What's Changed

[unreleased]

Bug Fixes

• Update versioning format to remove 'v' prefix in tags and URLs (@vinhnx)

• Resolve critical scrolling issue and remove unused slash command handlers (@vinhnx)

• Correct exec_code policy and update TODO for markdown rendering issue (@vinhnx)

• Update default model in configuration to glm-5:cloud (@vinhnx)

• Correct changelog generation to use the previous release tag instead of a fixed version. (@vinhnx)

• Update chat input placeholders for clarity and improved user guidance (Vinh Nguyen)

• Update chat input placeholders for clarity and improved user guidance (Vinh Nguyen)

• Disable scroll indicator in status bar (Vinh Nguyen)

Documentation

• Update changelog for 0.79.2 [skip ci] (vtcode-release-bot)

• Update changelog for 0.79.3 [skip ci] (vtcode-release-bot)

• Update changelog for 0.79.4 [skip ci] (vtcode-release-bot)

• Update contributing guidelines to reference CONTRIBUTING.md and AGENTS.md. (@vinhnx)

• Update changelog for 0.80.0 [skip ci] (vtcode-release-bot)

• Update documentation for TECH_DEBT_TRACKER and QUALITY_SCORE; add tests for subagent loading and file operations (@vinhnx)

• Update changelog for 0.80.1 [skip ci] (vtcode-release-bot)

• Update changelog for 0.81.0 [skip ci] (vtcode-release-bot)

• Update changelog for 0.81.1 [skip ci] (vtcode-release-bot)

• Update changelog for 0.81.2 [skip ci] (vtcode-release-bot)

• Update changelog for 0.81.3 [skip ci] (vtcode-release-bot)

• Add a guide for adding new models to AGENTS.md. (@vinhnx)

• Update changelog for 0.82.0 [skip ci] (vtcode-release-bot)

• Update changelog for 0.82.1 [skip ci] (vtcode-release-bot)

• Update TODO.md with additional PTY truncate display information and test references (@vinhnx)

• Update changelog for 0.82.2 [skip ci] (vtcode-release-bot)

• Update changelog for 0.83.0 [skip ci] (vtcode-release-bot)

• Update changelog for 0.82.3 [skip ci] (vtcode-release-bot)

• Update TODO.md with new tasks and references (Vinh Nguyen)

• Update TODO.md with examples and improve TUI display for truncated outputs (Vinh Nguyen)

Features

• Add MiniMax M2.5 model support across various providers and update related constants (@vinhnx)

• Add Qwen3 Coder Next model support and update related constants (@vinhnx)

• Add skill bundle import/export functionality with zip support (@vinhnx)

• Implement plan mode toggle and strip proposed plan blocks in rendering (@vinhnx)

• Implement in-process teammate runner and enhance team protocol messaging (@vinhnx)

• Add /share-log command to export session log as JSON for debugging (@vinhnx)

• Implement agent steering mechanism to control runloop execution, including stop, pause, resume, and input injection capabilities. (@vinhnx)

• Enhance reasoning display by introducing structured ReasoningSegment with stages and improved rendering in the TUI. (@vinhnx)

• Use configurable constants for agent session limits and expose the default max context tokens function. (@vinhnx)

• Introduce agent legibility guidelines and refine steering message variants for clarity and structured output. (@vinhnx)

• Add Kimi K2.5 model support across OpenRouter, Ollama, and HuggingFace. (@vinhnx)

• Add sanitizer module for secret redaction and integrate into output handling (@vinhnx)

• Implement credential storage using OS keyring and file fallback (@vinhnx)

• Add timeout handling for turn metadata collection (@vinhnx)

• Implement mouse scroll handling for improved navigation (@vinhnx)

• Add Qwen3.5-397B-A17B model with hybrid architecture and update configuration (@vinhnx)

• Implement secure storage for custom API keys using OS keyring (@vinhnx)

• Add CI workflows for building Linux and Windows binaries; optimize release process (@vinhnx)

• Add full CI mode to release script for all platforms (@vinhnx)

• Refactor build process to use conditional cross compilation for Linux and Windows (@vinhnx)

• Implement mouse scroll support for TUI session and history picker, and update default agent configuration to Ollama. (@vinhnx)

• Render GFM tables inside markdown code blocks as tables and prevent word-wrapping for table lines in the TUI. (@vinhnx)

• Implement mouse text selection in the TUI and add a new vtcode.toml configuration file. (@vinhnx)

• Add Claude Sonnet 4.6 model support and integrate it across model definitions, parsing, catalog, and documentation. (@vinhnx)

• Implement Gemini 3.1 Pro Preview models with updated token limits and system prompt handling. (@vinhnx)

• Implement Gemini prompt caching with TTL using a new CacheControl part and add support for Gemini 3.1 Pro preview models. (@vinhnx)

• Add prompt_cache_key to OpenAI requests for improved cache locality and simplify Responses API usage logic. (@vinhnx)

• Add top-level cache control to Anthropic requests, with TTL determined by breakpoint consumption. (@vinhnx)

• Standardize MiniMax-M2.5 model identifier, promote it as the default, and update configuration defaults. (@vinhnx)

• Introduce CI cost optimization strategies, add a new --ci-only release mode, and document release workflow details. (@vinhnx)

• Add prompt cache key to LLM requests and enhance unified_file tool execution diagnostics. (@vinhnx)

• Refactor Ollama non-streaming request handling and add a fallback to non-streaming for initial stream failures. (@vinhnx)

• Improve spooled tool output handling by verifying file existence and add a mechanism to suppress agent follow-up prompt detection for auto-generated prompts. (@vinhnx)

• Enhance error handling and recovery mechanisms across various components (@vinhnx)

• Implement tool reentrancy guard to prevent recursive execution and improve panic reporting with better-panic. (@vinhnx)

• Implement chunked reading for spooled tool outputs with improved agent messaging and update default LLM provider configuration. (@vinhnx)

• Add chunked file read spool progress tracking and refine token usage calculation for context management. (@vinhnx)

• Generate consolidated checksums.txt for releases and centralize script utilities into common.sh. (@vinhnx)

• Implement TaskTracker tool and enhance agent guards and documentation based on NL2Repo-Bench insights. (@vinhnx)

• Integrate AI agent best practices into system prompts and loop detection for improved planning, root cause analysis, and uncertainty recognition. (@vinhnx)

• Enhance documentation on grounding, uncertainty, and regression verification; improve loop detection guidance (@vinhnx)

• Enhance AskUserChoice with freeform input, custom labels, placeholders, and default selections. (@vinhnx)

• Implement freeform text input for wizard modals, guided by system prompt and toggled by the Tab key. (@vinhnx)

• Refine plan mode transitions by adding more aliases, enabling contextual exit confirmations, and providing user guidance. (Vinh Nguyen)

• Set custom terminal title for VT Code TUI (Vinh Nguyen)

• Migrate changelog generation to git-cliff and update related documentation (Vinh Nguyen)

Other

• Prevent footer panic when hint is absent, refactor path argument to &Path, and optimize sidebar string truncation. (@vinhnx)

Refactors

• Remove unused ReasoningSegment import from turn_processing.rs (@vinhnx)

• Reimplement LLM streaming and event handling using AgentSessionController and its event sink mechanism. (@vinhnx)

• Extract large event handler modules into smaller files for improved navigation (@vinhnx)

• Streamline file operations and enhance workspace path handling (@vinhnx)

• Replace manual file operations with shared utility functions for consistency (@vinhnx)

• Replace manual file operations with shared utility functions for consistency (@vinhnx)

• Replace manual file operations with shared utility functions for consistency (@vinhnx)

• Consolidate duplicated logic across workspace crates into shared utility functions (@vinhnx)

• Streamline MCP tool management and indexing in ToolRegistry (@vinhnx)

• Remove Rust cache step from release workflow (@vinhnx)

• Clean up code formatting and improve readability across multiple files (@vinhnx)

• Remove unused imports and enhance configuration for credential storage (@vinhnx)

• Make TUI signal cleanup and dotfile permission backup UNIX-specific. (@vinhnx)

• Improve previous SemVer tag identification by searching commit history in release scripts (@vinhnx)

• Remove unified tool resolver module to streamline codebase (Vinh Nguyen)

• Remove unused TUI components and improve event handling for focus changes (Vinh Nguyen)

• Standardize continuation prefix handling in wrap_block_lines functions (Vinh Nguyen)

Full Changelog: https://github.com/vinhnx/vtcode/compare/0.82.4

What's Changed

Features

• Implement freeform text input for wizard modals, guided by system prompt and toggled by the Tab key. (9b54cdd) (@vinhnx)
• Enhance AskUserChoice with freeform input, custom labels, placeholders, and default selections. (53e0e11) (@vinhnx)
• Enhance documentation on grounding, uncertainty, and regression verification; improve loop detection guidance (064ea63) (@vinhnx)
• Integrate AI agent best practices into system prompts and loop detection for improved planning, root cause analysis, and uncertainty recognition. (91e5e29) (@vinhnx)
• Implement TaskTracker tool and enhance agent guards and documentation based on NL2Repo-Bench insights. (45a9a15) (@vinhnx)

Refactors

• improve previous SemVer tag identification by searching commit history in release scripts (0fcdce3) (@vinhnx)

Other

• Update commit (925f355) (@vinhnx)
• Add reference to git-cliff for changelog generation (8dd703f) (@vinhnx)
• Refactor user input option generation and enhance markdown rendering in modals (a72a63c) (@vinhnx)
• Add navigation loop guidance and improve plan mode handling (5d162ae) (@vinhnx)
• Add plan-mode task tracker with CRUD functionality and integrate with existing tools (56c7e3b) (@vinhnx)
• Rename UpdatePlanCommand to TaskTrackerCommand and refactor related files and documentation (b452027) (@vinhnx)
• Update commit (0642ff3) (@vinhnx)

Full Changelog: 0.82.2...0.82.3

What's Changed

Features

• Generate consolidated checksums.txt for releases and centralize script utilities into common.sh. (4bdb080) (@vinhnx)
• Add chunked file read spool progress tracking and refine token usage calculation for context management. (ef8f162) (@vinhnx)
• Implement chunked reading for spooled tool outputs with improved agent messaging and update default LLM provider configuration. (b5b0c23) (@vinhnx)
• Implement tool reentrancy guard to prevent recursive execution and improve panic reporting with better-panic. (44351bf) (@vinhnx)
• enhance error handling and recovery mechanisms across various components (7902206) (@vinhnx)
• improve spooled tool output handling by verifying file existence and add a mechanism to suppress agent follow-up prompt detection for auto-generated prompts. (083ae71) (@vinhnx)
• refactor Ollama non-streaming request handling and add a fallback to non-streaming for initial stream failures. (3068333) (@vinhnx)
• Add prompt cache key to LLM requests and enhance unified_file tool execution diagnostics. (4073aed) (@vinhnx)
• introduce CI cost optimization strategies, add a new --ci-only release mode, and document release workflow details. (dd2f316) (@vinhnx)
• standardize MiniMax-M2.5 model identifier, promote it as the default, and update configuration defaults. (ff6dcef) (@vinhnx)
• Add top-level cache control to Anthropic requests, with TTL determined by breakpoint consumption. (91c0c9e) (@vinhnx)
• Add prompt_cache_key to OpenAI requests for improved cache locality and simplify Responses API usage logic. (45c9002) (@vinhnx)
• Implement Gemini prompt caching with TTL using a new CacheControl part and add support for Gemini 3.1 Pro preview models. (8b5b42a) (@vinhnx)
• Implement Gemini 3.1 Pro Preview models with updated token limits and system prompt handling. (dc0742c) (@vinhnx)
• add Claude Sonnet 4.6 model support and integrate it across model definitions, parsing, catalog, and documentation. (d460c56) (@vinhnx)
• Implement mouse text selection in the TUI and add a new vtcode.toml configuration file. (8356715) (@vinhnx)
• Render GFM tables inside markdown code blocks as tables and prevent word-wrapping for table lines in the TUI. (c90f06e) (@vinhnx)
• Implement mouse scroll support for TUI session and history picker, and update default agent configuration to Ollama. (db99f4d) (@vinhnx)
• refactor build process to use conditional cross compilation for Linux and Windows (d15bb55) (@vinhnx)
• add full CI mode to release script for all platforms (326a2c8) (@vinhnx)
• add CI workflows for building Linux and Windows binaries; optimize release process (090bebb) (@vinhnx)
• implement secure storage for custom API keys using OS keyring (3da5a60) (@vinhnx)
• add Qwen3.5-397B-A17B model with hybrid architecture and update configuration (26a9a7e) (@vinhnx)
• implement mouse scroll handling for improved navigation (24a2d64) (@vinhnx)
• add timeout handling for turn metadata collection (1b1f91d) (@vinhnx)
• implement credential storage using OS keyring and file fallback (1e94c71) (@vinhnx)
• add sanitizer module for secret redaction and integrate into output handling (4263808) (@vinhnx)
• add Kimi K2.5 model support across OpenRouter, Ollama, and HuggingFace. (fddc488) (@vinhnx)
• introduce agent legibility guidelines and refine steering message variants for clarity and structured output. (52b13dd) (@vinhnx)
• Use configurable constants for agent session limits and expose the default max context tokens function. (21d1183) (@vinhnx)
• Enhance reasoning display by introducing structured ReasoningSegment with stages and improved rendering in the TUI. (68d07c9) (@vinhnx)
• Implement agent steering mechanism to control runloop execution, including stop, pause, resume, and input injection capabilities. (ac806e0) (@vinhnx)
• add /share-log command to export session log as JSON for debugging (6430582) (@vinhnx)
• implement in-process teammate runner and enhance team protocol messaging (4aff931) (@vinhnx)
• implement plan mode toggle and strip proposed plan blocks in rendering (79f0327) (@vinhnx)
• add skill bundle import/export functionality with zip support (dea5b5b) (@vinhnx)
• add Qwen3 Coder Next model support and update related constants (5a4303e) (@vinhnx)
• add MiniMax M2.5 model support across various providers and update related constants (968963f) (@vinhnx)

Bug Fixes

• correct changelog generation to use the previous release tag instead of a fixed version. (b0437d2) (@vinhnx)
• Update default model in configuration to glm-5:cloud (1700a7e) (@vinhnx)
• correct exec_code policy and update TODO for markdown rendering issue (9b87f88) (@vinhnx)
• resolve critical scrolling issue and remove unused slash command handlers (bcb8143) (@vinhnx)

Refactors

• Make TUI signal cleanup and dotfile permission backup UNIX-specific. (14a4f2d) (@vinhnx)
• remove unused imports and enhance configuration for credential storage (b79f2bd) (@vinhnx)
• clean up code formatting and improve readability across multiple files (b1ae3ad) (@vinhnx)
• remove Rust cache step from release workflow (e36c5f5) (@vinhnx)
• streamline MCP tool management and indexing in ToolRegistry (a5c3677) (@vinhnx)
• consolidate duplicated logic across workspace crates into shared utility functions (a9df41f) (@vinhnx)
• replace manual file operations with shared utility functions for consistency (15c45f9) (@vinhnx)
• replace manual file operations with shared utility functions for consistency (7fcbe5f) (@vinhnx)
• replace manual file operations with shared utility functions for consistency (54c447a) (@vinhnx)
• streamline file operations and enhance workspace path handling (f7ebb78) (@vinhnx)
• extract large event handler modules into smaller files for improved navigation (9eda39e) (@vinhnx)
• reimplement LLM streaming and event handling using AgentSessionController and its event sink mechanism. (95bcd08) (@vinhnx)
• remove unused ReasoningSegment import from turn_processing.rs (9f4672d) (@vinhnx)

Documentation

• Update TODO.md with additional PTY truncate display information and test references (cd3a385) (@vinhnx)
• Add a guide for adding new models to AGENTS.md. (8648b58) (@vinhnx)
• update documentation for TECH_DEBT_TRACKER and QUALITY_SCORE; add tests for subagent loading and file operations (fb7c094) (@vinhnx)
• update contributing guidelines to reference CONTRIBUTING.md and AGENTS.md. (b4a1ef7) (@vinhnx)
• update documentation and improve clarity on execution plans, architectural invariants, and quality scores feat: enhance system instruction generation to replace placeholders with unified tool guidance (27c61ef) (@vinhnx)

Chores

• Release (cf5d5f7) (@vinhnx)
• Release (28a8476) (@vinhnx)
• Release (77422be) (@vinhnx)
• Release (1402781) (@vinhnx)
• Release (6c982a3) (@vinhnx)
• clean up configuration file by removing unused custom API keys and simplifying array formatting (ad594e4) (@vinhnx)
• Release (4bd94bd) (@vinhnx)
• Release (800c706) (@vinhnx)
• Release (a08f765) (@vinhnx)
• Release (accdcc2) (@vinhnx)
• Release (69df0e2) (@vinhnx)
• Release (10e4f28) (@vinhnx)

Other

• Increase max tool calls per turn to 48 and implement budget warning system in harness (7b6cade) (@vinhnx)
• Add spool chunk read tracking and enforce limits per turn (c09ef6d) (@vinhnx)
• Fix: Prevent footer panic when hint is absent, refactor path argument to &Path, and optimize sidebar string truncation. (59525d4) (@vinhnx)
• Update TODO.md (3391d6b) (@1097578+vinhnx)
• Update commit (9d05e9d) (@vinhnx)
• Enhance model behavior configuration for LLM providers (0fa1233) (@vinhnx)
• Add scripts for documentation link validation and markdown location checks (7290fc5) (@vinhnx)
• Update default model in vtcode.toml to minimax-m2:cloud; format code for consistency (e024a48) (@vinhnx)
• Add additional_agent_dirs configuration option to vtcode.toml (0f6d174) (@vinhnx)
• Remove custom prompts feature and related code; update error handling for agent actions; refine UI shortcuts and command handling (cfcc976) (@vinhnx)
• Remove custom prompts feature and related code (dfc3ec5) (@vinhnx)
• Update LLM provider configuration to use Ollama and remove unused typos.toml file (ca83bdc) (@vinhnx)
• Enhance agent runner settings and improve loop detection; update CLI commands for reasoning effort and verbosity; refine patch handling in file operations; adjust markdown diff summary; modify configuration for LLM provider. (ff221d1) (@vinhnx)
• Refactor agent runner and tool registry for improved error handling and normalization; enhance loop detection and add tests for new functionality. (101a2b0) (@vinhnx)
• Refactor LLM request handling, improve reasoning processing, and enhance tool command parsing (896f6c6) (@vinhnx)
• Implement streaming response rendering with reasoning support and helper functions (b3ba347) (@vinhnx)
• Refactor file operations to use utility functions for directory creation and file reading/writing (7f800b3) (@vinhnx)
• Implement unified session loop for agent execution and remove plugin marketplace commands (17d9597) (@vinhnx)
• Add tests for model picker and prompt refinement functionality (0305390) (@vinhnx)
• Enhance configuration and logging for agent and hooks; add mock MCP server for integration tests (59a48db) (@vinhnx)
• Refactor agent runner to use AgentSessionState for session management and update related components (083fcac) (@vinhnx)
• Refactor apply_patch handler for improved output handling; streamline sandbox policy mapping (67c0e05) (@vinhnx)
• Refactor caching logic for improved performance; enhance error context handling; update tests for accurate cache statistics (5a10f0d) (@vinhnx)
• Refactor exec_policy and command validation; consolidate HTTP client utilities; enhance error handling; improve file operations; update middleware to async; clean up validation cache; and adjust rate ...

What's Changed

Features

• introduce CI cost optimization strategies, add a new --ci-only release mode, and document release workflow details. (dd2f316) (@vinhnx)
• standardize MiniMax-M2.5 model identifier, promote it as the default, and update configuration defaults. (ff6dcef) (@vinhnx)
• Add top-level cache control to Anthropic requests, with TTL determined by breakpoint consumption. (91c0c9e) (@vinhnx)
• Add prompt_cache_key to OpenAI requests for improved cache locality and simplify Responses API usage logic. (45c9002) (@vinhnx)
• Implement Gemini prompt caching with TTL using a new CacheControl part and add support for Gemini 3.1 Pro preview models. (8b5b42a) (@vinhnx)
• Implement Gemini 3.1 Pro Preview models with updated token limits and system prompt handling. (dc0742c) (@vinhnx)
• add Claude Sonnet 4.6 model support and integrate it across model definitions, parsing, catalog, and documentation. (d460c56) (@vinhnx)
• Implement mouse text selection in the TUI and add a new vtcode.toml configuration file. (8356715) (@vinhnx)
• Render GFM tables inside markdown code blocks as tables and prevent word-wrapping for table lines in the TUI. (c90f06e) (@vinhnx)
• Implement mouse scroll support for TUI session and history picker, and update default agent configuration to Ollama. (db99f4d) (@vinhnx)
• refactor build process to use conditional cross compilation for Linux and Windows (d15bb55) (@vinhnx)
• add full CI mode to release script for all platforms (326a2c8) (@vinhnx)
• add CI workflows for building Linux and Windows binaries; optimize release process (090bebb) (@vinhnx)
• implement secure storage for custom API keys using OS keyring (3da5a60) (@vinhnx)
• add Qwen3.5-397B-A17B model with hybrid architecture and update configuration (26a9a7e) (@vinhnx)
• implement mouse scroll handling for improved navigation (24a2d64) (@vinhnx)
• add timeout handling for turn metadata collection (1b1f91d) (@vinhnx)
• implement credential storage using OS keyring and file fallback (1e94c71) (@vinhnx)
• add sanitizer module for secret redaction and integrate into output handling (4263808) (@vinhnx)
• add Kimi K2.5 model support across OpenRouter, Ollama, and HuggingFace. (fddc488) (@vinhnx)
• introduce agent legibility guidelines and refine steering message variants for clarity and structured output. (52b13dd) (@vinhnx)
• Use configurable constants for agent session limits and expose the default max context tokens function. (21d1183) (@vinhnx)
• Enhance reasoning display by introducing structured ReasoningSegment with stages and improved rendering in the TUI. (68d07c9) (@vinhnx)
• Implement agent steering mechanism to control runloop execution, including stop, pause, resume, and input injection capabilities. (ac806e0) (@vinhnx)
• add /share-log command to export session log as JSON for debugging (6430582) (@vinhnx)
• implement in-process teammate runner and enhance team protocol messaging (4aff931) (@vinhnx)
• implement plan mode toggle and strip proposed plan blocks in rendering (79f0327) (@vinhnx)
• add skill bundle import/export functionality with zip support (dea5b5b) (@vinhnx)
• add Qwen3 Coder Next model support and update related constants (5a4303e) (@vinhnx)
• add MiniMax M2.5 model support across various providers and update related constants (968963f) (@vinhnx)

Bug Fixes

• correct exec_code policy and update TODO for markdown rendering issue (9b87f88) (@vinhnx)
• resolve critical scrolling issue and remove unused slash command handlers (bcb8143) (@vinhnx)

Refactors

• Make TUI signal cleanup and dotfile permission backup UNIX-specific. (14a4f2d) (@vinhnx)
• remove unused imports and enhance configuration for credential storage (b79f2bd) (@vinhnx)
• clean up code formatting and improve readability across multiple files (b1ae3ad) (@vinhnx)
• remove Rust cache step from release workflow (e36c5f5) (@vinhnx)
• streamline MCP tool management and indexing in ToolRegistry (a5c3677) (@vinhnx)
• consolidate duplicated logic across workspace crates into shared utility functions (a9df41f) (@vinhnx)
• replace manual file operations with shared utility functions for consistency (15c45f9) (@vinhnx)
• replace manual file operations with shared utility functions for consistency (7fcbe5f) (@vinhnx)
• replace manual file operations with shared utility functions for consistency (54c447a) (@vinhnx)
• streamline file operations and enhance workspace path handling (f7ebb78) (@vinhnx)
• extract large event handler modules into smaller files for improved navigation (9eda39e) (@vinhnx)
• reimplement LLM streaming and event handling using AgentSessionController and its event sink mechanism. (95bcd08) (@vinhnx)
• remove unused ReasoningSegment import from turn_processing.rs (9f4672d) (@vinhnx)

Documentation

• Add a guide for adding new models to AGENTS.md. (8648b58) (@vinhnx)
• update documentation for TECH_DEBT_TRACKER and QUALITY_SCORE; add tests for subagent loading and file operations (fb7c094) (@vinhnx)
• update contributing guidelines to reference CONTRIBUTING.md and AGENTS.md. (b4a1ef7) (@vinhnx)
• update documentation and improve clarity on execution plans, architectural invariants, and quality scores feat: enhance system instruction generation to replace placeholders with unified tool guidance (27c61ef) (@vinhnx)

Chores

• Release (28a8476) (@vinhnx)
• Release (77422be) (@vinhnx)
• Release (1402781) (@vinhnx)
• Release (6c982a3) (@vinhnx)
• clean up configuration file by removing unused custom API keys and simplifying array formatting (ad594e4) (@vinhnx)
• Release (4bd94bd) (@vinhnx)
• Release (800c706) (@vinhnx)
• Release (a08f765) (@vinhnx)
• Release (accdcc2) (@vinhnx)
• Release (69df0e2) (@vinhnx)
• Release (10e4f28) (@vinhnx)

Other

• Update commit (9d05e9d) (@vinhnx)
• Enhance model behavior configuration for LLM providers (0fa1233) (@vinhnx)
• Add scripts for documentation link validation and markdown location checks (7290fc5) (@vinhnx)
• Update default model in vtcode.toml to minimax-m2:cloud; format code for consistency (e024a48) (@vinhnx)
• Add additional_agent_dirs configuration option to vtcode.toml (0f6d174) (@vinhnx)
• Remove custom prompts feature and related code; update error handling for agent actions; refine UI shortcuts and command handling (cfcc976) (@vinhnx)
• Remove custom prompts feature and related code (dfc3ec5) (@vinhnx)
• Update LLM provider configuration to use Ollama and remove unused typos.toml file (ca83bdc) (@vinhnx)
• Enhance agent runner settings and improve loop detection; update CLI commands for reasoning effort and verbosity; refine patch handling in file operations; adjust markdown diff summary; modify configuration for LLM provider. (ff221d1) (@vinhnx)
• Refactor agent runner and tool registry for improved error handling and normalization; enhance loop detection and add tests for new functionality. (101a2b0) (@vinhnx)
• Refactor LLM request handling, improve reasoning processing, and enhance tool command parsing (896f6c6) (@vinhnx)
• Implement streaming response rendering with reasoning support and helper functions (b3ba347) (@vinhnx)
• Refactor file operations to use utility functions for directory creation and file reading/writing (7f800b3) (@vinhnx)
• Implement unified session loop for agent execution and remove plugin marketplace commands (17d9597) (@vinhnx)
• Add tests for model picker and prompt refinement functionality (0305390) (@vinhnx)
• Enhance configuration and logging for agent and hooks; add mock MCP server for integration tests (59a48db) (@vinhnx)
• Refactor agent runner to use AgentSessionState for session management and update related components (083fcac) (@vinhnx)
• Refactor apply_patch handler for improved output handling; streamline sandbox policy mapping (67c0e05) (@vinhnx)
• Refactor caching logic for improved performance; enhance error context handling; update tests for accurate cache statistics (5a10f0d) (@vinhnx)
• Refactor exec_policy and command validation; consolidate HTTP client utilities; enhance error handling; improve file operations; update middleware to async; clean up validation cache; and adjust rate limiting implementation. (e6245af) (@vinhnx)
• Adjust provider configurations and logging. (a649d02) (@vinhnx)
• Add support for inline skill bundles and network policies in skills (ddb9d28) (@vinhnx)
• Add architectural invariants, core beliefs, execution plans, quality score, and tech debt tracker documentation (80cf6d6) (@vinhnx)

Full Changelog: v0.79.1...0.82.1

What's Changed

Features

• Implement Gemini prompt caching with TTL using a new CacheControl part and add support for Gemini 3.1 Pro preview models. (8b5b42a) (@vinhnx)
• Implement Gemini 3.1 Pro Preview models with updated token limits and system prompt handling. (dc0742c) (@vinhnx)
• add Claude Sonnet 4.6 model support and integrate it across model definitions, parsing, catalog, and documentation. (d460c56) (@vinhnx)
• Implement mouse text selection in the TUI and add a new vtcode.toml configuration file. (8356715) (@vinhnx)
• Render GFM tables inside markdown code blocks as tables and prevent word-wrapping for table lines in the TUI. (c90f06e) (@vinhnx)
• Implement mouse scroll support for TUI session and history picker, and update default agent configuration to Ollama. (db99f4d) (@vinhnx)
• refactor build process to use conditional cross compilation for Linux and Windows (d15bb55) (@vinhnx)
• add full CI mode to release script for all platforms (326a2c8) (@vinhnx)
• add CI workflows for building Linux and Windows binaries; optimize release process (090bebb) (@vinhnx)
• implement secure storage for custom API keys using OS keyring (3da5a60) (@vinhnx)
• add Qwen3.5-397B-A17B model with hybrid architecture and update configuration (26a9a7e) (@vinhnx)
• implement mouse scroll handling for improved navigation (24a2d64) (@vinhnx)
• add timeout handling for turn metadata collection (1b1f91d) (@vinhnx)
• implement credential storage using OS keyring and file fallback (1e94c71) (@vinhnx)
• add sanitizer module for secret redaction and integrate into output handling (4263808) (@vinhnx)
• add Kimi K2.5 model support across OpenRouter, Ollama, and HuggingFace. (fddc488) (@vinhnx)
• introduce agent legibility guidelines and refine steering message variants for clarity and structured output. (52b13dd) (@vinhnx)
• Use configurable constants for agent session limits and expose the default max context tokens function. (21d1183) (@vinhnx)
• Enhance reasoning display by introducing structured ReasoningSegment with stages and improved rendering in the TUI. (68d07c9) (@vinhnx)
• Implement agent steering mechanism to control runloop execution, including stop, pause, resume, and input injection capabilities. (ac806e0) (@vinhnx)
• add /share-log command to export session log as JSON for debugging (6430582) (@vinhnx)
• implement in-process teammate runner and enhance team protocol messaging (4aff931) (@vinhnx)
• implement plan mode toggle and strip proposed plan blocks in rendering (79f0327) (@vinhnx)
• add skill bundle import/export functionality with zip support (dea5b5b) (@vinhnx)
• add Qwen3 Coder Next model support and update related constants (5a4303e) (@vinhnx)
• add MiniMax M2.5 model support across various providers and update related constants (968963f) (@vinhnx)

Bug Fixes

• correct exec_code policy and update TODO for markdown rendering issue (9b87f88) (@vinhnx)
• resolve critical scrolling issue and remove unused slash command handlers (bcb8143) (@vinhnx)

Refactors

• remove unused imports and enhance configuration for credential storage (b79f2bd) (@vinhnx)
• clean up code formatting and improve readability across multiple files (b1ae3ad) (@vinhnx)
• remove Rust cache step from release workflow (e36c5f5) (@vinhnx)
• streamline MCP tool management and indexing in ToolRegistry (a5c3677) (@vinhnx)
• consolidate duplicated logic across workspace crates into shared utility functions (a9df41f) (@vinhnx)
• replace manual file operations with shared utility functions for consistency (15c45f9) (@vinhnx)
• replace manual file operations with shared utility functions for consistency (7fcbe5f) (@vinhnx)
• replace manual file operations with shared utility functions for consistency (54c447a) (@vinhnx)
• streamline file operations and enhance workspace path handling (f7ebb78) (@vinhnx)
• extract large event handler modules into smaller files for improved navigation (9eda39e) (@vinhnx)
• reimplement LLM streaming and event handling using AgentSessionController and its event sink mechanism. (95bcd08) (@vinhnx)
• remove unused ReasoningSegment import from turn_processing.rs (9f4672d) (@vinhnx)

Documentation

• Add a guide for adding new models to AGENTS.md. (8648b58) (@vinhnx)
• update documentation for TECH_DEBT_TRACKER and QUALITY_SCORE; add tests for subagent loading and file operations (fb7c094) (@vinhnx)
• update contributing guidelines to reference CONTRIBUTING.md and AGENTS.md. (b4a1ef7) (@vinhnx)
• update documentation and improve clarity on execution plans, architectural invariants, and quality scores feat: enhance system instruction generation to replace placeholders with unified tool guidance (27c61ef) (@vinhnx)

Chores

• Release (77422be) (@vinhnx)
• Release (1402781) (@vinhnx)
• Release (6c982a3) (@vinhnx)
• clean up configuration file by removing unused custom API keys and simplifying array formatting (ad594e4) (@vinhnx)
• Release (4bd94bd) (@vinhnx)
• Release (800c706) (@vinhnx)
• Release (a08f765) (@vinhnx)
• Release (accdcc2) (@vinhnx)
• Release (69df0e2) (@vinhnx)
• Release (10e4f28) (@vinhnx)

Other

• Update commit (9d05e9d) (@vinhnx)
• Enhance model behavior configuration for LLM providers (0fa1233) (@vinhnx)
• Add scripts for documentation link validation and markdown location checks (7290fc5) (@vinhnx)
• Update default model in vtcode.toml to minimax-m2:cloud; format code for consistency (e024a48) (@vinhnx)
• Add additional_agent_dirs configuration option to vtcode.toml (0f6d174) (@vinhnx)
• Remove custom prompts feature and related code; update error handling for agent actions; refine UI shortcuts and command handling (cfcc976) (@vinhnx)
• Remove custom prompts feature and related code (dfc3ec5) (@vinhnx)
• Update LLM provider configuration to use Ollama and remove unused typos.toml file (ca83bdc) (@vinhnx)
• Enhance agent runner settings and improve loop detection; update CLI commands for reasoning effort and verbosity; refine patch handling in file operations; adjust markdown diff summary; modify configuration for LLM provider. (ff221d1) (@vinhnx)
• Refactor agent runner and tool registry for improved error handling and normalization; enhance loop detection and add tests for new functionality. (101a2b0) (@vinhnx)
• Refactor LLM request handling, improve reasoning processing, and enhance tool command parsing (896f6c6) (@vinhnx)
• Implement streaming response rendering with reasoning support and helper functions (b3ba347) (@vinhnx)
• Refactor file operations to use utility functions for directory creation and file reading/writing (7f800b3) (@vinhnx)
• Implement unified session loop for agent execution and remove plugin marketplace commands (17d9597) (@vinhnx)
• Add tests for model picker and prompt refinement functionality (0305390) (@vinhnx)
• Enhance configuration and logging for agent and hooks; add mock MCP server for integration tests (59a48db) (@vinhnx)
• Refactor agent runner to use AgentSessionState for session management and update related components (083fcac) (@vinhnx)
• Refactor apply_patch handler for improved output handling; streamline sandbox policy mapping (67c0e05) (@vinhnx)
• Refactor caching logic for improved performance; enhance error context handling; update tests for accurate cache statistics (5a10f0d) (@vinhnx)
• Refactor exec_policy and command validation; consolidate HTTP client utilities; enhance error handling; improve file operations; update middleware to async; clean up validation cache; and adjust rate limiting implementation. (e6245af) (@vinhnx)
• Adjust provider configurations and logging. (a649d02) (@vinhnx)
• Add support for inline skill bundles and network policies in skills (ddb9d28) (@vinhnx)
• Add architectural invariants, core beliefs, execution plans, quality score, and tech debt tracker documentation (80cf6d6) (@vinhnx)

Full Changelog: v0.79.1...0.82.0

What's Changed

Features

• refactor build process to use conditional cross compilation for Linux and Windows (d15bb55) (@vinhnx)
• add full CI mode to release script for all platforms (326a2c8) (@vinhnx)
• add CI workflows for building Linux and Windows binaries; optimize release process (090bebb) (@vinhnx)
• implement secure storage for custom API keys using OS keyring (3da5a60) (@vinhnx)
• add Qwen3.5-397B-A17B model with hybrid architecture and update configuration (26a9a7e) (@vinhnx)
• implement mouse scroll handling for improved navigation (24a2d64) (@vinhnx)
• add timeout handling for turn metadata collection (1b1f91d) (@vinhnx)
• implement credential storage using OS keyring and file fallback (1e94c71) (@vinhnx)
• add sanitizer module for secret redaction and integrate into output handling (4263808) (@vinhnx)
• add Kimi K2.5 model support across OpenRouter, Ollama, and HuggingFace. (fddc488) (@vinhnx)
• introduce agent legibility guidelines and refine steering message variants for clarity and structured output. (52b13dd) (@vinhnx)
• Use configurable constants for agent session limits and expose the default max context tokens function. (21d1183) (@vinhnx)
• Enhance reasoning display by introducing structured ReasoningSegment with stages and improved rendering in the TUI. (68d07c9) (@vinhnx)
• Implement agent steering mechanism to control runloop execution, including stop, pause, resume, and input injection capabilities. (ac806e0) (@vinhnx)
• add /share-log command to export session log as JSON for debugging (6430582) (@vinhnx)
• implement in-process teammate runner and enhance team protocol messaging (4aff931) (@vinhnx)
• implement plan mode toggle and strip proposed plan blocks in rendering (79f0327) (@vinhnx)
• add skill bundle import/export functionality with zip support (dea5b5b) (@vinhnx)
• add Qwen3 Coder Next model support and update related constants (5a4303e) (@vinhnx)
• add MiniMax M2.5 model support across various providers and update related constants (968963f) (@vinhnx)

Bug Fixes

• correct exec_code policy and update TODO for markdown rendering issue (9b87f88) (@vinhnx)
• resolve critical scrolling issue and remove unused slash command handlers (bcb8143) (@vinhnx)

Refactors

• remove unused imports and enhance configuration for credential storage (b79f2bd) (@vinhnx)
• clean up code formatting and improve readability across multiple files (b1ae3ad) (@vinhnx)
• remove Rust cache step from release workflow (e36c5f5) (@vinhnx)
• streamline MCP tool management and indexing in ToolRegistry (a5c3677) (@vinhnx)
• consolidate duplicated logic across workspace crates into shared utility functions (a9df41f) (@vinhnx)
• replace manual file operations with shared utility functions for consistency (15c45f9) (@vinhnx)
• replace manual file operations with shared utility functions for consistency (7fcbe5f) (@vinhnx)
• replace manual file operations with shared utility functions for consistency (54c447a) (@vinhnx)
• streamline file operations and enhance workspace path handling (f7ebb78) (@vinhnx)
• extract large event handler modules into smaller files for improved navigation (9eda39e) (@vinhnx)
• reimplement LLM streaming and event handling using AgentSessionController and its event sink mechanism. (95bcd08) (@vinhnx)
• remove unused ReasoningSegment import from turn_processing.rs (9f4672d) (@vinhnx)

Documentation

• update documentation for TECH_DEBT_TRACKER and QUALITY_SCORE; add tests for subagent loading and file operations (fb7c094) (@vinhnx)
• update contributing guidelines to reference CONTRIBUTING.md and AGENTS.md. (b4a1ef7) (@vinhnx)
• update documentation and improve clarity on execution plans, architectural invariants, and quality scores feat: enhance system instruction generation to replace placeholders with unified tool guidance (27c61ef) (@vinhnx)

Chores

• Release (1402781) (@vinhnx)
• Release (6c982a3) (@vinhnx)
• clean up configuration file by removing unused custom API keys and simplifying array formatting (ad594e4) (@vinhnx)
• Release (4bd94bd) (@vinhnx)
• Release (800c706) (@vinhnx)
• Release (a08f765) (@vinhnx)
• Release (accdcc2) (@vinhnx)
• Release (69df0e2) (@vinhnx)
• Release (10e4f28) (@vinhnx)

Other

• Enhance model behavior configuration for LLM providers (0fa1233) (@vinhnx)
• Add scripts for documentation link validation and markdown location checks (7290fc5) (@vinhnx)
• Update default model in vtcode.toml to minimax-m2:cloud; format code for consistency (e024a48) (@vinhnx)
• Add additional_agent_dirs configuration option to vtcode.toml (0f6d174) (@vinhnx)
• Remove custom prompts feature and related code; update error handling for agent actions; refine UI shortcuts and command handling (cfcc976) (@vinhnx)
• Remove custom prompts feature and related code (dfc3ec5) (@vinhnx)
• Update LLM provider configuration to use Ollama and remove unused typos.toml file (ca83bdc) (@vinhnx)
• Enhance agent runner settings and improve loop detection; update CLI commands for reasoning effort and verbosity; refine patch handling in file operations; adjust markdown diff summary; modify configuration for LLM provider. (ff221d1) (@vinhnx)
• Refactor agent runner and tool registry for improved error handling and normalization; enhance loop detection and add tests for new functionality. (101a2b0) (@vinhnx)
• Refactor LLM request handling, improve reasoning processing, and enhance tool command parsing (896f6c6) (@vinhnx)
• Implement streaming response rendering with reasoning support and helper functions (b3ba347) (@vinhnx)
• Refactor file operations to use utility functions for directory creation and file reading/writing (7f800b3) (@vinhnx)
• Implement unified session loop for agent execution and remove plugin marketplace commands (17d9597) (@vinhnx)
• Add tests for model picker and prompt refinement functionality (0305390) (@vinhnx)
• Enhance configuration and logging for agent and hooks; add mock MCP server for integration tests (59a48db) (@vinhnx)
• Refactor agent runner to use AgentSessionState for session management and update related components (083fcac) (@vinhnx)
• Refactor apply_patch handler for improved output handling; streamline sandbox policy mapping (67c0e05) (@vinhnx)
• Refactor caching logic for improved performance; enhance error context handling; update tests for accurate cache statistics (5a10f0d) (@vinhnx)
• Refactor exec_policy and command validation; consolidate HTTP client utilities; enhance error handling; improve file operations; update middleware to async; clean up validation cache; and adjust rate limiting implementation. (e6245af) (@vinhnx)
• Adjust provider configurations and logging. (a649d02) (@vinhnx)
• Add support for inline skill bundles and network policies in skills (ddb9d28) (@vinhnx)
• Add architectural invariants, core beliefs, execution plans, quality score, and tech debt tracker documentation (80cf6d6) (@vinhnx)

Full Changelog: v0.79.1...0.81.3

What's Changed

Features

• add full CI mode to release script for all platforms (326a2c8) (@vinhnx)
• add CI workflows for building Linux and Windows binaries; optimize release process (090bebb) (@vinhnx)
• implement secure storage for custom API keys using OS keyring (3da5a60) (@vinhnx)
• add Qwen3.5-397B-A17B model with hybrid architecture and update configuration (26a9a7e) (@vinhnx)
• implement mouse scroll handling for improved navigation (24a2d64) (@vinhnx)
• add timeout handling for turn metadata collection (1b1f91d) (@vinhnx)
• implement credential storage using OS keyring and file fallback (1e94c71) (@vinhnx)
• add sanitizer module for secret redaction and integrate into output handling (4263808) (@vinhnx)
• add Kimi K2.5 model support across OpenRouter, Ollama, and HuggingFace. (fddc488) (@vinhnx)
• introduce agent legibility guidelines and refine steering message variants for clarity and structured output. (52b13dd) (@vinhnx)
• Use configurable constants for agent session limits and expose the default max context tokens function. (21d1183) (@vinhnx)
• Enhance reasoning display by introducing structured ReasoningSegment with stages and improved rendering in the TUI. (68d07c9) (@vinhnx)
• Implement agent steering mechanism to control runloop execution, including stop, pause, resume, and input injection capabilities. (ac806e0) (@vinhnx)
• add /share-log command to export session log as JSON for debugging (6430582) (@vinhnx)
• implement in-process teammate runner and enhance team protocol messaging (4aff931) (@vinhnx)
• implement plan mode toggle and strip proposed plan blocks in rendering (79f0327) (@vinhnx)
• add skill bundle import/export functionality with zip support (dea5b5b) (@vinhnx)
• add Qwen3 Coder Next model support and update related constants (5a4303e) (@vinhnx)
• add MiniMax M2.5 model support across various providers and update related constants (968963f) (@vinhnx)

Bug Fixes

• correct exec_code policy and update TODO for markdown rendering issue (9b87f88) (@vinhnx)
• resolve critical scrolling issue and remove unused slash command handlers (bcb8143) (@vinhnx)

Refactors

• remove unused imports and enhance configuration for credential storage (b79f2bd) (@vinhnx)
• clean up code formatting and improve readability across multiple files (b1ae3ad) (@vinhnx)
• remove Rust cache step from release workflow (e36c5f5) (@vinhnx)
• streamline MCP tool management and indexing in ToolRegistry (a5c3677) (@vinhnx)
• consolidate duplicated logic across workspace crates into shared utility functions (a9df41f) (@vinhnx)
• replace manual file operations with shared utility functions for consistency (15c45f9) (@vinhnx)
• replace manual file operations with shared utility functions for consistency (7fcbe5f) (@vinhnx)
• replace manual file operations with shared utility functions for consistency (54c447a) (@vinhnx)
• streamline file operations and enhance workspace path handling (f7ebb78) (@vinhnx)
• extract large event handler modules into smaller files for improved navigation (9eda39e) (@vinhnx)
• reimplement LLM streaming and event handling using AgentSessionController and its event sink mechanism. (95bcd08) (@vinhnx)
• remove unused ReasoningSegment import from turn_processing.rs (9f4672d) (@vinhnx)

Documentation

• update documentation for TECH_DEBT_TRACKER and QUALITY_SCORE; add tests for subagent loading and file operations (fb7c094) (@vinhnx)
• update contributing guidelines to reference CONTRIBUTING.md and AGENTS.md. (b4a1ef7) (@vinhnx)
• update documentation and improve clarity on execution plans, architectural invariants, and quality scores feat: enhance system instruction generation to replace placeholders with unified tool guidance (27c61ef) (@vinhnx)

Chores

• Release (6c982a3) (@vinhnx)
• clean up configuration file by removing unused custom API keys and simplifying array formatting (ad594e4) (@vinhnx)
• Release (4bd94bd) (@vinhnx)
• Release (800c706) (@vinhnx)
• Release (a08f765) (@vinhnx)
• Release (accdcc2) (@vinhnx)
• Release (69df0e2) (@vinhnx)
• Release (10e4f28) (@vinhnx)

Other

• Enhance model behavior configuration for LLM providers (0fa1233) (@vinhnx)
• Add scripts for documentation link validation and markdown location checks (7290fc5) (@vinhnx)
• Update default model in vtcode.toml to minimax-m2:cloud; format code for consistency (e024a48) (@vinhnx)
• Add additional_agent_dirs configuration option to vtcode.toml (0f6d174) (@vinhnx)
• Remove custom prompts feature and related code; update error handling for agent actions; refine UI shortcuts and command handling (cfcc976) (@vinhnx)
• Remove custom prompts feature and related code (dfc3ec5) (@vinhnx)
• Update LLM provider configuration to use Ollama and remove unused typos.toml file (ca83bdc) (@vinhnx)
• Enhance agent runner settings and improve loop detection; update CLI commands for reasoning effort and verbosity; refine patch handling in file operations; adjust markdown diff summary; modify configuration for LLM provider. (ff221d1) (@vinhnx)
• Refactor agent runner and tool registry for improved error handling and normalization; enhance loop detection and add tests for new functionality. (101a2b0) (@vinhnx)
• Refactor LLM request handling, improve reasoning processing, and enhance tool command parsing (896f6c6) (@vinhnx)
• Implement streaming response rendering with reasoning support and helper functions (b3ba347) (@vinhnx)
• Refactor file operations to use utility functions for directory creation and file reading/writing (7f800b3) (@vinhnx)
• Implement unified session loop for agent execution and remove plugin marketplace commands (17d9597) (@vinhnx)
• Add tests for model picker and prompt refinement functionality (0305390) (@vinhnx)
• Enhance configuration and logging for agent and hooks; add mock MCP server for integration tests (59a48db) (@vinhnx)
• Refactor agent runner to use AgentSessionState for session management and update related components (083fcac) (@vinhnx)
• Refactor apply_patch handler for improved output handling; streamline sandbox policy mapping (67c0e05) (@vinhnx)
• Refactor caching logic for improved performance; enhance error context handling; update tests for accurate cache statistics (5a10f0d) (@vinhnx)
• Refactor exec_policy and command validation; consolidate HTTP client utilities; enhance error handling; improve file operations; update middleware to async; clean up validation cache; and adjust rate limiting implementation. (e6245af) (@vinhnx)
• Adjust provider configurations and logging. (a649d02) (@vinhnx)
• Add support for inline skill bundles and network policies in skills (ddb9d28) (@vinhnx)
• Add architectural invariants, core beliefs, execution plans, quality score, and tech debt tracker documentation (80cf6d6) (@vinhnx)

Full Changelog: v0.79.1...0.81.2

What's Changed

Features

• implement secure storage for custom API keys using OS keyring (3da5a60) (@vinhnx)
• add Qwen3.5-397B-A17B model with hybrid architecture and update configuration (26a9a7e) (@vinhnx)
• implement mouse scroll handling for improved navigation (24a2d64) (@vinhnx)
• add timeout handling for turn metadata collection (1b1f91d) (@vinhnx)
• implement credential storage using OS keyring and file fallback (1e94c71) (@vinhnx)
• add sanitizer module for secret redaction and integrate into output handling (4263808) (@vinhnx)
• add Kimi K2.5 model support across OpenRouter, Ollama, and HuggingFace. (fddc488) (@vinhnx)
• introduce agent legibility guidelines and refine steering message variants for clarity and structured output. (52b13dd) (@vinhnx)
• Use configurable constants for agent session limits and expose the default max context tokens function. (21d1183) (@vinhnx)
• Enhance reasoning display by introducing structured ReasoningSegment with stages and improved rendering in the TUI. (68d07c9) (@vinhnx)
• Implement agent steering mechanism to control runloop execution, including stop, pause, resume, and input injection capabilities. (ac806e0) (@vinhnx)
• add /share-log command to export session log as JSON for debugging (6430582) (@vinhnx)
• implement in-process teammate runner and enhance team protocol messaging (4aff931) (@vinhnx)
• implement plan mode toggle and strip proposed plan blocks in rendering (79f0327) (@vinhnx)
• add skill bundle import/export functionality with zip support (dea5b5b) (@vinhnx)
• add Qwen3 Coder Next model support and update related constants (5a4303e) (@vinhnx)
• add MiniMax M2.5 model support across various providers and update related constants (968963f) (@vinhnx)

Bug Fixes

• correct exec_code policy and update TODO for markdown rendering issue (9b87f88) (@vinhnx)
• resolve critical scrolling issue and remove unused slash command handlers (bcb8143) (@vinhnx)

Refactors

• remove unused imports and enhance configuration for credential storage (b79f2bd) (@vinhnx)
• clean up code formatting and improve readability across multiple files (b1ae3ad) (@vinhnx)
• remove Rust cache step from release workflow (e36c5f5) (@vinhnx)
• streamline MCP tool management and indexing in ToolRegistry (a5c3677) (@vinhnx)
• consolidate duplicated logic across workspace crates into shared utility functions (a9df41f) (@vinhnx)
• replace manual file operations with shared utility functions for consistency (15c45f9) (@vinhnx)
• replace manual file operations with shared utility functions for consistency (7fcbe5f) (@vinhnx)
• replace manual file operations with shared utility functions for consistency (54c447a) (@vinhnx)
• streamline file operations and enhance workspace path handling (f7ebb78) (@vinhnx)
• extract large event handler modules into smaller files for improved navigation (9eda39e) (@vinhnx)
• reimplement LLM streaming and event handling using AgentSessionController and its event sink mechanism. (95bcd08) (@vinhnx)
• remove unused ReasoningSegment import from turn_processing.rs (9f4672d) (@vinhnx)

Documentation

• update documentation for TECH_DEBT_TRACKER and QUALITY_SCORE; add tests for subagent loading and file operations (fb7c094) (@vinhnx)
• update contributing guidelines to reference CONTRIBUTING.md and AGENTS.md. (b4a1ef7) (@vinhnx)
• update documentation and improve clarity on execution plans, architectural invariants, and quality scores feat: enhance system instruction generation to replace placeholders with unified tool guidance (27c61ef) (@vinhnx)

Chores

• clean up configuration file by removing unused custom API keys and simplifying array formatting (ad594e4) (@vinhnx)
• Release (4bd94bd) (@vinhnx)
• Release (800c706) (@vinhnx)
• Release (a08f765) (@vinhnx)
• Release (accdcc2) (@vinhnx)
• Release (69df0e2) (@vinhnx)
• Release (10e4f28) (@vinhnx)

Other

• Enhance model behavior configuration for LLM providers (0fa1233) (@vinhnx)
• Add scripts for documentation link validation and markdown location checks (7290fc5) (@vinhnx)
• Update default model in vtcode.toml to minimax-m2:cloud; format code for consistency (e024a48) (@vinhnx)
• Add additional_agent_dirs configuration option to vtcode.toml (0f6d174) (@vinhnx)
• Remove custom prompts feature and related code; update error handling for agent actions; refine UI shortcuts and command handling (cfcc976) (@vinhnx)
• Remove custom prompts feature and related code (dfc3ec5) (@vinhnx)
• Update LLM provider configuration to use Ollama and remove unused typos.toml file (ca83bdc) (@vinhnx)
• Enhance agent runner settings and improve loop detection; update CLI commands for reasoning effort and verbosity; refine patch handling in file operations; adjust markdown diff summary; modify configuration for LLM provider. (ff221d1) (@vinhnx)
• Refactor agent runner and tool registry for improved error handling and normalization; enhance loop detection and add tests for new functionality. (101a2b0) (@vinhnx)
• Refactor LLM request handling, improve reasoning processing, and enhance tool command parsing (896f6c6) (@vinhnx)
• Implement streaming response rendering with reasoning support and helper functions (b3ba347) (@vinhnx)
• Refactor file operations to use utility functions for directory creation and file reading/writing (7f800b3) (@vinhnx)
• Implement unified session loop for agent execution and remove plugin marketplace commands (17d9597) (@vinhnx)
• Add tests for model picker and prompt refinement functionality (0305390) (@vinhnx)
• Enhance configuration and logging for agent and hooks; add mock MCP server for integration tests (59a48db) (@vinhnx)
• Refactor agent runner to use AgentSessionState for session management and update related components (083fcac) (@vinhnx)
• Refactor apply_patch handler for improved output handling; streamline sandbox policy mapping (67c0e05) (@vinhnx)
• Refactor caching logic for improved performance; enhance error context handling; update tests for accurate cache statistics (5a10f0d) (@vinhnx)
• Refactor exec_policy and command validation; consolidate HTTP client utilities; enhance error handling; improve file operations; update middleware to async; clean up validation cache; and adjust rate limiting implementation. (e6245af) (@vinhnx)
• Adjust provider configurations and logging. (a649d02) (@vinhnx)
• Add support for inline skill bundles and network policies in skills (ddb9d28) (@vinhnx)
• Add architectural invariants, core beliefs, execution plans, quality score, and tech debt tracker documentation (80cf6d6) (@vinhnx)

Full Changelog: v0.79.1...0.81.1

What's Changed

Features

• add Qwen3.5-397B-A17B model with hybrid architecture and update configuration (26a9a7e) (@vinhnx)
• implement mouse scroll handling for improved navigation (24a2d64) (@vinhnx)
• add timeout handling for turn metadata collection (1b1f91d) (@vinhnx)
• implement credential storage using OS keyring and file fallback (1e94c71) (@vinhnx)
• add sanitizer module for secret redaction and integrate into output handling (4263808) (@vinhnx)
• add Kimi K2.5 model support across OpenRouter, Ollama, and HuggingFace. (fddc488) (@vinhnx)
• introduce agent legibility guidelines and refine steering message variants for clarity and structured output. (52b13dd) (@vinhnx)
• Use configurable constants for agent session limits and expose the default max context tokens function. (21d1183) (@vinhnx)
• Enhance reasoning display by introducing structured ReasoningSegment with stages and improved rendering in the TUI. (68d07c9) (@vinhnx)
• Implement agent steering mechanism to control runloop execution, including stop, pause, resume, and input injection capabilities. (ac806e0) (@vinhnx)
• add /share-log command to export session log as JSON for debugging (6430582) (@vinhnx)
• implement in-process teammate runner and enhance team protocol messaging (4aff931) (@vinhnx)
• implement plan mode toggle and strip proposed plan blocks in rendering (79f0327) (@vinhnx)
• add skill bundle import/export functionality with zip support (dea5b5b) (@vinhnx)
• add Qwen3 Coder Next model support and update related constants (5a4303e) (@vinhnx)
• add MiniMax M2.5 model support across various providers and update related constants (968963f) (@vinhnx)

Bug Fixes

• correct exec_code policy and update TODO for markdown rendering issue (9b87f88) (@vinhnx)
• resolve critical scrolling issue and remove unused slash command handlers (bcb8143) (@vinhnx)

Refactors

• remove unused imports and enhance configuration for credential storage (b79f2bd) (@vinhnx)
• clean up code formatting and improve readability across multiple files (b1ae3ad) (@vinhnx)
• remove Rust cache step from release workflow (e36c5f5) (@vinhnx)
• streamline MCP tool management and indexing in ToolRegistry (a5c3677) (@vinhnx)
• consolidate duplicated logic across workspace crates into shared utility functions (a9df41f) (@vinhnx)
• replace manual file operations with shared utility functions for consistency (15c45f9) (@vinhnx)
• replace manual file operations with shared utility functions for consistency (7fcbe5f) (@vinhnx)
• replace manual file operations with shared utility functions for consistency (54c447a) (@vinhnx)
• streamline file operations and enhance workspace path handling (f7ebb78) (@vinhnx)
• extract large event handler modules into smaller files for improved navigation (9eda39e) (@vinhnx)
• reimplement LLM streaming and event handling using AgentSessionController and its event sink mechanism. (95bcd08) (@vinhnx)
• remove unused ReasoningSegment import from turn_processing.rs (9f4672d) (@vinhnx)

Documentation

• update documentation for TECH_DEBT_TRACKER and QUALITY_SCORE; add tests for subagent loading and file operations (fb7c094) (@vinhnx)
• update contributing guidelines to reference CONTRIBUTING.md and AGENTS.md. (b4a1ef7) (@vinhnx)
• update documentation and improve clarity on execution plans, architectural invariants, and quality scores feat: enhance system instruction generation to replace placeholders with unified tool guidance (27c61ef) (@vinhnx)

Chores

• Release (800c706) (@vinhnx)
• Release (a08f765) (@vinhnx)
• Release (accdcc2) (@vinhnx)
• Release (69df0e2) (@vinhnx)
• Release (10e4f28) (@vinhnx)

Other

• Enhance model behavior configuration for LLM providers (0fa1233) (@vinhnx)
• Add scripts for documentation link validation and markdown location checks (7290fc5) (@vinhnx)
• Update default model in vtcode.toml to minimax-m2:cloud; format code for consistency (e024a48) (@vinhnx)
• Add additional_agent_dirs configuration option to vtcode.toml (0f6d174) (@vinhnx)
• Remove custom prompts feature and related code; update error handling for agent actions; refine UI shortcuts and command handling (cfcc976) (@vinhnx)
• Remove custom prompts feature and related code (dfc3ec5) (@vinhnx)
• Update LLM provider configuration to use Ollama and remove unused typos.toml file (ca83bdc) (@vinhnx)
• Enhance agent runner settings and improve loop detection; update CLI commands for reasoning effort and verbosity; refine patch handling in file operations; adjust markdown diff summary; modify configuration for LLM provider. (ff221d1) (@vinhnx)
• Refactor agent runner and tool registry for improved error handling and normalization; enhance loop detection and add tests for new functionality. (101a2b0) (@vinhnx)
• Refactor LLM request handling, improve reasoning processing, and enhance tool command parsing (896f6c6) (@vinhnx)
• Implement streaming response rendering with reasoning support and helper functions (b3ba347) (@vinhnx)
• Refactor file operations to use utility functions for directory creation and file reading/writing (7f800b3) (@vinhnx)
• Implement unified session loop for agent execution and remove plugin marketplace commands (17d9597) (@vinhnx)
• Add tests for model picker and prompt refinement functionality (0305390) (@vinhnx)
• Enhance configuration and logging for agent and hooks; add mock MCP server for integration tests (59a48db) (@vinhnx)
• Refactor agent runner to use AgentSessionState for session management and update related components (083fcac) (@vinhnx)
• Refactor apply_patch handler for improved output handling; streamline sandbox policy mapping (67c0e05) (@vinhnx)
• Refactor caching logic for improved performance; enhance error context handling; update tests for accurate cache statistics (5a10f0d) (@vinhnx)
• Refactor exec_policy and command validation; consolidate HTTP client utilities; enhance error handling; improve file operations; update middleware to async; clean up validation cache; and adjust rate limiting implementation. (e6245af) (@vinhnx)
• Adjust provider configurations and logging. (a649d02) (@vinhnx)
• Add support for inline skill bundles and network policies in skills (ddb9d28) (@vinhnx)
• Add architectural invariants, core beliefs, execution plans, quality score, and tech debt tracker documentation (80cf6d6) (@vinhnx)

Full Changelog: v0.79.1...0.81.0

What's Changed

Features

• implement mouse scroll handling for improved navigation (24a2d64) (@vinhnx)
• add timeout handling for turn metadata collection (1b1f91d) (@vinhnx)
• implement credential storage using OS keyring and file fallback (1e94c71) (@vinhnx)
• add sanitizer module for secret redaction and integrate into output handling (4263808) (@vinhnx)
• add Kimi K2.5 model support across OpenRouter, Ollama, and HuggingFace. (fddc488) (@vinhnx)
• introduce agent legibility guidelines and refine steering message variants for clarity and structured output. (52b13dd) (@vinhnx)
• Use configurable constants for agent session limits and expose the default max context tokens function. (21d1183) (@vinhnx)
• Enhance reasoning display by introducing structured ReasoningSegment with stages and improved rendering in the TUI. (68d07c9) (@vinhnx)
• Implement agent steering mechanism to control runloop execution, including stop, pause, resume, and input injection capabilities. (ac806e0) (@vinhnx)
• add /share-log command to export session log as JSON for debugging (6430582) (@vinhnx)
• implement in-process teammate runner and enhance team protocol messaging (4aff931) (@vinhnx)
• implement plan mode toggle and strip proposed plan blocks in rendering (79f0327) (@vinhnx)
• add skill bundle import/export functionality with zip support (dea5b5b) (@vinhnx)
• add Qwen3 Coder Next model support and update related constants (5a4303e) (@vinhnx)
• add MiniMax M2.5 model support across various providers and update related constants (968963f) (@vinhnx)

Bug Fixes

• correct exec_code policy and update TODO for markdown rendering issue (9b87f88) (@vinhnx)
• resolve critical scrolling issue and remove unused slash command handlers (bcb8143) (@vinhnx)

Refactors

• remove unused imports and enhance configuration for credential storage (b79f2bd) (@vinhnx)
• clean up code formatting and improve readability across multiple files (b1ae3ad) (@vinhnx)
• remove Rust cache step from release workflow (e36c5f5) (@vinhnx)
• streamline MCP tool management and indexing in ToolRegistry (a5c3677) (@vinhnx)
• consolidate duplicated logic across workspace crates into shared utility functions (a9df41f) (@vinhnx)
• replace manual file operations with shared utility functions for consistency (15c45f9) (@vinhnx)
• replace manual file operations with shared utility functions for consistency (7fcbe5f) (@vinhnx)
• replace manual file operations with shared utility functions for consistency (54c447a) (@vinhnx)
• streamline file operations and enhance workspace path handling (f7ebb78) (@vinhnx)
• extract large event handler modules into smaller files for improved navigation (9eda39e) (@vinhnx)
• reimplement LLM streaming and event handling using AgentSessionController and its event sink mechanism. (95bcd08) (@vinhnx)
• remove unused ReasoningSegment import from turn_processing.rs (9f4672d) (@vinhnx)

Documentation

• update documentation for TECH_DEBT_TRACKER and QUALITY_SCORE; add tests for subagent loading and file operations (fb7c094) (@vinhnx)
• update contributing guidelines to reference CONTRIBUTING.md and AGENTS.md. (b4a1ef7) (@vinhnx)
• update documentation and improve clarity on execution plans, architectural invariants, and quality scores feat: enhance system instruction generation to replace placeholders with unified tool guidance (27c61ef) (@vinhnx)

Chores

• Release (a08f765) (@vinhnx)
• Release (accdcc2) (@vinhnx)
• Release (69df0e2) (@vinhnx)
• Release (10e4f28) (@vinhnx)

Other

• Enhance model behavior configuration for LLM providers (0fa1233) (@vinhnx)
• Add scripts for documentation link validation and markdown location checks (7290fc5) (@vinhnx)
• Update default model in vtcode.toml to minimax-m2:cloud; format code for consistency (e024a48) (@vinhnx)
• Add additional_agent_dirs configuration option to vtcode.toml (0f6d174) (@vinhnx)
• Remove custom prompts feature and related code; update error handling for agent actions; refine UI shortcuts and command handling (cfcc976) (@vinhnx)
• Remove custom prompts feature and related code (dfc3ec5) (@vinhnx)
• Update LLM provider configuration to use Ollama and remove unused typos.toml file (ca83bdc) (@vinhnx)
• Enhance agent runner settings and improve loop detection; update CLI commands for reasoning effort and verbosity; refine patch handling in file operations; adjust markdown diff summary; modify configuration for LLM provider. (ff221d1) (@vinhnx)
• Refactor agent runner and tool registry for improved error handling and normalization; enhance loop detection and add tests for new functionality. (101a2b0) (@vinhnx)
• Refactor LLM request handling, improve reasoning processing, and enhance tool command parsing (896f6c6) (@vinhnx)
• Implement streaming response rendering with reasoning support and helper functions (b3ba347) (@vinhnx)
• Refactor file operations to use utility functions for directory creation and file reading/writing (7f800b3) (@vinhnx)
• Implement unified session loop for agent execution and remove plugin marketplace commands (17d9597) (@vinhnx)
• Add tests for model picker and prompt refinement functionality (0305390) (@vinhnx)
• Enhance configuration and logging for agent and hooks; add mock MCP server for integration tests (59a48db) (@vinhnx)
• Refactor agent runner to use AgentSessionState for session management and update related components (083fcac) (@vinhnx)
• Refactor apply_patch handler for improved output handling; streamline sandbox policy mapping (67c0e05) (@vinhnx)
• Refactor caching logic for improved performance; enhance error context handling; update tests for accurate cache statistics (5a10f0d) (@vinhnx)
• Refactor exec_policy and command validation; consolidate HTTP client utilities; enhance error handling; improve file operations; update middleware to async; clean up validation cache; and adjust rate limiting implementation. (e6245af) (@vinhnx)
• Adjust provider configurations and logging. (a649d02) (@vinhnx)
• Add support for inline skill bundles and network policies in skills (ddb9d28) (@vinhnx)
• Add architectural invariants, core beliefs, execution plans, quality score, and tech debt tracker documentation (80cf6d6) (@vinhnx)

Full Changelog: v0.79.1...0.80.1