#DeepAsk Changelog

More details with pictures, please check LifeOS for Obsidian

#2.0.36

• Improved the DeepAsk mobile chat composer so attachment and context areas are height-limited and scroll independently, reducing page jumps during focus, loading, and hover states.
• Hardened mobile chat scrolling anchors and composer layout so narrow screens are less likely to overflow or jitter around the bottom action area.

#2.0.35

• Fixed configured Claude Code or Codex executable paths failing when meaningful whitespace was trimmed from the path
• Fixed rapid changes across multiple DeepAsk settings sometimes saving only the last field; updates within the same debounce window are now merged
• Improved localized activation errors and targeted plugin reloads after updates; reload failures now report failure instead of claiming the update succeeded
• Updated the bundled LifeOS Agent guidance with a Memos template, existing-vault migration, and a more complete first-run workflow

#2.0.34

• Regenerated and redeployed the complete release package and integrity metadata to prevent update or activation failures caused by mismatches between downloads, version archives, and verification values

#2.0.33

• Improved the waiting experience when DeepAsk uses local coding agents. The chat now shows clearer progress states and reduces first-launch idle time.

#2.0.32

• Fixed command prompt windows appearing on Windows when DeepAsk starts local agents or tool services, keeping the workflow inside Obsidian.

#2.0.31

• Fixed local coding-agent launch failures on Windows when DeepAsk sends large vault context.

#2.0.30

• Fixed clipped top-right actions when the right sidebar is narrow. The DeepAsk title now hides in compact containers so model, conversation, settings, and help buttons remain accessible.
• Fixed the bottom quick-suggestion row being cut off in narrow sidebars. The suggestion list now supports horizontal scrolling.

#2.0.29

• Fixed chat-list jitter while DeepAsk is streaming a reply. The message list now follows the bottom steadily during live output and does not force-scroll users back down after they scroll up to read history.

#2.0.28

• Added a settings entry to the AI chat surface so model, provider, and DeepAsk configuration can be opened directly
• Extended the shared settings button to target related settings sections, making the right configuration easier to find when multiple LifeOS plugins are enabled

#2.0.27

• Maintenance release for the shared LifeOS plugin foundation, keeping the current stable release content complete

#2.0.26

• Maintenance release for the shared LifeOS plugin foundation, keeping the current stable release content complete

#2.0.25

• Maintenance release for the shared LifeOS plugin foundation, keeping the current stable release content complete

#2.0.24

• Maintenance release for the shared LifeOS plugin foundation, keeping the current stable release content complete

#2.0.23

• Maintenance release for the shared LifeOS plugin foundation, keeping compatibility with the current Obsidian plugin versions

#2.0.22

• Fixed agent context so DeepAsk includes the active note, current web page, and open tab summary when sending requests

#2.0.21

• Fixed periodic daily-note lookup to honor Obsidian Daily Notes folder and format settings, including month subfolders

#2.0.20

• Fixed cross-plugin settings updates sometimes affecting DeepAsk state when multiple LifeOS plugins are enabled

#2.0.19

• Improved DeepAsk desktop component loading stability, reducing missing-component issues after updates
• Fixed the chat panel sometimes reporting a false loading failure right after plugin updates

#2.0.18

• Improved DeepAsk chat panel loading so required components are less likely to be missing after updates
• Fixed desktop components sometimes missing after updates from older versions

#2.0.17

• Fixed DeepAsk chat panel and local capabilities sometimes failing to load after updates

#2.0.15

• Fixed Codex CLI replies stopping after the first partial segment in DeepAsk

#2.0.14

• Updated Ordinary Model Tools settings so built-in capabilities are available by default while external capabilities stay disabled by default
• Split write/update permission from delete permission for ordinary model chat
• Fixed the Ordinary Model Tools settings layout so switches and inputs display cleanly

#2.0.13

• Fixed DeepAsk failing to load because of dependency version mismatches

#2.0.12

• Fixed the latest DeepAsk release missing the Ordinary Model Tools settings section in AI Connect
• Added a note that Ordinary Model Tools only apply to DeepAsk ordinary model chat and do not affect local coding-agent modes

#2.0.11

• Fixed the Obsidian third-party plugin list sometimes hiding the settings button by registering the settings tab before vault indexing starts

#2.0.10

• Added controlled tool calling for ordinary AI model chat, with permission-aware context reading and tool use
• Added ordinary model tool-call settings, with write and delete capabilities disabled by default to prevent accidental note edits
• Added the AI Connect settings tab for related DeepAsk AI connection, install, and update entries
• Fixed the missing AI Connect settings tab in DeepAsk
• Fixed settings white-screen and loading failures

#2.0.9

• Fixed AI model dropdowns in Obsidian's detached settings window drifting to the main window or becoming hard to select
• Fixed other settings dropdowns and active tab highlight behavior
• Fixed duplicate input borders in settings fields
• Fixed possible settings white-screen after upgrade and plugin state display issues

#2.0.0

• Added device management: view device usage, refresh the device list, and unbind unused devices from plugin settings
• Added a manual update entry, making it easier to get the latest plugin when automatic updates fail
• Added Anthropic configuration support while keeping the existing OpenAI-compatible services available
• Added more flexible model service configuration, so the same service can keep separate settings for different usage modes
• Added local coding-agent modes, allowing Obsidian context to be sent directly to local agents
• Added OpenAI and Anthropic identity marks in the chat page, making the active model service clearer
• Added an animated pre-response placeholder, so sending a message immediately shows that a reply is being prepared
• Improved context loading for large vaults, especially when DeepAsk is used alongside other LifeOS plugins