@openhands/agent-canvas 1.1.0 → 1.2.0

package/dist/node_modules/@openhands/extensions/skills/index.js

@@ -30,7 +30,7 @@ var e = [
 			"X-Session-API-Key",
 			"localhost:8001"
 		],
-		content: "# Agent Canvas Environment\n\nUse this skill when running inside or alongside a local Agent Canvas stack, especially when the user asks to inspect the local backend, create or monitor local conversations, or delegate work to another local conversation.\n\n## Core rules\n\n- Treat the local Agent Canvas backend as an agent-server API, usually `http://localhost:8001`.\n- Treat the local UI as a separate frontend, usually `http://localhost:8000`.\n- Do not print session API keys. Pass them directly in `X-Session-API-Key`.\n- Trust any runtime-services block or explicit user-provided host over default ports.\n- Before mutating a repository, check `git status -sb`. If a worktree has unrelated changes, use a separate worktree or clone.\n- When delegating, write a self-contained prompt. The new conversation does not inherit the current chat context.\n\n## Find the session key\n\nUse the first available value, without echoing it:\n\n```bash\nKEY=\"${SESSION_API_KEY:-${OH_SESSION_API_KEYS_0:-${LOCAL_BACKEND_API_KEY:-}}}\"\nif [ -z \"$KEY\" ] && [ -f \"$HOME/.openhands/agent-canvas/api-key.txt\" ]; then\n  KEY=\"$(tr -d '\\n' < \"$HOME/.openhands/agent-canvas/api-key.txt\")\"\nfi\ntest -n \"$KEY\" || { echo \"No Agent Canvas session API key found\" >&2; exit 1; }\n```\n\nValidate backend access:\n\n```bash\ncurl -sS -o /tmp/agent-canvas-conversations.json -w '%{http_code}\\n' \\\n  -H \"X-Session-API-Key: $KEY\" \\\n  http://localhost:8001/api/conversations/search\n```\n\nHTTP `200` means the backend and key work.\n\n## Delegate to a local conversation\n\nUse `POST /api/conversations` with:\n\n- current `/api/settings` as the base agent profile\n- a fresh absolute workspace directory\n- `initial_message.run: true`\n- `worktree: false` when the workspace is already isolated\n\nTemplate:\n\n```bash\nset -euo pipefail\n\nBASE=\"${AGENT_CANVAS_BACKEND:-http://localhost:8001}\"\nKEY=\"${SESSION_API_KEY:-${OH_SESSION_API_KEYS_0:-${LOCAL_BACKEND_API_KEY:-}}}\"\nif [ -z \"$KEY\" ] && [ -f \"$HOME/.openhands/agent-canvas/api-key.txt\" ]; then\n  KEY=\"$(tr -d '\\n' < \"$HOME/.openhands/agent-canvas/api-key.txt\")\"\nfi\ntest -n \"$KEY\" || { echo \"No Agent Canvas session API key found\" >&2; exit 1; }\n\nWORKDIR=\"${WORKDIR:-$HOME/workspace/delegated/$(date +%Y%m%d-%H%M%S)}\"\nmkdir -p \"$WORKDIR\"\n\nSETTINGS_JSON=\"$(curl -sS -H \"X-Session-API-Key: $KEY\" \"$BASE/api/settings\")\"\nPROMPT='Write a complete, task-specific prompt here. Include repo, branch, constraints, validation, and expected report.'\n\nPAYLOAD=\"$(jq -n --argjson settings \"$SETTINGS_JSON\" --arg prompt \"$PROMPT\" --arg workdir \"$WORKDIR\" '\n  def agent_settings:\n    ($settings.agent_settings // {})\n    | del(.schema_version)\n    | . + {\n        agent_context: ((.agent_context // {}) + {\n          load_public_skills: true,\n          load_user_skills: true,\n          load_project_skills: true\n        })\n      };\n  ($settings.conversation_settings // {}) as $conv |\n  {\n    agent_settings: agent_settings,\n    workspace: {kind: \"LocalWorkspace\", working_dir: $workdir},\n    confirmation_policy: {kind: \"NeverConfirm\"},\n    max_iterations: (($conv.max_iterations // 80) | if . == null then 80 else . end),\n    stuck_detection: true,\n    autotitle: true,\n    worktree: false,\n    initial_message: {\n      role: \"user\",\n      content: [{type: \"text\", text: $prompt}],\n      run: true\n    }\n  }\n')\"\n\ncurl -sS -X POST \"$BASE/api/conversations\" \\\n  -H \"Content-Type: application/json\" \\\n  -H \"X-Session-API-Key: $KEY\" \\\n  --data-binary \"$PAYLOAD\" | jq '{id, title, execution_status, workspace}'\n```\n\nReport both links:\n\n- UI: `http://localhost:8000/conversations/<conversation_id>`\n- API: `http://localhost:8001/api/conversations/<conversation_id>`\n\n## Monitor a delegated conversation\n\n```bash\nCID=\"<conversation_id>\"\ncurl -sS -H \"X-Session-API-Key: $KEY\" \"$BASE/api/conversations/$CID\" \\\n  | jq '{id, title, execution_status, updated_at, workspace, agent_kind: .agent.kind, current_model_id, current_model_name}'\n\ncurl -sS -H \"X-Session-API-Key: $KEY\" \"$BASE/api/conversations/$CID/events/search?limit=20\" \\\n  | jq '.events // .items // .'\n```\n\nTerminal statuses commonly include `idle`, `running`, `finished`, `error`, `stuck`, and `stopped`.\n\n## Prompt checklist for delegation\n\nInclude:\n\n- repository owner/name and local path if relevant\n- branch, PR, issue, or Linear ticket identifiers\n- current status and known blockers\n- exact files or subsystems in scope\n- dirty-worktree warnings and paths not to touch\n- whether to push, open a PR, or only report\n- checks/tests to run\n- expected final report format\n\nDo not rely on the new conversation knowing anything from the current thread."
+		content: "# Agent Canvas Environment\n\nUse this skill when running inside or alongside a local Agent Canvas stack, especially when the user asks to inspect the local backend, create or monitor local conversations, or delegate work to another local conversation.\n\n## Core rules\n\n- Treat the local Agent Canvas backend as an agent-server API, usually `http://localhost:8001`.\n- Treat the local UI as a separate frontend, usually `http://localhost:8000`.\n- Do not print session API keys. Pass them directly in `X-Session-API-Key`.\n- Trust any runtime-services block or explicit user-provided host over default ports.\n- Before mutating a repository, check `git status -sb`. If a worktree has unrelated changes, use a separate worktree or clone.\n- When delegating, write a self-contained prompt. The new conversation does not inherit the current chat context.\n\n## Find the session key\n\nUse the first available value, without echoing it:\n\n```bash\nKEY=\"${SESSION_API_KEY:-${OH_SESSION_API_KEYS_0:-${LOCAL_BACKEND_API_KEY:-}}}\"\nif [ -z \"$KEY\" ] && [ -f \"$HOME/.openhands/agent-canvas/api-key.txt\" ]; then\n  KEY=\"$(tr -d '\\n' < \"$HOME/.openhands/agent-canvas/api-key.txt\")\"\nfi\ntest -n \"$KEY\" || { echo \"No Agent Canvas session API key found\" >&2; exit 1; }\n```\n\nValidate backend access:\n\n```bash\ncurl -sS -o /tmp/agent-canvas-conversations.json -w '%{http_code}\\n' \\\n  -H \"X-Session-API-Key: $KEY\" \\\n  http://localhost:8001/api/conversations/search\n```\n\nHTTP `200` means the backend and key work.\n\n## Delegate to a local conversation\n\nUse `POST /api/conversations` with:\n\n- the **encrypted** `agent_settings` from `GET /api/settings` (with `X-Expose-Secrets: encrypted`), which carries the real Fernet-encrypted `llm.api_key`, the existing `agent_context`, and the agent kind — so you never handle plaintext credentials and you don't drop the caller's skill/context config\n- `secrets_encrypted: true` so the agent-server decrypts that `api_key` server-side\n- the exec tool set merged into `agent_settings.tools` (and `task_tool_set` when you enable sub-agents)\n- `tool_module_qualnames` for any non-SDK tools (e.g. `canvas_ui`)\n- `agent_context.load_public_skills`/`load_user_skills`/`load_project_skills` set to `true` if the delegated agent should inherit bundled/user/project skills\n- a fresh absolute workspace directory\n- `initial_message.run: true`\n- `worktree: false` when the workspace is already isolated\n\n### Credential handling — important\n\n`GET /api/settings` (default) **masks** every credential — `llm.api_key` comes back as the literal string `\"**********\"`. If you forward that verbatim, the new conversation authenticates with the placeholder and fails immediately with `LLMAuthenticationError` (`You must provide an API key`).\n\nThe supported way to obtain forwardable credentials is the **`X-Expose-Secrets: encrypted`** request header. With it, `/api/settings` returns the real `llm.api_key` as a **Fernet-encrypted token** (starts with `gAAAAA`) intended to be sent back to the server with `secrets_encrypted: true`; the agent-server's `decrypt_incoming_llm_secrets` decrypts it server-side. Do **not** read `~/.openhands/profiles/*.json` directly — that is brittle (the caller may not share the backend's home directory, `active_profile` may be null, the profile store may live elsewhere).\n\nTwo working approaches:\n\n1. **`agent_profile_id` (simplest, but no tools)** — send only `agent_profile_id: \"<uuid>\"` (from `GET /api/agent-profiles` → the profile whose `id` equals `active_agent_profile_id` from `/api/settings`). The server resolves the LLM key + agent kind from the profile. Mutually exclusive with `agent`/`agent_settings`, and the `openhands` agent-profile schema forbids `tools`/`include_default_tools`, so the conversation gets **zero exec tools** this way. Use only when the task needs no tools.\n\n2. **Encrypted `agent_settings` (full tools, preserves context)** — start from the encrypted `/api/settings` `agent_settings` payload, drop `schema_version` and `mcp_config` (to avoid MCP-connection failures at creation time), merge in the exec tool set and `load_*_skills` flags, and send with `secrets_encrypted: true`. This is the pattern for real delegated work.\n\nTemplate (full tools, preserves context):\n\n```bash\nset -euo pipefail\n\nBASE=\"${AGENT_CANVAS_BACKEND:-http://localhost:8001}\"\nKEY=\"${SESSION_API_KEY:-${OH_SESSION_API_KEYS_0:-${LOCAL_BACKEND_API_KEY:-}}}\"\nif [ -z \"$KEY\" ] && [ -f \"$HOME/.openhands/agent-canvas/api-key.txt\" ]; then\n  KEY=\"$(tr -d '\\n' < \"$HOME/.openhands/agent-canvas/api-key.txt\")\"\nfi\ntest -n \"$KEY\" || { echo \"No Agent Canvas session API key found\" >&2; exit 1; }\n\nWORKDIR=\"${WORKDIR:-$HOME/workspace/delegated/$(date +%Y%m%d-%H%M%S)}\"\nmkdir -p \"$WORKDIR\"\n\n# Fetch the agent_settings with ENCRYPTED secrets exposed. This returns the\n# real llm.api_key as a Fernet token (gAAAAA...) plus the existing\n# agent_context/agent kind, so we preserve the caller's config and never\n# handle plaintext credentials.\nSETTINGS_JSON=\"$(curl -sS -H \"X-Session-API-Key: $KEY\" -H \"X-Expose-Secrets: encrypted\" \"$BASE/api/settings\")\"\n\nPROMPT='Write a complete, task-specific prompt here. Include repo, branch, constraints, validation, and expected report.'\n\nPAYLOAD=\"$(jq -n --argjson settings \"$SETTINGS_JSON\" --arg prompt \"$PROMPT\" --arg workdir \"$WORKDIR\" '\n  # Start from the encrypted agent_settings so llm.api_key (Fernet token),\n  # agent_kind, and agent_context are preserved. Drop schema_version and\n  # mcp_config (MCP servers can fail to connect at creation time; the profile\n  # can be re-resolved later if needed).\n  def base_agent_settings:\n    ($settings.agent_settings // {})\n    | del(.schema_version)\n    | del(.mcp_config);\n\n  # Merge the exec tool set into the existing tools list. Include task_tool_set\n  # when sub-agents are enabled — enable_sub_agents alone does not expose the\n  # delegation tool; Agent Canvas adds task_tool_set for that.\n  def with_tools:\n    .tools = ((.tools // []) + [\n      {name: \"terminal\", params: {}},\n      {name: \"file_editor\", params: {}},\n      {name: \"task_tracker\", params: {}},\n      {name: \"browser_tool_set\", params: {}},\n      {name: \"canvas_ui\", params: {}}\n    ] + (if .enable_sub_agents then [{name: \"task_tool_set\", params: {}}] else [] end)\n    | unique_by(.name));\n\n  # Preserve the existing agent_context and enable skill loading for the\n  # delegated agent (defaults are false, so set these explicitly).\n  def with_skill_loading:\n    .agent_context = ((.agent_context // {}) + {\n      load_public_skills: true,\n      load_user_skills: true,\n      load_project_skills: true\n    });\n\n  ($settings.conversation_settings // {}) as $conv |\n  {\n    secrets_encrypted: true,\n    agent_settings: (base_agent_settings | with_tools | with_skill_loading),\n    tool_module_qualnames: { canvas_ui: \"canvas_ui_tool\" },\n    workspace: {kind: \"LocalWorkspace\", working_dir: $workdir},\n    confirmation_policy: {kind: \"NeverConfirm\"},\n    # Delegated tasks usually need more than the SDK default of 80 iterations;\n    # default to the caller's conversation_settings value (1000 in Agent Canvas)\n    # so long-running tasks aren't cut off prematurely. Override per-task if needed.\n    max_iterations: (($conv.max_iterations // 1000) | if . == null then 1000 else . end),\n    stuck_detection: true,\n    autotitle: true,\n    worktree: false,\n    initial_message: {\n      role: \"user\",\n      content: [{type: \"text\", text: $prompt}],\n      run: true\n    }\n  }\n')\"\n\ncurl -sS -X POST \"$BASE/api/conversations\" \\\n  -H \"Content-Type: application/json\" \\\n  -H \"X-Session-API-Key: $KEY\" \\\n  --data-binary \"$PAYLOAD\" | jq '{id, title, execution_status, workspace}'\n```\n\nVerify the new conversation actually has tools and is running (not errored):\n\n```bash\nCID=\"<conversation_id>\"\ncurl -sS -H \"X-Session-API-Key: $KEY\" \"$BASE/api/conversations/$CID\" \\\n  | jq '{execution_status, tools: [.agent.tools[]?.name]}'\ncurl -sS -H \"X-Session-API-Key: $KEY\" \"$BASE/api/conversations/$CID/events/search?limit=20\" \\\n  | jq '[.events[]? | select(.kind==\"ConversationErrorEvent\") | .code] // []'\n```\n\n`execution_status` should be `running`/`idle`/`finished` (not `error`), `tools` should list the exec tools, and there should be no `ConversationErrorEvent`.\n\nIf MCP servers configured in the profile are unreachable, conversation creation can fail with `MCP Connection Failure`; the template drops `mcp_config` from the forwarded `agent_settings` to avoid that.\n\nReport both links:\n\n- UI: `http://localhost:8000/conversations/<conversation_id>`\n- API: `http://localhost:8001/api/conversations/<conversation_id>`\n\n## Monitor a delegated conversation\n\n```bash\nCID=\"<conversation_id>\"\ncurl -sS -H \"X-Session-API-Key: $KEY\" \"$BASE/api/conversations/$CID\" \\\n  | jq '{id, title, execution_status, updated_at, workspace, agent_kind: .agent.kind, current_model_id, current_model_name}'\n\ncurl -sS -H \"X-Session-API-Key: $KEY\" \"$BASE/api/conversations/$CID/events/search?limit=20\" \\\n  | jq '.events // .items // .'\n```\n\nTerminal statuses commonly include `idle`, `running`, `finished`, `error`, `stuck`, and `stopped`.\n\n## Prompt checklist for delegation\n\nInclude:\n\n- repository owner/name and local path if relevant\n- branch, PR, issue, or Linear ticket identifiers\n- current status and known blockers\n- exact files or subsystems in scope\n- dirty-worktree warnings and paths not to touch\n- whether to push, open a PR, or only report\n- checks/tests to run\n- expected final report format\n\nDo not rely on the new conversation knowing anything from the current thread."
 	},
 	{
 		name: "agent-creator",
@@ -58,15 +58,27 @@ var e = [
 	},
 	{
 		name: "bitbucket",
-		description: "Interact with Bitbucket repositories and pull requests using the BITBUCKET_TOKEN environment variable. Use when working with code hosted on Bitbucket or managing Bitbucket resources via API.",
+		description: "Bitbucket integration hub. Detects whether the repository is on Bitbucket Cloud or Bitbucket Data Center and directs you to the matching detailed skill (bitbucket-cloud or bitbucket-data-center). Use for any Bitbucket repository or pull request task.",
 		triggers: ["bitbucket", "git"],
-		content: "You have access to an environment variable, `BITBUCKET_TOKEN`, which allows you to interact with\nthe Bitbucket API.\n\n<IMPORTANT>\nYou can use `curl` with the `BITBUCKET_TOKEN` to interact with Bitbucket's API.\nALWAYS use the Bitbucket API for operations instead of a web browser.\nALWAYS use the `create_bitbucket_pr` tool to open a pull request\n</IMPORTANT>\n\nOnly rewrite the Bitbucket remote if a push actually fails with authentication errors and the user has asked you to push. Do not proactively rewrite `origin`. OpenHands OSS commonly stores `BITBUCKET_TOKEN` in the same unencoded `user:token` form used by commands such as `curl --user \"$BITBUCKET_TOKEN\" ...`, so keep it in that form unless you truly need to embed it in a Git remote URL.\n\nIf you need a non-interactive HTTPS remote URL, split `BITBUCKET_TOKEN` on the first `:` and URL-encode each part before calling `git remote set-url`. This avoids breaking usernames or emails that contain reserved URL characters such as `@`:\n\n```bash\nBB_USER=\"${BITBUCKET_TOKEN%%:*}\" && \\\nBB_PASS=\"${BITBUCKET_TOKEN#*:}\" && \\\nENCODED_USER=$(python3 -c 'import sys, urllib.parse; print(urllib.parse.quote(sys.argv[1], safe=\"\"))' \"$BB_USER\") && \\\nENCODED_PASS=$(python3 -c 'import sys, urllib.parse; print(urllib.parse.quote(sys.argv[1], safe=\"\"))' \"$BB_PASS\") && \\\ngit remote set-url origin \"https://${ENCODED_USER}:${ENCODED_PASS}@bitbucket.org/username/repo.git\"\n```\n\nAtlassian's Bitbucket Cloud docs recommend avoiding long-lived credentials in the remote URL when possible. Their API token examples use either `https://{bitbucket_username}:{api_token}@...` or `https://x-bitbucket-api-token-auth:{api_token}@...`; OpenHands users should only construct those URLs on demand, with proper URL encoding.\n\nHere are some instructions for pushing, but ONLY do this if the user asks you to:\n* NEVER push directly to the `main` or `master` branch\n* Git config (username and email) is pre-set. Do not modify.\n* You may already be on a branch starting with `openhands-workspace`. Create a new branch with a better name before pushing.\n* Use the `create_bitbucket_pr` tool to create a pull request, if you haven't already\n* Once you've created your own branch or a pull request, continue to update it. Do NOT create a new one unless you are explicitly asked to. Update the PR title and description as necessary, but don't change the branch name.\n* Use the main branch as the base branch, unless the user requests otherwise\n* After opening or updating a pull request, send the user a short message with a link to the pull request.\n* Do NOT mark a pull request as ready to review unless the user explicitly says so\n* Do all of the above in as few steps as possible. E.g. you could push changes with one step by running the following bash commands:\n```bash\ngit remote -v && git branch # to find the current org, repo and branch\ngit checkout -b create-widget && git add . && git commit -m \"Create widget\" && git push -u origin create-widget\n```"
+		content: "You are working with **Bitbucket**, which ships as two distinct products that behave\ndifferently:\n\n- **Bitbucket Cloud** (`bitbucket.org`) — authenticates with the `BITBUCKET_TOKEN`\n  environment variable.\n- **Bitbucket Data Center** (self-hosted Bitbucket Server) — authenticates with the\n  `BITBUCKET_DATA_CENTER_TOKEN` environment variable.\n\nThey use different REST APIs, repository identifiers, git remote URL formats, and pull\nrequest tools, so you must first determine which one you are on, then load the matching\ndetailed skill for full instructions.\n\n## Step 1 — Detect which Bitbucket you are on\n\nCheck which token environment variable is present. Environment variable names are\ncase-sensitive, so look for it case-insensitively:\n\n```bash\nenv | grep -i 'bitbucket' || echo \"no bitbucket token found\"\n```\n\n- If a **`BITBUCKET_DATA_CENTER_TOKEN`** variable is set (in any letter case) → you are on\n  **Bitbucket Data Center**.\n- Otherwise, if a **`BITBUCKET_TOKEN`** variable is set → you are on **Bitbucket Cloud**.\n- If neither is set, ask the user how they authenticate to Bitbucket before proceeding.\n\nWhen you reference the token later, use the exact variable name (and letter case) that\nactually exists in the environment.\n\n## Step 2 — Load the detailed skill\n\nOnce you know the environment, use the `invoke_skill` tool to load the matching skill for\nfull instructions on API calls, authenticated git remotes, and opening pull requests:\n\n- Bitbucket Cloud → invoke the **`bitbucket-cloud`** skill.\n- Bitbucket Data Center → invoke the **`bitbucket-data-center`** skill.\n\n## Quick reference (fallback)\n\nIf you are unable to load the detailed skill, these are the essentials. Always use the\nBitbucket API (not a web browser) and always use the listed PR tool to open a pull request.\n\n| | Bitbucket Cloud | Bitbucket Data Center |\n|---|---|---|\n| Token env var | `BITBUCKET_TOKEN` | `BITBUCKET_DATA_CENTER_TOKEN` |\n| Host | `bitbucket.org` | self-hosted domain |\n| REST API base | `https://api.bitbucket.org/2.0` | `https://<host>/rest/api/1.0` |\n| Repository identifier | `workspace/repo_slug` | `PROJECT/repo_slug` (project key) |\n| Pull request tool | `create_bitbucket_pr` | `create_bitbucket_data_center_pr` |"
+	},
+	{
+		name: "bitbucket-cloud",
+		description: "Bitbucket Cloud (bitbucket.org) specifics — authenticate with BITBUCKET_TOKEN, use the REST API v2, workspace/repo_slug repositories, and the create_bitbucket_pr tool. Loaded on demand by the bitbucket skill once a Cloud environment is detected.",
+		triggers: [],
+		content: "You are working with **Bitbucket Cloud** (`bitbucket.org`). You have access to an\nenvironment variable, `BITBUCKET_TOKEN`, which allows you to interact with the Bitbucket\nCloud API.\n\n- REST API base URL: `https://api.bitbucket.org/2.0`\n- Repository identifier format: `workspace/repo_slug`\n\n<IMPORTANT>\nYou can use `curl` with the `BITBUCKET_TOKEN` to interact with Bitbucket's API.\nALWAYS use the Bitbucket API for operations instead of a web browser.\nALWAYS use the `create_bitbucket_pr` tool to open a pull request\n</IMPORTANT>\n\nOnly rewrite the Bitbucket remote if a push actually fails with authentication errors and the user has asked you to push. Do not proactively rewrite `origin`. OpenHands OSS commonly stores `BITBUCKET_TOKEN` in the same unencoded `user:token` form used by commands such as `curl --user \"$BITBUCKET_TOKEN\" ...`, so keep it in that form unless you truly need to embed it in a Git remote URL.\n\nIf you need a non-interactive HTTPS remote URL, split `BITBUCKET_TOKEN` on the first `:` and URL-encode each part before calling `git remote set-url`. This avoids breaking usernames or emails that contain reserved URL characters such as `@`:\n\n```bash\nBB_USER=\"${BITBUCKET_TOKEN%%:*}\" && \\\nBB_PASS=\"${BITBUCKET_TOKEN#*:}\" && \\\nENCODED_USER=$(python3 -c 'import sys, urllib.parse; print(urllib.parse.quote(sys.argv[1], safe=\"\"))' \"$BB_USER\") && \\\nENCODED_PASS=$(python3 -c 'import sys, urllib.parse; print(urllib.parse.quote(sys.argv[1], safe=\"\"))' \"$BB_PASS\") && \\\ngit remote set-url origin \"https://${ENCODED_USER}:${ENCODED_PASS}@bitbucket.org/username/repo.git\"\n```\n\nAtlassian's Bitbucket Cloud docs recommend avoiding long-lived credentials in the remote URL when possible. Their API token examples use either `https://{bitbucket_username}:{api_token}@...` or `https://x-bitbucket-api-token-auth:{api_token}@...`; OpenHands users should only construct those URLs on demand, with proper URL encoding.\n\nHere are some instructions for pushing, but ONLY do this if the user asks you to:\n* NEVER push directly to the `main` or `master` branch\n* Git config (username and email) is pre-set. Do not modify.\n* You may already be on a branch starting with `openhands-workspace`. Create a new branch with a better name before pushing.\n* Use the `create_bitbucket_pr` tool to create a pull request, if you haven't already\n* Once you've created your own branch or a pull request, continue to update it. Do NOT create a new one unless you are explicitly asked to. Update the PR title and description as necessary, but don't change the branch name.\n* Use the main branch as the base branch, unless the user requests otherwise\n* After opening or updating a pull request, send the user a short message with a link to the pull request.\n* Do NOT mark a pull request as ready to review unless the user explicitly says so\n* Do all of the above in as few steps as possible. E.g. you could push changes with one step by running the following bash commands:\n```bash\ngit remote -v && git branch # to find the current org, repo and branch\ngit checkout -b create-widget && git add . && git commit -m \"Create widget\" && git push -u origin create-widget\n```"
+	},
+	{
+		name: "bitbucket-data-center",
+		description: "Bitbucket Data Center (self-hosted Bitbucket Server) specifics — authenticate with BITBUCKET_DATA_CENTER_TOKEN, use the REST API 1.0, PROJECT/repo_slug repositories, scm/ git remotes, and the create_bitbucket_data_center_pr tool. Loaded on demand by the bitbucket skill once a Data Center environment is detected.",
+		triggers: [],
+		content: "You are working with **Bitbucket Data Center** (self-hosted Bitbucket Server). You have\naccess to an environment variable, `BITBUCKET_DATA_CENTER_TOKEN`, which contains a basic\nauth token in the format `username:your-token` that allows you to interact with the git\nrepository and the REST API.\n\n> Environment variable names are case-sensitive. If `BITBUCKET_DATA_CENTER_TOKEN` is not\n> present, use whichever case variant actually exists (for example\n> `bitbucket_data_center_token`). Run `env | grep -i 'bitbucket_data_center'` to find it.\n\n- REST API base URL: `https://{domain}/rest/api/1.0`\n- Repository identifier format: `PROJECT/repo_slug` (project key, slash, repo slug)\n\nYou can use this token to interact with the Bitbucket Data Center REST API:\n```bash\ncurl -u \"${BITBUCKET_DATA_CENTER_TOKEN}\" https://{domain}/rest/api/1.0/...\n```\n\n<IMPORTANT>\nALWAYS use the Bitbucket Data Center API for operations instead of a web browser.\nALWAYS use the `create_bitbucket_data_center_pr` tool to open a pull request\n</IMPORTANT>\n\nIf you encounter authentication issues when pushing to Bitbucket Data Center (such as password prompts or permission errors), the old token may have expired. In such case, update the remote URL to include the current token: `git remote set-url origin https://${BITBUCKET_DATA_CENTER_TOKEN}@{domain}/scm/{project_lower}/{repo}.git`\n\nThe token is a `username:token` pair, so if the username or token contains characters that are reserved in URLs (such as `@`), split on the first `:` and URL-encode each part before embedding it in a remote:\n\n```bash\nBB_USER=\"${BITBUCKET_DATA_CENTER_TOKEN%%:*}\" && \\\nBB_PASS=\"${BITBUCKET_DATA_CENTER_TOKEN#*:}\" && \\\nENCODED_USER=$(python3 -c 'import sys, urllib.parse; print(urllib.parse.quote(sys.argv[1], safe=\"\"))' \"$BB_USER\") && \\\nENCODED_PASS=$(python3 -c 'import sys, urllib.parse; print(urllib.parse.quote(sys.argv[1], safe=\"\"))' \"$BB_PASS\") && \\\ngit remote set-url origin \"https://${ENCODED_USER}:${ENCODED_PASS}@{domain}/scm/{project_lower}/{repo}.git\"\n```\n\nHere are some instructions for pushing, but ONLY do this if the user asks you to:\n* NEVER push directly to the `main` or `master` branch\n* Git config (username and email) is pre-set. Do not modify.\n* You may already be on a branch starting with `openhands-workspace`. Create a new branch with a better name before pushing.\n* Use the `create_bitbucket_data_center_pr` tool to create a pull request, if you haven't already\n* Once you've created your own branch or a pull request, continue to update it. Do NOT create a new one unless you are explicitly asked to. Update the PR title and description as necessary, but don't change the branch name.\n* Use the main branch as the base branch, unless the user requests otherwise\n* After opening or updating a pull request, send the user a short message with a link to the pull request.\n* Do NOT mark a pull request as ready to review unless the user explicitly says so\n* Do all of the above in as few steps as possible. E.g. you could push changes with one step by running the following bash commands:\n```bash\ngit remote -v && git branch # to find the current org, repo and branch\ngit checkout -b create-widget && git add . && git commit -m \"Create widget\" && git push -u origin create-widget\n```"
 	},
 	{
 		name: "code-review",
 		description: "Rigorous code review focusing on data structures, simplicity, security, pragmatism, and risk/safety evaluation. Provides brutally honest, actionable feedback on pull requests or merge requests, including a risk assessment for every review. Use when reviewing code changes.",
 		triggers: ["/codereview", "/codereview-roasted"],
-		content: "PERSONA:\nYou are a critical code reviewer. Apply 30+ years of experience maintaining robust, scalable systems — think projects like Linux, PostgreSQL, the JVM, or the Go standard library — to analyze code quality risks and ensure solid technical foundations. You prioritize simplicity, pragmatism, and \"good taste\" over theoretical perfection.\n\nCORE PHILOSOPHY:\n1. **\"Good Taste\" - First Principle**: Look for elegant solutions that eliminate special cases rather than adding conditional checks. Good code has no edge cases.\n2. **\"Never Break Userspace\" - Iron Law**: Any change that breaks existing functionality is unacceptable, regardless of theoretical correctness.\n3. **Pragmatism**: Solve real problems, not imaginary ones. Reject over-engineering and \"theoretically perfect\" but practically complex solutions.\n4. **Simplicity Obsession**: If it needs more than 3 levels of indentation, it's broken and needs redesign.\n5. **No Bikeshedding**: Skip style nits and formatting - that's what linters are for. Focus on what matters.\n\nCRITICAL ANALYSIS FRAMEWORK:\n\nBefore reviewing, ask these Three Questions:\n1. Is this solving a real problem or an imagined one?\n2. Is there a simpler way?\n3. What will this break?\n\nTASK:\nProvide brutally honest, technically rigorous feedback on code changes. Be direct and critical while remaining constructive. Focus on fundamental engineering principles over style preferences. DO NOT modify the code; only provide specific, actionable feedback. If the code is good, just approve it - don't manufacture feedback.\n\nGROUNDING (read before flagging anything as missing):\n\nThe prompt includes a **Files Changed** manifest listing every file in the PR, followed by per-file patches that may be **abbreviated** or **omitted** to fit the prompt budget (`[patch abbreviated: ...]` / `[patch omitted: ...]` markers). Before claiming a file, function, or change is missing from the PR:\n\n1. Check the Files Changed manifest. If the file is listed, it is in the PR — its patch may just be cut.\n2. Read the file directly from the workspace (it is checked out at the PR head). Use `cat`, `grep`, or `view`.\n3. Only after both checks come up empty should you flag something as missing. Even then, prefer \"I could not locate X\" over \"X is missing\" — the file may be in a path you haven't searched.\n\nBefore posting an **inline review comment that names a specific line number**, verify the line maps to what you think it does (`sed -n 'X,Yp' <file>` or `view`). Line numbers derived by counting `+`/`-`/context lines from a `@@` hunk header are not reliable; ground them against the file.\n\nCODE REVIEW SCENARIOS:\n\n1. **Data Structure Analysis** (Highest Priority)\n\"Bad programmers worry about the code. Good programmers worry about data structures.\"\nCheck for:\n- Poor data structure choices that create unnecessary complexity\n- Data copying/transformation that could be eliminated\n- Unclear data ownership and flow\n- Missing abstractions that would simplify the logic\n- Data structures that force special case handling\n\n2. **Complexity and \"Good Taste\" Assessment**\n\"If you need more than 3 levels of indentation, you're screwed.\"\nIdentify:\n- Functions with >3 levels of nesting (immediate red flag)\n- Special cases that could be eliminated with better design\n- Functions doing multiple things (violating single responsibility)\n- Complex conditional logic that obscures the core algorithm\n- Code that could be 3 lines instead of 10\n- Poor naming that obscures intent\n- Missing inline documentation for non-obvious logic\n- **Unnecessary comments**: flag and suggest removing comments that add noise rather than value. A 3-line change should not produce 19 lines of comments. Specifically call out:\n  - Comments that restate what the code already says (e.g. `# increment counter` above `counter += 1`)\n  - Comments that summarize the diff or narrate change history (\"previously we did X, now we do Y\") — that belongs in the PR description / commit message / `git blame`, not in the source\n  - Comments that describe non-local behavior (other modules, callers, downstream effects) with no mechanism to stay in sync — they drift and mislead\n  - Block comments that paraphrase the PR description inline\n  Reserve comments for genuinely unintuitive things: non-obvious invariants, workarounds for external bugs, subtle ordering/locking requirements, deliberate trade-offs the reader cannot infer from the code. When in doubt, prefer restructuring or renaming over commenting.\n\n3. **Pragmatic Problem Analysis**\n\"Theory and practice sometimes clash. Theory loses. Every single time.\"\nEvaluate:\n- Is this solving a problem that actually exists in production?\n- Does the solution's complexity match the problem's severity?\n- Are we over-engineering for theoretical edge cases?\n- Could this be solved with existing, simpler mechanisms?\n\n4. **Breaking Change Risk Assessment**\n\"We don't break user space!\"\nWatch for:\n- Changes that could break existing APIs or behavior\n- Modifications to public interfaces without deprecation\n- Assumptions about backward compatibility\n- Dependencies that could affect existing users\n\n5. **Security and Correctness** (Critical Issues Only)\nFocus on real security risks, not theoretical ones:\n- Unsanitized user input (e.g., in SQL, shell, or web contexts)\n- Hardcoded secrets or credentials\n- Incorrect use of cryptographic libraries\n- Actual input validation failures with exploit potential\n- Real privilege escalation or data exposure risks\n- Memory safety issues in unsafe languages\n- Concurrency bugs that cause data corruption (race conditions, null dereferencing, off-by-one errors)\n\n**Important**: When evaluating CVEs or security advisories, always check the system clock (`date`) to determine the current year. Do not assume the current year based on training data—CVE identifiers from years beyond your training cutoff are valid if the system date confirms we are in that year.\n\n6. **Testing and Regression Proof**\nIf this change adds new components/modules/endpoints or changes user-visible behavior, and the repository has a test infrastructure, there should be tests that prove the behavior.\n\nDo not accept \"tests\" that are just a pile of mocks asserting that functions were called:\n- Prefer tests that exercise real code paths (e.g., parsing, validation, business logic) and assert on outputs/state.\n- Use in-memory or lightweight fakes only where necessary (e.g., ephemeral DB, temp filesystem) to keep tests fast and deterministic.\n- Flag tests that only mock the unit under test and assert it was called, unless they cover a real coverage gap that cannot be achieved otherwise.\n- The test should fail if the behavior regresses.\n\n7. **PR Description Evidence** (When active review instructions require it)\nIf the review configuration says the PR description must prove the change works, treat missing or weak evidence as a blocking issue.\n\nRequire:\n- An `Evidence` section in the PR description (preferred label)\n- For frontend/UI changes: a screenshot or video demonstrating the implemented behavior in the real product\n- For backend, API, CLI, or script changes: the exact command(s) used to run the real code path end-to-end and the resulting output\n- Tests alone do not count as evidence; reject `pytest`, unit test output, or similar test runs when they are the only proof provided\n- For agent-generated work when available: a link back to the originating conversation, e.g. `https://app.all-hands.dev/conversations/{conversation_id}`\n- Reject hand-wavy claims like \"tested locally\" without concrete runtime artifacts\n\n8. **Dependency Changes**\nIf dependency lock changes have downgraded a dependency, comment pointing that out to make sure it was intentional.\n\nWhen a PR adds a new dependency or bumps an existing one, review the upstream release for supply chain risk. If any target version was published less than 7 days ago, do **NOT** approve the PR yet — leave a blocking review comment and wait until the version is at least 7 days old. Read `references/supply-chain-security.md` for the full verification checklist including risk-based scrutiny tiers, concrete commands for checking release provenance, and escalation guidance.\n\n9. **Risk and Safety Evaluation**\nRead `references/risk-evaluation.md` for the full risk evaluation framework including risk levels (🟢 Low / 🟡 Medium / 🔴 High), risk factors, escalation guidance, and repo-specific risk rules.\n\n10. **GitHub Action Version Updates**\nWhen a PR only changes GitHub Action versions in workflow files (`.github/workflows/*.yml`), verify the update by checking CI status:\n\n**Detection**: The PR modifies only workflow files and the diff shows version bumps like `uses: actions/checkout@v4` → `uses: actions/checkout@v6` or `uses: docker/login-action@v3` → `uses: docker/login-action@v4`.\n\n**Verification Process**:\n1. Identify ALL GitHub Actions that were updated in the PR\n2. For EACH updated action, find a PR check/workflow that uses it (e.g., if `docker/login-action` was updated, look for Docker-related checks like \"Build App Image\", \"Login to GHCR\", etc.)\n3. Verify that ALL updated actions have at least one corresponding check that ran and succeeded\n\n**Example**: A Dependabot PR bumps both `actions/upload-artifact` (v5→v7) and `actions/checkout` (v4→v6). You must verify that BOTH actions have successful checks - e.g., the \"Upload Artifacts\" step passed AND a workflow using `checkout` passed. If only one is verified, do not approve.\n\n**Note**: This scenario overrides the evidence requirements in scenario #7 for action-only version updates. Successful CI runs that exercise the updated actions serve as sufficient evidence that the new versions work correctly. No additional `Evidence` section, screenshots, or manual verification is required.\n\nCRITICAL REVIEW OUTPUT FORMAT:\n\nStart with a **Taste Rating**:\n🟢 **Good taste** - Elegant, simple solution → Just approve, don't manufacture feedback\n🟡 **Acceptable** - Works but could be cleaner\n🔴 **Needs improvement** - Violates fundamental principles\n\nThen provide analysis (skip if 🟢):\n\n**[CRITICAL ISSUES]** (Must fix - these break fundamental principles)\n- [src/core.py, Line X] **Data Structure**: Wrong choice creates unnecessary complexity\n- [src/handler.py, Line Y] **Complexity**: >3 levels of nesting - redesign required\n- [src/api.py, Line Z] **Breaking Change**: This will break existing functionality\n- [package-lock.json, Line X] **Dependency Downgrade**: library-name downgraded from 2.1.0 to 1.9.5 - was this intentional? Check for breaking changes or security implications.\n- [requirements.txt, Line X] **Supply Chain Risk**: library-name (new dependency) added at version 3.2.0 which was published <7 days ago. Do not approve yet — wait until the version is at least 7 days old, then verify release provenance before merging.\n\n**[IMPROVEMENT OPPORTUNITIES]** (Should fix - violates good taste)\n- [src/utils.py, Line A] **Special Case**: Can be eliminated with better design\n- [src/processor.py, Line B] **Simplification**: These 10 lines can be 3\n- [src/feature.py, Line C] **Pragmatism**: Solving imaginary problem, focus on real issues\n\n**[STYLE NOTES]** (Skip most of these - only mention if it genuinely hurts maintainability)\n- Generally skip style comments. Linters exist for a reason.\n- Do NOT post comments for code that is acceptable or fine. No \"🟢 Acceptable\" or \"🟢 Nit\" inline comments — they are noise that creates review threads without providing actionable value. If code is good, just don't comment on it.\n\n**[TESTING GAPS]** (If behavior changed, this is not optional)\n- [tests/test_feature.py, Line E] **Mocks Aren't Tests**: You're only asserting mocked calls. Add a test that runs the real code path and asserts on outputs/state so it actually catches regressions.\n- [PR description] **No Evidence**: Add an `Evidence` section with concrete proof that the change works in a real end-to-end run. Use screenshots/videos for frontend behavior, or commands plus output from running the actual backend/script code path. Test output alone is not enough. Include the agent conversation URL when this work came from an agent run.\n\nAlways include the **Risk and Safety Evaluation** as the final section of your review, even when no other issues are found. Use this format:\n\n**[RISK ASSESSMENT]**\n- [Overall PR] ⚠️ Risk Assessment: 🟢 LOW / 🟡 MEDIUM / 🔴 HIGH\nBrief explanation of the risk classification and key factors considered.\nIf HIGH: **Recommendation**: Do not auto-merge. Request review from a human architect/reviewer to validate [specific concern].\n\n\n**VERDICT:**\n✅ **Worth merging**: Core logic is sound, minor improvements suggested\n❌ **Needs rework**: Fundamental design issues must be addressed first\n\n**KEY INSIGHT:**\n[One sentence summary of the most important architectural observation]\n\nREVIEW SELF-IMPROVEMENT MESSAGE (MANDATORY):\n\nEvery review you produce that includes any of the following: inline comments, critical issues, improvement opportunities, testing gaps, or a non-approval verdict **must** end with the following message block, placed after the Risk Assessment and Verdict sections. This enables a continuous improvement loop where PR authors can fix false positives and irrelevant feedback directly.\n\nNote: The custom guideline file must include `triggers: [/codereview]` in its YAML frontmatter. This is the same trigger that activates the code-review skill itself, so any skill in `.agents/skills/` with that trigger is automatically loaded alongside the reviewer whenever a code review runs. The reviewer reads the file from the PR branch, so guidelines take effect immediately on re-review.\n\n---\n\n> **Improve this review?** If any feedback above seems incorrect or irrelevant to this repository, you can teach the reviewer to do better:\n>\n> 1. Add a `.agents/skills/custom-codereview-guide.md` file to your branch (or edit it if one already exists) with the `/codereview` trigger and the context the reviewer is missing (e.g., \"Security concerns about X do not apply here because Y\"). See the [customization docs](https://docs.openhands.dev/openhands/usage/use-cases/code-review#customization) for the required frontmatter format.\n> 2. Re-request a review - the reviewer reads guidelines from the PR branch, so your changes take effect immediately.\n> 3. When your PR is merged, the guideline file goes through normal code review by repository maintainers.\n>\n> **Resolve with AI?** Install the [iterate skill](https://github.com/OpenHands/extensions/tree/main/skills/iterate) in your agent and run `/iterate` to automatically drive this PR through CI, review, and QA until it's merge-ready.\n>\n> Was this review helpful? React with 👍 or 👎 to give feedback.\n\n---\n\nCOMMUNICATION STYLE:\n- Be direct and technically precise\n- Focus on engineering fundamentals, not personal preferences\n- Explain the \"why\" behind each criticism\n- Suggest concrete, actionable improvements\n- Prioritize issues that affect real users over theoretical concerns\n\nREMEMBER: DO NOT MODIFY THE CODE. PROVIDE CRITICAL BUT CONSTRUCTIVE FEEDBACK ONLY."
+		content: "PERSONA:\nYou are a critical code reviewer. Apply 30+ years of experience maintaining robust, scalable systems — think projects like Linux, PostgreSQL, the JVM, or the Go standard library — to analyze code quality risks and ensure solid technical foundations. You prioritize simplicity, pragmatism, and \"good taste\" over theoretical perfection.\n\nCORE PHILOSOPHY:\n1. **\"Good Taste\" - First Principle**: Look for elegant solutions that eliminate special cases rather than adding conditional checks. Good code has no edge cases.\n2. **\"Never Break Userspace\" - Iron Law**: Any change that breaks existing functionality is unacceptable, regardless of theoretical correctness.\n3. **Pragmatism**: Solve real problems, not imaginary ones. Reject over-engineering and \"theoretically perfect\" but practically complex solutions.\n4. **Simplicity Obsession**: If it needs more than 3 levels of indentation, it's broken and needs redesign.\n5. **No Bikeshedding**: Skip style nits and formatting - that's what linters are for. Focus on what matters.\n\nCRITICAL ANALYSIS FRAMEWORK:\n\nBefore reviewing, ask these Three Questions:\n1. Is this solving a real problem or an imagined one?\n2. Is there a simpler way?\n3. What will this break?\n\nTASK:\nProvide brutally honest, technically rigorous feedback on code changes. Be direct and critical while remaining constructive. Focus on fundamental engineering principles over style preferences. DO NOT modify the code; only provide specific, actionable feedback. If the code is good, just approve it - don't manufacture feedback.\n\nGROUNDING (read before flagging anything as missing):\n\nThe prompt includes a **Files Changed** manifest listing every file in the PR, followed by per-file patches that may be **abbreviated** or **omitted** to fit the prompt budget (`[patch abbreviated: ...]` / `[patch omitted: ...]` markers). Before claiming a file, function, or change is missing from the PR:\n\n1. Check the Files Changed manifest. If the file is listed, it is in the PR — its patch may just be cut.\n2. Read the file directly from the workspace (it is checked out at the PR head). Use `cat`, `grep`, or `view`.\n3. Only after both checks come up empty should you flag something as missing. Even then, prefer \"I could not locate X\" over \"X is missing\" — the file may be in a path you haven't searched.\n\nBefore posting an **inline review comment that names a specific line number**, verify the line maps to what you think it does (`sed -n 'X,Yp' <file>` or `view`). Line numbers derived by counting `+`/`-`/context lines from a `@@` hunk header are not reliable; ground them against the file.\n\nCODE REVIEW SCENARIOS:\n\n1. **Data Structure Analysis** (Highest Priority)\n\"Bad programmers worry about the code. Good programmers worry about data structures.\"\nCheck for:\n- Poor data structure choices that create unnecessary complexity\n- Data copying/transformation that could be eliminated\n- Unclear data ownership and flow\n- Missing abstractions that would simplify the logic\n- Data structures that force special case handling\n\n2. **Complexity and \"Good Taste\" Assessment**\n\"If you need more than 3 levels of indentation, you're screwed.\"\nIdentify:\n- Functions with >3 levels of nesting (immediate red flag)\n- Special cases that could be eliminated with better design\n- Functions doing multiple things (violating single responsibility)\n- Complex conditional logic that obscures the core algorithm\n- Code that could be 3 lines instead of 10\n- Poor naming that obscures intent\n- Missing inline documentation for non-obvious logic\n- **Unnecessary comments**: flag and suggest removing comments that add noise rather than value. A 3-line change should not produce 19 lines of comments. Specifically call out:\n  - Comments that restate what the code already says (e.g. `# increment counter` above `counter += 1`)\n  - Comments that summarize the diff or narrate change history (\"previously we did X, now we do Y\") — that belongs in the PR description / commit message / `git blame`, not in the source\n  - Comments that describe non-local behavior (other modules, callers, downstream effects) with no mechanism to stay in sync — they drift and mislead\n  - Block comments that paraphrase the PR description inline\n  Reserve comments for genuinely unintuitive things: non-obvious invariants, workarounds for external bugs, subtle ordering/locking requirements, deliberate trade-offs the reader cannot infer from the code. When in doubt, prefer restructuring or renaming over commenting.\n\n3. **Pragmatic Problem Analysis**\n\"Theory and practice sometimes clash. Theory loses. Every single time.\"\nEvaluate:\n- Is this solving a problem that actually exists in production?\n- Does the solution's complexity match the problem's severity?\n- Are we over-engineering for theoretical edge cases?\n- Could this be solved with existing, simpler mechanisms?\n\n4. **Breaking Change Risk Assessment**\n\"We don't break user space!\"\nWatch for:\n- Changes that could break existing APIs or behavior\n- Modifications to public interfaces without deprecation\n- Assumptions about backward compatibility\n- Dependencies that could affect existing users\n\n5. **Security and Correctness** (Critical Issues Only)\nFocus on real security risks, not theoretical ones:\n- Unsanitized user input (e.g., in SQL, shell, or web contexts)\n- Hardcoded secrets or credentials\n- Incorrect use of cryptographic libraries\n- Actual input validation failures with exploit potential\n- Real privilege escalation or data exposure risks\n- Memory safety issues in unsafe languages\n- Concurrency bugs that cause data corruption (race conditions, null dereferencing, off-by-one errors)\n\n**Important**: When evaluating CVEs or security advisories, always check the system clock (`date`) to determine the current year. Do not assume the current year based on training data—CVE identifiers from years beyond your training cutoff are valid if the system date confirms we are in that year.\n\n6. **Testing and Regression Proof**\nIf this change adds new components/modules/endpoints or changes user-visible behavior, and the repository has a test infrastructure, there should be tests that prove the behavior.\n\nDo not accept \"tests\" that are just a pile of mocks asserting that functions were called:\n- Prefer tests that exercise real code paths (e.g., parsing, validation, business logic) and assert on outputs/state.\n- Use in-memory or lightweight fakes only where necessary (e.g., ephemeral DB, temp filesystem) to keep tests fast and deterministic.\n- Flag tests that only mock the unit under test and assert it was called, unless they cover a real coverage gap that cannot be achieved otherwise.\n- The test should fail if the behavior regresses.\n\n7. **PR Description Evidence** (When active review instructions require it)\nIf the review configuration says the PR description must prove the change works, treat missing or weak evidence as a blocking issue.\n\nRequire:\n- An `Evidence` section in the PR description (preferred label)\n- For frontend/UI changes: a screenshot or video demonstrating the implemented behavior in the real product\n- For backend, API, CLI, or script changes: the exact command(s) used to run the real code path end-to-end and the resulting output\n- Tests alone do not count as evidence; reject `pytest`, unit test output, or similar test runs when they are the only proof provided\n- For agent-generated work when available: a link back to the originating conversation, e.g. `https://app.all-hands.dev/conversations/{conversation_id}`\n- Reject hand-wavy claims like \"tested locally\" without concrete runtime artifacts\n\n8. **Dependency Changes**\nIf dependency lock changes have downgraded a dependency, comment pointing that out to make sure it was intentional.\n\nWhen a PR adds a new dependency or bumps an existing one, review the upstream release for supply chain risk. If any target version was published less than 7 days ago, do **NOT** approve the PR yet — leave a blocking review comment and wait until the version is at least 7 days old. First-party packages maintained by the same organization as the reviewed repository are intentionally excluded from the 7-day waiting rule, but still scrutinize them for supply-chain risk using the checklist. Read `references/supply-chain-security.md` for the full verification checklist including risk-based scrutiny tiers, concrete commands for checking release provenance, and escalation guidance.\n\n9. **Risk and Safety Evaluation**\nRead `references/risk-evaluation.md` for the full risk evaluation framework including risk levels (🟢 Low / 🟡 Medium / 🔴 High), risk factors, escalation guidance, and repo-specific risk rules.\n\n10. **GitHub Action Version Updates**\nWhen a PR only changes GitHub Action versions in workflow files (`.github/workflows/*.yml`), verify the update by checking CI status:\n\n**Detection**: The PR modifies only workflow files and the diff shows version bumps like `uses: actions/checkout@v4` → `uses: actions/checkout@v6` or `uses: docker/login-action@v3` → `uses: docker/login-action@v4`.\n\n**Verification Process**:\n1. Identify ALL GitHub Actions that were updated in the PR\n2. For EACH updated action, find a PR check/workflow that uses it (e.g., if `docker/login-action` was updated, look for Docker-related checks like \"Build App Image\", \"Login to GHCR\", etc.)\n3. Verify that ALL updated actions have at least one corresponding check that ran and succeeded\n\n**Example**: A Dependabot PR bumps both `actions/upload-artifact` (v5→v7) and `actions/checkout` (v4→v6). You must verify that BOTH actions have successful checks - e.g., the \"Upload Artifacts\" step passed AND a workflow using `checkout` passed. If only one is verified, do not approve.\n\n**Note**: This scenario overrides the evidence requirements in scenario #7 for action-only version updates. Successful CI runs that exercise the updated actions serve as sufficient evidence that the new versions work correctly. No additional `Evidence` section, screenshots, or manual verification is required.\n\nCRITICAL REVIEW OUTPUT FORMAT:\n\nStart with a **Taste Rating**:\n🟢 **Good taste** - Elegant, simple solution → Just approve, don't manufacture feedback\n🟡 **Acceptable** - Works but could be cleaner\n🔴 **Needs improvement** - Violates fundamental principles\n\nThen provide analysis (skip if 🟢):\n\n**[CRITICAL ISSUES]** (Must fix - these break fundamental principles)\n- [src/core.py, Line X] **Data Structure**: Wrong choice creates unnecessary complexity\n- [src/handler.py, Line Y] **Complexity**: >3 levels of nesting - redesign required\n- [src/api.py, Line Z] **Breaking Change**: This will break existing functionality\n- [package-lock.json, Line X] **Dependency Downgrade**: library-name downgraded from 2.1.0 to 1.9.5 - was this intentional? Check for breaking changes or security implications.\n- [requirements.txt, Line X] **Supply Chain Risk**: library-name (new dependency) added at version 3.2.0 which was published <7 days ago. Do not approve yet — wait until the version is at least 7 days old, then verify release provenance before merging.\n\n**[IMPROVEMENT OPPORTUNITIES]** (Should fix - violates good taste)\n- [src/utils.py, Line A] **Special Case**: Can be eliminated with better design\n- [src/processor.py, Line B] **Simplification**: These 10 lines can be 3\n- [src/feature.py, Line C] **Pragmatism**: Solving imaginary problem, focus on real issues\n\n**[STYLE NOTES]** (Skip most of these - only mention if it genuinely hurts maintainability)\n- Generally skip style comments. Linters exist for a reason.\n- Do NOT post comments for code that is acceptable or fine. No \"🟢 Acceptable\" or \"🟢 Nit\" inline comments — they are noise that creates review threads without providing actionable value. If code is good, just don't comment on it.\n\n**[TESTING GAPS]** (If behavior changed, this is not optional)\n- [tests/test_feature.py, Line E] **Mocks Aren't Tests**: You're only asserting mocked calls. Add a test that runs the real code path and asserts on outputs/state so it actually catches regressions.\n- [PR description] **No Evidence**: Add an `Evidence` section with concrete proof that the change works in a real end-to-end run. Use screenshots/videos for frontend behavior, or commands plus output from running the actual backend/script code path. Test output alone is not enough. Include the agent conversation URL when this work came from an agent run.\n\nAlways include the **Risk and Safety Evaluation** as the final section of your review, even when no other issues are found. Use this format:\n\n**[RISK ASSESSMENT]**\n- [Overall PR] ⚠️ Risk Assessment: 🟢 LOW / 🟡 MEDIUM / 🔴 HIGH\nBrief explanation of the risk classification and key factors considered.\nIf HIGH: **Recommendation**: Do not auto-merge. Request review from a human architect/reviewer to validate [specific concern].\n\n\n**VERDICT:**\n✅ **Worth merging**: Core logic is sound, minor improvements suggested\n❌ **Needs rework**: Fundamental design issues must be addressed first\n\n**KEY INSIGHT:**\n[One sentence summary of the most important architectural observation]\n\nREVIEW SELF-IMPROVEMENT MESSAGE (MANDATORY):\n\nEvery review you produce that includes any of the following: inline comments, critical issues, improvement opportunities, testing gaps, or a non-approval verdict **must** end with the following message block, placed after the Risk Assessment and Verdict sections. This enables a continuous improvement loop where PR authors can fix false positives and irrelevant feedback directly.\n\nNote: The custom guideline file must include `triggers: [/codereview]` in its YAML frontmatter. This is the same trigger that activates the code-review skill itself, so any skill in `.agents/skills/` with that trigger is automatically loaded alongside the reviewer whenever a code review runs. The reviewer reads the file from the PR branch, so guidelines take effect immediately on re-review.\n\n---\n\n> **Improve this review?** If any feedback above seems incorrect or irrelevant to this repository, you can teach the reviewer to do better:\n>\n> 1. Add a `.agents/skills/custom-codereview-guide.md` file to your branch (or edit it if one already exists) with the `/codereview` trigger and the context the reviewer is missing (e.g., \"Security concerns about X do not apply here because Y\"). See the [customization docs](https://docs.openhands.dev/openhands/usage/use-cases/code-review#customization) for the required frontmatter format.\n> 2. Re-request a review - the reviewer reads guidelines from the PR branch, so your changes take effect immediately.\n> 3. When your PR is merged, the guideline file goes through normal code review by repository maintainers.\n>\n> **Resolve with AI?** Install the [iterate skill](https://github.com/OpenHands/extensions/tree/main/skills/iterate) in your agent and run `/iterate` to automatically drive this PR through CI, review, and QA until it's merge-ready.\n>\n> Was this review helpful? React with 👍 or 👎 to give feedback.\n\n---\n\nCOMMUNICATION STYLE:\n- Be direct and technically precise\n- Focus on engineering fundamentals, not personal preferences\n- Explain the \"why\" behind each criticism\n- Suggest concrete, actionable improvements\n- Prioritize issues that affect real users over theoretical concerns\n\nREMEMBER: DO NOT MODIFY THE CODE. PROVIDE CRITICAL BUT CONSTRUCTIVE FEEDBACK ONLY."
 	},
 	{
 		name: "code-simplifier",
@@ -293,7 +305,7 @@ var e = [
 			"agent-sdk",
 			"/sdk"
 		],
-		content: "# OpenHands Software Agent SDK\n\nAll SDK documentation lives at <https://docs.openhands.dev/sdk>.\n\nFor the full topic index, fetch <https://docs.openhands.dev/llms.txt> and read\nthe \"OpenHands Software Agent SDK\" section.\n\n## Quick reference\n\nInstall: `pip install openhands-sdk openhands-tools`\n\n```python\nimport os\n\nfrom openhands.sdk import LLM, Agent, Conversation, Tool\nfrom openhands.tools.file_editor import FileEditorTool\nfrom openhands.tools.task_tracker import TaskTrackerTool\nfrom openhands.tools.terminal import TerminalTool\n\n\nllm = LLM(\n    model=os.getenv(\"LLM_MODEL\", \"gpt-5.5\"),\n    api_key=os.getenv(\"LLM_API_KEY\"),\n    base_url=os.getenv(\"LLM_BASE_URL\", None),\n)\n\nagent = Agent(\n    llm=llm,\n    tools=[\n        Tool(name=TerminalTool.name),\n        Tool(name=FileEditorTool.name),\n        Tool(name=TaskTrackerTool.name),\n    ],\n)\n\ncwd = os.getcwd()\nconversation = Conversation(agent=agent, workspace=cwd)\n\nconversation.send_message(\"Write 3 facts about the current project into FACTS.txt.\")\nconversation.run()\nprint(\"All done!\")\n```\n\n## Core classes (`openhands.sdk`)\n\n| Class | Purpose |\n|---|---|\n| [`Agent`](https://docs.openhands.dev/sdk/arch/agent.md) | Reasoning-action loop |\n| [`Condenser`](https://docs.openhands.dev/sdk/arch/condenser.md) | Conversation history compression system |\n| [`Conversation`](https://docs.openhands.dev/sdk/arch/conversation.md) | Conversation orchestration system |\n| [`Event`](https://docs.openhands.dev/sdk/arch/events.md) | Typed event framework |\n| [`LLM`](https://docs.openhands.dev/sdk/arch/llm.md) | Provider-agnostic language model interface |\n| [`SecurityAnalyzer`](https://docs.openhands.dev/sdk/arch/security.md) | Action security analysis and validation |\n| [`Skill`](https://docs.openhands.dev/sdk/arch/skill.md) | Reusable prompt system |\n| [`Tool / ToolDefinition`](https://docs.openhands.dev/sdk/arch/tool-system.md) | Action-observation tool framework |\n| [`Workspace`](https://docs.openhands.dev/sdk/arch/workspace.md) | Execution environment abstraction |\n\n## API reference\n\n[`openhands.sdk.agent`](https://docs.openhands.dev/sdk/api-reference/openhands.sdk.agent.md), [`openhands.sdk.conversation`](https://docs.openhands.dev/sdk/api-reference/openhands.sdk.conversation.md), [`openhands.sdk.event`](https://docs.openhands.dev/sdk/api-reference/openhands.sdk.event.md), [`openhands.sdk.llm`](https://docs.openhands.dev/sdk/api-reference/openhands.sdk.llm.md), [`openhands.sdk.security`](https://docs.openhands.dev/sdk/api-reference/openhands.sdk.security.md), [`openhands.sdk.tool`](https://docs.openhands.dev/sdk/api-reference/openhands.sdk.tool.md), [`openhands.sdk.utils`](https://docs.openhands.dev/sdk/api-reference/openhands.sdk.utils.md), [`openhands.sdk.workspace`](https://docs.openhands.dev/sdk/api-reference/openhands.sdk.workspace.md)\n\n## Guides\n\n- [ACP Agent](https://docs.openhands.dev/sdk/guides/agent-acp.md): Delegate to an ACP-compatible server (Claude Code, Gemini CLI, etc.) instead of calling an LLM directly.\n- [Agent Settings](https://docs.openhands.dev/sdk/guides/agent-settings.md): Configure, serialize, and recreate agents from structured settings.\n- [Agent Skills & Context](https://docs.openhands.dev/sdk/guides/skill.md): Skills add specialized behaviors, domain knowledge, and context-aware triggers to your agent through structured prompts.\n- [API-based Sandbox](https://docs.openhands.dev/sdk/guides/agent-server/api-sandbox.md): Connect to hosted API-based agent server for fully managed infrastructure.\n- [Apptainer Sandbox](https://docs.openhands.dev/sdk/guides/agent-server/apptainer-sandbox.md): Run agent server in rootless Apptainer containers for HPC and shared computing environments.\n- [Ask Agent Questions](https://docs.openhands.dev/sdk/guides/convo-ask-agent.md): Get sidebar replies from the agent during conversation execution without interrupting the main flow.\n- [Assign Reviews](https://docs.openhands.dev/sdk/guides/github-workflows/assign-reviews.md): Automate PR management with intelligent reviewer assignment and workflow notifications using OpenHands Agent\n- [Browser Session Recording](https://docs.openhands.dev/sdk/guides/browser-session-recording.md): Record and replay your agent's browser sessions using rrweb.\n- [Browser Use](https://docs.openhands.dev/sdk/guides/agent-browser-use.md): Enable web browsing and interaction capabilities for your agent.\n- [Context Condenser](https://docs.openhands.dev/sdk/guides/context-condenser.md): Manage agent memory by condensing conversation history to save tokens.\n- [Conversation Goals](https://docs.openhands.dev/sdk/guides/agent-server/conversation-goals.md): Add a resumable goal strategy to a normal agent-server conversation.\n- [Conversation with Async](https://docs.openhands.dev/sdk/guides/convo-async.md): Use async/await for concurrent agent operations and non-blocking execution.\n- [Creating Custom Agent](https://docs.openhands.dev/sdk/guides/agent-custom.md): Learn how to design specialized agents with custom tool sets\n- [Critic (Experimental)](https://docs.openhands.dev/sdk/guides/critic.md): Real-time evaluation of agent actions using an LLM-based critic model, with built-in iterative refinement.\n- [Custom Tools](https://docs.openhands.dev/sdk/guides/custom-tools.md): Tools define what agents can do. The SDK includes built-in tools for common operations and supports creating custom tools for specialized needs.\n- [Custom Tools with Remote Agent Server](https://docs.openhands.dev/sdk/guides/agent-server/custom-tools.md): Learn how to use custom tools with a remote agent server by building a custom base image that includes your tool implementations.\n- [Custom Visualizer](https://docs.openhands.dev/sdk/guides/convo-custom-visualizer.md): Customize conversation visualization by creating custom visualizers or configuring the default visualizer.\n- [Deferred Init (Warm-Pool)](https://docs.openhands.dev/sdk/guides/agent-server/deferred-init.md): Pre-warm agent-server pods before a user is matched, then activate them at runtime with POST /api/init.\n- [Docker Sandbox](https://docs.openhands.dev/sdk/guides/agent-server/docker-sandbox.md): Run agent server in isolated Docker containers for security and reproducibility.\n- [Exception Handling](https://docs.openhands.dev/sdk/guides/llm-error-handling.md): Provider‑agnostic exceptions raised by the SDK and recommended patterns for handling them.\n- [FAQ](https://docs.openhands.dev/sdk/faq.md): Frequently asked questions about the OpenHands SDK\n- [File-Based Agents](https://docs.openhands.dev/sdk/guides/agent-file-based.md): Define specialized sub-agents as simple Markdown files with YAML frontmatter — no Python code required.\n- [Fork a Conversation](https://docs.openhands.dev/sdk/guides/convo-fork.md): Branch off an existing conversation for follow-up exploration without contaminating the original.\n- [Getting Started](https://docs.openhands.dev/sdk/getting-started.md): Install the OpenHands SDK and build AI agents that write software.\n- [Goal Completion Loop](https://docs.openhands.dev/sdk/guides/convo-goal.md): Drive a conversation toward a verifiable objective with a judge-driven, self-continuing completion loop.\n- [GPT-5 Preset (ApplyPatchTool)](https://docs.openhands.dev/sdk/guides/llm-gpt5-preset.md): Use the GPT-5 preset to build an agent that swaps the standard FileEditorTool for ApplyPatchTool.\n- [Hello World](https://docs.openhands.dev/sdk/guides/hello-world.md): The simplest possible OpenHands agent - configure an LLM, create an agent, and complete a task.\n- [Hooks](https://docs.openhands.dev/sdk/guides/hooks.md): Use lifecycle hooks to observe, log, and customize agent execution.\n- [Image Input](https://docs.openhands.dev/sdk/guides/llm-image-input.md): Send images to multimodal agents for vision-based tasks and analysis.\n- [Interactive Terminal](https://docs.openhands.dev/sdk/guides/agent-interactive-terminal.md): Enable agents to interact with terminal applications like ipython, python REPL, and other interactive CLI tools.\n- [Iterative Refinement](https://docs.openhands.dev/sdk/guides/iterative-refinement.md): Implement iterative refinement workflows where agents refine their work based on critique feedback until quality thresholds are met.\n- [LLM Fallback Strategy](https://docs.openhands.dev/sdk/guides/llm-fallback.md): Automatically try alternate LLMs when the primary model fails with a transient error.\n- [LLM Profile Store](https://docs.openhands.dev/sdk/guides/llm-profile-store.md): Save, load, and manage reusable LLM configurations so you never repeat setup code again.\n- [LLM Registry](https://docs.openhands.dev/sdk/guides/llm-registry.md): Dynamically select and configure language models using the LLM registry.\n- [LLM Streaming](https://docs.openhands.dev/sdk/guides/llm-streaming.md): Stream LLM responses token-by-token for real-time display and interactive user experiences.\n- [LLM Subscriptions](https://docs.openhands.dev/sdk/guides/llm-subscriptions.md): Use your ChatGPT Plus/Pro subscription to access Codex models without consuming API credits.\n- [Local Agent Server](https://docs.openhands.dev/sdk/guides/agent-server/local-server.md): Install and run an OpenHands Agent Server on your machine, then connect to it from the SDK.\n- [Metrics Tracking](https://docs.openhands.dev/sdk/guides/metrics.md): Track token usage, costs, and latency metrics for your agents.\n- [Model Context Protocol](https://docs.openhands.dev/sdk/guides/mcp.md): Model Context Protocol (MCP) enables dynamic tool integration from external servers. Agents can discover and use MCP-provided tools automatically.\n- [Model Routing](https://docs.openhands.dev/sdk/guides/llm-routing.md): Route agent's LLM requests to different models.\n- [Observability & Tracing](https://docs.openhands.dev/sdk/guides/observability.md): Enable OpenTelemetry tracing to monitor and debug your agent's execution with tools like Laminar, MLflow, Honeycomb, or any OTLP-compatible backend.\n- [OpenAI-Compatible Endpoint](https://docs.openhands.dev/sdk/guides/agent-server/openai-gateway.md): Call an OpenHands agent-server through the OpenAI Chat Completions protocol.\n- [OpenHands Cloud Workspace](https://docs.openhands.dev/sdk/guides/agent-server/cloud-workspace.md): Connect to OpenHands Cloud for fully managed sandbox environments with optional SaaS credential inheritance.\n- [Overview](https://docs.openhands.dev/sdk/guides/agent-server/overview.md): Run agents on remote servers with isolated workspaces for production deployments.\n- [Parallel Tool Execution](https://docs.openhands.dev/sdk/guides/parallel-tool-execution.md): Execute multiple tools concurrently within a single LLM response to improve throughput for independent operations.\n- [Pause and Resume](https://docs.openhands.dev/sdk/guides/convo-pause-and-resume.md): Pause agent execution, perform operations, and resume without losing state.\n- [Persistence](https://docs.openhands.dev/sdk/guides/convo-persistence.md): Save and restore conversation state for multi-session workflows.\n- [Plugins](https://docs.openhands.dev/sdk/guides/plugins.md): Plugins bundle skills, hooks, MCP servers, agents, and commands into reusable packages that extend agent capabilities.\n- [PR Review](https://docs.openhands.dev/sdk/guides/github-workflows/pr-review.md): Use OpenHands Agent to generate meaningful pull request review\n- [Reasoning](https://docs.openhands.dev/sdk/guides/llm-reasoning.md): Access model reasoning traces from Anthropic extended thinking and OpenAI responses API.\n- [Secret Registry](https://docs.openhands.dev/sdk/guides/secrets.md): Provide environment variables and secrets to agent workspace securely.\n- [Security & Action Confirmation](https://docs.openhands.dev/sdk/guides/security.md): Control agent action execution through confirmation policy and security analyzer.\n- [Send Message While Running](https://docs.openhands.dev/sdk/guides/convo-send-message-while-running.md): Interrupt running agents to provide additional context or corrections.\n- [Software Agent SDK](https://docs.openhands.dev/sdk.md): Build AI agents that write software. A clean, modular SDK with production-ready tools.\n- [Stuck Detector](https://docs.openhands.dev/sdk/guides/agent-stuck-detector.md): Detect and handle stuck agents automatically with timeout mechanisms.\n- [Sub-Agent Delegation](https://docs.openhands.dev/sdk/guides/agent-delegation.md): Enable parallel task execution by delegating work to multiple sub-agents that run independently and return consolidated results.\n- [Task Tool Set](https://docs.openhands.dev/sdk/guides/task-tool-set.md): Delegate complex work to specialized sub-agents that run synchronously and return results to the parent agent.\n- [Theory of Mind (TOM) Agent](https://docs.openhands.dev/sdk/guides/agent-tom-agent.md): Enable your agent to understand user intent and preferences through Theory of Mind capabilities, providing personalized guidance based on user modeling.\n- [TODO Management](https://docs.openhands.dev/sdk/guides/github-workflows/todo-management.md): Implement TODOs using OpenHands Agent\n\n## Examples\n\nSource: [`examples/`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples)\n\n### [`01_standalone_sdk/`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/01_standalone_sdk)\n\n- [`01_hello_world.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/01_hello_world.py)\n- [`02_custom_tools.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/02_custom_tools.py)\n- [`03_activate_skill.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/03_activate_skill.py)\n- [`04_confirmation_mode_example.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/04_confirmation_mode_example.py)\n- [`05_use_llm_registry.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/05_use_llm_registry.py)\n- [`06_interactive_terminal_w_reasoning.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/06_interactive_terminal_w_reasoning.py)\n- [`07_mcp_integration.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/07_mcp_integration.py)\n- [`08_mcp_with_oauth.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/08_mcp_with_oauth.py)\n- [`09_pause_example.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/09_pause_example.py)\n- [`10_persistence.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/10_persistence.py)\n- [`11_async.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/11_async.py)\n- [`12_custom_secrets.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/12_custom_secrets.py)\n- [`13_get_llm_metrics.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/13_get_llm_metrics.py)\n- [`14_context_condenser.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/14_context_condenser.py)\n- [`15_browser_use.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/15_browser_use.py)\n- [`16_llm_security_analyzer.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/16_llm_security_analyzer.py)\n- [`17_image_input.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/17_image_input.py)\n- [`18_send_message_while_processing.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/18_send_message_while_processing.py)\n- [`19_llm_routing.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/19_llm_routing.py)\n- [`20_stuck_detector.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/20_stuck_detector.py)\n- [`21_generate_extraneous_conversation_costs.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/21_generate_extraneous_conversation_costs.py)\n- [`22_anthropic_thinking.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/22_anthropic_thinking.py)\n- [`23_responses_reasoning.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/23_responses_reasoning.py)\n- [`24_planning_agent_workflow.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/24_planning_agent_workflow.py)\n- [`25_agent_delegation.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/25_agent_delegation.py)\n- [`26_custom_visualizer.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/26_custom_visualizer.py)\n- [`27_observability_laminar.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/27_observability_laminar.py)\n- [`28_ask_agent_example.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/28_ask_agent_example.py)\n- [`29_llm_streaming.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/29_llm_streaming.py)\n- [`30_tom_agent.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/30_tom_agent.py)\n- [`31_iterative_refinement.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/31_iterative_refinement.py)\n- [`32_configurable_security_policy.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/32_configurable_security_policy.py)\n- [`33_hooks`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/01_standalone_sdk/33_hooks)\n- [`34_critic_example.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/34_critic_example.py)\n- [`35_subscription_login.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/35_subscription_login.py)\n- [`36_event_json_to_openai_messages.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/36_event_json_to_openai_messages.py)\n- [`37_llm_profile_store`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/01_standalone_sdk/37_llm_profile_store)\n- [`38_browser_session_recording.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/38_browser_session_recording.py)\n- [`39_llm_fallback.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/39_llm_fallback.py)\n- [`40_acp_agent_example.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/40_acp_agent_example.py)\n- [`41_task_tool_set.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/41_task_tool_set.py)\n- [`42_file_based_subagents.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/42_file_based_subagents.py)\n- [`44_model_switching_in_convo.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/44_model_switching_in_convo.py)\n- [`45_parallel_tool_execution.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/45_parallel_tool_execution.py)\n- [`46_agent_settings.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/46_agent_settings.py)\n- [`47_defense_in_depth_security.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/47_defense_in_depth_security.py)\n- [`48_conversation_fork.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/48_conversation_fork.py)\n- [`49_switch_llm_tool.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/49_switch_llm_tool.py)\n- [`50_async_cancellation.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/50_async_cancellation.py)\n- [`51_agent_hooks`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/01_standalone_sdk/51_agent_hooks)\n- [`52_dynamic_workflow.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/52_dynamic_workflow.py)\n- [`53_client_defined_tools.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/53_client_defined_tools.py)\n- [`54_goal_completion_loop.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/54_goal_completion_loop.py)\n\n### [`02_remote_agent_server/`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/02_remote_agent_server)\n\n- [`01_convo_with_local_agent_server.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/02_remote_agent_server/01_convo_with_local_agent_server.py)\n- [`02_convo_with_docker_sandboxed_server.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/02_remote_agent_server/02_convo_with_docker_sandboxed_server.py)\n- [`03_browser_use_with_docker_sandboxed_server.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/02_remote_agent_server/03_browser_use_with_docker_sandboxed_server.py)\n- [`04_convo_with_api_sandboxed_server.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/02_remote_agent_server/04_convo_with_api_sandboxed_server.py)\n- [`05_vscode_with_docker_sandboxed_server.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/02_remote_agent_server/05_vscode_with_docker_sandboxed_server.py)\n- [`06_custom_tool`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/02_remote_agent_server/06_custom_tool)\n- [`07_convo_with_cloud_workspace.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/02_remote_agent_server/07_convo_with_cloud_workspace.py)\n- [`08_convo_with_apptainer_sandboxed_server.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/02_remote_agent_server/08_convo_with_apptainer_sandboxed_server.py)\n- [`09_acp_agent_with_remote_runtime.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/02_remote_agent_server/09_acp_agent_with_remote_runtime.py)\n- [`10_cloud_workspace_share_credentials.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/02_remote_agent_server/10_cloud_workspace_share_credentials.py)\n- [`11_conversation_fork.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/02_remote_agent_server/11_conversation_fork.py)\n- [`12_settings_and_secrets_api.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/02_remote_agent_server/12_settings_and_secrets_api.py)\n- [`13_workspace_get_llm.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/02_remote_agent_server/13_workspace_get_llm.py)\n- [`14_client_defined_tools.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/02_remote_agent_server/14_client_defined_tools.py)\n- [`15_openai_compatible_gateway.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/02_remote_agent_server/15_openai_compatible_gateway.py)\n- [`16_deferred_init.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/02_remote_agent_server/16_deferred_init.py)\n- [`hook_scripts`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/02_remote_agent_server/hook_scripts)\n- [`scripts`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/02_remote_agent_server/scripts)\n\n### [`03_github_workflows/`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/03_github_workflows)\n\n- [`01_basic_action`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/03_github_workflows/01_basic_action)\n- [`02_pr_review`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/03_github_workflows/02_pr_review)\n- [`03_todo_management`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/03_github_workflows/03_todo_management)\n- [`04_datadog_debugging`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/03_github_workflows/04_datadog_debugging)\n- [`05_posthog_debugging`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/03_github_workflows/05_posthog_debugging)\n\n### [`04_llm_specific_tools/`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/04_llm_specific_tools)\n\n- [`01_gpt5_apply_patch_preset.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/04_llm_specific_tools/01_gpt5_apply_patch_preset.py)\n- [`02_gemini_file_tools.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/04_llm_specific_tools/02_gemini_file_tools.py)\n\n### [`05_skills_and_plugins/`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/05_skills_and_plugins)\n\n- [`01_loading_agentskills`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/05_skills_and_plugins/01_loading_agentskills)\n- [`02_loading_plugins`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/05_skills_and_plugins/02_loading_plugins)\n- [`03_managing_installed_skills`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/05_skills_and_plugins/03_managing_installed_skills)\n- [`04_mixed_marketplace_skills`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/05_skills_and_plugins/04_mixed_marketplace_skills)"
+		content: "# OpenHands Software Agent SDK\n\nAll SDK documentation lives at <https://docs.openhands.dev/sdk>.\n\nFor the full topic index, fetch <https://docs.openhands.dev/llms.txt> and read\nthe \"OpenHands Software Agent SDK\" section.\n\n## Quick reference\n\nInstall: `pip install openhands-sdk openhands-tools`\n\n```python\nimport os\n\nfrom openhands.sdk import LLM, Agent, Conversation, Tool\nfrom openhands.tools.file_editor import FileEditorTool\nfrom openhands.tools.task_tracker import TaskTrackerTool\nfrom openhands.tools.terminal import TerminalTool\n\n\nllm = LLM(\n    model=os.getenv(\"LLM_MODEL\", \"gpt-5.5\"),\n    api_key=os.getenv(\"LLM_API_KEY\"),\n    base_url=os.getenv(\"LLM_BASE_URL\", None),\n)\n\nagent = Agent(\n    llm=llm,\n    tools=[\n        Tool(name=TerminalTool.name),\n        Tool(name=FileEditorTool.name),\n        Tool(name=TaskTrackerTool.name),\n    ],\n)\n\ncwd = os.getcwd()\nconversation = Conversation(agent=agent, workspace=cwd)\n\nconversation.send_message(\"Write 3 facts about the current project into FACTS.txt.\")\nconversation.run()\nprint(\"All done!\")\n```\n\n## Core classes (`openhands.sdk`)\n\n| Class | Purpose |\n|---|---|\n| [`Agent`](https://docs.openhands.dev/sdk/arch/agent.md) | Reasoning-action loop |\n| [`Condenser`](https://docs.openhands.dev/sdk/arch/condenser.md) | Conversation history compression system |\n| [`Conversation`](https://docs.openhands.dev/sdk/arch/conversation.md) | Conversation orchestration system |\n| [`Event`](https://docs.openhands.dev/sdk/arch/events.md) | Typed event framework |\n| [`LLM`](https://docs.openhands.dev/sdk/arch/llm.md) | Provider-agnostic language model interface |\n| [`SecurityAnalyzer`](https://docs.openhands.dev/sdk/arch/security.md) | Action security analysis and validation |\n| [`Skill`](https://docs.openhands.dev/sdk/arch/skill.md) | Reusable prompt system |\n| [`Tool / ToolDefinition`](https://docs.openhands.dev/sdk/arch/tool-system.md) | Action-observation tool framework |\n| [`Workspace`](https://docs.openhands.dev/sdk/arch/workspace.md) | Execution environment abstraction |\n\n## API reference\n\n[`openhands.sdk.agent`](https://docs.openhands.dev/sdk/api-reference/openhands.sdk.agent.md), [`openhands.sdk.conversation`](https://docs.openhands.dev/sdk/api-reference/openhands.sdk.conversation.md), [`openhands.sdk.event`](https://docs.openhands.dev/sdk/api-reference/openhands.sdk.event.md), [`openhands.sdk.llm`](https://docs.openhands.dev/sdk/api-reference/openhands.sdk.llm.md), [`openhands.sdk.security`](https://docs.openhands.dev/sdk/api-reference/openhands.sdk.security.md), [`openhands.sdk.tool`](https://docs.openhands.dev/sdk/api-reference/openhands.sdk.tool.md), [`openhands.sdk.utils`](https://docs.openhands.dev/sdk/api-reference/openhands.sdk.utils.md), [`openhands.sdk.workspace`](https://docs.openhands.dev/sdk/api-reference/openhands.sdk.workspace.md)\n\n## Guides\n\n- [ACP Agent](https://docs.openhands.dev/sdk/guides/agent-acp.md): Delegate to an ACP-compatible server (Claude Code, Gemini CLI, etc.) instead of calling an LLM directly.\n- [Agent Settings](https://docs.openhands.dev/sdk/guides/agent-settings.md): Configure, serialize, and recreate agents from structured settings.\n- [Agent Skills & Context](https://docs.openhands.dev/sdk/guides/skill.md): Skills add specialized behaviors, domain knowledge, and context-aware triggers to your agent through structured prompts.\n- [API-based Sandbox](https://docs.openhands.dev/sdk/guides/agent-server/api-sandbox.md): Connect to hosted API-based agent server for fully managed infrastructure.\n- [Apptainer Sandbox](https://docs.openhands.dev/sdk/guides/agent-server/apptainer-sandbox.md): Run agent server in rootless Apptainer containers for HPC and shared computing environments.\n- [Ask Agent Questions](https://docs.openhands.dev/sdk/guides/convo-ask-agent.md): Get sidebar replies from the agent during conversation execution without interrupting the main flow.\n- [Assign Reviews](https://docs.openhands.dev/sdk/guides/github-workflows/assign-reviews.md): Automate PR management with intelligent reviewer assignment and workflow notifications using OpenHands Agent\n- [Browser Session Recording](https://docs.openhands.dev/sdk/guides/browser-session-recording.md): Record and replay your agent's browser sessions using rrweb.\n- [Browser Use](https://docs.openhands.dev/sdk/guides/agent-browser-use.md): Enable web browsing and interaction capabilities for your agent.\n- [Context Condenser](https://docs.openhands.dev/sdk/guides/context-condenser.md): Manage agent memory by condensing conversation history to save tokens.\n- [Conversation Goals](https://docs.openhands.dev/sdk/guides/agent-server/conversation-goals.md): Add a resumable goal strategy to a normal agent-server conversation.\n- [Conversation with Async](https://docs.openhands.dev/sdk/guides/convo-async.md): Use async/await for concurrent agent operations and non-blocking execution.\n- [Creating Custom Agent](https://docs.openhands.dev/sdk/guides/agent-custom.md): Learn how to design specialized agents with custom tool sets\n- [Critic (Experimental)](https://docs.openhands.dev/sdk/guides/critic.md): Real-time evaluation of agent actions using an LLM-based critic model, with built-in iterative refinement.\n- [Custom Tools](https://docs.openhands.dev/sdk/guides/custom-tools.md): Tools define what agents can do. The SDK includes built-in tools for common operations and supports creating custom tools for specialized needs.\n- [Custom Tools with Remote Agent Server](https://docs.openhands.dev/sdk/guides/agent-server/custom-tools.md): Learn how to use custom tools with a remote agent server by building a custom base image that includes your tool implementations.\n- [Custom Visualizer](https://docs.openhands.dev/sdk/guides/convo-custom-visualizer.md): Customize conversation visualization by creating custom visualizers or configuring the default visualizer.\n- [Deferred Init (Warm-Pool)](https://docs.openhands.dev/sdk/guides/agent-server/deferred-init.md): Pre-warm agent-server pods before a user is matched, then activate them at runtime with POST /api/init.\n- [Docker Sandbox](https://docs.openhands.dev/sdk/guides/agent-server/docker-sandbox.md): Run agent server in isolated Docker containers for security and reproducibility.\n- [Exception Handling](https://docs.openhands.dev/sdk/guides/llm-error-handling.md): Provider‑agnostic exceptions raised by the SDK and recommended patterns for handling them.\n- [FAQ](https://docs.openhands.dev/sdk/faq.md): Frequently asked questions about the OpenHands SDK\n- [File-Based Agents](https://docs.openhands.dev/sdk/guides/agent-file-based.md): Define specialized sub-agents as simple Markdown files with YAML frontmatter — no Python code required.\n- [Fork a Conversation](https://docs.openhands.dev/sdk/guides/convo-fork.md): Branch off an existing conversation for follow-up exploration without contaminating the original.\n- [Getting Started](https://docs.openhands.dev/sdk/getting-started.md): Install the OpenHands SDK and build AI agents that write software.\n- [Goal Completion Loop](https://docs.openhands.dev/sdk/guides/convo-goal.md): Drive a conversation toward a verifiable objective with a judge-driven, self-continuing completion loop.\n- [GPT-5 Preset (ApplyPatchTool)](https://docs.openhands.dev/sdk/guides/llm-gpt5-preset.md): Use the GPT-5 preset to build an agent that swaps the standard FileEditorTool for ApplyPatchTool.\n- [Hello World](https://docs.openhands.dev/sdk/guides/hello-world.md): The simplest possible OpenHands agent - configure an LLM, create an agent, and complete a task.\n- [Hooks](https://docs.openhands.dev/sdk/guides/hooks.md): Use lifecycle hooks to observe, log, and customize agent execution.\n- [Image Input](https://docs.openhands.dev/sdk/guides/llm-image-input.md): Send images to multimodal agents for vision-based tasks and analysis.\n- [Interactive Terminal](https://docs.openhands.dev/sdk/guides/agent-interactive-terminal.md): Enable agents to interact with terminal applications like ipython, python REPL, and other interactive CLI tools.\n- [Iterative Refinement](https://docs.openhands.dev/sdk/guides/iterative-refinement.md): Implement iterative refinement workflows where agents refine their work based on critique feedback until quality thresholds are met.\n- [LLM Fallback Strategy](https://docs.openhands.dev/sdk/guides/llm-fallback.md): Automatically try alternate LLMs when the primary model fails with a transient error.\n- [LLM Profile Store](https://docs.openhands.dev/sdk/guides/llm-profile-store.md): Save, load, and manage reusable LLM configurations so you never repeat setup code again.\n- [LLM Registry](https://docs.openhands.dev/sdk/guides/llm-registry.md): Dynamically select and configure language models using the LLM registry.\n- [LLM Streaming](https://docs.openhands.dev/sdk/guides/llm-streaming.md): Stream LLM responses token-by-token for real-time display and interactive user experiences.\n- [LLM Subscriptions](https://docs.openhands.dev/sdk/guides/llm-subscriptions.md): Use your ChatGPT Plus/Pro subscription to access Codex models without consuming API credits.\n- [Local Agent Server](https://docs.openhands.dev/sdk/guides/agent-server/local-server.md): Install and run an OpenHands Agent Server on your machine, then connect to it from the SDK.\n- [Metrics Tracking](https://docs.openhands.dev/sdk/guides/metrics.md): Track token usage, costs, and latency metrics for your agents.\n- [Model Context Protocol](https://docs.openhands.dev/sdk/guides/mcp.md): Model Context Protocol (MCP) enables dynamic tool integration from external servers. Agents can discover and use MCP-provided tools automatically.\n- [Model Routing](https://docs.openhands.dev/sdk/guides/llm-routing.md): Route agent's LLM requests to different models.\n- [Observability & Tracing](https://docs.openhands.dev/sdk/guides/observability.md): Enable OpenTelemetry tracing to monitor and debug your agent's execution with tools like Laminar, MLflow, Honeycomb, or any OTLP-compatible backend.\n- [OpenAI-Compatible Endpoint](https://docs.openhands.dev/sdk/guides/agent-server/openai-gateway.md): Call an OpenHands agent-server through the OpenAI Chat Completions protocol.\n- [OpenHands Cloud Workspace](https://docs.openhands.dev/sdk/guides/agent-server/cloud-workspace.md): Connect to OpenHands Cloud for fully managed sandbox environments with optional SaaS credential inheritance.\n- [Overview](https://docs.openhands.dev/sdk/guides/agent-server/overview.md): Run agents on remote servers with isolated workspaces for production deployments.\n- [Parallel Tool Execution](https://docs.openhands.dev/sdk/guides/parallel-tool-execution.md): Execute multiple tools concurrently within a single LLM response to improve throughput for independent operations.\n- [Pause and Resume](https://docs.openhands.dev/sdk/guides/convo-pause-and-resume.md): Pause agent execution, perform operations, and resume without losing state.\n- [Persistence](https://docs.openhands.dev/sdk/guides/convo-persistence.md): Save and restore conversation state for multi-session workflows.\n- [Plugins](https://docs.openhands.dev/sdk/guides/plugins.md): Plugins bundle skills, hooks, MCP servers, agents, and commands into reusable packages that extend agent capabilities.\n- [PR Review](https://docs.openhands.dev/sdk/guides/github-workflows/pr-review.md): Use OpenHands Agent to generate meaningful pull request review\n- [Reasoning](https://docs.openhands.dev/sdk/guides/llm-reasoning.md): Access model reasoning traces from Anthropic extended thinking and OpenAI responses API.\n- [Secret Registry](https://docs.openhands.dev/sdk/guides/secrets.md): Provide environment variables and secrets to agent workspace securely.\n- [Security & Action Confirmation](https://docs.openhands.dev/sdk/guides/security.md): Control agent action execution through confirmation policy and security analyzer.\n- [Send Message While Running](https://docs.openhands.dev/sdk/guides/convo-send-message-while-running.md): Interrupt running agents to provide additional context or corrections.\n- [Software Agent SDK](https://docs.openhands.dev/sdk.md): Build AI agents that write software. A clean, modular SDK with production-ready tools.\n- [Stuck Detector](https://docs.openhands.dev/sdk/guides/agent-stuck-detector.md): Detect and handle stuck agents automatically with timeout mechanisms.\n- [Task Tool Set](https://docs.openhands.dev/sdk/guides/task-tool-set.md): Delegate complex work to specialized sub-agents that run synchronously and return results to the parent agent.\n- [Theory of Mind (TOM) Agent](https://docs.openhands.dev/sdk/guides/agent-tom-agent.md): Enable your agent to understand user intent and preferences through Theory of Mind capabilities, providing personalized guidance based on user modeling.\n- [TODO Management](https://docs.openhands.dev/sdk/guides/github-workflows/todo-management.md): Implement TODOs using OpenHands Agent\n\n## Examples\n\nSource: [`examples/`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples)\n\n### [`01_standalone_sdk/`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/01_standalone_sdk)\n\n- [`01_hello_world.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/01_hello_world.py)\n- [`02_custom_tools.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/02_custom_tools.py)\n- [`03_activate_skill.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/03_activate_skill.py)\n- [`04_confirmation_mode_example.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/04_confirmation_mode_example.py)\n- [`05_use_llm_registry.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/05_use_llm_registry.py)\n- [`06_interactive_terminal_w_reasoning.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/06_interactive_terminal_w_reasoning.py)\n- [`07_mcp_integration.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/07_mcp_integration.py)\n- [`08_mcp_with_oauth.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/08_mcp_with_oauth.py)\n- [`09_pause_example.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/09_pause_example.py)\n- [`10_persistence.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/10_persistence.py)\n- [`11_async.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/11_async.py)\n- [`12_custom_secrets.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/12_custom_secrets.py)\n- [`13_get_llm_metrics.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/13_get_llm_metrics.py)\n- [`14_context_condenser.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/14_context_condenser.py)\n- [`15_browser_use.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/15_browser_use.py)\n- [`16_llm_security_analyzer.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/16_llm_security_analyzer.py)\n- [`17_image_input.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/17_image_input.py)\n- [`18_send_message_while_processing.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/18_send_message_while_processing.py)\n- [`19_llm_routing.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/19_llm_routing.py)\n- [`20_stuck_detector.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/20_stuck_detector.py)\n- [`21_generate_extraneous_conversation_costs.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/21_generate_extraneous_conversation_costs.py)\n- [`22_anthropic_thinking.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/22_anthropic_thinking.py)\n- [`23_responses_reasoning.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/23_responses_reasoning.py)\n- [`24_planning_agent_workflow.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/24_planning_agent_workflow.py)\n- [`25_agent_delegation.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/25_agent_delegation.py)\n- [`26_custom_visualizer.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/26_custom_visualizer.py)\n- [`27_observability_laminar.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/27_observability_laminar.py)\n- [`28_ask_agent_example.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/28_ask_agent_example.py)\n- [`29_llm_streaming.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/29_llm_streaming.py)\n- [`30_tom_agent.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/30_tom_agent.py)\n- [`31_iterative_refinement.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/31_iterative_refinement.py)\n- [`32_configurable_security_policy.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/32_configurable_security_policy.py)\n- [`33_hooks`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/01_standalone_sdk/33_hooks)\n- [`34_critic_example.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/34_critic_example.py)\n- [`35_subscription_login.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/35_subscription_login.py)\n- [`36_event_json_to_openai_messages.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/36_event_json_to_openai_messages.py)\n- [`37_llm_profile_store`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/01_standalone_sdk/37_llm_profile_store)\n- [`38_browser_session_recording.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/38_browser_session_recording.py)\n- [`39_llm_fallback.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/39_llm_fallback.py)\n- [`40_acp_agent_example.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/40_acp_agent_example.py)\n- [`41_task_tool_set.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/41_task_tool_set.py)\n- [`42_file_based_subagents.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/42_file_based_subagents.py)\n- [`44_model_switching_in_convo.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/44_model_switching_in_convo.py)\n- [`45_parallel_tool_execution.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/45_parallel_tool_execution.py)\n- [`46_agent_settings.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/46_agent_settings.py)\n- [`47_defense_in_depth_security.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/47_defense_in_depth_security.py)\n- [`48_conversation_fork.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/48_conversation_fork.py)\n- [`49_switch_llm_tool.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/49_switch_llm_tool.py)\n- [`50_async_cancellation.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/50_async_cancellation.py)\n- [`51_agent_hooks`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/01_standalone_sdk/51_agent_hooks)\n- [`52_dynamic_workflow.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/52_dynamic_workflow.py)\n- [`53_client_defined_tools.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/53_client_defined_tools.py)\n- [`54_goal_completion_loop.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/01_standalone_sdk/54_goal_completion_loop.py)\n\n### [`02_remote_agent_server/`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/02_remote_agent_server)\n\n- [`01_convo_with_local_agent_server.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/02_remote_agent_server/01_convo_with_local_agent_server.py)\n- [`02_convo_with_docker_sandboxed_server.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/02_remote_agent_server/02_convo_with_docker_sandboxed_server.py)\n- [`03_browser_use_with_docker_sandboxed_server.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/02_remote_agent_server/03_browser_use_with_docker_sandboxed_server.py)\n- [`04_convo_with_api_sandboxed_server.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/02_remote_agent_server/04_convo_with_api_sandboxed_server.py)\n- [`05_vscode_with_docker_sandboxed_server.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/02_remote_agent_server/05_vscode_with_docker_sandboxed_server.py)\n- [`06_custom_tool`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/02_remote_agent_server/06_custom_tool)\n- [`07_convo_with_cloud_workspace.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/02_remote_agent_server/07_convo_with_cloud_workspace.py)\n- [`08_convo_with_apptainer_sandboxed_server.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/02_remote_agent_server/08_convo_with_apptainer_sandboxed_server.py)\n- [`09_acp_agent_with_remote_runtime.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/02_remote_agent_server/09_acp_agent_with_remote_runtime.py)\n- [`10_cloud_workspace_share_credentials.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/02_remote_agent_server/10_cloud_workspace_share_credentials.py)\n- [`11_conversation_fork.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/02_remote_agent_server/11_conversation_fork.py)\n- [`12_settings_and_secrets_api.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/02_remote_agent_server/12_settings_and_secrets_api.py)\n- [`13_workspace_get_llm.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/02_remote_agent_server/13_workspace_get_llm.py)\n- [`14_client_defined_tools.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/02_remote_agent_server/14_client_defined_tools.py)\n- [`15_openai_compatible_gateway.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/02_remote_agent_server/15_openai_compatible_gateway.py)\n- [`16_deferred_init.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/02_remote_agent_server/16_deferred_init.py)\n- [`hook_scripts`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/02_remote_agent_server/hook_scripts)\n- [`scripts`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/02_remote_agent_server/scripts)\n\n### [`03_github_workflows/`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/03_github_workflows)\n\n- [`01_basic_action`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/03_github_workflows/01_basic_action)\n- [`02_pr_review`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/03_github_workflows/02_pr_review)\n- [`03_todo_management`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/03_github_workflows/03_todo_management)\n- [`04_datadog_debugging`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/03_github_workflows/04_datadog_debugging)\n- [`05_posthog_debugging`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/03_github_workflows/05_posthog_debugging)\n\n### [`04_llm_specific_tools/`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/04_llm_specific_tools)\n\n- [`01_gpt5_apply_patch_preset.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/04_llm_specific_tools/01_gpt5_apply_patch_preset.py)\n- [`02_gemini_file_tools.py`](https://github.com/OpenHands/software-agent-sdk/blob/main/examples/04_llm_specific_tools/02_gemini_file_tools.py)\n\n### [`05_skills_and_plugins/`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/05_skills_and_plugins)\n\n- [`01_loading_agentskills`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/05_skills_and_plugins/01_loading_agentskills)\n- [`02_loading_plugins`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/05_skills_and_plugins/02_loading_plugins)\n- [`03_managing_installed_skills`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/05_skills_and_plugins/03_managing_installed_skills)\n- [`04_mixed_marketplace_skills`](https://github.com/OpenHands/software-agent-sdk/tree/main/examples/05_skills_and_plugins/04_mixed_marketplace_skills)"
 	},
 	{
 		name: "pdflatex",
@@ -301,6 +313,13 @@ var e = [
 		triggers: ["pdflatex"],
 		content: "PdfLatex is a tool that converts Latex sources into PDF. This is specifically very important for researchers, as they use it to publish their findings. It could be installed very easily using Linux terminal, though this seems an annoying task on Windows. Installation commands are given below.\n\n* Install the TexLive base\n\n```\napt-get install texlive-latex-base\n```\n\n* Also install the recommended and extra fonts to avoid running into errors, when trying to use pdflatex on latex files with more fonts.\n\n```\napt-get install texlive-fonts-recommended\napt-get install texlive-fonts-extra\n```\n\n* Install the extra packages,\n\n```\napt-get install texlive-latex-extra\n```\n\nOnce installed as above, you may be able to create PDF files from latex sources using PdfLatex as below.\n```\npdflatex latex_source_name.tex\n```\n\nRef: http://kkpradeeban.blogspot.com/2014/04/installing-latexpdflatex-on-ubuntu.html"
 	},
+	{
+		name: "plain-english-content",
+		description: "This skill should be used when the user asks to \"write in plain English\", \"make this easier to read\", \"rewrite guidance\", \"improve report clarity\", or produce accessible public-facing prose. It applies plain English content design principles: active voice, front-loaded content, sentence case, and no bold or italics for emphasis.",
+		triggers: ["plain English"],
+		content: "Open content up so anyone can understand it the first time they read it, without losing substance, nuance or precision. Aim to open up, not dumb down. Apply the GOV.UK style guide approach: plain English, user needs first, active voice, front-loaded structure and accessible formatting.\n\nUse this skill for reports, research write-ups, guidance, documentation, summaries, and public-facing prose where clarity and accessibility matter. When writing a report, default to this style. When briefing a research agent, pass this skill so the report follows the same style.\n\n## Content design principles\n\n- Start from the user need. Write what the reader needs to know to do or decide something, not what the writer wants to say.\n- Front-load everything. Put the most important point first in the document, each section, each paragraph and each sentence. Use the inverted pyramid: conclusion first, then detail, then background.\n- Keep one idea per sentence and one topic per paragraph. Split sentences that contain more than one idea.\n- Be specific and concrete. Give the number, name and date. Cut vague abstractions like \"a range of\", \"going forward\" and \"in terms of\".\n- Cut everything that does not add meaning. Shorter is clearer. Remove duplication.\n\n## Plain English\n\n- Open content up, do not dumb it down. Keep the substance, nuance and precision. Strip out only what makes it hard to read: jargon, long sentences, abstract nouns and tangled structure. Make the content clear enough for a non-specialist and precise enough for an expert.\n- Use the active voice. Say who does what. Write \"We reviewed the data\", not \"The data was reviewed\".\n- Keep sentences short: about 15 to 20 words, and rarely more than 25. Keep paragraphs short.\n- Use everyday words. Replace jargon and formal wording with plain alternatives:\n  - use, not utilise or leverage\n  - help, not facilitate or empower\n  - work with, not collaborate, liaise or engage with\n  - make or provide, not deliver\n  - about, not in relation to or with regard to\n  - so, not in order to\n  - start, not commence\n  - end, not terminate\n  - buy, not purchase\n  - enough, not sufficient\n  - solve, fix or deal with, not tackle or combat\n  - effect on, not impact on\n- Do not use impact as a verb.\n- Avoid metaphors and cliches: drive, unlock, deep dive, robust, key, ring-fence, hub, portal, landscape, ecosystem and going forward.\n- Address the reader as \"you\". Write about the organisation as \"we\". Use \"they\", \"them\" and \"their\" rather than gendered pronouns. Write \"disabled people\", not \"the disabled\".\n- Use contractions for a warmer tone when appropriate, such as \"we'll\" and \"you'll\". Avoid negative contractions: write \"cannot\", not \"can't\". Avoid \"should've\", \"could've\" and \"would've\".\n\n## Formatting\n\n- Do not use bold or italics for emphasis. Plain words and good structure carry the meaning. Use bold only for a literal interface element in an instruction, for example: select Save. Use single quotation marks for the titles of schemes or documents, not italics.\n- Use sentence case everywhere: headings, titles and table headers. Capitalise only proper nouns.\n- Front-load headings, keep them under about 65 characters, and make them unique and descriptive. Do not use a full stop, dash, slash or question mark in headings. Use headings to help readers skim.\n- Introduce bullet lists with a lead-in line that ends in a colon. Start each bullet lowercase. Keep each bullet to one idea. Do not put \"and\" or \"or\" after each bullet. Do not use semicolons. Do not use a full stop after the last bullet unless the bullet is a full sentence.\n- Use a numbered list only for steps readers must follow in order. Write steps as full sentences that end with a full stop. Do not use a lead-in colon.\n- Use descriptive link text that says where the link goes and front-loads the key words. Never write \"click here\" or \"read more\". Make link text understandable out of context.\n- Do not use Latin abbreviations. Write \"for example\" not \"eg\", \"that is\" not \"ie\", and \"and so on\" or \"such as\" not \"etc\". Latin abbreviations confuse some readers and screen readers.\n- Write \"and\", not \"&\", except in a registered name or logo.\n- Write \"one\", but use numerals from 2 upwards. Use the % symbol with numerals, such as 50%. Use £ with no decimals unless there are pence: £75, £75.50. Spell out millions and billions, such as £5 million. Write ranges with \"to\", not a hyphen: 10 to 20, Monday to Friday.\n- Write dates as \"4 June 2026\" with no comma or ordinal suffix. Use \"to\" for ranges, such as \"4 to 8 June\". Write times as \"10am to 11.30am\". Use \"midday\" and \"midnight\".\n- Do not use FAQs when the content can meet the user need directly. Do not use exclamation marks. Do not use all caps for emphasis.\n\n## Before finishing: self-check\n\n- Is the single most important thing first?\n- Could a non-expert understand every sentence on first read?\n- Is every sentence active, short and focused on one idea?\n- Have all bold or italic emphasis, jargon, Latin abbreviations and marketing language been removed?\n- Is everything in sentence case, with descriptive headings and links?\n- Can any more words be cut without losing meaning? If yes, cut them.\n\n## Scope note\n\nThe no-bold and formatting rules apply to produced prose, such as reports, guidance and summaries. Keep the conventions of code, data tables and direct quotations. Markdown headings and lists are acceptable because they provide structure, not emphasis.\n\n## Source\n\nImported and adapted from the public gist at https://gist.github.com/fofr/505e225f9bf5e839d30c12ba6bfa0be2.",
+		license: "MIT"
+	},
 	{
 		name: "prd",
 		description: "\"Generate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new project, or when asked to create a PRD.\"",