docs: auto-sync with merged PRs (through 2026-08-26)

packages/kilo-docs/pages/automate/agent-manager.md

@@ -189,7 +189,8 @@ Imported work stays associated with its branch or worktree and can be continued
 
 - Create a worktree session to start a new agent in an isolated branch
 - Press `Cmd+T` (macOS) / `Ctrl+T` (Windows/Linux) to start another session in the selected worktree
-- Use session history to reopen local sessions or preview cloud sessions
+- Use session history to reopen local sessions or preview cloud sessions. Open it with the history button in the **WORKTREES** header; in multi-project mode, each project row has its own history button, including collapsed projects. Opening a project's button activates that project and filters the Local history tab to that project's sessions.
+- Hover a session in the history list for direct actions: open the session in a newly created worktree, or move it to the project root and open it in the project's local tabs.
 - When a worktree is selected, open session history to use the **Worktree** source, which is selected by default and lists only sessions assigned to that worktree. Opening a worktree session returns to its owning worktree.
 - Continue a cloud session locally from Agent Manager using the same extension sign-in and provider settings
 
@@ -218,9 +219,11 @@ Each request can include 1-20 tasks. Each task must include at least one of `pro
 
 The companion `agent_manager_models` tool searches models and their supported reasoning variants on demand. Results are grouped by model name (with the offering providers listed for reference) and limited to 20 per call, so the full catalog is never added to the conversation context.
 
-The same tool also manages existing sessions. It can return an overview of sections, worktrees, and local sessions, send a prompt to one managed session, stop a managed session, or move a session's worktree into a section. The overview includes section IDs, each section's assigned worktrees, worktree IDs, and session IDs. Use those exact IDs for a subsequent move. Moving accepts a section ID from the overview, or `null` to ungroup the worktree. Moving a session moves its whole worktree, including multi-version siblings. Local sessions cannot be assigned to a section. Stopping aborts the session's active work and removes it from the panel, just like closing the session tab.
+The same tool also manages existing sessions. It can return an overview of sections, worktrees, and local sessions, send a prompt to one managed session, stop a managed session, move a session's worktree into a section, or answer a managed session's pending question. The overview includes section IDs, each section's assigned worktrees, worktree IDs, and session IDs. Use those exact IDs for a subsequent move. Moving accepts a section ID from the overview, or `null` to ungroup the worktree. Moving a session moves its whole worktree, including multi-version siblings. Local sessions cannot be assigned to a section. Stopping aborts the session's active work and removes it from the panel, just like closing the session tab.
 
-The tool uses the `agent_manager` permission. Approval prompts are scoped to the requested capability, so approving `worktree` does not automatically approve `local`, an overview, or a targeted prompt. Prompting an existing managed session requires an explicit `prompt` approval the first time, even if Agent Manager session creation was previously approved broadly. Stopping a session likewise requires an explicit `stop` approval, and moving a worktree requires an explicit `move` approval.
+A session waiting on a question refuses prompts. The failed prompt names the session ID, the pending question's ID and text, and its option labels, so a follow-up `answer` call can resolve the question with the exact labels shown. Answering resolves questions only — a session blocked on a permission request must be approved in the Agent Manager UI instead.
+
+The tool uses the `agent_manager` permission. Approval prompts are scoped to the requested capability, so approving `worktree` does not automatically approve `local`, an overview, or a targeted prompt. Prompting an existing managed session requires an explicit `prompt` approval the first time, even if Agent Manager session creation was previously approved broadly. Stopping a session likewise requires an explicit `stop` approval, moving a worktree requires an explicit `move` approval, and answering a pending question requires an explicit `answer` approval.
 
 ## Sections
 

packages/kilo-docs/pages/code-with-ai/platforms/cloud-agent.md

@@ -27,6 +27,15 @@ Before using Cloud Agents:
   - Please provide any feedback in our Cloud Agents beta Discord channel: [Kilo Discord](https://kilo.ai/discord)
 - **Kilo Code credits are still used** when the agent performs work (model usage, operations, etc.).
 
+### Session cost display
+
+The session header shows two separate entries:
+
+- **Token Usage** — the session's inference spend (model usage), paid in Kilo credits.
+- **Compute** — a server-provided estimate for the session's container: an estimated hourly rate while idle, a shared interval estimate while active, and **Not currently charged** in shadow mode. Stopping and unavailable states are shown when no estimate is available.
+
+If a compute billing check fails — for example, when the paying account has insufficient credits — the error appears next to the composer with recovery actions appropriate to the paying account (personal or organization) and your role in it. Your prompt text is preserved so you can retry after resolving the billing issue.
+
 ## How to Use
 
 1. **Connect your GitHub or GitLab account** in the [Integrations](https://app.kilo.ai/integrations) tab of your personal or organization dashboard.

packages/kilo-docs/pages/code-with-ai/platforms/jetbrains.md

@@ -17,6 +17,28 @@ Open **Settings → Tools → Kilo Code** to configure the plugin. The JetBrains
 - **Context** — toggle auto-compaction, set the auto-compaction limit (the percentage of the model window that triggers compaction), enable pruning of old tool outputs, and manage file watcher ignore patterns. See [Context Condensing](/docs/customize/context/context-condensing) and [.kilocodeignore](/docs/customize/context/kilocodeignore) for what these settings control.
 - **Agent Behavior → Skills** — inspect loaded skills, add extra skill sources (local paths or remote URLs), edit or remove custom skills, and open skill files in the editor. See [Skills](/docs/customize/skills) for the skill format and discovery rules.
 
+## Chat and Agents tabs
+
+The Kilo Code tool window is split into two tabs:
+
+- **Chat** — the conversation with the agent in the current workspace.
+- **Agents** — the Agent Manager, a control panel for running and orchestrating multiple agents in parallel, each in its own git worktree. A notification dot appears on the tab when a worktree session needs attention.
+
+### Working with worktrees
+
+- The worktree list shows each session's activity state with compact status icons and badges, including a running indicator for active sessions.
+- Drag worktrees to reorder them; the order is persisted and selection stays stable across refreshes.
+- Session history is scoped to the current worktree, so sessions from the main checkout or sibling worktrees are not mixed in. Sessions started from a worktree's separate IDE frame also appear in Agent Manager.
+
+### Chat branch dock
+
+When the workspace is a git repository, the chat header shows a branch dock with the current branch, a file-change summary, and worktree actions:
+
+- **New Worktree** — create a new git worktree with its own branch and session.
+- **Move to Worktree** — move the conversation and your current local changes into a dedicated worktree for isolated follow-up work. Available whenever the repository has local changes, even before the chat has a session.
+
+When the branch has an associated pull request, the dock shows the PR badge and title with access to the diff. Worktree actions appear only while the session is idle.
+
 ## Reviewing session changes
 
 - **Modified files per turn** — each assistant turn that changed files shows a **Modified** card with the affected files and their diff stats. Expand a file to see its diff inline, or open all of the turn's changes in the **Changed files** diff viewer.

packages/kilo-docs/pages/code-with-ai/platforms/mobile.md

@@ -25,6 +25,16 @@ The mobile app lets you:
 - Review GitHub pull requests end to end — diffs, checks, comments, and merging.
 - Start a new session on a connected `kilo remote` CLI instance with the **Run on** picker.
 
+## Language and region
+
+The app renders in 87 languages. It follows your device language by default and falls back to English when the device language is not supported.
+
+To override the device language, use the language picker on the login screen or in **Preferences**. The picker supports search and shows each language in its own script. Dates, times, and currency formatting follow the active language.
+
+Choosing a language with a different layout direction (such as Arabic or Hebrew) restarts the app into a mirrored, right-to-left layout; a same-direction change applies in place. A restart keeps the email you typed on the login screen.
+
+Push notifications arrive in the language the device had when it registered, so each device gets its own language.
+
 ## Privacy and telemetry
 
 On first launch, the app asks for your consent before enabling optional telemetry — product analytics, attribution, and performance tracing. Optional telemetry is pre-selected during onboarding; you can turn it off before accepting. No optional analytics starts before you make a choice.

packages/kilo-docs/pages/deploy-secure/security-reviews.md

@@ -375,9 +375,11 @@ SLA notifications require both SLA tracking and SLA notifications to be enabled.
 
 ## Notification delivery
 
-Security Agent currently sends notifications only by email.
+Security Agent sends notifications by email and by push to the mobile app.
 
-Notification kinds:
+Push notifications are sent when an analysis completes or fails, and when a remediation is queued, opens a pull request, fails, is blocked, needs no changes, or is cancelled. For a personal Security Agent, pushes go to the owning user. For an organization Security Agent, they go to the organization owners.
+
+Email notification kinds:
 
 | Kind | When eligible |
 |---|---|
@@ -408,6 +410,8 @@ The audit report shows Security Finding activity recorded for an owner during a
 - `/security-agent/audit-report`
 - `/organizations/:organizationId/security-agent/audit-report`
 
+The audit report is also available as a native screen in the mobile app, showing the report period and each finding's recorded activity.
+
 The audit report is based on activity recorded by Kilo. It does not prove that every historical event is present, show repository scan coverage, or provide aggregate SLA compliance.
 
 ### Report period and filters
@@ -480,7 +484,7 @@ The following capabilities are not yet implemented but are being considered for
 
 - GitLab support for Security Agent findings and remediation.
 - Security Finding sources beyond Dependabot alerts, such as npm audit and SBOM analysis.
-- Notification channels beyond email.
+- Notification channels beyond email and mobile push.
 - Historical replay when you enable New-finding Notifications.
 - Analysis and remediation without queue delays. This work currently runs through queues and can be delayed by account capacity or worker backlog.
 - Automatic finding updates based on the full remediation PR lifecycle. A finding currently closes only when Dependabot reports it fixed or someone dismisses it.

packages/kilo-docs/pages/getting-started/settings/auto-approving-actions.md

@@ -70,7 +70,7 @@ Use the shield button in the prompt controls to toggle runtime auto-approve for
 
 Expand **Manage Auto-Approve Rules** to add commands or patterns to your allowed or denied lists. These rules are then appended to the bottom of the approval rules in settings and the config file.
 
-For the `agent_manager` tool, runtime approvals use the requested capability as the pattern: `worktree`, `local`, `overview`, or `prompt`. Prompting an existing managed session always requires an explicit `prompt` approval the first time, even when a broad Agent Manager allow rule already exists.
+For the `agent_manager` tool, runtime approvals use the requested capability as the pattern: `worktree`, `local`, `overview`, `prompt`, `stop`, `move`, or `answer`. Prompting an existing managed session always requires an explicit `prompt` approval the first time, even when a broad Agent Manager allow rule already exists. The same applies to stopping a session, moving a worktree, and answering a managed session's pending question — each requires its own explicit approval.
 
 ## MCP Tool Permissions