# Create a new agent Source: https://www.skyvern.com/docs/api-reference/agents/create-a-new-agent /api-reference/openapi.json post /v1/agents Create a new agent # Delete an agent Source: https://www.skyvern.com/docs/api-reference/agents/delete-an-agent /api-reference/openapi.json post /v1/agents/{workflow_id}/delete Delete an agent # Get agent versions Source: https://www.skyvern.com/docs/api-reference/agents/get-agent-versions /api-reference/openapi.json get /v1/agents/{workflow_permanent_id}/versions Get all versions of a workflow by its permanent ID. # Get all agents Source: https://www.skyvern.com/docs/api-reference/agents/get-all-agents /api-reference/openapi.json get /v1/agents Get all workflows with the latest version for the organization. Search semantics: - If `search_key` is provided, its value is used as a unified search term for `workflows.title`, `folders.title`, and workflow parameter metadata (key, description, and default_value for `WorkflowParameterModel`). - Falls back to deprecated `title` (title-only search) if `search_key` is not provided. - Parameter metadata search excludes soft-deleted parameter rows across all parameter tables. # Get an agent by id Source: https://www.skyvern.com/docs/api-reference/agents/get-an-agent-by-id /api-reference/openapi.json get /v1/agents/{workflow_permanent_id} Fetch a single agent definition by its permanent id, optionally pinned to a specific version. Returns the agent's blocks, parameters, and metadata. # Update an agent Source: https://www.skyvern.com/docs/api-reference/agents/update-an-agent /api-reference/openapi.json post /v1/agents/{workflow_id} Update an agent # Get artifact content Source: https://www.skyvern.com/docs/api-reference/artifacts/get-artifact-content /api-reference/openapi.json get /v1/artifacts/{artifact_id}/content Download the raw content of an artifact (supports bundled artifacts). # Get artifacts for a run Source: https://www.skyvern.com/docs/api-reference/artifacts/get-artifacts-for-a-run /api-reference/openapi.json get /v1/runs/{run_id}/artifacts Get artifacts for a run # Create a browser profile Source: https://www.skyvern.com/docs/api-reference/browser-profiles/create-a-browser-profile /api-reference/openapi.json post /v1/browser_profiles Create a blank browser profile, or create one from a persistent browser session or workflow run. # Delete browser profile Source: https://www.skyvern.com/docs/api-reference/browser-profiles/delete-browser-profile /api-reference/openapi.json delete /v1/browser_profiles/{profile_id} Delete a browser profile (soft delete) # Get browser profile Source: https://www.skyvern.com/docs/api-reference/browser-profiles/get-browser-profile /api-reference/openapi.json get /v1/browser_profiles/{profile_id} Get a specific browser profile by ID # Get browser profile usage Source: https://www.skyvern.com/docs/api-reference/browser-profiles/get-browser-profile-usage /api-reference/openapi.json get /v1/browser_profiles/{profile_id}/usage List the workflows, credentials, and recent runs that depend on a browser profile. # List browser profiles Source: https://www.skyvern.com/docs/api-reference/browser-profiles/list-browser-profiles /api-reference/openapi.json get /v1/browser_profiles Get all browser profiles for the organization # Update browser profile Source: https://www.skyvern.com/docs/api-reference/browser-profiles/update-browser-profile /api-reference/openapi.json patch /v1/browser_profiles/{profile_id} Update a browser profile's name and/or description # Close a session Source: https://www.skyvern.com/docs/api-reference/browser-sessions/close-a-session /api-reference/openapi.json post /v1/browser_sessions/{browser_session_id}/close Close a session. Once closed, the session cannot be used again. # Create a session Source: https://www.skyvern.com/docs/api-reference/browser-sessions/create-a-session /api-reference/openapi.json post /v1/browser_sessions Create a browser session that persists across multiple runs # Extend a session Source: https://www.skyvern.com/docs/api-reference/browser-sessions/extend-a-session /api-reference/openapi.json post /v1/browser_sessions/{browser_session_id}/extend Extend a live browser session by a number of minutes. Sessions are created with a timeout of at most 240 minutes and can be extended, one or more times, up to a total lifetime of 360 minutes (6 hours). The minutes are added to the session's current deadline. A request for more than the remaining headroom is granted the remainder, and the response carries a warning. The response's `timeout` is the session's new total budget in minutes, counted from when the session started. # Get a session Source: https://www.skyvern.com/docs/api-reference/browser-sessions/get-a-session /api-reference/openapi.json get /v1/browser_sessions/{browser_session_id} Get details about a specific browser session, including the browser address for cdp connection. # Get active browser sessions Source: https://www.skyvern.com/docs/api-reference/browser-sessions/get-active-browser-sessions /api-reference/openapi.json get /v1/browser_sessions Get all active browser sessions for the organization # Update a session Source: https://www.skyvern.com/docs/api-reference/browser-sessions/update-a-session /api-reference/openapi.json patch /v1/browser_sessions/{browser_session_id} Update a live browser session. Currently supports toggling generate_browser_profile, which is read when the session ends to decide whether to save its browser profile. # Create credential Source: https://www.skyvern.com/docs/api-reference/credentials/create-credential /api-reference/openapi.json post /v1/credentials Creates a new credential for the current organization # Delete credential Source: https://www.skyvern.com/docs/api-reference/credentials/delete-credential /api-reference/openapi.json post /v1/credentials/{credential_id}/delete Deletes a specific credential by its ID # Get all credentials Source: https://www.skyvern.com/docs/api-reference/credentials/get-all-credentials /api-reference/openapi.json get /v1/credentials Retrieves a paginated list of credentials for the current organization # Get credential by ID Source: https://www.skyvern.com/docs/api-reference/credentials/get-credential-by-id /api-reference/openapi.json get /v1/credentials/{credential_id} Retrieves a specific credential by its ID # Send TOTP code Source: https://www.skyvern.com/docs/api-reference/credentials/send-totp-code /api-reference/openapi.json post /v1/credentials/totp Forward a TOTP (2FA, MFA) email or sms message containing the code to Skyvern. This endpoint stores the code in database so that Skyvern can use it while running tasks/workflows. # Update credential Source: https://www.skyvern.com/docs/api-reference/credentials/update-credential /api-reference/openapi.json post /v1/credentials/{credential_id}/update Overwrites the stored credential data (e.g. username/password) while keeping the same credential_id. # Delete File Source: https://www.skyvern.com/docs/api-reference/files/delete-file /api-reference/openapi.json delete /v1/files/{file_id} Delete a previously uploaded file. A file that does not exist, was already deleted, or belongs to another organization all answer 404 alike — the endpoint must not tell a caller whether someone else's file id exists. # Upload a file Source: https://www.skyvern.com/docs/api-reference/files/upload-a-file /api-reference/openapi.json post /v1/upload_file Upload a file to Skyvern storage so runs can reference it as an input. Returns the file id, its storage URI, a presigned download URL, and the expiry implied by the requested retention period. # Create folder Source: https://www.skyvern.com/docs/api-reference/folders/create-folder /api-reference/openapi.json post /v1/folders Create a new folder to organize workflows # Delete folder Source: https://www.skyvern.com/docs/api-reference/folders/delete-folder /api-reference/openapi.json delete /v1/folders/{folder_id} Delete a folder. Optionally delete all workflows in the folder. # Get folder Source: https://www.skyvern.com/docs/api-reference/folders/get-folder /api-reference/openapi.json get /v1/folders/{folder_id} Get a specific folder by ID # Get folders Source: https://www.skyvern.com/docs/api-reference/folders/get-folders /api-reference/openapi.json get /v1/folders Get all folders for the organization # Update agent folder Source: https://www.skyvern.com/docs/api-reference/folders/update-agent-folder /api-reference/openapi.json put /v1/agents/{workflow_permanent_id}/folder Update a workflow's folder assignment for the latest version # Update folder Source: https://www.skyvern.com/docs/api-reference/folders/update-folder /api-reference/openapi.json put /v1/folders/{folder_id} Update a folder's title or description # Apply to a job Source: https://www.skyvern.com/docs/api-reference/recipes/apply-to-a-job /api-reference/openapi.json post /v1/recipes/jobs/apply Start a workflow run that applies to a job with a résumé and optional credentials. # Extract a job application posting Source: https://www.skyvern.com/docs/api-reference/recipes/extract-a-job-application-posting /api-reference/openapi.json post /v1/recipes/jobs/extract Start a workflow run that extracts structured details from a job posting. # List job recipe runs Source: https://www.skyvern.com/docs/api-reference/recipes/list-job-recipe-runs /api-reference/openapi.json get /v1/recipes/jobs/runs List workflow runs started by job recipe requests. # Bulk cancel runs Source: https://www.skyvern.com/docs/api-reference/runs/bulk-cancel-runs /api-reference/openapi.json post /v1/runs/cancel Cancel multiple runs (tasks or workflows) in a single request # Cancel a run by id Source: https://www.skyvern.com/docs/api-reference/runs/cancel-a-run-by-id /api-reference/openapi.json post /v1/runs/{run_id}/cancel Cancel a run (task or workflow) # Get all runs Source: https://www.skyvern.com/docs/api-reference/runs/get-all-runs /api-reference/openapi.json get /v1/agents/runs List workflow runs across all workflows for the current organization. Results are paginated and can be filtered by **status**, **search_key**, and **error_code**. All filters are combined with **AND** logic — a run must match every supplied filter to be returned. ### search_key A case-insensitive substring search that matches against **any** of the following fields: | Searched field | Description | |---|---| | `workflow_run_id` | The unique run identifier (e.g. `wr_123…`) | | `workflow_permanent_id` | The permanent ID of the workflow that ran (e.g. `wpid_123…`) | | Workflow **title** | The title of the workflow that ran | | Parameter **key** | The `key` of any workflow parameter definition associated with the run | | Parameter **description** | The `description` of any workflow parameter definition | | Run parameter **value** | The actual value supplied for any parameter when the run was created | | `extra_http_headers` | Extra HTTP headers attached to the run (searched as raw JSON text) | | `webhook_callback_url` | The webhook URL the run posts its result to | Soft-deleted parameter definitions are excluded from key/description matching. A run is returned if **any** of the fields above contain the search term. A **complete** identifier also matches the run that used it, by exact equality: | Identifier | Description | |---|---| | `browser_profile_id` | The browser profile the run used (e.g. `bp_123…`) | | `browser_session_id` | The browser session the run used (e.g. `pbs_123…`) | | **Credential id** | A credential the run used (e.g. `cred_123…`) | A complete browser profile or browser session id is matched against those identifiers only, not the text fields above. A credential id matches a run when it is the run's sequential credential, the credential the run selected from a pool or fell back to, or the credential bound by a credential parameter on the run's workflow version when the run was created and the run recorded no selection for that parameter. Other pool and fallback members the run did not use do not match. ### error_code An **exact-match** filter against the `error_code` field inside each task's `errors` JSON array. A run matches if **any** of its tasks contains an error object with a matching `error_code` value. Error codes are user-defined strings set during workflow execution (e.g. `INVALID_CREDENTIALS`, `LOGIN_FAILED`, `CAPTCHA_DETECTED`). ### Combining filters All query parameters use AND logic: - `?status=failed` — only failed runs - `?status=failed&error_code=LOGIN_FAILED` — failed runs **and** have a LOGIN_FAILED error - `?status=failed&error_code=LOGIN_FAILED&search_key=prod_credential` — all three conditions must match # Get all runs by agent Source: https://www.skyvern.com/docs/api-reference/runs/get-all-runs-by-agent /api-reference/openapi.json get /v1/agents/{workflow_id}/runs List runs for a specific workflow. Supports filtering by **status**, **search_key**, and **error_code**. All filters are combined with **AND** logic. ### search_key Case-insensitive substring search across: workflow run ID, parameter key, parameter description, run parameter value, extra HTTP headers and webhook callback URL. A run is returned if any of these fields match. Soft-deleted parameter definitions are excluded from key/description matching. A complete browser profile ID, browser session ID or credential ID matches the run that used it exactly (no substring match). A complete browser profile or browser session ID is matched against those identifiers only, not the text fields. A credential ID matches when it is the run's sequential credential, the credential the run selected from a pool or fell back to, or the credential bound by a credential parameter on the run's workflow version when the run was created and the run recorded no selection for it. The workflow title and workflow permanent ID are matched as well. ### error_code Exact-match filter on the `error_code` field inside each task's `errors` JSON array. A run matches if any of its tasks contains an error with a matching `error_code`. ### include_child_runs Child runs — runs this workflow started from inside another workflow run — are **excluded by default**, so the history shows only top-level runs. Pass `include_child_runs=true` to list them as well; every run carries a `parent_workflow_run_id` that is `null` for top-level runs. # Get run info by id Source: https://www.skyvern.com/docs/api-reference/runs/get-run-info-by-id /api-reference/openapi.json get /v1/runs/{run_id} Get run information (task run, workflow run) # Get run timeline Source: https://www.skyvern.com/docs/api-reference/runs/get-run-timeline /api-reference/openapi.json get /v1/runs/{run_id}/timeline Get timeline for a run (workflow run or task_v2 run) # Replay a run webhook Source: https://www.skyvern.com/docs/api-reference/runs/replay-a-run-webhook /api-reference/openapi.json post /v1/runs/{run_id}/retry_webhook Retry sending the webhook for a run # Retry a run Source: https://www.skyvern.com/docs/api-reference/runs/retry-a-run /api-reference/openapi.json post /v1/agents/runs/{workflow_run_id}/retry Retry a workflow run using the original run parameters. # Run an agent Source: https://www.skyvern.com/docs/api-reference/runs/run-an-agent /api-reference/openapi.json post /v1/run/agents Run an agent # Cancel a one-time agent schedule Source: https://www.skyvern.com/docs/api-reference/schedules/cancel-a-one-time-agent-schedule /api-reference/openapi.json post /v1/agents/{workflow_permanent_id}/schedules/{workflow_schedule_id}/cancel Cancel a one-time schedule that has not fired yet. The schedule stays readable with dispatch_status canceled. Returns 409 once it has fired or was already canceled, and 422 for a recurring schedule. # Create a schedule for an agent Source: https://www.skyvern.com/docs/api-reference/schedules/create-a-schedule-for-an-agent /api-reference/openapi.json post /v1/agents/{workflow_permanent_id}/schedules Create a cron, fixed-interval or one-time schedule that runs the given agent automatically with a fixed set of parameters. An interval schedule first runs at first_fire_at, or one interval after creation. A one-time schedule runs once at run_at. Returns the stored schedule and its next upcoming run times. # Delete an agent schedule Source: https://www.skyvern.com/docs/api-reference/schedules/delete-an-agent-schedule /api-reference/openapi.json delete /v1/agents/{workflow_permanent_id}/schedules/{workflow_schedule_id} Permanently delete a schedule so it never triggers again. Returns an acknowledgement flag. # Disable an agent schedule Source: https://www.skyvern.com/docs/api-reference/schedules/disable-an-agent-schedule /api-reference/openapi.json post /v1/agents/{workflow_permanent_id}/schedules/{workflow_schedule_id}/disable Pause a schedule so it stops triggering runs, without deleting it. Returns the updated schedule. # Enable an agent schedule Source: https://www.skyvern.com/docs/api-reference/schedules/enable-an-agent-schedule /api-reference/openapi.json post /v1/agents/{workflow_permanent_id}/schedules/{workflow_schedule_id}/enable Resume a paused schedule so it starts triggering runs again. Returns the updated schedule. # Get an agent schedule by id Source: https://www.skyvern.com/docs/api-reference/schedules/get-an-agent-schedule-by-id /api-reference/openapi.json get /v1/agents/{workflow_permanent_id}/schedules/{workflow_schedule_id} Fetch one schedule belonging to an agent. Returns the schedule's cron expression or interval, timezone, parameters, enabled state, and next upcoming run times. # List all schedules for the organization Source: https://www.skyvern.com/docs/api-reference/schedules/list-all-schedules-for-the-organization /api-reference/openapi.json get /v1/schedules List every schedule in the organization, across all agents, filterable by active/paused status and a search term matched against agent title or schedule name. Returns a paginated list plus the total count. # List schedules for an agent Source: https://www.skyvern.com/docs/api-reference/schedules/list-schedules-for-an-agent /api-reference/openapi.json get /v1/agents/{workflow_permanent_id}/schedules List all schedules attached to a single agent. Returns the schedules in creation order. # Update an agent schedule Source: https://www.skyvern.com/docs/api-reference/schedules/update-an-agent-schedule /api-reference/openapi.json put /v1/agents/{workflow_permanent_id}/schedules/{workflow_schedule_id} Replace a schedule's cron expression, interval or one-time run_at, timezone, run parameters, and enabled state. A one-time schedule stays one-time and can change only until it fires; afterwards this returns 409. Returns the updated schedule and its next upcoming run times. # Get server version Source: https://www.skyvern.com/docs/api-reference/server/get-server-version /api-reference/openapi.json get /v1/version Returns the current Skyvern server version (git SHA for official builds). # List selectable browser types Source: https://www.skyvern.com/docs/api-reference/server/list-selectable-browser-types /api-reference/openapi.json get /v1/browser_types List the selectable browser engines for the workflow/run browser_type setting. The list is runtime-capability aware: a runtime that can honor an explicit engine (the cloud dynamic-browser capability) returns all supported engines, while a runtime without it (OSS/self-host) returns an empty list rather than advertising selections the server would reject. # Changelog Source: https://www.skyvern.com/docs/changelog New features, improvements, and fixes in Skyvern

TIMELINE

Week of Sep 28, 2026 Week of Sep 21, 2026 Week of Sep 14, 2026 Week of Sep 7, 2026 Week of Aug 31, 2026 Week of Aug 24, 2026 Week of Aug 17, 2026 Week of Aug 10, 2026 Week of Aug 3, 2026 Week of Jul 27, 2026 Week of Jul 20, 2026 Week of Jul 13, 2026 Week of Jul 6, 2026 Week of Jun 30, 2026 Week of Jun 22, 2026 Week of Jun 15, 2026 Week of Jun 8, 2026 Week of Jun 1, 2026 Week of May 25, 2026 Week of May 18, 2026 Week of May 11, 2026 Week of May 4, 2026 Week of Apr 27, 2026 Week of Apr 20, 2026 Week of Apr 13, 2026 Week of Feb 23, 2026 Week of Feb 16, 2026 Week of Feb 9, 2026 Week of Feb 2, 2026 Week of Jan 26, 2026 Week of Jan 19, 2026 Week of Jan 5, 2026

Changelog

New features, improvements, and fixes in Skyvern

## New features * **Downloadable Copilot-Generated Files** — Secure CodeBlocks and Copilot can now publish generated XLSX, PDF, CSV, and ZIP files as run downloads and chat download buttons. ([#8693](https://github.com/Skyvern-AI/skyvern/pull/8693)) * **Clipboard Paste in Live Browser Control** — You can now paste your clipboard while in control of a live browser, from one control bar shared by CDP and VNC sessions. ([#8699](https://github.com/Skyvern-AI/skyvern/pull/8699)) * **Redesigned Discover Home** — The Discover page's prompt, examples, and templates have been redesigned. * **Guided Full-Page Welcome for New Sign-Ups** — New accounts now land on a full-page walkthrough covering goals, expected volume, and role, replacing the old setup modal. * **Guided Template Walkthrough** — Using a home page template now copies it, opens Copilot with a numbered summary of what it does, and shows an inputs card for the credentials and values it needs. ([#8730](https://github.com/Skyvern-AI/skyvern/pull/8730)) ## Improvements * **Google Sheets Range Support** — Copilot now resolves a Sheets tab from a URL's `gid` at save time and shows the Range in append mode. ([#8696](https://github.com/Skyvern-AI/skyvern/pull/8696)) * **Clearer Personal Account Naming** — A personal account is now named after its Skyvern organization in the org menu and settings sidebar. * **Recording Controls** — The Copilot recording sticky bar is now labeled and includes a stop control. * **Redesigned Prompt Box Settings** — Advanced prompt box settings now live in a gear popover. * **Clearer Credential Refresh** — The saved-login refresh link now explains what it does. * **Clearer Copilot Change Review** — Copilot now shows its proposed changes on one annotated canvas, with plans and credential receipts shown where they happened in the turn. * **File Input URLs for Copilot** — Copilot now knows a file input can accept a user-supplied URL, not just an upload. * **Pinned Copilot Questions** — Pending Copilot questions now dock above the composer instead of scrolling out of view. * **Flexible Copilot Answers** — Copilot questions can now be answered in your own words instead of only the offered choices. ([#8713](https://github.com/Skyvern-AI/skyvern/pull/8713)) * **Chronological Copilot Activity Log** — Copilot's activity log now reads in the order things happened, with redesigned answered-question cards. ([#8718](https://github.com/Skyvern-AI/skyvern/pull/8718)) * **More Resilient Workflow Studio** — Workflow Studio now contains pane crashes instead of taking down the editor. * **Skyvern 3.0 Recommended** — The Skyvern 3.0 engine badge is now labeled "Recommended" instead of "Beta". * **Code Block Goal Editing** — Editing a code block's Goal now keeps your text and offers to update the block to match. ([#8711](https://github.com/Skyvern-AI/skyvern/pull/8711)) * **Faster Web Search** — Copilot and code blocks now search the web through a dedicated search API instead of a browser tab. ([#8708](https://github.com/Skyvern-AI/skyvern/pull/8708)) * **Clearer Billing Errors** — Skyvern now shows the reason when a billing plan change fails. * **Faster Credential Failures** — A login block now fails fast with a clear reason when it isn't bound to any of the workflow's credentials, instead of opening a browser first. * **Copilot Test Results as Cards** — Each block Copilot tests now shows as one card with its status, code change, and failing line. * **Copilot Run History by Status** — Copilot can now list a workflow's recent runs filtered by status, such as failed or terminated, instead of only seeing the most recent run. * **Longer Task Runs on Long Forms** — Task runs now get more time to finish long forms that are still making visible progress, instead of stopping once the token budget runs out. * **Unsubscribe from Skyvern Emails** — You can now unsubscribe from categories of email Skyvern sends, like the analytics digest, with a one-click link. * **Default Engine Option in Workflow Editor** — The block engine picker now has a "Default" option separate from Skyvern 1.0 and 2.0, which are now labeled Legacy. ([#8735](https://github.com/Skyvern-AI/skyvern/pull/8735)) * **Docked Copilot Sign-In Requests** — Copilot's sign-in and Google account requests now dock above the chat input instead of scrolling out of view with the transcript. * **More Reliable Copilot Repairs on SSL Errors** — Copilot no longer gives up early on ambiguous SSL connection errors during automatic repairs; it now attempts a fix. ([#8731](https://github.com/Skyvern-AI/skyvern/pull/8731)) * **Upstream Output Reuse in Copilot Repair Tests** — Testing a repaired block that reads an earlier block's output no longer fails with a template error; the test now reuses that output automatically. ([#8737](https://github.com/Skyvern-AI/skyvern/pull/8737)) ## Bug fixes * Fixed the extension bridge processing page events out of order relative to earlier responses. ([#8694](https://github.com/Skyvern-AI/skyvern/pull/8694)) * Fixed bot-challenge pages being reported as "no challenge" instead of correctly detected. ([#8695](https://github.com/Skyvern-AI/skyvern/pull/8695)) * Fixed credential approvals being lost for credentials used past the recording evidence size cap. * Fixed run errors losing their mapped error code when the task also had an OTP timeout. * Fixed Copilot forgetting an accepted state across page reloads. * Fixed a closed Workflow Studio pane reopening at the wrong edge instead of where it was. * Fixed Copilot comparing proposals against a stale staged draft instead of the current canvas. * Fixed edits being lost when rejecting a Copilot proposal that only renamed the workflow or never reached the canvas. * Fixed Gemini rejecting the MCP tool list due to a missing schema on an output parameter. * Fixed the extension relay stopping when an event callback raised an error. * Fixed run failure messages leading with an outer error instead of the actual cause. * Fixed false "Copilot is locked" toasts when expanding chat steps or switching editor views. * Fixed runs failing at max retries instead of terminating with the correct mapped error code. * Fixed plan upgrades not rolling back correctly if an in-progress ACH payment failed. * Fixed the self-hosted Discover page crashing on sign-in hooks. * Fixed literal "N/A" and "NULL" text being dropped when parsing Excel files. * Fixed PDF generation failing permanently after a page-renderer crash; it now retries on a replacement tab. * Fixed clicks on natively disabled controls taking up to 15 seconds to fail; they now fail in 2 seconds. * Fixed the AI fallback for code blocks recovering at the wrong address for a wrapped or indented `goto`. * Fixed concurrent Copilot test runs overwriting each other's workflow version. * Fixed read-only and disabled fields reporting a successful fill or clear instead of being refused. * Fixed agents with no blocks being runnable. * Fixed the Recording and Screenshots pills showing on finished runs that have neither. * Fixed the onboarding questionnaire not reappearing after a page refresh. ([#8706](https://github.com/Skyvern-AI/skyvern/pull/8706)) * Fixed a recording refinement draft being presented as a validated workflow before it was. ([#8712](https://github.com/Skyvern-AI/skyvern/pull/8712)) * Fixed Skyvern 3.0 refusing a re-ask conversion whenever a settled page's layout shifted at all, instead of only when the underlying document changed. * Fixed Copilot's Review view landing on a pending-proposal card with no available actions. ([#8714](https://github.com/Skyvern-AI/skyvern/pull/8714)) * Fixed the Copilot review-gate buttons wrapping in a narrow pane and its Test end-to-end action not being locked like Reject. ([#8715](https://github.com/Skyvern-AI/skyvern/pull/8715)) * Fixed Skyvern 3.0 mishandling a covering layer over the target field and mis-scoring an action block whose one action succeeded but whose follow-up was refused by the step cap. ([#8722](https://github.com/Skyvern-AI/skyvern/pull/8722)) * Fixed one-shot downloads not recovering correctly after a server error. * Fixed the organizations page showing a blank state instead of a full-page retry option when it failed to load. * Fixed Workflow Studio showing replay pills before there was anything to replay. * Fixed a Cloudflare Turnstile checkbox being reported as solved after it silently reset, instead of being re-clicked. * Fixed browser pages hanging for other users sharing a browser session after one person disconnected mid-interaction. ([#8736](https://github.com/Skyvern-AI/skyvern/pull/8736)) * Fixed Copilot failing before sending any request when using certain GPT-6 models. * Fixed task runs refusing to click a checkbox that sits on top of its own styled replacement, reporting it as not rendered. ([#8734](https://github.com/Skyvern-AI/skyvern/pull/8734)) * Fixed task runs losing track of a page after a click opened a new tab, causing the run to stall. ([#8733](https://github.com/Skyvern-AI/skyvern/pull/8733)) * Fixed a dark-mode flash of a white screen on sign-in, refresh, and other full page loads. ## New features * **Terminate Block** — A new workflow block lets a run end early with a custom reason, instead of running through remaining blocks. * **Copilot-Managed Schedules** — Copilot can now create and manage the open workflow's recurring schedules directly from chat. * **SMS Two-Factor Authentication** — Credentials now support SMS-based two-factor authentication with managed phone numbers. * **Elapsed-Interval Schedules** — Workflow schedules can now run on a fixed interval measured from an anchor time, instead of only fixed calendar times. ([#8660](https://github.com/Skyvern-AI/skyvern/pull/8660)) * **One-Time Scheduled Runs** — Workflow schedules can now be set to run once at a specific date and time. ([#8680](https://github.com/Skyvern-AI/skyvern/pull/8680)) * **Copilot File Upload to Pages** — Copilot can now upload a file you attach in chat directly into a page's file picker. ([#8691](https://github.com/Skyvern-AI/skyvern/pull/8691)) ## Improvements * **Full YAML Workflow Editing** — The workflow editor's YAML view now exposes and accepts every workflow setting. * **Declared Code Block Return Schema** — Code blocks can now declare a return schema for Copilot, and AI-fallback output is recorded as the block's output. * **Optional Extension User Scripts** — Browser control no longer requires the User Scripts permission to be enabled. * **Copilot Repair Test Accuracy** — Copilot repair test runs now reuse the original failed run's inputs. * **Clearer Billing Navigation** — The sidebar "Add credits" button is now labeled "Upgrade plan" / "Plan & usage". * **Organization Terminology** — Settings, the org menu, and analytics banners now say "Organization" instead of "Workspace". ([#8697](https://github.com/Skyvern-AI/skyvern/pull/8697)) * **Agent Creator Visibility** — The agents list now shows each agent's original creator. * **Agent Creation Date** — The agents list now shows each agent's first-version creation date. * **Local File Reads in Blocks** — Blocks can now read a local-storage upload referenced by a `file://` URI. * **Copilot Page-Challenge Recovery** — Copilot can now solve a page challenge or start a fresh browser when scouting a page. * **Clearer Copilot Run Results** — Copilot now reports how it picked a run for results and lists newer finished runs. * **Browser Profile Preview** — The workflow editor now shows a read-only preview of the browser profile a run would load. * **CAPTCHA Support in Code Blocks and Copilot** — Code blocks and Copilot browser-code cells can now solve image-text CAPTCHAs directly. * **More Resilient Browser Recordings** — Record Browser no longer rejects a recording outright; it now emits repair steps for actions it can't replay. * **Recording Visibility in Copilot Chat** — Browser recordings now show as a live chapter inside the Copilot chat. * **Save Credential on Enter** — Pressing Enter in the password field now saves the credential. * **Chat During Recording** — You can now talk to Copilot while a browser recording is capturing. * **Credential and Session Ownership** — Credentials and browser sessions now show who created them. ([#8654](https://github.com/Skyvern-AI/skyvern/pull/8654)) * **Cached Script Retention** — Data-retention cleanup no longer removes cached scripts, keeping optimized runs fast. * **Customer Instructions Take Priority** — Under a new run setting, Skyvern 3.0 now lets your workflow instructions override its general behavior rules, and no longer lets page content override customer-provided values. * **Layout-Resilient Cached Code** — Saved code blocks can now target metric cards with a label-anchored selector, so they survive page layout changes. * **Cleaner Run Timelines** — Run timelines now show an action's result only when one was actually recorded. * **Plain-Language Failure Labels** — Run failures now show plain-language labels instead of raw internal category names. * **More Reliable CAPTCHA Solving** — Skyvern now remembers which CAPTCHA type a given site rejects, improving solve reliability on protected pages. ([#8657](https://github.com/Skyvern-AI/skyvern/pull/8657)) * **Clearer Browser Block Validation** — The first browser block's URL is now required and validated before the block runs. * **Queued Message Indicator** — A queued Copilot message now shows as a strip on the message box. ([#8659](https://github.com/Skyvern-AI/skyvern/pull/8659)) * **Quieter Browser Pane** — The browser pane header is now less cluttered, with an overflow menu, run-only replay tabs, and clearer browser status. ([#8668](https://github.com/Skyvern-AI/skyvern/pull/8668)) * **Fewer Extension Permissions** — The Skyvern Agent browser extension no longer requests the User Scripts or unused host permissions. * **Search Block Improvements** — The Search block now uses standard error messages, and a Data Schema can be used without a Prompt. ([#8679](https://github.com/Skyvern-AI/skyvern/pull/8679)) * **Copilot Test Accuracy** — Copilot build tests now start from the saved browser profile. * **Copilot CAPTCHA Reading** — Copilot can now read image-text CAPTCHAs while scouting a page and in saved code blocks. ([#8683](https://github.com/Skyvern-AI/skyvern/pull/8683)) * **Run Attribution** — The Runs page now shows who started each workflow run. ([#8677](https://github.com/Skyvern-AI/skyvern/pull/8677)) * **Clearer Copilot Status** — Copilot now shows when it's working or waiting on you above the message box, and the Stop button matches Send. ## Bug fixes * Fixed the workflow editor losing your exact state after a rejected Copilot proposal; saves are now transactional. * Fixed one-time-code entry: Skyvern now retries once with a fresh code when a site rejects a multi-box code, and types full verification codes into one-character boxes reliably. ([#8717](https://github.com/Skyvern-AI/skyvern/pull/8717)) * Fixed the Copilot credential card staying open after picking a saved login on a new chat. * Fixed intermittent loss of live-browser control by re-sending take-control on VNC reconnect and opening the live-view socket only after VNC connects. * Fixed a sent Copilot prompt occasionally staying stuck in the queue. * Fixed several Skyvern 3.0 typing issues: appended text is now reported and placed correctly, and an offered autocomplete row is committed when none exactly matches the typed value. * Fixed clicks into embedded frames failing when the frame hadn't finished rendering. * Fixed the Copilot activity log losing a finished step's title when new work started right after. * Fixed Skyvern 3.0 hiding a read of a different browser tab as if it were a repeated read. * Fixed Skyvern 3.0 accepting task completion on a blank page or without checking the result against the stated goal. * Fixed Copilot sending a canned message instead of a real reply when a tool call produced an empty model response. * Fixed credentials chosen during a browser recording not carrying into its refinement turn. * Fixed Skyvern 3.0 hiding or mislabeling clickable rows, menu options, and buttons combined with clickable containers during page observation. ([#8716](https://github.com/Skyvern-AI/skyvern/pull/8716)) * Fixed Skyvern 3.0 not generating a real code for a credential's TOTP placeholder, unlike the previous engine. * Fixed dropdown search fields that only filter on Enter, so Skyvern 3.0 can search and filter windowed dropdowns correctly. * Fixed proxy tunnel and SOCKS failures being mislabeled as navigation failures. * Patched a security vulnerability in TLS certificate hostname validation used by outbound requests. * Fixed extension-bridge tabs and page reads breaking when a page changed its URL. * Fixed code blocks failing as busy under load instead of waiting for a free runner slot. * Fixed Copilot forgetting answers to its own questions after a few more tool calls. * Fixed Skyvern 3.0 writing dates into the wrong segment of a segmented date field. * Fixed Copilot's turn not finishing recovery correctly when a stream loss occurred but the turn ended normally. * Fixed the Search block returning results outside the requested site filter or missing results with no cached content. * Fixed Copilot showing a false "unsaved changes" warning on retry. * Fixed Reject retries in Copilot chat leaking across chats instead of staying scoped to the chat they came from. * Fixed the browser extension grouping tabs together in popup windows. * Fixed data extraction nulling out fields the goal asked to produce, instead of only nulling fields not present on the page. * Fixed Skyvern 3.0 skipping later toggle clicks in a batch after an earlier one failed. * Fixed code block page requests bypassing the run's configured browser proxy. * Fixed Skyvern 3.0 refusing to re-enter a login username the page had overwritten, while keeping the existing cap on password re-entry. * Fixed action steps being charged for calls Skyvern 3.0 refused before acting on the page. ([#8688](https://github.com/Skyvern-AI/skyvern/pull/8688)) * Fixed Copilot's first workflow submissions failing on malformed syntax; they're now built from structured objects. * Fixed a terminated Skyvern 3.0 block not getting a retry when the site skipped a screen its criterion expected. ([#8687](https://github.com/Skyvern-AI/skyvern/pull/8687)) * Fixed Copilot losing rows past the 50,000-row cut when paging a long run's results. ([#8684](https://github.com/Skyvern-AI/skyvern/pull/8684)) ## Improvements * **Workflow API settings** — PUT updates keep stored values when you omit `extra_http_headers`, `cdp_connect_headers`, `totp_identifier`, `totp_verification_url`, `webhook_callback_url`, or `proxy_location`. Explicit `null` clears these settings. A supplied value replaces the stored value. * **Header updates** — An empty mapping (`{}`) clears headers. A `***` entry in `cdp_connect_headers` keeps the stored value for that key. Values in public `extra_http_headers` updates, including `***`, are literal. **Compatibility change:** `cdp_connect_headers: null` now clears headers. Omit the field to keep them. * **Copilot settings** — Copilot inherits omitted workflow settings and resolves stored values at Accept. Model-facing workflow documents retain root `extra_http_headers` and `cdp_connect_headers` header names, with every value replaced by `***`. They omit empty header maps, TOTP identifiers, TOTP verification URLs, webhook URLs, and non-geo proxy mappings entirely. Valid geo targets, including city, subdivision, and `isISP`, remain visible. Block settings retain their existing document behavior. * **URL diagnostics** — URL validation errors identify the field and failure class without returning the URL or host. Run-request callback errors identify the callback field. Copilot removes TOTP values from runtime diagnostics sent to the model. Customer runtime diagnostics remain available. ## Improvements * **Credential Source Status** — Credential settings now show the credential source and keep service account tokens out of the interface. * **Copilot Run Context** — Copilot now receives challenge details, recovery options, every result row, and clearer browser error context for better workflow repair. * **Protected Form Submissions** — Supported job application forms now wait for challenge completion before the submit continues, reducing duplicate submissions. * **Clearer Run Timeline Statuses** — Run timelines now show verified clicks as completed and provide labels for every status glyph. * **Wider Past Runs Range** — The agent page now shows the last 365 days by default, so older runs appear without extra filter changes. * **Agent List Search Persists** — Agent list searches now survive back navigation, reloads, and shared links. * **Sidebar Links Stay Visible** — Resource links now appear on every page with a sidebar, so you can reach help without leaving the page. ## Bug fixes * Fixed dropdown selections failing when the selected label differed from the option text. ## New features * **Interactive Questions in Copilot** — Copilot can now ask questions with choices or text fields and resume after you answer. ([#8447](https://github.com/Skyvern-AI/skyvern/pull/8447)) * **Web Search for Copilot and Code Blocks** — Copilot and code blocks can now search the web directly, so workflows can collect results without scraping search pages. ([#8464](https://github.com/Skyvern-AI/skyvern/pull/8464)) * **Schema-Directed Parquet Exports** — Workflows can now export extracted data to typed Parquet files from a standalone or extraction block. ([#8368](https://github.com/Skyvern-AI/skyvern/pull/8368), [#8397](https://github.com/Skyvern-AI/skyvern/pull/8397)) * **Login Blocks from Browser Recordings** — Browser recordings now create login blocks from saved credentials and retain native select choices. * **In-Chat Credential Requests** — Copilot can now ask for missing credentials in chat and continue after you provide or skip them. ([#8420](https://github.com/Skyvern-AI/skyvern/pull/8420)) * **Google Sheets Connections in Chat** — Copilot can now connect Google Sheets accounts in chat and resolve unambiguous saved connection names. ([#8412](https://github.com/Skyvern-AI/skyvern/pull/8412)) ## Improvements * **Embedded-Page Support** — Copilot and secure CodeBlocks now keep selected frame data current across navigation, popups, and detached frames. ([#8341](https://github.com/Skyvern-AI/skyvern/pull/8341), [#8361](https://github.com/Skyvern-AI/skyvern/pull/8361)) * **Clearer Copilot Failure Diagnosis** — Fix with Copilot now sends run details directly; repairs preserve drafts, outputs, page values, selectors, and safety details. ([#8343](https://github.com/Skyvern-AI/skyvern/pull/8343), [#8350](https://github.com/Skyvern-AI/skyvern/pull/8350), [#8413](https://github.com/Skyvern-AI/skyvern/pull/8413)) * **More Reliable Browser Recovery** — Browser sessions now recover from slow liveness checks, crashed tabs, and stalled screenshot captures. ([#8401](https://github.com/Skyvern-AI/skyvern/pull/8401), [#8463](https://github.com/Skyvern-AI/skyvern/pull/8463)) ## Bug fixes * Fixed checkout handling for retries, plan changes, and enterprise accounts. * Fixed duplicate downloads, missing download artifacts, and stranded download popups. ([#8344](https://github.com/Skyvern-AI/skyvern/pull/8344), [#8358](https://github.com/Skyvern-AI/skyvern/pull/8358)) * Fixed Sheets appends that shifted neighboring values into another row. ## New features * **Guided Onboarding for New Users** — Eligible new users in enabled organizations get a guided onboarding flow with a working example, progress, and tailored next steps. * **Flexible Credential Setup** — Credential workflows now support passwordless entries, 1Password login items, custom one-time-code fields, saved OTP bindings, and separate rotating browser state. ([#8317](https://github.com/Skyvern-AI/skyvern/pull/8317)) * **Save Credentials from Record Browser** — Record Browser drafts now redact secrets and let users save the matching credential type. ([#8307](https://github.com/Skyvern-AI/skyvern/pull/8307), [#8323](https://github.com/Skyvern-AI/skyvern/pull/8323)) * **Failure-Focused Analytics** — For organizations with analytics enabled, analytics reports now show failures, selected statuses, action totals, and relevant credit metrics. ([#8304](https://github.com/Skyvern-AI/skyvern/pull/8304)) ## Improvements * **Public API and MCP Reliability** — API and MCP clients now get discoverable metadata, rate-limit guidance, retry responses, and clearer validation errors. ([#8283](https://github.com/Skyvern-AI/skyvern/pull/8283)) * **Faster Live Browser Sessions** — Live browser sessions now announce loading status, detect dead connections, and recover from temporary stalls. Vendor CDP live views send mouse moves at native rates. * **Copilot Repair Evidence** — Copilot now keeps browser evidence, records code failures, and waits for progressing runs before reporting repair results. ([#8325](https://github.com/Skyvern-AI/skyvern/pull/8325)) * **Copilot Activity and Responses** — Copilot now shows activity, formatted responses, and terminal results in one readable view. * **Google Connected Accounts** — Google workflow blocks and Copilot now accept a connected account's name or email. * **Workflow Inputs at the Start** — Workflow editors now show declared inputs beside the starting block. ## Bug fixes * Fixed workflow runs failing to commit downloads, custom selections, dates, and typeahead values. ([#8328](https://github.com/Skyvern-AI/skyvern/pull/8328)) * Fixed run views and workflow editors showing blank pages, wrong live states, hidden outputs, false unsaved-change warnings, or unavailable runs. ## New features * **MCP Access and Run History** — Hosted MCP clients can now renew access, complete OAuth callbacks, and include child runs in workflow history. * **Human-Approval Steps in Copilot** — Copilot can now add a human-interaction step and report paused runs as pauses. ## Improvements * **Faster Copilot Block Testing** — Copilot can now edit one block and rerun it from the browser state that produced the recorded page. * **Grounded Copilot Page Evidence** — Copilot now uses page evidence from the run browser, including screenshots, links, overlays, and hidden authentication options, to guide repairs. ([#8239](https://github.com/Skyvern-AI/skyvern/pull/8239)) * **Clearer Copilot Reviews and Failures** — Copilot now shows accurate review state and preserves useful failure details for faster repairs. * **More Reliable Sign-In and OTP Handling** — Sign-in flows now wait for forms, verify fields, submit fresh codes, recover connected accounts, and report delivery problems clearly. * **Reliable Workflow Files** — Workflow files now stay linked to their run, handle download interstitials, and report aborted transfers or unsupported formats clearly. * **More Accurate Form Interactions** — Form interactions now verify live controls, clear retry fields, match values accurately, prevent false submission reports, and avoid wrong selectors. * **Past Runs Filters Persist** — Past Runs search and status filters now stay in the URL, so back navigation and reload restore the same list. ## Bug fixes * Fixed lost browser recordings, dark live views, and raw errors after browser or MCP connections close. * Fixed invalid browser session and workflow inputs returning misleading responses or leaving runs without terminal states. * Fixed billing flows that could start duplicate checkouts or direct exhausted-credit users to unavailable recovery options. ## New features * **Focused MCP Connections** — MCP now offers focused tool sets for local and hosted connections and clear expired-session guidance. * **Structured MCP Output and Page Reading** — The `lean` and `all` MCP tool sets gain an optional final-output validation tool. An opt-in reader tool reads large pages in bounded chunks. * **Custom SMTP Delivery** — Send Email blocks can send messages through a customer’s SMTP server. * **Full-Page Live Control** — Persistent live-browser sessions now keep the full page reachable during takeover. ## Improvements * **Copilot Email Verification** — Copilot now uses saved credentials or connected inboxes for email verification. ([#8200](https://github.com/Skyvern-AI/skyvern/pull/8200)) * **Reliable Download Workflows** — Download flows accept locators, recover files, expose the helper early, and confirm registered files. * **Copilot Workflow Editing** — Copilot preserves browser context, adds blocks incrementally, retains existing edits, and suggests text-based selectors. ([#8205](https://github.com/Skyvern-AI/skyvern/pull/8205), [#8206](https://github.com/Skyvern-AI/skyvern/pull/8206)) * **Copilot Test Run Guidance** — Copilot now limits credential approvals and follows test runs with page and challenge evidence. ([#8210](https://github.com/Skyvern-AI/skyvern/pull/8210), [#8204](https://github.com/Skyvern-AI/skyvern/pull/8204), [#8214](https://github.com/Skyvern-AI/skyvern/pull/8214)) * **Workflow Studio Preview: Clearer Activity** — The opt-in Studio preview retains pane choices, shows terminal browser states, and makes Copilot progress easier to follow. * **Simpler Workflow Integrations** — Google integrations need fewer permissions and use native blocks; workflow setup supports optional credentials, parser choices, and root Drive files. ([#8202](https://github.com/Skyvern-AI/skyvern/pull/8202)) ## Bug fixes * Fixed incorrect toggles, lost outputs, unclear run errors, stale browser actions, credential or dropdown failures, and repeated Copilot requests. ## New features * **Credential Run Controls** — You can serialize runs sharing a credential while fresh profiles omit old login files and saved profiles retain recent sign-ins. ([#7995](https://github.com/Skyvern-AI/skyvern/pull/7995), [#8001](https://github.com/Skyvern-AI/skyvern/pull/8001), [#8097](https://github.com/Skyvern-AI/skyvern/pull/8097)) * **MCP Local Browser Access** — MCP can now control an existing local browser, and its bridge starts serving requests promptly. ([#8070](https://github.com/Skyvern-AI/skyvern/pull/8070), [#8175](https://github.com/Skyvern-AI/skyvern/pull/8175)) * **External Browser Live View** — You can view and navigate externally hosted browser sessions, and use keyboard editing in live view. ([#8101](https://github.com/Skyvern-AI/skyvern/pull/8101), [#8114](https://github.com/Skyvern-AI/skyvern/pull/8114), [#8143](https://github.com/Skyvern-AI/skyvern/pull/8143)) * **Modern Code Blocks** — Code blocks use the editor shape, open shared-session tabs, recover transient startup timeouts, and emit typed errors for downstream routing. ([#8006](https://github.com/Skyvern-AI/skyvern/pull/8006), [#8022](https://github.com/Skyvern-AI/skyvern/pull/8022), [#8033](https://github.com/Skyvern-AI/skyvern/pull/8033), [#8034](https://github.com/Skyvern-AI/skyvern/pull/8034), [#8055](https://github.com/Skyvern-AI/skyvern/pull/8055), [#8163](https://github.com/Skyvern-AI/skyvern/pull/8163)) * **Bulk Agent Export** — Bulk exports now download as one ZIP with a separate file for each agent. ([#8105](https://github.com/Skyvern-AI/skyvern/pull/8105)) ## Improvements * **Deterministic Custom-Select Inputs** — Typed entries now use exact matching when possible, reducing model fallback and incorrect success reports. ([#7996](https://github.com/Skyvern-AI/skyvern/pull/7996)) * **Copilot Credential Assistance** — Copilot now finds credential IDs, lets you choose credentials, shows automatic selections, and starts from a credential's saved login page. ([#8026](https://github.com/Skyvern-AI/skyvern/pull/8026), [#8013](https://github.com/Skyvern-AI/skyvern/pull/8013), [#8065](https://github.com/Skyvern-AI/skyvern/pull/8065), [#8064](https://github.com/Skyvern-AI/skyvern/pull/8064), [#8061](https://github.com/Skyvern-AI/skyvern/pull/8061), [#8094](https://github.com/Skyvern-AI/skyvern/pull/8094), [#8099](https://github.com/Skyvern-AI/skyvern/pull/8099)) * **Reliable Email Verification Retrieval** — Email OTP and sign-in-link lookup now preserves exact values, reads externalized message parts, and respects the expected code type. ([#8028](https://github.com/Skyvern-AI/skyvern/pull/8028), [#8062](https://github.com/Skyvern-AI/skyvern/pull/8062), [#8091](https://github.com/Skyvern-AI/skyvern/pull/8091)) * **Reliable Browser Session Artifacts** — Downloads now complete more reliably, and recordings remain available after browser-session teardown. ([#8007](https://github.com/Skyvern-AI/skyvern/pull/8007), [#8021](https://github.com/Skyvern-AI/skyvern/pull/8021), [#8019](https://github.com/Skyvern-AI/skyvern/pull/8019), [#8115](https://github.com/Skyvern-AI/skyvern/pull/8115), [#8125](https://github.com/Skyvern-AI/skyvern/pull/8125), [#8167](https://github.com/Skyvern-AI/skyvern/pull/8167)) * **Copilot Workflow Editing** — Copilot now preserves workflow code and data, shows plain-language run steps, supports longer repairs, and returns successful results. ([#8058](https://github.com/Skyvern-AI/skyvern/pull/8058), [#8104](https://github.com/Skyvern-AI/skyvern/pull/8104), [#8106](https://github.com/Skyvern-AI/skyvern/pull/8106), [#8142](https://github.com/Skyvern-AI/skyvern/pull/8142), [#8122](https://github.com/Skyvern-AI/skyvern/pull/8122), [#8166](https://github.com/Skyvern-AI/skyvern/pull/8166)) ## Bug fixes * Fixed Copilot turns stopping valid actions, resending queued prompts, or showing empty expansion controls. ([#8025](https://github.com/Skyvern-AI/skyvern/pull/8025), [#8060](https://github.com/Skyvern-AI/skyvern/pull/8060), [#8089](https://github.com/Skyvern-AI/skyvern/pull/8089), [#8137](https://github.com/Skyvern-AI/skyvern/pull/8137)) * Fixed browser sessions failing after stale connections, leaving released occupancy behind, or reporting false navigation, closure, expiry, or final-status errors. ([#7997](https://github.com/Skyvern-AI/skyvern/pull/7997), [#8043](https://github.com/Skyvern-AI/skyvern/pull/8043), [#8164](https://github.com/Skyvern-AI/skyvern/pull/8164)) ## New features * **Expanded OTP Recovery** — OTP handling now preserves raw content, detects code types, reads connected email accounts, and supports magic links in credential view. ([#7849](https://github.com/Skyvern-AI/skyvern/pull/7849), [#7859](https://github.com/Skyvern-AI/skyvern/pull/7859), [#7866](https://github.com/Skyvern-AI/skyvern/pull/7866), [#7886](https://github.com/Skyvern-AI/skyvern/pull/7886), [#7901](https://github.com/Skyvern-AI/skyvern/pull/7901), [#7908](https://github.com/Skyvern-AI/skyvern/pull/7908)) * **Weekly Analytics Email Digest** — Eligible organizations with the digest enabled receive a weekly email summary with recent activity, credit use, and lowest-success workflows. * **Scoped Browser Session Access** — Browser sessions can start at a requested URL. In supported regions, enabled first-party sessions use scoped router addresses for live browser viewing. ([#7915](https://github.com/Skyvern-AI/skyvern/pull/7915)) ## Improvements * **Job Application Form Handling** — Supported job application forms now handle rich fields, rejected values, and live credential pages, with optional visual secret masking. ([#7771](https://github.com/Skyvern-AI/skyvern/pull/7771), [#7773](https://github.com/Skyvern-AI/skyvern/pull/7773), [#7777](https://github.com/Skyvern-AI/skyvern/pull/7777), [#7955](https://github.com/Skyvern-AI/skyvern/pull/7955), [#7966](https://github.com/Skyvern-AI/skyvern/pull/7966), [#7967](https://github.com/Skyvern-AI/skyvern/pull/7967)) * **Shorter Browser Session Lifetime** — Browser sessions now have a maximum lifetime of 4 hours instead of 24. Longer timeouts are clamped, and Enterprise accounts can request longer sessions. Recordings, downloads, and live-stream paste are more reliable. ([#7772](https://github.com/Skyvern-AI/skyvern/pull/7772), [#7774](https://github.com/Skyvern-AI/skyvern/pull/7774), [#7804](https://github.com/Skyvern-AI/skyvern/pull/7804), [#7838](https://github.com/Skyvern-AI/skyvern/pull/7838), [#7883](https://github.com/Skyvern-AI/skyvern/pull/7883), [#7902](https://github.com/Skyvern-AI/skyvern/pull/7902), [#7916](https://github.com/Skyvern-AI/skyvern/pull/7916), [#7929](https://github.com/Skyvern-AI/skyvern/pull/7929), [#7930](https://github.com/Skyvern-AI/skyvern/pull/7930), [#7944](https://github.com/Skyvern-AI/skyvern/pull/7944), [#7979](https://github.com/Skyvern-AI/skyvern/pull/7979)) * **Copilot Authoring Reliability** — Copilot verifies outputs, preserves drafts, uses connected accounts, acts on pages, reports activity and failures, and keeps repairing through stalls. ([#7779](https://github.com/Skyvern-AI/skyvern/pull/7779), [#7791](https://github.com/Skyvern-AI/skyvern/pull/7791), [#7792](https://github.com/Skyvern-AI/skyvern/pull/7792), [#7794](https://github.com/Skyvern-AI/skyvern/pull/7794), [#7796](https://github.com/Skyvern-AI/skyvern/pull/7796), [#7802](https://github.com/Skyvern-AI/skyvern/pull/7802), [#7806](https://github.com/Skyvern-AI/skyvern/pull/7806), [#7845](https://github.com/Skyvern-AI/skyvern/pull/7845), [#7869](https://github.com/Skyvern-AI/skyvern/pull/7869), [#7871](https://github.com/Skyvern-AI/skyvern/pull/7871), [#7873](https://github.com/Skyvern-AI/skyvern/pull/7873), [#7878](https://github.com/Skyvern-AI/skyvern/pull/7878), [#7885](https://github.com/Skyvern-AI/skyvern/pull/7885), [#7911](https://github.com/Skyvern-AI/skyvern/pull/7911), [#7913](https://github.com/Skyvern-AI/skyvern/pull/7913), [#7914](https://github.com/Skyvern-AI/skyvern/pull/7914), [#7934](https://github.com/Skyvern-AI/skyvern/pull/7934), [#7972](https://github.com/Skyvern-AI/skyvern/pull/7972)) * **Safer MCP and Browser Requests** — MCP tools now handle arguments and page waits more reliably while browser and webhook requests validate destinations and headers. ([#7765](https://github.com/Skyvern-AI/skyvern/pull/7765), [#7782](https://github.com/Skyvern-AI/skyvern/pull/7782), [#7932](https://github.com/Skyvern-AI/skyvern/pull/7932), [#7941](https://github.com/Skyvern-AI/skyvern/pull/7941), [#7962](https://github.com/Skyvern-AI/skyvern/pull/7962), [#7976](https://github.com/Skyvern-AI/skyvern/pull/7976), [#7982](https://github.com/Skyvern-AI/skyvern/pull/7982)) * **Clearer Billing Usage** — The billing page now shows OTP usage. * **Google Sheets Workflow Fields** — Spreadsheet and sheet pickers now show compact destinations and support template expressions for dynamic targets. ([#7840](https://github.com/Skyvern-AI/skyvern/pull/7840), [#7875](https://github.com/Skyvern-AI/skyvern/pull/7875)) * **Larger File Workflows** — File workflows accept larger storage uploads, return ZIP file lists, and process up to 1,000 loop iterations. ([#7793](https://github.com/Skyvern-AI/skyvern/pull/7793), [#7899](https://github.com/Skyvern-AI/skyvern/pull/7899), [#7907](https://github.com/Skyvern-AI/skyvern/pull/7907)) ## Bug fixes * Fixed CAPTCHA actions showing false completion, missing checkbox frames, or losing settings during cached replay. ([#7787](https://github.com/Skyvern-AI/skyvern/pull/7787)) * Fixed workflow runs reusing stale outputs or losing status, webhook delivery, browser pages, timeline data, code-block execution, or run-pane access. ([#7775](https://github.com/Skyvern-AI/skyvern/pull/7775), [#7809](https://github.com/Skyvern-AI/skyvern/pull/7809), [#7827](https://github.com/Skyvern-AI/skyvern/pull/7827), [#7841](https://github.com/Skyvern-AI/skyvern/pull/7841), [#7842](https://github.com/Skyvern-AI/skyvern/pull/7842), [#7864](https://github.com/Skyvern-AI/skyvern/pull/7864), [#7890](https://github.com/Skyvern-AI/skyvern/pull/7890), [#7903](https://github.com/Skyvern-AI/skyvern/pull/7903), [#7953](https://github.com/Skyvern-AI/skyvern/pull/7953), [#7960](https://github.com/Skyvern-AI/skyvern/pull/7960), [#7978](https://github.com/Skyvern-AI/skyvern/pull/7978)) ## New features * **Password-Free Login and CAPTCHA Handling** — Copilot can use email sign-in codes or links and solve CAPTCHA challenges during login exploration. ([#7727](https://github.com/Skyvern-AI/skyvern/pull/7727), [#7755](https://github.com/Skyvern-AI/skyvern/pull/7755), [#7756](https://github.com/Skyvern-AI/skyvern/pull/7756), [#7761](https://github.com/Skyvern-AI/skyvern/pull/7761)) * **Live Action Progress During Test Runs** — Code-block test runs stream recorded browser actions while they run. The Copilot preview shows these actions live for enabled organizations. ([#7608](https://github.com/Skyvern-AI/skyvern/pull/7608), [#7609](https://github.com/Skyvern-AI/skyvern/pull/7609), [#7610](https://github.com/Skyvern-AI/skyvern/pull/7610)) * **MCP Setup and Session Visibility** — MCP now offers in-app setup, live timelines, clear argument errors, code-only guidance, and profile cleanup. ([#7587](https://github.com/Skyvern-AI/skyvern/pull/7587), [#7574](https://github.com/Skyvern-AI/skyvern/pull/7574), [#7619](https://github.com/Skyvern-AI/skyvern/pull/7619), [#7693](https://github.com/Skyvern-AI/skyvern/pull/7693), [#7577](https://github.com/Skyvern-AI/skyvern/pull/7577), [#7580](https://github.com/Skyvern-AI/skyvern/pull/7580)) * **Workflow Studio Preview: Run Navigation** — The opt-in Studio preview makes past runs easier to find with linked titles, shorter URLs, clear details, and branch navigation. ([#7602](https://github.com/Skyvern-AI/skyvern/pull/7602), [#7604](https://github.com/Skyvern-AI/skyvern/pull/7604), [#7607](https://github.com/Skyvern-AI/skyvern/pull/7607), [#7642](https://github.com/Skyvern-AI/skyvern/pull/7642), [#7643](https://github.com/Skyvern-AI/skyvern/pull/7643), [#7644](https://github.com/Skyvern-AI/skyvern/pull/7644), [#7646](https://github.com/Skyvern-AI/skyvern/pull/7646), [#7667](https://github.com/Skyvern-AI/skyvern/pull/7667), [#7758](https://github.com/Skyvern-AI/skyvern/pull/7758)) * **Agent Filter for Run History** — Run History now filters runs by agent while keeping server-side search and pagination. ([#7618](https://github.com/Skyvern-AI/skyvern/pull/7618)) * **Claude Opus 5 Model** — Claude Opus 5 is now available as a selectable model for agent runs for Enterprise accounts on Skyvern Cloud. ([#7741](https://github.com/Skyvern-AI/skyvern/pull/7741)) * **Paused Status in the Public API** — The public run status now includes paused runs, so status reads and webhooks work during verification waits. ([#7576](https://github.com/Skyvern-AI/skyvern/pull/7576)) ## Improvements * **More Reliable Copilot Workflow Authoring** — Copilot now completes more requests, repairs missing workflow steps, handles credentials safely, and reports outcomes honestly. ([#7563](https://github.com/Skyvern-AI/skyvern/pull/7563), [#7565](https://github.com/Skyvern-AI/skyvern/pull/7565), [#7567](https://github.com/Skyvern-AI/skyvern/pull/7567), [#7613](https://github.com/Skyvern-AI/skyvern/pull/7613), [#7628](https://github.com/Skyvern-AI/skyvern/pull/7628), [#7629](https://github.com/Skyvern-AI/skyvern/pull/7629), [#7630](https://github.com/Skyvern-AI/skyvern/pull/7630), [#7632](https://github.com/Skyvern-AI/skyvern/pull/7632), [#7648](https://github.com/Skyvern-AI/skyvern/pull/7648), [#7649](https://github.com/Skyvern-AI/skyvern/pull/7649), [#7656](https://github.com/Skyvern-AI/skyvern/pull/7656), [#7658](https://github.com/Skyvern-AI/skyvern/pull/7658), [#7673](https://github.com/Skyvern-AI/skyvern/pull/7673), [#7686](https://github.com/Skyvern-AI/skyvern/pull/7686), [#7688](https://github.com/Skyvern-AI/skyvern/pull/7688), [#7689](https://github.com/Skyvern-AI/skyvern/pull/7689), [#7695](https://github.com/Skyvern-AI/skyvern/pull/7695), [#7699](https://github.com/Skyvern-AI/skyvern/pull/7699), [#7701](https://github.com/Skyvern-AI/skyvern/pull/7701), [#7703](https://github.com/Skyvern-AI/skyvern/pull/7703), [#7711](https://github.com/Skyvern-AI/skyvern/pull/7711), [#7713](https://github.com/Skyvern-AI/skyvern/pull/7713), [#7714](https://github.com/Skyvern-AI/skyvern/pull/7714), [#7715](https://github.com/Skyvern-AI/skyvern/pull/7715), [#7716](https://github.com/Skyvern-AI/skyvern/pull/7716), [#7719](https://github.com/Skyvern-AI/skyvern/pull/7719), [#7734](https://github.com/Skyvern-AI/skyvern/pull/7734)) * **Job Application Form Reliability** — Supported job application forms now handle more field widgets, recover rewritten inputs, and confirm successful submissions. ([#7570](https://github.com/Skyvern-AI/skyvern/pull/7570), [#7585](https://github.com/Skyvern-AI/skyvern/pull/7585)) * **More Reliable Remote Browser Startup** — Remote browser startup now retries transient connections, reports rate limits clearly, uses fallback browsers, and supports custom proxies. * **CodeBlock Authoring and Output Improvements** — CodeBlock workflows now show outputs and safe errors, support page evaluation, wire inputs, carry MCP metadata, and make JSON searchable. ([#7578](https://github.com/Skyvern-AI/skyvern/pull/7578), [#7586](https://github.com/Skyvern-AI/skyvern/pull/7586), [#7670](https://github.com/Skyvern-AI/skyvern/pull/7670), [#7697](https://github.com/Skyvern-AI/skyvern/pull/7697), [#7730](https://github.com/Skyvern-AI/skyvern/pull/7730), [#7733](https://github.com/Skyvern-AI/skyvern/pull/7733), [#7754](https://github.com/Skyvern-AI/skyvern/pull/7754)) ## Bug fixes * Fixed template URLs, selection failures, missing downloads, invalid limits, missing invoice feedback, analytics charts for enabled organizations, and interactions in the Studio preview. ([#7569](https://github.com/Skyvern-AI/skyvern/pull/7569), [#7575](https://github.com/Skyvern-AI/skyvern/pull/7575), [#7598](https://github.com/Skyvern-AI/skyvern/pull/7598), [#7599](https://github.com/Skyvern-AI/skyvern/pull/7599), [#7601](https://github.com/Skyvern-AI/skyvern/pull/7601), [#7638](https://github.com/Skyvern-AI/skyvern/pull/7638), [#7650](https://github.com/Skyvern-AI/skyvern/pull/7650), [#7651](https://github.com/Skyvern-AI/skyvern/pull/7651), [#7690](https://github.com/Skyvern-AI/skyvern/pull/7690), [#7696](https://github.com/Skyvern-AI/skyvern/pull/7696)) ## New features * **External File Storage Targets** — Download blocks can now send files to external storage, and large Google Drive uploads resume after interruptions. ([#7444](https://github.com/Skyvern-AI/skyvern/pull/7444), [#7373](https://github.com/Skyvern-AI/skyvern/pull/7373), [#7391](https://github.com/Skyvern-AI/skyvern/pull/7391)) * **Record and Synthesize Browser Sessions** — MCP sessions can now record safe browser actions and turn them directly into replayable code blocks. ([#7498](https://github.com/Skyvern-AI/skyvern/pull/7498), [#7522](https://github.com/Skyvern-AI/skyvern/pull/7522)) * **Credential Help in Copilot** — The Copilot preview shows a credential card with Connect and Skip actions for enabled organizations. The card appears when a build needs access. ([#7418](https://github.com/Skyvern-AI/skyvern/pull/7418)) * **Browser Profile Refresh and Usage Checks** — Browser Profiles now show dependencies, support refresh, and warn before deleting a profile in use. ([#7548](https://github.com/Skyvern-AI/skyvern/pull/7548), [#7550](https://github.com/Skyvern-AI/skyvern/pull/7550)) ## Improvements * **Grounded Copilot Workflows** — Copilot now preserves captured steps and completion checks, recognizes values by format, reuses inputs, and reports verified downloads. ([#7374](https://github.com/Skyvern-AI/skyvern/pull/7374), [#7349](https://github.com/Skyvern-AI/skyvern/pull/7349), [#7381](https://github.com/Skyvern-AI/skyvern/pull/7381), [#7375](https://github.com/Skyvern-AI/skyvern/pull/7375), [#7397](https://github.com/Skyvern-AI/skyvern/pull/7397), [#7439](https://github.com/Skyvern-AI/skyvern/pull/7439), [#7438](https://github.com/Skyvern-AI/skyvern/pull/7438), [#7441](https://github.com/Skyvern-AI/skyvern/pull/7441), [#7455](https://github.com/Skyvern-AI/skyvern/pull/7455)) * **Safer Copilot Authoring** — Copilot now checks goal reach, code validity, and completion conditions before saving, then gives clear retry guidance. ([#7419](https://github.com/Skyvern-AI/skyvern/pull/7419), [#7429](https://github.com/Skyvern-AI/skyvern/pull/7429), [#7466](https://github.com/Skyvern-AI/skyvern/pull/7466), [#7507](https://github.com/Skyvern-AI/skyvern/pull/7507), [#7556](https://github.com/Skyvern-AI/skyvern/pull/7556), [#7442](https://github.com/Skyvern-AI/skyvern/pull/7442), [#7512](https://github.com/Skyvern-AI/skyvern/pull/7512), [#7336](https://github.com/Skyvern-AI/skyvern/pull/7336), [#7527](https://github.com/Skyvern-AI/skyvern/pull/7527), [#7549](https://github.com/Skyvern-AI/skyvern/pull/7549), [#7557](https://github.com/Skyvern-AI/skyvern/pull/7557)) * **More Reliable Browser Actions** — Browser runs now verify form controls and wait for protected pages. ([#7334](https://github.com/Skyvern-AI/skyvern/pull/7334), [#7406](https://github.com/Skyvern-AI/skyvern/pull/7406), [#7454](https://github.com/Skyvern-AI/skyvern/pull/7454), [#7480](https://github.com/Skyvern-AI/skyvern/pull/7480), [#7483](https://github.com/Skyvern-AI/skyvern/pull/7483), [#7474](https://github.com/Skyvern-AI/skyvern/pull/7474)) * **Reliable Artifacts and Downloads** — Artifact views refresh expired links, while downloads reject login pages and missing profiles start faster. ([#7459](https://github.com/Skyvern-AI/skyvern/pull/7459), [#7484](https://github.com/Skyvern-AI/skyvern/pull/7484), [#7411](https://github.com/Skyvern-AI/skyvern/pull/7411), [#7350](https://github.com/Skyvern-AI/skyvern/pull/7350)) * **MCP Workflow and Browser Tools** — MCP now gives clearer guidance, valid snippets, file-based edits for large workflows, and selected iframe content. ([#7333](https://github.com/Skyvern-AI/skyvern/pull/7333), [#7460](https://github.com/Skyvern-AI/skyvern/pull/7460), [#7422](https://github.com/Skyvern-AI/skyvern/pull/7422), [#7433](https://github.com/Skyvern-AI/skyvern/pull/7433)) * **Analytics and Run Health** — For organizations with analytics enabled, analytics now shows accurate credit usage and run outcomes. Runs retry transient failures, and run lists surface self-healing risk. ([#7493](https://github.com/Skyvern-AI/skyvern/pull/7493), [#7494](https://github.com/Skyvern-AI/skyvern/pull/7494), [#7523](https://github.com/Skyvern-AI/skyvern/pull/7523), [#7526](https://github.com/Skyvern-AI/skyvern/pull/7526), [#7541](https://github.com/Skyvern-AI/skyvern/pull/7541)) * **Workflow Studio Preview: Usability** — The opt-in Studio preview now follows themes, shows changes, links run review to blocks, and restores run inputs and outputs. ([#7408](https://github.com/Skyvern-AI/skyvern/pull/7408), [#7417](https://github.com/Skyvern-AI/skyvern/pull/7417), [#7513](https://github.com/Skyvern-AI/skyvern/pull/7513), [#7409](https://github.com/Skyvern-AI/skyvern/pull/7409), [#7495](https://github.com/Skyvern-AI/skyvern/pull/7495), [#7388](https://github.com/Skyvern-AI/skyvern/pull/7388), [#7423](https://github.com/Skyvern-AI/skyvern/pull/7423), [#7426](https://github.com/Skyvern-AI/skyvern/pull/7426), [#7543](https://github.com/Skyvern-AI/skyvern/pull/7543)) ## Bug fixes * Fixed TOTP issuer errors and retryable OTP failures; tier upgrades now start fresh billing periods. ([#7365](https://github.com/Skyvern-AI/skyvern/pull/7365), [#7509](https://github.com/Skyvern-AI/skyvern/pull/7509)) ## New features * **Workflow Studio Preview: Navigation and Layout** — The opt-in Studio preview now searches blocks, expands hidden containers, jumps through long workflows, and remembers panel layouts. ([#7103](https://github.com/Skyvern-AI/skyvern/pull/7103), [#7104](https://github.com/Skyvern-AI/skyvern/pull/7104), [#7107](https://github.com/Skyvern-AI/skyvern/pull/7107), [#7112](https://github.com/Skyvern-AI/skyvern/pull/7112), [#7118](https://github.com/Skyvern-AI/skyvern/pull/7118), [#7201](https://github.com/Skyvern-AI/skyvern/pull/7201), [#7270](https://github.com/Skyvern-AI/skyvern/pull/7270)) * **Workflow File Tools** — Workflow file tools can now split PDFs, select upload files, deliver files to SFTP, and use sandbox scratch files. ([#7258](https://github.com/Skyvern-AI/skyvern/pull/7258), [#7268](https://github.com/Skyvern-AI/skyvern/pull/7268), [#7301](https://github.com/Skyvern-AI/skyvern/pull/7301)) * **Organization OAuth Setup** — Organization-level OAuth setup is available for enabled organizations, and connections that need reconnection are clearly marked after settings changes. ([#7283](https://github.com/Skyvern-AI/skyvern/pull/7283), [#7288](https://github.com/Skyvern-AI/skyvern/pull/7288)) * **Email Inbox Workflows** — Email Inbox workflows can read matching Gmail or Outlook messages for downstream processing. ([#7303](https://github.com/Skyvern-AI/skyvern/pull/7303), [#7309](https://github.com/Skyvern-AI/skyvern/pull/7309)) * **Run History and Result Links** — Run history now filters by run type, while the Studio preview and MCP expose available outputs and recording links. ([#7251](https://github.com/Skyvern-AI/skyvern/pull/7251), [#7269](https://github.com/Skyvern-AI/skyvern/pull/7269), [#7307](https://github.com/Skyvern-AI/skyvern/pull/7307)) ## Improvements * **Copilot Build Progress and Recovery** — Copilot and agent runs now show live progress and recover from build, login, and model-response failures. ([#7097](https://github.com/Skyvern-AI/skyvern/pull/7097), [#7098](https://github.com/Skyvern-AI/skyvern/pull/7098), [#7099](https://github.com/Skyvern-AI/skyvern/pull/7099), [#7100](https://github.com/Skyvern-AI/skyvern/pull/7100), [#7120](https://github.com/Skyvern-AI/skyvern/pull/7120), [#7149](https://github.com/Skyvern-AI/skyvern/pull/7149), [#7155](https://github.com/Skyvern-AI/skyvern/pull/7155), [#7162](https://github.com/Skyvern-AI/skyvern/pull/7162), [#7216](https://github.com/Skyvern-AI/skyvern/pull/7216), [#7246](https://github.com/Skyvern-AI/skyvern/pull/7246), [#7275](https://github.com/Skyvern-AI/skyvern/pull/7275), [#7277](https://github.com/Skyvern-AI/skyvern/pull/7277), [#7308](https://github.com/Skyvern-AI/skyvern/pull/7308), [#7313](https://github.com/Skyvern-AI/skyvern/pull/7313), [#7314](https://github.com/Skyvern-AI/skyvern/pull/7314), [#7315](https://github.com/Skyvern-AI/skyvern/pull/7315), [#7327](https://github.com/Skyvern-AI/skyvern/pull/7327)) * **Analytics Console Clarity** — For organizations with analytics enabled, Analytics now uses shared filters, clearer charts, accurate workflow breakdowns, and stable custom date ranges. ([#7136](https://github.com/Skyvern-AI/skyvern/pull/7136), [#7209](https://github.com/Skyvern-AI/skyvern/pull/7209)) * **MCP Browser Reliability** — MCP now connects reliably, guides keys to setup, accepts query aliases, protects inputs, retains references, and supports direct dropdown actions. ([#7165](https://github.com/Skyvern-AI/skyvern/pull/7165), [#7166](https://github.com/Skyvern-AI/skyvern/pull/7166), [#7203](https://github.com/Skyvern-AI/skyvern/pull/7203), [#7206](https://github.com/Skyvern-AI/skyvern/pull/7206), [#7220](https://github.com/Skyvern-AI/skyvern/pull/7220), [#7250](https://github.com/Skyvern-AI/skyvern/pull/7250), [#7285](https://github.com/Skyvern-AI/skyvern/pull/7285)) * **Browser Automation Reliability** — Browser automation now handles captchas, captures client-created files, preserves download names, and avoids extra recordings. ([#7102](https://github.com/Skyvern-AI/skyvern/pull/7102), [#7111](https://github.com/Skyvern-AI/skyvern/pull/7111), [#7123](https://github.com/Skyvern-AI/skyvern/pull/7123), [#7153](https://github.com/Skyvern-AI/skyvern/pull/7153), [#7156](https://github.com/Skyvern-AI/skyvern/pull/7156), [#7172](https://github.com/Skyvern-AI/skyvern/pull/7172), [#7192](https://github.com/Skyvern-AI/skyvern/pull/7192)) ## Bug fixes * Fixed credential setup so editable accounts, saved instructions, reused profile names, test cleanup, and token errors work correctly. ([#7122](https://github.com/Skyvern-AI/skyvern/pull/7122), [#7157](https://github.com/Skyvern-AI/skyvern/pull/7157), [#7160](https://github.com/Skyvern-AI/skyvern/pull/7160), [#7184](https://github.com/Skyvern-AI/skyvern/pull/7184), [#7219](https://github.com/Skyvern-AI/skyvern/pull/7219)) * Fixed template run details failing to load, loading slowly, or omitting the Stop control in the Studio preview. ([#7105](https://github.com/Skyvern-AI/skyvern/pull/7105), [#7265](https://github.com/Skyvern-AI/skyvern/pull/7265), [#7330](https://github.com/Skyvern-AI/skyvern/pull/7330)) * Fixed run inputs hiding download instructions, corrupting formatted card numbers, and mishandling workflow files or malformed definitions. ([#7202](https://github.com/Skyvern-AI/skyvern/pull/7202), [#7260](https://github.com/Skyvern-AI/skyvern/pull/7260), [#7264](https://github.com/Skyvern-AI/skyvern/pull/7264), [#7305](https://github.com/Skyvern-AI/skyvern/pull/7305), [#7306](https://github.com/Skyvern-AI/skyvern/pull/7306)) ## New features * **Workflow Studio Preview: Side-by-Side Panes** — The opt-in Workflow Studio preview now offers side-by-side panes, responsive layouts, and clearer run views. ([#7007](https://github.com/Skyvern-AI/skyvern/pull/7007), [#7008](https://github.com/Skyvern-AI/skyvern/pull/7008), [#7009](https://github.com/Skyvern-AI/skyvern/pull/7009), [#7010](https://github.com/Skyvern-AI/skyvern/pull/7010), [#7013](https://github.com/Skyvern-AI/skyvern/pull/7013), [#7021](https://github.com/Skyvern-AI/skyvern/pull/7021), [#7022](https://github.com/Skyvern-AI/skyvern/pull/7022), [#7024](https://github.com/Skyvern-AI/skyvern/pull/7024), [#7025](https://github.com/Skyvern-AI/skyvern/pull/7025), [#7043](https://github.com/Skyvern-AI/skyvern/pull/7043), [#7044](https://github.com/Skyvern-AI/skyvern/pull/7044), [#7045](https://github.com/Skyvern-AI/skyvern/pull/7045), [#7046](https://github.com/Skyvern-AI/skyvern/pull/7046), [#7047](https://github.com/Skyvern-AI/skyvern/pull/7047), [#7056](https://github.com/Skyvern-AI/skyvern/pull/7056)) * **Code-First Workflow Authoring** — Teams can edit workflows as YAML or use MCP tools to lint, synthesize, validate, and save code-only workflows. ([#6997](https://github.com/Skyvern-AI/skyvern/pull/6997), [#6998](https://github.com/Skyvern-AI/skyvern/pull/6998), [#7017](https://github.com/Skyvern-AI/skyvern/pull/7017), [#7030](https://github.com/Skyvern-AI/skyvern/pull/7030), [#7065](https://github.com/Skyvern-AI/skyvern/pull/7065)) * **ZIP Files in File Parser** — File Parser blocks now process ZIP archives, so workflows can extract data from bundled documents. ([#7049](https://github.com/Skyvern-AI/skyvern/pull/7049)) * **Credential and Session Reuse** — Workflows can rotate login credentials across runs and save browser state in managed profiles. ([#7032](https://github.com/Skyvern-AI/skyvern/pull/7032), [#7053](https://github.com/Skyvern-AI/skyvern/pull/7053)) * **Secret Values Across Blocks** — Workflows can pass selected HTTP response values as secrets between downstream blocks. Enabled self-hosted deployments can store credentials locally. ([#7054](https://github.com/Skyvern-AI/skyvern/pull/7054)) ## Improvements * **Block Type Shown in Workflow Studio Header** — The block detail panel in Workflow Studio now displays the block type in the header, making it easier to identify what kind of block you're editing at a glance. ([#6956](https://github.com/Skyvern-AI/skyvern/pull/6956)) * **Improved Extraction Accuracy for Absent Data** — The agent now better handles cases where requested output is genuinely absent from the page, reducing false positives in extraction results. ([#6957](https://github.com/Skyvern-AI/skyvern/pull/6957)) * **Data-Only Validation Skips Page Evidence** — Validation steps that check only extracted data no longer capture page screenshots when they aren't needed, reducing unnecessary work during runs. ([#6960](https://github.com/Skyvern-AI/skyvern/pull/6960)) * **Copilot Block Runs Routed to UI Worker** — Copilot block runs are now dispatched to a dedicated UI worker, keeping the editor responsive during live automation. ([#6962](https://github.com/Skyvern-AI/skyvern/pull/6962)) * **Clearer Invalid JSON Errors in Workflow Editor** — The workflow editor now surfaces a descriptive error when a parameter contains invalid JSON, making it faster to diagnose and fix configuration mistakes. ([#6963](https://github.com/Skyvern-AI/skyvern/pull/6963)) * **"Ignore System Prompt" Moved to Advanced Settings** — The "Ignore system prompt" option has been relocated to the advanced settings panel, reducing clutter in the default block configuration view. ([#6964](https://github.com/Skyvern-AI/skyvern/pull/6964)) * **Empty Extra HTTP Headers Hidden** — Extra HTTP header fields that are empty no longer appear in block configurations, reducing visual noise in the workflow editor. ([#6966](https://github.com/Skyvern-AI/skyvern/pull/6966)) * **Block Selection Persisted in URL** — The selected block in Workflow Studio is now encoded in the URL, so your selection is preserved on reload and can be shared via link. ([#6969](https://github.com/Skyvern-AI/skyvern/pull/6969)) * **Code-Block Self-Heal Minimum Retry Floor** — The code-block self-healing loop now enforces a minimum number of repair attempts before giving up, preventing premature failures on recoverable errors. ([#6971](https://github.com/Skyvern-AI/skyvern/pull/6971)) * **Faster Live-Draft Enrichment** — Workflow recording live-draft enrichment now uses a faster model and a shorter debounce interval, making draft suggestions appear noticeably sooner while recording. ([#6973](https://github.com/Skyvern-AI/skyvern/pull/6973)) * **Responsive Browser Recording** — Browser recording now shows editable live drafts and stays responsive across long sessions, repeat recordings, and browser transport changes. ([#6995](https://github.com/Skyvern-AI/skyvern/pull/6995), [#6999](https://github.com/Skyvern-AI/skyvern/pull/6999), [#7002](https://github.com/Skyvern-AI/skyvern/pull/7002), [#7004](https://github.com/Skyvern-AI/skyvern/pull/7004), [#7005](https://github.com/Skyvern-AI/skyvern/pull/7005), [#7036](https://github.com/Skyvern-AI/skyvern/pull/7036), [#7048](https://github.com/Skyvern-AI/skyvern/pull/7048)) ## Bug fixes * Fixed syntax highlighting disappearing when viewing large webhook payloads. ([#6967](https://github.com/Skyvern-AI/skyvern/pull/6967)) * Fixed LLM blocks not enforcing their configured output schema, which could allow malformed data to propagate to downstream blocks. ([#6965](https://github.com/Skyvern-AI/skyvern/pull/6965)) * Fixed Copilot repairs and builds that failed or stopped early when output evidence, action history, or prior outputs were incomplete. ([#6993](https://github.com/Skyvern-AI/skyvern/pull/6993), [#6994](https://github.com/Skyvern-AI/skyvern/pull/6994), [#6996](https://github.com/Skyvern-AI/skyvern/pull/6996), [#7000](https://github.com/Skyvern-AI/skyvern/pull/7000), [#7014](https://github.com/Skyvern-AI/skyvern/pull/7014), [#7015](https://github.com/Skyvern-AI/skyvern/pull/7015), [#7031](https://github.com/Skyvern-AI/skyvern/pull/7031), [#7040](https://github.com/Skyvern-AI/skyvern/pull/7040), [#7055](https://github.com/Skyvern-AI/skyvern/pull/7055), [#7069](https://github.com/Skyvern-AI/skyvern/pull/7069), [#7081](https://github.com/Skyvern-AI/skyvern/pull/7081), [#7086](https://github.com/Skyvern-AI/skyvern/pull/7086), [#7087](https://github.com/Skyvern-AI/skyvern/pull/7087), [#7088](https://github.com/Skyvern-AI/skyvern/pull/7088), [#7090](https://github.com/Skyvern-AI/skyvern/pull/7090), [#7091](https://github.com/Skyvern-AI/skyvern/pull/7091)) * Fixed failures in workflow navigation, remote browser cleanup, and task listings. ([#7001](https://github.com/Skyvern-AI/skyvern/pull/7001), [#7006](https://github.com/Skyvern-AI/skyvern/pull/7006), [#7042](https://github.com/Skyvern-AI/skyvern/pull/7042), [#7084](https://github.com/Skyvern-AI/skyvern/pull/7084), [#7085](https://github.com/Skyvern-AI/skyvern/pull/7085)) ## New features * **Gmail-Backed OTP Lookup** — Agents can now retrieve one-time passwords from Gmail via OAuth, enabling automated login flows that depend on email-delivered verification codes. ([#6769](https://github.com/Skyvern-AI/skyvern/pull/6769)) * **Copilot Chat History per Workflow** — The Copilot now retains its full conversation history scoped to each individual workflow, so prior context and decisions are preserved as you continue building. ([#6767](https://github.com/Skyvern-AI/skyvern/pull/6767)) * **Code-First Editor Polish** — Code-first code blocks now display block labels, correctly render extraction output, and include a Build-vs-Code toggle for switching between visual and code editing modes. ([#6771](https://github.com/Skyvern-AI/skyvern/pull/6771)) * **Workflow Studio (Preview)** — A redesigned workflow editor with a refreshed build canvas, integrated browser view, and run viewer is now available as an opt-in preview, giving teams an early look at the next-generation authoring experience. ([#6782](https://github.com/Skyvern-AI/skyvern/pull/6782)) * **DeepSeek and Xiaomi MiMo Models** — DeepSeek and Xiaomi MiMo are now available in the model dropdown for agent runs. Gemini 2.5 Pro and 2.5 Flash have been deprecated. ([#6831](https://github.com/Skyvern-AI/skyvern/pull/6831)) * **Label Management Settings** — Labels can now be renamed, recolored, and soft-deleted directly from the Settings page, making it easier to maintain a clean tag taxonomy. ([#6830](https://github.com/Skyvern-AI/skyvern/pull/6830)) * **Browser Profiles in MCP Sessions** — Browser sessions initiated via MCP can now be associated with a browser profile, enabling credential and state reuse across MCP-driven runs. ([#6798](https://github.com/Skyvern-AI/skyvern/pull/6798)) * **Workflow-Tag Filter on Analytics** — The analytics dashboard now supports filtering runs and metrics by workflow tag. ([#6780](https://github.com/Skyvern-AI/skyvern/pull/6780)) ## Improvements * **Copilot Repair Shows Quiet Progress** — The Copilot's code-seam repair steps now appear as compact progress indicators instead of repeated chat messages, keeping the conversation readable during long repairs. ([#6746](https://github.com/Skyvern-AI/skyvern/pull/6746)) * **Collapsible Sidebar with Avatar** — The left sidebar now features an edge toggle, a closed-state user avatar, and a smooth open/close animation for a more polished navigation experience. ([#6754](https://github.com/Skyvern-AI/skyvern/pull/6754)) * **Structured Output Verified Before Completion** — Runs that produce structured data now verify the output satisfies the configured schema before marking the run as successfully complete. ([#6751](https://github.com/Skyvern-AI/skyvern/pull/6751)) * **MCP Workflow Overlap Settings Preserved** — Overlap settings configured via MCP are now retained correctly when the workflow is subsequently edited, preventing unintentional resets. ([#6748](https://github.com/Skyvern-AI/skyvern/pull/6748)) * **Browser Profile List Sorted Newest First** — The browser profile picker now orders profiles with the most recently created at the top, making recent profiles easier to find and select. ([#6739](https://github.com/Skyvern-AI/skyvern/pull/6739)) * **Remote Browser Sessions Capped at Four Hours** — Remote browser sessions now have a maximum duration of four hours, preventing orphaned sessions from consuming resources indefinitely. * **Debug Sessions Stay Open After Runs** — Browser sessions launched from the workflow editor in debug mode now remain alive after a run completes, so you can inspect the final page state without the session closing immediately. ([#6832](https://github.com/Skyvern-AI/skyvern/pull/6832)) * **GPT-5 Mini via OpenRouter** — GPT-5 Mini is now available as a selectable model via OpenRouter. ([#6816](https://github.com/Skyvern-AI/skyvern/pull/6816)) * **Extraction and AI Steps in Code-Block View** — Extraction and AI steps are now surfaced in the code-block run view, filling a gap in execution visibility. ([#6823](https://github.com/Skyvern-AI/skyvern/pull/6823)) * **Color Palette for Grouped Workflow Tags** — Tags that belong to a group are now displayed with a curated color palette, making it easier to distinguish tag groups at a glance. ([#6801](https://github.com/Skyvern-AI/skyvern/pull/6801)) * **Improved Authenticator 2FA Credential Setup** — The credential setup flow for authenticator-based 2FA has been improved with clearer guidance and a smoother configuration experience. ([#6783](https://github.com/Skyvern-AI/skyvern/pull/6783)) * **Copilot Data-Write Blocks Default to Safe Failure Mode** — New Copilot-generated data-write blocks now default to `continue_on_failure=false`, preventing downstream blocks from running on bad data. ([#6779](https://github.com/Skyvern-AI/skyvern/pull/6779)) * **End-State Screenshots for All Open Tabs** — Task runs now capture end-state screenshots for every open tab at completion, giving a full snapshot of the browser state. ([#6777](https://github.com/Skyvern-AI/skyvern/pull/6777)) * **Partial Deliverable on Budget Exhaustion** — Tasks that hit their credit budget now return the best-effort deliverable collected so far instead of failing without output. ([#6778](https://github.com/Skyvern-AI/skyvern/pull/6778)) * **Planner Supports EXTRACT\_INFORMATION and GOTO\_URL** — The task planner can now emit EXTRACT\_INFORMATION and GOTO\_URL actions, expanding the set of strategies available during automated planning. ([#6800](https://github.com/Skyvern-AI/skyvern/pull/6800)) * **Copilot Completion Recognition Improvements** — The Copilot completion recognizer is now more authoritative and evidence-backed, with stable criteria counts and more reliable recognition across runs. ([#6789](https://github.com/Skyvern-AI/skyvern/pull/6789)) * **Copilot Code Repair Loop Reliability** — The Copilot code authoring repair loop is now more reliable, reducing cases where stuck repairs would stall progress. ([#6792](https://github.com/Skyvern-AI/skyvern/pull/6792)) * **Workflow Studio Browser and Panel Improvements** — The Workflow Studio editor now supports take-control and viewport centering for the live browser, with alignment and toolbar polish for the run/editor panels. ([#6810](https://github.com/Skyvern-AI/skyvern/pull/6810)) * **Analytics Tag Filters Accept Flexible Input Shapes** — Analytics tag filters now accept labels, groups, or `group:label` pairs in all three supported filter shapes. ([#6802](https://github.com/Skyvern-AI/skyvern/pull/6802)) * **Run ID Search Fallback on Runs List** — The runs list now falls back to searching by run ID when no parameter-value match is found, making it easier to locate specific runs. ([#6788](https://github.com/Skyvern-AI/skyvern/pull/6788)) ## Bug fixes * Fixed login credentials not being reattached after editing a workflow via MCP, which could cause credential-gated runs to fail. ([#6761](https://github.com/Skyvern-AI/skyvern/pull/6761)) * Fixed conditional routing logic not being preserved when loading a workflow stored in the v1 format. ([#6760](https://github.com/Skyvern-AI/skyvern/pull/6760)) * Fixed the active run context being lost when switching between organizations, requiring a page refresh to restore the correct run view. ([#6753](https://github.com/Skyvern-AI/skyvern/pull/6753)) * Fixed browser connection settings defined in a TaskV2 block not being forwarded to child task runs. ([#6750](https://github.com/Skyvern-AI/skyvern/pull/6750)) * Fixed telephone number inputs dropping digits when bare NANP-format phone numbers were typed. ([#6826](https://github.com/Skyvern-AI/skyvern/pull/6826)) * Fixed the workflow builder freezing due to an infinite FlowRenderer dimension/layout feedback loop. ([#6824](https://github.com/Skyvern-AI/skyvern/pull/6824)) * Fixed the code editor crashing with a stack overflow when opened on large or deeply-nested JSON. ([#6817](https://github.com/Skyvern-AI/skyvern/pull/6817)) * Fixed the app failing to load after a deploy due to stale webpack chunks; the app now auto-recovers via a cache-busting reload. ([#6818](https://github.com/Skyvern-AI/skyvern/pull/6818)) * Fixed runs returning an incorrect terminal outcome when the extraction schema had been modified after the initial recording. ([#6815](https://github.com/Skyvern-AI/skyvern/pull/6815)) * Fixed MCP workflow edits dropping non-credential parameter-to-block links. ([#6813](https://github.com/Skyvern-AI/skyvern/pull/6813)) * Fixed address bar paste not working in the VNC streaming view. ([#6812](https://github.com/Skyvern-AI/skyvern/pull/6812)) * Fixed newly added workflow blocks not receiving focus in the editor. ([#6809](https://github.com/Skyvern-AI/skyvern/pull/6809)) * Fixed Copilot code-block file downloads being written to the wrong directory. ([#6797](https://github.com/Skyvern-AI/skyvern/pull/6797)) * Fixed parameter-value search not appearing in the v2 runs list. ([#6796](https://github.com/Skyvern-AI/skyvern/pull/6796)) * Fixed extra actions firing after selecting a combobox option during text entry. ([#6787](https://github.com/Skyvern-AI/skyvern/pull/6787)) * Fixed shadow DOM text nodes being missed during element text extraction. ([#6791](https://github.com/Skyvern-AI/skyvern/pull/6791)) * Fixed persistent browser sessions incorrectly reporting a cached session as live when it had become stale. ## New features * **OTP Fill at Runtime in Code-Block Sandbox** — Code blocks can now fill OTP fields using your stored TOTP credentials at runtime, enabling fully automated two-factor authentication flows without manual input. ([#6571](https://github.com/Skyvern-AI/skyvern/pull/6571)) * **Uncapped Workflow Runtime** — Workflows can now be configured to run without a maximum time limit, enabling long-running automations that previously timed out. ([#6567](https://github.com/Skyvern-AI/skyvern/pull/6567)) * **Code-First Code Block Editor** — Code blocks now feature a dedicated code editor with syntax highlighting, Jinja parameter hints, and a run timeline showing each action taken, giving developers full visibility and control over code-driven automations. ([#6604](https://github.com/Skyvern-AI/skyvern/pull/6604)) * **Period-Aware Analytics Drill-Down** — The agent analytics drill-down panel now respects the selected time period (7/30/90/365 days or custom range) and shows per-agent average duration, credits per run, and period-over-period trends. * **Agent Directory Tree** — The agents and folders list has been redesigned as a navigable directory tree, making it easier to browse and organize agents across nested folder hierarchies. ([#6631](https://github.com/Skyvern-AI/skyvern/pull/6631)) * **GCP Self-Host: Storage and Vault** — Self-hosted deployments on Google Cloud Platform now support GCS artifact storage and GCP Secret Manager vault, enabling full GCP-native deployments. ([#6632](https://github.com/Skyvern-AI/skyvern/pull/6632)) * **1Password Credential Picker** — Credential inputs now include an item picker for 1Password vaults, letting you browse and select vault items directly during credential setup. ([#6651](https://github.com/Skyvern-AI/skyvern/pull/6651)) * **Typed Extraction Schema for Copilot Code Blocks** — Copilot-generated code blocks now support a typed data extraction schema (matching `data_schema` parity), enabling structured data output from code-block automations. ([#6674](https://github.com/Skyvern-AI/skyvern/pull/6674)) * **SDK-Backed Remote Browser Provider** — Agents can now connect to external browser providers via SDK, enabling tighter integration with third-party remote browser services. ([#6687](https://github.com/Skyvern-AI/skyvern/pull/6687)) * **Bitwarden Credential Integration** — Saved credentials can now be sourced directly from Bitwarden vaults, bringing Bitwarden to full UI and functional parity with other supported credential providers. ([#6729](https://github.com/Skyvern-AI/skyvern/pull/6729)) ## Improvements * **Smarter Loop Planning for Repeated Work** — The task planner now prefers loop-based tasks when it detects repeated same-shaped operations, improving throughput on multi-item automation runs. ([#6575](https://github.com/Skyvern-AI/skyvern/pull/6575)) * **Agent Auto-Acts on Stalled Pages** — When the agent re-evaluates a page that hasn't changed, it now applies steering heuristics and acts immediately instead of stalling. ([#6577](https://github.com/Skyvern-AI/skyvern/pull/6577)) * **Final Answer Surfaced Directly** — The task agent now returns the final deliverable directly instead of spinning through redundant synthesis steps, reducing latency on completed tasks. ([#6574](https://github.com/Skyvern-AI/skyvern/pull/6574)) * **Copilot Stops Stuck Repair Loops** — The Workflow Copilot now detects when consecutive repairs make no verified progress, halts after three attempts, and presents an honest escalation with the draft preserved for review. ([#6608](https://github.com/Skyvern-AI/skyvern/pull/6608)) * **Voice Input Microphone Permission** — The browser microphone permission prompt now appears correctly when using voice dictation in the Prompt Box and Workflow Copilot. ([#6601](https://github.com/Skyvern-AI/skyvern/pull/6601)) * **`page.evaluate` Recorded in Code Block Timeline** — JavaScript `page.evaluate(...)` calls made inside code blocks are now recorded as actions in the run timeline, filling a gap in execution visibility. ([#6600](https://github.com/Skyvern-AI/skyvern/pull/6600)) * **Active Run Shown on Browser Session Page** — Browser session detail pages now display which workflow run currently occupies the session, making it easier to understand session usage. ([#6691](https://github.com/Skyvern-AI/skyvern/pull/6691)) * **Distinct Visual for Terminate Actions** — Terminate actions now appear with a distinct amber triangle icon in the run timeline, making it easy to spot where a run was stopped. ([#6693](https://github.com/Skyvern-AI/skyvern/pull/6693)) * **PDF Field Mapping by Positional Labels** — PDF form filling now uses positional field labels to improve accuracy when mapping data to form fields with ambiguous names. ([#6663](https://github.com/Skyvern-AI/skyvern/pull/6663)) * **MiMo-V2.5 Model Support via OpenRouter** — Added Xiaomi MiMo-V2.5 as a selectable LLM via OpenRouter for agent runs. ([#6636](https://github.com/Skyvern-AI/skyvern/pull/6636)) * **Settings "API Keys" Renamed to "General"** — The "API Keys" section in Settings has been renamed to "General" to better reflect its full scope of configuration options. ([#6642](https://github.com/Skyvern-AI/skyvern/pull/6642)) * **Run URLs Surfaced in MCP and CLI** — The agent app URL and session recording URLs are now included in run responses returned via MCP and the CLI, making it easier to link directly to a live run. ([#6719](https://github.com/Skyvern-AI/skyvern/pull/6719)) * **Email OTP Credentials Supported in Copilot** — The Copilot can now use stored email OTP credentials when generating and validating code-block automations that require email-based authentication. ([#6716](https://github.com/Skyvern-AI/skyvern/pull/6716)) * **Auto-Fill Default Google Account for Sheets Blocks** — Google Sheets blocks now automatically select the default linked Google account, reducing manual setup when configuring Sheets integrations. ([#6715](https://github.com/Skyvern-AI/skyvern/pull/6715)) * **Copilot Output Accurately Reflects Verified Results** — The Copilot no longer under-reports successfully verified output, ensuring the run summary accurately reflects what was accomplished. ([#6710](https://github.com/Skyvern-AI/skyvern/pull/6710)) * **Runs Halt Reliably on Terminal Blockers** — When the agent encounters strong evidence of an unresolvable blocker (such as a persistent challenge page), it now stops immediately rather than continuing to attempt further actions. ([#6714](https://github.com/Skyvern-AI/skyvern/pull/6714)) * **Workflow Save Performance Improved** — Cache invalidation on workflow save is now batched, eliminating a per-block N+1 query pattern that slowed saves for large workflows. ([#6718](https://github.com/Skyvern-AI/skyvern/pull/6718)) ## Bug fixes * Fixed the Run Inputs panel collapsing unexpectedly when filtering Run History. ([#6573](https://github.com/Skyvern-AI/skyvern/pull/6573)) * Fixed the agent incorrectly retrying click fallbacks after an action dispatch timed out, causing unintended interactions. ([#6569](https://github.com/Skyvern-AI/skyvern/pull/6569)) * Fixed session recordings and page interpretation not resuming correctly after navigation, causing missed recording segments. ([#6568](https://github.com/Skyvern-AI/skyvern/pull/6568)) * Fixed code block runs not generating a recording entry, causing the Recording tab to appear empty. ([#6607](https://github.com/Skyvern-AI/skyvern/pull/6607)) * Fixed code block action screenshots not appearing on the run Overview page. ([#6605](https://github.com/Skyvern-AI/skyvern/pull/6605)) * Fixed long usernames or email addresses hiding the sidebar collapse button on desktop. * Fixed the FileParserBlock crashing instead of surfacing a clear error when it encountered an unparseable file. ([#6657](https://github.com/Skyvern-AI/skyvern/pull/6657)) * Fixed the Inputs field missing from the Code view of code-first code blocks. ([#6633](https://github.com/Skyvern-AI/skyvern/pull/6633)) * Fixed Copilot-synthesized download blocks not downloading the file during code replay. ([#6637](https://github.com/Skyvern-AI/skyvern/pull/6637), [#6638](https://github.com/Skyvern-AI/skyvern/pull/6638)) * Fixed multi-step login flows not advancing when credentials were filled into JavaScript-gated fields. ([#6650](https://github.com/Skyvern-AI/skyvern/pull/6650)) * Fixed an infinite update loop on the workflow build page when certain block configurations were active. ([#6660](https://github.com/Skyvern-AI/skyvern/pull/6660)) * Fixed adopted-session file downloads not being available as run artifacts after the session ended. ([#6679](https://github.com/Skyvern-AI/skyvern/pull/6679)) * Fixed the run timeline showing action and step rows for non-code blocks when they should only appear for code blocks. ([#6675](https://github.com/Skyvern-AI/skyvern/pull/6675)) * Fixed workflow run actions not appearing in the timeline for all block types. * Fixed workflow runs not stopping when a configured time limit was exceeded. ([#6677](https://github.com/Skyvern-AI/skyvern/pull/6677)) * Fixed the analytics plan-tier badge showing the incorrect tier for some organizations. * Fixed credits not being recorded when data was captured inside a Navigate block in task runs. ([#6698](https://github.com/Skyvern-AI/skyvern/pull/6698)) * Fixed Copilot directory mode synthesizing incorrect code bindings. ([#6702](https://github.com/Skyvern-AI/skyvern/pull/6702)) * Fixed FileUpload blocks silently skipping the upload when no file was provided, instead of recording a clean no-op and continuing. ([#6728](https://github.com/Skyvern-AI/skyvern/pull/6728)) * Fixed the product tour not launching when triggered from the "Take a tour" menu option. ([#6727](https://github.com/Skyvern-AI/skyvern/pull/6727)) * Fixed scanned PDF files being parsed as a single large page rather than processed page-by-page, which caused extraction to miss content on multi-page documents. ([#6722](https://github.com/Skyvern-AI/skyvern/pull/6722)) * Fixed the block library drawer overflowing its container bounds in the workflow builder. ([#6721](https://github.com/Skyvern-AI/skyvern/pull/6721)) ## New features * **Copilot Ask/Build/Code Mode Routing** — The Copilot now routes each request based on the active mode: Ask returns answers without modifying the workflow, Build creates or updates workflows, and Code generates executable code blocks. ([#6459](https://github.com/Skyvern-AI/skyvern/pull/6459)) * **GCS Storage Backend** — Added Google Cloud Storage as an artifact storage backend for self-hosted deployments. ([#6442](https://github.com/Skyvern-AI/skyvern/pull/6442)) * **Key-Optional Labels and Flexible Tag Filters** — Tags now support key-optional labels, and tag filter queries accept more flexible formats for richer agent organization. ([#6458](https://github.com/Skyvern-AI/skyvern/pull/6458)) * **Self-Serve Editor Onboarding** — New users in the workflow editor now see a get-started modal with intent routing and template cards, a 4-stop guided product tour, and smart empty states on the dashboard and runs pages to accelerate time-to-first-automation. ([#6475](https://github.com/Skyvern-AI/skyvern/pull/6475)) * **Multi-Tab Browser Control** — The autonomous agent loop can now open and interact with multiple browser tabs simultaneously, enabling workflows that span across new tab links and pop-ups. ([#6507](https://github.com/Skyvern-AI/skyvern/pull/6507)) * **Gemini 3.5 Flash Model Support** — Added Google Gemini 3.5 Flash as a selectable LLM for agent runs, providing a faster inference option. ([#6505](https://github.com/Skyvern-AI/skyvern/pull/6505)) * **GCP Secret Manager Vault Adapter** — Added Google Cloud Secret Manager as a supported vault backend for storing and retrieving secrets in self-hosted deployments. ([#6488](https://github.com/Skyvern-AI/skyvern/pull/6488)) * **Bulk Actions on Agents List** — You can now select multiple agents at once and apply bulk actions directly from the agents list page. ([#6485](https://github.com/Skyvern-AI/skyvern/pull/6485)) * **Self-Service Credential Clears** — Saved credentials can now be individually cleared from the credentials settings page without deleting and recreating them. ([#6480](https://github.com/Skyvern-AI/skyvern/pull/6480)) * **Per-Run Session Recordings as Artifacts** — Recordings are now clipped to each run's time window and stored as downloadable run-scoped artifacts. ([#6479](https://github.com/Skyvern-AI/skyvern/pull/6479)) * **Credential-Aware Scouting in Code-Block Mode** — The Copilot now uses saved credentials while scouting pages for code-block generation and produces credential-typed code that fills login fields using your stored credentials. ([#6521](https://github.com/Skyvern-AI/skyvern/pull/6521)) * **Claude Fable 5 Model Support** — Added Claude Fable 5 as a selectable model for agent runs. ([#6539](https://github.com/Skyvern-AI/skyvern/pull/6539)) * **Live Browser Recording with Instant Placeholders** — Session recordings now commit navigation and wait blocks immediately as placeholders during live recording, with support for capture pause and draft interpretation. ([#6561](https://github.com/Skyvern-AI/skyvern/pull/6561)) * **Act-and-Observe Copilot Scouting** — The Copilot's page scouting now uses act-and-observe interactions that return bounded page evidence alongside gathered actions, improving code-block generation accuracy. ([#6533](https://github.com/Skyvern-AI/skyvern/pull/6533)) ## Improvements * **Deterministic Copilot Code-Block Synthesis** — Code blocks generated by the Copilot from scouted page interactions are now deterministic, producing consistent scripts across repeated generations. ([#6463](https://github.com/Skyvern-AI/skyvern/pull/6463)) * **Smarter Element Focus in Page Analysis** — The agent now drops non-navigable links from its internal element tree, reducing noise and improving targeting accuracy. ([#6461](https://github.com/Skyvern-AI/skyvern/pull/6461)) * **Workflow Builder Left Sidebar Preserved** — The left sidebar in the workflow builder now stays open when you switch between blocks, keeping your panel state between edits. ([#6453](https://github.com/Skyvern-AI/skyvern/pull/6453)) * **TOTP Prioritized Over Webhook for OTP** — Stored TOTP secrets are now tried before webhook polling when retrieving one-time passwords, speeding up authentication flows that use stored credentials. ([#6451](https://github.com/Skyvern-AI/skyvern/pull/6451)) * **Improved Caching for Click-Reached Blocks** — Scout interactions for blocks reached via click are now automatically credited toward the cached script, increasing cache hit rates. ([#6450](https://github.com/Skyvern-AI/skyvern/pull/6450)) * **Accessible Status Badges** — Status badges across the product have been updated with improved contrast and consistent pill styling for better accessibility. ([#6444](https://github.com/Skyvern-AI/skyvern/pull/6444)) * **Block Title Editable from Settings Sidebar** — Workflow block titles can now be edited from the right-hand settings sidebar, without needing to use the inline editor on the canvas. ([#6443](https://github.com/Skyvern-AI/skyvern/pull/6443)) * **API Reference Split into Agents and Runs Sections** — The public API reference is now organized into separate Agents and Runs sections for easier navigation. ([#6448](https://github.com/Skyvern-AI/skyvern/pull/6448)) * **Label-First Tag Editor and Flexible Tag Filter UI** — The tag editor now accepts standalone labels or `group:label` format in a single input, and the filter bar supports filtering by label, group, or group:label for richer agent organization. ([#6470](https://github.com/Skyvern-AI/skyvern/pull/6470)) * **2FA Field Progressive Disclosure in Login Block** — Two-factor authentication fields in the login workflow block are now collapsed by default and expanded on demand, reducing visual noise for workflows that don't use 2FA. ([#6490](https://github.com/Skyvern-AI/skyvern/pull/6490)) * **Persistent Browser Session Profile Generation Now Opt-In** — Automatic browser profile generation during persistent sessions is now opt-in, giving you explicit control over when profiles are captured. ([#6489](https://github.com/Skyvern-AI/skyvern/pull/6489)) * **Icon-Only Status Pills on Mobile Viewports** — Status badges now render in a compact icon-only format on small screen widths, preventing layout overflow on mobile devices. ([#6481](https://github.com/Skyvern-AI/skyvern/pull/6481)) * **Hardened Webhook Delivery** — Workflow webhook delivery is now more reliable, with improved handling of transient failures and prioritized delivery ordering. ([#6478](https://github.com/Skyvern-AI/skyvern/pull/6478)) * **Reduced Live Recording Draft Latency** — Live session recordings now appear almost instantly with placeholder entries, with final blocks committed after a short debounce window. ([#6553](https://github.com/Skyvern-AI/skyvern/pull/6553)) * **Copilot Stops on Terminal Blockers** — The Copilot now correctly halts when it reaches a condition that blocks further progress, preventing runaway sessions. ([#6535](https://github.com/Skyvern-AI/skyvern/pull/6535)) * **Copilot Chat Shows Run Outcome Verdict** — The Copilot chat timeline now reflects the actual run outcome verdict, giving a more accurate view of what the agent accomplished. ([#6532](https://github.com/Skyvern-AI/skyvern/pull/6532)) ## Bug fixes * Fixed org-verified discovered credentials not being credited in the Copilot credential gate, which could prevent runs from starting. ([#6462](https://github.com/Skyvern-AI/skyvern/pull/6462)) * Fixed OTP codes from previous workflow runs being picked up and incorrectly used in new runs. ([#6455](https://github.com/Skyvern-AI/skyvern/pull/6455)) * Fixed persistent-session screen recordings not appearing in the run view when the recording timestamp fell outside the run's time window. ([#6454](https://github.com/Skyvern-AI/skyvern/pull/6454)) * Fixed Copilot inconsistently asking for a URL before running discovery when the user had only named a site without providing one. ([#6473](https://github.com/Skyvern-AI/skyvern/pull/6473)) * Fixed Copilot asking for a URL after already successfully navigating to the requested site during discovery. ([#6472](https://github.com/Skyvern-AI/skyvern/pull/6472)) * Fixed self-hosted deployments rejecting requests with "Invalid credentials" (HTTP 403) when the Docker UI injected an API key that the container's server incorrectly filtered out. * Fixed persistent session recordings not being finalized when the video encoding process outlasted the session's cleanup window. ([#6519](https://github.com/Skyvern-AI/skyvern/pull/6519)) * Fixed the saved credentials status indicator not updating until the page was manually refreshed. ([#6517](https://github.com/Skyvern-AI/skyvern/pull/6517)) * Fixed the workflow run timeline rendering blocks in branch-tree order instead of execution order, producing a confusing step sequence. ([#6515](https://github.com/Skyvern-AI/skyvern/pull/6515)) * Fixed downloaded files inside loop blocks being shared across all iterations instead of scoped to the block that downloaded them. ([#6487](https://github.com/Skyvern-AI/skyvern/pull/6487)) * Fixed session recordings defaulting to an incorrect resolution; recordings now use Playwright's default viewport size. ([#6524](https://github.com/Skyvern-AI/skyvern/pull/6524)) * Fixed Copilot failing to recognize and use a saved credential when the credential ID was typed with a space or hyphen separator instead of an underscore; malformed IDs are now normalized and resolved correctly. ([#6529](https://github.com/Skyvern-AI/skyvern/pull/6529)) * Fixed Copilot chat showing workflow blocks as completed even when the overall run goal was not demonstrated — the recorded run outcome verdict is now surfaced in the chat narrative. ([#6528](https://github.com/Skyvern-AI/skyvern/pull/6528)) * Fixed Copilot browser sessions incorrectly blocking localhost navigation during page scouting, which could prevent evidence from being gathered from locally-served pages. ([#6527](https://github.com/Skyvern-AI/skyvern/pull/6527)) * Fixed single-element JSON arrays being unwrapped to a scalar when passed as workflow run inputs. ([#6560](https://github.com/Skyvern-AI/skyvern/pull/6560)) * Fixed code blocks silently dropping non-dict return values instead of passing them through to downstream blocks. ([#6556](https://github.com/Skyvern-AI/skyvern/pull/6556)) * Fixed the task agent ignoring the `max_iterations` override, causing runs to exceed their configured step limit. ([#6544](https://github.com/Skyvern-AI/skyvern/pull/6544)) * Fixed generated workflow parameter keys being duplicated, which caused a hard failure when the workflow was run. ([#6543](https://github.com/Skyvern-AI/skyvern/pull/6543)) * Fixed task runs completing successfully even when a required sub-goal had not been satisfied. ([#6546](https://github.com/Skyvern-AI/skyvern/pull/6546)) * Fixed the credential-clear confirmation dialog being hidden behind other overlays. ([#6542](https://github.com/Skyvern-AI/skyvern/pull/6542)) * Fixed click actions on elements wrapped in disabled containers not being retargeted to the clickable child element. ([#6540](https://github.com/Skyvern-AI/skyvern/pull/6540)) * Fixed Copilot loop detector incorrectly triggering at block dispatch boundaries. ([#6550](https://github.com/Skyvern-AI/skyvern/pull/6550)) ## New features * **Workflows are now Agents** — We've renamed "Workflows" to "Agents" across the product, public API, and docs. The API is now served under `/agents` (e.g. `POST /v1/run/agents`) and accepts an `agent_id` alias for `workflow_id` (same `wpid_` value), with `agent_id` echoed in responses. Fully backwards-compatible: existing `workflow_id` inputs, `/workflows` endpoints, SDK methods, and bookmarked doc URLs all keep working. * **Feature Preview Section in Settings** — A new "Feature Preview" panel in account settings lets you opt into upcoming features before they are fully released. ([#6318](https://github.com/Skyvern-AI/skyvern/pull/6318)) * **Filter Workflows by Tags** — The `GET /workflows` API now accepts a `?tags=` query parameter to filter results by tag. ([#6334](https://github.com/Skyvern-AI/skyvern/pull/6334)) * **Workflow Schedules in Open Source** — Self-hosted Skyvern deployments now support workflow schedules, previously a cloud-only feature. ([#6344](https://github.com/Skyvern-AI/skyvern/pull/6344)) * **Claude Opus 4.8 Support** — Added Claude Opus 4.8 as a selectable model for both direct Anthropic and AWS Bedrock inference paths. ([#6409](https://github.com/Skyvern-AI/skyvern/pull/6409)) * **Automatic Re-save of Expired Credential Sessions** — Saved credential sessions that have expired or encountered an error are now automatically re-saved, keeping browser profiles available without manual intervention. ([#6435](https://github.com/Skyvern-AI/skyvern/pull/6435)) * **GPT-5-mini Support** — Added GPT-5-mini as a selectable LLM for customers using their own OpenAI API keys, providing a faster, lower-cost inference option. ## Improvements * **Improved CAPTCHA Solving Reliability** — Added a timeout circuit breaker and better timing around CAPTCHA solves on submit-protected pages, reducing failures caused by timing races. ([#6349](https://github.com/Skyvern-AI/skyvern/pull/6349)) * **Undo/Redo Moved to Canvas Toolbar** — Undo and redo controls are back on the workflow canvas toolbar for easier access. ([#6310](https://github.com/Skyvern-AI/skyvern/pull/6310)) * **Better Loading and Error States in Browser Streams** — Improved copy and animations for loading and error states across all browser stream views. ([#6332](https://github.com/Skyvern-AI/skyvern/pull/6332)) * **Extended Credential Test Timeout** — The browser profile credential test now polls for up to 10 minutes, accommodating slower authentication flows that previously timed out. ([#6359](https://github.com/Skyvern-AI/skyvern/pull/6359)) * **Code-First Copilot Validation Gates** — The code-first Copilot now runs preflight checks, MCP evidence gates, and validation steps before executing generated code blocks, reducing silent failures. ([#6410](https://github.com/Skyvern-AI/skyvern/pull/6410)) * **OpenRouter Cost Tracking** — LLM token counts and costs are now tracked for runs using OpenRouter models, making per-run spending visible alongside other LLM providers. ([#6427](https://github.com/Skyvern-AI/skyvern/pull/6427)) * **CUA and Claude Opus Models Now Enterprise-Only** — The CUA browser-control mode and Claude Opus model family are now reserved for enterprise accounts. ([#6420](https://github.com/Skyvern-AI/skyvern/pull/6420)) ## Bug fixes * Fixed session cookies not being restored when reusing a saved browser profile. ([#6362](https://github.com/Skyvern-AI/skyvern/pull/6362)) * Fixed TOTP codes not being recovered from webhook response bodies that are not strictly valid JSON. ([#6354](https://github.com/Skyvern-AI/skyvern/pull/6354)) * Fixed webhook responses being truncated at 2KB when routed through the NAT proxy. * Fixed filtered dropdown options not being selectable in certain search-driven input components. ([#6348](https://github.com/Skyvern-AI/skyvern/pull/6348)) * Fixed block prompts not rendering in the workflow version comparison view. ([#6331](https://github.com/Skyvern-AI/skyvern/pull/6331)) * Fixed agent navigation buttons rendered via CSS `::before`/`::after` pseudo-content icons being missed when the icon element's bounding rect was zero due to out-of-flow positioning. ([#6385](https://github.com/Skyvern-AI/skyvern/pull/6385)) * Fixed credential edit form values and in-progress test state being cleared when the credentials list refreshed in the background during a browser profile test. ([#6404](https://github.com/Skyvern-AI/skyvern/pull/6404)) * Fixed workflow canvas layout not updating correctly when a container block is collapsed. ([#6436](https://github.com/Skyvern-AI/skyvern/pull/6436)) * Fixed session cookie capture not persisting correctly when saving browser credential sessions. ([#6434](https://github.com/Skyvern-AI/skyvern/pull/6434)) * Fixed persistent browser session final status not being reconciled when a session close races a timeout cleanup. * Fixed shadow DOM inputs inside closed dropdown components incorrectly being forced visible. ([#6433](https://github.com/Skyvern-AI/skyvern/pull/6433)) ## New features * **Redesigned Sidebar Navigation** — The app sidebar has been redesigned with collapsible groups, improved visual hierarchy, and a cleaner layout. ([#6211](https://github.com/Skyvern-AI/skyvern/pull/6211)) * **Workflow Run Retry** — Workflow runs can now be retried directly from the UI or API without creating a new run from scratch. ([#6195](https://github.com/Skyvern-AI/skyvern/pull/6195)) * **New Workflow Run Page Layout** — The workflow run detail page has been split into a compact timeline and a detail panel for faster navigation and better readability. ([#6214](https://github.com/Skyvern-AI/skyvern/pull/6214)) * **Copilot Turn Narrative** — The workflow copilot now displays a summary bubble after each turn, giving you a clear audit trail of what the agent did and decided. ([#6231](https://github.com/Skyvern-AI/skyvern/pull/6231)) * **Block Completion Progress on Run Page** — The workflow run page now shows an N/M progress indicator so you can see how many blocks have completed at a glance. ([#6230](https://github.com/Skyvern-AI/skyvern/pull/6230)) * **Selector and AI Fallback Fields in Action Blocks** — Action blocks now expose explicit selector and AI fallback configuration, giving you finer control over element targeting. ([#6212](https://github.com/Skyvern-AI/skyvern/pull/6212)) * **Workflow Tagging API** — Tags can now be created, applied, queried, and managed via the API for programmatic workflow organization. ([#6251](https://github.com/Skyvern-AI/skyvern/pull/6251)) * **Run Cost Visibility in Task Runs** — Task runs now expose LLM, proxy, and captcha cost fields, making per-run spending trackable via the API. ([#6219](https://github.com/Skyvern-AI/skyvern/pull/6219)) * **Double-Click Action Support** — The click action block now supports double-click for elements that require it. ([#6166](https://github.com/Skyvern-AI/skyvern/pull/6166)) * **Search on Credentials Page** — Added a search bar to the credentials page for quick filtering by name. ## Improvements * **"Inputs" Replaces "Parameters" Across the UI** — Workflow block parameters are now consistently labeled "Inputs" throughout the editor and run views. ([#6296](https://github.com/Skyvern-AI/skyvern/pull/6296)) * **Sidebar Flyout on Hover** — Hovering over a collapsed sidebar icon now reveals the flyout menu without requiring a click. ([#6270](https://github.com/Skyvern-AI/skyvern/pull/6270)) * **Copilot Follows Live Frontier During Runs** — The copilot chat panel now tracks the active workflow frontier as the run progresses, keeping you oriented on the agent's current work. ([#6283](https://github.com/Skyvern-AI/skyvern/pull/6283)) * **Completed Copilot Turns Collapse to Summary Card** — Finished copilot turns now collapse into a compact summary card, reducing clutter in long sessions. ([#6280](https://github.com/Skyvern-AI/skyvern/pull/6280)) * **Copilot Workflow Proposal Staged View** — Accepting or rejecting a copilot workflow proposal now shows a staged diff view that snaps back cleanly on cancel or reject. ([#6260](https://github.com/Skyvern-AI/skyvern/pull/6260)) * **Browser Profile Saving Indicator** — A placeholder row now appears while a browser profile is being saved, giving immediate visual confirmation that the save is in progress. ([#6215](https://github.com/Skyvern-AI/skyvern/pull/6215)) * **Copilot Loop Detection** — The copilot now detects when it is stuck repeating the same reply and actively rewrites its approach to break the loop. ([#6161](https://github.com/Skyvern-AI/skyvern/pull/6161)) ## Bug fixes * Fixed credentials with embedded multi-placeholder secret references not being resolved correctly during workflow runs. ([#6245](https://github.com/Skyvern-AI/skyvern/pull/6245)) ## New features * **Guided Browser Profile Setup** — A new step-by-step flow walks you through creating a saved browser profile, making it easier to set up persistent login sessions. ([#6043](https://github.com/Skyvern-AI/skyvern/pull/6043)) * **MCP Setup in Cloud Settings** — Added a dedicated MCP setup section to cloud account settings for easier MCP client configuration. * **Draggable Workflow Blocks** — Blocks in the workflow editor can now be reordered by dragging and collapsed to save space, making it easier to navigate complex workflows. * **CDP Connect Headers** — The workflow editor now exposes a settings field for custom CDP connect headers, enabling authentication with remotely managed browser instances. ([#6125](https://github.com/Skyvern-AI/skyvern/pull/6125)) * **Credits Consumed per Run** — Workflow run detail pages now show how many credits were consumed by that specific run. ([#6133](https://github.com/Skyvern-AI/skyvern/pull/6133)) * **Bulk Cancel Runs** — A new API endpoint lets you cancel multiple in-progress workflow runs in a single request. ## Improvements * **Archived Artifact Status** — Workflow runs now show when their artifacts have been archived, with a clear status indicator in the UI. ([#6075](https://github.com/Skyvern-AI/skyvern/pull/6075)) * **Automatic Webhook Retry on Infrastructure Failures** — Workflow webhooks are now retried automatically after transient infrastructure failures, reducing missed notifications. ([#6062](https://github.com/Skyvern-AI/skyvern/pull/6062)) * **Faster Script-Mode Runs** — Speculative extract-action steps are skipped in script-mode workflows, cutting unnecessary LLM calls. ([#6057](https://github.com/Skyvern-AI/skyvern/pull/6057)) * **LLM Router Length-Truncation Fallback** — When a model response is cut off by a length limit, the router now automatically retries with a fallback model instead of returning a partial response. ([#6079](https://github.com/Skyvern-AI/skyvern/pull/6079)) * **Analytics Range Extended to 365 Days** — The analytics dashboard now offers a "365 days" time range, replacing "All time" which was slow for high-volume accounts. * **Copilot Recovers from Unexpected Errors** — The workflow copilot now catches unexpected errors mid-run and presents a recovery option instead of silently stopping. ([#6143](https://github.com/Skyvern-AI/skyvern/pull/6143)) * **Copilot Surfaces Missing-Context Fallback** — When the copilot lacks enough context to proceed, it now shows a clear fallback message explaining what information is needed. ([#6144](https://github.com/Skyvern-AI/skyvern/pull/6144)) * **Reduced LLM Context Overflow Failures** — Prompt data (element trees, extraction goals) is now capped before being sent to the LLM, significantly reducing context-overflow and rate-limit errors on complex pages. ([#6098](https://github.com/Skyvern-AI/skyvern/pull/6098)) ## Bug fixes * Fixed popup pages opened during a run not being included in session recordings. ([#6078](https://github.com/Skyvern-AI/skyvern/pull/6078)) * Fixed XHR-triggered file downloads not being captured when using download action blocks. ([#6054](https://github.com/Skyvern-AI/skyvern/pull/6054)) * Fixed transient download-error popups incorrectly causing run failures. ([#6080](https://github.com/Skyvern-AI/skyvern/pull/6080)) * Fixed child tasks not being terminated and workflow runs getting resurrected after a cleanup cron timeout. ([#6047](https://github.com/Skyvern-AI/skyvern/pull/6047)) * Fixed copilot feasibility check stalling when given diagnostic input for an existing workflow. ([#6061](https://github.com/Skyvern-AI/skyvern/pull/6061)) * Fixed reCAPTCHA v2 invisible variant being misidentified as v3, causing solve failures. * Fixed downloaded file links on workflow runs showing internal storage paths instead of actual filenames. ([#6137](https://github.com/Skyvern-AI/skyvern/pull/6137)) * Fixed the workflow copilot stopping unexpectedly when a browser session becomes unresponsive. ([#6106](https://github.com/Skyvern-AI/skyvern/pull/6106)) ## New features * **Analytics Dashboard** — A new /analytics page provides a breakdown of workflow run activity and performance over time. ([#5980](https://github.com/Skyvern-AI/skyvern/pull/5980)) * **Browser Profile Management Page** — A dedicated browser profiles page lets you view, search, and rename your saved browser profiles. ([#5990](https://github.com/Skyvern-AI/skyvern/pull/5990)) * **Smarter Element Targeting** — The agent now uses deterministic HTML element-tree compression, improving selector reliability on complex pages. ([#5970](https://github.com/Skyvern-AI/skyvern/pull/5970)) * **Block-Scoped Parameter Prompts in Debugger** — The workflow debugger now prompts for parameters scoped to the specific block being tested, making per-block runs easier to set up. ## Improvements * **Scheduled Trigger Badge on Runs Page** — The global Runs page now shows a badge on runs triggered by a schedule, making scheduled runs easy to identify. ([#5948](https://github.com/Skyvern-AI/skyvern/pull/5948)) * **Signed Artifact Content URLs** — Artifact content URLs are now always signed with configurable expiry for secure access control. ([#5940](https://github.com/Skyvern-AI/skyvern/pull/5940)) * **Faster Workflow Run API** — The GET workflow run endpoint has been significantly optimized for speed. ([#5993](https://github.com/Skyvern-AI/skyvern/pull/5993)) * **Copilot Diff View Detects Nested Changes** — The Copilot diff panel now correctly highlights changes inside nested conditional and loop blocks. ([#5945](https://github.com/Skyvern-AI/skyvern/pull/5945)) * **Output Parameter Size Protection** — Workflow output parameter values are now capped to prevent oversized JSON payloads from causing downstream failures. ([#5974](https://github.com/Skyvern-AI/skyvern/pull/5974)) ## Bug fixes * Fixed scheduled workflow runs not appearing on the global Runs page. ([#5949](https://github.com/Skyvern-AI/skyvern/pull/5949)) * Fixed webhook delivery silently failing on transient 403, 5xx, or network errors. ([#5952](https://github.com/Skyvern-AI/skyvern/pull/5952)) * Fixed artifact downloads failing for clients that send HTTP Range request headers. ([#5982](https://github.com/Skyvern-AI/skyvern/pull/5982)) * Fixed FileParserBlock failures not appearing in workflow run outputs. ([#5964](https://github.com/Skyvern-AI/skyvern/pull/5964)) ## New features * **While Loop Block** — A new workflow block type that repeats a sub-workflow until a condition is met, enabling dynamic iteration without a fixed loop count. ([#5809](https://github.com/Skyvern-AI/skyvern/pull/5809)) * **Multiple Schedules per Workflow** — Workflows can now have multiple independent schedules (e.g., run at 9am on weekdays and noon on weekends). ([#5799](https://github.com/Skyvern-AI/skyvern/pull/5799)) * **Google Sheets Connector (Open Source)** — The Google Sheets connector authentication flow is now part of the open source package. ([#5815](https://github.com/Skyvern-AI/skyvern/pull/5815)) * **Runs Tab on Browser Session Page** — The browser session detail page now includes a Runs tab listing all workflow runs associated with that session. ([#5830](https://github.com/Skyvern-AI/skyvern/pull/5830)) * **Per-Workflow Total Step Cap** — A new workflow-run step cap lets you limit the maximum number of agent steps across all blocks in a single run. ([#5834](https://github.com/Skyvern-AI/skyvern/pull/5834)) ## Improvements * **TOTP Scoped to Active Credential** — Credential-derived TOTP values are now scoped to the active credential, preventing stale tokens from being used mid-run. ([#5805](https://github.com/Skyvern-AI/skyvern/pull/5805)) * **Browser Dialogs Surfaced to Agent** — JavaScript dialogs (alerts, confirms, prompts) that the browser blocks are now surfaced to the agent so it can adapt its next action. ([#5810](https://github.com/Skyvern-AI/skyvern/pull/5810)) ## Bug fixes * Fixed the workflow-deleted banner not appearing on the run detail page when the parent workflow has been deleted. ([#5800](https://github.com/Skyvern-AI/skyvern/pull/5800)) ## New features * **Workflow Schedule Management via MCP** — Manage workflow schedules from MCP clients (e.g., Claude Code) using the new `skyvern schedule` CLI commands. ([#5713](https://github.com/Skyvern-AI/skyvern/pull/5713)) * **Org Settings via MCP** — Configure organization settings from MCP clients using the new `skyvern config` CLI tool. ([#5694](https://github.com/Skyvern-AI/skyvern/pull/5694)) * **MCP OAuth Org Selection** — Multi-org users can now choose which organization to connect to during MCP OAuth authentication. ([#5699](https://github.com/Skyvern-AI/skyvern/pull/5699)) * **Platform-Level JS Dialog Handler** — The agent now handles JavaScript dialogs at the browser level using LLM-guided decision logic, improving reliability on dialog-heavy pages. ([#5679](https://github.com/Skyvern-AI/skyvern/pull/5679)) * **Print-to-PDF in Downloaded Files** — Workflow blocks that trigger a browser print-to-PDF now expose the resulting file in the block's downloaded files list. ([#5784](https://github.com/Skyvern-AI/skyvern/pull/5784)) ## Improvements * **Cursor Visualization in Run Recordings** — Playwright recordings now overlay a visible cursor, making it easy to follow the agent's actions when reviewing a recording. ([#5683](https://github.com/Skyvern-AI/skyvern/pull/5683)) * **Short Signed Recording URLs** — Browser session recording links are now compact signed URLs instead of full S3 paths. ([#5686](https://github.com/Skyvern-AI/skyvern/pull/5686)) * **Configurable Artifact URL Expiry** — A settings field lets you control how long artifact content URLs stay valid before expiring. ([#5690](https://github.com/Skyvern-AI/skyvern/pull/5690)) * **Copilot Hard-Cancel** — A hard-cancel button immediately stops an in-progress copilot run without waiting for the current step to finish. ([#5726](https://github.com/Skyvern-AI/skyvern/pull/5726)) * **Copilot Reuses Live Debug Browser Session** — When testing a workflow from the debugger, the copilot now reuses the open browser session instead of starting a new one. ([#5709](https://github.com/Skyvern-AI/skyvern/pull/5709)) * **Copilot Surfaces WIP Workflow on Timeout** — If the copilot times out or a test fails, it now offers the in-progress workflow so you can review and continue. ([#5755](https://github.com/Skyvern-AI/skyvern/pull/5755)) * **Pre-Filled Debugger Run Dialog** — The Run dialog in the workflow debugger now pre-fills with values from your last run. ([#5724](https://github.com/Skyvern-AI/skyvern/pull/5724)) * **Copilot Atomic Workflow Accept** — Accepting a copilot workflow proposal now applies all block changes atomically, preventing partial updates. ([#5695](https://github.com/Skyvern-AI/skyvern/pull/5695)) * **Loop Block Failure-Handling Clarity** — The loop block UI has clearer controls and labels for configuring how failures inside the loop are handled. ([#5731](https://github.com/Skyvern-AI/skyvern/pull/5731)) ## Bug fixes * Fixed the in-progress workflow not being preserved when closing the copilot mid-run. ([#5787](https://github.com/Skyvern-AI/skyvern/pull/5787)) ## Improvements * **Copilot Live Status Narration** — The workflow editor copilot now displays a short live status line while it works, so you can see what the agent is doing instead of waiting in silence. ([#5567](https://github.com/Skyvern-AI/skyvern/pull/5567)) * **Renamed Browser Profile Reset Action** — The API endpoint for clearing a persisted browser session has been renamed from `/browser_session/refresh` to `/browser_session/reset_profile` for clarity. The old path remains available as a deprecated alias. ([#5572](https://github.com/Skyvern-AI/skyvern/pull/5572)) * **Fewer Screenshots for API Runs** — Screenshot capture frequency has been reduced for API-triggered runs, lowering storage overhead on long-running automations without affecting interactive sessions. ([#5565](https://github.com/Skyvern-AI/skyvern/pull/5565)) ## Bug fixes * Fixed the workflow copilot incorrectly proposing a workflow it had just failed to build. The copilot now only surfaces an Accept/Reject panel when the last test actually passed. ([#5574](https://github.com/Skyvern-AI/skyvern/pull/5574)) * Fixed 2FA entry failing on pages with custom overlay input components where the real input field is hidden. The agent now types digit keys directly when no interactable input exists. ([#5568](https://github.com/Skyvern-AI/skyvern/pull/5568)) ## New features * **Saudi Arabia Proxy Location** — Added `RESIDENTIAL_SA` as a proxy geolocation option for automations targeting Saudi Arabian websites. * **Workflow-Level Error Code Mapping** — Workflows now support an `error_code_mapping` field that all blocks inherit automatically. Block-level mappings still take precedence, giving you a single place to define default error handling without repeating it on every block. ([#5506](https://github.com/Skyvern-AI/skyvern/pull/5506)) * **AI Summarize for Workflow Run Outputs** — A magic-wand "Summarize with AI" button now appears next to block and workflow run output sections, generating a plain-language summary of raw JSON output on demand. ([#5556](https://github.com/Skyvern-AI/skyvern/pull/5556)) * **Reset Browser Profile API** — A new `POST /workflows/{workflow_permanent_id}/browser_session/reset_profile` endpoint clears a corrupted persisted browser session so the next run starts from a fresh browser state. ([#5544](https://github.com/Skyvern-AI/skyvern/pull/5544)) * **MCP OAuth for Remote Clients** — MCP clients (e.g. Claude Code, Codex) can now complete browser-based OAuth to authenticate with Skyvern without getting stuck in redirect chains. ([#5558](https://github.com/Skyvern-AI/skyvern/pull/5558)) * **OpenClaw MCP Setup** — `skyvern setup openclaw` and `skyvern mcp switch` now support OpenClaw as an MCP client target for both remote and local stdio configurations. ([#5536](https://github.com/Skyvern-AI/skyvern/pull/5536)) ## Improvements * **Smarter Extraction Cache Keys** — The extraction cache now normalizes session-volatile tokens (random UUIDs, CSRF values, nonce query params, timestamps) before hashing cache keys. Semantically identical page visits now share cached extraction results, improving cache hit rates across workflow re-runs. ([#5504](https://github.com/Skyvern-AI/skyvern/pull/5504)) * **Reduced Rate-Limit Errors on Extraction Prompts** — Extraction prompts are now capped in size before being sent to the LLM. Oversized `previous_extracted_information`, `extracted_information_schema`, and element trees are truncated rather than sent whole, significantly reducing `429 RESOURCE_EXHAUSTED` errors on high-volume workflows. ([#5502](https://github.com/Skyvern-AI/skyvern/pull/5502)) * **Cross-Run Extraction Cache** — Extraction results are now cached in Redis across workflow runs, scoped to the workflow. Recurring scheduled workflows skip redundant LLM calls when the page content hasn't changed. ([#5562](https://github.com/Skyvern-AI/skyvern/pull/5562)) * **Copilot Survives Tab Switches and Reconnects** — The workflow copilot agent now runs to completion even if the browser tab is closed or the connection drops mid-request, and the AI reply is persisted so it appears when you reconnect. ([#5560](https://github.com/Skyvern-AI/skyvern/pull/5560)) * **Copilot Fails Fast on Unresolvable URLs** — The workflow copilot now immediately surfaces the real error (e.g. DNS resolution failure) and stops retrying when a URL cannot be reached, rather than reporting success. ([#5563](https://github.com/Skyvern-AI/skyvern/pull/5563)) ## Bug fixes * Fixed CSV parsing failing on files whose first header row exceeded \~1 MB, causing valid wide-format CSVs to be rejected with "Could not determine delimiter". ([#5510](https://github.com/Skyvern-AI/skyvern/pull/5510)) * Fixed a browser automation crash on sites with cross-origin stylesheets (e.g. MUI-based apps). CSS hover styles are now parsed entirely in memory without modifying the DOM, preventing React reconciliation errors that caused the agent to loop until max steps. ([#5508](https://github.com/Skyvern-AI/skyvern/pull/5508)) * Fixed context-window overflow failures being misdiagnosed. Steps that fail due to oversized input are now correctly counted and short-circuit to a clear `LLM_ERROR` failure reason instead of triggering a redundant LLM-based failure analysis. ([#5507](https://github.com/Skyvern-AI/skyvern/pull/5507)) * Fixed workflow file-download blocks losing their configured `download_suffix` at task finalization, causing downloaded files to be persisted without the expected filename suffix. ([#5499](https://github.com/Skyvern-AI/skyvern/pull/5499)) * Fixed cached scripts for non-ATS workflows incorrectly generating `fill_form()` calls, which defeated the performance benefits of caching by delegating back to AI at runtime. ([#5497](https://github.com/Skyvern-AI/skyvern/pull/5497)) * Fixed the pagination navigator on the Workflow Past Runs and Run History pages being right-aligned instead of centered. * Fixed run recordings missing an end timestamp and broken scrubbing. Recordings are now finalized with a stream-copy remux so players correctly show duration and support seeking. ([#5551](https://github.com/Skyvern-AI/skyvern/pull/5551)) * Fixed tag input fields (e.g. skill set fields on job application forms) not selecting values from the dropdown. These fields are now correctly treated as auto-completion inputs. ([#5557](https://github.com/Skyvern-AI/skyvern/pull/5557)) * Fixed per-step video sync spawning a redundant ffmpeg process on every step, causing CPU spikes and log noise. ([#5559](https://github.com/Skyvern-AI/skyvern/pull/5559)) * Fixed workflow parameter edit and delete buttons being hidden when a parameter name was too long. * Fixed webhook delivery failing silently when a stored webhook URL had a leading or trailing space. ([#5550](https://github.com/Skyvern-AI/skyvern/pull/5550)) ## New features * **Adaptive Caching (Script Generation)** — Skyvern can now learn from repeated workflow runs and generate cached scripts that speed up future executions. When a block runs successfully, Skyvern records a reusable script and replays it on subsequent runs, falling back to the AI agent only if the script fails. ([#4908](https://github.com/Skyvern-AI/skyvern/pull/4908), [#4916](https://github.com/Skyvern-AI/skyvern/pull/4916), [#4917](https://github.com/Skyvern-AI/skyvern/pull/4917), [#4920](https://github.com/Skyvern-AI/skyvern/pull/4920), [#4922](https://github.com/Skyvern-AI/skyvern/pull/4922), [#4931](https://github.com/Skyvern-AI/skyvern/pull/4931)) * **Workflow Trigger Block** — A new block type that lets one workflow trigger another from within the workflow editor. Chain workflows together as building blocks for complex automations. ([#4885](https://github.com/Skyvern-AI/skyvern/pull/4885)) * **Browser-based CLI Signup** — New users can sign up for Skyvern Cloud directly from the CLI. Running `skyvern signup` opens a browser flow that creates your account and stores your API key locally. ([#4925](https://github.com/Skyvern-AI/skyvern/pull/4925)) * **Interactive ngrok Tunnel** — `skyvern browser serve` can now create an ngrok tunnel automatically, making it easy to expose your local browser to Skyvern Cloud without manual network configuration. ([#4924](https://github.com/Skyvern-AI/skyvern/pull/4924)) * **South Korea Proxy Location** — Added `RESIDENTIAL_KR` as a proxy geolocation option for automations targeting South Korean websites. ([#4918](https://github.com/Skyvern-AI/skyvern/pull/4918)) * **Downloaded Files Tab** — Browser session detail pages now include a Downloaded Files tab for viewing and accessing files captured during a session. ([#4911](https://github.com/Skyvern-AI/skyvern/pull/4911)) * **CDP Proxy Authentication** — Remote browser connections now support authenticated proxies via the CDP `Fetch.authRequired` protocol. ([#4936](https://github.com/Skyvern-AI/skyvern/pull/4936)) * **Remote Browser Download Interception** — File downloads triggered by XHR requests and other non-navigation events are now captured when using remote CDP browser connections. ([#4906](https://github.com/Skyvern-AI/skyvern/pull/4906), [#4921](https://github.com/Skyvern-AI/skyvern/pull/4921), [#4934](https://github.com/Skyvern-AI/skyvern/pull/4934)) * **`current_date` Reserved Parameter** — Workflows now have a built-in `current_date` parameter that resolves to today's date automatically. ([#4854](https://github.com/Skyvern-AI/skyvern/pull/4854)) * **Reserved Parameters in Block Editor** — The workflow block parameter picker now shows reserved system parameters, making them discoverable without memorizing names. ([#4857](https://github.com/Skyvern-AI/skyvern/pull/4857)) * **Natural Language Loop `data_schema`** — Loop blocks driven by natural language extraction now support a `data_schema` field for consistent output structure. ([#4851](https://github.com/Skyvern-AI/skyvern/pull/4851)) * **Gemini 3.1 Pro and Inception Mercury-2** — Two new LLM engine options for your automations. ([#4847](https://github.com/Skyvern-AI/skyvern/pull/4847)) * **MCP Server on API Service** — The MCP remote server is now mounted at `/mcp` on the existing API, eliminating the need for a separate process. ([#4843](https://github.com/Skyvern-AI/skyvern/pull/4843)) ## Improvements * **Renamed "Login-Free" to "Saved Profile"** — Clearer terminology throughout the UI. Browser session checkbox wording has also been improved. ([#4914](https://github.com/Skyvern-AI/skyvern/pull/4914)) * **TOTP Verification Improvements** — Better timer handling, expired code retry, 2FA banner suppression, and more reliable goal-text extraction during TOTP flows. ([#4860](https://github.com/Skyvern-AI/skyvern/pull/4860)) * **TOTP Webhook includes `workflow_permanent_id`** — Easier to identify which workflow is requesting a 2FA code. ([#4871](https://github.com/Skyvern-AI/skyvern/pull/4871)) * **Consolidated Gemini 3 Pro Model Key** — `VERTEX_GEMINI_3_PRO` now auto-resolves to the latest version, so you no longer need to update config when Google releases point versions. ([#4926](https://github.com/Skyvern-AI/skyvern/pull/4926)) * **Browser Rotation for Remote Connections** — Remote browser environments now support context rotation, improving reliability for long-running automations. ([#4929](https://github.com/Skyvern-AI/skyvern/pull/4929)) * Workflow save validation (HTTP 422) now returns clear, field-level error messages. ([#4852](https://github.com/Skyvern-AI/skyvern/pull/4852)) * Browser launch errors now show actionable messages instead of raw exceptions. ([#4844](https://github.com/Skyvern-AI/skyvern/pull/4844)) * Cloud LLM fallback overrides are now properly applied when selecting models. ([#4839](https://github.com/Skyvern-AI/skyvern/pull/4839)) ## Bug fixes * Fixed a race condition where final task status could be overwritten by a late-arriving non-final status. ([#4928](https://github.com/Skyvern-AI/skyvern/pull/4928)) * Conditional blocks no longer crash when evaluating empty or null parameters. ([#4907](https://github.com/Skyvern-AI/skyvern/pull/4907)) * Browser sessions using `FORCE_BROWSER_SESSION` no longer time out prematurely. ([#4903](https://github.com/Skyvern-AI/skyvern/pull/4903)) * SVG-based captcha text is now correctly extracted during DOM scraping. ([#4880](https://github.com/Skyvern-AI/skyvern/pull/4880)) * MCP remote tool handlers now route to the correct API environment. ([#4869](https://github.com/Skyvern-AI/skyvern/pull/4869)) * MCP remote auth token comparison no longer fails on encrypted tokens. ([#4863](https://github.com/Skyvern-AI/skyvern/pull/4863)) * `skyvern quickstart` now handles local PostgreSQL without a pre-existing `skyvern` role. ([#4878](https://github.com/Skyvern-AI/skyvern/pull/4878)) * WebSocket URLs through ngrok tunnels now rewrite correctly for live browser streaming. ([#4927](https://github.com/Skyvern-AI/skyvern/pull/4927)) * Conditional blocks no longer crash when all branches use Jinja templates. ([#4849](https://github.com/Skyvern-AI/skyvern/pull/4849)) * Conditional blocks no longer misinterpret resolved Jinja template variables. ([#4841](https://github.com/Skyvern-AI/skyvern/pull/4841)) ## New features * **Browser Profile Testing UI (Frontend)** — The Browsers page now lets you launch a test run against a saved browser profile to confirm its login state is still valid before scheduling production workflows. ([#4833](https://github.com/Skyvern-AI/skyvern/pull/4833)) * **2FA Verification Code UI and Notifications** — When a workflow pauses for a 2FA code, the UI now shows a clear prompt and pushes a notification so you don't miss it. ([#4787](https://github.com/Skyvern-AI/skyvern/pull/4787)) * **Gated Admin Impersonation for MCP API Keys** — Adds gated admin controls so support engineers can impersonate an organization scope when troubleshooting MCP-based automations, with audit-friendly access controls. ([#4822](https://github.com/Skyvern-AI/skyvern/pull/4822)) * **Browser Profile Testing** — Test browser profiles directly from the UI to verify that saved login sessions are still valid. Workflows can also run with a saved browser profile, enabling login-free automations that reuse authenticated sessions. ([#4818](https://github.com/Skyvern-AI/skyvern/pull/4818)) * **Skyvern Skills Package** — The new `skyvern skill` CLI command provides pre-built workflow templates and reference documentation for common automation patterns. ([#4817](https://github.com/Skyvern-AI/skyvern/pull/4817)) * **Clear Cached Scripts API** — A new endpoint lets you clear cached automation scripts for a workflow when a target website changes and you want to force Skyvern to re-learn. ([#4809](https://github.com/Skyvern-AI/skyvern/pull/4809)) * **Automatic 2FA Detection Without TOTP Credentials** — Skyvern now detects when a website asks for a 2FA code even without pre-configured TOTP credentials. The system pauses and waits for you to provide the code via the UI or webhook. ([#4786](https://github.com/Skyvern-AI/skyvern/pull/4786)) * **Full CLI Parity with MCP** — The CLI now supports browser session management, credential management, block operations, and enhanced workflow commands. Everything available through MCP is now accessible from the command line. ([#4789](https://github.com/Skyvern-AI/skyvern/pull/4789), [#4792](https://github.com/Skyvern-AI/skyvern/pull/4792), [#4793](https://github.com/Skyvern-AI/skyvern/pull/4793)) * **Claude Opus 4.6 CUA Support** — Anthropic's Claude Opus 4.6 is now available as a Computer Use Agent model for driving browser interactions. ([#4780](https://github.com/Skyvern-AI/skyvern/pull/4780)) * **Anthropic Claude Opus 4.6** — Added Claude Opus 4.6 as an available LLM engine for web automation tasks. ([#4777](https://github.com/Skyvern-AI/skyvern/pull/4777), [#4778](https://github.com/Skyvern-AI/skyvern/pull/4778)) * **Unified Browser Task Block** — The Navigation V1 and Task V2 blocks have been merged into a single **Browser Task** block. The block now exposes both engines as a dropdown, simplifying the workflow editor and reducing block-type confusion. ([#4695](https://github.com/Skyvern-AI/skyvern/pull/4695)) * **Block Discovery MCP Tools** — Added MCP tools that let AI assistants enumerate available block types and their schemas, plus richer instructions for building workflows through MCP. ([#4683](https://github.com/Skyvern-AI/skyvern/pull/4683)) * **Edit Existing Credentials API** — A new endpoint lets you update credential values without deleting and recreating them, preserving credential IDs across changes. ([#4693](https://github.com/Skyvern-AI/skyvern/pull/4693)) * **Filter Workflow Runs by Error Code and Search Key** — The workflow runs list endpoint now supports `error_code` and `search_key` query parameters for narrowing down failed runs. ([#4694](https://github.com/Skyvern-AI/skyvern/pull/4694)) * **GPT-5 Mini in Model Selector** — GPT-5 Mini is now selectable as an LLM engine. GPT-5 has been hidden in favor of more reliable variants. ([#4686](https://github.com/Skyvern-AI/skyvern/pull/4686)) ## Improvements * **2FA Backend Cleanup** — Refactored the 2FA pipeline to make code delivery more reliable across both the UI form and the API endpoint. ([#4826](https://github.com/Skyvern-AI/skyvern/pull/4826)) * **Environment Variables Override Mounted API Keys** — In Skyvern's Streamlit-based deployment, env vars now take precedence over keys baked into the image, making local overrides simpler. ([#4824](https://github.com/Skyvern-AI/skyvern/pull/4824)) * The workflow run timeline now properly displays loop iterations and conditional branches, making complex runs easier to debug. ([#4782](https://github.com/Skyvern-AI/skyvern/pull/4782)) * **Block Failure Reasons Surfaced in UI** — Every block type now shows its `failure_reason` in the run timeline, making debugging non-obvious failures faster. ([#4672](https://github.com/Skyvern-AI/skyvern/pull/4672)) * **Webhook Payload Truncation in Logs** — Large webhook payloads are now truncated in log entries, keeping logs readable without losing context. ([#4701](https://github.com/Skyvern-AI/skyvern/pull/4701)) ## Bug fixes * When both a TOTP credential and a webhook are configured for 2FA, the credential is now correctly prioritized. ([#4811](https://github.com/Skyvern-AI/skyvern/pull/4811)) * Fixed conditional blocks evaluating the wrong value after Jinja template rendering. ([#4801](https://github.com/Skyvern-AI/skyvern/pull/4801)) * Fixed MFA resolution priority when both TOTP credentials and webhooks are configured. ([#4800](https://github.com/Skyvern-AI/skyvern/pull/4800)) * Fixed the cursor jumping to the end while editing conditional expressions in the workflow editor. ([#4682](https://github.com/Skyvern-AI/skyvern/pull/4682)) * Fixed dotted Jinja variables (e.g. `{{ block_output.field }}`) rendering incorrectly in the expression preview. ([#4684](https://github.com/Skyvern-AI/skyvern/pull/4684)) * The API now returns 404 instead of 500 when a workflow is not found. ([#4699](https://github.com/Skyvern-AI/skyvern/pull/4699)) ## New features * **Conditional Block Caching** — The script cache now supports Conditional blocks, so workflows that branch based on page state can replay from cache instead of re-running the AI agent. ([#4642](https://github.com/Skyvern-AI/skyvern/pull/4642)) * **OpenTelemetry Backend** — Skyvern can now export metrics, traces, and logs to any OTEL-compatible collector for centralized observability. ([#4632](https://github.com/Skyvern-AI/skyvern/pull/4632)) * **Workflow API Route Reorganization** — Workflow API endpoints have been split into focused routers, making the OpenAPI surface easier to navigate. ([#4628](https://github.com/Skyvern-AI/skyvern/pull/4628)) ## Improvements * **Workflow Copilot Auto-Opens for Empty Workflows** — When you create a new workflow with no blocks yet, the Workflow Copilot opens by default to help you get started. ([#4625](https://github.com/Skyvern-AI/skyvern/pull/4625)) * **Run Workflow Button Moved to Top** — The Run button now lives at the top of the workflow editor for easier access. ([#4626](https://github.com/Skyvern-AI/skyvern/pull/4626)) * **Skip LLM for Single-Match Location Autocomplete** — Location autocomplete now skips the LLM call when only one option matches the user's input, reducing cost and latency. ([#4631](https://github.com/Skyvern-AI/skyvern/pull/4631)) * **Improved Version History Icon** — The workflow version history button now uses an icon that better represents document versions. ([#4640](https://github.com/Skyvern-AI/skyvern/pull/4640)) ## Bug fixes * Fixed `ForLoop` blocks failing to execute under script caching (regression from v1.0.12). ([#4630](https://github.com/Skyvern-AI/skyvern/pull/4630)) * Fixed `ActionDragPath` subscript error in CUA drag-action parsing. ([#4623](https://github.com/Skyvern-AI/skyvern/pull/4623)) * Fixed cron-scheduled tasks getting stuck with "task not found" errors. ([#4627](https://github.com/Skyvern-AI/skyvern/pull/4627)) * Fixed parameter creation dialog not clearing default-value state when switching to credential type. ([#4622](https://github.com/Skyvern-AI/skyvern/pull/4622)) * Fixed debugger loop-block visual overlap when the status row appeared. ([#4641](https://github.com/Skyvern-AI/skyvern/pull/4641)) ## New features * **Task V2 Termination** — Task V2 (the planner-agent-validator system) can now be terminated mid-run via API, matching the cancel behavior already available for Task V1. ([#4589](https://github.com/Skyvern-AI/skyvern/pull/4589)) * **ForLoop Block Caching** — Cached scripts now support `ForLoop` blocks. Workflows that iterate over lists can replay from cache after the first successful run. ([#4600](https://github.com/Skyvern-AI/skyvern/pull/4600)) * **Conditional Block Caching** — Initial support for caching workflows that include conditional branching. ([#4603](https://github.com/Skyvern-AI/skyvern/pull/4603)) * **`run_with` Parameter for Run Task** — The `run_task` endpoint now accepts a `run_with` parameter so you can target Task V2 (or future variants) without changing the endpoint. ([#4576](https://github.com/Skyvern-AI/skyvern/pull/4576)) * **`skyvern run dev` Command** — A new CLI command spins up a Superset workspace alongside the standard dev environment for local analytics work. ([#4593](https://github.com/Skyvern-AI/skyvern/pull/4593)) ## Improvements * **All Branch Evaluations Shown in Conditional Block Timeline** — The run timeline now shows every conditional branch's evaluation result, not just the chosen one — useful when debugging "why did it pick that branch?" ([#4577](https://github.com/Skyvern-AI/skyvern/pull/4577)) * **Sidebar Expand/Collapse Icon** — Replaced the pin icon with a chevron, matching common conventions. ([#4586](https://github.com/Skyvern-AI/skyvern/pull/4586)) * **PDF Parsing Token Cap** — PDF parsing now caps token volume per request to avoid total failure on very large documents. ([#4602](https://github.com/Skyvern-AI/skyvern/pull/4602)) * **`DATABASE_STRING` Parameter on Quickstart** — `skyvern quickstart` now accepts a `DATABASE_STRING` argument for explicit DB connection configuration. ([#4580](https://github.com/Skyvern-AI/skyvern/pull/4580)) ## Bug fixes * Fixed credentials not clearing from the Login block when deselected from the picker. ([#4581](https://github.com/Skyvern-AI/skyvern/pull/4581)) * Fixed workflow run timeline missing recent steps until a manual refresh. ([#4587](https://github.com/Skyvern-AI/skyvern/pull/4587)) * Fixed the workflow editor showing spurious "unsaved changes" when switching between conditional branches. ([#4588](https://github.com/Skyvern-AI/skyvern/pull/4588)) ## New features * **Workflow Copilot Generally Available** — The Workflow Copilot is now enabled for all users. Describe what you want in natural language and it generates a multi-block workflow you can edit. ([#4533](https://github.com/Skyvern-AI/skyvern/pull/4533)) * **Browser Sessions v2 Frontend** — The new browser session management UI lands on the Browsers page, building on the v2 backend shipped in v1.0.10. ([#4514](https://github.com/Skyvern-AI/skyvern/pull/4514)) * **TOTP Endpoint OTP Type Filter** — The TOTP listing endpoint now accepts an `otp_type` query parameter for filtering numeric codes vs. magic links. ([#4529](https://github.com/Skyvern-AI/skyvern/pull/4529)) * **Mintlify Documentation Setup** — Skyvern's documentation site moves to Mintlify, with redirects for the legacy Fern URLs. ([#4516](https://github.com/Skyvern-AI/skyvern/pull/4516)) ## Improvements * **Async File I/O via aiofiles** — Replaced blocking file I/O with `aiofiles` throughout the agent runtime, improving throughput on I/O-heavy workloads. ([#4520](https://github.com/Skyvern-AI/skyvern/pull/4520)) * **Cached Experimentation Provider TTL** — `BaseExperimentationProvider` now caches feature-flag lookups with a per-item TTL, reducing pressure on the experimentation backend. ([#4536](https://github.com/Skyvern-AI/skyvern/pull/4536), [#4540](https://github.com/Skyvern-AI/skyvern/pull/4540)) ## Bug fixes * Fixed `ai_fallback` not being read correctly from the database for cached workflow runs. ([#4524](https://github.com/Skyvern-AI/skyvern/pull/4524)) * Fixed iframe-tree extraction crashing when the page raised a transient exception. ([#4530](https://github.com/Skyvern-AI/skyvern/pull/4530)) * Fixed the workflow version comparison view ordering versions on the wrong sides. ([#4531](https://github.com/Skyvern-AI/skyvern/pull/4531)) * Fixed the workflow history panel scroll behavior in debug mode. ([#4532](https://github.com/Skyvern-AI/skyvern/pull/4532)) * Fixed `TypeError` when comparing offset-naive and offset-aware datetimes during workflow scheduling. ([#4534](https://github.com/Skyvern-AI/skyvern/pull/4534)) * Fixed schema regeneration overwriting unchanged block field names. ([#4535](https://github.com/Skyvern-AI/skyvern/pull/4535)) * Fixed `uvicorn` reload breaking on Windows due to async event loop policy. ([#4538](https://github.com/Skyvern-AI/skyvern/pull/4538)) ## New features * **Browser Sessions v2 (Backend)** — A new persistent browser session architecture with cleaner lifecycle management, better resource reuse, and improved reliability for long-running automations. The frontend follows in v1.0.11. ([#4515](https://github.com/Skyvern-AI/skyvern/pull/4515)) * **General Text CAPTCHA Solver** — Skyvern can now solve a wider range of text-based CAPTCHAs without site-specific configuration. ([#4517](https://github.com/Skyvern-AI/skyvern/pull/4517)) * **TOTP Webhook Retries** — TOTP webhook delivery now retries automatically on transient failures, reducing the rate of "no code received" errors during 2FA flows. ([#4518](https://github.com/Skyvern-AI/skyvern/pull/4518)) * **Block-Label Validation in `run_blocks`** — The `run_blocks` endpoint now validates block labels up front, returning a clear error instead of failing partway through execution. ([#4500](https://github.com/Skyvern-AI/skyvern/pull/4500)) * **Print PDF Block** — A new workflow block that prints the current page to PDF and saves it to your run's downloaded files, useful for archiving receipts, invoices, and reports. ([#4452](https://github.com/Skyvern-AI/skyvern/pull/4452)) * **HTTP File Downloads** — The HTTP Request block can now download files directly via HTTP (not just GET JSON), enabling workflows that pull artifacts from authenticated APIs. ([#4440](https://github.com/Skyvern-AI/skyvern/pull/4440)) * **Workflow Copilot Streaming with Cancel** — The Workflow Copilot now streams its responses with a cancel button, so you can stop generation mid-stream if you want to refine your prompt. ([#4437](https://github.com/Skyvern-AI/skyvern/pull/4437), [#4456](https://github.com/Skyvern-AI/skyvern/pull/4456)) * **"Execute on Any Outcome" (Finally) Block Option** — Blocks can now be configured to run regardless of whether prior blocks succeeded, enabling cleanup steps and "always send report" workflows. ([#4443](https://github.com/Skyvern-AI/skyvern/pull/4443)) * **Persistent Browser Session Uptime Billing** — Billing v2 now meters persistent browser session uptime separately, with PostHog feature flags controlling rollout. ([#4444](https://github.com/Skyvern-AI/skyvern/pull/4444)) * **GPT-5 Mini Flex Engine** — Added GPT-5 Mini Flex as an available LLM engine. ([#4432](https://github.com/Skyvern-AI/skyvern/pull/4432)) * **Clipboard Copy over HTTP** — The browser now exposes clipboard copy functionality that works in HTTP-served browser sessions, not just HTTPS. ([#4446](https://github.com/Skyvern-AI/skyvern/pull/4446)) ## Improvements * **Confirmation Dialog Shows Affected Blocks** — Deleting a parameter or block now lists every block that references it, so you don't accidentally break downstream logic. ([#4519](https://github.com/Skyvern-AI/skyvern/pull/4519)) * **Workflow Updates Return 409 on Race** — Concurrent workflow updates now return HTTP 409 instead of silently overwriting each other. ([#4510](https://github.com/Skyvern-AI/skyvern/pull/4510)) * **Tiktoken Caching** — Tokenizer instances are now cached, cutting per-step overhead on token counting. ([#4521](https://github.com/Skyvern-AI/skyvern/pull/4521)) * **HTTP Block Boolean and Integer Templates** — The HTTP Request block now correctly passes boolean and integer template values without coercing them to strings. ([#4435](https://github.com/Skyvern-AI/skyvern/pull/4435)) * **Bitwarden and Azure Vault Tooltips** — Added inline help tooltips explaining how to set up Bitwarden and Azure Key Vault credential sources. ([#4447](https://github.com/Skyvern-AI/skyvern/pull/4447)) * **Smaller S3 Objects Use STANDARD Tier** — Storage cost optimization: small artifacts now use STANDARD instead of GLACIER\_IR. ([#4453](https://github.com/Skyvern-AI/skyvern/pull/4453)) * **Reduced Max SVG Parsing** — Lowered the SVG parsing cap to prevent runaway memory usage on pathological pages. ([#4430](https://github.com/Skyvern-AI/skyvern/pull/4430)) ## Bug fixes * Fixed a Gemini 3 Flash cache-creation bug that caused false-positive fallback detection. ([#4502](https://github.com/Skyvern-AI/skyvern/pull/4502)) * Fixed Bitwarden item-ID format validation rejecting valid IDs. ([#4508](https://github.com/Skyvern-AI/skyvern/pull/4508)) * Fixed dangling block-output and parameter references after rename or deletion. ([#4507](https://github.com/Skyvern-AI/skyvern/pull/4507)) ## New features * **Workflow Copilot v1** — The first version of the Workflow Copilot ships behind a feature flag. Describe a workflow in natural language and the copilot generates blocks, parameters, and connections you can edit on the canvas. ([#4401](https://github.com/Skyvern-AI/skyvern/pull/4401), [#4413](https://github.com/Skyvern-AI/skyvern/pull/4413), [#4416](https://github.com/Skyvern-AI/skyvern/pull/4416), [#4423](https://github.com/Skyvern-AI/skyvern/pull/4423)) * **Per-Action Credit Billing (Billing v2)** — A new billing model meters credits per browser action instead of per step, giving more predictable cost behavior on action-heavy workflows. ([#4398](https://github.com/Skyvern-AI/skyvern/pull/4398)) * **Azure Key Vault Secret Storage** — Skyvern can now store and retrieve credentials from Azure Key Vault as a managed secret backend. ([#4384](https://github.com/Skyvern-AI/skyvern/pull/4384)) * **Conditional Inside Conditional** — Conditional blocks can now be nested inside other conditional blocks for richer branching logic. ([#4362](https://github.com/Skyvern-AI/skyvern/pull/4362)) * **Reference Workflow Output in Sub-Blocks** — Blocks can now reference upstream `workflow_output` variables, simplifying multi-stage workflows. ([#4414](https://github.com/Skyvern-AI/skyvern/pull/4414)) * **Browser Type Choice for Persistent Browser Sessions** — Persistent sessions now let you choose the browser type (Chromium, etc.) at create time. ([#4406](https://github.com/Skyvern-AI/skyvern/pull/4406)) * **Browser Extension Support for PBS** — Persistent browser sessions can launch with a specified browser extension. ([#4364](https://github.com/Skyvern-AI/skyvern/pull/4364)) * **Step Count in Webhooks and Run Payloads** — Webhook payloads and `get_run` responses now include `step_count` for cost reconciliation. ([#4410](https://github.com/Skyvern-AI/skyvern/pull/4410)) * **PH (Philippines) Proxy Location** — Added Philippines as a residential proxy option. ([#4395](https://github.com/Skyvern-AI/skyvern/pull/4395)) * **TextPromptBlock Artifact Storage** — TextPromptBlock now saves the LLM prompt and response as run artifacts for debugging. ([#4361](https://github.com/Skyvern-AI/skyvern/pull/4361)) * **Action–Screenshot Linking** — Actions in the run timeline now link directly to the screenshot captured at the time of execution, so you can see what the agent saw when it made each decision. ([#4403](https://github.com/Skyvern-AI/skyvern/pull/4403), [#4404](https://github.com/Skyvern-AI/skyvern/pull/4404)) ## Improvements * **Clearer Errors for Missing Workflow Parameters** — Missing required parameters now return a clear HTTP 400 instead of HTTP 500. ([#4380](https://github.com/Skyvern-AI/skyvern/pull/4380)) * **Empty-String Defaults for String Parameters** — Workflow string parameters without explicit defaults now initialize to `""` instead of `null`, matching common Jinja-template expectations. ([#4382](https://github.com/Skyvern-AI/skyvern/pull/4382)) * **HAR Files Use Zstd Compression** — HAR archives now ship as `.har.zst`, cutting storage size significantly with no fidelity loss. ([#4420](https://github.com/Skyvern-AI/skyvern/pull/4420)) * **Hydrated Workflow Title in Run Responses** — `workflow_run` responses now include the workflow title for cleaner logging without an extra API call. ([#4363](https://github.com/Skyvern-AI/skyvern/pull/4363)) * **Cached Workflow-Script Lookup** — `get_workflow_script_by_cache_key_value` is now cached and post-action execution can re-enable code generation. ([#4385](https://github.com/Skyvern-AI/skyvern/pull/4385)) * **Updated Datacenter Proxy Provider** — Datacenter proxies now route through a new provider with broader IP coverage. ([#4386](https://github.com/Skyvern-AI/skyvern/pull/4386)) * **Improved Conditional NL Branch Tooltip** — Updated tooltip and placeholder text on conditional blocks to better describe how natural-language branches are evaluated. ([#4368](https://github.com/Skyvern-AI/skyvern/pull/4368), [#4369](https://github.com/Skyvern-AI/skyvern/pull/4369)) * **OLLAMA Vision Support Toggle** — Added `OLLAMA_SUPPORTS_VISION` env var to enable vision-capable Ollama models. ([#4351](https://github.com/Skyvern-AI/skyvern/pull/4351)) ## Bug fixes * Fixed older credentials becoming inaccessible after an internal schema change. ([#4358](https://github.com/Skyvern-AI/skyvern/pull/4358)) * Fixed scrolling actions misfiring on pages with overflow-hidden ancestors. ([#4389](https://github.com/Skyvern-AI/skyvern/pull/4389)) * Fixed `close_browser_on_completion` not being honored during workflow run cleanup. ([#4381](https://github.com/Skyvern-AI/skyvern/pull/4381)) * Fixed run-ID generation collisions under high concurrency. ([#4383](https://github.com/Skyvern-AI/skyvern/pull/4383)) * Fixed empty browser-extension config crashing PBS launch. ([#4365](https://github.com/Skyvern-AI/skyvern/pull/4365)) * Fixed wrong screenshots being attached to certain actions. ([#4400](https://github.com/Skyvern-AI/skyvern/pull/4400)) * Fixed nested DB connection management in workflow execution. ([#4402](https://github.com/Skyvern-AI/skyvern/pull/4402), [#4411](https://github.com/Skyvern-AI/skyvern/pull/4411)) * Fixed `local variable not defined` errors in cached-action execution. ([#4376](https://github.com/Skyvern-AI/skyvern/pull/4376)) * Fixed artifacts endpoint incorrectly including `api/` in the path. ([#4417](https://github.com/Skyvern-AI/skyvern/pull/4417)) * Fixed S3 storage class selection for small objects (`_get_storage_class_for_org`). ([#4424](https://github.com/Skyvern-AI/skyvern/pull/4424)) * Fixed cached actions executing without a brief settling delay. ([#4418](https://github.com/Skyvern-AI/skyvern/pull/4418))
# API Key Source: https://www.skyvern.com/docs/cloud/account-settings/api-keys Find, copy, and use your Skyvern API key from the Cloud UI Settings page to authenticate REST API and SDK requests. Every API call to Skyvern requires an API key. The key identifies your organization and determines billing. ## Finding your API key Open **Settings** in the sidebar. Your API key is shown in a masked field. Click the **eye icon** to reveal the full value, or the **copy icon** to copy it to your clipboard. API key display with reveal and copy buttons Treat your API key like a password. Anyone with this key can create runs, read results, and manage agents on behalf of your organization. ## Using your key Every Skyvern API request requires the `x-api-key` header: ```bash theme={null} curl -X POST "https://api.skyvern.com/v1/run/tasks" \ -H "x-api-key: YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "url": "https://example.com", "prompt": "Extract the pricing table" }' ``` With the Python SDK: ```python theme={null} from skyvern import Skyvern client = Skyvern(api_key="YOUR_API_KEY") ``` Store the key in an environment variable (`SKYVERN_API_KEY`) rather than hardcoding it. In production, use your platform's secrets management (AWS Secrets Manager, Vault, etc.). Full endpoint documentation with interactive playground What an API key can reach, OAuth scopes, and how to isolate access Understand how runs are metered and billed # API Versioning & Deprecation Source: https://www.skyvern.com/docs/cloud/account-settings/api-versioning-and-deprecation Skyvern's API versioning scheme (URL path /v1/), what counts as a backward-compatible change, and the deprecation policy - 6 months minimum notice, Deprecation and Sunset response headers, and changelog announcements. Skyvern's REST API is versioned in the URL path. The current and only supported version is **v1**, served from `https://api.skyvern.com/v1/`. ```bash theme={null} curl -X POST "https://api.skyvern.com/v1/run/tasks" \ -H "x-api-key: YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "url": "https://example.com", "prompt": "Extract the pricing table" }' ``` ## How versioning works The major version appears once, as the first path segment. It never appears in a header, query parameter, or `Accept` media type. | Change type | How it ships | | - | - | | Backward-compatible change | Released into `v1` with no new version and no client action required | | Breaking change | Released under a new path prefix (`/v2/`), with `v1` kept alive through the deprecation window below | Skyvern does not use date-based or header-negotiated versions. If your client pins `https://api.skyvern.com/v1`, no deployment we make will change the shape of a response you already depend on. ## What counts as backward compatible Treat the following as expected within `v1`, and make sure your client tolerates them: * New endpoints and new HTTP methods on existing paths * New optional request parameters and request body fields * New fields in response bodies * New values in existing enums (for example, a new run status or failure reason) * New or reworded human-readable `detail` strings on error responses * Changes to the ordering of JSON object keys or of items in an unordered collection The practical rule: **ignore unknown fields rather than failing on them**, and treat an unrecognized enum value as "something newer than my client" instead of an error. ## What we will not do inside v1 These are breaking changes. They only ship in a new major version, never into `v1`: * Removing or renaming an endpoint, a request field, or a response field * Changing the type or format of an existing field * Making an optional parameter required, or adding a new required parameter * Removing a value from an enum * Changing the HTTP status code or error code for an existing failure mode * Changing the authentication a route requires ## Stability guarantees by surface | Surface | Stability | | - | - | | `https://api.skyvern.com/v1/*` | Stable and covered by this policy. Described by the [OpenAPI specification](/docs/api-reference/openapi.json) | | `/api/v1/*`, `/api/v2/*` | Legacy compatibility paths. Excluded from the OpenAPI specification and from this policy. Do not build new integrations on them; use `/v1/` | | Official SDKs (Python, TypeScript) | Semantic versioning, generated from the same OpenAPI specification. A major SDK bump can accompany an API major version | | MCP server (`https://api.skyvern.com/mcp`) | Tool names and arguments follow the same compatibility rules as `v1` endpoints | | Undocumented endpoints and fields | Anything absent from the OpenAPI specification and these docs is internal and may change without notice | ## Deprecation and sunset policy When we do deprecate part of the API, this is what you can count on: * **At least 6 months notice.** That is the minimum time between the deprecation announcement and the sunset date on which the endpoint stops serving traffic. Removing an entire major version gets at least 12 months. * **A changelog announcement** on the [Skyvern changelog](/docs/changelog), naming the affected endpoints, the replacement, and the sunset date. * **Machine-readable response headers** on every response from a deprecated endpoint, following [RFC 9745](https://www.rfc-editor.org/rfc/rfc9745.html) (`Deprecation`) and [RFC 8594](https://www.rfc-editor.org/rfc/rfc8594.html) (`Sunset`). * **`deprecated: true` in the OpenAPI specification** for the affected operation, parameter, or schema field, so generated clients and API tooling surface the warning automatically. * **No silent removals.** An endpoint that has not been announced, header-flagged, and given its full notice window will not be turned off. A response from a deprecated endpoint looks like this: ```http theme={null} HTTP/1.1 200 OK Deprecation: @1767225600 Sunset: Wed, 01 Jul 2026 00:00:00 GMT Link: ; rel="deprecation"; type="text/html" ``` `Deprecation` carries the moment the endpoint became deprecated, `Sunset` the moment it stops responding, and the `Link` header points at the announcement explaining the migration. No `/v1` endpoint is deprecated today, so these headers are not present on any current response. The two deprecations in flight are field-level and documented in place: the `title` query parameter on `GET /v1/agents` (use `search_key`) and `publish_workflow` on task creation. ## Building a client that survives changes * Pin the version prefix (`/v1/`), not a specific SDK patch release. * Parse responses leniently: ignore unknown fields, default unknown enum values to a safe branch. * Log any response carrying a `Deprecation` or `Sunset` header, and alert on it — that header is the earliest programmatic signal you will get. * Watch the [changelog](/docs/changelog) for announcements, and diff the [OpenAPI specification](/docs/api-reference/openapi.json) in CI if you generate your own client. ## Where changes are announced | Channel | What it carries | | - | - | | [Changelog](/docs/changelog) | Weekly entries: new features, improvements, fixes, and every deprecation announcement | | [OpenAPI specification](/docs/api-reference/openapi.json) | The authoritative machine-readable contract, including `deprecated` flags | | `Deprecation` / `Sunset` headers | Per-request signal on any deprecated endpoint | Questions about a migration: [support@skyvern.com](mailto:support@skyvern.com). # Authentication & Permissions Source: https://www.skyvern.com/docs/cloud/account-settings/authentication-and-permissions How Skyvern scopes access - organization-scoped API keys sent as x-api-key, OAuth 2.0 browser sign-in and its supported scopes, the hosted MCP server, and how to isolate access between environments and teams. Every Skyvern credential is scoped to **one organization**. There are two ways to authenticate, and both resolve to the same thing: full API access on behalf of that organization. | Method | Credential | How you send it | Best for | | - | - | - | - | | API key | Long-lived organization key | `x-api-key` header | Servers, CI, SDKs, scripts | | OAuth 2.0 | Access token from browser sign-in, refreshable | `Authorization: Bearer` header | MCP clients and AI assistants, apps acting for a signed-in user | ## API keys An API key is an organization-scoped bearer credential. Send it in the `x-api-key` header: ```bash theme={null} curl -X POST "https://api.skyvern.com/v1/run/tasks" \ -H "x-api-key: YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "url": "https://example.com", "prompt": "Extract the pricing table" }' ``` Find and copy your key from **Settings** in the Cloud dashboard, or at [app.skyvern.com/settings](https://app.skyvern.com/settings). ### What an API key can do The key identifies the organization it belongs to. Authorization is at that granularity and no finer: * It can call **every** documented endpoint that the organization can reach — create and cancel runs, read run history and artifacts, create and delete workflows, manage browser sessions and profiles, and read and write stored credentials. * Usage and cost are metered to that organization. * It carries no expiry of its own; it is valid until revoked. There are no read-only keys, per-endpoint keys, or per-resource keys today. Any API key grants full organization-level authority, so treat one like a root password: store it in a secrets manager, never commit it, and never ship it to a browser or mobile client. ### Isolating access Because scoping is per organization, the organization is the isolation boundary. To separate access: * Use **separate organizations** for separate blast radii — production versus staging, or one per customer or per team. * Rotate keys from **Settings** when someone with access leaves or a key may have leaked. Revoking a key immediately invalidates every client using it, including OAuth tokens issued against it. * Put outbound results behind [webhooks](/docs/developers/going-to-production/webhooks) with signature verification rather than handing a key to a third party so it can poll. ## OAuth 2.0 Skyvern Cloud is an OAuth 2.0 authorization server, backed by Clerk. It exists so MCP clients and AI assistants can authenticate a human with a browser sign-in instead of asking them to paste a static key into a config file. Discovery metadata is public: ```bash theme={null} curl https://api.skyvern.com/.well-known/oauth-authorization-server curl https://api.skyvern.com/.well-known/oauth-protected-resource ``` | Property | Value | | - | - | | Issuer | `https://clerk.skyvern.com` | | Authorization endpoint | `https://api.skyvern.com/oauth/authorize` | | Token endpoint | `https://api.skyvern.com/oauth/token` | | Revocation endpoint | `https://clerk.skyvern.com/oauth/token/revoke` | | Dynamic client registration | `https://clerk.skyvern.com/oauth/register` | | Grant types | `authorization_code`, `refresh_token` | | Response types | `code` | | PKCE | `S256` required | | Protected resource | `https://api.skyvern.com/mcp` | | Bearer methods | `header` | Clients that support MCP OAuth discovery — Claude Code, Claude Desktop, Cursor, Codex CLI, ChatGPT — need no client ID or client secret in their config; they register dynamically and open a browser for sign-in. See the [MCP server setup guide](/docs/developers/getting-started/mcp) for per-client commands. ### Supported scopes The authorization server advertises these `scopes_supported`: | Scope | Meaning | | - | - | | `openid` | OpenID Connect sign-in; issue an ID token | | `profile` | Basic profile claims (name) | | `email` | Email address claim | | `public_metadata` | Public user metadata claims | | `private_metadata` | Private user metadata claims | | `offline_access` | Issue a refresh token so the client can stay connected | | `user:org:read` | Read the signed-in user's organization membership | The protected-resource metadata for the MCP server narrows the advertised set to `profile` and `email`. These are **identity scopes, not API permission scopes.** They describe which claims about the signed-in user the token carries. They do not restrict which Skyvern endpoints or tools the token can reach. Once the authorization code is exchanged, the resulting access token authorizes as the organization the signed-in user belongs to, with the same organization-wide authority as an API key. Requesting fewer scopes does not produce a more restricted token. Access tokens expire and are refreshable with `offline_access`; a refresh token is single-use and rotated on every exchange, and replaying an old one revokes the whole token family. Revoking the organization's API key also invalidates tokens issued against it. ## MCP server The hosted Model Context Protocol server is at **`https://api.skyvern.com/mcp`**. It accepts either credential: * OAuth: `Authorization: Bearer ` * API key: `x-api-key: YOUR_API_KEY` You can narrow the **tool list** a client sees, either with a scoped URL or a header: ```bash theme={null} # Scoped URL https://api.skyvern.com/mcp/x/operate # Or the default URL plus a header X-Skyvern-Scope: operate ``` Valid values are `operate`, `build`, `browser`, `lean`, and `all`. Omitting the scope is identical to `all`. Tool scopes are a **usability filter, not an authorization boundary.** They change which tools the server advertises, so a smaller scope means a smaller, sharper tool list for the model — but the request still authenticates with the same organization-wide credential. Do not rely on a narrow scope to prevent a client from taking an action. ## Summary of the scoping model * **Organization** is the only authorization boundary. Every credential is bound to exactly one, and grants full access within it. * **API keys** are org-scoped bearer credentials with no sub-scopes, sent as `x-api-key`. * **OAuth scopes** control identity claims about the signed-in user, not API reach. * **MCP tool scopes** control the advertised tool catalog, not permissions. * To limit what a credential can touch, create a separate organization. Find, copy, and rotate your key in the Cloud dashboard Per-client OAuth and API-key setup for the hosted MCP server # Billing & Usage Source: https://www.skyvern.com/docs/cloud/account-settings/billing-usage Understand Skyvern's credit-based billing model, compare Free, Hobby, Pro, and Enterprise plans, and manage your subscription from the Cloud UI Billing page. Skyvern bills per **credit**: each browser action the AI takes during a run consumes credits. You pay for real work, not for agents created or credentials stored. ## Plans Open **Billing** in the sidebar to see available plans and your current balance. Billing page showing plan options and current balance | Plan | Price | Credits | Estimated actions | Concurrent runs | | - | - | - | - | - | | **Free** | \$0 | 5,000 one-time | \~200 | 1 | | **Hobby** | \$29/month | 30,000/month | \~1,200 | 10 | | **Pro** | \$149/month | 150,000/month | \~6,200 | 25 | | **Enterprise** | Custom | Unlimited | Unlimited | Unlimited | **Free** is available to all new accounts with a one-time credit grant and zero commitment. **Hobby** and **Pro** are monthly subscriptions. Click **Switch to Hobby** or **Switch to Pro** to change plans. Your remaining dollar balance is applied as a credit toward your first subscription payment. Need HIPAA compliance, SOC-2 reports, custom code blocks, or dedicated support? Use the **Book a call** link at the bottom of the Billing page to discuss **Enterprise**, or visit [skyvern.com/pricing](https://skyvern.com/pricing) for a complete feature comparison. ### What's included in each plan **5,000 one-time credits** (\~200 actions) Perfect for evaluating Skyvern and prototyping automations. * 1 concurrent run * Webhooks * Country geo-targeting * Community support **30,000 credits/month** (\~1,200 actions) • **\$29/month** * 10 concurrent runs * Basic CAPTCHA solver * Webhooks * Stored credentials * Country geo-targeting * Email support **150,000 credits/month** (\~6,200 actions) • **\$149/month** Everything in Hobby, plus: * 25 concurrent runs * Advanced CAPTCHA solver * Team workspaces * 2FA / TOTP support * 1Password integration * Residential proxy * City-level geo-targeting * Priority support **Unlimited credits** • **Custom pricing** Everything in Pro, plus: * Unlimited concurrent runs * HIPAA compliant infrastructure * SOC-2 Type II Report * Dedicated Slack channel * Azure Key Vault integration * Bitwarden integration * Custom code blocks * Human-in-the-loop agents [Contact sales](https://skyvern.com/contact) to discuss Enterprise. ## How credits are consumed A credit maps to one discrete browser action: clicking a button, typing into a field, selecting a dropdown, or extracting data from a page. Navigation counts too. | Example | Approximate credits | | - | - | | Login flow (email, password, submit) | \~3 | | Form fill (10 fields + submit) | \~11 | | Multi-page extraction (5 pages) | \~15–25 | Credits consumed by a run are visible on the [Run Details](/docs/cloud/viewing-results/run-details) page. The **Actions** counter at the top of the Overview timeline shows exactly how many actions the AI took. Reduce credit usage by being specific in your prompts. "Find information about pricing" causes the AI to explore multiple pages. "Extract the monthly price from the pricing table on /pricing" gets there directly. ## Your current balance The **Your Current Balance** section shows your remaining dollar balance. Credits are deducted as runs execute in real time. If your balance reaches zero, new runs won't start until you add credits or switch to a subscription plan. ## FAQ Each browser action the AI takes (clicking, typing, navigating, extracting) costs one credit. Credits are deducted in real time as runs execute. Free accounts receive a one-time credit grant. Paid plans include a monthly credit allowance that resets each billing cycle. Unused included credits don't roll over. Yes. If you exhaust your included allowance, you can purchase additional credits from the Billing page. You can also upgrade to a higher plan for a larger monthly allowance. Yes. Downgrade or cancel your subscription from the Billing page. The change takes effect at the end of your current billing cycle, and you keep access to your credits until then. Manage API keys for programmatic access Manage your team and organization details # Organization Settings Source: https://www.skyvern.com/docs/cloud/account-settings/organization-settings Manage your organization name, invite and remove team members, and configure access settings from the Skyvern Cloud UI Settings page. Everything in Skyvern (agents, credentials, runs, API keys) belongs to an **organization**. One is created automatically when you sign up. ## Organization details Open **Settings** in the sidebar. The Settings page shows your organization name and current plan. The organization name appears throughout the UI and in API responses. To rename your organization, update the **Organization Name** field and click **Save**. ## Team members Plans that support multiple users (Pro and Enterprise) show a **Members** section below the organization details. ### Inviting members Click **Invite Member**, enter their email address, and send the invitation. They'll receive an email with a link to join your organization. Once they accept, they appear in the members list with full access to agents, runs, credentials, and API keys. ### Removing members Click the **remove icon** next to a member's name to revoke their access. They lose access to all organization resources immediately. When removing a team member, also review your [API keys](/docs/cloud/account-settings/api-keys); they may have copied keys that remain active. Role-based access control (restricting what individual members can do) is available on **Enterprise** plans. On other plans, all members have full access to the organization's resources. Manage your personal account settings View and manage API keys for your organization # Profile Settings Source: https://www.skyvern.com/docs/cloud/account-settings/profile-settings Update your display name, change your password, and review active sessions from the Skyvern Cloud UI Account page. Click your avatar at the bottom of the sidebar to open the **Account** page. It has two tabs: **Profile** and **Security**. ## Profile The **Profile** tab shows your display name and email address. Update your display name and click **Save** to apply. ## Security The **Security** tab is where you manage your password and review active sessions. Account Security tab showing password fields and active devices Under **Set password**, enter your new password and confirm it. A green checkmark appears when the password meets requirements and both fields match. Check **Sign out of all other devices** if you want to invalidate existing sessions, recommended if you suspect unauthorized access. Click **Save** to apply. **Active devices** lists every device currently signed into your account, showing the browser, IP address, and last access time. Use this to verify that all sessions are yours. If you signed up with Google or another SSO provider, password management is handled by the external provider and this section may not appear. Manage your team and organization details View and manage API keys # Browser Profiles Source: https://www.skyvern.com/docs/cloud/browser-management/browser-profiles Save and reuse browser state snapshots in the Skyvern Cloud UI to skip login flows by restoring cookies and session data from a previously authenticated browser session. A **browser profile** is a saved snapshot of browser state: cookies, localStorage, and session files. Load a profile into a new [browser session](/docs/cloud/browser-management/browser-sessions) and the browser starts with that saved state restored, skipping login flows you've already completed. Profiles are ideal when you: * Run the same automation repeatedly with the same account (daily reports, scheduled data extraction) * Want to skip login steps that consume credits and time * Need multiple agents to share the same authenticated state Looking to manage profiles from code? See the [API & SDK guide](/docs/developers/optimization/browser-profiles) instead. *** ## How profiles are created Browser profiles are created automatically when you test a password credential with the **Save browser session** option enabled. There is no standalone "create profile" button; the profile is a byproduct of a successful login test. ### Creating a profile from a credential Click **Credentials** in the left sidebar under **General**. Click **+ Add → Password** to create a new credential, or click the **pencil icon** on an existing one. Enter the username and password. See [Password Credentials](/docs/cloud/managing-credentials/password-credentials) for details. Add password credential dialog with name, username, and password fields Below the password fields, enable the **Save browser session** option. Enter the **login URL** for the site (e.g., `https://app.example.com/login`). You can also add optional context to help the AI navigate the login flow. Click **Test**. Skyvern opens a browser, navigates to the login URL, signs in with the credential, and, if the login succeeds, saves the browser state as a profile. The profile is linked to this credential automatically. When the test completes, the credential row shows a **saved-profile** badge with the site hostname. This means the browser profile is ready to use. Credential listed with a profile badge The **Save browser session** flow is the easiest way to create a profile. It handles the full lifecycle: open browser, log in, save state. No agents or API calls required. *** ## When to refresh profiles Cookies and session tokens expire. A profile that worked last week may not work today if the site's authentication tokens have a short lifespan. **Signs a profile needs refreshing:** * Tasks that use the profile start failing with login-related errors * The browser loads a login page instead of the authenticated dashboard * The site forces re-authentication after a set period **To refresh:** go back to the credential, click **Test** again with **Save browser session** enabled. The new profile replaces the old one. For sites with short-lived sessions (banks, healthcare portals), refresh profiles before each batch of runs. For sites with long-lived cookies (most SaaS apps), weekly or monthly refreshes are usually sufficient. *** ## Sessions vs profiles | | Browser Session | Browser Profile | | - | - | - | | **What it is** | Live browser instance | Saved snapshot of browser state | | **Lifetime** | Minutes to hours | Days to months | | **State** | Current page, cookies, open connections | Cookies, localStorage, session files | | **Billing** | Charged while open | No cost when not in use | | **Best for** | Back-to-back tasks, human-in-the-loop | Repeated logins, scheduled agents | *** ## What's next Keep a browser open across multiple tasks Store the login details that profiles are built from Create and manage profiles programmatically # Browser Sessions Source: https://www.skyvern.com/docs/cloud/browser-management/browser-sessions Create and manage persistent browser sessions in the Skyvern Cloud UI to preserve cookies, login state, and page context across multiple tasks and agents. A **browser session** is a live browser instance that stays open between runs. Cookies, login state, cart contents, and page context all persist, like keeping a browser tab open. Use sessions when you need back-to-back tasks to share state, or when you want to interact with the browser yourself between automated steps. Looking to use browser sessions from code? See the [API & SDK guide](/docs/developers/optimization/browser-sessions) instead. *** ## The Browsers page Click **Browsers** in the left sidebar to open the Browsers page. It lists all browser sessions in your organization. Browsers page with the sessions table showing columns for ID, open status, occupied status, started time, timeout, and CDP URL Each row shows: | Column | What it shows | | - | - | | **ID** | Session identifier (starts with `pbs_`) | | **Open** | Whether the browser is currently running | | **Occupied** | Whether a task or agent is actively using the session | | **Started** | When the session launched | | **Timeout** | How long the session stays open before auto-closing | | **CDP URL** | Chrome DevTools Protocol address for direct connection | *** ## Creating a session Click the **Create Browser Session** button at the top of the Browsers page. A panel opens with the following settings: Create Browser Session panel showing fields for timeout, proxy location, browser type, extensions, and browser profile | Setting | What it does | | - | - | | **Timeout** | How long the session stays open, in minutes. Min: 5; max: 240 (4 hours) — requests above 240 are capped at 240 with a warning. A running session can be extended through the API up to 360 minutes (6 hours); see [extend\_browser\_session](/docs/sdk-reference/browser-sessions/extend-browser-session). Longer durations are available on the enterprise plan (contact [sales@skyvern.com](mailto:sales@skyvern.com)). Default: 60. | | **Proxy Location** | Route the browser through a residential proxy in a specific country. Default: US. | | **Browser Type** | Chrome (default, widest compatibility) or Microsoft Edge. | | **Extensions** | Optional add-ons: **Ad Blocker** (removes overlay ads that interfere with clicks) and **Captcha Solver** (auto-solves CAPTCHAs). | | **Browser Profile** | Load a saved [browser profile](/docs/cloud/browser-management/browser-profiles) to restore cookies and login state from a previous session. | Click **Create** to launch the session. It appears in the table within a few seconds. Sessions bill while open, even when idle. Set the timeout to match your use case and close sessions when you're done. *** ## Viewing a live session Click any session row in the table to open its detail page. The detail page has three tabs: ### Stream A live view of the browser. You can watch pages load and actions fire in real time. Click on Take Control to interact with the browser yourself. Use this to log in, dismiss a popup, solve a CAPTCHA. Browser session detail page with the Stream tab active, showing a live browser view and session controls ### Recordings Video recordings of activity in the session. Each recording captures what happened during a task or agent that ran inside this session. ### Downloads Files downloaded by the browser during the session. Click any file to save it locally. Browser session download page with the preview or download links for anything downloaded during the session *** ## Using a session with a task Once you have a running session, you can run tasks inside it from the [Discover page](/docs/cloud/getting-started/run-a-task): 1. Copy the session ID (`pbs_...`) from the Browsers page 2. Go to the **Discover** page 3. Click the **gear icon** to open Advanced Settings 4. Paste the ID into the **Browser Session ID** field 5. Write your prompt and run The task executes inside your existing session. Cookies, login state, and page context from previous tasks are still there. Advanced settings panel on the Discover page with a pbs_ session ID entered in the Browser Session ID field *** ## Using a session with an agent You can also run agents inside an existing session: 1. Copy the session ID from the Browsers page 2. Go to **Agents** and click **Run** on your agent 3. On the parameters page, scroll to **Run Settings** 4. Paste the ID into the **Browser Session ID** field 5. Click **Run Agent** The agent picks up where the browser left off: same page, same cookies, same form data. Agent run settings panel with a pbs_ session ID entered in the Browser Session ID field *** ## Closing a session From the session detail page, click **Stop**. A confirmation dialog appears. The browser shuts down immediately and the session moves to `closed` status. Stop browser session confirmation dialog with Cancel and Stop buttons Sessions also close automatically when their timeout expires, **even if a task is still running**. Set timeouts with enough margin for your longest expected task. Closed sessions cannot be reopened, and a session only saves its browser state at close when profile generation is enabled for it. The **Save browser session** credential flow handles this automatically; for API-created sessions, see [Save a session's profile](/docs/developers/optimization/browser-sessions#save-a-sessions-profile). If you need the same login state later, capture it as a [browser profile](/docs/cloud/browser-management/browser-profiles) before closing. *** ## When to use sessions vs agents If your steps run back-to-back with no pauses between them, an [agent](/docs/cloud/building-agents/build-an-agent) is more efficient. Agent blocks share one browser instance with no inter-step startup cost. Sessions are the right choice when you need: * **Pauses between steps**: review results, get approval, or wait for external input before continuing * **Human-in-the-loop**: interact with the browser yourself between automated steps * **Ad-hoc sequences**: run different tasks one after another without pre-building an agent *** ## Sessions vs profiles | | Browser Session | Browser Profile | | - | - | - | | **What it is** | Live browser instance | Saved snapshot of browser state | | **Lifetime** | Minutes to hours | Days to months | | **State** | Current page, cookies, open connections | Cookies, localStorage, session files | | **Billing** | Charged while open | No cost when not in use | | **Best for** | Back-to-back tasks, human-in-the-loop | Repeated logins, scheduled agents | Use a session when you need a live browser right now. Use a [profile](/docs/cloud/browser-management/browser-profiles) when you want to save login state and reuse it later. *** ## What's next Save login state and reuse it across sessions Create and manage sessions programmatically # Agent Parameters Source: https://www.skyvern.com/docs/cloud/building-agents/add-parameters Define input and credential parameters in the Skyvern Cloud UI agent editor to pass dynamic values like URLs, JSON data, and vault credentials into agents at runtime. Parameters let you create reusable agents that accept different input values each time they run. Instead of hardcoding a URL or search term into a block, you reference a parameter and fill in the value when you run the agent. This page covers parameters in the Cloud UI agent editor. If you're building automations in code, parameters are just function arguments. See [Browser Automation](/docs/developers/browser-automations/overview) for the code-first approach. *** ## Opening the parameters panel In the [agent editor](/docs/cloud/building-agents/build-an-agent), click the **Parameters** button in the header bar. A panel appears below the header showing all defined parameters and controls to add new ones. Parameters panel *** ## Adding a parameter Click **Add Parameter** in the panel. Two types are available: | Type | Use for | | - | - | | **Input Parameter** | Values the user provides when running the agent (text, numbers, JSON, etc.) | | **Credential Parameter** | Securely inject login credentials from a vault (Bitwarden, 1Password, Azure, AWS, or Skyvern) | Each parameter requires a unique **key**. This is the name you use to reference it in blocks. Keys cannot contain spaces and cannot use [reserved names](#reserved-variables). You can also add an optional **description** (shown as help text when running) and a **default value**. *** ## Parameter value types Input parameters support these value types: | Type | Input control | Example | | - | - | - | | **String** | Text field | `"https://example.com"` | | **Integer** | Number field | `10` | | **Float** | Number field | `19.99` | | **Boolean** | Toggle switch | `true` | | **JSON** | Code editor | `{"key": "value"}` | | **File URL** | Text field (paste a URL) | `"https://example.com/data.csv"` | | **Credential ID** | Dropdown selector (shown at runtime) | Selected from stored credentials | *** ## Referencing parameters in blocks Use Jinja2 double-brace syntax to reference parameters inside block fields like prompts, URLs, and data schemas. **Basic reference:** ``` {{ url }} ``` **Nested field access** (for JSON parameters): ``` {{ config.search_term }} ``` **Convert to JSON string:** ``` {{ my_data | tojson }} ``` **Example in a Navigation block prompt:** ``` Navigate to {{ url }} and search for {{ search_term }} ``` Any block field that accepts text supports parameter references. *** ## Credential parameters Credential parameters securely inject login credentials into blocks without exposing them in prompts or logs. | Source | What it provides | | - | - | | **Skyvern Credential** | Username and password stored on the Skyvern Credentials page | | **Bitwarden Login** | Username, password, and optional TOTP from your Bitwarden vault | | **Bitwarden Credit Card** | Card number, holder name, expiry, and CVV from Bitwarden | | **Bitwarden Sensitive Information** | Sensitive data fields from Bitwarden | | **1Password** | Username, password, card data, or TOTP from 1Password | | **Azure Key Vault** | Secrets stored in Azure Key Vault | | **AWS Secret** | Secrets stored in AWS Secrets Manager | | **Azure Secret** | Secrets stored in Azure Secret | When you add a credential parameter, you configure the source and connection details (collection ID, vault ID, etc.). At runtime, Skyvern fetches the real credentials from the vault and injects them into the agent. Credential values are masked in logs and outputs. *** ## Output parameters Every block automatically produces an **output parameter** containing its results. You can reference a previous block's output in any downstream block. The syntax uses the block's label (lowercased, spaces replaced with underscores) followed by `_output`: ``` {{ extraction_block_output.extracted_information }} ``` ``` {{ login_output.success }} ``` This is how you chain data between blocks. Extract data in one block, then use it in the next. *** ## Reserved variables These variable names are built-in and cannot be used as parameter keys: | Variable | Available in | Description | | - | - | - | | `current_value` | Loop blocks | The current item being iterated | | `current_item` | Loop blocks | Alias for `current_value` | | `current_index` | Loop and While Loop blocks | Zero-based index of the current iteration | | `workflow_run_id` | All blocks | Unique ID of the current run | | `workflow_id` | All blocks | The workflow's ID | | `workflow_permanent_id` | All blocks | The workflow's permanent ID | | `workflow_title` | All blocks | The workflow's title | **Example in a loop:** ``` Process item {{ current_index }}: {{ current_value.name }} ``` *** ## What's next Configuration fields for every block type Execute agents and fill in parameter values # Build an Agent Source: https://www.skyvern.com/docs/cloud/building-agents/build-an-agent Create multi-step browser automations in the Skyvern Cloud UI using the visual agent editor with blocks for navigation, extraction, loops, conditionals, and email. Agents are multi-step automations built visually in the Cloud UI. You drag blocks onto a canvas, wire them together, configure each one, and run the whole sequence with a click. No code required. Agents can be versioned, shared across your team, scheduled on a cron, and run with different parameters each time. If you prefer writing automation code in Python or TypeScript, see [Browser Automation](/docs/developers/browser-automations/overview) in the developer docs. Both approaches handle multi-step work across pages. Agents are the visual path, browser automations are the code path. **Agents vs. Browser Automation:** Agents are defined in this visual editor and run from the Cloud UI (or [triggered from code](/docs/cloud/building-agents/run-from-code)). Browser automations are written in Python/TypeScript using Page, Agent, and Browser. Choose based on whether your team prefers a visual editor or a code editor. This page explains how agents work, walks you through building one from scratch, and covers the editor's features. ## How agents work An agent is a sequence of **blocks** that run one after another. Each block does one thing: navigate to a page, extract data, send an email, run custom code, loop, or branch. You connect blocks on a visual canvas, pass data between them, and run the whole chain with one click. ``` [Browser Task] → [Extraction] → [Loop] → [Send Email] ↓ ↓ ↓ ↓ opens the page JSON output per-item digest sent processing ``` ### How data flows between blocks Every block produces an output. Downstream blocks reference it using the pattern `{{ block_label_output }}`. For example, an Extraction block labeled `scrape_listings` produces output that later blocks access as `{{ scrape_listings_output }}`. The label is lowercased with spaces replaced by underscores, then `_output` is appended. This is how you chain steps together. One block's output becomes the next block's input. ### Block categories | Category | What it does | Examples | | - | - | - | | **Browser Automation** | Interact with web pages using AI | Browser Task, Browser Action, Extraction, Login, Go to URL, Print Page | | **Data and Extraction** | Transform data without a browser | Text Prompt, File Parser | | **Control Flow** | Branch, loop, validate, or pause | Loop, While Loop, Conditional, AI Validation, Code, Wait | | **Files** | Download and upload files | File Download, Cloud Storage Upload | | **Communication** | Send data to external services or humans | Send Email, HTTP Request, Human Interaction | See [Block Reference](/docs/cloud/building-agents/configure-blocks) for every block type and its configuration fields. If your block needs a browser, pick a browser automation block. If it just needs to process data, use Text Prompt or Code. If you need to repeat or branch, use control flow. *** ## Tutorial: Build a job listing tracker Let's build a real agent. You'll create an automation that finds the top 5 job listings from Hacker News's monthly "Who is Hiring" thread, summarizes each one, and emails you a digest. This uses 5 blocks across 3 categories: browser automation, data and extraction, and communication. Go to **Agents** in the left sidebar and click **Create → Blank Agent**. Create agent dropdown showing Blank Agent and From Template options The editor opens with an empty canvas showing a single start node. Click the agent title at the top left and rename it to **HN Job Tracker**. Hover over the **+** button on the edge below the start node and select **Add Block**. A searchable block library opens on the right. Find and select **Browser Task Block**. The block appears on the canvas with a configuration panel on the right. Fill in: | Field | Value | | - | - | | **Label** | `find_hiring_thread` | | **URL** | `https://news.ycombinator.com` | | **Prompt** | `Find and open the latest monthly "Ask HN: Who is hiring?" thread. The task is complete when the thread is open and job listing comments are visible.` | The Browser Task block uses AI to navigate the page and accomplish the goal described in your prompt. Include your success criteria directly in the prompt so the AI knows when it's done. Browser Task block configured with find_hiring_thread label, URL, and prompt The URL for the latest hiring thread changes every month. The Browser Task block uses AI to find the right link on the page. Use Go to URL when you know the exact destination URL upfront. Hover over the **+** on the edge after `find_hiring_thread`, select **Add Block**, then choose **Extraction Block**. Configure: | Field | Value | | - | - | | **Label** | `scrape_listings` | | **Data Extraction Goal** | `Extract the top 5 job listings. For each listing, get the company name, role title, and a brief description of the position.` | Now enable the **Data Schema** checkbox to reveal the JSON editor, and paste: ```json theme={null} { "type": "object", "properties": { "listings": { "type": "array", "items": { "type": "object", "properties": { "company": { "type": "string" }, "role": { "type": "string" }, "description": { "type": "string" } } } } } } ``` The schema tells Skyvern exactly what structure to return. Without it, the AI picks its own format. You can also click **Generate with AI** next to the schema field to have Skyvern suggest a schema based on your extraction goal. Extraction block configured with scrape_listings label, extraction goal, Data Schema checkbox enabled, and JSON schema Label your blocks descriptively. The label determines the output variable name. `scrape_listings` means downstream blocks reference its data as `{{ scrape_listings_output }}`. Hover over the **+** after `scrape_listings`, select **Add Block**, then choose **Loop Block**. Configure the loop: | Field | Value | | - | - | | **Label** | `process_each` | | **Loop Value** | `{{ scrape_listings_output.extracted_information.listings }}` | This iterates over the 5 listings extracted in the previous step. Now add a block *inside* the loop. Hover over the **+** inside the loop body, select **Add Block**, and choose **Text Prompt Block**. Configure the Text Prompt: | Field | Value | | - | - | | **Label** | `summarize` | | **Prompt** | `Summarize this job listing in one sentence. Company: {{ current_value.company }}, Role: {{ current_value.role }}, Description: {{ current_value.description }}` | Enable the **Data Schema** checkbox and paste: ```json theme={null} { "type": "object", "properties": { "summary": { "type": "string" } } } ``` The Text Prompt block sends text to the LLM without opening a browser. It processes data only. Each iteration produces a one-line summary of that job listing. Loop block with process_each label containing a summarize Text Prompt block inside Inside a loop, two reserved variables are available: * `{{ current_value }}`: the current item from the list being iterated * `{{ current_index }}`: the item's position, starting from 0 These only exist inside loop blocks. In this example, `{{ current_value.company }}` gives you the company name for the current listing. Hover over the **+** on the edge *after* the loop (back on the main flow, not inside it), select **Add Block**, then choose **Send Email Block**. Configure: | Field | Value | | - | - | | **Label** | `send_digest` | | **Recipients** | Your email address | | **Subject** | `HN Job Digest - Top 5 Listings` | | **Body** | `Here are today's top job listings from Hacker News:\n\n{{ process_each_output }}` | The `{{ process_each_output }}` reference pulls in the collected summaries from every loop iteration. Agents are **not** auto-saved. Click the **Save** button (disk icon) in the header bar before navigating away or you'll lose your work. Click **Save**, then click **Run** in the top right. A parameters page opens where you can review and confirm the agent's settings. Click **Run Agent** to start execution. The [live execution view](/docs/cloud/getting-started/monitor-a-run) opens. Watch as Skyvern navigates Hacker News, extracts listings, summarizes each one, and sends your email. ### What you built ```mermaid theme={null} flowchart LR A["find_hiring_thread
Browser Task"] --> B["scrape_listings
Extraction"] B --> C["process_each
Loop"] C --> D["summarize
Text Prompt"] D --> E["send_digest
Send Email"] ``` Five blocks, three categories, zero code. You can now re-run this agent anytime, tweak the extraction schema to pull different fields, swap the email for an HTTP Request to post to Slack, or add a Conditional block to only email when listings match certain criteria. *** ## Editor reference ### Layout Agent editor overview | Area | What it shows | | - | - | | **Header bar** (top) | Agent title (click to rename), Parameters button, Save button, Template toggle, History button, Run button | | **Canvas** (center) | Visual graph of blocks connected in sequence. Zoom with the scroll wheel, pan by dragging the background. | | **Configuration panel** (right) | Opens when you click a block. Shows that block's settings form. | ### Adding blocks Hover over the **+** button on any edge (the connecting line between blocks) to reveal the menu. Select **Add Block** to open the block library, a searchable list of all available block types. Click a block to insert it at that position. The menu also offers **Record task** (record actions in a live browser to generate blocks) and **Upload SOP** (upload a PDF procedure to auto-generate an agent). When you create a blank agent, hover over the **+** on the start edge to add your first block. Add block panel ### Configuring blocks Click any block on the canvas to open its configuration panel on the right. Each block has a **Label** field (which determines its output variable name) and block-specific settings. Browser-based blocks share additional fields like URL, Engine, and Max Retries. See [Block Reference](/docs/cloud/building-agents/configure-blocks) for the full list of fields on each block type. ### Connecting and reordering blocks Blocks auto-connect when you insert them via the **+** button. They execute top to bottom in the order shown on the canvas. **Conditional blocks** create branches. Each branch connects to a different sequence of blocks and merges back at a common point. **Loop blocks** contain child blocks that repeat for each item in the loop's list. **While Loop blocks** contain child blocks that repeat while their condition remains true. To reorder blocks, delete the block you want to move and re-add it at the desired position using the **+** button. ### Deleting blocks Click the **three-dot menu** on a block's header and select **Delete Block**. Downstream blocks reconnect to the previous block automatically. ### Saving Agents are **not** auto-saved. Click the **Save** button (disk icon) in the header bar to persist your changes. The editor warns you if you try to navigate away with unsaved work. The **Run** button also saves before starting execution. ### Header bar actions | Button | Description | | - | - | | **Save** (disk icon) | Save the current agent definition | | **Template** (bookmark icon) | Toggle whether this agent is saved as an organization template | | **History** (clock icon) | View past runs of this agent | | **Schedule** (clock icon) | Create or manage recurring schedules for this agent (see [Create a Schedule](/docs/cloud/building-agents/scheduling)) | | **Parameters** | Open the parameters panel (see [Agent Parameters](/docs/cloud/building-agents/add-parameters)) | | **Run** (play icon) | Save and start a new execution (see [Running Agents](/docs/cloud/building-agents/run-an-agent)) | *** ## What's next Configuration fields for every block type Pass dynamic values into your agents Execute agents and track results Set up recurring cron-based execution # Block Types and Configuration Source: https://www.skyvern.com/docs/cloud/building-agents/configure-blocks Reference guide for every agent block type in the Skyvern Cloud UI, including Browser Task, Extraction, Login, Loop, While Loop, Conditional, Code, HTTP Request, and more. Agents are built from blocks. Each block performs one specific operation: navigating a page, extracting data, making an API call, or branching logic. This page covers every block type available in the Cloud UI [agent editor](/docs/cloud/building-agents/build-an-agent), grouped by category. If you're writing automations in code instead, the equivalent operations are Page and Agent methods. See the [Actions Reference](/docs/developers/browser-automations/actions-reference) for the code-first counterparts to these blocks. how to add a block to an agent in Skyvern ## Quick reference | Category | Blocks | | - | - | | [Browser Automation](#browser-automation) | Browser Task, Browser Action, Extraction, Login, Go to URL, Print Page | | [Data and Extraction](#data-and-extraction) | Web Search, Text Prompt, File Parser | | [Control Flow](#control-flow) | Loop, While Loop, Conditional, AI Validation, Code, Wait | | [Files](#files) | File Download, Cloud Storage Upload | | [Communication](#communication) | Send Email, HTTP Request, Human Interaction | *** ## Common fields These fields appear on most blocks: | Field | Description | | - | - | | **Label** | Display name on the canvas. Also determines how downstream blocks reference this block's output (`{{ label_output }}`). | | **Continue on Failure** | Allow the agent to continue if this block fails | | **Next Loop on Failure** | Only inside loops. Skip to the next iteration on failure. | | **Model** | Override the default LLM model for this block (Advanced Settings on most blocks) | Browser-based blocks (Browser Task, Browser Action, Extraction, Login, File Download) share these additional fields: | Field | Description | | - | - | | **URL** | Starting URL. Leave blank to continue from the previous block's page. | | **Engine** | AI engine. Skyvern 1.0 is the default for new browser blocks. | | **Max Steps Override** | Cap the number of AI reasoning steps | | **Disable Cache** | Skip cached script execution | | **TOTP Identifier** | Link TOTP credentials for 2FA handling | | **TOTP Verification URL** | Endpoint this block polls when it needs a 2FA code | | **Error Code Mapping** | Map error conditions to custom error codes (JSON) | Set **TOTP Verification URL** on the block that may encounter 2FA. Top-level workflow run `totp_url` values do not automatically populate empty block fields. *** ## Browser Automation ### Browser Task The primary block for browser automation. Accepts a natural-language prompt and autonomously navigates the browser to accomplish the goal. The block uses Skyvern 1.0 by default. Existing agents that already contain V2 browser blocks remain editable and may show a reduced field set. **Skyvern 1.0:** | Field | Type | Description | | - | - | - | | **URL** | text | Starting URL (optional) | | **Prompt** | text | Natural language instructions for the AI | **Existing V2 blocks:** | Field | Type | Description | | - | - | - | | **URL** | text | Starting URL (optional) | | **Prompt** | text | Natural language instructions for the AI | | **Max Steps** | number | Maximum AI steps | | **Disable Cache** | boolean | Skip cached script execution | Additional fields in **Advanced Settings** (Skyvern 1.0 only): | Field | Type | Description | | - | - | - | | **Complete if...** | text | Condition that signals the block is done | | **Include Action History in Verification** | boolean | Include prior actions when verifying completion | | **Complete on Download** | switch | Mark the block as complete when a file download occurs | | **File Name** | text | Custom filename for downloaded files | *Plus [common browser fields](#common-fields).* Browser Task block configuration with URL and prompt fields Browser Task is the recommended block for most browser automation. Use it for anything from form filling to multi-page navigation. Include your success criteria directly in the prompt so the AI knows when it's done. ### Browser Action Execute a single browser action. Best for precise, one-step operations like clicking a specific button or entering text in a field. | Field | Type | Description | | - | - | - | | **URL** | text | Starting URL (optional) | | **Action Instruction** | text | Specify the single action to perform | Additional fields in **Advanced Settings:** | Field | Type | Description | | - | - | - | | **Complete on Download** | switch | Mark the block as complete when a file download occurs | | **File Name** | text | Custom filename for downloaded files | *Plus [common browser fields](#common-fields).* ### Extraction Extract structured data from the current page using AI. | Field | Type | Description | | - | - | - | | **Data Extraction Goal** | text | What data to extract | | **Data Schema** | JSON | [JSON Schema](https://json-schema.org/) defining the output format. Enable the checkbox to reveal the editor. Click **Generate with AI** to auto-suggest a schema from your extraction goal. | *Plus [common browser fields](#common-fields).* Extraction block configuration with Data Extraction Goal and Data Schema fields ### Login Authenticate to a website using stored credentials. Pre-filled with a default login goal that handles common login flows including 2FA. | Field | Type | Description | | - | - | - | | **URL** | text | Login page URL | | **Login Goal** | text | Login instructions (pre-filled with a comprehensive default) | | **Credential** | selector | Select stored credentials for authentication | Additional fields in **Advanced Settings:** | Field | Type | Description | | - | - | - | | **Complete if...** | text | How to know login succeeded | *Plus [common browser fields](#common-fields).* Login block configuration with URL, Login Goal, and Credential fields ### Go to URL Navigate the browser directly to a specific URL without AI interaction. | Field | Type | Description | | - | - | - | | **URL** | text | **(Required)** The URL to navigate to. Supports [parameter references](/docs/cloud/building-agents/add-parameters#referencing-parameters-in-blocks). | Go to URL block configuration with URL field ### Print Page Print the current browser page to a PDF file. The PDF is saved as a downloadable artifact. | Field | Type | Description | | - | - | - | | **Page Format** | select | Paper size: A4, Letter, Legal, or Tabloid | | **Print Background** | boolean | Include CSS background colors and images in the PDF | | **Headers & Footers** | boolean | Add date, title, URL, and page numbers to the PDF | Additional fields in **Advanced Settings:** | Field | Type | Description | | - | - | - | | **Custom Filename** | text | Custom name for the generated PDF | | **Landscape** | boolean | Use landscape orientation | Print Page block configuration with page format, print background, and headers & footers options *** ## Data and Extraction ### Web Search Search Google or Exa over an API. Add `site:example.com` to the query to search within a site. This block does not open a browser or read linked pages. Google supports site restrictions. With a single `site:domain` or `site:domain/path` filter, the block removes results outside the filter. It repeats the search up to twice when Google returns only results outside that filter. It does not filter queries with quotation marks, parentheses, `|`, `OR`, or multiple `site:` filters. Exa supports one positive `site:domain` filter. Unsupported Exa expressions fail instead of expanding the search. | Field | Type | Description | | - | - | - | | **Search Query** | text | Required query. Supports input and output parameter references. | | **Search Provider** | selector | Automatic (default), Google, or Exa. Google uses SerpAPI. | | **Maximum Results** | integer | Between 1 and 100; default 10. The provider may return fewer results. | | **Prompt** | text | Optional instructions to summarize, rank, extract, or transform results. | | **Model** | selector | Model for Prompt, Data Schema, and error detection. | | **Data Schema** | JSON | Optional output shape. Works with or without a Prompt. | | **Error Messages** | mapping | Error codes and descriptions that the model checks against the outcome. | Automatic starts with Google. It tries Exa only if Google fails before returning results and the server has an Exa key. Empty results do not trigger fallback. Selecting Google or Exa uses only that provider. A Prompt receives the normalized results, including an empty list. Without a Data Schema, its answer is text. A Data Schema alone asks the model to return the results in that shape. The answer is stored in `prompt_output`. Invalid schemas are rejected when you save. Schemas with parameter references are checked after those references are filled in. A response that fails validation retries once before the block fails. Leave Prompt and Data Schema blank to skip result processing. Error Messages still make an LLM call when configured on the block or workflow. Block entries override workflow entries with the same code. The model checks results, processed answers, and block failures against those descriptions, including failures before the search starts. A successful search completes when no error code matches, including when it returns zero results. A matching code terminates a successful search. If the search or Prompt fails or times out, a matching code attaches to that failure without changing its status or system failure reason. If error detection fails, the block keeps the search outcome without a code. The old `no_results_error_code` and `no_match_error_code` fields are deprecated. Saved values are read as Error Messages. They describe empty results and results that do not satisfy the Prompt. An explicit Error Messages entry with the same code takes precedence. The output always includes: * `query`: the rendered query, or the configured query if rendering fails. * `provider`: `google` or `exa`. * `results`: objects with `title`, `link`, `snippet`, `display_link`, and one-based `position`. * `total_count`: the number of returned results. * `prompt_output`: null, text, or the JSON value defined by Data Schema. * `raw_response.pages`: provider responses, with credentials removed. With Exa, a result's `snippet` is empty when Exa has no cached copy of the page or when the request for page highlights fails. For example, use `{{ web_search_1_output.results }}` in a downstream block. A later page failure keeps validated partial results and completes the search. A Prompt failure keeps those results but fails the block. Failed and terminated outputs also include `status`, `failure_reason`, and `errors`. They carry a `failure_category`. For execution denials, such as insufficient credits, its value is `null`. Detected codes appear in the run's `errors` list with their explanations. Enable **Continue on Failure** to let the next block inspect the output. The Search failure category applies to the run only when the block ends it. A terminated Search block shows its failure reason in the timeline instead of the result count. ```yaml theme={null} block_type: web_search label: web_search_1 query: "site:example.com annual report" provider: auto num_results: 10 prompt: null json_schema: null error_code_mapping: null ``` Skyvern Cloud supplies provider credentials. Self-hosted installations configure `SERPAPI_API_KEY` and `EXA_API_KEY` in the server environment. Google pagination can use multiple API searches for a single block run. *** ### Text Prompt Send text to the LLM for processing without browser interaction. Useful for summarizing, transforming, or analyzing data between browser steps. | Field | Type | Description | | - | - | - | | **Prompt** | text | The text prompt to send to the LLM | | **Model** | selector | Which LLM model to use | | **Data Schema** | JSON | Expected output structure. Enable the checkbox to reveal the editor. Click **Generate with AI** to auto-suggest a schema. | Text Prompt block configuration with Prompt, Model, and Data Schema fields ### File Parser Parse PDFs, CSVs, Excel files, images, DOCX files, and ZIP archives. ZIP inputs are unzipped, and the block outputs the extracted file list as `file_name`, `file_path`, and `file_size`. Data Schema is ignored for ZIP inputs; loop over the file list and pass each `file_path` to another File Parser block to parse individual files. Very large files can exceed the parser's time budget and fail the block. When a File Parser sits inside a loop, set **On block failure** (Advanced Settings) to *Skip to next iteration* so files that cannot be parsed are skipped and the rest of the list still runs. | Field | Type | Description | | - | - | - | | **File URL** | text | URL or parameter reference to the file | | **Data Schema** | JSON | Schema for the extracted output. Enable the checkbox to reveal the editor. | | **Model** | selector | Which LLM model to use | File Parser block configuration with File URL, Data Schema, and Model fields *** ## Control Flow ### Loop Repeat a sequence of blocks for each item in a list. Child blocks are placed inside the loop on the canvas. | Field | Type | Description | | - | - | - | | **Loop Value** | text | The list to iterate over. Use a parameter reference (e.g., `{{ my_list }}`) or a natural language description (e.g., "Extract links of the top 5 posts") which triggers automatic extraction. | | **Continue if Empty** | boolean | Mark the loop as complete if the list is empty | Inside loop blocks, use these [reserved variables](/docs/cloud/building-agents/add-parameters#reserved-variables): * `{{ current_value }}`: the current item * `{{ current_index }}`: the iteration number (0-based) Loop block configuration Use Loop when the item list is already known before the loop starts, such as rows extracted from a table, files uploaded by a user, or URLs passed as agent parameters. ### While Loop Repeat a sequence of blocks while a condition remains true. Child blocks are placed inside the loop on the canvas. | Field | Type | Description | | - | - | - | | **Condition** | expression | Jinja2 template or natural-language prompt evaluated before each iteration | Inside while-loop blocks, use these [reserved variables](/docs/cloud/building-agents/add-parameters#reserved-variables): * `{{ current_index }}`: the iteration number (0-based) Use While Loop for flows where the number of iterations is discovered during the run, such as pagination, polling, or retrying until a recoverable page state clears. For pagination, a common pattern is to extract a `has_next_page` boolean inside the loop, click Next, and let the next condition check decide whether to continue. ### Conditional Branch the agent based on conditions. The UI shows branches as tabs (A, B, C, etc.). Each branch has an expression that determines when it executes. Expressions can be Jinja2 templates or natural language prompts. | Field | Type | Description | | - | - | - | | **Branches** | tabs | One or more conditions. Each branch has an **Expression** field. Click **+** to add branches. | | **Else branch** | auto | Automatically added. Executes when no other condition matches. | **Example Jinja2 expression:** ``` {{ extraction_output.price > 100 }} ``` Conditional block configuration with branch expressions ### AI Validation Assert conditions using AI and halt the agent on failure. Useful for checking that a previous block produced expected results before continuing. | Field | Type | Description | | - | - | - | | **Complete if...** | text | Condition that means validation passed | | **Terminate if...** | text | Condition that means validation failed | Additional fields in **Advanced Settings:** | Field | Type | Description | | - | - | - | | **Error Code Mapping** | JSON | Custom error codes for failure reasons | | **Input Parameters** | select | Parameters to evaluate | AI Validation block configuration with Complete if and Terminate if fields ### Code Execute custom Python code. Input parameters are available as global variables. Top-level variables in your code become the block's output. | Field | Type | Description | | - | - | - | | **Code** | code editor | Python code to execute | | **Input Parameters** | select | Parameters available as globals in the code | Password credential input parameters expose plaintext fields such as `login_credential.username` and `login_credential.password`. These values are readable by Python code inside the runner; they are not opaque handles. Use them only where needed, such as passing them directly to browser operations. For one-time codes, use `await login_credential.otp()`, the supported pattern across both execution paths. Do not rely on `.totp` or the top-level `otp(...)` helper, whose behavior differs between paths. If no OTP source is configured, `login_credential.otp()` fails with a clear one-time-code-unavailable error. ```python theme={null} await page.fill("#username", login_credential.username) await page.fill("#password", login_credential.password) await page.fill("#otp", await login_credential.otp()) ``` The sandbox does not reject code that prints, returns, or transforms credential values. Before string values in a successful block output or a surfaced failure reason are persisted, Skyvern masks exact registered-secret matches; registered secrets of at least five characters are also masked inside larger strings. Derived or transformed values may no longer match. Do not expose credentials through output or errors. Opaque credential containment is tracked separately in SKY-11771. Code block configuration with Python code editor and Input Parameters field ### Wait Pause agent execution for a specified duration. | Field | Type | Description | | - | - | - | | **Wait in Seconds** | number | Seconds to wait (0–300) | Wait block configuration with Wait in Seconds field *** ## Files ### File Download Navigate the browser to download a file. | Field | Type | Description | | - | - | - | | **URL** | text | Starting URL (optional) | | **Download Goal** | text | Instructions for finding and downloading the file | | **Download Timeout (sec)** | number | Seconds to wait for the download to complete | Additional fields in **Advanced Settings:** | Field | Type | Description | | - | - | - | | **File Name** | text | Custom filename for the download | *Plus [common browser fields](#common-fields).* File Download block configuration with URL, Download Goal, and Download Timeout fields ### Cloud Storage Upload Upload downloaded files to S3 or Azure Blob Storage. | Field | Type | Description | | - | - | - | | **Storage Type** | select | `Amazon S3` or `Azure Blob Storage` | | **Folder Path** | text | Upload path/prefix (optional) | | Field | Description | | - | - | | **S3 Bucket** | Bucket name | | **AWS Access Key ID** | AWS credential | | **AWS Secret Access Key** | AWS credential | | **Region Name** | AWS region | | Field | Description | | - | - | | **Storage Account Name** | Storage account name | | **Storage Account Key** | Storage account key | | **Blob Container Name** | Container name | Cloud Storage Upload block configuration with Storage Type and Folder Path fields *** ## Communication ### Send Email Send an email notification, optionally with file attachments from previous blocks. | Field | Type | Description | | - | - | - | | **Recipients** | text | Comma-separated email addresses | | **Subject** | text | Email subject line. Supports [parameter references](/docs/cloud/building-agents/add-parameters#referencing-parameters-in-blocks) — add `{{workflow_run_id}}` to tag the subject with the run, e.g. `Your Run is Finished {{workflow_run_id}}`. | | **Body** | text | Email body. Supports [parameter references](/docs/cloud/building-agents/add-parameters#referencing-parameters-in-blocks). | | **Body format** | select | `Text` (default) sends the body exactly as written. `HTML` renders the body as a formatted email and adds a plain-text version for clients that cannot show HTML; `