v0.1.15

Changelog

v0.1.15

🐛 Bug Fixes

• Vendored Search Tool Availability

  • Fixed grep and find so they prepare embedded rg / fd binaries on demand instead of failing when vendored tools have not been extracted yet
  • Restored executable permissions for already-extracted vendored binaries to avoid permission denied failures on reuse

• Bash Tool Result Handling

  • Fixed bash tool responses to report stdout, stderr, working directory, and exit code in a stable structured format
  • Preserved non-zero command exits as normal tool results with explicit exit_code output instead of mixing shell failures into transport-level errors
  • Standardized empty stdout/stderr rendering as (no output) for more predictable downstream handling

Full Changelog: v0.1.14...v0.1.15

v0.1.14

Changelog

v0.1.14

🐛 Bug Fixes

• Session Continue Context Injection (-c)
  • Fixed a TUI state coupling issue where continued sessions could display history but fail to inject that history into the model context for follow-up prompts
  • Split session history state into separate UI-display and agent-injection flags to ensure resumed conversations keep prior context
  • Reset agent history-injection state consistently when the agent is recreated (abort/mode/model/skill/session switches)
  • Added missing TUI handlers for EventStatus and EventMessageStart so status/warning messages are rendered reliably

🧪 Testing

• Added regressions that cover:
  • history injection when UI history is already loaded
  • real startup ordering (Init() history load, then follow-up input) for continued sessions

---

v0.1.13

🐛 Bug Fixes

• Streaming Event and Tool Call Robustness

  • Preserved terminal agent events in the TUI event listener so done/error/status handling is not dropped during streaming
  • Added Anthropic thinking signature streaming and replay support, and surfaced SSE error events as proper stream errors
  • Generated fallback tool call IDs for OpenAI-compatible streamed tool calls when providers omit IDs, with an extra defensive fallback in the agent loop

• Sandbox Environment Inheritance

  • Fixed none sandbox execution so commands inherit the parent environment, including variables such as $HOME
  • Clarified bubblewrap environment override handling to match runtime behavior

🛠 Improvements

• Vendored Tool Build Flow

  • Unified build and distribution targets around prepare-vendored
  • Removed the old vendored-tools release step and deprecated the stale extract helper script

• Documentation Site Layout

  • Expanded the docs landing page content width for better large-screen readability

• Package Metadata

  • Updated npm package versions for installer packages

📖 Documentation

• Updated README and docs landing pages to highlight safer approval handling, unified cache metrics, and consistent provider debugging
• Simplified AGENTS.md guidance for repository agents

🧪 Testing

• Added bash tool output coverage for stdout-only, stderr-only, no-output, and non-zero exit cases
• Added TUI regression tests for status/warning rendering and done/error event passthrough
• Added OpenAI streaming regression coverage for tool calls with missing IDs

v0.1.12

v0.1.12

🐛 Bug Fixes

• Unified Cache Hit Rate Semantics

  • Restored cache hit rate calculation to use the full prompt footprint (CacheRead / TotalInputTokens())
  • Aligned CLI print mode token display with TUI cache-aware totals
  • Updated Anthropic cache tests and shared provider usage tests to match the unified definition

• Approval Safety in Non-Interactive and YOLO Flows

  • Made bashBlacklist effective in approval checks with higher priority than bashWhitelist
  • Blacklisted bash commands now still require approval in yolo mode
  • --print mode now fails fast instead of auto-approving commands that would require user confirmation

🛠 Improvements

• Debug Output Consistency

  • --debug now also enables provider-level request/response debug output
  • Applied the same behavior to ACP mode

• Cross-Platform Path Handling

  • Replaced string-based .skills path construction with filepath.Join(...)

📖 Documentation

• Updated CLI reference to document stricter --print behavior and debug output behavior
• Updated configuration guide for approval precedence and VIBECODING_DEBUG
• Updated root README and documentation landing pages to highlight safer approval handling, unified cache metrics, and provider debug behavior

🧪 Testing

• Added approval behavior tests for whitelist/blacklist and yolo mode
• Added print mode regression test for approval-required tool calls
• Expanded cache-related provider tests to cover the unified cache hit rate definition

---

Full Changelog: v0.1.11...v0.1.12

v0.1.11

Full Changelog: v0.1.10...v0.1.11

v0.1.10

v0.1.10

✨ Features

• ACP Support Documentation
  • Added ACP (Agent Client Protocol) support documentation to READMEs
  • VibeCoding can run as an ACP stdio agent for editor integrations
  • Compatible with VS Code, Zed, and JetBrains IDEs (IntelliJ IDEA/WebStorm) via ACP plugins

📖 Documentation

• Updated main README.md with ACP support feature
• Updated English README with features section
• Updated Chinese README with features section

---

v0.1.8

v0.1.8

🐛 Bug Fixes

• Token Counting with Cache-Aware TotalTokens
  • Fixed Anthropic TotalTokens calculation to include CacheRead and CacheWrite tokens
  • Added PromptTokens() and TotalInputTokens() helper methods to Usage struct
  • Updated CacheInfo() to use TotalInputTokens() as denominator for accurate cache hit rates
  • Updated TUI to display correct token counts including cache tokens

🧪 Testing

• Added comprehensive tests for PromptTokens() and TotalInputTokens() helper methods
• Updated Anthropic provider tests with TotalTokens validation

---

v0.1.6

v0.1.6

✨ Features

• Session Management Command
  • Added /sessions command for browsing and managing project sessions
  • Supports listing, switching, clearing, and deleting sessions
  • Shows session details including file path and message count

🐛 Bug Fixes

• Sandbox Initialization
  • Fixed sandbox initialization validation and bwrap multiarch compatibility
  • Improved error handling for sandbox setup

📖 Documentation

• Updated AGENTS.md with current version information
• Formatted Go code for consistency

v0.1.5

v0.1.5

✨ Features

• DeepSeek V4 Default Models
  • Updated default model specs to DeepSeek V4 (Flash and Pro)
  • 1M context window, up to 384K max output tokens
• Install Script Improvements
  • Install scripts now show config directory path on completion

🐛 Bug Fixes

• Windows IME Support
  • Fixed Windows IME (CJK input) support in terminal
  • Fixed shell command resolution on Windows
  • Added config loading diagnostics for troubleshooting
• Musl Deb Packages
  • Fixed invalid dpkg architecture names for musl deb packages

🛠 Improvements

• Configuration Simplification
  • Removed auth.json support — all credentials now in settings.json only
  • Cleaner config path with single source of truth

📖 Documentation

• Clarified that OpenAI/Anthropic API-compatible services are also supported
• Removed all auth.json references from docs and install scripts
• Added expanded Windows %APPDATA% path examples
• Clearly distinguished Windows vs Linux/macOS config paths

---

v0.1.4

v0.1.4

✨ Features

• Linux musl Build Support
  • Added make build-linux-musl target for statically linked musl binaries (amd64 + aarch64)
  • musl tarballs produced via dist-tarball and dist targets
  • musl Debian packages produced via dist-deb target (amd64-musl / arm64-musl)
  • npm packages: vibecoding-installer-linux-musl-x64 and vibecoding-installer-linux-musl-arm64
  • npm uses libc field for proper musl/glibc resolution (npm >=9.4)
  • postinstall.js auto-detects musl vs glibc on Linux

---

v0.1.2

v0.1.2

✨ Features

• Prompt Cache Optimization

  • Implemented prompt cache optimization following LLM_Agent_Cache.md strategy
  • Cache system prompts and static context across multiple turns
  • Reduces API costs by reusing cached tokens for repeated prefixes

• TUI Markdown Syntax Highlighting

  • Assistant messages in TUI now have markdown syntax highlighting
  • Code blocks, headers, and formatting are visually distinguished
  • Improves readability of LLM responses

🐛 Bug Fixes

• Security & Correctness

  • Resolved critical security, race condition, and correctness issues
  • Addressed high and medium severity correctness issues across codebase
  • Removed dead code and improved overall code correctness

• TUI Stability

  • Fixed TUI startup hang caused by clearStdin blocking on unsupported stdin
  • Fixed TUI assistant message rendering broken by ANSI escape codes in prefix check

🛠 Improvements

• Code Quality
  • Addressed remaining medium severity issues across codebase
  • npm package versions updated