartbeat runs)
@@ -144,7 +170,7 @@ Sam cleans up the task board using bulk select mode.
 4. Verify stop conditions and delivery channels
 5. Toggle **Pause/Resume** as needed
 
-### Step 11: Leverage Episodic Memory
+### Step 13: Leverage Episodic Memory
 
 Sam notices agents are re-researching the same topics. Episodic memory lets agents retain factual knowledge across executions.
 
@@ -158,7 +184,7 @@ Sam notices agents are re-researching the same topics. Episodic memory lets agen
 
 > **Tip:** Episodic memory means a Financial Analyst profile that researches a company once can recall that research in future tasks without re-doing the work. It builds institutional knowledge automatically.
 
-### Step 12: Watch Agent Execution in Real-Time
+### Step 14: Watch Agent Execution in Real-Time
 
 ![Agent monitoring dashboard showing real-time execution logs](../screengrabs/monitor-list.png)
 
@@ -170,16 +196,16 @@ Sam notices agents are re-researching the same topics. Episodic memory lets agen
 
 > **Tip:** The Monitor is Sam's operational dashboard. When something goes wrong in an autonomous loop at 3am, the execution traces are the fastest path to diagnosis.
 
-### Step 13: Use Chat Suggested Prompts
+### Step 15: Use Chat Suggested Prompts
 
-![Chat suggested prompts with Create tab selected](../screengrabs/chat-create-tab.png)
+![Chat interface with suggested prompt categories](../screengrabs/chat-list.png)
 
 1. Navigate to **Chat** and notice the **suggested prompt tabs** (Explore, Create, Debug, Automate)
 2. Click the **Create** tab to see prompts for creating tasks, workflows, and schedules
 3. Click a suggested prompt to populate the input
 4. Edit and send -- these prompts are optimized for the best agent responses
 
-### Step 14: Chain Everything Together
+### Step 16: Chain Everything Together
 
 Sam connects the dots: profiles define *how*, workflows define *what*, schedules define *when*, Ollama handles the *cheap stuff*, episodic memory provides the *knowledge*, and delivery channels deliver the *results*.
 
@@ -195,7 +221,7 @@ Sam connects the dots: profiles define *how*, workflows define *what*, schedules
 
 > **Tip:** Sam's automation philosophy: start small, observe, then expand. Run a workflow manually three times before scheduling it. Trust builds incrementally -- and so should autonomy.
 
-### Step 15: What's Next
+### Step 17: What's Next
 
 Sam's workspace is a fully autonomous operations engine. The next step is going deeper into the platform layer.
 

package/docs/journeys/work-use.md

@@ -4,9 +4,9 @@ category: "user-journey"
 persona: "work"
 difficulty: "intermediate"
 estimatedTime: "30 minutes"
-sections: ["projects", "chat", "documents", "workflows", "schedules", "cost-usage", "inbox-notifications", "delivery-channels"]
-tags: ["intermediate", "team", "documents", "workflows", "schedules", "costs", "inbox", "channels", "handoffs"]
-lastUpdated: "2026-03-31"
+sections: ["projects", "chat", "documents", "tables", "workflows", "schedules", "cost-usage", "inbox-notifications", "delivery-channels"]
+tags: ["intermediate", "team", "documents", "tables", "workflows", "schedules", "costs", "inbox", "channels", "handoffs"]
+lastUpdated: "2026-04-03"
 ---
 
 # Work Use Guide
@@ -50,7 +50,7 @@ Jordan clicks into a project to check on task progress.
 
 Rather than clicking through every page, Jordan asks Chat for a quick status update.
 
-![Active chat conversation with messages and Quick Access navigation pills](../screengrabs/chat-conversation.png)
+![Chat interface with conversation thread and Quick Access navigation](../screengrabs/chat-detail.png)
 
 1. Click **Chat** in the sidebar
 2. Type a question such as "What is the status of the Q2 planning project?"
@@ -82,7 +82,35 @@ Jordan switches to grid view for a visual overview.
 2. Browse document cards with file name, type icon, and project association
 3. Toggle back to **table view** when you need to sort or filter
 
-### Step 6: Browse Workflow Blueprints
+### Step 6: Create a Table from a Template
+
+Jordan needs a structured tracker for the team's quarterly OKRs. Instead of building one from scratch, the template gallery has a ready-made option.
+
+![Template gallery showing pre-built table templates](../screengrabs/tables-templates.png)
+
+1. Click **Tables** in the sidebar under the **Work** group
+2. Click **Create Table** and browse the **Template Gallery**
+3. Select a template that fits the use case (e.g., "OKR Tracker" or "Sprint Board")
+4. Review the pre-configured columns and customize as needed
+5. Click **Create** to generate the table with the template structure
+
+> **Tip:** Templates include pre-set column types and formulas. They save setup time and ensure the team starts with a proven structure.
+
+### Step 7: Import Document Data into a Table
+
+Jordan has a CSV export from the previous quarter's performance review. Importing it into a table takes seconds.
+
+![Create table dialog with fields filled in](../screengrabs/tables-create-form-filled.png)
+
+1. From the **Tables** page, click **Create Table**
+2. Choose **Import** and select the CSV or XLSX file
+3. Review the column mapping -- Stagent auto-detects column types from the data
+4. Assign the table to the relevant project
+5. Click **Create** to import the data into a fully editable spreadsheet view
+
+> **Tip:** Imported tables retain all their data as editable rows. You can add formula columns, charts, and workflow triggers on top of imported data.
+
+### Step 8: Browse Workflow Blueprints
 
 Jordan wants to set up a structured review process. The blueprint gallery now includes business-function templates alongside technical ones.
 
@@ -95,7 +123,7 @@ Jordan wants to set up a structured review process. The blueprint gallery now in
 
 > **Tip:** Business-function blueprints pair naturally with the corresponding business profiles (Marketing Strategist, Sales Researcher, Financial Analyst, etc.).
 
-### Step 7: Review Active Workflows
+### Step 9: Review Active Workflows
 
 ![Workflows list with tabs showing status and step progress](../screengrabs/workflows-list.png)
 
@@ -104,7 +132,7 @@ Jordan wants to set up a structured review process. The blueprint gallery now in
 3. Click on a running workflow for step-by-step details
 4. Check for steps in a "waiting" state that may need approval
 
-### Step 8: Schedule with Natural Language
+### Step 10: Schedule with Natural Language
 
 Jordan schedules a weekly status summary using plain English instead of cron syntax.
 
@@ -120,7 +148,7 @@ Jordan schedules a weekly status summary using plain English instead of cron syn
 
 > **Tip:** The interval parser understands plain English. You do not need to write cron expressions.
 
-### Step 9: Monitor Spending and Budgets
+### Step 11: Monitor Spending and Budgets
 
 ![Cost and Usage dashboard showing spend metrics and budget gauges](../screengrabs/cost-usage-list.png)
 
@@ -129,7 +157,7 @@ Jordan schedules a weekly status summary using plain English instead of cron syn
 3. Check the **budget gauge** for spend cap proximity
 4. Examine per-project and per-model breakdowns
 
-### Step 10: Analyze Cost Breakdown
+### Step 12: Analyze Cost Breakdown
 
 ![Cost and Usage page scrolled to show detailed usage breakdown table](../screengrabs/cost-usage-below-fold.png)
 
@@ -139,7 +167,7 @@ Jordan schedules a weekly status summary using plain English instead of cron syn
 
 > **Tip:** The breakdown table is your audit trail. Trace every dollar back to a specific task.
 
-### Step 11: Review Agent Notifications and Handoffs
+### Step 13: Review Agent Notifications and Handoffs
 
 Jordan's agents have been running in the background. Some have generated handoff requests where one agent wants to delegate work to another.
 
@@ -152,7 +180,7 @@ Jordan's agents have been running in the background. Some have generated handoff
 
 > **Tip:** Agent handoffs are governed -- chain depth limits prevent infinite loops, and self-handoffs are blocked automatically.
 
-### Step 12: Inspect Notification Details
+### Step 14: Inspect Notification Details
 
 ![Inbox with expanded notification showing full content and approval options](../screengrabs/inbox-expanded.png)
 
@@ -161,11 +189,11 @@ Jordan's agents have been running in the background. Some have generated handoff
 3. Choose **Approve**, **Deny**, or **Always Allow**
 4. For handoffs, approve to let the receiving agent begin work
 
-### Step 13: Configure Multi-Channel Notifications
+### Step 15: Configure Multi-Channel Notifications
 
 Jordan sets up Slack so the entire team receives schedule results and important alerts.
 
-![Settings delivery channels with configured channels](../screengrabs/settings-channels.png)
+![Settings page showing provider and runtime configuration](../screengrabs/settings-auth.png)
 
 1. Open **Settings** and scroll to **Delivery Channels**
 2. Click **+ Add Channel** and select **Slack**
@@ -175,7 +203,7 @@ Jordan sets up Slack so the entire team receives schedule results and important
 
 > **Tip:** With Chat enabled on Slack, anyone in the channel can message Stagent and get workspace-aware responses. This turns Slack into a team-wide AI assistant interface.
 
-### Step 14: Manage Schedules
+### Step 16: Manage Schedules
 
 ![Schedules list with status indicators and next run timestamps](../screengrabs/schedules-list.png)
 
@@ -185,7 +213,7 @@ Jordan sets up Slack so the entire team receives schedule results and important
 4. Click to review firing history and generated tasks
 5. Edit or pause as needed
 
-### Step 15: What's Next
+### Step 17: What's Next
 
 Jordan's working session covered team projects, documents, business-function workflows, natural language scheduling, multi-channel notifications, agent handoff approvals, and cost governance. To go deeper:
 

package/docs/manifest.json

@@ -1,6 +1,6 @@
 {
-  "generated": "2026-03-31T21:00:00Z",
-  "version": 2,
+  "generated": "2026-04-03T22:00:00Z",
+  "version": 3,
   "sections": [
     {
       "slug": "home-workspace",
@@ -72,6 +72,16 @@
       "features": ["document-manager", "file-attachment-data-layer", "document-preprocessing", "agent-document-context", "document-output-generation"],
       "screengrabCount": 2
     },
+    {
+      "slug": "tables",
+      "title": "Tables",
+      "category": "feature-reference",
+      "path": "features/tables.md",
+      "route": "/tables",
+      "tags": ["tables", "structured-data", "spreadsheet", "charts", "triggers", "templates", "import", "export", "formulas"],
+      "features": ["tables-data-layer", "tables-list-page", "tables-spreadsheet-editor", "tables-document-import", "tables-template-gallery", "tables-agent-integration", "tables-chat-queries", "tables-computed-columns", "tables-cross-joins", "tables-agent-charts", "tables-workflow-triggers", "tables-nl-creation", "tables-export", "tables-versioning"],
+      "screengrabCount": 8
+    },
     {
       "slug": "monitoring",
       "title": "Monitor",
@@ -118,8 +128,8 @@
       "category": "feature-reference",
       "path": "features/settings.md",
       "route": "/settings",
-      "tags": ["settings", "authentication", "permissions", "presets", "budgets", "browser-tools", "ollama", "channels"],
-      "features": ["session-management", "tool-permission-persistence", "tool-permission-presets", "browser-use", "spend-budget-guardrails", "ollama-runtime-provider", "multi-channel-delivery", "bidirectional-channel-chat"],
+      "tags": ["settings", "authentication", "permissions", "presets", "budgets", "browser-tools", "ollama", "channels", "snapshots"],
+      "features": ["session-management", "tool-permission-persistence", "tool-permission-presets", "browser-use", "spend-budget-guardrails", "ollama-runtime-provider", "multi-channel-delivery", "bidirectional-channel-chat", "database-snapshot-backup"],
       "screengrabCount": 9
     },
     {
@@ -136,7 +146,7 @@
       "slug": "playbook",
       "title": "User Guide",
       "category": "feature-reference",
-      "path": "features/playbook.md",
+      "path": "features/user-guide.md",
       "route": "/user-guide",
       "tags": ["user-guide", "documentation", "adoption-tracking"],
       "features": ["playbook-documentation", "documentation-adoption-tracking"],
@@ -232,8 +242,8 @@
       "persona": "personal",
       "difficulty": "beginner",
       "path": "journeys/personal-use.md",
-      "sections": ["home-workspace", "chat", "dashboard-kanban", "projects", "schedules", "delivery-channels", "user-guide"],
-      "stepCount": 14
+      "sections": ["home-workspace", "chat", "dashboard-kanban", "projects", "tables", "schedules", "delivery-channels", "user-guide"],
+      "stepCount": 15
     },
     {
       "slug": "work-use",
@@ -241,8 +251,8 @@
       "persona": "work",
       "difficulty": "intermediate",
       "path": "journeys/work-use.md",
-      "sections": ["projects", "chat", "documents", "workflows", "schedules", "cost-usage", "inbox-notifications", "delivery-channels"],
-      "stepCount": 15
+      "sections": ["projects", "chat", "documents", "tables", "workflows", "schedules", "cost-usage", "inbox-notifications", "delivery-channels"],
+      "stepCount": 16
     },
     {
       "slug": "power-user",
@@ -250,8 +260,8 @@
       "persona": "power-user",
       "difficulty": "advanced",
       "path": "journeys/power-user.md",
-      "sections": ["dashboard-kanban", "profiles", "chat", "workflows", "schedules", "monitoring", "settings"],
-      "stepCount": 15
+      "sections": ["dashboard-kanban", "profiles", "chat", "workflows", "tables", "schedules", "monitoring", "settings"],
+      "stepCount": 16
     },
     {
       "slug": "developer",
@@ -259,14 +269,14 @@
       "persona": "developer",
       "difficulty": "advanced",
       "path": "journeys/developer.md",
-      "sections": ["settings", "environment", "chat", "monitoring", "profiles", "workflows", "schedules", "delivery-channels"],
-      "stepCount": 14
+      "sections": ["settings", "environment", "chat", "monitoring", "profiles", "tables", "workflows", "schedules", "delivery-channels"],
+      "stepCount": 15
     }
   ],
   "metadata": {
-    "totalDocs": 29,
-    "totalScreengrabs": 44,
-    "featuresCovered": 68,
-    "appSections": 15
+    "totalDocs": 30,
+    "totalScreengrabs": 48,
+    "featuresCovered": 82,
+    "appSections": 16
   }
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "stagent",
-  "version": "0.6.3",
+  "version": "0.8.0",
   "description": "AI Business Operating System — run your business with AI agents. Local-first, multi-provider, governed.",
   "keywords": [
     "ai",
@@ -94,6 +94,7 @@
     "react-dom": "^19",
     "react-hook-form": "^7.71.2",
     "react-markdown": "^10.1.0",
+    "recharts": "^3.8.1",
     "remark-gfm": "^4.0.1",
     "sharp": "^0.34.5",
     "smol-toml": "^1.6.1",
@@ -101,6 +102,7 @@
     "sugar-high": "^1.0.0",
     "tailwind-merge": "^3",
     "tailwindcss": "^4",
+    "tar": "^7.5.13",
     "tw-animate-css": "^1",
     "typescript": "^5",
     "zod": "^4.3.6"

package/src/app/api/chat/entities/search/route.ts

@@ -1,6 +1,6 @@
 import { NextResponse } from "next/server";
 import { db } from "@/lib/db";
-import { projects, tasks, workflows, documents, schedules } from "@/lib/db/schema";
+import { projects, tasks, workflows, documents, schedules, userTables } from "@/lib/db/schema";
 import { like, desc } from "drizzle-orm";
 import { listProfiles } from "@/lib/agents/profiles/registry";
 
@@ -25,7 +25,7 @@ export async function GET(request: Request) {
 
   const hasQuery = query.trim().length > 0;
   const pattern = hasQuery ? `%${query}%` : "";
-  const perType = Math.max(2, Math.floor(limit / 5));
+  const perType = Math.max(2, Math.floor(limit / 7));
 
   const results: EntityResult[] = [];
 
@@ -45,9 +45,12 @@ export async function GET(request: Request) {
   const scheduleQuery = db
     .select({ id: schedules.id, name: schedules.name, status: schedules.status })
     .from(schedules);
+  const tableQuery = db
+    .select({ id: userTables.id, name: userTables.name, rowCount: userTables.rowCount, source: userTables.source })
+    .from(userTables);
 
   // Search in parallel across all entity types
-  const [projectRows, taskRows, workflowRows, documentRows, scheduleRows] =
+  const [projectRows, taskRows, workflowRows, documentRows, scheduleRows, tableRows] =
     await Promise.all([
       (hasQuery ? projectQuery.where(like(projects.name, pattern)) : projectQuery)
         .orderBy(desc(projects.updatedAt))
@@ -64,6 +67,9 @@ export async function GET(request: Request) {
       (hasQuery ? scheduleQuery.where(like(schedules.name, pattern)) : scheduleQuery)
         .orderBy(desc(schedules.updatedAt))
         .limit(perType),
+      (hasQuery ? tableQuery.where(like(userTables.name, pattern)) : tableQuery)
+        .orderBy(desc(userTables.updatedAt))
+        .limit(perType),
     ]);
 
   for (const p of projectRows) {
@@ -81,6 +87,9 @@ export async function GET(request: Request) {
   for (const s of scheduleRows) {
     results.push({ entityType: "schedule", entityId: s.id, label: s.name, status: s.status });
   }
+  for (const t of tableRows) {
+    results.push({ entityType: "table", entityId: t.id, label: t.name, description: `${t.rowCount ?? 0} rows · ${t.source}` });
+  }
 
   // Search profiles in-memory (file-based registry)
   const allProfiles = listProfiles();