> ## Documentation Index > Fetch the complete documentation index at: https://skyvern.com/docs/llms.txt > Use this file to discover all available pages before exploring further. # Changelog > New features, improvements, and fixes in Skyvern

TIMELINE

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 * **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))