Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
---
title: Deployment Patterns
title: Deployment patterns
description: >-
Common architectures for deploying cloud agents, including CLI-only,
Oz-hosted, and self-hosted execution patterns.
Expand Down
6 changes: 3 additions & 3 deletions src/content/docs/agent-platform/cloud-agents/faqs.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -57,7 +57,7 @@ Yes. Cloud agent runs execute in a full Linux environment and behave like a loca

The cloud agents platform supports self-hosting the **agent sandbox** (the execution environment) on your own infrastructure. The **control plane**—which handles orchestration, tracking, and auditability—remains Warp-managed and is not self-hosted.

Self-hosted execution is available on **Enterprise** plans. See [Self-Hosting](/agent-platform/cloud-agents/self-hosting/) and [Deployment Patterns](/agent-platform/cloud-agents/deployment-patterns/) for details.
Self-hosted execution is available on **Enterprise** plans. See [Self-hosting](/agent-platform/cloud-agents/self-hosting/) and [Deployment patterns](/agent-platform/cloud-agents/deployment-patterns/) for details.

:::note
[Bring Your Own Key (BYOK)](/support-and-community/plans-and-billing/bring-your-own-api-key/) does not apply to cloud agents. BYOK keys are stored locally on your device and cannot be passed to cloud-hosted or self-hosted agent runs. All cloud agent runs consume [Warp credits](/support-and-community/plans-and-billing/credits/).
Expand Down Expand Up @@ -203,7 +203,7 @@ With self-hosting, repositories are cloned and stored only on your infrastructur
* **Execution plane (your infrastructure)** — Repository clones, build artifacts, runtime secrets, and container filesystem state stay on the machines you control.
* **Control plane (Warp-hosted)** — Session transcripts (which include code context from agent interactions), orchestration metadata, and LLM inference route through Warp's backend under [Zero Data Retention (ZDR)](/enterprise/security-and-compliance/security-overview/#zero-data-retention-zdr) agreements. Warp does not persistently store your source code or use it for model training.

See [Self-Hosting](/agent-platform/cloud-agents/self-hosting/) for deployment options and [Security Overview](/enterprise/security-and-compliance/security-overview/) for full details.
See [Self-hosting](/agent-platform/cloud-agents/self-hosting/) for deployment options and [Security Overview](/enterprise/security-and-compliance/security-overview/) for full details.

### Can I use `oz agent run` in CI or existing runners?

Expand All @@ -226,7 +226,7 @@ Yes. LLM inference routes through Warp's backend, which has [Zero Data Retention
The [unmanaged architecture](/agent-platform/cloud-agents/self-hosting/unmanaged/) is well-suited for large monorepos because agents run directly in your pre-provisioned environment — there is no Docker image build or repo cloning step. For the [managed architecture](/agent-platform/cloud-agents/self-hosting/#managed-architecture), the Docker backend supports volume mounts (`-v` flag) to mount a pre-existing repo checkout from the host into task containers. With the Kubernetes backend, use `pod_template` to configure persistent volume claims or pre-populated storage for the same purpose.

:::note
The managed architecture supports three execution backends: **Docker** (default), **Kubernetes**, and **Direct** (no container runtime). The Kubernetes backend runs each task as a Kubernetes Job and includes a Helm chart for deployment. See [Self-Hosting](/agent-platform/cloud-agents/self-hosting/#choosing-a-managed-backend) for details on choosing a backend.
The managed architecture supports three execution backends: **Docker** (default), **Kubernetes**, and **Direct** (no container runtime). The Kubernetes backend runs each task as a Kubernetes Job and includes a Helm chart for deployment. See [Self-hosting](/agent-platform/cloud-agents/self-hosting/#choosing-a-managed-backend) for details on choosing a backend.
:::

### Do Kubernetes pods provide enough sandboxing for self-hosted agents?
Expand Down
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
---
title: Managing Cloud Agents
title: Managing cloud agents
description: >-
Monitor and manage cloud agent activity across your team with Warp's
centralized management view, including filtering, status tracking, and
Expand Down
2 changes: 1 addition & 1 deletion src/content/docs/agent-platform/cloud-agents/overview.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -57,7 +57,7 @@ Cloud agents run on the [Oz Platform](/agent-platform/cloud-agents/platform/), w

The exact way tasks are triggered and executed depends on your deployment model (for example CLI-only, Warp-hosted orchestration, or self-hosted execution). Those options are covered in the [Deployment Patterns](/agent-platform/cloud-agents/deployment-patterns/) pages.

For teams that need execution to stay within their network boundary, self-hosting supports two architectures: a **managed** worker daemon that lets Oz orchestrate agents in Docker containers on your machines, and an **unmanaged** mode where you run `oz agent run` directly in your CI, Kubernetes, or dev environment. See [Self-Hosting](/agent-platform/cloud-agents/self-hosting/) for details.
For teams that need execution to stay within their network boundary, self-hosting supports two architectures: a **managed** worker daemon that lets Oz orchestrate agents in Docker containers on your machines, and an **unmanaged** mode where you run `oz agent run` directly in your CI, Kubernetes, or dev environment. See [Self-hosting](/agent-platform/cloud-agents/self-hosting/) for details.

### What you get by default

Expand Down
2 changes: 1 addition & 1 deletion src/content/docs/agent-platform/cloud-agents/platform.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -185,7 +185,7 @@ With self-hosting:
* This is used when teams want code and execution to remain on their own systems rather than being cloned or executed in Warp's cloud.

:::note
**Enterprise feature**: Self-hosted execution requires an Enterprise plan. See [Self-Hosting](/agent-platform/cloud-agents/self-hosting/) for setup instructions.
**Enterprise feature**: Self-hosted execution requires an Enterprise plan. See [Self-hosting](/agent-platform/cloud-agents/self-hosting/) for setup instructions.
:::

---
Expand Down
2 changes: 1 addition & 1 deletion src/content/docs/code/overview.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@ description: >-
---
import VideoEmbed from '@components/VideoEmbed.astro';

Warp's coding features help you go from prompt to production. They combine a dedicated coding agent — consistently ranked among the top on SWE-bench Verified — with a native code editor, inline diff review, codebase context, and project-level rules for accurate, context-aware code generation.
Warp's coding features help you go from prompt to production. They combine a dedicated coding agent — consistently ranked among the top on SWE-bench Verified — with a native code editor, inline diff review, Codebase Context, and project-level rules for accurate, context-aware code generation.

:::note
On macOS and Linux SSH sessions, Warp's [SSH extension](/terminal/warpify/ssh/#installing-the-ssh-extension) brings the file tree, native file reads, and native code diffs to remote hosts. See [Feature support over SSH](/code/ssh-feature-support/) for the current support matrix.
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -163,7 +163,7 @@ Once your team is set up:
* **Agent Profiles** - Configure default [Agent Profiles](/agent-platform/capabilities/agent-profiles-permissions/) for different types of work to give teams appropriate autonomy and control
* **BYOLLM** - Set up [Bring Your Own LLM](/enterprise/enterprise-features/bring-your-own-llm/) to route inference through your cloud infrastructure for data locality and cost control
* **Monitor usage** - Review usage analytics in the Admin Panel to track adoption and measure engineering productivity gains
* **Self-hosting** - Run agents on your own infrastructure to control where agents run and keep repository clones on your own machines. See [Self-Hosting](/agent-platform/cloud-agents/self-hosting/) for setup instructions
* **Self-hosting** - Run agents on your own infrastructure to control where agents run and keep repository clones on your own machines. See [Self-hosting](/agent-platform/cloud-agents/self-hosting/) for setup instructions

## Troubleshooting

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -49,7 +49,7 @@ In the demo, we run three parallel workflows:
Analyze how many pull requests a team member has assigned.

```
Use the Github CLI tool to summarize all open PRs for review that are assigned to user. I'd like to see who is the author of the PR, when was it opened, how long has it been open for, which repo is it in, are there open an dunaddressed commens on it, and is it ready for review?
Use the GitHub CLI tool to summarize all open PRs for review that are assigned to user. I'd like to see who is the author of the PR, when was it opened, how long has it been open for, which repo is it in, are there open an dunaddressed commens on it, and is it ready for review?
```
</TabItem>
<TabItem label="Log Analysis">
Expand Down
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
---
title: Building a Real-time Chat App (Github MCP + Railway )
title: Building a Real-time Chat App (GitHub MCP + Railway)
description: >-
Build and deploy a real-time chat app with Python, FastAPI, and JavaScript —
from idea to production, all inside Warp.
Expand Down Expand Up @@ -229,6 +229,6 @@ The project: a **real-time chat application** built with **Python (FastAPI)** an

### Appendix

* [Github MCP Server](https://github.com/github/github-mcp-server)
* [GitHub MCP Server](https://github.com/github/github-mcp-server)
* [Docker Desktop download](https://www.docker.com/products/docker-desktop/)
* [Railway](https://railway.com/)
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
---
title: "Github MCP: Summarizing Open PRs & Creating GH Issues"
title: "GitHub MCP: Summarizing Open PRs & Creating GH Issues"
description: >-
Connect the GitHub MCP server to Warp to summarize open PRs, create issues
from TODO comments, and automate repo management.
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -55,5 +55,5 @@ This error is returned when:
## Related

* [Cloud Agents Overview](/agent-platform/cloud-agents/overview/) — How cloud agent tasks work
* [Self-Hosting](/agent-platform/cloud-agents/self-hosting/) — Self-hosted agent configuration
* [Self-hosting](/agent-platform/cloud-agents/self-hosting/) — Self-hosted agent configuration
* [Oz API & SDK](/reference/api-and-sdk/) — API reference for managing agent tasks
Original file line number Diff line number Diff line change
Expand Up @@ -102,7 +102,7 @@ If you're a [Team](/knowledge-and-collaboration/teams/) admin, the deletion flow
| `Agent Mode Setup Banner Accepted` | Agent Mode setup banner accepted |
| `Agent Mode Setup Banner Dismissed` | Agent Mode setup banner dismissed |
| `Agent Mode Setup Project Scoped Rules Action` | User clicked a button in the Agent Mode setup project scoped rules step |
| `Agent Mode.Setup Codebase Context Action` | User clicked a button in the Agent Mode setup codebase context step |
| `Agent Mode.Setup Codebase Context Action` | User clicked a button in the Agent Mode setup Codebase Context step |
| `Agent Predict` | Completed an Agent Predict prediction |
| `Agent Toolbar Dismissed` | User dismissed the use-agent toolbar |
| `AgentManagement.AgentTypeSelectorOpened` | User opened the agent type selector from agent management |
Expand Down Expand Up @@ -144,7 +144,7 @@ If you're a [Team](/knowledge-and-collaboration/teams/) admin, the deletion flow
| `AgentMode.Code.SuggestedEditAcceptClicked` | User selected Accept for a code diff suggestion in Agent Mode |
| `AgentMode.Code.SuggestedEditReceived` | Agent Mode suggested a code edit |
| `AgentMode.Code.SuggestedEditResolved` | Agent Mode pending code edit suggestion resolved |
| `AgentMode.CreatedAIBlock` | Created an AI block in agent mode |
| `AgentMode.CreatedAIBlock` | Created an AI block in Agent Mode |
| `AgentMode.Error` | Received an error when getting Agent Mode response |
| `AgentMode.ExecutedWarpDrivePrompt` | Executed a saved prompt. |
| `AgentMode.ExitedShellProcess` | An agent-requested command caused the shell process to exit |
Expand All @@ -153,7 +153,7 @@ If you're a [Team](/knowledge-and-collaboration/teams/) admin, the deletion flow
| `AgentMode.Grep.Failed` | The grep tool failed to complete |
| `AgentMode.Grep.Succeeded` | The grep tool completed successfully |
| `AgentMode.NaturalLanguageDetection.InputBufferSubmitted` | Input buffer submitted |
| `AgentMode.OpenedCitation` | Opened a citation that was surfaced in agent mode |
| `AgentMode.OpenedCitation` | Opened a citation that was surfaced in Agent Mode |
| `AgentMode.Orchestration.TeamAgentCommunicationFailed` | Failed to send an orchestration message or lifecycle event for a TeamAgent |
| `AgentMode.PotentialAutoDetectionFalsePositive` | Manually toggled input to shell mode after input was auto-detected as natural language. |
| `AgentMode.QueryAttemptAtLImit` | Tried to send an Agent Mode query but they already reached the query limit |
Expand Down Expand Up @@ -304,8 +304,8 @@ If you're a [Team](/knowledge-and-collaboration/teams/) admin, the deletion flow
| `CodexModal.UseCodexClicked` | User clicked 'Use Codex' in the Codex modal |
| `Command Correction Event` | Accepted command correction |
| `Command File Run` | Opened a .cmd or unix executable file and ran it directly in Warp |
| `Command Palette Search Accepted` | Accepted a command palette search result |
| `Command Palette Search Exited` | Exited command palette search without accepting a result |
| `Command Palette Search Accepted` | Accepted a Command Palette search result |
| `Command Palette Search Exited` | Exited Command Palette search without accepting a result |
| `Command Search Async Query Completed` | Finished searching for a command in the background |
| `Command Search Exited` | Exited command search (universal search panel to search) without accepting a result |
| `Command Search Filter Changed` | Changed command search filter |
Expand Down Expand Up @@ -510,7 +510,7 @@ If you're a [Team](/knowledge-and-collaboration/teams/) admin, the deletion flow
| `SSH Tmux Warpify Block Dismissed` | User dismissed an ssh tmux warpify block |
| `Save Launch Config` | Saved current launch configuration of windows, tabs, and panes |
| `Select App Icon` | Selected app icon |
| `Select Command Palette Option` | Selected option from command palette (i.e. CMD-P) |
| `Select Command Palette Option` | Selected option from Command Palette (i.e. CMD-P) |
| `Select Cursor Type` | Selected cursor type |
| `Select Navigation Palette Item` | Selected session from the Session Navigation Palette (search across panes, tabs, and windows) |
| `Select Theme` | Selected theme |
Expand Down Expand Up @@ -561,15 +561,15 @@ If you're a [Team](/knowledge-and-collaboration/teams/) admin, the deletion flow
| `Thin Strokes Setting Changed` | Changed thin strokes setting in settings -> Appearance |
| `Tier Limit Hit` | User hit the tier limit for a feature |
| `Toggle Active AI Enablement` | Toggled active AI enablement. |
| `Toggle Agent Mode Codebase Context` | Toggled on/off the enablement of codebase context usage for Agent Mode. |
| `Toggle Agent Mode Codebase Context` | Toggled on/off the enablement of Codebase Context usage for Agent Mode. |
| `Toggle Agent Mode Query Suggestions Setting` | Toggled on/off the prompt suggestions setting |
| `Toggle Approvals Modal` | Opened or closed teams modal |
| `Toggle Block Filter Case Sensitivity` | Toggled on/off case sensitivity within the block filter editor |
| `Toggle Block Filter Invert` | Toggled on/off invert within the block filter editor |
| `Toggle Block Filter Query` | Toggled on/off a block filter query |
| `Toggle Block Filter Regex` | Toggled on/off regex within the block filter editor |
| `Toggle Code Suggestions Setting` | Toggled on/off the code suggestions setting |
| `Toggle Codebase Context Autoindexing` | Toggled on/off the enablement of autoindexing for codebase context. |
| `Toggle Codebase Context Autoindexing` | Toggled on/off the enablement of autoindexing for Codebase Context. |
| `Toggle Dim Inactive Panes` | Whether the dim inactive panes feature has been toggled |
| `Toggle Focus Pane On Hover` | Toggled on/off focus pane on hover feature, which causes panes to automatically focus when hovering over them |
| `Toggle Git Operations Autogen Setting` | Toggled on/off the git operations autogen setting |
Expand Down
Loading