- Added librarian and oracle agents for library research and technical diagnostics.
- Expanded tool support across explore, plan, and reviewer agents with lsp, fetch, web_search, and ast_grep.
- Added dependencies and risks output fields to explore agent for enhanced analysis.
- Renamed explore agent output field from query to summary with expanded description.
- Restructured submit_result tool parameter schema to wrap data and error fields in a nested result object.
- Updated all prompt documentation to reference the new result.data and result.error parameter paths.
- Added validation logic to ensure result is an object containing exactly one of data or error.
- Updated test cases to reflect the new nested result object parameter structure.
- Standardized prompt format, removing XML-like tags.
- Emphasized RFC 2119 keywords using bolding across all prompts.
- Rewrote the core system prompt with enhanced structure and directives.
- Standardized XML tag naming from snake_case to kebab-case across 50+ prompt files for consistency.
- Replaced imperative language with RFC 2119 keywords (MUST/SHOULD/MAY/MUST NOT) throughout system and tool prompts for clarity.
- Removed artifactsDir parameter from Python executor and simplified environment variable handling to use PI_SESSION_FILE only.
- Renamed read_path.md to read-path.md and updated memory guidance with hierarchy rules and conflict resolution workflow.
- Added noEscape option to bash URL expansion and extracted cwd parameter from leading cd commands for improved path handling.
- Exported NO_PAGER_ENV constant from bash-interactive module for centralized environment variable management.
- Added AgentBusyError exception class for concurrent operation handling across agent packages.
- Added automatic retry logic with 30-second timeout for agent prompts when agent is busy.
- Changed concurrent operation errors from generic Error to AgentBusyError for better error handling.
- Fixed model discovery to use default refresh mode instead of explicit 'online' parameter.
- Extracted model priority configuration from TypeScript constants to external priority.json file.
- Updated agent prompts (reviewer, explore, plan) to reference new model tier aliases (pi/slow, pi/smol, pi/plan).
- Removed hardcoded SMOL_MODEL_PRIORITY and SLOW_MODEL_PRIORITY constants from model-resolver.ts.
- Improved prompt formatting with consistent newlines and whitespace in agent configuration files.
- Refactored task API to use 'assignment' field instead of 'args' for per-task instructions, enabling clearer separation between shared context and task-specific work.
- Introduced structured context/assignment separation pattern with '<swarm_context>' wrapper for template rendering, replacing placeholder-based substitution.
- Changed agent frontmatter field from 'thinkingLevel' to 'thinking-level' (kebab-case) for consistency with YAML conventions.
- Removed 'context' parameter from ExecutorOptions as context is now prepended at template level rather than executor level.
- Removed 'args' field from AgentProgress and SingleResult interfaces, simplifying task result tracking.
- Updated task rendering to display full task text instead of formatted args, improving clarity in progress output.
- Added jsonStringify Handlebars helper to enable safe JSON serialization of template variables in frontmatter generation.
- Improved frontmatter parsing error messages to include source context, making debugging easier when YAML frontmatter parsing fails.
- Standardized markdown table formatting with consistent column alignment and spacing across SKILL.md documentation.
- Added blank lines after section headers and before code blocks to improve documentation readability.
- Updated nested markdown code block fence from triple to quadruple backticks for proper syntax highlighting.
- Fixed XML element indentation and closing tags for </procedure> and </system_directive> elements.
- Removed 'ls' tool from agent definitions (explore, plan, reviewer) to streamline available tool sets.
- Expanded model list in explore agent to include additional model variants (haiku-4.5, gemini-flash-latest, glm variants, gpt-5.1-codex-mini).
- Condensed prompt documentation throughout by removing articles, auxiliary verbs, and redundant explanations for improved clarity and conciseness.
- Simplified system prompts by replacing multi-line explanations with terse, semicolon-separated fragments and removing verbose motivational language.
- Reformatted tool documentation to use abbreviated language, removing 'the', 'a', and 'is' throughout for more direct technical writing.
- Removed blank lines and consolidated spacing in prompt files to reduce vertical whitespace and improve document density.
- Added model preference matching system with ModelMatchPreferences and ModelPreferenceContext interfaces to enable intelligent model selection based on usage history and provider preferences.
- Implemented buildPreferenceContext and pickPreferredModel functions to rank and select models based on usage order, provider history, and deprioritization settings.
- Enhanced parseModelPattern function to accept optional ModelMatchPreferences parameter, enabling model resolution to consider user preferences and usage history.
- Updated model matching logic to prioritize models based on historical usage patterns and provider preferences when multiple candidates match a pattern.
- Renamed 'complete' tool to 'submit_result' throughout codebase for clarity and consistency.
- Updated all tool references, function names, and variable names from 'complete' to 'submit_result' in executor, render, and tools modules.
- Renamed CompleteTool class to SubmitResultTool and CompleteDetails interface to SubmitResultDetails.
- Updated agent prompts and documentation to reference the new 'submit_result' tool name.
- Reorganized task.md prompt to move critical guidance to the top and restructure instructions for better clarity.
- Added ToolChoice type and toolChoice parameter support across all AI providers (OpenAI, Azure OpenAI, Anthropic, Google) enabling fine-grained control over tool/function selection during LLM calls.
- Added toolChoice override capability to Agent.prompt() method and session prompt options allowing callers to control tool selection behavior per request.
- Added provider-specific tool choice mapping functions (mapAnthropicToolChoice, mapGoogleToolChoice, mapOpenAiToolChoice) to normalize tool choice formats across different LLM APIs.
- Removed kernel heartbeat/ping mechanism from PythonKernel, simplifying health monitoring by relying on direct isAlive() checks instead of periodic HTTP requests.
- Added 'plan' model role option to support architectural planning with dedicated model selection via CLI argument (--plan), environment variable (OMP_PLAN_MODEL), and UI menu action.
- Updated model selector to display 'PLAN' badge for plan models and prioritize them in the model sorting order.
- Relaxed task management constraints to allow multiple tasks to be in_progress simultaneously, enabling parallel task execution instead of enforcing single-task-at-a-time workflow.
- Improved todo validation to check for blocking pending tasks before allowing a todo to be marked in_progress, with more specific error messages indicating which earlier tasks are blocking progress.
- Refined descriptions to be more concise and focused.
- Restructured content for improved clarity and consistency across all plan mode prompts.
- Tightened critical sections with more direct language.
- Improved plan mode prompt clarity and organization.
- Plan mode provides structured workflow where agents propose plans for user approval before execution.
- Added plan:// internal URL protocol for accessing plan files and injecting plan-mode context into subagent prompts.
- Added plan mode toggle shortcut and paused status indicator in status line.
- Fixed plan reference injection to properly pass workflow state to plan-mode system prompts.
- Improved autocomplete fuzzy matching to support subsequence matching for skill suggestions.
- 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.
- 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 Python shared gateway setting for resource-efficient kernel reuse across sessions.
- Enhanced Python tool with session-scoped kernel isolation and workdir-aware session IDs.
- Added Python tool cancellation support with timeout handling and proper cleanup.
- Expanded Python prelude with enhanced file operations, git utilities, and improved output handling.
- Fixed AI provider message transformation for proper tool call handling and error recovery.
- Added IPython-backed Python tool with streaming output and image/JSON rendering.
- Implemented Jupyter kernel gateway integration with WebSocket communication.
- Added Python prelude with 30+ shell-like utility functions for file operations.
- Migrated environment variables from PI_ to OMP_ prefix with automatic migration.
- Added streaming output system with automatic spill-to-disk for large outputs.
- Reorganized settings interface into behavior, tools, display, voice, status, lsp, and exa tabs.
- Added thinkingLevel field to agent frontmatter allowing subagents to override thinking level with clamping to model capabilities.
- Added structured output schema to reviewer agent ensuring consistent review output format with findings, correctness verdict, and confidence.
- Expanded system prompt with defensive reasoning guidance including assumption checks, edge case awareness, and completion reflex inhibition.
- Consolidated expandPath, parseFrontmatter, and parseAgentFields utilities into discovery/helpers module eliminating code duplication across loaders.
- Replaced silent error handling with logger.warn calls across config parsing, migrations, extension loading, and OAuth refresh failures.
- Updated Task tool documentation to emphasize that subagents have no access to conversation history and require all relevant context to be explicitly passed.
- Revised task agent prompt to clarify that subagents have full tool access and can make file edits, run commands, and create files.
- Replaced example in Task tool docs with a more realistic refactoring scenario demonstrating context passing.
- Removed built-in agent commands: 'architect-plan', 'implement', and 'implement-with-critic' from coding-agent.
- Improved file autocomplete to show directory listing when typing '@' with no query.
- Added fallback to prefix matching when fuzzy search returns no results for file autocomplete.
- Fixed 'fd' tool detection to automatically find 'fd' or 'fdfind' in PATH when not explicitly configured.
- Removed rulebook tool and migrated rules loading to use read tool instead.
- Reorganized prompt files into subdirectories: agents/, compaction/, and system/.
- Added Handlebars helpers for template rendering including list, join, table, codeblock, xml, when, pluralize, and arithmetic operations.
- Migrated prompt template rendering from simple string replacement to Handlebars-style templating with structured data objects.
- Refactored system prompt generation to pass structured data instead of pre-formatted strings.
- Removed rulebookRules property from ToolSession interface and updated all test files accordingly.
can1357