- Added real-time thinking line that updates with streaming message preview during agent processing.
- Changed tool execution output to display name and formatted argument block separately.
- Replaced generic message labels with content previews extracted from assistant responses.
- Replaced deterministic pipeline with agent session using specialized git tools for diff analysis.
- Introduced git-overview, git-file-diff, git-hunk, and analyze-file tools for fine-grained inspection.
- Added split-commit support to create multiple atomic commits for unrelated changes.
- Added commit message validation with filler word detection, meta phrase filtering, and unicode normalization.
- Added --legacy flag to use the deterministic pipeline when preferred.
- Extracted formatCommitMessage and model selection logic into dedicated modules.
- Added file locking mechanism to prevent concurrent write races in settings persistence.
- Exported `withFileLock` utility function for coordinating file access across processes.
- Integrated file locking into SettingsManager.save() to ensure atomic config updates.
- Added distinct root tracking to scope candidate extraction for improved wide change detection.
- Introduced extractTopLevelRoot() helper function to identify top-level directory roots in file paths.
- Enhanced isWideChange() function to consider number of distinct roots (3+) as a wide change indicator.
- Changed tool result rendering to merge call and result displays with tool arguments in headers across 13 tools.
- Added args parameter to render methods enabling display of contextual metadata like patterns, paths, and commands.
- Changed Read tool title to display line range when offset or limit arguments provided.
- Changed worker instantiation to use direct URL import instead of pre-bundled worker files.
- Removed streaming preview rendering logic from write tool.
- Created new TUI component library with renderStatusLine, renderOutputBlock, renderCodeCell, renderFileList, and renderTreeList utilities for consistent tool output rendering.
- Refactored 13+ tools to use centralized TUI components, replacing inline theme formatting and ToolUIKit class usage with declarative component APIs.
- Moved tree rendering utilities (getTreeBranch, getTreeContinuePrefix) from tool render-utils to TUI module for improved code organization.
- Streamlined render function return types across tools from Text to Component objects with render/invalidate methods for better state management.
- Added configurable map-reduce analysis settings for concurrency, timeout, file thresholds, and token limits.
- Made changelog diff truncation limit configurable via maxDiffChars parameter.
- Added support for excluding YAML lock files from commit analysis via suffix patterns.
- Created GitError custom error class with command and stderr tracking for structured error handling.
- Converted relative imports to alias-based '$c' imports across commit modules.
- Added CommitSettings interface with configurable map-reduce and changelog parameters.
- Added getCommitSettings() method to SettingsManager for retrieving commit configuration with sensible defaults.
- Added commit settings field to Settings interface.
- Improved YAML formatting by adding indentation parameter to YAML.stringify() calls for better readability.
- Removed redundant mkdirSync calls before Bun.write operations.
- Reorganized import statements in alphabetical order for consistency.
- Added worker bundle caching to pre-build and cache the worker script at startup, improving worker initialization performance.
- Introduced `workerBundlePromise` that bundles worker.ts using Bun.build and caches it in ~/.omp/worker-bundle.js for reuse across worker instances.
- Modified worker instantiation to use the pre-built bundle instead of loading the raw TypeScript file directly.
- Added `omp commit` command for generating conventional commits with AI-powered analysis of staged changes.
- Implemented conventional commit analysis pipeline with scope detection, changelog categorization, and summary generation.
- Added map-reduce analysis pattern for efficiently processing large diffs using smaller models for file-level observations.
- Implemented automatic changelog generation and updates to CHANGELOG.md files based on commit analysis.
- Added git operations wrapper (ControlledGit) for managing staged files, diffs, commits, and push operations.
- Implemented comprehensive validation for conventional commit format, scope naming, and changelog entries.
- Settings now stored in ~/.omp/agent/config.yaml instead of agent.db
- Models config now supports models.yaml (preferred) alongside models.json
- Auto-migration from agent.db settings and models.json on first run
- AgentStorage.saveSettings() deprecated (getSettings() kept for migration)
- storage-migration.ts now only handles auth.json migration
- Added AgentOutputManager to allocate unique IDs for agent outputs across task invocations, preventing artifact collisions.
- Implemented automatic ID scanning in ArtifactManager to resume sessions without overwriting existing artifacts.
- Integrated AgentOutputManager into task processing to allocate unique IDs before template rendering.
- Added agentOutputManager property to ToolSession interface for managing unique agent:// IDs across task invocations.
- Added antigravity provider support for image generation with Google Cloud authentication.
- Added support for google-antigravity API credentials in model registry.
- Added antigravity-specific request handling with SSE streaming.
- Added projectId parameter to antigravity credentials parsing.
- Added antigravity provider to preferred image provider selection.
- Fixed file descriptor leak in OutputSink when write fails
- Fixed isError flag not propagating to UI for grouped tool calls
- Fixed Python streaming updates during cell execution (missing onChunk)
- Fixed ls icon detection broken by age suffix in entry names
- Added Tool Output Infrastructure section to DEVELOPMENT.md
- converted relative imports to path aliases ($c/*, $ai/*, $tui/*, etc.) across all packages
- added per-package tsconfig.json with complete path mappings for runtime resolution
- set importModuleSpecifier to non-relative for IDE auto-import preferences
- updated dev script to run from monorepo root for consistent path resolution
- Added output-utils module with tail buffer and artifact allocation helpers.
- Added tool-result module for standardized tool result construction with metadata.
- Replaced inline output truncation with structured metadata system across all tools.
- Updated executors to track detailed output statistics instead of full file paths.
- Standardized artifact storage using pre-allocated paths instead of inline writing.
- Simplified Python gateway coordination by removing reference counting and idle timeout functionality.
- Updated Python kernel initialization to support environment variable setup and working directory configuration.
- Modified interactive status display to show Python and venv paths instead of client counts.
- Updated system prompt to clarify CHECKPOINT step 0 timing after user request completion.
- Fixed Python environment warming to use await for proper async error handling.
- Changed interactive mode shutdown to use postmortem.quit instead of process.exit.
- Enhanced bash and python executors to save full output as artifacts when truncated.
- Replaced manual error formatting with ToolError.render() for standardized handling.
- Fixed timeout parameter handling to auto-convert milliseconds to seconds.
- Added artifact storage system with artifact:// URL protocol for truncated outputs.
- Added structured output metadata system with OutputMetaBuilder for consistent notices.
- Added standardized tool error types (ToolError, MultiError, ToolAbortError).
- Updated all tools to use structured metadata instead of inline notices.
- Removed activeForm field from TodoItem interface and simplified todo display logic.
- Converted dynamic imports to static imports in installer and exa tools.
- Renamed task parameter from vars to args throughout task tool interface.
- Simplified task template validation by removing strict placeholder requirements.
- Renamed task parameter from vars to args throughout task tool interface.
- Enhanced task template rendering with built-in {{id}} and {{description}} placeholders.
- Simplified task template validation by removing strict placeholder requirements.
- Streamlined CHECKPOINT step requirements in system prompts.
- Removed internal URL handling from fetch tool to use read tool instead.
- Updated fetch and task tool documentation to reference read tool for agent:// URLs.
- Added timeout clamping to reasonable ranges across all tools.
- Fixed timeout parameter handling to auto-convert milliseconds to seconds.
- Simplified todo-write tool by removing active_form parameter requirement.
- Added internal URL routing system with agent:// and skill:// protocol handlers.
- Enhanced fetch tool to support internal URLs and JSON extraction from agent outputs.
- Extended read tool to handle internal URLs with pagination and query extraction.
- Removed Output tool and replaced functionality with agent:// URL integration.
- Replaced minimatch dependency with Bun.Glob for pattern matching across modules.
- Simplified todo-write tool by removing active_form parameter requirement.
- Updated todo-write tool to use single content field for task descriptions.
- Modified todo-write display logic to show content instead of active_form for in-progress tasks.
- Added format-prompts script for standardizing prompt file formatting across the codebase.
- Updated system prompt tags from `<required>`/`<antipatterns>` to `<important>`/`<avoid>` for clarity.
- Enhanced prompt formatting by removing blank lines after colons and around blocks for consistency.
- Standardized whitespace handling across all prompt files to improve readability.
- Updated task decomposition guidance with clearer triggers for using Task tool.
- Added mandatory CHECKPOINT step for task evaluation before first tool call.
- Enhanced skills and rules checking with explicit validation requirements.
- Improved task decomposition criteria with dependency analysis.
- Added failure conditions for checkpoint and parallel processing validation.
- Renamed web_fetch tool to fetch for consistency across codebase and documentation.
- Removed format parameter from output tool and added automatic JSON to YAML conversion.
- Updated tool documentation and CLI help text to reflect tool name changes.
- Adjusted output truncation limits for bash and python tools.
- Simplified web-search tool parameters by removing advanced configuration options.
- Standardized web-search tool to use built-in system prompt for consistent responses.
- Updated web-search tool to use `recency` parameter instead of `search_recency_filter`.
- Added unified web search system prompt with research assistant guidelines.
- Standardized documentation format across all 18 tools with consistent XML sections.
- Added `<output>` sections to clarify return values and behavior for all tools.
- Reorganized tool instructions with clearer `<instruction>`, `<critical>`, and `<avoid>` sections.
- Renamed Patch tool to Edit and Edit tool to Replace for better naming consistency.
- Standardized timeout parameters across all tools to use seconds instead of milliseconds.
- Added automatic conversion and validation for timeout values with reasonable clamping ranges.
- Renamed web-search parameter from num_results to limit for consistency.
- Updated parameter naming from camelCase to snake_case format across tools.
- Replaced parseMCPToolName function with direct mcpToolName and mcpServerName properties.
- Updated MCP tool parameter naming from camelCase to snake_case for consistency.
- Refactored MCP tool execution to use explicit server and tool name fields.
- Improved MCP tool metadata extraction with direct property access.
- Added nonAbortable option to AgentTool interface for ignoring abort signals during tool execution.
- Added isolated option to task tool for running tasks in isolated git worktrees.
- Simplified tool parameter descriptions across all coding-agent tools for better readability.
- Updated find tool to always sort results by modification time and removed sortByMtime parameter.
- Changed web-fetch timeout default from 20s to 45s maximum and updated bash prompt to use cwd parameter.
- Removed model parameter from task and gemini-image tools to use session/provider defaults.
- Removed model parameter from task and gemini-image tools to use session/provider defaults.
- Changed model inheritance logic to prioritize agent model over session model.
- Added humanizeKey function to display single variables inline with Title Case formatting.
- Updated task schema types to remove optional model field.
- Removed centralized tool descriptions from prompt generation logic.
- Eliminated consolidated tool list rendering in system prompts.
- Added explicit tool name headings to individual tool documentation files.
- Simplifies prompt construction by decentralizing tool information.
- Added isolated task execution feature with git worktree support.
- Implemented automatic patch generation and application for isolated tasks.
- Added worktree management with baseline capture and delta patching.
- Enhanced task result display to show isolation status and patch information.
- Updated system prompt structure and formatting for better readability.
- Reorganized tool hierarchy and discipline sections.
- Added parallel work guidance for task-based workflows.
- Enhanced verification and integration methodology sections.
- Updated skills and rules formatting for cleaner presentation.
- Added stronger emphasis on completeness and quality standards.
- Added comprehensive usage tracking system with normalized schema for provider quota/limit endpoints.
- Added usage providers for Claude, GitHub Copilot, Google Antigravity, Google Gemini CLI, OpenAI Codex, and ZAI.
- Added `/usage` command to display provider usage and limits with visual progress bars and account aggregation.
- Refactored usage tracking from Codex-specific to generic provider system with persistent caching.
- Fixed API validation errors when sending empty user messages across multiple providers.
- Clamped OpenAI Codex reasoning effort "minimal" to "low" for gpt-5.2 models.
- Limited diagnostic messages to 50 items to prevent overwhelming output when processing files with many issues.
- Updated changelog to reflect diagnostic message limiting behavior.
- Fixed external editor to work properly on Unix systems by correctly handling terminal I/O.
- Fixed external editor to show warning message when it fails to open instead of silently failing.
- Added output() function for reading task/agent outputs by ID with multiple formats.
- Added session file support to Python executor for accessing task outputs.
- Added jq-like query support when reading JSON outputs.
- Added offset and limit parameters for reading specific line ranges from outputs.
- Added "." and "c" shortcuts to continue agent without sending visible message.
- Fixed find tool to handle no matches case without treating as error.
- Fixed read tool to handle no matches case without treating as error.
- Improved fd error handling to distinguish between no results and actual errors.
- Added cell-by-cell Python execution tracking with duration and exit codes.
- Added template system with {{placeholders}} for task tool context rendering.
- Enhanced patch applicator to preserve exact indentation when intended.
- Changed Python tool to use cells array instead of single code parameter.
- Updated task tool schema to require vars instead of task field.
can1357