diff --git a/.agents/references/terminology.md b/.agents/references/terminology.md index 184d7b53..17bf101a 100644 --- a/.agents/references/terminology.md +++ b/.agents/references/terminology.md @@ -69,8 +69,8 @@ For the summary of the most critical terms (core features, Oz terms, terms to av ## Agent concepts -- **Ambient Agents** — Oz agents that run automatically in the background on a schedule or trigger, without interactive input. - *Usage note:* Capitalize as a feature/section name. Use lowercase "ambient agents" only when describing the generic concept of agents running in the background. +- **Cloud Agents** — Agents that run in the cloud on a schedule, trigger, or integration, without interactive input. Managed by the Oz Platform. + *Usage note:* Use lowercase "cloud agents" in most contexts. Capitalize as "Cloud Agents" only when referring to the product section or feature name. - **Agent Profiles** — Saved configurations that define how an Agent runs (for example, permissions and model selection). *Usage note:* Use when describing "choose how your Agent behaves." @@ -130,33 +130,33 @@ For the summary of the most critical terms (core features, Oz terms, terms to av ## Oz terminology -### Oz vs Warp +### Warp Agent vs Oz -- **Warp** is the terminal and coding surface -- **Oz** is Warp's programmable agent for running and coordinating agents at scale +- **Warp Agent** — Warp's built-in agent harness. Use "Warp Agent" when specifically referring to the built-in harness, especially when contrasting with third-party agents (Claude Code, Codex, etc.), or when referencing the Settings label (**Settings** > **Agents** > **Warp Agent**). +- **Oz** — Warp's programmable platform for running and coordinating agents at scale - There is typically one Warp environment per user session. Oz can run many agents concurrently, across machines, repos, and teams. -### Core Oz terms +### Core terms -- **Environment** — The execution context for an Oz agent, including repo access, dependencies, secrets, compute, and runtime configuration. +- **agent** — A combination of agent instructions (skill or prompt), trigger (cron, webhook, manual), environment (local, cloud), profile, and host. Agents can be local or cloud. Use lowercase "agent" in most contexts; use "Warp Agent" only when referring specifically to the built-in Warp harness. + *Example:* Launch an agent from the CLI, the web app, an API or SDK, or directly inside Warp. -- **Oz** — Warp's programmable agent for running and coordinating agents at scale. - *Example:* With Oz, you can orchestrate multiple agents to automate and parallelize complex workflows. +- **cloud agent** — An agent running in the cloud, from a trigger, schedule, or started from someone's local machine. -- **Oz agent** — A combination of agent instructions (skill or prompt), trigger (cron, webhook, manual), environment (local, cloud), profile, and host. Agents can be local or cloud, and interactive or ambient. - *Example:* Launch an Oz agent from the CLI, the web app, an API or SDK, or directly inside Warp. +- **conversation** — An interactive execution lifecycle within the Warp Terminal, regardless of whether it's local or in the cloud. -- **Oz cloud agent** — An Oz agent running in the cloud, from a trigger, schedule, or started from someone's local machine. Cloud agents can be interactive or ambient. +- **Environment** — The execution context for an agent, including repo access, dependencies, secrets, compute, and runtime configuration. -- **Oz conversation** — An interactive execution lifecycle within the Warp Terminal. An Oz conversation is interactive, started in the terminal regardless of whether it's local or in the cloud. +- **Oz** — Warp's programmable platform for running and coordinating agents at scale. + *Example:* With Oz, you can orchestrate multiple agents to automate and parallelize complex workflows. - **Oz dashboard** — The app surface to manage all Oz runs, unified across the Warp app and web. -- **Oz run** — A single execution lifecycle of an Oz agent, including actions, outputs, and logs. An Oz run is always ambient and cloud-based. +- **Oz run** — A single execution lifecycle of an agent, including actions, outputs, and logs. An Oz run is always cloud-based. -- **Oz subagent** — A child Oz agent created by a parent Oz agent to parallelize or delegate work. +- **Oz web app** — The web app for configuring agents and managing runs. -- **Oz web app** — The web app for configuring Oz agents and managing runs. +- **subagent** — A child agent created by a parent agent to parallelize or delegate work. ### Oz CLI commands @@ -164,8 +164,8 @@ For the summary of the most critical terms (core features, Oz terms, terms to av - `oz agent run-cloud` — Run an adhoc cloud agent - `oz environment create/list/get/update/delete` — CRUD on environments - `oz integration create` — Install integrations (Slack, Linear) -- `oz run list/get` — Get info on ambient agent runs -- `oz schedule create/list/get/update/delete` — CRUD on scheduled ambient agents +- `oz run list/get` — Get info on cloud agent runs +- `oz schedule create/list/get/update/delete` — CRUD on scheduled cloud agents - `oz secret create/list/update/delete` — CRUD on Warp-managed secrets ### Preferred phrases @@ -176,11 +176,16 @@ For the summary of the most critical terms (core features, Oz terms, terms to av ### Terms to avoid -- ❌ "Ozzies" → Use "Oz agents", "instances", or "Oz subagents" -- ❌ "Deploying an Oz" → Use "Deploying an Oz agent" -- ❌ "The Oz Agent" → Use "An Oz agent" or "A parent Oz agent" -- ❌ "Oz is running" → Use "An Oz agent is running" or "A run is in progress" +- ❌ "Oz agent" / "Oz agents" → Use "agent" / "agents" (or "Warp Agent" / "Warp Agents" when referring to the built-in harness) +- ❌ "Oz cloud agent" → Use "cloud agent" +- ❌ "Oz subagent" → Use "subagent" +- ❌ "Oz conversation" → Use "conversation" +- ❌ "Ozzies" → Use "agents", "instances", or "subagents" +- ❌ "Deploying an Oz" → Use "Deploying an agent" +- ❌ "The Oz Agent" → Use "the agent" or "the Warp Agent" +- ❌ "Oz is running" → Use "An agent is running" or "A run is in progress" - ❌ "AI agents" → Use "agents" (the "AI" prefix is redundant) +- ❌ "Ambient Agents" / "ambient agents" → Use "Cloud Agents" / "cloud agents" ("ambient" is no longer a product term; acceptable only in code identifiers like `AmbientAgentConfig`) ## Platform terms diff --git a/.agents/rules/oz-style-guidelines.md b/.agents/rules/oz-style-guidelines.md index 561ab244..99675b24 100644 --- a/.agents/rules/oz-style-guidelines.md +++ b/.agents/rules/oz-style-guidelines.md @@ -34,46 +34,52 @@ When writing about Warp products or features, tie back to at least one of these ## Oz Terminology and Capitalization -### Core Oz Terms +### Core Terms - **Oz** - Warp's programmable platform for running and coordinating agents at scale -- **Oz agent** - A combination of agent instructions (skill or prompt), trigger (cron, webhook, manual), environment (local, cloud), profile, and host. Can be local or cloud, interactive or ambient -- **Oz cloud agent (general)** - An Oz agent running in the cloud, from a trigger, schedule, or started from someone's local machine -- **Oz subagent** - A child Oz agent created by a parent Oz agent to parallelize or delegate work -- **Oz run** - A single execution lifecycle of an Oz agent, including actions, outputs, and logs. Always ambient and cloud-based -- **Oz conversation** - An interactive execution lifecycle within Warp terminal, regardless of whether it's local or in the cloud -- **Environment** - The execution context for an Oz agent, including repo access, dependencies, secrets, compute, and runtime configuration +- **Warp Agent** - Warp's built-in agent harness. Use "Warp Agent" when specifically referring to the built-in harness, especially when contrasting with third-party agents (Claude Code, Codex, etc.) +- **agent** - A combination of agent instructions (skill or prompt), trigger (cron, webhook, manual), environment (local, cloud), profile, and host. Can be local or cloud. Use lowercase "agent" in most contexts. +- **cloud agent** - An agent running in the cloud, from a trigger, schedule, or started from someone's local machine +- **subagent** - A child agent created by a parent agent to parallelize or delegate work +- **Oz run** - A single execution lifecycle of an agent, including actions, outputs, and logs. Always cloud-based +- **conversation** - An interactive execution lifecycle within Warp terminal, regardless of whether it's local or in the cloud +- **Environment** - The execution context for an agent, including repo access, dependencies, secrets, compute, and runtime configuration - **Oz dashboard** - The app surface to manage all Oz runs, unified across the Warp app and web -- **Oz web app** - The web app for configuring Oz agents and managing runs +- **Oz web app** - The web app for configuring agents and managing runs ### Capitalization Rules **Cloud agents:** -- **Product** (capitalized): "Oz Cloud Agent" or "Oz Cloud Agents" when referring to Warp's specific product feature - - "Oz Cloud Agents send you session sharing links" - - "Launch an Oz Cloud Agent from the CLI" +- **Product** (capitalized): "Cloud Agent" or "Cloud Agents" when referring to Warp's specific product feature + - "Cloud Agents send you session sharing links" + - "Launch a Cloud Agent from the CLI" - **Concept** (lowercase): "cloud agent" or "cloud agents" when referring to the general concept - "Running cloud agents lets you escape the limits of your local machine" - "The cloud agent architecture enables scalability" **Other terms:** - Use "agents" not "AI agents" (redundant) +- Use "agent" not "Oz agent" (deprecated); use "Warp Agent" only when referring to the built-in harness - "Skills" not "skills" (capitalized) - "AGENTS.md" not "agents.md" (all caps) ### Terms to Avoid ❌ **Don't use:** -- "Ozzies" → Use "Oz agents", "instances", or "Oz subagents" -- "Deploying an Oz" → Use "Deploying an Oz agent" -- "The Oz Agent" → Use "An Oz agent" or "A parent Oz agent" -- "Oz is running" → Use "An Oz agent is running" or "A run is in progress" +- "Oz agent" / "Oz agents" → Use "agent" / "agents" (or "Warp Agent" / "Warp Agents" when referring to the built-in harness) +- "Oz cloud agent" → Use "cloud agent" +- "Oz subagent" → Use "subagent" +- "Oz conversation" → Use "conversation" +- "Ozzies" → Use "agents", "instances", or "subagents" +- "Deploying an Oz" → Use "Deploying an agent" +- "The Oz Agent" → Use "the agent" or "the Warp Agent" +- "Oz is running" → Use "An agent is running" or "A run is in progress" - "AI agents" → Use "agents" - "Warp's terminal" → Use "Warp" or "Warp terminal" ### Important Context About Oz -**All agents in Warp are Oz agents**, whether they are running in the cloud or running locally. +Oz is Warp's programmable platform for running and coordinating agents at scale, whether they are running in the cloud or running locally. Oz exists to take agent workflows beyond a single prompt or a single laptop, making them scalable, autonomous, collaborative, and auditable. diff --git a/.agents/skills/answer_question/SKILL.md b/.agents/skills/answer_question/SKILL.md index 1029e017..e7a17577 100644 --- a/.agents/skills/answer_question/SKILL.md +++ b/.agents/skills/answer_question/SKILL.md @@ -49,7 +49,7 @@ Both repos are indexed for `codebase_semantic_search`. Use `grep` for exact symb - Be direct and matter-of-fact. Answer the question, don't summarize the docs. - Be comprehensive — cover what the user needs to fully understand the answer — but don't pad with tangential information. -- Use Warp's standard terminology from `AGENTS.md` and the full glossary in `.warp/references/terminology.md`. Key rules: capitalize feature names (Agent, Agent Mode, Warp Drive, Codebase Context), use "Oz agent" not "Ozzie" or "the Oz Agent", use "credits" not "AI credits." +- Use Warp's standard terminology from `AGENTS.md` and the full glossary in `.warp/references/terminology.md`. Key rules: capitalize feature names (Agent, Agent Mode, Warp Drive, Codebase Context), use "agent" (generic) or "Warp Agent" (built-in harness) not "Oz agent" or "Ozzie", use "credits" not "AI credits." - If the docs do not cover the topic, say so honestly. Do not guess or fabricate information. ### 4. Generate doc links diff --git a/.agents/skills/missing_docs/references/feature_surface_map.md b/.agents/skills/missing_docs/references/feature_surface_map.md index ccf0eb02..7698faca 100644 --- a/.agents/skills/missing_docs/references/feature_surface_map.md +++ b/.agents/skills/missing_docs/references/feature_surface_map.md @@ -8,7 +8,7 @@ Lines starting with `#` are comments. Blank lines are ignored. # Maintenance: when a new GA feature flag ships, add a mapping here. # Run `python3 .warp/skills/missing_docs/scripts/audit_docs.py` to find unmapped flags. -# This audit is also run as a recurring scheduled Oz agent to catch drift. +# This audit is also run as a recurring scheduled cloud agent to catch drift. ## Feature flags -> doc pages diff --git a/.agents/skills/missing_docs/references/stale_terms.md b/.agents/skills/missing_docs/references/stale_terms.md index 555a2b3e..d6756ca1 100644 --- a/.agents/skills/missing_docs/references/stale_terms.md +++ b/.agents/skills/missing_docs/references/stale_terms.md @@ -25,10 +25,17 @@ mac os -> Use 'macOS' ## Deprecated terminology -ozzies -> Use 'Oz agents', 'instances', or 'Oz subagents' -warp agent -> Use 'Agent' or 'Oz agent' depending on context -warp agents -> Use 'Agents' or 'Oz agents' depending on context +ambient agent -> Use 'cloud agent' — 'ambient' is no longer a product term +ambient agents -> Use 'cloud agents' — 'ambient' is no longer a product term +ozzies -> Use 'agents', 'instances', or 'subagents' +oz agent -> Use 'agent' or 'Warp Agent' depending on context +oz agents -> Use 'agents' or 'Warp Agents' depending on context +oz cloud agent -> Use 'cloud agent' +oz cloud agents -> Use 'cloud agents' +oz subagent -> Use 'subagent' +oz subagents -> Use 'subagents' +oz conversation -> Use 'conversation' agent-mode -> Use 'Agent Mode' (two words, no hyphen) -deploying an oz -> Use 'Deploying an Oz agent' -the oz agent -> Use 'An Oz agent' or 'A parent Oz agent' -oz is running -> Use 'An Oz agent is running' or 'A run is in progress' +deploying an oz -> Use 'Deploying an agent' +the oz agent -> Use 'the agent' or 'the Warp Agent' +oz is running -> Use 'An agent is running' or 'A run is in progress' diff --git a/.agents/skills/style_lint/SKILL.md b/.agents/skills/style_lint/SKILL.md index f2550d94..188c2a84 100644 --- a/.agents/skills/style_lint/SKILL.md +++ b/.agents/skills/style_lint/SKILL.md @@ -52,7 +52,7 @@ python3 .warp/skills/style_lint/style_lint.py --all --fix --create-pr ### Terminology checks - **Product name casing**: "Warp Terminal" (→ "Warp"), "agent mode" (→ "Agent Mode"), "warp drive" (→ "Warp Drive"), "codebase context" (→ "Codebase Context"), "agent management panel" (→ "Agent Management Panel") -- **Oz terms to avoid**: "Ozzies", "Deploying an Oz", "The Oz Agent", "Oz is running", "AI agents" +- **Oz terms to avoid**: "Oz agent", "Oz cloud agent", "Oz subagent", "Oz conversation", "Ozzies", "Deploying an Oz", "The Oz Agent", "Oz is running", "AI agents" - **Deprecated terminology**: "whitelist" (→ "allowlist"), "blacklist"/"blocklist" (→ "denylist") - **External product names**: "Github" (→ "GitHub"), "github actions" (→ "GitHub Actions"), "MacOS" (→ "macOS"), "A.I." (→ "AI") - **Unrecognized terms** (warning): Bolded terms that look like product names but aren't in `terminology.md`. Flags candidates for glossary addition — not errors, just suggestions. @@ -65,7 +65,7 @@ When run with `--fix`: ## Relationship to validate_ui_refs -This skill checks broader formatting and terminology. The `validate_ui_refs` skill validates UI paths and Command Palette names against the warp-internal codebase. They complement each other with no overlap. Both can run in scheduled Oz agent workflows. +This skill checks broader formatting and terminology. The `validate_ui_refs` skill validates UI paths and Command Palette names against the warp-internal codebase. They complement each other with no overlap. Both can run in scheduled cloud agent workflows. ## Dependencies @@ -73,7 +73,7 @@ Requires Python 3.7+. Optional: `requests` (for Slack notifications), `gh` CLI ( ## Cloud agent / scheduling -For scheduled Oz cloud agent runs: +For scheduled cloud agent runs: 1. Configure the environment with the docs repo 2. Set the `SLACK_BOT_TOKEN` secret in the environment (for `--slack-notify`) 3. Run: `python3 .warp/skills/style_lint/style_lint.py --all --fix --create-pr --slack-notify` diff --git a/.agents/skills/style_lint/style_lint.py b/.agents/skills/style_lint/style_lint.py index 414f62e7..644ef86b 100644 --- a/.agents/skills/style_lint/style_lint.py +++ b/.agents/skills/style_lint/style_lint.py @@ -35,7 +35,7 @@ # Feature names that are correctly Title Case (exceptions to sentence-case rule) PROPER_FEATURE_NAMES = { "Admin Panel", "Agent Management Panel", "Agent Mode", "Agent Profiles", - "Ambient Agents", "Auto-detection Mode", + "Auto-detection Mode", "Cloud Agents", "Codebase Context", "Code Review", "Command Palette", "Global Rules", "Oz CLI", "Oz Platform", "Project Rules", "Slash Commands", "Terminal Mode", "Universal Input", "Warp Drive", @@ -73,11 +73,16 @@ # Oz terms to avoid (case-insensitive patterns) OZ_TERMS_TO_AVOID = [ - (r"\bOzzies\b", "Use 'Oz agents', 'instances', or 'Oz subagents'"), - (r"\bDeploying an Oz\b", "Use 'Deploying an Oz agent'"), - (r"\bThe Oz Agent\b", "Use 'An Oz agent' or 'A parent Oz agent'"), - (r"\bOz is running\b", "Use 'An Oz agent is running' or 'A run is in progress'"), + (r"\bOzzies\b", "Use 'agents', 'instances', or 'subagents'"), + (r"\bDeploying an Oz\b", "Use 'Deploying an agent'"), + (r"\bThe Oz Agent\b", "Use 'the agent' or 'the Warp Agent'"), + (r"\bOz is running\b", "Use 'An agent is running' or 'A run is in progress'"), (r"\bAI agents?\b", "Use 'agents' (the 'AI' prefix is redundant)"), + (r"\bOz cloud agents?\b", "Use 'cloud agent(s)'"), + (r"\bOz subagents?\b", "Use 'subagent(s)'"), + (r"\bOz conversation\b", "Use 'conversation'"), + (r"\bOz agents?\b", "Use 'agent(s)' or 'Warp Agent(s)' depending on context"), + (r"\b[Aa]mbient [Aa]gents?\b", "Use 'cloud agent(s)' — 'ambient' is no longer a product term"), ] # Action verbs that precede UI elements (should be bold, not backtick) @@ -389,13 +394,23 @@ def check_product_casing(lines: List[str], filepath: str) -> List[Issue]: def check_oz_terms(lines: List[str], filepath: str) -> List[Issue]: - """Check for Oz terms to avoid.""" + """Check for Oz terms to avoid. + + Skips fenced code blocks and strips inline code (backtick-wrapped text) + so that legitimate CLI commands like `oz agent run` are not flagged. + """ issues = [] + in_code_block = False for i, line in enumerate(lines, 1): - if line.strip().startswith("```") or line.strip().startswith("`"): + if line.strip().startswith("```"): + in_code_block = not in_code_block + continue + if in_code_block: continue + # Strip inline code spans so `oz agent run` is not matched + prose_line = re.sub(r"`[^`]+`", "", line) for pattern, suggestion in OZ_TERMS_TO_AVOID: - for m in re.finditer(pattern, line, re.IGNORECASE): + for m in re.finditer(pattern, prose_line, re.IGNORECASE): issues.append(Issue( filepath, i, "oz-term", f"Avoid \"{m.group(0)}\" → {suggestion}", diff --git a/.agents/skills/sync-error-docs/references/error-page-template.md b/.agents/skills/sync-error-docs/references/error-page-template.md index a9210d6b..6d9067b0 100644 --- a/.agents/skills/sync-error-docs/references/error-page-template.md +++ b/.agents/skills/sync-error-docs/references/error-page-template.md @@ -60,7 +60,7 @@ This error is returned when: ## Related -* [Oz Agent API & SDK](https://docs.warp.dev/reference/api-and-sdk/agent) — API reference +* [Agent API & SDK](https://docs.warp.dev/reference/api-and-sdk/agent) — API reference * [Cloud Agents Overview](https://docs.warp.dev/agent-platform/cloud-agents/overview) — How cloud agents work ``` diff --git a/.agents/skills/validate_ui_refs/SKILL.md b/.agents/skills/validate_ui_refs/SKILL.md index 8b76f2b4..4b1ce868 100644 --- a/.agents/skills/validate_ui_refs/SKILL.md +++ b/.agents/skills/validate_ui_refs/SKILL.md @@ -135,7 +135,7 @@ The `--slack-notify` flag posts a summary to the configured Slack channel when u ### Intended behavior for scheduled runs -When this skill is configured as a scheduled Oz agent, Slack notifications should alert the team in two cases: +When this skill is configured as a scheduled cloud agent, Slack notifications should alert the team in two cases: 1. **Auto-fixes applied** — the script found and corrected issues, and created a PR. The notification should include the PR link so the team can review and merge. 2. **Unfixed issues remain** — some issues could not be auto-corrected (e.g., a renamed or removed section) and require manual attention. The notification should list these for triage. @@ -162,7 +162,7 @@ python3 .warp/skills/validate_ui_refs/validate_ui_refs.py --all --slack-notify ## Cloud Agent / Scheduling -For scheduled Oz cloud agent runs: +For scheduled cloud agent runs: 1. Configure the environment with the docs repo 2. Keep `valid_paths.json` up-to-date by running `--refresh-valid-paths` as a pre-step (requires `warp-internal` in the environment) diff --git a/.agents/templates/faq.md b/.agents/templates/faq.md index 73f36bd0..a1e32ac4 100644 --- a/.agents/templates/faq.md +++ b/.agents/templates/faq.md @@ -1,7 +1,7 @@ --- description: >- [1-2 sentences: what topic area these FAQs cover. - Example: "Answers to common questions about Oz cloud agents, billing, and environments."] + Example: "Answers to common questions about cloud agents, billing, and environments."] --- # [Title — sentence case. Title convention: "[Feature] FAQs" or "Frequently asked questions"] diff --git a/.agents/templates/quickstart.md b/.agents/templates/quickstart.md index 9adac6c0..1cb9d362 100644 --- a/.agents/templates/quickstart.md +++ b/.agents/templates/quickstart.md @@ -1,7 +1,7 @@ --- description: >- [1-2 sentences: what the reader will accomplish + time estimate. - Example: "Learn how to run your first Oz cloud agent in ~10 minutes."] + Example: "Learn how to run your first cloud agent in ~10 minutes."] --- # [Descriptive title — sentence case. Title convention: "[Feature] quickstart" or "Quickstart for [product]". Do NOT use a bare "Quickstart" — include the feature name.] diff --git a/.agents/templates/troubleshooting.md b/.agents/templates/troubleshooting.md index 561c3948..ea91da9e 100644 --- a/.agents/templates/troubleshooting.md +++ b/.agents/templates/troubleshooting.md @@ -1,7 +1,7 @@ --- description: >- [1-2 sentences describing common issues covered on this page. - Example: "Solutions for common issues with Oz cloud agents, environments, and integrations."] + Example: "Solutions for common issues with cloud agents, environments, and integrations."] --- # [Title — sentence case. Title convention: "Troubleshooting [feature]" or "Known issues with [feature]"] diff --git a/.github/workflows/respond-to-comment.yml b/.github/workflows/respond-to-comment.yml deleted file mode 100644 index 4d87a86c..00000000 --- a/.github/workflows/respond-to-comment.yml +++ /dev/null @@ -1,249 +0,0 @@ -name: Respond to Comment -on: - issue_comment: - types: - - created - pull_request_review_comment: - types: - - created -jobs: - respond: - runs-on: ubuntu-latest - if: | - contains(github.event.comment.body,'@oz-agent') && - ( - github.event_name == 'pull_request_review_comment' || - (github.event_name == 'issue_comment' && github.event.issue.pull_request) - ) && - github.actor != 'github-actions[bot]' - permissions: - contents: write - pull-requests: write - issues: write - steps: - - name: Check author permissions - uses: actions/github-script@v7 - with: - github-token: ${{ github.token }} - script: | - const { data } = await github.rest.repos.getCollaboratorPermissionLevel({ - owner: context.repo.owner, - repo: context.repo.repo, - username: context.payload.comment.user.login, - }); - if (!['admin', 'write'].includes(data.permission)) { - core.setFailed(`Comment author @${context.payload.comment.user.login} lacks write access (has '${data.permission}')`); - } - - name: Checkout Action - uses: actions/checkout@v4 - - name: Acknowledge Comment - env: - GH_TOKEN: ${{ github.token }} - run: | - COMMENT_ID="${{ github.event.comment.id }}" - REACTION="eyes" - - if [ "${{ github.event_name }}" == "pull_request_review_comment" ]; then - gh api \ - --method POST \ - -H "Accept: application/vnd.github+json" \ - -H "X-GitHub-Api-Version: 2022-11-28" \ - /repos/${{ github.repository }}/pulls/comments/$COMMENT_ID/reactions \ - -f content="$REACTION" - else - gh api \ - --method POST \ - -H "Accept: application/vnd.github+json" \ - -H "X-GitHub-Api-Version: 2022-11-28" \ - /repos/${{ github.repository }}/issues/comments/$COMMENT_ID/reactions \ - -f content="$REACTION" - fi - - name: Checkout PR - env: - GH_TOKEN: ${{ github.token }} - run: | - PR_NUMBER="${{ github.event.issue.number }}" - if [ -z "$PR_NUMBER" ]; then - PR_NUMBER="${{ github.event.pull_request.number }}" - fi - - echo "Checking out PR #$PR_NUMBER" - gh pr checkout "$PR_NUMBER" - - name: Construct Prompt - id: prompt - uses: actions/github-script@v7 - with: - github-token: ${{ github.token }} - script: | - const { owner, repo } = context.repo; - let prNumber; - if (context.eventName === 'issue_comment') { - prNumber = context.payload.issue.number; - } else { - prNumber = context.payload.pull_request.number; - } - - // Fetch PR details to provide full context - const { data: pr } = await github.rest.pulls.get({ - owner, - repo, - pull_number: prNumber, - }); - - // Get the list of files changed in the PR - const { data: files } = await github.rest.pulls.listFiles({ - owner, - repo, - pull_number: prNumber, - }); - - const fileList = files.map(f => f.filename).join(', '); - - const commentBody = context.payload.comment.body; - const author = context.payload.comment.user.login; - - let prompt = `You are an expert software engineer and the Oz Agent. - You are responding to a specific request on a Pull Request. This may involve answering questions, providing explanations, or implementing code changes. - - **Context**: - - **PR Title**: ${pr.title} - - **PR Description**: ${pr.body || 'No description provided.'} - - **Changed Files**: ${fileList} - - **User Request**: "${commentBody}" (from user @${author}) - `; - - if (context.eventName === 'pull_request_review_comment') { - const path = context.payload.comment.path; - const line = context.payload.comment.line; - const diffHunk = context.payload.comment.diff_hunk; - prompt += ` - - **Location**: File '${path}' at line ${line}. - - **Diff Context**: - \`\`\`diff - ${diffHunk} - \`\`\` - `; - prompt += ` - **Instructions**: - 1. Read the file at '${path}' to understand the full context around the line. - `; - } else { - prompt += ` - **Instructions**: - 1. Focus your analysis on the changed files (${fileList}) unless the request explicitly mentions other files. - `; - } - - prompt += `2. Determine if the user is asking a question or requesting code changes. - 3. If asking a question: Answer it based on your analysis of the code and context. - 4. If requesting code changes: Implement them carefully, ensuring correctness and following existing style. - 5. Do not output code diffs in your final message; only provide a clear explanation of what you did or answered. - 6. Format your response in Markdown. - 7. Your output will be posted as a reply to the user. - 8. Do not attempt to stage or commit changes manually. This happens automatically after you complete your response. - `; - - core.setOutput('prompt', prompt); - - name: Run Oz Agent - uses: warpdotdev/oz-agent-action@v1 - env: - GH_TOKEN: ${{ github.token }} - id: agent - with: - prompt: ${{ steps.prompt.outputs.prompt }} - warp_api_key: ${{ secrets.WARP_API_KEY }} - profile: '' - output_format: json - model: '' - name: '' - mcp: '' - - name: Commit and Push Changes - if: success() - env: - GH_TOKEN: ${{ github.token }} - run: | - git config user.name "Oz Agent" - git config user.email "agent@warp.dev" - - if [[ -n $(git status --porcelain) ]]; then - git add . - git commit -m "Oz Agent: Address comment" - git push - else - echo "No changes to commit." - fi - - name: Reply to Comment - if: success() - uses: actions/github-script@v7 - env: - AGENT_OUTPUT: ${{ steps.agent.outputs.agent_output }} - with: - github-token: ${{ github.token }} - script: | - const raw = process.env.AGENT_OUTPUT || ''; - - // Walk JSONL lines and capture the last agent text message, if any. - let lastText = ''; - for (const line of raw.split('\n')) { - const trimmed = line.trim(); - if (!trimmed) continue; - try { - const obj = JSON.parse(trimmed); - if (obj.type === 'agent' && typeof obj.text === 'string') { - lastText = obj.text; - } - } catch (e) { - // Ignore non-JSON lines - } - } - - const content = (lastText || raw || '').trim(); - if (!content) { - core.info('No agent output to reply with.'); - return; - } - - const body = `@${context.payload.comment.user.login}: ${content}`; - const { owner, repo } = context.repo; - - if (context.eventName === 'pull_request_review_comment') { - await github.rest.pulls.createReplyForReviewComment({ - owner, - repo, - pull_number: context.payload.pull_request.number, - comment_id: context.payload.comment.id, - body, - }); - } else { - await github.rest.issues.createComment({ - owner, - repo, - issue_number: context.payload.issue.number, - body, - }); - } - - name: Report Agent Error - if: failure() && steps.agent.outcome == 'failure' - uses: actions/github-script@v7 - with: - github-token: ${{ github.token }} - script: | - const body = `@${context.payload.comment.user.login}: ⚠️ I encountered an error while processing your request. Please check the [workflow run logs] for more details.`; - const { owner, repo } = context.repo; - - if (context.eventName === 'pull_request_review_comment') { - await github.rest.pulls.createReplyForReviewComment({ - owner, - repo, - pull_number: context.payload.pull_request.number, - comment_id: context.payload.comment.id, - body, - }); - } else { - await github.rest.issues.createComment({ - owner, - repo, - issue_number: context.payload.issue.number, - body, - }); - } diff --git a/.github/workflows/review-pr.yml b/.github/workflows/review-pr.yml deleted file mode 100644 index 772db569..00000000 --- a/.github/workflows/review-pr.yml +++ /dev/null @@ -1,196 +0,0 @@ -name: Auto PR Review - -on: - pull_request: - types: [opened, ready_for_review] - -jobs: - review_pr: - if: github.event.pull_request.head.repo.full_name == github.repository - runs-on: ubuntu-latest - permissions: - contents: read - pull-requests: write - issues: write - - steps: - - name: Checkout Repository - uses: actions/checkout@v4 - - - name: Review PR with Oz agent - uses: warpdotdev/oz-agent-action@v1 - env: - GH_TOKEN: ${{ github.token }} - with: - warp_api_key: ${{ secrets.WARP_API_KEY }} - skill: review-docs-pr - - - name: Post Review - uses: actions/github-script@v7 - if: always() - with: - script: | - const fs = require('fs'); - const { owner, repo } = context.repo; - const prNumber = context.payload.pull_request.number; - const commitSha = context.payload.pull_request.head.sha; - - try { - if (!fs.existsSync('review.json')) { - console.log('No review.json found. Skipping review posting.'); - return; - } - - const reviewContent = fs.readFileSync('review.json', 'utf8'); - - let review; - try { - review = JSON.parse(reviewContent); - } catch (parseError) { - core.warning(`Failed to parse review.json: ${parseError.message}`); - const sanitized = reviewContent.replace(/[\u0000-\u001F]+/g, ' '); - try { - review = JSON.parse(sanitized); - } catch (sanitizedError) { - core.setFailed(`Failed to parse review.json even after sanitizing: ${sanitizedError.message}`); - return; - } - } - - const decodeNewlines = (text) => { - if (typeof text !== 'string') return text; - return text.replace(/\r\n/g, '\n').replace(/\\n/g, '\n'); - }; - - const rawComments = Array.isArray(review.comments) ? review.comments : []; - - // Fetch valid file paths from the PR - const prFiles = await github.paginate( - github.rest.pulls.listFiles, - { owner, repo, pull_number: prNumber } - ); - const validPaths = new Set(prFiles.map(f => f.filename)); - - // Build a map of valid diff line numbers per file and side. - // GitHub's createReview API only accepts line numbers that appear - // in the PR diff; comments targeting other lines cause a 422. - const validLines = new Map(); // key: "path:side" -> Set of line numbers - for (const file of prFiles) { - if (!file.patch) continue; - const rightLines = new Set(); - const leftLines = new Set(); - let oldLine = 0; - let newLine = 0; - for (const raw of file.patch.split('\n')) { - const hunkHeader = raw.match(/^@@ -(?:\d+)(?:,\d+)? \+(\d+)(?:,\d+)? @@/); - if (hunkHeader) { - const parts = raw.match(/^@@ -(\d+)(?:,\d+)? \+(\d+)(?:,\d+)? @@/); - oldLine = parseInt(parts[1], 10); - newLine = parseInt(parts[2], 10); - continue; - } - if (raw.startsWith('+')) { - rightLines.add(newLine); - newLine++; - } else if (raw.startsWith('-')) { - leftLines.add(oldLine); - oldLine++; - } else { - // Context line — valid on both sides - rightLines.add(newLine); - leftLines.add(oldLine); - newLine++; - oldLine++; - } - } - validLines.set(`${file.filename}:RIGHT`, rightLines); - validLines.set(`${file.filename}:LEFT`, leftLines); - } - - const comments = []; - const displaced = []; // comments whose lines aren't in the diff - - for (const c of rawComments) { - if (!c || typeof c !== 'object') continue; - if (typeof c.body !== 'string' || !c.body.trim()) continue; - if (typeof c.path !== 'string' || !c.path.trim()) continue; - - // Normalize path - const normalizedPath = c.path.trim() - .replace(/^([ab]\/)*/, '') - .replace(/^\.\//, ''); - - if (!validPaths.has(normalizedPath)) { - console.log(`Skipping comment with invalid path: ${c.path} -> ${normalizedPath}`); - continue; - } - - const line = Number(c.line); - if (!Number.isInteger(line) || line <= 0) { - console.log('Skipping comment with invalid line:', c); - continue; - } - - let side = (c.side || 'RIGHT').toString().toUpperCase(); - if (side !== 'LEFT' && side !== 'RIGHT') { - console.log(`Invalid side '${c.side}', defaulting to RIGHT`); - side = 'RIGHT'; - } - - const body = decodeNewlines(c.body); - - // Validate that this line number exists in the diff for this file/side - const key = `${normalizedPath}:${side}`; - const lineSet = validLines.get(key); - if (!lineSet || !lineSet.has(line)) { - console.log(`Comment targets line ${line} (${side}) in ${normalizedPath} which is outside the diff — moving to summary.`); - displaced.push({ path: normalizedPath, line, side, body }); - continue; - } - - comments.push({ path: normalizedPath, line, side, body }); - } - - let summary = typeof review.summary === 'string' ? decodeNewlines(review.summary).trim() : ''; - - // Append displaced comments to the summary so feedback isn't lost - if (displaced.length > 0) { - const extra = displaced.map(d => - `**${d.path}** (line ${d.line}):\n${d.body}` - ).join('\n\n---\n\n'); - const header = '\n\n---\n\n**Additional comments** (targeting lines outside the diff):\n\n'; - summary = summary ? summary + header + extra : header.trimStart() + extra; - } - const hasSummary = summary.length > 0; - - if (!hasSummary && comments.length === 0) { - console.log('No valid summary or inline comments found. Skipping review posting.'); - return; - } - - const payload = { - owner, - repo, - pull_number: prNumber, - commit_id: commitSha, - event: 'COMMENT', - }; - - if (hasSummary) { - payload.body = summary; - } else { - payload.body = 'Automated review by Oz Agent'; - } - - if (comments.length > 0) { - payload.comments = comments; - } - - await github.rest.pulls.createReview(payload); - - console.log('Review posted successfully.'); - - } catch (error) { - console.error('Failed to post review:', error); - core.setFailed(`Failed to post review: ${error.message}`); - } diff --git a/AGENTS.md b/AGENTS.md index f957b6d1..53984087 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -553,7 +553,7 @@ Product feature names retain their standard capitalization. Match the exact casi - **Agent** or **Agents** (capitalized when referring to Warp's AI agents) - **Agent Mode** (not "agent mode" or "Agent-mode") - **Terminal and Agent modes** - The two distinct modes in Warp: terminal mode (for shell commands) and Agent Mode (for multi-turn agent conversations). Use "Terminal and Agent modes" on first reference; use "terminal mode" or "Agent Mode" individually in subsequent references. Do not use "agent modality" or "Agent Modality" — this was an internal name that is not user-facing. -- **Ambient Agents** (capitalized as a feature/section name; lowercase "ambient agents" only when describing the generic concept) +- **Cloud Agents** (capitalized as a product section/feature name; lowercase "cloud agents" in most contexts) - **Warp Drive** - Shared workspace for saving and organizing commands, workflows, and environment variables across your team. - **Codebase Context** - Warp indexes your Git-tracked codebase to help Agents understand your code. - **Admin Panel** - Team management surface for controlling members, roles, and billing. @@ -563,30 +563,30 @@ Product feature names retain their standard capitalization. Match the exact casi ### Oz terminology -#### Oz vs Warp -- **Warp** is the terminal and coding surface -- **Oz** is Warp's programmable agent for running and coordinating agents at scale +#### Warp Agent vs Oz +- **Warp Agent** — Warp's built-in agent harness. Use "Warp Agent" when specifically referring to the built-in harness, especially when contrasting with third-party agents (Claude Code, Codex, etc.), or when referencing the Settings label (**Settings** > **Agents** > **Warp Agent**). +- **Oz** — Warp's programmable platform for running and coordinating agents at scale - There is typically one Warp environment per user session. Oz can run many agents concurrently, across machines, repos, and teams. -#### Core Oz terms -- **Oz** - Warp's programmable agent for running and coordinating agents at scale -- **Oz agent** - A combination of agent instructions (skill or prompt), trigger (cron, webhook, manual), environment (local, cloud), profile, and host. Agents can be local or cloud, and interactive or ambient. -- **Oz cloud agent** - An Oz agent running in the cloud, from a trigger, schedule, or started from someone's local machine -- **Oz subagent** - A child Oz agent created by a parent Oz agent to parallelize or delegate work -- **Oz run** - A single execution lifecycle of an Oz agent, including actions, outputs, and logs. Always ambient and cloud-based. -- **Oz conversation** - An interactive execution lifecycle within the Warp Terminal, regardless of whether it's local or in the cloud -- **Environment** - The execution context for an Oz agent, including repo access, dependencies, secrets, compute, and runtime configuration +#### Core terms +- **agent** - A combination of agent instructions (skill or prompt), trigger (cron, webhook, manual), environment (local, cloud), profile, and host. Agents can be local or cloud. Use lowercase "agent" in most contexts; use "Warp Agent" only when referring specifically to the built-in Warp harness. +- **cloud agent** - An agent running in the cloud, from a trigger, schedule, or started from someone's local machine +- **subagent** - A child agent created by a parent agent to parallelize or delegate work +- **conversation** - An interactive execution lifecycle within the Warp Terminal, regardless of whether it's local or in the cloud +- **Oz** - Warp's programmable platform for running and coordinating agents at scale +- **Oz run** - A single execution lifecycle of an agent, including actions, outputs, and logs. Always cloud-based. +- **Environment** - The execution context for an agent, including repo access, dependencies, secrets, compute, and runtime configuration - **Oz dashboard** - The app surface to manage all Oz runs, unified across the Warp app and web -- **Oz web app** - The web app for configuring Oz agents and managing runs +- **Oz web app** - The web app for configuring agents and managing runs #### Oz CLI commands - `oz agent run` - Run a local agent - `oz agent run-cloud` - Run an adhoc cloud agent - `oz integration create` - Install integrations (Slack, Linear) - `oz environment create/list/get/update/delete` - CRUD on environments -- `oz schedule create/list/get/update/delete` - CRUD on scheduled ambient agents +- `oz schedule create/list/get/update/delete` - CRUD on scheduled cloud agents - `oz secret create/list/update/delete` - CRUD on Warp-managed secrets -- `oz run list/get` - Get info on ambient agent runs +- `oz run list/get` - Get info on cloud agent runs #### Preferred phrases - ✅ "Ask Oz to..." @@ -594,11 +594,16 @@ Product feature names retain their standard capitalization. Match the exact casi - ✅ "What would you like Oz to do?" #### Terms to avoid -- ❌ "Ozzies" → Use "Oz agents", "instances", or "Oz subagents" -- ❌ "Deploying an Oz" → Use "Deploying an Oz agent" -- ❌ "The Oz Agent" → Use "An Oz agent" or "A parent Oz agent" -- ❌ "Oz is running" → Use "An Oz agent is running" or "A run is in progress" +- ❌ "Oz agent" / "Oz agents" → Use "agent" / "agents" (or "Warp Agent" / "Warp Agents" when referring to the built-in harness) +- ❌ "Oz cloud agent" → Use "cloud agent" +- ❌ "Oz subagent" → Use "subagent" +- ❌ "Oz conversation" → Use "conversation" +- ❌ "Ozzies" → Use "agents", "instances", or "subagents" +- ❌ "Deploying an Oz" → Use "Deploying an agent" +- ❌ "The Oz Agent" → Use "the agent" or "the Warp Agent" +- ❌ "Oz is running" → Use "An agent is running" or "A run is in progress" - ❌ "AI agents" → Use "agents" (the "AI" prefix is redundant) +- ❌ "Ambient Agents" / "ambient agents" → Use "Cloud Agents" / "cloud agents" ("ambient" is no longer a product term) - ❌ "Agent Modality" or "agent modality" → Use "Terminal and Agent modes" (this was an internal name, not user-facing) ### Technical terms diff --git a/README.md b/README.md index 94963121..342f87a8 100644 --- a/README.md +++ b/README.md @@ -73,7 +73,7 @@ Read [CONTRIBUTING.md](CONTRIBUTING.md) for the full contribution flow, local se ## Agent skills -The `.warp/skills/` directory contains [Oz agent skills](https://docs.warp.dev/agent-platform/capabilities/skills) used by the Warp docs team for automated workflows, including style linting, link checking, changelog updates, and terminology syncing. The skills are included for transparency and as examples of how Oz skills can automate documentation workflows. See [`warpdotdev/oz-skills`](https://github.com/warpdotdev/oz-skills) for more examples. +The `.warp/skills/` directory contains [agent skills](https://docs.warp.dev/agent-platform/capabilities/skills) used by the Warp docs team for automated workflows, including style linting, link checking, changelog updates, and terminology syncing. The skills are included for transparency and as examples of how Oz skills can automate documentation workflows. See [`warpdotdev/oz-skills`](https://github.com/warpdotdev/oz-skills) for more examples. Some skills depend on internal Warp repositories (`warp-internal`, `warp-server`) and won't run end-to-end without access to those codebases. diff --git a/developers/agent-api-openapi.yaml b/developers/agent-api-openapi.yaml index cd2bc4b7..83f2285b 100644 --- a/developers/agent-api-openapi.yaml +++ b/developers/agent-api-openapi.yaml @@ -1,9 +1,9 @@ openapi: 3.0.0 info: - title: Oz Agent API + title: Agent API version: 1.0.0 description: | - API for creating, managing, and querying Oz cloud agent runs. + API for creating, managing, and querying cloud agent runs. These endpoints allow users to programmatically spawn agents, list runs, and retrieve detailed run information. diff --git a/package-lock.json b/package-lock.json index fc85a379..e1237593 100644 --- a/package-lock.json +++ b/package-lock.json @@ -8232,9 +8232,9 @@ "license": "MIT" }, "node_modules/devalue": { - "version": "5.7.1", - "resolved": "https://registry.npmjs.org/devalue/-/devalue-5.7.1.tgz", - "integrity": "sha512-MUbZ586EgQqdRnC4yDrlod3BEdyvE4TapGYHMW2CiaW+KkkFmWEFqBUaLltEZCGi0iFXCEjRF0OjF0DV2QHjOA==", + "version": "5.8.1", + "resolved": "https://registry.npmjs.org/devalue/-/devalue-5.8.1.tgz", + "integrity": "sha512-4CXDYRBGqN+57wVJkuXBYmpAVUSg3L6JAQa/DFqm238G73E1wuyc/JhGQJzN7vUf/CMphYau2zXbfWzDR5aTEw==", "license": "MIT" }, "node_modules/devlop": { @@ -8881,9 +8881,9 @@ "license": "BSD-3-Clause" }, "node_modules/fast-xml-builder": { - "version": "1.1.5", - "resolved": "https://registry.npmjs.org/fast-xml-builder/-/fast-xml-builder-1.1.5.tgz", - "integrity": "sha512-4TJn/8FKLeslLAH3dnohXqE3QSoxkhvaMzepOIZytwJXZO69Bfz0HBdDHzOTOon6G59Zrk6VQ2bEiv1t61rfkA==", + "version": "1.2.0", + "resolved": "https://registry.npmjs.org/fast-xml-builder/-/fast-xml-builder-1.2.0.tgz", + "integrity": "sha512-00aAWieqff+ZJhsXA4g1g7M8k+7AYoMUUHF+/zFb5U6Uv/P0Vl4QZo84/IcufzYalLuEj9928bXN9PbbFzMF0Q==", "funding": [ { "type": "github", @@ -8892,7 +8892,8 @@ ], "license": "MIT", "dependencies": { - "path-expression-matcher": "^1.1.3" + "path-expression-matcher": "^1.5.0", + "xml-naming": "^0.1.0" } }, "node_modules/fast-xml-parser": { @@ -17292,6 +17293,21 @@ "url": "https://github.com/sponsors/sindresorhus" } }, + "node_modules/xml-naming": { + "version": "0.1.0", + "resolved": "https://registry.npmjs.org/xml-naming/-/xml-naming-0.1.0.tgz", + "integrity": "sha512-k8KO9hrMyNk6tUWqUfkTEZbezRRpONVOzUTnc97VnCvyj6Tf9lyUR9EDAIeiVLv56jsMcoXEwjW8Kv5yPY52lw==", + "funding": [ + { + "type": "github", + "url": "https://github.com/sponsors/NaturalIntelligence" + } + ], + "license": "MIT", + "engines": { + "node": ">=16.0.0" + } + }, "node_modules/xxhash-wasm": { "version": "1.1.0", "resolved": "https://registry.npmjs.org/xxhash-wasm/-/xxhash-wasm-1.1.0.tgz", diff --git a/scripts/generate-og-api.mjs b/scripts/generate-og-api.mjs index 984d63fc..87469db7 100644 --- a/scripts/generate-og-api.mjs +++ b/scripts/generate-og-api.mjs @@ -45,7 +45,7 @@ const svg = ` - Oz Agent API Reference + Agent API Reference Create and manage cloud agent runs, schedules, and more. diff --git a/src/content/docs/agent-platform/agent-memory/index.mdx b/src/content/docs/agent-platform/agent-memory/index.mdx index f9b5b82c..2701051d 100644 --- a/src/content/docs/agent-platform/agent-memory/index.mdx +++ b/src/content/docs/agent-platform/agent-memory/index.mdx @@ -18,8 +18,8 @@ Memory creation and retrieval are asynchronous and run in the background, so the ## Key features -* **Cross-harness memory** — One memory layer shared across the Warp Agent, Claude Code, Codex, and other harnesses as they're added. Third-party harnesses are covered when they run as Oz cloud agents. -* **Both local and cloud agents** — Supports interactive local agents in Warp and background Oz cloud agents. +* **Cross-harness memory** — One memory layer shared across the Warp Agent, Claude Code, Codex, and other harnesses as they're added. Third-party harnesses are covered when they run as cloud agents. +* **Both local and cloud agents** — Supports interactive local agents in Warp and background cloud agents. * **Asynchronous by design** — Memory creation runs after a conversation ends. Retrieval runs in the background during a run. Neither consumes tokens or adds latency to the active task. * **Automatic memory from conversations** — When a conversation ends, Oz extracts durable facts, learnings, and outcomes and writes them as memories. New knowledge merges with existing memories or supersedes them on conflict. * **Agent-scoped, shareable stores** — By default, each agent has its own memory store. Stores can also be shared across multiple agents, or across an entire team, when the same knowledge should travel with the work. @@ -34,8 +34,8 @@ Memory creation and retrieval are asynchronous and run in the background, so the Agent Memory is part of Oz. Storage, memory creation, and retrieval all run on the same Oz instance that hosts your agents — either Warp-hosted Oz (the default) or a [self-hosted Oz](/agent-platform/cloud-agents/self-hosting/) instance that your team operates inside its own perimeter. The same memory is accessible from any agent you run on Oz: * The local Warp Agent. -* Oz cloud agents triggered from the CLI, web app, schedules, or integrations. -* Third-party harnesses running as Oz cloud agents — Claude Code, Codex, and others as they're added. (Running third-party harnesses locally isn't supported during the research preview.) +* Cloud agents triggered from the CLI, web app, schedules, or integrations. +* Third-party harnesses running as cloud agents — Claude Code, Codex, and others as they're added. (Running third-party harnesses locally isn't supported during the research preview.) Memory stays bound to its owner (a user or a team), independent of which harness reads or writes. diff --git a/src/content/docs/agent-platform/capabilities/agent-notifications.mdx b/src/content/docs/agent-platform/capabilities/agent-notifications.mdx index 15f931e8..b2859487 100644 --- a/src/content/docs/agent-platform/capabilities/agent-notifications.mdx +++ b/src/content/docs/agent-platform/capabilities/agent-notifications.mdx @@ -77,14 +77,14 @@ Desktop notifications require system permissions. If you're not receiving them, Agent notifications currently work with: -* **Oz agent** - supported out of the box. No setup required. +* **Warp Agent** - supported out of the box. No setup required. * **Claude Code** - full support via notification plugin. * **Codex** - full support via native Codex configuration. * **OpenCode** - full support via notification plugin. ## Setting up notifications -For the **Oz agent**, notifications work out of the box — no setup needed. +For the **Warp Agent**, notifications work out of the box — no setup needed. For **third-party CLI agents**, each agent requires a one-time setup. The process varies by agent: diff --git a/src/content/docs/agent-platform/capabilities/agent-profiles-permissions.mdx b/src/content/docs/agent-platform/capabilities/agent-profiles-permissions.mdx index c93c436f..d7da4531 100644 --- a/src/content/docs/agent-platform/capabilities/agent-profiles-permissions.mdx +++ b/src/content/docs/agent-platform/capabilities/agent-profiles-permissions.mdx @@ -6,6 +6,8 @@ description: >- --- import { Tabs, TabItem } from '@astrojs/starlight/components'; +Agent Profiles let you configure how Warp's agents behave in different situations, including autonomy level, base model, tool access, and command permissions. Create multiple profiles for different workflows, control which commands run automatically, and set MCP server access rules per profile. + ## Agent Profiles Agent Profiles let you configure how your Agent behaves in different situations. Each profile defines the Agent's autonomy, base models, and tool access. You can create multiple profiles and edit them directly in **Settings** > **Agents** > **Profiles**. diff --git a/src/content/docs/agent-platform/capabilities/codebase-context.mdx b/src/content/docs/agent-platform/capabilities/codebase-context.mdx index 03b7b0f2..da9351eb 100644 --- a/src/content/docs/agent-platform/capabilities/codebase-context.mdx +++ b/src/content/docs/agent-platform/capabilities/codebase-context.mdx @@ -121,7 +121,7 @@ Files excluded by ignore rules **do not** count toward your codebase's file limi ## Codebase Context in cloud agent runs -Codebase Context is available in all Oz cloud agent runs — including runs triggered from the CLI, API/SDK, integrations (Slack, Linear, GitHub Actions), and schedules — as long as Codebase Context is enabled for your account. +Codebase Context is available in all cloud agent runs — including runs triggered from the CLI, API/SDK, integrations (Slack, Linear, GitHub Actions), and schedules — as long as Codebase Context is enabled for your account. **No additional configuration is needed.** If Codebase Context is enabled, cloud agents use it automatically. diff --git a/src/content/docs/agent-platform/capabilities/full-terminal-use.mdx b/src/content/docs/agent-platform/capabilities/full-terminal-use.mdx index cd2f8659..3d655e7f 100644 --- a/src/content/docs/agent-platform/capabilities/full-terminal-use.mdx +++ b/src/content/docs/agent-platform/capabilities/full-terminal-use.mdx @@ -7,7 +7,7 @@ description: >- import { Tabs, TabItem } from '@astrojs/starlight/components'; import VideoEmbed from '@components/VideoEmbed.astro'; -Full Terminal Use lets Warp's agent operate directly inside interactive terminal applications, such as database shells, debuggers, text editors, long-running servers, and more. +Full Terminal Use lets Warp's agent operate directly inside interactive terminal applications like database shells, debuggers, text editors, and long-running servers. The agent can see the live terminal buffer, write commands, respond to prompts, and hand control back to you at any time. The agent can see the live terminal buffer (terminal state), write to the PTY to run commands, respond to prompts, and continue working inside the running process while you stay in control. diff --git a/src/content/docs/agent-platform/capabilities/index.mdx b/src/content/docs/agent-platform/capabilities/index.mdx index 242e05b5..76c6459d 100644 --- a/src/content/docs/agent-platform/capabilities/index.mdx +++ b/src/content/docs/agent-platform/capabilities/index.mdx @@ -5,9 +5,7 @@ description: >- what context they have access to, and how they execute tasks. --- -These capabilities are the foundational building blocks that define how agents operate. These include the context sources agents can access, the rules that guide their behavior, and the tools they can use. - -Understanding these capabilities helps you get the most out of agents by configuring them to match your workflows and preferences. +Agent capabilities are the core building blocks that define how Warp's agents operate, including the context sources agents can access, the rules that guide their behavior, the tools they can use, and the models they run on. Configure these capabilities to match your workflows and preferences. ## Capabilities in this section diff --git a/src/content/docs/agent-platform/capabilities/model-choice.mdx b/src/content/docs/agent-platform/capabilities/model-choice.mdx index 95e14e6c..1e8d3f21 100644 --- a/src/content/docs/agent-platform/capabilities/model-choice.mdx +++ b/src/content/docs/agent-platform/capabilities/model-choice.mdx @@ -7,6 +7,8 @@ description: >- auto-select the best model). --- +Warp lets you choose from a curated set of large language models to power your agents, or let Warp auto-select the best model for each task. Models from OpenAI, Anthropic, Google, and open source providers are available, with configurable reasoning levels and per-profile defaults. + ## Available models Warp lets you choose from a curated set of Large Language Models (LLMs) to power your Agentic Development Environment. @@ -80,7 +82,6 @@ Warp also supports leading open source models hosted via Fireworks AI, so you ca | Model | `model_id` | | --- | --- | -| GLM 5 | `glm-5-fireworks` | | GLM 5.1 | `glm-5.1-fireworks` | | Kimi K2.5 | `kimi-k25-fireworks` | | Kimi K2.6 | `kimi-k26-fireworks` | diff --git a/src/content/docs/agent-platform/capabilities/slash-commands.mdx b/src/content/docs/agent-platform/capabilities/slash-commands.mdx index e3a2d51d..3f0920c4 100644 --- a/src/content/docs/agent-platform/capabilities/slash-commands.mdx +++ b/src/content/docs/agent-platform/capabilities/slash-commands.mdx @@ -5,7 +5,7 @@ description: >- built-in actions or saved prompts without leaving the input field. --- -When using Agent Mode or Auto-Detection Mode, typing `/` in the input field opens the Slash Commands menu. +Slash Commands are quick actions and saved prompts you can invoke by typing `/` in Agent Mode or Auto-Detection Mode. They provide instant access to built-in actions like starting conversations, creating environments, switching models, and running saved prompts from Warp Drive.
![Slash Commands menu](../../../../assets/agent-platform/slash-commands-menu.png) diff --git a/src/content/docs/agent-platform/capabilities/task-lists.mdx b/src/content/docs/agent-platform/capabilities/task-lists.mdx index 06c69128..effdbfb4 100644 --- a/src/content/docs/agent-platform/capabilities/task-lists.mdx +++ b/src/content/docs/agent-platform/capabilities/task-lists.mdx @@ -6,9 +6,7 @@ description: >- time. --- -The Agent can automatically break down complex requests into clear, trackable steps in the form of a task list with to-do items.\ -\ -When you make a sufficiently complex request that requires multiple actions, the Agent will automatically create a list of steps, execute them in order, and track progress from start to finish. There’s no need to adjust settings or enable a special mode—the Agent detects and creates task lists automatically. +Task Lists let Warp's agent automatically break down complex requests into clear, trackable steps. When a request requires multiple actions, the agent creates a structured list, executes each step in order, and tracks progress in real time. No configuration is needed—the agent detects and creates task lists automatically.
![An example of a task list in progress.](../../../../assets/agent-platform/in-progress-tasklist.png) diff --git a/src/content/docs/agent-platform/cloud-agents/agents.mdx b/src/content/docs/agent-platform/cloud-agents/agents.mdx index 29f1d839..902e84c1 100644 --- a/src/content/docs/agent-platform/cloud-agents/agents.mdx +++ b/src/content/docs/agent-platform/cloud-agents/agents.mdx @@ -8,7 +8,7 @@ sidebar: label: "Agent identities" --- -An **agent identity** is a team-scoped identity that can own and execute Oz cloud agent runs. Every Warp team starts with a single default agent identity. Creating additional agent identities lets you separate workflows, scope credentials, and attribute automated runs to a specific bot account instead of a person. +An **agent identity** is a team-scoped identity that can own and execute cloud agent runs. Every Warp team starts with a single default agent identity. Creating additional agent identities lets you separate workflows, scope credentials, and attribute automated runs to a specific bot account instead of a person. Agent identities are useful when you want to: @@ -18,7 +18,7 @@ Agent identities are useful when you want to: ## How agent identities work -Each team has one default agent identity that runs receive automatically when no specific identity is chosen. You can create additional agent identities on top of that default and run as any of them. Identities are team-scoped, so every member of a team can see and use the same set of agent identities. +Each team has one default agent identity. Headless runs (such as team API key runs that don't specify an identity) execute under this default. User-triggered runs default to running as the calling user — surfaced as **Quick run** in the web app — unless you pick a specific agent identity. You can create additional agent identities on top of the default and run as any of them. Identities are team-scoped, so every member of a team can see and use the same set of agent identities. You can attach the following configuration to an agent identity: @@ -81,7 +81,7 @@ There are two ways to run a cloud agent as a specific agent identity: * **Authenticate with a key bound to the identity** - Every run started with that key executes as the bound agent identity. This is the typical path for CI pipelines and scheduled work. * **Pass `agent_identity_uid` on `POST /agent/runs`** - For one-off runs, send the agent identity's `uid` in the request body. The field is only valid for team-owned runs. -When neither path is used, runs execute under the default identity. +When neither path is used, headless runs (team API key runs without an identity) execute under the team's default agent identity. User-triggered runs (Warp app, personal API key, Slack, Linear) execute as the calling user — surfaced as **Quick run** in the web app. ## Where agent identities appear in the product diff --git a/src/content/docs/agent-platform/cloud-agents/deployment-patterns.mdx b/src/content/docs/agent-platform/cloud-agents/deployment-patterns.mdx index ecb3542d..c83a9623 100644 --- a/src/content/docs/agent-platform/cloud-agents/deployment-patterns.mdx +++ b/src/content/docs/agent-platform/cloud-agents/deployment-patterns.mdx @@ -11,7 +11,7 @@ Teams adopt cloud agents in a few repeatable ways. This page outlines the most c #### Quick mental model -Oz cloud agent setups usually have four moving parts: +Cloud agent setups usually have four moving parts: 1. **Trigger**: something happens (CI step, webhook, cron, Slack mention). 2. **Orchestration**: something decides what to run and tracks it (Oz orchestrator, GitHub Actions, your internal system). @@ -83,7 +83,7 @@ Use this when you want Oz to run agent workloads on Warp-managed infrastructure, * **First-party integrations (Slack, Linear, etc.)** that create tasks automatically from external events. * **Scheduled agents** for recurring work (cron-like automation). * **Custom triggers** from your own systems using Warp’s API/SDK. -* **On-demand cloud jobs** using CLI commands like oz agent run-cloud. +* **On-demand cloud jobs** using CLI commands like `oz agent run-cloud`. #### Example recipe: daily dead-code cleanup @@ -103,7 +103,7 @@ Use this when you want Oz to run agent workloads on Warp-managed infrastructure, If a task is naturally divisible: -* Launch multiple cloud agents via oz agent run-cloud, each with: +* Launch multiple cloud agents via `oz agent run-cloud`, each with: * A shard of the repo (directory/module ownership) * A shard of the prompt (one responsibility) * Aggregate results (PRs, notes, plans) in whatever system you prefer. diff --git a/src/content/docs/agent-platform/cloud-agents/environments.mdx b/src/content/docs/agent-platform/cloud-agents/environments.mdx index a36a971f..ee398826 100644 --- a/src/content/docs/agent-platform/cloud-agents/environments.mdx +++ b/src/content/docs/agent-platform/cloud-agents/environments.mdx @@ -66,7 +66,7 @@ Components in the execution flow: 6. **Outputs** – The run produces PRs, messages, reports, or transcripts :::note -**Local agent** runs (using `oz agent run`) don't require an environment. These runs use your current machine's setup. Environments are required for **automated platform** runs like Oz cloud agents and integrations +**Local agent** runs (using `oz agent run`) don't require an environment. These runs use your current machine's setup. Environments are required for **automated platform** runs like cloud agents and integrations ::: ### Hosts and environments diff --git a/src/content/docs/agent-platform/cloud-agents/faqs.mdx b/src/content/docs/agent-platform/cloud-agents/faqs.mdx index 265a84f7..3d367628 100644 --- a/src/content/docs/agent-platform/cloud-agents/faqs.mdx +++ b/src/content/docs/agent-platform/cloud-agents/faqs.mdx @@ -47,7 +47,7 @@ If you're not happy with where it landed, you can take over to finish the task. ### Do cloud agents have access to Codebase Context and indexing? -Yes. [Codebase Context](/agent-platform/capabilities/codebase-context/) is enabled for all Oz cloud agent runs, as long as Codebase Context is enabled for your account. This includes runs triggered from the CLI, API/SDK, integrations (Slack, Linear, GitHub Actions), and schedules. No additional configuration is needed — if Codebase Context is enabled, cloud agents use it automatically. +Yes. [Codebase Context](/agent-platform/capabilities/codebase-context/) is enabled for all cloud agent runs, as long as Codebase Context is enabled for your account. This includes runs triggered from the CLI, API/SDK, integrations (Slack, Linear, GitHub Actions), and schedules. No additional configuration is needed — if Codebase Context is enabled, cloud agents use it automatically. ### Can I access a shell inside a cloud agent environment? Are there limitations (Docker, Playwright, etc.)? diff --git a/src/content/docs/agent-platform/cloud-agents/harnesses/index.mdx b/src/content/docs/agent-platform/cloud-agents/harnesses/index.mdx index 91020cb4..b7e00642 100644 --- a/src/content/docs/agent-platform/cloud-agents/harnesses/index.mdx +++ b/src/content/docs/agent-platform/cloud-agents/harnesses/index.mdx @@ -1,7 +1,7 @@ --- title: Harnesses in Oz description: >- - Run Claude Code or Codex as Oz cloud agents. Both inherit the same triggers, + Run Claude Code or Codex as cloud agents. Both inherit the same triggers, environments, secrets, and observability as Warp Agent. sidebar: label: "Overview" diff --git a/src/content/docs/agent-platform/cloud-agents/integrations/azure-devops.mdx b/src/content/docs/agent-platform/cloud-agents/integrations/azure-devops.mdx index a76169d5..4ea16bc1 100644 --- a/src/content/docs/agent-platform/cloud-agents/integrations/azure-devops.mdx +++ b/src/content/docs/agent-platform/cloud-agents/integrations/azure-devops.mdx @@ -3,11 +3,11 @@ title: Azure DevOps integration sidebar: label: "Azure DevOps" description: >- - Connect Oz cloud agents to Azure DevOps repos using personal access tokens + Connect cloud agents to Azure DevOps repos using personal access tokens and Warp-managed secrets. --- -Oz cloud agents work with any Git repository, including those hosted on Azure DevOps. A native Azure DevOps integration is not yet available, but you can grant agents access to your repositories using a personal access token and Warp-managed secrets. Once configured, your environment works with any Oz trigger—Slack, Linear, schedules, or the CLI. +Cloud agents work with any Git repository, including those hosted on Azure DevOps. A native Azure DevOps integration is not yet available, but you can grant agents access to your repositories using a personal access token and Warp-managed secrets. Once configured, your environment works with any Oz trigger—Slack, Linear, schedules, or the CLI. This page explains how to generate an Azure DevOps personal access token, store it securely, and configure a cloud agent environment that clones your repository at runtime. diff --git a/src/content/docs/agent-platform/cloud-agents/integrations/bitbucket.mdx b/src/content/docs/agent-platform/cloud-agents/integrations/bitbucket.mdx index 300f4d19..2f02af4d 100644 --- a/src/content/docs/agent-platform/cloud-agents/integrations/bitbucket.mdx +++ b/src/content/docs/agent-platform/cloud-agents/integrations/bitbucket.mdx @@ -3,11 +3,11 @@ title: Bitbucket integration sidebar: label: "Bitbucket" description: >- - Connect Oz cloud agents to Bitbucket repos using access tokens and + Connect cloud agents to Bitbucket repos using access tokens and Warp-managed secrets. --- -Oz cloud agents work with any Git repository, including those hosted on Bitbucket. Unlike GitHub, Bitbucket does not have a native Warp integration, but you can grant agents access to your Bitbucket repositories using an access token and Warp-managed secrets. Once configured, your environment works with any Oz trigger—Slack, Linear, schedules, or the CLI. +Cloud agents work with any Git repository, including those hosted on Bitbucket. Unlike GitHub, Bitbucket does not have a native Warp integration, but you can grant agents access to your Bitbucket repositories using an access token and Warp-managed secrets. Once configured, your environment works with any Oz trigger—Slack, Linear, schedules, or the CLI. This page explains how to generate a Bitbucket access token, store it securely, and configure a cloud agent environment that clones your repository at runtime. diff --git a/src/content/docs/agent-platform/cloud-agents/integrations/cloud-providers.mdx b/src/content/docs/agent-platform/cloud-agents/integrations/cloud-providers.mdx index b3c99cef..f19a2840 100644 --- a/src/content/docs/agent-platform/cloud-agents/integrations/cloud-providers.mdx +++ b/src/content/docs/agent-platform/cloud-agents/integrations/cloud-providers.mdx @@ -1,16 +1,12 @@ --- title: Cloud Providers (Preview) description: >- - Connect Oz cloud agents to your AWS and GCP services. + Connect cloud agents to your AWS and GCP services. sidebar: label: "AWS, GCP, and other cloud providers" --- -Oz cloud agents can securely access cloud providers using short-lived OpenID Connect credentials. - -This page explains how to configure a cloud agent environment to automatically authenticate to your -cloud provider. Oz has built-in support for AWS and GCP, and can work with any provider that -supports OIDC tokens. +Cloud agents can securely access AWS, GCP, and other cloud providers using short-lived OpenID Connect (OIDC) credentials. Configure your cloud agent environment to automatically authenticate to your cloud provider without storing long-lived keys, using Warp's built-in OIDC federation support. --- @@ -119,7 +115,7 @@ To allow multiple specific principals, use a list of subjects: ... ``` -4. Click **Next** and add permissions policies. These policies determine what Oz agents can access +4. Click **Next** and add permissions policies. These policies determine what agents can access in your AWS account. 5. Click **Next** and enter a role name and optional description. 6. Click **Create role**, then open the role and note down the role ARN. This will be of the form `arn:aws:iam:::role/`. @@ -128,7 +124,7 @@ To allow multiple specific principals, use a list of subjects: ### Step 3: Enable AWS federation in your cloud agent environment -Finally, configure the Oz cloud agent environment to use your new AWS role. +Finally, configure the cloud agent environment to use your new AWS role. 1. Open the Oz web app at [https://oz.warp.dev](https://oz.warp.dev). 2. Create or edit an environment. See [Environments](/agent-platform/cloud-agents/oz-web-app/#environments) for instructions. @@ -139,7 +135,7 @@ Finally, configure the Oz cloud agent environment to use your new AWS role. Currently, AWS federation can only be configured in the Oz web app, not the CLI. ::: -Oz agents running in this environment will now automatically assume the configured role when using +Agents running in this environment will now automatically assume the configured role when using the `aws` CLI or a compatible SDK. :::note @@ -191,16 +187,16 @@ Replace `` with the UID of your Warp team. This is the last component panel URL is `https://app.warp.dev/admin/abc123def456`, your team UID would be `abc123def456`. :::caution -If you do not set an attribute condition, then _any_ Oz agent will be able to use your Workload -Identity Federation provider, even if they do not belong to your team. +If you do not set an attribute condition, then _any cloud agent_ will be able to use your Workload +Identity Federation provider, even if it does not belong to your team. ::: ### Step 2: Configure IAM policies -You will need to configure IAM policies in GCP that allow Oz agents in the Workload Identity +You will need to configure IAM policies in GCP that allow agents in the Workload Identity Federation pool access to resources. -To give all Oz agents on your team read-only access to all Compute Engine resources in a project, +To give all agents on your team read-only access to all Compute Engine resources in a project, for example, you would run: ```bash @@ -214,7 +210,7 @@ for the full syntax supported. ### Step 3: Enable Workload Identity Federation in your cloud agent environment -Finally, configure the Oz cloud agent environment to use your Workload Identity Federation provider. +Finally, configure the cloud agent environment to use your Workload Identity Federation provider. 1. Open the Oz web app at [https://oz.warp.dev](https://oz.warp.dev). 2. Create or edit an environment. See [Environments](/agent-platform/cloud-agents/oz-web-app/#environments) for instructions. @@ -225,7 +221,7 @@ Finally, configure the Oz cloud agent environment to use your Workload Identity Currently, Workload Identity Federation can only be configured in the Oz web app, not the CLI. ::: -Oz agents running in this environment will now automatically configure +Agents running in this environment will now automatically configure [Application Default Credentials](https://docs.cloud.google.com/docs/authentication/application-default-credentials) to use the configured pool. Both the `GOOGLE_APPLICATION_CREDENTIALS` and `CLOUDSDK_AUTH_CREDENTIAL_FILE_OVERRIDE` environment variables are set, so both the `gcloud` CLI and official Google SDKs will use the Oz @@ -246,7 +242,7 @@ oz federate issue-token --audience your-provider.com --output-format json ``` Optionally, add `--duration ` to customize the token validity. This cannot exceed the -maximum runtime of an Oz agent. +maximum runtime of an agent. You may then exchange this token for provider-specific credentials. @@ -262,7 +258,7 @@ such as `https://iam.googleapis.com/projects//locations/global/w ### Subject (`sub`) -The `sub` claim is set to the identity that an Oz agent is executing as. This will either be a +The `sub` claim is set to the identity that an agent is executing as. This will either be a Warp user ID or an autogenerated account ID for team-scoped agent runs. By default, the `sub` claim uses the format `:`: @@ -313,7 +309,7 @@ list only ever contains a single value. ### Oz run -The following claims are derived from an Oz agent run: +The following claims are derived from an agent run: * `run_id`: the unique identifier for the individual run. This is not suitable for configuring access, but is useful to log for debugging. @@ -324,7 +320,7 @@ The following claims are derived from an Oz agent run: ### Example token -The following OIDC token references an Oz agent running as a specific Warp user: +The following OIDC token references an agent running as a specific Warp user: ```json // JWT Header diff --git a/src/content/docs/agent-platform/cloud-agents/integrations/demo-issue-triage-bot.mdx b/src/content/docs/agent-platform/cloud-agents/integrations/demo-issue-triage-bot.mdx index 53d009b1..1fa8e695 100644 --- a/src/content/docs/agent-platform/cloud-agents/integrations/demo-issue-triage-bot.mdx +++ b/src/content/docs/agent-platform/cloud-agents/integrations/demo-issue-triage-bot.mdx @@ -8,6 +8,8 @@ sidebar: --- import VideoEmbed from '@components/VideoEmbed.astro'; +This demo shows how to trigger Warp's coding agent from a GitHub Action to automate bug report handling. The agent evaluates whether a report is actionable, requests missing details when needed, and escalates directly into a draft pull request when the issue is ready for a fix. + :::note diff --git a/src/content/docs/agent-platform/cloud-agents/integrations/github-actions.mdx b/src/content/docs/agent-platform/cloud-agents/integrations/github-actions.mdx index 2b89bbdb..9bf7f2d7 100644 --- a/src/content/docs/agent-platform/cloud-agents/integrations/github-actions.mdx +++ b/src/content/docs/agent-platform/cloud-agents/integrations/github-actions.mdx @@ -1,12 +1,12 @@ --- title: GitHub Actions description: >- - Run Oz agents in GitHub Actions to automate code review, issue triage, and + Run agents in GitHub Actions to automate code review, issue triage, and CI fixes. --- import VideoEmbed from '@components/VideoEmbed.astro'; -Run Oz agents directly in your GitHub Actions workflows using `oz-agent-action`. The agent integrates seamlessly into your CI pipeline, automating tasks like code review, issue triage, bug fixing, and maintenance using your repository context and GitHub permissions. This page covers how the integration works, how to set it up, and common automation patterns for development teams. +Run agents directly in your GitHub Actions workflows using `oz-agent-action`. The agent integrates seamlessly into your CI pipeline, automating tasks like code review, issue triage, bug fixing, and maintenance using your repository context and GitHub permissions. This page covers how the integration works, how to set it up, and common automation patterns for development teams. :::note **Getting started?** See the [GitHub Actions quickstart](/agent-platform/cloud-agents/integrations/quickstart-github-actions/) to set up your first workflow, or visit the [oz-agent-action repository](https://github.com/warpdotdev/oz-agent-action) for detailed setup instructions and ready-to-use workflow templates. @@ -29,7 +29,7 @@ In this demo The `oz-agent-action` is a GitHub Action that wraps the Oz CLI and: -* Runs an Oz agent inside an Actions job +* Runs an agent inside an Actions job * Caches package installation for faster builds * Captures the agent's output for use in subsequent workflow steps * Lets you pass workflow context, event data, and previous step outputs into the agent prompt @@ -39,7 +39,7 @@ The `oz-agent-action` is a GitHub Action that wraps the Oz CLI and: ### Requirements -To use Oz agents in GitHub Actions, you need: +To use agents in GitHub Actions, you need: * A [**Warp API Key**](/reference/cli/#generating-api-keys) stored as a [GitHub secret](https://docs.github.com/en/actions/security-for-github-actions/security-guides/using-secrets-in-github-actions) — this authenticates the agent with Warp * Workflow permissions that match your intended actions (for example, `pull-requests: write` if the agent should commit or comment on PRs) — the agent performs actions on your behalf using the GitHub token available to the workflow @@ -49,7 +49,7 @@ To use Oz agents in GitHub Actions, you need: ### Using Skills -Skills provide reusable instructions for Oz agents. You can use pre-built skills from the [oz-skills repository](https://github.com/warpdotdev/oz-skills) or create custom [skills](/agent-platform/capabilities/skills/) for your specific workflows. Skills can also be deployed as [standalone agents](/agent-platform/capabilities/skills/#skills-as-agents) to run on a schedule or in response to events. +Skills provide reusable instructions for agents. You can use pre-built skills from the [oz-skills repository](https://github.com/warpdotdev/oz-skills) or create custom [skills](/agent-platform/capabilities/skills/) for your specific workflows. Skills can also be deployed as [standalone agents](/agent-platform/capabilities/skills/#skills-as-agents) to run on a schedule or in response to events. #### How to use skills diff --git a/src/content/docs/agent-platform/cloud-agents/integrations/gitlab.mdx b/src/content/docs/agent-platform/cloud-agents/integrations/gitlab.mdx index aa6fc21b..6f9dcc65 100644 --- a/src/content/docs/agent-platform/cloud-agents/integrations/gitlab.mdx +++ b/src/content/docs/agent-platform/cloud-agents/integrations/gitlab.mdx @@ -3,11 +3,11 @@ title: GitLab integration sidebar: label: "GitLab" description: >- - Connect Oz cloud agents to GitLab repos using personal access tokens and + Connect cloud agents to GitLab repos using personal access tokens and Warp-managed secrets. --- -Oz cloud agents work with any Git repository, including those hosted on GitLab. Unlike GitHub, GitLab does not have a native Warp integration, but you can grant agents access to your GitLab repositories using a personal access token and Warp-managed secrets. Once configured, your environment works with any Oz trigger—Slack, Linear, schedules, or the CLI. +Cloud agents work with any Git repository, including those hosted on GitLab. Unlike GitHub, GitLab does not have a native Warp integration, but you can grant agents access to your GitLab repositories using a personal access token and Warp-managed secrets. Once configured, your environment works with any Oz trigger—Slack, Linear, schedules, or the CLI. This page explains how to generate a GitLab personal access token, store it securely, and configure a cloud agent environment that clones your repository at runtime. diff --git a/src/content/docs/agent-platform/cloud-agents/integrations/linear.mdx b/src/content/docs/agent-platform/cloud-agents/integrations/linear.mdx index ecd2f177..3f112fdf 100644 --- a/src/content/docs/agent-platform/cloud-agents/integrations/linear.mdx +++ b/src/content/docs/agent-platform/cloud-agents/integrations/linear.mdx @@ -3,7 +3,7 @@ title: Linear integration sidebar: label: "Linear" description: >- - Automate Linear issues with Oz agents that run code in the cloud and create + Automate Linear issues with agents that run code in the cloud and create pull requests on your behalf. --- import VideoEmbed from '@components/VideoEmbed.astro'; diff --git a/src/content/docs/agent-platform/cloud-agents/integrations/quickstart-github-actions.mdx b/src/content/docs/agent-platform/cloud-agents/integrations/quickstart-github-actions.mdx index 82e28bb3..4d2ebc38 100644 --- a/src/content/docs/agent-platform/cloud-agents/integrations/quickstart-github-actions.mdx +++ b/src/content/docs/agent-platform/cloud-agents/integrations/quickstart-github-actions.mdx @@ -1,13 +1,13 @@ --- title: GitHub Actions quickstart description: >- - Set up your first Oz agent in GitHub Actions in ~10 minutes. Run agents as + Set up your first agent in GitHub Actions in ~10 minutes. Run agents as workflow steps to automate code review and issue triage. sidebar: label: "Quickstart" --- -Add Oz agents to your GitHub Actions workflows with [`oz-agent-action`](https://github.com/warpdotdev/oz-agent-action). This quickstart walks you through setting up your first GitHub Actions integration: a PR review workflow that automatically analyzes pull requests and posts inline review comments. +Add agents to your GitHub Actions workflows with [`oz-agent-action`](https://github.com/warpdotdev/oz-agent-action). This quickstart walks you through setting up your first GitHub Actions integration: a PR review workflow that automatically analyzes pull requests and posts inline review comments. --- @@ -30,7 +30,7 @@ Store your Warp API key as a GitHub Actions secret so workflows can authenticate ## 2. Create the workflow file -This workflow triggers an Oz agent whenever a PR is opened or marked ready for review. The agent reviews the diff and posts inline comments. +This workflow triggers an agent whenever a PR is opened or marked ready for review. The agent reviews the diff and posts inline comments. Create `.github/workflows/oz-pr-review.yml` in your repository with the following content: diff --git a/src/content/docs/agent-platform/cloud-agents/integrations/quickstart.mdx b/src/content/docs/agent-platform/cloud-agents/integrations/quickstart.mdx index b411e5f2..37c0ea76 100644 --- a/src/content/docs/agent-platform/cloud-agents/integrations/quickstart.mdx +++ b/src/content/docs/agent-platform/cloud-agents/integrations/quickstart.mdx @@ -1,7 +1,7 @@ --- title: Integrations quickstart description: >- - Trigger your first Oz agent from Slack in ~15 minutes and get results + Trigger your first agent from Slack in ~15 minutes and get results in-thread. sidebar: label: "Quickstart" @@ -18,7 +18,7 @@ Oz integrations let you trigger cloud agents directly from the tools your team a ## Prerequisites * **Eligible plan** - The Slack integration requires a Warp team on Build, Max, or Business plan with at least 20 credits available. See [Access, Billing, and Identity](/agent-platform/cloud-agents/team-access-billing-and-identity/). -* **An Oz cloud environment** - Agents run inside a configured environment that includes repos and other dependencies. If you don't have one yet, follow the [Cloud Agents Quickstart](/agent-platform/cloud-agents/quickstart/) or run `/create-environment` in Warp. +* **A cloud environment** - Agents run inside a configured environment that includes repos and other dependencies. If you don't have one yet, follow the [Cloud Agents Quickstart](/agent-platform/cloud-agents/quickstart/) or run `/create-environment` in Warp. * **GitHub authorization** - Warp needs access to your repos to clone code and open PRs. You'll be prompted to authorize the Warp GitHub app when you first create the integration. --- @@ -77,5 +77,5 @@ When the task is complete, Oz posts a summary back to the original Slack thread. ## Next steps * **Customize agent behavior** - Use a [skill](/agent-platform/cloud-agents/skills-as-agents/) as the base prompt for your integration to give Oz consistent, reusable instructions across every run. -* **Trigger agents programmatically** - Use the [API & SDK](/reference/api-and-sdk/) to build custom automations and integrations on top of Oz agents. +* **Trigger agents programmatically** - Use the [API & SDK](/reference/api-and-sdk/) to build custom automations and integrations on top of agents. * **Read the full Slack reference** - [Slack](/agent-platform/cloud-agents/integrations/slack/) covers identity mapping, team access, monitoring runs, troubleshooting, and uninstall instructions. diff --git a/src/content/docs/agent-platform/cloud-agents/integrations/slack.mdx b/src/content/docs/agent-platform/cloud-agents/integrations/slack.mdx index f724666f..b37d510b 100644 --- a/src/content/docs/agent-platform/cloud-agents/integrations/slack.mdx +++ b/src/content/docs/agent-platform/cloud-agents/integrations/slack.mdx @@ -3,10 +3,12 @@ title: Slack integration sidebar: label: "Slack" description: >- - Trigger Oz agents from Slack to run cloud tasks, track progress, and create + Trigger agents from Slack to run cloud tasks, track progress, and create pull requests. --- +The Slack integration lets your team trigger cloud agents directly from Slack conversations. Tag @Oz in a message or DM the bot to start a cloud agent that clones your repos, works through the task, posts progress updates, and opens pull requests back into the same thread. + ### Overview The Slack integration lets your team trigger agents directly from conversations in Slack. When you tag **@Oz** in a message or DM the bot, Warp will start an agent in the cloud, clone the repositories defined in your environment, and begin working through the task with full context from your codebase and the Slack thread. diff --git a/src/content/docs/agent-platform/cloud-agents/overview.mdx b/src/content/docs/agent-platform/cloud-agents/overview.mdx index 243f4119..4c35494b 100644 --- a/src/content/docs/agent-platform/cloud-agents/overview.mdx +++ b/src/content/docs/agent-platform/cloud-agents/overview.mdx @@ -8,7 +8,7 @@ sidebar: --- import VideoEmbed from '@components/VideoEmbed.astro'; -Oz Cloud Agents are **cloud-connected**, **background agents** that run on the [Oz Platform](/agent-platform/cloud-agents/platform/). +Cloud agents are autonomous, background agents that run on Warp's cloud infrastructure or your own, triggered by system events, schedules, or integrations like Slack and GitHub. They execute tasks with full observability — every run is tracked, auditable, and shareable across your team. **New to cloud agents?** Start with the [Cloud agents quickstart](/agent-platform/cloud-agents/quickstart/) to run your first cloud agent in ~10 minutes. @@ -147,7 +147,7 @@ If your credit balance reaches zero, cloud agent runs will not be able to execut * [Harnesses](/agent-platform/cloud-agents/harnesses/) — pick between Warp Agent, Claude Code, and Codex for any cloud agent run. * [Agent identities](/agent-platform/cloud-agents/agents/) — team-scoped bot accounts that own and execute cloud agent runs. * [Skills as Agents](/agent-platform/cloud-agents/skills-as-agents/) — run agents based on reusable skill definitions from the CLI, web app, API, or on a schedule. -* [Oz CLI](/reference/cli/) — shows how to run Oz agents in non-interactive mode from CI, scripts, or remote machines, including auth and common commands. +* [Oz CLI](/reference/cli/) — shows how to run agents in non-interactive mode from CI, scripts, or remote machines, including auth and common commands. * [Environments](/agent-platform/cloud-agents/environments/) — explains how environments provide the runtime context (repo, image, startup commands) for agent tasks. * [Oz API and SDK](/reference/api-and-sdk/) — documents the REST API for creating, querying, and monitoring agent tasks programmatically. * [Agent Secrets](/agent-platform/cloud-agents/secrets/) — covers how to store, scope, and inject credentials into agent runs safely. diff --git a/src/content/docs/agent-platform/cloud-agents/oz-web-app.mdx b/src/content/docs/agent-platform/cloud-agents/oz-web-app.mdx index 1f1e4bd4..6d29a549 100644 --- a/src/content/docs/agent-platform/cloud-agents/oz-web-app.mdx +++ b/src/content/docs/agent-platform/cloud-agents/oz-web-app.mdx @@ -47,7 +47,7 @@ When you first sign in to the Oz web app, you'll see a guided onboarding flow th The onboarding asks "What brings you to Oz?" and offers three paths: * **Create an agent automation** — Walks you through setting up a scheduled agent, integration-triggered agent, or other automation -* **Run Oz Cloud Agents in Warp** — Opens the Warp desktop app (or takes you to the download page) to run cloud agents interactively +* **Run Cloud Agents in Warp** — Opens the Warp desktop app (or takes you to the download page) to run cloud agents interactively * **Build an app that uses agents** — Links to the [Oz Platform](/agent-platform/cloud-agents/platform/) docs for using the CLI, SDK, or API You can skip onboarding at any time to go directly to the Runs page. diff --git a/src/content/docs/agent-platform/cloud-agents/platform.mdx b/src/content/docs/agent-platform/cloud-agents/platform.mdx index 34c188b2..7b378be3 100644 --- a/src/content/docs/agent-platform/cloud-agents/platform.mdx +++ b/src/content/docs/agent-platform/cloud-agents/platform.mdx @@ -46,7 +46,7 @@ In practice: **triggers create tasks; tasks execute on a host (optionally in an ### Oz CLI -The [Oz CLI](/reference/cli/) is the **headless interface** for running Oz agents in non-interactive mode. It's commonly used in CI, scripts, and server environments where there is no interactive UI. For interactive workflows, use the [agent](/agent-platform/local-agents/overview/) embedded in Warp's desktop app. +The [Oz CLI](/reference/cli/) is the **headless interface** for running agents in non-interactive mode. It's commonly used in CI, scripts, and server environments where there is no interactive UI. For interactive workflows, use the [agent](/agent-platform/local-agents/overview/) embedded in Warp's desktop app. A key property of the CLI is that it is **cloud-connected**. Even when an agent is started on a local machine or in CI, it reports progress to Warp’s servers. This enables team visibility, session sharing (where supported), and programmatic tracking through the API. @@ -142,7 +142,7 @@ The Oz [Agent API](/reference/api-and-sdk/) is the HTTP interface to the Oz Plat * Monitor execution by listing tasks and tracking state transitions over time (for example: `QUEUED` → `INPROGRESS` → `SUCCEEDED/FAILED`). * Inspect results and provenance by fetching a task’s full details, including the original prompt, creator/source metadata, session link, and resolved agent configuration. -**Oz Agent SDKs** +**Oz SDKs** Oz provides official [Python](https://github.com/warpdotdev/oz-sdk-python) and [TypeScript SDKs](https://github.com/warpdotdev/oz-sdk-typescript) that wrap the Oz API with: @@ -217,7 +217,7 @@ Examples of context extracted by first-party integrations: #### Custom integrations -With custom integrations, you own the webhook and event-handling logic. Your system receives an event, applies any filtering or enrichment you need, and then calls the Oz API (directly or via an SDK) to create a task. The resulting task is still a full Oz agent run — observable, manageable, and auditable like any other. +With custom integrations, you own the webhook and event-handling logic. Your system receives an event, applies any filtering or enrichment you need, and then calls the Oz API (directly or via an SDK) to create a task. The resulting task is still a full cloud agent run — observable, manageable, and auditable like any other. Custom integrations are a good fit when: diff --git a/src/content/docs/agent-platform/cloud-agents/quickstart.mdx b/src/content/docs/agent-platform/cloud-agents/quickstart.mdx index 19d1b643..7cd15eb8 100644 --- a/src/content/docs/agent-platform/cloud-agents/quickstart.mdx +++ b/src/content/docs/agent-platform/cloud-agents/quickstart.mdx @@ -1,14 +1,14 @@ --- title: Cloud agents quickstart description: >- - Learn how to run your first Oz cloud agent in ~10 minutes. Cloud agents run + Learn how to run your first cloud agent in ~10 minutes. Cloud agents run in remote environments, enabling automation, scheduling, and team collaboration. sidebar: label: "Quickstart" --- -**Oz cloud agents** run in a remote environment and can be triggered from events, schedules, integrations, or manually. This enables scaling agents off your laptop, automating development tasks, and building apps on top of agents. Oz handles the orchestration, execution, and observability. +**Cloud agents** run in a remote environment and can be triggered from events, schedules, integrations, or manually. This enables scaling agents off your laptop, automating development tasks, and building apps on top of agents. Oz handles the orchestration, execution, and observability. Cloud agents can run interactively (where you steer them in real-time) or autonomously (as background tasks). Each run creates a persistent session that your team can inspect, share, and query through the Warp app, the CLI, web app, or API. @@ -35,7 +35,7 @@ New to Warp? You'll get credits to try cloud agents. You need at least 20 credit --- -## Running your first Oz cloud agent +## Running your first cloud agent _~10 minutes • Recommended for all users_ @@ -142,7 +142,7 @@ oz schedule create \ Integrations require a team on Build, Max, or Business plan. ::: -### Build automations and apps on top of Oz agents +### Build automations and apps on top of agents Use the [Oz API & SDK](/reference/api-and-sdk/) to trigger agents programmatically from your own systems and workflows. diff --git a/src/content/docs/agent-platform/cloud-agents/self-hosting/index.mdx b/src/content/docs/agent-platform/cloud-agents/self-hosting/index.mdx index 453ca100..5272fe77 100644 --- a/src/content/docs/agent-platform/cloud-agents/self-hosting/index.mdx +++ b/src/content/docs/agent-platform/cloud-agents/self-hosting/index.mdx @@ -1,19 +1,19 @@ --- title: Self-hosting overview description: >- - Run Oz cloud agents on your own infrastructure. Choose between a managed + Run cloud agents on your own infrastructure. Choose between a managed worker daemon orchestrated by Oz or unmanaged CLI-based execution you control. --- -Self-hosting lets your team run Oz cloud agent workloads on your own infrastructure instead of Warp-managed servers. You control the execution environment, compute resources, and network access. Repositories are cloned and stored only on your machines, and agents can reach services behind your VPN or firewall. +Self-hosting lets your team run cloud agent workloads on your own infrastructure instead of Warp-managed servers. You control the execution environment, compute resources, and network access. Repositories are cloned and stored only on your machines, and agents can reach services behind your VPN or firewall. **New to self-hosting?** Start with the [Self-hosting quickstart](/agent-platform/cloud-agents/self-hosting/quickstart/) to get a managed worker running on Docker in under 10 minutes. **Want a CLI-only path with no Docker requirement?** Jump straight to the [Unmanaged quickstart](/agent-platform/cloud-agents/self-hosting/unmanaged/#unmanaged-quickstart) to run `oz agent run` directly on any host. :::note -**Enterprise feature**: Self-hosted Oz agents are available exclusively to teams on an Enterprise plan. To enable self-hosting for your team, [contact sales](https://warp.dev/contact-sales). +**Enterprise feature**: Self-hosted agents are available exclusively to teams on an Enterprise plan. To enable self-hosting for your team, [contact sales](https://warp.dev/contact-sales). ::: ## Managed vs unmanaged @@ -115,7 +115,7 @@ You're responsible for executing `oz agent run` on your infrastructure — simil ## Routing runs to self-hosted workers -This section applies to **all managed backends** (Docker, Kubernetes, and Direct). Once a worker is connected, route Oz cloud agent runs to it by specifying the `--host` flag (or equivalent) with your worker ID. The `--host` value must match the `--worker-id` of a connected worker exactly. +This section applies to **all managed backends** (Docker, Kubernetes, and Direct). Once a worker is connected, route cloud agent runs to it by specifying the `--host` flag (or equivalent) with your worker ID. The `--host` value must match the `--worker-id` of a connected worker exactly. :::note Unmanaged runs don't need routing — you invoke `oz agent run` directly on the host where you want the agent to execute. Routing is only relevant for managed workers. diff --git a/src/content/docs/agent-platform/cloud-agents/self-hosting/quickstart.mdx b/src/content/docs/agent-platform/cloud-agents/self-hosting/quickstart.mdx index d96bb44c..14a27eb3 100644 --- a/src/content/docs/agent-platform/cloud-agents/self-hosting/quickstart.mdx +++ b/src/content/docs/agent-platform/cloud-agents/self-hosting/quickstart.mdx @@ -7,7 +7,7 @@ sidebar: label: "Quickstart" --- -Run your first Oz cloud agent on your own infrastructure in ~10 minutes using the managed architecture with the Docker backend — the default and fastest path to self-hosting. +Run your first cloud agent on your own infrastructure in ~10 minutes using the managed architecture with the Docker backend — the default and fastest path to self-hosting. :::note This quickstart sets up the [managed architecture](/agent-platform/cloud-agents/self-hosting/#managed-architecture), where Oz orchestrates the agent and your worker provides the compute. **Prefer a CLI-only path with no Docker requirement?** Jump to the [Unmanaged quickstart](/agent-platform/cloud-agents/self-hosting/unmanaged/#unmanaged-quickstart) to run `oz agent run` directly on any host. diff --git a/src/content/docs/agent-platform/cloud-agents/self-hosting/security-and-networking.mdx b/src/content/docs/agent-platform/cloud-agents/self-hosting/security-and-networking.mdx index 6ada0785..8533c7cd 100644 --- a/src/content/docs/agent-platform/cloud-agents/self-hosting/security-and-networking.mdx +++ b/src/content/docs/agent-platform/cloud-agents/self-hosting/security-and-networking.mdx @@ -34,7 +34,7 @@ While repositories are cloned and stored only on your infrastructure, code conte ## Network requirements -Self-hosted Oz agents **do not require any network ingress**. They require outbound (egress) access to the following services: +Self-hosted agents **do not require any network ingress**. They require outbound (egress) access to the following services: **Warp's backend (all architectures):** diff --git a/src/content/docs/agent-platform/cloud-agents/self-hosting/unmanaged.mdx b/src/content/docs/agent-platform/cloud-agents/self-hosting/unmanaged.mdx index 84a2a11f..a912561f 100644 --- a/src/content/docs/agent-platform/cloud-agents/self-hosting/unmanaged.mdx +++ b/src/content/docs/agent-platform/cloud-agents/self-hosting/unmanaged.mdx @@ -1,7 +1,7 @@ --- title: Unmanaged architecture description: >- - Run Oz agents in your existing CI, Kubernetes, or dev environments using + Run agents in your existing CI, Kubernetes, or dev environments using the oz agent run CLI with Warp tracking and observability. sidebar: label: "Unmanaged" @@ -72,7 +72,7 @@ The `--share` flag can be repeated to combine multiple sharing targets. If you a Warp maintains the [`warpdotdev/oz-agent-action`](https://github.com/warpdotdev/oz-agent-action) action for running agents in GitHub Actions. The action wraps `oz agent run` and is a drop-in for CI workflows: ```yaml -- name: Run Oz agent +- name: Run agent uses: warpdotdev/oz-agent-action@v1 # wraps `oz agent run` under the hood with: prompt: "Review the code changes on this branch" diff --git a/src/content/docs/agent-platform/cloud-agents/team-access-billing-and-identity.mdx b/src/content/docs/agent-platform/cloud-agents/team-access-billing-and-identity.mdx index 3d676612..93bde902 100644 --- a/src/content/docs/agent-platform/cloud-agents/team-access-billing-and-identity.mdx +++ b/src/content/docs/agent-platform/cloud-agents/team-access-billing-and-identity.mdx @@ -102,13 +102,13 @@ This ensures runs are scoped to what the user is allowed to see and modify, and ## Team GitHub authorization -By default, Oz cloud agents authenticate with GitHub using the personal token of the user who triggered the run. Team GitHub authorization gives you an alternative: authenticate with the **Oz by Warp** GitHub App instead, so agents can clone repositories and open pull requests without relying on any individual's token. +By default, cloud agents authenticate with GitHub using the personal token of the user who triggered the run. Team GitHub authorization gives you an alternative: authenticate with the **Oz by Warp** GitHub App instead, so agents can clone repositories and open pull requests without relying on any individual's token. This is useful for fully automated workflows that use a [team API key](/reference/cli/api-keys/), like CI/CD pipelines, scheduled agents, and SDK-triggered runs, where you want code changes attributed to the GitHub App rather than a specific person. ### How it works -When an Oz agent task is initiated with a team API key, there is no individual user to authenticate on behalf of. Instead, Warp uses tokens issued by the **Oz by Warp** GitHub App installation to authenticate directly with GitHub. +When an agent task is initiated with a team API key, there is no individual user to authenticate on behalf of. Instead, Warp uses tokens issued by the **Oz by Warp** GitHub App installation to authenticate directly with GitHub. The GitHub App token gives the agent access to the repositories included in the app installation — it can clone repos, create branches, push commits, and open pull requests. During installation, you choose whether the app can access **all repositories** or only **selected repositories** in your GitHub organization, and this controls what team API key runs can access. @@ -140,7 +140,7 @@ There are two places you may encounter this installation flow: ### How this relates to environments -An [environment](/agent-platform/cloud-agents/environments/) is a template for an Oz cloud agent's sandbox — it defines the Docker image, repos, and setup commands, but it does not carry its own GitHub permissions. The same environment can be used by different users or by team API key runs, and each will authenticate to GitHub independently. +An [environment](/agent-platform/cloud-agents/environments/) is a template for a cloud agent's sandbox — it defines the Docker image, repos, and setup commands, but it does not carry its own GitHub permissions. The same environment can be used by different users or by team API key runs, and each will authenticate to GitHub independently. The environment configuration and the **Enabled GitHub Orgs** setting in the Admin Panel serve different purposes: diff --git a/src/content/docs/agent-platform/cloud-agents/triggers/scheduled-agents-quickstart.mdx b/src/content/docs/agent-platform/cloud-agents/triggers/scheduled-agents-quickstart.mdx index 21946c90..279b7067 100644 --- a/src/content/docs/agent-platform/cloud-agents/triggers/scheduled-agents-quickstart.mdx +++ b/src/content/docs/agent-platform/cloud-agents/triggers/scheduled-agents-quickstart.mdx @@ -1,14 +1,14 @@ --- title: Scheduled Agents quickstart description: >- - Schedule an Oz cloud agent to run recurring tasks automatically — issue + Schedule a cloud agent to run recurring tasks automatically — issue triage, dependency checks, code cleanup, and more. sidebar: label: "Quickstart" --- import VideoEmbed from '@components/VideoEmbed.astro'; -Scheduled agents are Oz cloud agents that run on a recurring cron schedule, handling recurring tasks automatically without manual triggers. This guide walks you through setting up an agent that triages your GitHub bug reports every week, checks whether each issue has enough detail to investigate, and posts follow-up comments when information is missing. You'll use a prebundled skill and the Oz web app; no CLI or custom code required. +Scheduled agents are cloud agents that run on a recurring cron schedule, handling recurring tasks automatically without manual triggers. This guide walks you through setting up an agent that triages your GitHub bug reports every week, checks whether each issue has enough detail to investigate, and posts follow-up comments when information is missing. You'll use a prebundled skill and the Oz web app; no CLI or custom code required. Watch this short demo of creating and testing a scheduled agent: @@ -18,7 +18,7 @@ Watch this short demo of creating and testing a scheduled agent: ## Prerequisites * **A Warp account on an eligible plan** - Build, Max, or Business, with credits available. See [Access, Billing, and Identity](/agent-platform/cloud-agents/team-access-billing-and-identity/). -* **An Oz cloud environment** - Agents run inside a configured environment that includes repos and other dependencies. If you don't have one, follow the [Cloud Agents Quickstart](/agent-platform/cloud-agents/quickstart/) to create one first. +* **A cloud environment** - Agents run inside a configured environment that includes repos and other dependencies. If you don't have one, follow the [Cloud Agents Quickstart](/agent-platform/cloud-agents/quickstart/) to create one first. --- diff --git a/src/content/docs/agent-platform/getting-started/agents-in-warp.mdx b/src/content/docs/agent-platform/getting-started/agents-in-warp.mdx index 81548d30..9a97d156 100644 --- a/src/content/docs/agent-platform/getting-started/agents-in-warp.mdx +++ b/src/content/docs/agent-platform/getting-started/agents-in-warp.mdx @@ -1,18 +1,20 @@ --- title: Agents in Warp description: >- - Warp's Oz agents are capable collaborators that help you write code, debug + Warp's agents are capable collaborators that help you write code, debug issues, and complete terminal workflows, all from natural language prompts. --- import VideoEmbed from '@components/VideoEmbed.astro'; +Warp's agents help you write code, debug issues, and complete terminal workflows from natural language prompts. They operate with full context from your codebase, Warp Drive, and connected tools while you control their autonomy, permissions, and model choices. + -Warp includes Oz agents. These coding agents are designed to help you build, test, deploy, and debug while keeping you in control. Describe what you want to do in natural language (_you can even use your voice_), and Oz will take action using your environment, codebase, and saved context. +Warp includes powerful coding agents designed to help you build, test, deploy, and debug while keeping you in control. Describe what you want to do in natural language (_you can even use your voice_), and the agent will take action using your environment, codebase, and saved context. -## What Oz agents can do +## What agents can do -Oz agents understand your codebase and can execute tasks autonomously while keeping you in control: +Agents understand your codebase and can execute tasks autonomously while keeping you in control: * **Write and edit code** - Create new files, refactor existing code, or make changes across multiple files in your codebase * **Debug and fix errors** - Analyze stack traces, interpret error output, and apply fixes @@ -66,7 +68,7 @@ For more details, see [Agent Profiles & Permissions](/agent-platform/capabilitie ## Managing agents -You can run multiple Oz agents simultaneously in Warp. All active agents—both local conversations and cloud agent runs—are tracked in the [management view](/agent-platform/cloud-agents/managing-cloud-agents/). +You can run multiple agents simultaneously in Warp. All active agents—both local conversations and cloud agent runs—are tracked in the [management view](/agent-platform/cloud-agents/managing-cloud-agents/). Agents notify you when they need input, such as permission to run a command or approval to apply a code diff. This lets you focus on other work, knowing you'll be alerted when your attention is required. @@ -76,7 +78,7 @@ To access conversations across devices, share them with teammates, or restore pa ## Context and knowledge -Oz agents work best when they understand your codebase and workflows. Warp provides several ways to give agents the context they need: +Agents work best when they understand your codebase and workflows. Warp provides several ways to give agents the context they need: * [**Codebase Context**](/agent-platform/capabilities/codebase-context/) - Warp indexes your Git-tracked files so agents can search and understand your code * [**Rules**](/agent-platform/capabilities/rules/) - Define global and project-level guidelines that shape agent behavior @@ -88,7 +90,7 @@ Oz agents work best when they understand your codebase and workflows. Warp provi ## Third-Party CLI Agents -In addition to Warp's built-in Oz agent, Warp provides first-class support for third-party CLI coding agents like Claude Code, Codex, and OpenCode. Run any supported agent inside Warp and get rich input, code review, agent notifications, vertical tabs with agent metadata, and more. +In addition to Warp's built-in agent, Warp provides first-class support for third-party CLI coding agents like Claude Code, Codex, and OpenCode. Run any supported agent inside Warp and get rich input, code review, agent notifications, vertical tabs with agent metadata, and more. → [Learn about Third-Party CLI Agents](/agent-platform/cli-agents/overview/) @@ -96,7 +98,7 @@ In addition to Warp's built-in Oz agent, Warp provides first-class support for t ## From local to cloud -The same Oz agent capabilities that power interactive conversations in Warp also run in the cloud. Cloud agents can: +The same agent capabilities that power interactive conversations in Warp also run in the cloud. Cloud agents can: * React to events from Slack, Linear, or GitHub * Run on schedules for recurring tasks like dependency updates diff --git a/src/content/docs/agent-platform/getting-started/faqs.mdx b/src/content/docs/agent-platform/getting-started/faqs.mdx index 5c237f00..a400fed2 100644 --- a/src/content/docs/agent-platform/getting-started/faqs.mdx +++ b/src/content/docs/agent-platform/getting-started/faqs.mdx @@ -7,6 +7,8 @@ description: >- models, privacy practices, credit limits, billing, and usage guidelines. --- +Answers to frequently asked questions about Warp's agents, including supported models, data privacy, credit limits, billing, and common error messages. For billing-specific questions, see the pricing FAQs. + ## General ### What data is sent and/or stored when using Agents in Warp? diff --git a/src/content/docs/agent-platform/index.mdx b/src/content/docs/agent-platform/index.mdx index 0580760f..ee66a21e 100644 --- a/src/content/docs/agent-platform/index.mdx +++ b/src/content/docs/agent-platform/index.mdx @@ -5,7 +5,7 @@ description: >- and autonomous agents for development workflows. --- -Warp includes **Oz**, the orchestration platform for cloud agents. While Warp provides the terminal and coding surface you work in day-to-day, Oz is the underlying orchestration layer that makes running agents at scale possible. +Warp includes **Oz**, the orchestration platform that powers all of Warp's agents. Oz runs interactive agents locally inside Warp for real-time coding assistance and deploys autonomous agents in the cloud for background automation, event-driven workflows, and parallel execution across repos and teams. Warp's client is open source under [AGPL v3](https://github.com/warpdotdev/warp/blob/master/LICENSE-AGPL), so the editor and terminal that host your agents are fully auditable. See [Contributing to Warp](/support-and-community/community/contributing/) for the source and contribution flow. @@ -22,9 +22,9 @@ Oz is fully programmable—launch agents manually or build custom logic around t ## Key capabilities -* [**Local Agents**](/agent-platform/local-agents/overview/) - Interactive Oz agents embedded in Warp. Use natural language to write code, debug issues, run commands, and automate development tasks with full terminal access. +* [**Local Agents**](/agent-platform/local-agents/overview/) - Interactive agents embedded in Warp. Use natural language to write code, debug issues, run commands, and automate development tasks with full terminal access. * [**Third-Party CLI Agents**](/agent-platform/cli-agents/overview/) - Use Claude Code, Codex, OpenCode, and other CLI coding agents in Warp with rich input, notifications, code review, and remote session control. -* [**Oz Cloud Agents**](/agent-platform/cloud-agents/overview/) - Autonomous Oz agents that run in the background in response to system events, schedules, or integrations. +* [**Cloud Agents**](/agent-platform/cloud-agents/overview/) - Autonomous agents that run in the background in response to system events, schedules, or integrations. * [**Integrations**](/agent-platform/cloud-agents/integrations/) - Connect external system events to autonomous agent execution. Use [Slack](/agent-platform/cloud-agents/integrations/slack/), [Linear](/agent-platform/cloud-agents/integrations/linear/), [GitHub Actions](/agent-platform/cloud-agents/integrations/github-actions/), and other integrations to trigger agents in the cloud. * [**Oz Platform**](/agent-platform/cloud-agents/platform/) - The underlying infrastructure that powers Oz, including the CLI, API/SDK, orchestration layer, environments, secrets, and management/observability. @@ -32,7 +32,7 @@ Oz is fully programmable—launch agents manually or build custom logic around t ## Getting started -* [**Agents in Warp**](/agent-platform/getting-started/agents-in-warp/) - Start using Oz agents interactively in Warp +* [**Agents in Warp**](/agent-platform/getting-started/agents-in-warp/) - Start using agents interactively in Warp * [**Oz web app**](https://oz.warp.dev) - Create runs, manage schedules, browse skills, and configure integrations * [**Oz CLI**](/reference/cli/) - Run agents from the command line, in CI, or on remote machines * [**Oz API & SDK**](/reference/api-and-sdk/) - Programmatically create and monitor agent runs diff --git a/src/content/docs/agent-platform/local-agents/active-ai.mdx b/src/content/docs/agent-platform/local-agents/active-ai.mdx index 63f82f24..5bb6f8be 100644 --- a/src/content/docs/agent-platform/local-agents/active-ai.mdx +++ b/src/content/docs/agent-platform/local-agents/active-ai.mdx @@ -5,6 +5,8 @@ description: >- on your command line errors, inputs, and outputs. --- +Active AI Recommendations proactively suggest fixes and next actions based on your terminal errors, inputs, and outputs. Features include Prompt Suggestions that activate Agent Mode, Next Command predictions from your shell history, and Suggested Code Diffs that automatically surface fixes for command-line errors. + :::note Active AI features can be disabled in **Settings** > **Agents** > **Warp Agent** with the Active AI toggle. ::: diff --git a/src/content/docs/agent-platform/local-agents/agent-context/blocks-as-context.mdx b/src/content/docs/agent-platform/local-agents/agent-context/blocks-as-context.mdx index fbe910c3..75e40d8e 100644 --- a/src/content/docs/agent-platform/local-agents/agent-context/blocks-as-context.mdx +++ b/src/content/docs/agent-platform/local-agents/agent-context/blocks-as-context.mdx @@ -6,6 +6,8 @@ description: >- --- import { Tabs, TabItem } from '@astrojs/starlight/components'; +Attach terminal output blocks to your agent prompts so the agent can understand errors, commands, and outputs from your current or previous sessions. Blocks can be attached with keyboard shortcuts, mouse clicks, or automatically within agent conversations. + ## Attaching blocks as context Warp’s Agent can use blocks from your Agent conversations as context to better understand your queries and generate more relevant responses. diff --git a/src/content/docs/agent-platform/local-agents/agent-context/images-as-context.mdx b/src/content/docs/agent-platform/local-agents/agent-context/images-as-context.mdx index 50e775fc..6e7adfde 100644 --- a/src/content/docs/agent-platform/local-agents/agent-context/images-as-context.mdx +++ b/src/content/docs/agent-platform/local-agents/agent-context/images-as-context.mdx @@ -5,6 +5,8 @@ description: >- can use visual context when generating responses. --- +Attach screenshots, diagrams, or other images directly to agent prompts so the agent can use visual context when generating responses. Warp supports drag-and-drop, copy-paste, and file upload for up to 5 images per request across all supported models. + ## **Attaching images as context** To provide visual context, you can attach images directly to an agent prompt. This is useful for including screenshots, diagrams, or other visual references alongside your query. diff --git a/src/content/docs/agent-platform/local-agents/agent-context/selection-as-context.mdx b/src/content/docs/agent-platform/local-agents/agent-context/selection-as-context.mdx index 91c7cbff..bb2f82ba 100644 --- a/src/content/docs/agent-platform/local-agents/agent-context/selection-as-context.mdx +++ b/src/content/docs/agent-platform/local-agents/agent-context/selection-as-context.mdx @@ -5,6 +5,8 @@ description: >- context for your Agent prompts. --- +Attach text selections or diff hunks directly from Warp's code editor or Code Review panel as context for agent prompts. Select code, press a keyboard shortcut, and Warp inserts the file path, line numbers, and content into your prompt automatically. + ### Attaching selections from Warp's native code editor When you have Warp’s [native code editor](/code/code-editor/) open beside a regular pane, you can easily attach specific lines of code as context: diff --git a/src/content/docs/agent-platform/local-agents/agent-context/urls-as-context.mdx b/src/content/docs/agent-platform/local-agents/agent-context/urls-as-context.mdx index c416ed2d..25ae2fef 100644 --- a/src/content/docs/agent-platform/local-agents/agent-context/urls-as-context.mdx +++ b/src/content/docs/agent-platform/local-agents/agent-context/urls-as-context.mdx @@ -5,6 +5,8 @@ description: >- content. --- +Attach a public URL to any agent prompt to provide page content as context. Warp scrapes the page and surfaces the extracted text directly to the model, giving the agent access to documentation, references, or any publicly accessible web content. + ## Referencing websites via URLs You can attach a public URL to any prompt to provide page content as context. Warp will scrape the page and surface the extracted text directly to the model. diff --git a/src/content/docs/agent-platform/local-agents/agent-context/using-to-add-context.mdx b/src/content/docs/agent-platform/local-agents/agent-context/using-to-add-context.mdx index c2b67403..32777665 100644 --- a/src/content/docs/agent-platform/local-agents/agent-context/using-to-add-context.mdx +++ b/src/content/docs/agent-platform/local-agents/agent-context/using-to-add-context.mdx @@ -6,6 +6,8 @@ description: >- --- import VideoEmbed from '@components/VideoEmbed.astro'; +Use the @ symbol in agent prompts to reference files, folders, code symbols, Warp Drive objects, and blocks from other sessions as context. The @ menu searches your entire Git repository from the project root and works immediately without codebase indexing. + ## How the @ context menu works You can attach specific files, folders, code symbols, Warp Drive objects, and blocks from other sessions as context to a prompt using the @ symbol. When you’re inside a **Git repository**, typing @ opens a context menu that allows you to search for and select files or directories to include. diff --git a/src/content/docs/agent-platform/local-agents/code-diffs.mdx b/src/content/docs/agent-platform/local-agents/code-diffs.mdx index c2ca0fb3..e8abece9 100644 --- a/src/content/docs/agent-platform/local-agents/code-diffs.mdx +++ b/src/content/docs/agent-platform/local-agents/code-diffs.mdx @@ -8,6 +8,8 @@ description: >- --- import VideoEmbed from '@components/VideoEmbed.astro'; +When Warp's agent generates code changes, they appear as visual diffs in a built-in editor. Review proposed changes line by line, refine them with natural language, make manual edits, or accept them to apply the modifications to your files. + ## Reviewing code diffs During an Agent Conversation, Warp can generate code diffs that open directly in a built-in diff editor. diff --git a/src/content/docs/agent-platform/local-agents/generate.mdx b/src/content/docs/agent-platform/local-agents/generate.mdx index 55cf5000..93be673f 100644 --- a/src/content/docs/agent-platform/local-agents/generate.mdx +++ b/src/content/docs/agent-platform/local-agents/generate.mdx @@ -8,6 +8,8 @@ description: >- import { Tabs, TabItem } from '@astrojs/starlight/components'; import VideoEmbed from '@components/VideoEmbed.astro'; +Generate (Legacy) turns natural language queries into precise terminal commands or contextual suggestions inside interactive CLI tools. Type `#` in the command line to describe what you want, and Warp generates the matching command in real time. + ## What is Generate? Generate helps turn natural language queries into precise commands as terminal input or contextual suggestions inside interactive commands and programs, whether you're using psql, gdb, git, mysql, or any other CLI tool. diff --git a/src/content/docs/agent-platform/local-agents/interacting-with-agents/index.mdx b/src/content/docs/agent-platform/local-agents/interacting-with-agents/index.mdx index 9aa4a052..6438f547 100644 --- a/src/content/docs/agent-platform/local-agents/interacting-with-agents/index.mdx +++ b/src/content/docs/agent-platform/local-agents/interacting-with-agents/index.mdx @@ -7,6 +7,8 @@ description: >- import { Tabs, TabItem } from '@astrojs/starlight/components'; import VideoEmbed from '@components/VideoEmbed.astro'; +Agent conversations in Warp are multi-turn interactions tied to terminal sessions. Continue previous threads with follow-ups, manage conversation history, attach context from blocks and files, and run multiple conversations simultaneously across windows, tabs, or panes. + ## Conversations with Warp's Agent Conceptually, a conversation is a sequence of AI queries and blocks. Conversations are tied to sessions and you can run multiple Agent Mode conversations simultaneously in different windows, tabs, or panes. diff --git a/src/content/docs/agent-platform/local-agents/interacting-with-agents/terminal-and-agent-modes.mdx b/src/content/docs/agent-platform/local-agents/interacting-with-agents/terminal-and-agent-modes.mdx index d7386c6c..fa693766 100644 --- a/src/content/docs/agent-platform/local-agents/interacting-with-agents/terminal-and-agent-modes.mdx +++ b/src/content/docs/agent-platform/local-agents/interacting-with-agents/terminal-and-agent-modes.mdx @@ -6,7 +6,7 @@ description: >- --- import VideoEmbed from '@components/VideoEmbed.astro'; -Warp provides two distinct modes: a clean terminal for commands, and a dedicated conversation view for multi-turn conversations with [Oz, Warp's agent](/agent-platform/local-agents/interacting-with-agents/). +Warp provides two distinct modes: a clean terminal for running shell commands, and a dedicated conversation view for multi-turn interactions with Oz, Warp's agent. Terminal mode keeps the interface minimal by default, while Agent Mode surfaces full controls for model selection, voice input, image attachments, and conversation management. @@ -17,7 +17,7 @@ Warp provides two distinct modes: a clean terminal for commands, and a dedicated Before diving in, here are two key concepts: * **Terminal session** - Your shell environment where you run commands. This is the default mode when you open Warp—a clean, traditional terminal input. -* **Oz agent conversation** - A multi-turn interaction with Oz. Conversations maintain context across exchanges and have their own dedicated view with richer controls. +* **Agent conversation** - A multi-turn interaction with Oz. Conversations maintain context across exchanges and have their own dedicated view with richer controls. Terminal and Agent modes make switching between these two contexts seamless while keeping them visually distinct. @@ -67,7 +67,7 @@ If you disable the message bar while auto-detection is enabled, you won't see th The shortcuts shown on this page use macOS keybindings. For Windows and Linux shortcuts, see [Keyboard Shortcuts](/getting-started/keyboard-shortcuts/). ::: -### Oz agent conversation view (expanded UI) +### Agent conversation view (expanded UI) * A dedicated conversation view with richer agent controls including model select, voice input, image attachments, and conversation management. * Familiar "charms" (current directory, git branch, diff view entry point, etc.) are still available. @@ -111,7 +111,7 @@ This separation keeps your terminal view clean while preserving full context wit #### Cloud agent conversations -In addition to local agent conversations, you can start **Oz cloud agent conversations** that run in an isolated cloud environment. Cloud agents are useful for: +In addition to local agent conversations, you can start **cloud agent conversations** that run in an isolated cloud environment. Cloud agents are useful for: * Running parallel agents across multiple tasks * Running agents remotely on hosted computers (offloading compute from your local machine) @@ -124,7 +124,7 @@ Cloud agent conversations have a few differences from local conversations: * **Environment selector** - Choose which [Warp Environment](/agent-platform/cloud-agents/environments/) to run in * **Credits indicator** - Shows your remaining cloud agent credits -* **Different zero state** - The conversation header indicates "New Oz cloud agent conversation" +* **Different zero state** - The conversation header indicates "New cloud agent conversation" Cloud agent conversations are always stored in the cloud. For more details on accessing and sharing cloud conversations, see [Cloud-synced Conversations](/agent-platform/local-agents/cloud-conversations/). @@ -189,7 +189,7 @@ Auto-detection is enabled by default for new Warp users. For users who had Warp ### How to enter a conversation -There are several ways to start or enter an Oz agent conversation: +There are several ways to start or enter an agent conversation: #### A) Use the `/agent` or `/new` slash command @@ -311,7 +311,7 @@ If you prefer to type natural language at any point in a terminal session and ha ### Step 1 — Set new tabs to open in agent view -By default, new tabs and panes open in terminal mode. To launch directly into an Oz agent conversation instead: +By default, new tabs and panes open in terminal mode. To launch directly into an agent conversation instead: 1. Go to **Settings** > **Features** > **General**. 2. Change **Default mode for new sessions** to **Agent**. diff --git a/src/content/docs/agent-platform/local-agents/interactive-code-review.mdx b/src/content/docs/agent-platform/local-agents/interactive-code-review.mdx index b568d9f7..05837456 100644 --- a/src/content/docs/agent-platform/local-agents/interactive-code-review.mdx +++ b/src/content/docs/agent-platform/local-agents/interactive-code-review.mdx @@ -6,6 +6,8 @@ description: >- --- import VideoEmbed from '@components/VideoEmbed.astro'; +Interactive Code Review lets you review agent-generated code, leave inline comments on specific lines, batch your feedback, and send all requested changes to the agent in a single pass. It works with Warp's native agent and supported third-party CLI agents like Claude Code and Codex. + ### Overview Interactive Code Review lets you review, annotate, and refine code generated by any supported agent, whether that's Warp's native Agent or a third-party CLI agent running in Warp. Instead of relying on an AI to review another AI's output, Warp keeps the developer in control. diff --git a/src/content/docs/agent-platform/local-agents/overview.mdx b/src/content/docs/agent-platform/local-agents/overview.mdx index 2764ed64..c1cf191f 100644 --- a/src/content/docs/agent-platform/local-agents/overview.mdx +++ b/src/content/docs/agent-platform/local-agents/overview.mdx @@ -6,9 +6,11 @@ description: >- Environment. --- +Warp's local agents are interactive agents embedded directly in the terminal that help you write code, debug issues, run commands, and automate development tasks using natural language. Agents operate with full context from your codebase, Warp Drive, and connected tools, while you stay in control of every action. + ## AI in Warp -Warp includes intelligent Oz agents designed to help you build, test, deploy, and debug while keeping you in control. Interactive agent conversations in Warp can look up commands, execute tasks, fix bugs, and adapt to your workflows. You can manage agent behavior directly, with full context from your Warp Drive and your team. +Warp includes intelligent agents designed to help you build, test, deploy, and debug while keeping you in control. Interactive agent conversations in Warp can look up commands, execute tasks, fix bugs, and adapt to your workflows. You can manage agent behavior directly, with full context from your Warp Drive and your team. :::note Warp's AI features can be globally disabled in **Settings** > **Agents** > **Warp Agent** with the AI toggle.\ diff --git a/src/content/docs/agent-platform/local-agents/session-sharing.mdx b/src/content/docs/agent-platform/local-agents/session-sharing.mdx index 7982c6dd..b052f651 100644 --- a/src/content/docs/agent-platform/local-agents/session-sharing.mdx +++ b/src/content/docs/agent-platform/local-agents/session-sharing.mdx @@ -24,7 +24,7 @@ When you share an agent session, Warp publishes it to the cloud and generates a ## Sharing a session -1. Start or open an agent session in Warp. The agent can be an Oz agent, a third-party coding agent, or any interactive agent running in your terminal. +1. Start or open an agent session in Warp. The agent can be Warp's built-in agent, a third-party coding agent, or any interactive agent running in your terminal. 2. Open the share action from any of these entry points: * **Command Palette** - Search for "Share session" * **Pane header** - Click the overflow menu in the pane header diff --git a/src/content/docs/changelog/2026.mdx b/src/content/docs/changelog/2026.mdx index 2e07e788..fcefed2f 100644 --- a/src/content/docs/changelog/2026.mdx +++ b/src/content/docs/changelog/2026.mdx @@ -390,7 +390,7 @@ Submit bugs and feature requests on our [GitHub board!](https://github.com/warpd * \[macOS] Right-clicking on text files in Finder allows you to open in Warp's code editor. * Send code review comments, attach diff hunks as context, and send substrings as context (`cmd L`) to 3rd party CLI tools such as Claude Code, Codex, Opencode, etc. -* Oz agents can now ask users clarifying questions during Agent Mode interactions. +* Agents can now ask users clarifying questions during Agent Mode interactions. * Warp's agent now suggests followups when it is done. **Improvements** @@ -401,7 +401,7 @@ Submit bugs and feature requests on our [GitHub board!](https://github.com/warpd * Added "Sign up" option to the settings gear menu for non-logged-in users. * MCP config files edited by the agent now show an 'Open config' button in the code diff header, making it easy to jump directly to the config file. * Added `/skills` support in CLI agent rich input for browsing and invoking agent-specific skills. -* Sandboxed Oz agents now have dedicated autonomy settings, instead of inheriting the team-level defaults. +* Sandboxed agents now have dedicated autonomy settings, instead of inheriting the team-level defaults. * Updated settings info icon tooltips to clarify they open documentation. * Improved quality and latency of prompt suggestions and suggested code diffs. * Cloud agents can now accept images and file attachments as context. @@ -430,7 +430,7 @@ Submit bugs and feature requests on our [GitHub board!](https://github.com/warpd * Fixed Oz session sharing failing behind HTTP proxies on port 80. * The `OZ_RUN_ID` environment variable is now available inside agent terminal sessions, set to the current task ID. * Improved error messages when agent session sharing fails, removing repetitive text and providing clearer guidance. -* Oz agents can now ask users clarifying questions during Agent Mode interactions. +* Agents can now ask users clarifying questions during Agent Mode interactions. ### 2026.03.25 (v0.2026.03.25.08.24) @@ -579,12 +579,12 @@ Submit bugs and feature requests on our [GitHub board!](https://github.com/warpd * Fixed "open file" button in code review diff view not working when the pane is maximized. * Fixed git metadata background operations after a terminal is closed. * Mobile soft keyboard will now work for LRCs. -* Oz agents now report more detailed information about session-sharing failures. +* Agents now report more detailed information about session-sharing failures. **Oz updates** -* Oz agent tasks now report structured error codes to the server, enabling better error tracking and retryability handling. -* Fixed Oz cloud agent not waiting for automatic error retry on network failures. +* Agent tasks now report structured error codes to the server, enabling better error tracking and retryability handling. +* Fixed cloud agent not waiting for automatic error retry on network failures. * Added support for passing arguments to skill invocations (`$ARGUMENTS`, `$N`) and for including user queries with the invocation. ### 2026.02.25 (v0.2026.02.25.08.24) @@ -657,7 +657,7 @@ Oz is Warp's orchestration platform for cloud agents: launch parallel agents, au [Read the launch post →](https://www.warp.dev/blog/oz-orchestration-platform-cloud-agents) -#### Oz Cloud Agents +#### Cloud Agents * **Run Cloud Agents from anywhere with built-in tracking** — start agents from Warp or via the CLI, triggers, or schedules. Every run is auditable and steerable. [Cloud Agents docs →](https://docs.warp.dev/agent-platform/cloud-agents/overview) * **Cloud environments for consistent execution** — configure Docker-based environments (unlimited repos + setup commands) and run agents in isolated cloud sandboxes. [Environments docs →](https://docs.warp.dev/agent-platform/cloud-agents/environments) diff --git a/src/content/docs/code/code-editor/code-editor-vim-keybindings.mdx b/src/content/docs/code/code-editor/code-editor-vim-keybindings.mdx index cd5c6379..75226cf1 100644 --- a/src/content/docs/code/code-editor/code-editor-vim-keybindings.mdx +++ b/src/content/docs/code/code-editor/code-editor-vim-keybindings.mdx @@ -7,6 +7,8 @@ sidebar: label: "Code editor Vim keybindings" --- +Warp's built-in code editor supports native Vim keybindings for keyboard-driven navigation and editing. Enable Vim mode to use familiar motions, text objects, visual mode, registers, and editing commands directly in Warp without switching to an external editor. + ## About Vim keybindings The Vi family of programs (including Vim and Neovim) are modal text editors that allow for keyboard-driven text editing. Vi-style keybindings are especially popular among developers for their speed and precision in navigating and manipulating code. Warp’s [code editor](/code/code-editor/) now includes native support for Vim keybindings (also known as Vim mode), offering a familiar editing experience directly within your coding workflows. diff --git a/src/content/docs/code/code-editor/file-tree.mdx b/src/content/docs/code/code-editor/file-tree.mdx index a6ab1345..2a870704 100644 --- a/src/content/docs/code/code-editor/file-tree.mdx +++ b/src/content/docs/code/code-editor/file-tree.mdx @@ -5,6 +5,8 @@ description: >- context menu actions. --- +The File Tree is Warp's built-in project explorer for browsing, opening, and managing files alongside your terminal. It automatically reflects your project structure and supports context menu actions like attaching files as agent context, copying paths, and creating new files. + ![Warp's native file tree showing the project's file and folder structure in the left panel.](../../../../assets/terminal/filetree-main.png) Warp includes a **native file tree** that makes it easy to explore and manage project files. The file tree is available whenever in any directory and it automatically reflects your project structure as files are added, removed, or changed. diff --git a/src/content/docs/code/code-editor/find-and-replace.mdx b/src/content/docs/code/code-editor/find-and-replace.mdx index 073695fb..5b52870c 100644 --- a/src/content/docs/code/code-editor/find-and-replace.mdx +++ b/src/content/docs/code/code-editor/find-and-replace.mdx @@ -8,6 +8,8 @@ sidebar: --- import DemoVideo from '@components/DemoVideo.astro'; +Warp's code editor includes built-in find and replace with support for regex, case sensitivity, and smart case preservation. Search across a file, jump between matches, and replace text with automatic casing adjustments for PascalCase, camelCase, and hyphenated patterns. + ## Find Press `CMD-F` on macOS or `CTRL-SHIFT-F` on Windows and Linux to open the find menu. As you type, all matches in the file are highlighted, and the match closest to your cursor is selected. diff --git a/src/content/docs/code/code-review.mdx b/src/content/docs/code/code-review.mdx index f532917d..f411412e 100644 --- a/src/content/docs/code/code-review.mdx +++ b/src/content/docs/code/code-review.mdx @@ -7,6 +7,8 @@ description: >- import DemoVideo from '@components/DemoVideo.astro'; import VideoEmbed from '@components/VideoEmbed.astro'; +The Code Review panel lets you inspect, edit, and manage Git diffs directly inside Warp. Review uncommitted changes or compare branches, attach diffs as context for agents, revert specific hunks, and leave inline comments that agents can act on in real time. + ## Overview When you are working locally in a Git repository with uncommitted changes, the **Code Review panel** lets you inspect, edit, and manage code changes directly inside Warp. It integrates with Git and Warp's Agents, giving you the ability to: diff --git a/src/content/docs/code/overview.mdx b/src/content/docs/code/overview.mdx index a5abd773..3e2b7787 100644 --- a/src/content/docs/code/overview.mdx +++ b/src/content/docs/code/overview.mdx @@ -6,6 +6,8 @@ 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. + :::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. ::: diff --git a/src/content/docs/enterprise/enterprise-features/architecture-and-deployment.mdx b/src/content/docs/enterprise/enterprise-features/architecture-and-deployment.mdx index 43009fae..37dc72dc 100644 --- a/src/content/docs/enterprise/enterprise-features/architecture-and-deployment.mdx +++ b/src/content/docs/enterprise/enterprise-features/architecture-and-deployment.mdx @@ -29,7 +29,7 @@ Warp's cloud agent infrastructure has four key components: ## Warp-hosted (SaaS) -Warp-hosted is the default deployment model. Oz agents run on Warp-managed infrastructure with no setup required from your team. +Warp-hosted is the default deployment model. Agents run on Warp-managed infrastructure with no setup required from your team. ### How it works diff --git a/src/content/docs/enterprise/enterprise-features/bring-your-own-llm.mdx b/src/content/docs/enterprise/enterprise-features/bring-your-own-llm.mdx index 326b7314..e81d7032 100644 --- a/src/content/docs/enterprise/enterprise-features/bring-your-own-llm.mdx +++ b/src/content/docs/enterprise/enterprise-features/bring-your-own-llm.mdx @@ -12,7 +12,7 @@ This gives you control over cloud spend and model hosting, without changing how :::caution BYOLLM currently supports **AWS Bedrock** only. Coming soon: Azure Foundry and Google Vertex support. -BYOLLM applies to interactive Oz agents in the terminal. Oz cloud agents do not yet support BYOLLM routing. +BYOLLM applies to interactive agents in the terminal. Cloud agents do not yet support BYOLLM routing. ::: :::note @@ -35,7 +35,7 @@ Here's the high-level flow: 1. **Admin configures routing** - Your team admin sets routing policies in Warp's admin settings (e.g., "Route Claude Sonnet 4.5 through AWS Bedrock; disable direct Anthropic API"). 2. **Team members authenticate** - Each team member authenticates to AWS locally using the AWS CLI (`aws login`). -3. **Warp routes requests** - When a team member uses an interactive Oz agent in the terminal, Warp uses their short-lived session credentials to authenticate requests to your configured AWS Bedrock API endpoint. +3. **Warp routes requests** - When a team member uses an interactive agent in the terminal, Warp uses their short-lived session credentials to authenticate requests to your configured AWS Bedrock API endpoint. 4. **Inference executes in your cloud** - The model runs in your AWS account. Responses return to the Warp client. ### Credential lifecycle diff --git a/src/content/docs/enterprise/getting-started/getting-started-developers.mdx b/src/content/docs/enterprise/getting-started/getting-started-developers.mdx index 66ba2fe1..1e5ac983 100644 --- a/src/content/docs/enterprise/getting-started/getting-started-developers.mdx +++ b/src/content/docs/enterprise/getting-started/getting-started-developers.mdx @@ -7,10 +7,10 @@ description: >- This guide helps developers get up and running with their team in Warp. You'll learn how to download Warp, log in with your organization's SSO, and configure key features like Codebase Context, Warp Drive, and Agent Profiles to accelerate your work across the entire SDLC (all while staying in your terminal). -When you use agents in Warp, you're using **Oz agents**. Oz is Warp's programmable agent for running and coordinating agents at scale, whether they run locally on your machine or in the cloud. Oz provides the orchestration, tracking, and control plane that makes scaling agent workflows seamless. +When you use agents in Warp, you're working with **Warp's built-in agents**. Oz is Warp's programmable agent for running and coordinating agents at scale, whether they run locally on your machine or in the cloud. Oz provides the orchestration, tracking, and control plane that makes scaling agent workflows seamless. :::note -New to Warp Enterprise? Try the [Enterprise quickstart](/enterprise/getting-started/quickstart/) for a 10-minute walkthrough of SSO login, Warp setup, and running your first Oz agent. +New to Warp Enterprise? Try the [Enterprise quickstart](/enterprise/getting-started/quickstart/) for a 10-minute walkthrough of SSO login, Warp setup, and running your first agent. ::: ## Step 1: Download and install Warp @@ -121,13 +121,13 @@ Once codebase indexing is enabled, you can index individual repositories: During indexing, your code is sent to Warp's servers for processing where embeddings are created and stored. The code itself is not saved—only the embeddings are persisted. This allows agents to understand your codebase structure and context without storing your actual source code. :::note -For Oz cloud agents: Code snippets may be stored as part of conversation records when agents create or modify files, since diffs are preserved in the conversation history. +For cloud agents: Code snippets may be stored as part of conversation records when agents create or modify files, since diffs are preserved in the conversation history. ::: ### Agent Profiles {/* Warp also supports third-party CLI agents (Claude Code, Codex, Copilot), so we say "built-in" rather than "every." */} -Agent Profiles let you configure how Warp's built-in Oz agents behave. Profiles give you direct control over model selection, autonomy, tools, and permissions for your agent workflows. +Agent Profiles let you configure how Warp's built-in agents behave. Profiles give you direct control over model selection, autonomy, tools, and permissions for your agent workflows. **Creating an Agent Profile:** @@ -232,7 +232,7 @@ Warp keeps you in your terminal with agent help across the entire SDLC: **Testing** * "Write unit tests for this function following our existing patterns" * "Run the test suite and explain what failed" -* Configure Oz cloud agents to run test suites and validate coverage on PRs in the background +* Configure cloud agents to run test suites and validate coverage on PRs in the background ### Learning resources @@ -251,7 +251,7 @@ For common login, SSO, and access issues, see the [Enterprise FAQ](/enterprise/g Now that you're set up: -* **Explore agent capabilities** - Learn about [agents in Warp](/agent-platform/local-agents/overview/) and [Oz cloud agents](/agent-platform/cloud-agents/overview/) +* **Explore agent capabilities** - Learn about [agents in Warp](/agent-platform/local-agents/overview/) and [cloud agents](/agent-platform/cloud-agents/overview/) * **Contribute to team knowledge** - Add useful Workflows, Prompts, and Rules to your team's Warp Drive to compound productivity gains across your team * **Stay updated** - Check the [Warp changelog](/changelog/) for new features diff --git a/src/content/docs/enterprise/getting-started/getting-started-enterprise.mdx b/src/content/docs/enterprise/getting-started/getting-started-enterprise.mdx index 478d07b8..9ce05e1d 100644 --- a/src/content/docs/enterprise/getting-started/getting-started-enterprise.mdx +++ b/src/content/docs/enterprise/getting-started/getting-started-enterprise.mdx @@ -113,7 +113,7 @@ Alternatively, visit [app.warp.dev/admin](https://app.warp.dev/admin) directly. * **AI** - Configure general and AI autonomy settings for your team * **Models** - Configure which models are available to your team and AWS Bedrock * **Code** - Enable Codebase Context for your team -* **Platform** - Configure Oz cloud agent settings +* **Platform** - Configure cloud agent settings * **Privacy** - Configure user-generated content data collection, cloud conversation storage, and enterprise secret redaction * **Sharing** - Configure direct link sharing and "anyone with link" sharing permissions @@ -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 Oz 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 diff --git a/src/content/docs/enterprise/getting-started/quickstart.mdx b/src/content/docs/enterprise/getting-started/quickstart.mdx index 963e162c..2dcfc351 100644 --- a/src/content/docs/enterprise/getting-started/quickstart.mdx +++ b/src/content/docs/enterprise/getting-started/quickstart.mdx @@ -2,12 +2,12 @@ title: Enterprise quickstart description: >- Get up and running with Warp Enterprise in under 10 minutes. Log in, set up - your terminal, and run your first Oz agent. + your terminal, and run your first agent. sidebar: label: "Quickstart" --- -This quickstart walks you through the essentials: logging in via SSO, setting up Warp, and running your first Oz agent. You can complete this in under 10 minutes. +This quickstart walks you through the essentials: logging in via SSO, setting up Warp, and running your first agent. You can complete this in under 10 minutes. ## Step 1: Log in via SSO @@ -32,20 +32,20 @@ If you have an existing Warp account from before your organization enabled SSO, 3. Launch Warp and log in with SSO (Step 1). 4. Verify you see your team name in **Settings** > **Teams**. -## Step 3: Configure and run your first Oz agent +## Step 3: Configure and run your first agent -When you use agents in Warp, you're using **Oz agents**. Oz is Warp's programmable agent for running and coordinating agents at scale, whether they run locally on your machine or in the cloud. +When you use agents in Warp, you're working with **Warp's built-in agents**. Oz is Warp's programmable agent for running and coordinating agents at scale, whether they run locally on your machine or in the cloud. ### Index your codebase 1. Navigate to a Git repository in Warp. 2. Warp automatically detects the repo and begins indexing. 3. Optionally, run `/init` to manually trigger indexing or re-indexing after significant code changes. -4. Once indexed, Oz agents understand your code structure, patterns, and conventions. +4. Once indexed, agents understand your code structure, patterns, and conventions. -### Run your first Oz agent locally +### Run your first agent locally -Start an Oz conversation right in the terminal. Try the following prompt: +Start a conversation right in the terminal. Try the following prompt: ``` Explain the architecture of this project @@ -60,9 +60,9 @@ Oz reads your codebase, understands its structure, and responds with a context-a * **Explore** - "What patterns does this repo use for error handling?" * **Plan** - Use `/plan` to have Oz create a structured task plan for complex features -## Step 4: Run an Oz cloud agent +## Step 4: Run a cloud agent -Oz cloud agents run in the cloud for background work, unlimited parallelization, and long-running tasks. +Cloud agents run in the cloud for background work, unlimited parallelization, and long-running tasks. ### Create an environment @@ -88,10 +88,10 @@ Once your environment is ready, use the following command to launch a cloud agen oz agent run-cloud --env my-env --prompt "Review the open PRs in this repo" ``` -Monitor and steer Oz cloud agents from the Oz dashboard or directly in Warp. +Monitor and steer cloud agents from the Oz dashboard or directly in Warp. ## Next steps * **Set up key features** - Follow the full [Getting started for developers](/enterprise/getting-started/getting-started-developers/) guide to configure Codebase Context, Warp Drive, MCP integrations, and Agent Profiles. -* **Explore Oz cloud agents** - Learn about [Oz cloud agents](/agent-platform/cloud-agents/overview/) for background automation and parallel workflows. +* **Explore cloud agents** - Learn about [cloud agents](/agent-platform/cloud-agents/overview/) for background automation and parallel workflows. * **Learn more** - Visit [Warp Guides](/guides/) for video tutorials and end-to-end workflows. diff --git a/src/content/docs/enterprise/index.mdx b/src/content/docs/enterprise/index.mdx index 2b7aa966..458c0d82 100644 --- a/src/content/docs/enterprise/index.mdx +++ b/src/content/docs/enterprise/index.mdx @@ -40,11 +40,11 @@ Warp Enterprise serves three primary audiences: * **Warp Drive team workspace** - Share Workflows, Notebooks, Prompts, Plans, Rules, and Environment Variables across your team * **Codebase Context** - Team-level code indexing helps agents understand your repositories and generate accurate, context-aware responses * **MCP integrations** - Connect to your team's tools (Linear, Sentry, Figma, GitHub, and more) for context-aware agent responses -* **Session sharing** - Collaborate on terminal sessions and Oz conversations with shareable links +* **Session sharing** - Collaborate on terminal sessions and conversations with shareable links -### Oz agent capabilities +### Agent capabilities * **State-of-the-art agents** - Multi-model agents with full terminal access, code editing, and autonomous task execution -* **Oz cloud agents** - Run agents in the cloud for unlimited parallelization, background automation, and long-running workflows. Perfect for PR reviews, scheduled tasks, and distributed work across multiple repositories +* **Cloud agents** - Run agents in the cloud for unlimited parallelization, background automation, and long-running workflows. Perfect for PR reviews, scheduled tasks, and distributed work across multiple repositories * **Integrated control plane** - Launch, orchestrate, and manage local, cloud, and autonomous agents from a unified interface. Track all agent activity across your team from the Oz dashboard * **Agent Profiles** - Customize agent behavior, models, autonomy levels, and permissions * **Rules and guardrails** - Enforce coding standards, tech stack preferences, and security practices through team-wide or project-specific rules diff --git a/src/content/docs/enterprise/security-and-compliance/security-overview.mdx b/src/content/docs/enterprise/security-and-compliance/security-overview.mdx index 82febd95..b5101594 100644 --- a/src/content/docs/enterprise/security-and-compliance/security-overview.mdx +++ b/src/content/docs/enterprise/security-and-compliance/security-overview.mdx @@ -119,7 +119,7 @@ Warp's operational security practices — including access controls, monitoring, ### Self-hosted deployments -Enterprise teams can self-host Oz cloud agent execution to control where agents run and keep repositories on their own infrastructure. +Enterprise teams can self-host cloud agent execution to control where agents run and keep repositories on their own infrastructure. Self-hosted deployments use a split architecture: * **Execution plane (customer-hosted)** - Repository clones, build artifacts, runtime secrets, and container filesystem state stay on your infrastructure @@ -158,7 +158,7 @@ Security-relevant controls include: * **Sharing** - Restrict or permit direct link sharing and "anyone with link" sharing permissions * **AI** - Configure AI autonomy settings and general agent behavior for the team * **Models** - Control which LLM models are available to team members, including AWS Bedrock -* **Platform** - Configure Oz cloud agent access and settings +* **Platform** - Configure cloud agent access and settings ## Security features for developers diff --git a/src/content/docs/enterprise/support-and-resources/billing.mdx b/src/content/docs/enterprise/support-and-resources/billing.mdx index 5d4bb48e..b9f91462 100644 --- a/src/content/docs/enterprise/support-and-resources/billing.mdx +++ b/src/content/docs/enterprise/support-and-resources/billing.mdx @@ -11,7 +11,7 @@ This page covers general information about credits, cloud agent costs, and BYOLL ## Credits -Warp uses a credit-based billing model. Any interaction with Oz agents consumes credits based on the complexity of the task, the model used, and the amount of context processed. +Warp uses a credit-based billing model. Any interaction with agents consumes credits based on the complexity of the task, the model used, and the amount of context processed. ### How credits work @@ -31,7 +31,7 @@ Credit allocations vary by contract. Contact your account manager for details on ## Cloud agent billing -Oz cloud agents consume AI credits for inference, compute credits for the sandbox they run in, and platform credits for the orchestration layer. See [Credits](/support-and-community/plans-and-billing/credits/) for the full breakdown of how each credit type is metered. +Cloud agents consume AI credits for inference, compute credits for the sandbox they run in, and platform credits for the orchestration layer. See [Credits](/support-and-community/plans-and-billing/credits/) for the full breakdown of how each credit type is metered. ### How credits are consumed @@ -65,7 +65,7 @@ Administrators can configure monthly spending limits and receive alerts to preve Enterprise administrators can set monthly spending limits across the following four categories: -* **Cloud spending limit** - Cap monthly spend on Oz cloud agent usage. +* **Cloud spending limit** - Cap monthly spend on cloud agent usage. * **Local spending limit** - Cap monthly spend on local agent usage in the Warp app. * **Total spending limit** - Cap combined monthly spend across both cloud and local agents. * **Per-user spending limit** - Cap monthly spend for any individual user. Set a default that applies to all users, or configure limits on a per-user basis for predictable individual spend. diff --git a/src/content/docs/enterprise/team-management/admin-panel.mdx b/src/content/docs/enterprise/team-management/admin-panel.mdx index be62cc25..a6dd8d75 100644 --- a/src/content/docs/enterprise/team-management/admin-panel.mdx +++ b/src/content/docs/enterprise/team-management/admin-panel.mdx @@ -102,7 +102,7 @@ The features available in the Admin Panel scale with your Warp plan: * **Full admin control** - Configure all available settings * **Enterprise secret redaction** - Custom regex patterns for secrets * **BYOLLM** - Route inference through your cloud infrastructure -* **Self-hosting cloud agent workers** - Deploy Oz cloud agent workers on your own infrastructure +* **Self-hosting cloud agent workers** - Deploy cloud agent workers on your own infrastructure * **Advanced compliance** - SOC 2, HIPAA, and custom data handling agreements * **Priority support** - Dedicated Slack/Teams channels @@ -248,11 +248,11 @@ For organizations with sensitive internal processes, disable "Anyone with link" ### Platform settings -Configure Oz cloud agent settings for your team, including GitHub authorization for automated workflows. +Configure cloud agent settings for your team, including GitHub authorization for automated workflows. **Enabled GitHub Orgs** -The **Enabled GitHub Orgs** setting associates your Warp team with one or more GitHub App installations, enabling Oz cloud agents initiated with a [team API key](/reference/cli/api-keys/) to clone repositories and open pull requests using the Oz by Warp GitHub App. +The **Enabled GitHub Orgs** setting associates your Warp team with one or more GitHub App installations, enabling cloud agents initiated with a [team API key](/reference/cli/api-keys/) to clone repositories and open pull requests using the Oz by Warp GitHub App. To configure: diff --git a/src/content/docs/enterprise/team-management/roles-and-permissions.mdx b/src/content/docs/enterprise/team-management/roles-and-permissions.mdx index df5bd074..3481d097 100644 --- a/src/content/docs/enterprise/team-management/roles-and-permissions.mdx +++ b/src/content/docs/enterprise/team-management/roles-and-permissions.mdx @@ -44,7 +44,7 @@ Team Admins cannot demote or modify the Team Owner role. ### What members can do -* **Use agents** - Run Oz agents locally and in the cloud within the policies admins define. +* **Use agents** - Run agents locally and in the cloud within the policies admins define. * **Access team resources** - Use shared Workflows, Notebooks, Prompts, Rules, and Environment Variables in Warp Drive. * **Configure personal settings** - Adjust settings where admins have selected "Respect User Setting." * **Share sessions** - Collaborate via session sharing (if enabled by admins). diff --git a/src/content/docs/getting-started/supported-shells.mdx b/src/content/docs/getting-started/supported-shells.mdx index 7b0d9ed1..45ba8e84 100644 --- a/src/content/docs/getting-started/supported-shells.mdx +++ b/src/content/docs/getting-started/supported-shells.mdx @@ -7,6 +7,8 @@ sidebar: label: "Supported shells" --- +Warp supports bash, zsh, fish, and PowerShell (pwsh) across macOS, Windows, and Linux, loading your login shell by default. You can change the default shell per-session, customize each shell's configuration files and environment variables, and install additional shells like fish or PowerShell on macOS. + ## Warp default shell Warp tries to load your login shell by default. Currently, Warp supports bash, fish, zsh, and PowerShell (pwsh). If your login shell is set to something else (e.g. Nushell) Warp will show a banner indicating it's not supported and load the default shells listed below: diff --git a/src/content/docs/guides/configuration/how-to-set-up-self-serve-data-analytics-with-skills.mdx b/src/content/docs/guides/configuration/how-to-set-up-self-serve-data-analytics-with-skills.mdx index d9d78fe2..d3e7bcdd 100644 --- a/src/content/docs/guides/configuration/how-to-set-up-self-serve-data-analytics-with-skills.mdx +++ b/src/content/docs/guides/configuration/how-to-set-up-self-serve-data-analytics-with-skills.mdx @@ -19,7 +19,7 @@ Self-serve data analytics means anyone on your team can ask a data question and ## Walkthrough video -In this 40-minute livestream, Warp's data team demonstrates the workflow end-to-end, including the two Skills you'll install below and a third pattern (running the same Skills from Slack via an Oz cloud agent). Feel free to skip ahead if you prefer to follow the written steps. +In this 40-minute livestream, Warp's data team demonstrates the workflow end-to-end, including the two Skills you'll install below and a third pattern (running the same Skills from Slack via a cloud agent). Feel free to skip ahead if you prefer to follow the written steps. @@ -176,7 +176,7 @@ The `analysis-artifacts` Skill is largely stack-agnostic. It structures outputs, You installed two community Skills, customized the model index for your warehouse, and ran both a simple lookup and a full deep-dive analysis. -**Extend to Slack.** Wire the same two Skills into an Oz cloud agent configured with your dbt repo, and your teammates can ask data questions by @-mentioning Oz in a Slack channel, without opening a terminal. The Agent clones the repo, picks up the Skills from `.agents/skills/`, and replies in-thread. See the [Slack integration docs](https://docs.warp.dev/agent-platform/cloud-agents/integrations/slack/) and [Skills as Agents](https://docs.warp.dev/agent-platform/cloud-agents/skills-as-agents/) for setup. +**Extend to Slack.** Wire the same two Skills into a cloud agent configured with your dbt repo, and your teammates can ask data questions by @-mentioning Oz in a Slack channel, without opening a terminal. The agent clones the repo, picks up the Skills from `.agents/skills/`, and replies in-thread. See the [Slack integration docs](https://docs.warp.dev/agent-platform/cloud-agents/integrations/slack/) and [Skills as Agents](https://docs.warp.dev/agent-platform/cloud-agents/skills-as-agents/) for setup. Explore related guides and features: diff --git a/src/content/docs/index.mdx b/src/content/docs/index.mdx index 3ffaf9b3..9e489ea2 100644 --- a/src/content/docs/index.mdx +++ b/src/content/docs/index.mdx @@ -8,7 +8,7 @@ sidebar: --- import VideoEmbed from '@components/VideoEmbed.astro'; -Warp is an [open source](https://github.com/warpdotdev/warp) **Agentic Development Environment**, a modern terminal combined with powerful agents that help you build, test, deploy, and debug code. Warp's AI is powered by **Oz**, the orchestration platform for cloud agents. +Warp is an [open source](https://github.com/warpdotdev/warp) **Agentic Development Environment** that combines a modern, high-performance terminal with powerful agents to help you build, test, deploy, and debug code. Warp's agents are powered by **Oz**, the orchestration platform for running agents locally or in the cloud at scale.
![Warp, the Agentic Development Environment: Warp (a modern terminal built for coding with agents) and Oz (the orchestration platform for cloud agents)](../../assets/terminal/warp-oz-welcome.png) @@ -53,7 +53,7 @@ Local agents keep you in control. You can review changes, steer the agent mid-ta ### Cloud agents -Oz Cloud Agents run in the background on Warp's infrastructure (or your own) for automation at scale. +Cloud agents run in the background on Warp's infrastructure (or your own) for automation at scale. * **Triggers**: React to events from Slack, Linear, GitHub, or custom webhooks * **Schedules**: Run recurring tasks like dependency updates or dead code removal diff --git a/src/content/docs/knowledge-and-collaboration/admin-panel.mdx b/src/content/docs/knowledge-and-collaboration/admin-panel.mdx index 8c23a899..1c69a162 100644 --- a/src/content/docs/knowledge-and-collaboration/admin-panel.mdx +++ b/src/content/docs/knowledge-and-collaboration/admin-panel.mdx @@ -5,6 +5,8 @@ description: >- settings enforced across all team members. --- +The Admin Panel gives team administrators centralized control over organization-wide Warp settings, including agent autonomy, privacy controls, billing limits, codebase indexing, and sharing policies. Settings configured in the Admin Panel are enforced across all team members and override individual preferences. + ## What is the Admin Panel? The [Admin Panel](https://app.warp.dev/admin/) provides team administrators with centralized control over organization-wide settings in Warp. It allows you to manage workspace settings that are enforced across all members of your team. diff --git a/src/content/docs/knowledge-and-collaboration/teams.mdx b/src/content/docs/knowledge-and-collaboration/teams.mdx index 3602f8e9..7c3f8f76 100644 --- a/src/content/docs/knowledge-and-collaboration/teams.mdx +++ b/src/content/docs/knowledge-and-collaboration/teams.mdx @@ -5,6 +5,8 @@ description: >- --- import VideoEmbed from '@components/VideoEmbed.astro'; +A Warp team is a group of users who collaborate through a shared workspace in Warp Drive. Teams share Workflows, Notebooks, Prompts, Rules, and Environment Variables, with role-based permissions for admins and members. Each Warp user can belong to one team at a time. + ## What is a team? A team is a group of Warp users who can collaborate on the command line together. Warp teams can share a dedicated workspace in Warp Drive. [Learn about pricing](https://www.warp.dev/pricing) and see our [Pricing FAQ](/support-and-community/plans-and-billing/pricing-faqs/). diff --git a/src/content/docs/knowledge-and-collaboration/warp-drive/agent-mode-context.mdx b/src/content/docs/knowledge-and-collaboration/warp-drive/agent-mode-context.mdx index 79e885f9..247cc7f3 100644 --- a/src/content/docs/knowledge-and-collaboration/warp-drive/agent-mode-context.mdx +++ b/src/content/docs/knowledge-and-collaboration/warp-drive/agent-mode-context.mdx @@ -7,7 +7,7 @@ sidebar: label: "Agent Mode context" --- -[Agent Mode](/agent-platform/local-agents/interacting-with-agents/) can leverage your [Warp Drive](/knowledge-and-collaboration/warp-drive/) contents to tailor responses to your personal and team developer workflows and environments. +Warp's agents automatically pull context from your Warp Drive contents, including Workflows, Notebooks, Environment Variables, Rules, and MCP Servers, to generate responses tailored to your personal and team developer workflows. Referenced objects appear as citations in the conversation. ## Objects used as context diff --git a/src/content/docs/knowledge-and-collaboration/warp-drive/environment-variables.mdx b/src/content/docs/knowledge-and-collaboration/warp-drive/environment-variables.mdx index c4f893e9..fcfdcf98 100644 --- a/src/content/docs/knowledge-and-collaboration/warp-drive/environment-variables.mdx +++ b/src/content/docs/knowledge-and-collaboration/warp-drive/environment-variables.mdx @@ -4,6 +4,8 @@ description: >- Save or sync environment variables to load into your terminal sessions. --- +Environment Variables in Warp Drive let you save, sync, and load environment variables into your terminal sessions with a click. Support for both static values and dynamic secrets from external managers like 1Password, LastPass, and Hashicorp Vault keeps credentials secure and out of source code. + ## What are environment variables in Warp? Environment variables in Warp are similar to .env files, except you can: diff --git a/src/content/docs/knowledge-and-collaboration/warp-drive/index.mdx b/src/content/docs/knowledge-and-collaboration/warp-drive/index.mdx index 8ac2546a..690c3bc9 100644 --- a/src/content/docs/knowledge-and-collaboration/warp-drive/index.mdx +++ b/src/content/docs/knowledge-and-collaboration/warp-drive/index.mdx @@ -8,6 +8,8 @@ description: >- import { Tabs, TabItem } from '@astrojs/starlight/components'; import VideoEmbed from '@components/VideoEmbed.astro'; +Warp Drive is a built-in workspace for saving and sharing Workflows, Notebooks, Prompts, and Environment Variables across your team. All objects sync in real time, so you and your team always have access to the latest versions, whether you're working locally or collaborating across an organization. + ## What is Warp Drive? All objects stored in Warp Drive sync immediately as they’re updated, so you and your team will always have access to the latest versions. diff --git a/src/content/docs/knowledge-and-collaboration/warp-drive/notebooks.mdx b/src/content/docs/knowledge-and-collaboration/warp-drive/notebooks.mdx index 8259d964..cd1428b9 100644 --- a/src/content/docs/knowledge-and-collaboration/warp-drive/notebooks.mdx +++ b/src/content/docs/knowledge-and-collaboration/warp-drive/notebooks.mdx @@ -7,6 +7,8 @@ sidebar: --- import { Tabs, TabItem } from '@astrojs/starlight/components'; +Notebooks are interactive, runnable documents in Warp Drive that combine markdown text with executable shell command blocks. Use them for onboarding playbooks, debugging runbooks, and development workflows that teammates can search, share, and execute directly from the terminal. + ### What is a Notebook? Notebooks are runnable documentation consisting of markdown text and list elements, code blocks, and runnable shell snippets that can be automatically executed in your terminal session. Notebooks are searchable and accessible through the [Command Palette](/terminal/command-palette/) so you can access and run your documentation without ever leaving the terminal. You can also export Notebooks in .md format at any time. diff --git a/src/content/docs/knowledge-and-collaboration/warp-drive/prompts.mdx b/src/content/docs/knowledge-and-collaboration/warp-drive/prompts.mdx index 59119a24..b4fd44d4 100644 --- a/src/content/docs/knowledge-and-collaboration/warp-drive/prompts.mdx +++ b/src/content/docs/knowledge-and-collaboration/warp-drive/prompts.mdx @@ -7,6 +7,8 @@ sidebar: --- import VideoEmbed from '@components/VideoEmbed.astro'; +Prompts are parameterized natural language queries you can save in Warp Drive and reuse with agents. Name a prompt, add arguments for dynamic values, and execute it from the Command Palette or Warp Drive to repeat complex agent workflows without retyping. + ## What is a prompt? A prompt is a parameterized natural language query you can name and save in Warp to use with [Agent Mode](/agent-platform/local-agents/interacting-with-agents/). diff --git a/src/content/docs/knowledge-and-collaboration/warp-drive/web.mdx b/src/content/docs/knowledge-and-collaboration/warp-drive/web.mdx index 420a2892..be8f38b7 100644 --- a/src/content/docs/knowledge-and-collaboration/warp-drive/web.mdx +++ b/src/content/docs/knowledge-and-collaboration/warp-drive/web.mdx @@ -5,6 +5,8 @@ description: >- screen device, including mobile phones, tablets, and touch-enabled laptops. --- +Warp Drive on the Web lets you view and edit Warp Drive objects and shared sessions directly in any browser, including mobile devices and tablets. Access Workflows, Notebooks, Prompts, and session transcripts from anywhere without installing the Warp desktop app. + ## What is Warp on the web? Warp Drive on the Web lets you view and edit your Warp Drive objects and shared sessions directly in the browser, on any device. diff --git a/src/content/docs/knowledge-and-collaboration/warp-drive/workflows.mdx b/src/content/docs/knowledge-and-collaboration/warp-drive/workflows.mdx index baf7b737..307d1a40 100644 --- a/src/content/docs/knowledge-and-collaboration/warp-drive/workflows.mdx +++ b/src/content/docs/knowledge-and-collaboration/warp-drive/workflows.mdx @@ -9,6 +9,8 @@ sidebar: import DemoVideo from '@components/DemoVideo.astro'; import VideoEmbed from '@components/VideoEmbed.astro'; +Workflows are parameterized commands you can name, save, and share in Warp Drive. Define arguments with default values, add descriptions for search, and execute workflows from the Command Palette or Warp Drive to run frequently used commands without retyping them. + ## What is a workflow? A workflow is a parameterized command you can name and save in Warp with descriptions and arguments. Workflows are searchable and easily accessed from the [Command Palette](/terminal/command-palette/) so you can find and execute them without switching contexts. @@ -19,7 +21,7 @@ You can create a new workflow from various entry points in Warp: * From Warp Drive, + > New workflow * Using Block Actions, Save as Workflow -* From Oz agent results, Save as Workflow +* From agent results, Save as Workflow * From the [Command Palette](/terminal/command-palette/), Create a New Personal Workflow Any of these entry points will open the workflow editor where you can: @@ -81,7 +83,7 @@ Once a workflow has been created, you can edit it at any time, as long as you ha #### AI Autofill -Workflows also have the option to use an [Oz agent](/agent-platform/local-agents/overview/) to automatically generate a title, descriptions, or parameters. +Workflows also have the option to use an [agent](/agent-platform/local-agents/overview/) to automatically generate a title, descriptions, or parameters. * Create or edit a Workflow, in the edit view you should see the option to AutoFill. * Warp will fill in the fields based on the Workflow you're creating. diff --git a/src/content/docs/quickstart.mdx b/src/content/docs/quickstart.mdx index 92755569..c23cbb73 100644 --- a/src/content/docs/quickstart.mdx +++ b/src/content/docs/quickstart.mdx @@ -6,7 +6,7 @@ description: >- --- import { Tabs, TabItem } from '@astrojs/starlight/components'; -This guide walks you through installing Warp, trying the terminal features you'll use every day, and firing off your first agent prompt. After completing the steps in this guide, you'll have a working Warp setup and a clear picture of how terminal commands and agents work together. +Get up and running with Warp in about 10 minutes. Install the app, run your first commands using Blocks and the modern text editor, and start an agent conversation to write code, debug issues, or explore your codebase, all from natural language prompts inside the terminal. --- @@ -116,5 +116,5 @@ Now that you have the basics, check out the features that make Warp a full devel * **[Customizing Warp](/getting-started/quickstart/customizing-warp/)** — Pick a theme, configure your prompt, choose your AI model, and import keybindings from another terminal. * **[Codebase Context](/agent-platform/capabilities/codebase-context/)** — Index your Git repositories so agents understand your code and give context-aware answers across large, multi-repo systems. -* **[Oz cloud agents](/agent-platform/cloud-agents/overview/)** — Run agents in the background for PR review, issue triage, dependency updates, and other tasks that don't need your immediate attention. +* **[Cloud agents](/agent-platform/cloud-agents/overview/)** — Run agents in the background for PR review, issue triage, dependency updates, and other tasks that don't need your immediate attention. * **[Keyboard shortcuts](/getting-started/keyboard-shortcuts/)** — The full shortcut reference for power users. diff --git a/src/content/docs/reference/api-and-sdk/demo-sentry-monitoring-with-sdk.mdx b/src/content/docs/reference/api-and-sdk/demo-sentry-monitoring-with-sdk.mdx index 776b2da1..1eb31e6f 100644 --- a/src/content/docs/reference/api-and-sdk/demo-sentry-monitoring-with-sdk.mdx +++ b/src/content/docs/reference/api-and-sdk/demo-sentry-monitoring-with-sdk.mdx @@ -1,7 +1,7 @@ --- title: "Demo: Sentry monitoring with SDK" description: >- - Build a Sentry webhook handler that triggers Oz agents to investigate errors + Build a Sentry webhook handler that triggers agents to investigate errors and create draft PRs. --- import VideoEmbed from '@components/VideoEmbed.astro'; diff --git a/src/content/docs/reference/api-and-sdk/index.mdx b/src/content/docs/reference/api-and-sdk/index.mdx index 045ca861..152d8643 100644 --- a/src/content/docs/reference/api-and-sdk/index.mdx +++ b/src/content/docs/reference/api-and-sdk/index.mdx @@ -8,6 +8,8 @@ description: >- --- import VideoEmbed from '@components/VideoEmbed.astro'; +The Oz API and SDKs let you create, monitor, and inspect cloud agent runs programmatically. Use the REST API from any HTTP client, or the official Python and TypeScript SDKs for typed requests, built-in retries, and structured error handling. The SDKs are ideal for CI pipelines, internal tools, and custom integrations. + ### Oz API The Oz API lets you create and inspect [Cloud Agent](/agent-platform/cloud-agents/overview/) runs over HTTP from any system (CI, cron, backend services, internal tools), without requiring the Warp desktop app. @@ -24,7 +26,7 @@ This page is a high-level overview.\ For full API endpoint details, please refer to the [**Agents API Reference**](/api)**.** For schema definitions, see the SDK repos: [**Python SDK**](https://github.com/warpdotdev/oz-sdk-python) and [**TypeScript SDK**](https://github.com/warpdotdev/oz-sdk-typescript). ::: -### Oz Agent SDK +### Oz SDK Oz provides official [Python](https://github.com/warpdotdev/oz-sdk-python) and [TypeScript](https://github.com/warpdotdev/oz-sdk-typescript) SDKs that wrap the Oz API with: @@ -126,7 +128,7 @@ The API shares a set of reusable models across endpoints. Detailed JSON schemas, --- -## Oz Agent SDKs +## Oz SDKs ### Python SDK diff --git a/src/content/docs/reference/cli/agent-profiles.mdx b/src/content/docs/reference/cli/agent-profiles.mdx index 575f3e45..91dc9787 100644 --- a/src/content/docs/reference/cli/agent-profiles.mdx +++ b/src/content/docs/reference/cli/agent-profiles.mdx @@ -7,6 +7,8 @@ sidebar: label: "Agent Profiles" --- +Agent profiles control what the agent can do, how it behaves, and where it can act when running from the Oz CLI. Create profiles in the Warp app to configure file access, command execution, MCP server usage, model selection, and directory permissions, then reference them by ID in CLI commands. + Agent profiles control three things: * **What the agent can do** — file access, command execution, and MCP server usage diff --git a/src/content/docs/reference/cli/federate.mdx b/src/content/docs/reference/cli/federate.mdx index fe638baa..ecfcc9da 100644 --- a/src/content/docs/reference/cli/federate.mdx +++ b/src/content/docs/reference/cli/federate.mdx @@ -1,7 +1,7 @@ --- title: Federated identity tokens description: >- - Issue short-lived OIDC identity tokens from a running Oz agent so it can + Issue short-lived OIDC identity tokens from a running agent so it can authenticate to cloud providers without long-lived credentials. sidebar: label: "Federated identity" @@ -9,7 +9,7 @@ sidebar: `oz federate` issues short-lived OIDC identity tokens for the agent that's currently running. Use these tokens to authenticate to cloud providers (AWS, GCP, Azure, and other OIDC-aware systems) without baking long-lived credentials into your environment. -This command can only be called from inside a running Oz agent session — typically as part of a [skill](/agent-platform/capabilities/skills/), a tool, or a script the agent executes while a run is in progress. +This command can only be called from inside a running agent session — typically as part of a [skill](/agent-platform/capabilities/skills/), a tool, or a script the agent executes while a run is in progress. ## When to use federation diff --git a/src/content/docs/reference/cli/index.mdx b/src/content/docs/reference/cli/index.mdx index 816674cf..86022205 100644 --- a/src/content/docs/reference/cli/index.mdx +++ b/src/content/docs/reference/cli/index.mdx @@ -7,6 +7,8 @@ description: >- --- import { Tabs, TabItem } from '@astrojs/starlight/components'; +The Oz CLI is the command-line tool for running and managing Warp's cloud agents from any terminal, script, or CI pipeline. Use it to start agents locally or in the cloud, connect MCP servers, configure integrations, and authenticate without requiring the Warp desktop app. + :::note **`warp-cli` is deprecated and has been replaced by `oz`.** If you have `warp-cli` installed, it will auto-update to `oz`. All the same commands are available, just replace `warp-cli` with `oz` in your scripts and workflows. ::: diff --git a/src/content/docs/reference/cli/troubleshooting.mdx b/src/content/docs/reference/cli/troubleshooting.mdx index 81658beb..025b9d80 100644 --- a/src/content/docs/reference/cli/troubleshooting.mdx +++ b/src/content/docs/reference/cli/troubleshooting.mdx @@ -5,6 +5,8 @@ description: >- failures, environments, GitHub access, and Docker image issues. --- +Solutions for common Oz CLI errors, including authentication issues, agent failures, environment configuration, GitHub access problems, and Docker image compatibility. Use `oz help` for built-in documentation on any command. + ## Getting help The CLI includes built-in documentation for all commands: diff --git a/src/content/docs/reference/cli/warp-drive.mdx b/src/content/docs/reference/cli/warp-drive.mdx index 3311a9eb..3cda4c1c 100644 --- a/src/content/docs/reference/cli/warp-drive.mdx +++ b/src/content/docs/reference/cli/warp-drive.mdx @@ -7,6 +7,8 @@ sidebar: label: "Warp Drive Context" --- +Reference saved Warp Drive objects in Oz CLI commands to reuse prompts, notebooks, workflows, and rules as agent context. Pass a saved prompt ID with `--saved-prompt` or inline Warp Drive references using ``, ``, or `` syntax. + ## Reusing saved prompts When you find prompts that work well, save them in [Warp Drive](/knowledge-and-collaboration/warp-drive/) to reuse across sessions, share with teammates, and integrate into automated workflows. For more information, see [Prompts](/knowledge-and-collaboration/warp-drive/prompts/). diff --git a/src/content/docs/reference/index.mdx b/src/content/docs/reference/index.mdx index 360872bd..4acfd0f2 100644 --- a/src/content/docs/reference/index.mdx +++ b/src/content/docs/reference/index.mdx @@ -4,7 +4,7 @@ description: >- Technical reference documentation for the Oz CLI, API, and SDK. --- -This section covers the programmatic interfaces for running and managing Oz agents in CI pipelines, scripts, backend services, and custom tooling. +Technical reference documentation for the Oz CLI, API, and SDKs. Use these programmatic interfaces to run and manage agents from CI pipelines, scripts, backend services, and custom tooling without requiring the Warp desktop app. ## CLI @@ -15,7 +15,7 @@ The [Oz CLI](/reference/cli/) lets you run and configure agents from any environ - [MCP Servers](/reference/cli/mcp-servers/) - Pass MCP server configuration to agent runs using the `--mcp` flag, by UUID, inline JSON, or file path. - [Skills](/reference/cli/skills/) - Run agents from reusable instruction sets stored in your repositories using the `--skill` flag. - [Warp Drive Context](/reference/cli/warp-drive/) - Reference saved prompts, notebooks, workflows, and rules from Warp Drive directly in CLI agent commands. -- [Integration Setup](/reference/cli/integration-setup/) - Configure environments and connect external tools like Slack and Linear so you can trigger Oz agents from outside the terminal. +- [Integration Setup](/reference/cli/integration-setup/) - Configure environments and connect external tools like Slack and Linear so you can trigger agents from outside the terminal. - [Troubleshooting](/reference/cli/troubleshooting/) - Find solutions to common CLI errors, including authentication issues, agent failures, environment problems, and Docker image issues. ## API & SDK diff --git a/src/content/docs/support-and-community/community/open-source-partnership.mdx b/src/content/docs/support-and-community/community/open-source-partnership.mdx index 077761a3..8694c0a5 100644 --- a/src/content/docs/support-and-community/community/open-source-partnership.mdx +++ b/src/content/docs/support-and-community/community/open-source-partnership.mdx @@ -1,21 +1,21 @@ --- title: Oz Open Source Partnership description: >- - Warp supports high-impact open source projects with free Oz agent credits + Warp supports high-impact open source projects with free agent credits through the Oz Open Source Partnership program. --- -Warp is committed to supporting the open source community. Through the Oz Open Source Partnership program, we offer free Oz agent usage credits to high-impact open source projects, helping maintainers and contributors accelerate their development workflows. +Warp is committed to supporting the open source community. Through the Oz Open Source Partnership program, we offer free agent usage credits to high-impact open source projects, helping maintainers and contributors accelerate their development workflows. ## What you get -* **Free Oz credits** - Receive complimentary credits to run Oz agents on your open source project -* **Oz agent access** - Use cloud agents to automate tasks like code review, bug triage, documentation, and more across your repositories -* **Ongoing support** - Warp partners with accepted projects to ensure they get the most value from Oz agents +* **Free Oz credits** - Receive complimentary credits to run agents on your open source project +* **Agent access** - Use cloud agents to automate tasks like code review, bug triage, documentation, and more across your repositories +* **Ongoing support** - Warp partners with accepted projects to ensure they get the most value from agents ## Who can apply -The Oz Open Source Partnership program is designed for actively maintained, high-impact open source projects. When reviewing applications, we consider factors like community size, project activity, and the potential impact of Oz agents on your workflow. +The Oz Open Source Partnership program is designed for actively maintained, high-impact open source projects. When reviewing applications, we consider factors like community size, project activity, and the potential impact of agents on your workflow. :::note Have questions about the program? Reach out to us at [support@warp.dev](mailto:support@warp.dev). @@ -26,5 +26,5 @@ Have questions about the program? Reach out to us at [support@warp.dev](mailto:s Tell us about your open source project by filling out the [application form](https://tally.so/r/LZWxqG). We'll review your submission and follow up with next steps. :::note -The Oz Open Source Partnership program provides free Oz agent credits for open source projects. This is separate from Warp's open source client — the Warp client is published under AGPL v3 at [`warpdotdev/warp`](https://github.com/warpdotdev/warp); see [Contributing to Warp](/support-and-community/community/contributing/). For sponsorship opportunities for your project, reach out to [partnerships@warp.dev](mailto:partnerships@warp.dev). +The Oz Open Source Partnership program provides free agent credits for open source projects. This is separate from Warp's open source client — the Warp client is published under AGPL v3 at [`warpdotdev/warp`](https://github.com/warpdotdev/warp); see [Contributing to Warp](/support-and-community/community/contributing/). For sponsorship opportunities for your project, reach out to [partnerships@warp.dev](mailto:partnerships@warp.dev). ::: diff --git a/src/content/docs/support-and-community/index.mdx b/src/content/docs/support-and-community/index.mdx index 36217137..c58f94b9 100644 --- a/src/content/docs/support-and-community/index.mdx +++ b/src/content/docs/support-and-community/index.mdx @@ -43,7 +43,7 @@ We host [live events](https://luma.com/warpdotdev) year-round — product demos, * [**Warp Preview**](/support-and-community/community/warp-preview-and-alpha-program/) — Try experimental features before anyone else. Your feedback directly shapes what ships. * [**Refer a Friend**](/support-and-community/community/refer-a-friend/) — Send Warp to a developer you think would love it. Earn themes, swag, and gift cards. -* [**Oz Open Source Partnership**](/support-and-community/community/open-source-partnership/) — Free Oz agent credits for high-impact open source projects. +* [**Oz Open Source Partnership**](/support-and-community/community/open-source-partnership/) — Free agent credits for high-impact open source projects. :::note **Ambassador program** diff --git a/src/content/docs/support-and-community/plans-and-billing/bring-your-own-api-key.mdx b/src/content/docs/support-and-community/plans-and-billing/bring-your-own-api-key.mdx index 48f6354d..b3c95398 100644 --- a/src/content/docs/support-and-community/plans-and-billing/bring-your-own-api-key.mdx +++ b/src/content/docs/support-and-community/plans-and-billing/bring-your-own-api-key.mdx @@ -26,7 +26,7 @@ When you add your own model API keys in Warp, those keys are stored **locally on Warp uses these API keys to directly route your agent requests to the model provider you've configured. :::caution -BYOK does not apply to [Oz Cloud Agents](/agent-platform/cloud-agents/overview/). Because your API keys are stored locally on your device, they are not available to cloud-hosted agent runs. Cloud agent runs always consume [Warp credits](/support-and-community/plans-and-billing/credits/). +BYOK does not apply to [Cloud Agents](/agent-platform/cloud-agents/overview/). Because your API keys are stored locally on your device, they are not available to cloud-hosted agent runs. Cloud agent runs always consume [Warp credits](/support-and-community/plans-and-billing/credits/). ::: When a model is selected using your own key: @@ -81,7 +81,7 @@ Some AI-powered features are not affected by BYOK and are included as part of Wa | ----------------------------------------------------------------------------- | ------------------- | -------------------------------------------------------------------- | | [Active AI Recommendations](/agent-platform/local-agents/active-ai/) | No | Always included with Build and higher plans. | | [Codebase Context](/agent-platform/capabilities/codebase-context/) | Yes | Uses Warp's AI infrastructure and consumes credits. | -| [Oz Cloud Agents](/agent-platform/cloud-agents/overview/) | Yes | BYOK keys are stored locally and not available to cloud-hosted runs. | +| [Cloud Agents](/agent-platform/cloud-agents/overview/) | Yes | BYOK keys are stored locally and not available to cloud-hosted runs. | These features will continue to function normally regardless of whether you’ve configured BYOK. diff --git a/src/content/docs/support-and-community/plans-and-billing/index.mdx b/src/content/docs/support-and-community/plans-and-billing/index.mdx index ae1490f1..692b4fc9 100644 --- a/src/content/docs/support-and-community/plans-and-billing/index.mdx +++ b/src/content/docs/support-and-community/plans-and-billing/index.mdx @@ -5,7 +5,7 @@ description: >- billing settings. --- -Warp offers flexible plans designed for individual developers, teams, and enterprises. Learn about pricing, credits, and billing options. +Warp offers flexible plans for individual developers, teams, and enterprises, with credits powering all agent features. Choose from plan-included credits, add-on credit purchases, automatic reloads, or bring-your-own API keys. Compare plans, manage billing, and track credit usage from your account settings. * [**Plans & Pricing**](/support-and-community/plans-and-billing/plans-pricing-refunds/) - Compare plans, pricing tiers, and refund policies * [**Credits**](/support-and-community/plans-and-billing/credits/) - How credits are used and calculated across AI features diff --git a/src/content/docs/support-and-community/plans-and-billing/platform-credits.mdx b/src/content/docs/support-and-community/plans-and-billing/platform-credits.mdx index c70d85a2..3509ceb4 100644 --- a/src/content/docs/support-and-community/plans-and-billing/platform-credits.mdx +++ b/src/content/docs/support-and-community/plans-and-billing/platform-credits.mdx @@ -27,7 +27,7 @@ The three buckets are independent and a single run can consume from more than on ## How platform credits are measured -Platform credits accrue while an Oz agent is actively working on a task — from when the task starts running to when it finishes, fails, or is cancelled. Idle time, time spent waiting on user input, and time before the task starts don't accrue platform credits. +Platform credits accrue while an agent is actively working on a task — from when the task starts running to when it finishes, fails, or is cancelled. Idle time, time spent waiting on user input, and time before the task starts don't accrue platform credits. See [warp.dev/pricing](https://warp.dev/pricing) for current rates. @@ -37,7 +37,7 @@ Whether platform credits apply depends on where the agent runs and who's paying ### Uses platform credits -* **Cloud agents on any plan** use platform credits for every cloud agent run, regardless of which agent runs the task (Warp Agent, Claude Code, Codex, or Gemini), inference source (Warp-managed, BYOK, or BYOLLM), or compute source (Warp-hosted or self-hosted workers). Warp's platform infrastructure coordinates every cloud agent run. +* **Cloud agents on any plan** use platform credits for every cloud agent run, regardless of which agent runs the task (Warp Agent, Claude Code, or Codex), inference source (Warp-managed, BYOK, or BYOLLM), or compute source (Warp-hosted or self-hosted workers). Warp's platform infrastructure coordinates every cloud agent run. * **Local agents on Business or Enterprise with customer-supplied inference** use platform credits when the local agent run uses [BYOK](/support-and-community/plans-and-billing/bring-your-own-api-key/) or BYOLLM via Amazon Bedrock or Google Vertex. Warp isn't paying for the model call, but Warp's platform infrastructure is still running the local agent. BYOK and customer-supplied inference are subject to plan-size eligibility — see the callout above. ### Doesn't use platform credits diff --git a/src/content/docs/support-and-community/plans-and-billing/pricing-faqs.mdx b/src/content/docs/support-and-community/plans-and-billing/pricing-faqs.mdx index 2ee0d98d..df8c3815 100644 --- a/src/content/docs/support-and-community/plans-and-billing/pricing-faqs.mdx +++ b/src/content/docs/support-and-community/plans-and-billing/pricing-faqs.mdx @@ -162,7 +162,7 @@ Warp doesn’t currently offer discounts for students or non-profits. We recomme For open source teams, two paths are available: -* The [Oz Open Source Partnership](/support-and-community/community/open-source-partnership/) program offers free Oz agent credits to high-impact open source projects. +* The [Oz Open Source Partnership](/support-and-community/community/open-source-partnership/) program offers free agent credits to high-impact open source projects. * Warp's client itself is open source under [AGPL v3](https://github.com/warpdotdev/warp/blob/master/LICENSE-AGPL), so you can build, run, and contribute to it directly. See [Contributing to Warp](/support-and-community/community/contributing/) for the flow. ### Where is Warp Drive data for my team stored? diff --git a/src/content/docs/support-and-community/troubleshooting-and-support/known-issues.mdx b/src/content/docs/support-and-community/troubleshooting-and-support/known-issues.mdx index e27cdac8..92edb5ce 100644 --- a/src/content/docs/support-and-community/troubleshooting-and-support/known-issues.mdx +++ b/src/content/docs/support-and-community/troubleshooting-and-support/known-issues.mdx @@ -23,7 +23,7 @@ To enable Blocks over SSH, Warp uses an SSH Wrapper function; navigate to settin ### Online features don't work -There is a known issue that can occur that causes online features to break ([Oz agent](/agent-platform/local-agents/overview/), [Generate](/agent-platform/local-agents/overview/), [Block Sharing](/terminal/blocks/block-sharing/), [Refer a Friend](/support-and-community/community/refer-a-friend/) ). This is due to the login token going stale, typically due to a password change, and can be resolved by the following steps: +There is a known issue that can occur that causes online features to break ([Agent](/agent-platform/local-agents/overview/), [Generate](/agent-platform/local-agents/overview/), [Block Sharing](/terminal/blocks/block-sharing/), [Refer a Friend](/support-and-community/community/refer-a-friend/) ). This is due to the login token going stale, typically due to a password change, and can be resolved by the following steps: diff --git a/src/content/docs/support-and-community/troubleshooting-and-support/using-warp-offline.mdx b/src/content/docs/support-and-community/troubleshooting-and-support/using-warp-offline.mdx index 3a071c24..b4672966 100644 --- a/src/content/docs/support-and-community/troubleshooting-and-support/using-warp-offline.mdx +++ b/src/content/docs/support-and-community/troubleshooting-and-support/using-warp-offline.mdx @@ -17,7 +17,7 @@ Warp is "Offline" when you aren't connected to the internet, or if you're blocki Warp’s cloud-based features which require an internet connection will not work in offline mode. Those features include: * [Warp Drive](/knowledge-and-collaboration/warp-drive/#using-warp-drive-offline) (Some files may be read-only in offline mode) -* [Oz agent](/agent-platform/local-agents/overview/) +* [Agent](/agent-platform/local-agents/overview/) * [Agent Mode](/agent-platform/local-agents/interacting-with-agents/) * [Generate](/agent-platform/local-agents/overview/) * [AI Autofill](/knowledge-and-collaboration/warp-drive/workflows/#warp-ai-autofill) diff --git a/src/content/docs/terminal/blocks/index.mdx b/src/content/docs/terminal/blocks/index.mdx index 501e8cdf..f339991f 100644 --- a/src/content/docs/terminal/blocks/index.mdx +++ b/src/content/docs/terminal/blocks/index.mdx @@ -5,6 +5,8 @@ description: >- --- import VideoEmbed from '@components/VideoEmbed.astro'; +Blocks are Warp's fundamental unit for organizing terminal output. Every command and its output is grouped into a single Block that you can copy, search, filter, bookmark, share, and navigate independently — replacing the endless scroll of traditional terminals with structured, actionable output. + ## What are Blocks? Blocks enable us to easily: diff --git a/src/content/docs/terminal/command-palette.mdx b/src/content/docs/terminal/command-palette.mdx index 0dbfd508..7dc3999d 100644 --- a/src/content/docs/terminal/command-palette.mdx +++ b/src/content/docs/terminal/command-palette.mdx @@ -7,6 +7,8 @@ description: >- import { Tabs, TabItem } from '@astrojs/starlight/components'; import VideoEmbed from '@components/VideoEmbed.astro'; +The Command Palette is Warp's global search interface for quickly finding and launching Workflows, Notebooks, Prompts, keyboard shortcuts, file searches, settings, and other actions. Open it with a keyboard shortcut, then type or filter results by type to find exactly what you need. +
![Command Palette Panel](../../../assets/terminal/command-palette-panel.png)
Command Palette Panel.
diff --git a/src/content/docs/terminal/editor/index.mdx b/src/content/docs/terminal/editor/index.mdx index 9649b964..07d7dd78 100644 --- a/src/content/docs/terminal/editor/index.mdx +++ b/src/content/docs/terminal/editor/index.mdx @@ -7,6 +7,8 @@ description: >- import { Tabs, TabItem } from '@astrojs/starlight/components'; import VideoEmbed from '@components/VideoEmbed.astro'; +Warp's input editor works like a modern IDE text editor, with cursor movement, click-to-place, multi-line editing, copy-paste, word selection, and soft wrapping built in. Unlike traditional terminals, you can edit commands the same way you edit code — no memorizing shell-specific shortcuts required. + :::note Text Editor Input also works for [SSH sessions](/terminal/warpify/ssh/). ::: diff --git a/src/content/docs/terminal/input/classic-input.mdx b/src/content/docs/terminal/input/classic-input.mdx index 35195998..bdc1bd6e 100644 --- a/src/content/docs/terminal/input/classic-input.mdx +++ b/src/content/docs/terminal/input/classic-input.mdx @@ -29,22 +29,22 @@ You can enter Agent Mode in a few ways: - * Type any natural language, like a task or a question, in the terminal input. Warp will recognize natural language with a local auto-detection feature and prepare to send your query to an Oz agent. + * Type any natural language, like a task or a question, in the terminal input. Warp will recognize natural language with a local auto-detection feature and prepare to send your query to an agent. * Use the keyboard shortcut `⌘+I` to toggle into Agent Mode, or type `*+Space`. * Click the “AI” sparkles icon in the menu bar, and this will open a new terminal pane that starts in Agent Mode. - * From a block you want to ask an Oz agent about, you can click the sparkles icon in the toolbelt, or click on its block context menu item "Attach block(s) to AI query". + * From a block you want to ask an agent about, you can click the sparkles icon in the toolbelt, or click on its block context menu item "Attach block(s) to AI query". - * Type any natural language, like a task or a question, in the terminal input. Warp will recognize natural language with a local auto-detection feature and prepare to send your query to an Oz agent. + * Type any natural language, like a task or a question, in the terminal input. Warp will recognize natural language with a local auto-detection feature and prepare to send your query to an agent. * Use the keyboard shortcut `Ctrl+I` to toggle into Agent Mode, or type `*+Space`. * Click the "AI" sparkles icon in the menu bar, and this will open a new terminal pane that starts in Agent Mode. - * From a block you want to ask an Oz agent about, you can click the sparkles icon in the toolbelt, or click on its block context menu item "Attach block(s) to AI query". + * From a block you want to ask an agent about, you can click the sparkles icon in the toolbelt, or click on its block context menu item "Attach block(s) to AI query". - * Type any natural language, like a task or a question, in the terminal input. Warp will recognize natural language with a local auto-detection feature and prepare to send your query to an Oz agent. + * Type any natural language, like a task or a question, in the terminal input. Warp will recognize natural language with a local auto-detection feature and prepare to send your query to an agent. * Use the keyboard shortcut `Ctrl+I` to toggle into Agent Mode, or type `*+Space`. * Click the "AI" sparkles icon in the menu bar, and this will open a new terminal pane that starts in Agent Mode. - * From a block you want to ask an Oz agent about, you can click the sparkles icon in the toolbelt, or click on its block context menu item "Attach block(s) to AI query". + * From a block you want to ask an agent about, you can click the sparkles icon in the toolbelt, or click on its block context menu item "Attach block(s) to AI query". diff --git a/src/content/docs/terminal/sessions/index.mdx b/src/content/docs/terminal/sessions/index.mdx index 746c27b9..0a66f04a 100644 --- a/src/content/docs/terminal/sessions/index.mdx +++ b/src/content/docs/terminal/sessions/index.mdx @@ -7,6 +7,8 @@ description: >- import DemoVideo from '@components/DemoVideo.astro'; import VideoEmbed from '@components/VideoEmbed.astro'; +Warp sessions let you navigate between terminal sessions and automatically restore your workspace when you relaunch the app. Session Navigation helps you quickly switch between active sessions, while Session Restoration preserves your windows, tabs, and panes across restarts. + 1. [Session Navigation](/terminal/sessions/session-navigation/) enables you to easily navigate to any session in Warp. 2. [Session Restoration](/terminal/sessions/session-restoration/) automatically restores the window and tabs from your previous session. diff --git a/src/content/docs/terminal/windows/vertical-tabs.mdx b/src/content/docs/terminal/windows/vertical-tabs.mdx index 2137af19..dcee474a 100644 --- a/src/content/docs/terminal/windows/vertical-tabs.mdx +++ b/src/content/docs/terminal/windows/vertical-tabs.mdx @@ -33,7 +33,7 @@ Vertical tabs are especially useful when running multiple coding agents side by ### Tab management * **Search, drag and drop, and renaming** - Filter panes by title, directory, or branch; reorder tabs or move panes between tabs by dragging; double-click a tab to rename it inline. -* **New tab menu** - Create agent tabs, terminal tabs, Oz cloud agent sessions, worktree configs, and [Tab Configs](/terminal/windows/tab-configs/) from a unified **+** menu. +* **New tab menu** - Create agent tabs, terminal tabs, cloud agent sessions, worktree configs, and [Tab Configs](/terminal/windows/tab-configs/) from a unified **+** menu. ## Enabling vertical tabs @@ -141,7 +141,7 @@ Click the **+** button in the control bar to open the new tab menu. The menu inc * **Agent** - Open a new agent tab. * **Terminal** - Open a new terminal tab. -* **Oz cloud agent** - Open a new Oz cloud agent session tab. +* **Cloud agent** - Open a new cloud agent session tab. * **Tab Configs** - Any [Tab Configs](/terminal/windows/tab-configs/) you've created appear as menu items for one-click setup. * **New worktree config** - Create a new worktree-based Tab Config. * **New tab config** - Create a new Tab Config from a starter template. diff --git a/src/pages/api.astro b/src/pages/api.astro index dc0f183d..e4fc84cf 100644 --- a/src/pages/api.astro +++ b/src/pages/api.astro @@ -2,7 +2,7 @@ // Standalone Scalar API reference — not embedded in Starlight. // Accessible at docs.warp.dev/api // Spec lives at `developers/agent-api-openapi.yaml`, synced from the -// upstream Oz Agent API source. Re-sync that file when the API changes +// upstream Agent API source. Re-sync that file when the API changes // and this page picks it up at the next build. // // Note on `set:html={specJson}` below: the injected value is JSON.stringify() @@ -27,24 +27,24 @@ const specJson = JSON.stringify(specObject); - Oz Agent API Reference | Warp - + Agent API Reference | Warp + - - + + - + - - + + {/* PushFeedback CSS + JS are NOT loaded here — the lazy loader inside @@ -218,8 +218,8 @@ const specJson = JSON.stringify(specObject); // doesn't show a fake "interactive" affordance (per scalar/scalar#5079). defaultOpenAllTags: true, metaData: { - title: 'Oz Agent API Reference', - description: 'Interactive API reference for the Oz Agent API.', + title: 'Agent API Reference', + description: 'Interactive API reference for the Agent API.', }, // --------------------------------------------------------------- // Scalar consumes `customCss` as a runtime string, so we can't