v0.3.14

What's Changed

• fix: RPC connection failure — ServerStatus field mismatch + agent.dispatch streaming by @JasonHonKL in #331

Full Changelog: v0.3.13...v0.3.14

What's Changed

• fix: RPC connection failure — ServerStatus field mismatch + agent.dispatch streaming by @JasonHonKL in #331

Full Changelog: v0.3.13...v0.3.14

What's Changed

• fix: RPC connection failure — ServerStatus field mismatch + agent.dispatch streaming by @JasonHonKL in #331

Full Changelog: v0.3.13...v0.3.14

v0.3.13

Full Changelog: v0.3.12...v0.3.13

Full Changelog: v0.3.12...v0.3.13

Full Changelog: v0.3.12...v0.3.13

v0.3.12

What's Changed

• fix: resolve #109 — [MEDIUM] skill_manage artifacts can never be created due to action-tracking filter by @JasonSedimanBOT in #325
• fix(updater): add fallback to build from source when pre-built binaries are unavailable by @JasonHonKL in #328
• fix(agent): Refactor loop.py, fix critical runtime errors, improve web search detection by @JasonHonKL in #329
• feat: agent optimization, terminator wiring, browser mode fixes & test coverage by @JasonHonKL in #330

Full Changelog: v0.3.11...v0.3.12

What's Changed

• fix: resolve #109 — [MEDIUM] skill_manage artifacts can never be created due to action-tracking filter by @JasonSedimanBOT in #325
• fix(updater): add fallback to build from source when pre-built binaries are unavailable by @JasonHonKL in #328
• fix(agent): Refactor loop.py, fix critical runtime errors, improve web search detection by @JasonHonKL in #329
• feat: agent optimization, terminator wiring, browser mode fixes & test coverage by @JasonHonKL in #330

Full Changelog: v0.3.11...v0.3.12

What's Changed

• fix: resolve #109 — [MEDIUM] skill_manage artifacts can never be created due to action-tracking filter by @JasonSedimanBOT in #325
• fix(updater): add fallback to build from source when pre-built binaries are unavailable by @JasonHonKL in #328
• fix(agent): Refactor loop.py, fix critical runtime errors, improve web search detection by @JasonHonKL in #329
• feat: agent optimization, terminator wiring, browser mode fixes & test coverage by @JasonHonKL in #330

Full Changelog: v0.3.11...v0.3.12

v0.3.11

Full Changelog: v0.3.10...v0.3.11

Full Changelog: v0.3.10...v0.3.11

Full Changelog: v0.3.10...v0.3.11

v0.3.10

What's Changed

Streaming & Think Tags

• ThinkTagParser: New streaming parser that separates model thinking (<think> tags) from response content in real-time
• Strip think tags: Clean conversational response results for Response tab display and conversation history
• Fallback: Extract inner think content when entire response is wrapped in think tags
• Remove debug logging: Strip verbose structlog calls from stable parser
• 42 unit tests: Comprehensive test suite for ThinkTagParser

TUI Improvements

• Tabbed interface: Agent messages render with Thinking / Steps / Response tabs
• Auto-switch: Response tab auto-selects when agent result arrives
• Auto-expand: Tab auto-expands when switching to Response tab
• Thinking display: Model reasoning content shown in muted style under Thinking tab
• Live streaming: Real-time phase labels during agent execution

Bug Fixes

• Fix clippy warnings causing Rust TUI CI failure (unused imports, dead code)
• Fix conversation history storing raw think tags (wasting context tokens)
• Fix broken comprehensive test modules in sediman-tui-core (referenced non-existent APIs)

Chores

• Bump version to 0.3.10 in Cargo.toml and pyproject.toml
• Remove debug logger from stable ThinkTagParser

Full Changelog: v0.3.9...v0.3.10

What's Changed

• feat(tui): Add separate thinking display section by @JasonHonKL in #322
• feat(tui): Improve step display and fix API key persistence by @JasonHonKL in #323
• fix(streaming): strip tags from conversational response results + comprehensive tests by @JasonHonKL in #324
• chore: remove debug logger from think_parser, bump to v0.3.10 by @JasonHonKL in #326
• fix(tui): remove broken sediman-tui-core comprehensive test modules by @JasonHonKL in #327

Full Changelog: v0.3.9...v0.3.10

What's Changed

• feat(tui): Add separate thinking display section by @JasonHonKL in #322
• feat(tui): Improve step display and fix API key persistence by @JasonHonKL in #323
• fix(streaming): strip tags from conversational response results + comprehensive tests by @JasonHonKL in #324
• chore: remove debug logger from think_parser, bump to v0.3.10 by @JasonHonKL in #326
• fix(tui): remove broken sediman-tui-core comprehensive test modules by @JasonHonKL in #327

Full Changelog: v0.3.9...v0.3.10

What's Changed

• feat(tui): Add separate thinking display section by @JasonHonKL in #322
• feat(tui): Improve step display and fix API key persistence by @JasonHonKL in #323
• fix(streaming): strip tags from conversational response results + comprehensive tests by @JasonHonKL in #324
• chore: remove debug logger from think_parser, bump to v0.3.10 by @JasonHonKL in #326
• fix(tui): remove broken sediman-tui-core comprehensive test modules by @JasonHonKL in #327

Full Changelog: v0.3.9...v0.3.10

v0.3.9

Full Changelog: v0.3.8...v0.3.9

Full Changelog: v0.3.8...v0.3.9

Full Changelog: v0.3.8...v0.3.9

v0.3.8 - CRITICAL Ctrl+C Fix

CRITICAL FIX

Ctrl+C Now Works (CRITICAL)

• Problem: Ctrl+C would not terminate the TUI, forcing users to force quit
• Solution:
  • Moved exit check to top of main loop for immediate response
  • Set interrupt flag when Ctrl+C is pressed
  • Ensure terminal state is properly restored on exit
• Result: TUI now exits gracefully when Ctrl+C is pressed

Installation

curl -fsSL https://raw.githubusercontent.com/sediman-agent/OpenSkynet/main/scripts/install.sh | bash

For aarch64-macos (Apple Silicon):
Pre-built binaries not available. Build from source:

git clone https://github.com/sediman-agent/OpenSkynet.git
cd OpenSkynet
cargo build --release --package sediman-tui
cp target/release/sediman-tui ~/.local/bin/terminator
chmod +x ~/.local/bin/terminator

What This Fixes

1. Ctrl+C not working (CRITICAL) - FIXED
2. TUI hanging on exit - FIXED
3. Terminal state not restored - FIXED

This is a critical fix that makes the TUI usable. Without this fix,
users could not exit the TUI gracefully and had to force quit the application.

Full Changelog: v0.3.7...v0.3.8

Full Changelog: v0.3.7...v0.3.8

Full Changelog: v0.3.7...v0.3.8

Full Changelog: v0.3.7...v0.3.8

v0.3.7 - Thinking Tab Color Fix & Config Improvements

What's Fixed

Thinking Tab Color Fix

• Problem: Thinking text was same color as response, making it hard to distinguish
• Solution:
  • Thinking/Planning text now uses muted color (text_muted)
  • Responding text uses regular text color
  • Executing text uses regular text color
• Result: Easy to distinguish between thinking phase and actual response

Config Improvements

• Problem: Old config files missing provider/model/base_url fields caused issues
• Solution: Config loading now handles missing fields gracefully with defaults
• Result: Old configs auto-migrate to new structure

Previous Fixes Included

• Model selection now persists across restarts
• Step count no longer shows previous task's steps
• Expand/collapse label text fixed
• Agent always shows output (no empty responses)
• Branding updated to Terminator/OpenSkynet

Installation

curl -fsSL https://raw.githubusercontent.com/sediman-agent/OpenSkynet/main/scripts/install.sh | bash

For aarch64-macos (Apple Silicon):
Pre-built binaries not available. Build from source:

git clone https://github.com/sediman-agent/OpenSkynet.git
cd OpenSkynet
cargo build --release --package sediman-tui
cp target/release/sediman-tui ~/.local/bin/terminator
chmod +x ~/.local/bin/terminator

Manual Config Update (if needed)

If your config is missing provider/model, add to ~/.terminator/tui.toml:

provider = "minimax"
model = "m3"
base_url = ""

Full Changelog: v0.3.6...v0.3.7

Full Changelog: v0.3.6...v0.3.7

Full Changelog: v0.3.6...v0.3.7

v0.3.6 - Multiple Critical UX Improvements

Critical Fixes & Improvements

Model Selection Persistence (CRITICAL)

• Your selected model (e.g., minimax m3) now persists across restarts
• Provider and model are saved to ~/.terminator/tui.toml
• CLI args can override saved config if needed

Step Count Display Fix

• Fixed steps from previous task appearing in new task
• Added agent_running gate to prevent step pollution between tasks
• Clear streaming_phase state properly between tasks

Thinking Tab UI Fix

• Fixed expand/collapse label text (was showing inverted actions)
• Now correctly shows "Expand" when collapsed and "Collapse" when expanded
• Press Space bar when input is empty to toggle

Agent Output Improvements

• Agent always shows some output (no more empty responses)
• Added contextual fallbacks for acknowledgments (good, ok, yes, no, etc.)
• Improved conversational response handling with better prompts
• System prompt updated to ensure engaging responses

Branding Updates

• Updated branding to Terminator/OpenSkynet in prompts
• TUI already correctly shows "Your Terminator" and "OpenSkynet"
• Python folder remains as sediman (as requested)

Installation

curl -fsSL https://raw.githubusercontent.com/sediman-agent/OpenSkynet/main/scripts/install.sh | bash

What's Fixed

1. Model Selection Resetting (CRITICAL) - FIXED
2. Version Number Sync - FIXED
3. Step Count Showing Previous Steps - FIXED
4. Thinking Tab Expand/Collapse - FIXED
5. Empty Agent Responses - FIXED
6. Branding Consistency - FIXED

All critical UX issues have been addressed. The agent now behaves consistently
across multiple interactions with proper state management and branding.

Full Changelog: v0.3.5...v0.3.6

Full Changelog: v0.3.5...v0.3.6

Full Changelog: v0.3.5...v0.3.6

v0.3.5 - Fix model selection persistence (CRITICAL)

Critical Fixes

• fix(tui): persist provider and model selection to config - Fixes the issue where model selection resets to default every time the app restarts
• fix(agent): improve conversational response generation - Fixes duplicate generic messages
• chore: bump version to v0.3.5 - Ensures TUI and Python package versions are in sync

Installation

curl -fsSL https://raw.githubusercontent.com/sediman-agent/OpenSkynet/main/scripts/install.sh | bash

What's Fixed

1. Model Selection Persistence (CRITICAL)

   • Your selected model (e.g., minimax m3) now persists across restarts
   • Provider and model are saved to ~/.terminator/tui.toml
   • CLI args can override saved config if needed

2. Duplicate Conversational Messages

   • No more repetitive "I'm Sediman. How can I help you?" messages
   • Each response is now contextual and unique

3. Version Sync

   • TUI binary and Python package are now at the same version (v0.3.5)
   • Prevents the version mismatch issues from previous releases

Full Changelog: v0.3.4...v0.3.5

Full Changelog: v0.3.4...v0.3.5

Full Changelog: v0.3.4...v0.3.5

Full Changelog: v0.3.4...v0.3.5

Full Changelog: v0.3.4...v0.3.5