- 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.
- Converted wrapper class properties to dynamic getters that delegate to underlying tool objects.
- Added optional chaining operators for safer null/undefined access in JSON schema property handling.
- Changed output metadata wrapper to use Object.create() with property descriptors instead of object spread syntax.
- Added model-specific edit variant configuration allowing users to specify 'patch' or 'replace' mode per model pattern.
- Added `getEditVariantForModel()` method to determine appropriate edit mode based on user settings and default patterns.
- Made EditTool's `patchMode`, `description`, and `parameters` dynamic properties that adapt based on the active model.
- Added fallback mechanism in model resolution to support tool creation before agent initialization.
- Added ModelStatsTable component to display model statistics with columns for model, provider, requests, cost, tokens, throughput, and error rate.
- Added 'models' tab to stats dashboard for viewing aggregated model performance metrics.
- Added TTFT (Time to First Token) metric display in request details and overview statistics.
- Added Tokens/s (throughput) metric calculation and display in request list and model statistics.
- Improved code formatting and accessibility by adding semantic HTML attributes (type='button', role, aria-modal) and reformatting style objects for readability.
- Refactored loadData function to use useCallback hook for better performance optimization.
- Added artifact allocation for truncated fetch responses to preserve full content in output artifacts.
- Integrated truncateHead utility to apply consistent truncation limits (DEFAULT_MAX_BYTES and DEFAULT_MAX_LINES) to fetch tool output.
- Refactored output formatting into buildOutput helper function to support both truncated and full content rendering.
- Added Kimi Code provider integration with OAuth device authorization flow and token management.
- Added four new Kimi Code models (kimi-for-coding, kimi-k2, kimi-k2-turbo-preview, kimi-k2.5) with reasoning support and 262K context window.
- Added kimiUsageProvider for fetching and caching Kimi Code API usage quota information.
- Added kimi-code login command to CLI for OAuth authentication with Kimi Code.
- Updated openai-completions provider to support Kimi-specific headers and cached token formats.
- Updated MiniMax-M2 model pricing: input 1.2->0.6, output 1.2->3, cacheRead 0.6->0.1.
- Migrated import paths from absolute package imports to relative imports throughout coding-agent modules.
- Consolidated related imports in tools/index.ts to reduce import statement count.
- Removed guideline about avoiding relative parent imports from AGENTS.md documentation.
- Reformatted code examples in AGENTS.md for improved readability with multi-line formatting.
- Added timeout support to hook selector with auto-selection behavior on timeout.
- Extended ExtensionUIDialogOptions to include timeout and tui configuration properties.
- Changed hook selector timeout behavior from cancellation to auto-selecting the currently highlighted option.
- Updated UIContext.select() method signature to accept timeout option for automated selection scenarios.
- Renamed 'output' parameter to 'schema' throughout task configuration and documentation for clarity.
- Updated task schema definition to use 'schema' field with improved description clarifying it defines expected response structure.
- Restructured task summary output format to consolidate metadata into tag attributes and simplify XML structure.
- Added truncation detection for task output exceeding 5000 character threshold with truncated flag.
- Removed charCount from task metadata, retaining only lineCount and charSize properties.
- Extracted tool choice mapping logic into dedicated utility module for provider-specific format conversions.
- Refactored task summary generation to use template-based rendering instead of string concatenation.
- Migrated system prompt generation to use Handlebars templates with structured data instead of hardcoded strings.
- Extracted JTD to TypeScript conversion logic into dedicated utility module for schema documentation.
- Consolidated prompt template rendering across multiple modules using unified renderPromptTemplate function.
- Simplified type assertions in stream module to use generic OptionsForApi type instead of provider-specific types.
- 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 available tools list to system prompt for agent coherence.
- Improved output preview logic to show full output for smaller results and truncate larger outputs to 10 lines.
- Added session compaction auto-continue feature that automatically sends a synthetic continuation prompt after compaction completes when enabled in settings.
- Added tool output pruning system that intelligently removes verbose tool outputs from session history during compaction to reduce token usage while preserving critical information.
- Added short summary generation for compaction results, providing concise PR-style summaries of conversation changes alongside full summaries.
- Added session.compacting extension hook that allows extensions to customize compaction prompts, add context, and preserve metadata during summarization.
- Added synthetic message support to mark system-injected messages (like auto-continue prompts) and prevent them from being persisted to editor history.
- 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 detection and rendering of missing complete tool warning in agent output.
- Introduced extractMissingCompleteWarning function to parse and separate warning messages from agent output.
- Enhanced renderOutputSection to display warning indicators alongside output content.
- Updated agent result rendering to show warning status icon when subagent exits without calling complete tool.
Creates a new session file with the exact same state as the current session,
including all entries (messages, model changes, compactions, etc.) and
artifacts. The new session's parentSession field links to the original.
- Added fork() method to SessionManager that creates new session file with copied entries
- Added fork() method to AgentSession that handles artifact directory copying
- Added /fork command handler in input-controller and command-controller
- Extended session switch event reason type to include 'fork'
- Extracted type guard functions for improved type safety and code reusability across RPC and migration modules.
- Centralized AgentEvent type validation into a dedicated Set constant and type guard function in rpc-client.
- Replaced inline type assertions with type guard functions in RPC response and event handling logic.
- Refactored test utilities to use parseSessionEntries helper and type guard functions for cleaner test code.
- Added reasoning content configuration properties to OpenAI compatibility settings.
- Replaced external JSON/JSONL parsing libraries with Bun's built-in JSON5 and JSONL APIs across all packages.
- Removed dependencies: json5, ndjson, get-east-asian-width, json-stringify-safe, split2, through2, and @types/ndjson.
- Replaced custom text width and ANSI wrapping implementations with Bun.stringWidth() and Bun.wrapAnsi() APIs.
- Updated Bun type definitions from ^1.2.17 to ^1.2.18 and bun-types from ^1.3.5 to ^1.3.7.
- Refactored JSONL parsing throughout codebase to use Bun.JSONL.parse() and Bun.JSONL.parseChunk() with improved buffer management and error handling.
- Updated test assertions to use Bun.stringWidth() for dynamic width calculations instead of hardcoded values.
- 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.
- Inline preloaded skill contents in system prompts and allow task-level skill selection.
- Record session init entries with system prompt, task, tools, and output schema.
- Fix session persistence to keep pre-assistant entries in subagent logs.
- Throttled subagent progress emissions with a coalescing window and terminal flushes.
- Switched message_update handling to append text deltas into a bounded tail buffer for recent output.
- Removed deep cloning from TaskTool progress updates to keep progress rendering cheap.
- Refactored glob pattern handling to create Bun.Glob matcher inline for cleaner implementation.
- Improved empty result detection to return early with appropriate message when no files match.
- Renamed `head_limit` to `limit` in grep and find tools for consistency.
- Added `context` as optional alias for the `c` parameter in grep.
- Made hidden files inclusion configurable in find with `hidden` parameter.
- Integrated .gitignore and .ignore file support in find tool.
- Updated plan mode documentation for self-contained plan files.
- Added model_usage table to persist most-recently-used model timestamps across sessions.
- Model selector now sorts fuzzy-matched results by usage recency.
- Schema version bumped to 3 for model_usage table.
- Removed unused currentModel field from ModelSelectorComponent.
- 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.
- Model field now accepts string arrays for fallback model prioritization.
- Extracted model list parsing into dedicated parseModelList helper function.
- Extended default model alias detection to validate all entries in comma-separated lists.
- Removed duplicate hexToRgb and rgbToAnsi functions that were only used in foreground color conversion.
- Reused colorToAnsi for background colors by applying ANSI code substitution instead of reimplementing the full logic.
- Exposed mergeCallAndResult and inline rendering options from tools to their wrappers.
- Added normalizeTimeoutSeconds helper to validate and clamp timeout values with flexible unit support.
- Updated buildRenderContext JSDoc to include python tool in list requiring extra state.
- Removed Prettier configuration files (.prettierignore and .prettierrc) and migrated formatting to Biome.
- Updated Biome configuration from version 2.3.11 to 2.3.12 and changed arrowParentheses rule from 'always' to 'asNeeded'.
- Pinned @biomejs/biome dependency to exact version 2.3.12 in package.json and bun.lock.
- Applied consistent arrow function formatting across 489 files by removing unnecessary parentheses around single parameters.
- Removed blank lines after comment blocks and reorganized imports for consistency across the codebase.
- Changed loadCustomModels from async to sync using fs.readFileSync for immediate resolution.
- Updated discoverModels to return synchronously, removing await from main.ts, pipeline.ts, and commit index.ts.
- Migrated sdk.ts to use node:fs instead of node:fs/promises for synchronous operations.
- Refactored scanDirectoryForSkills to use recursive traversal instead of batch Promise.all.
- Added tarball Dockerfile for testing npm publish/install flow with verdaccio registry.
- Converted named imports from node modules (fs, path, os) to namespace imports across all packages.
- Extended extension loader error handling with isEacces and hasFsCode type guards.
- Fixed autocomplete race condition in editor by tracking request ID to discard stale results.
- Added guard clause in plugin-settings to prevent null reference when settings list is undefined.
- Added branch change callbacks in footer to update state after git head resolution.
- Added timing instrumentation to Python kernel startup and gateway acquisition.
- Improved error logging in settings manager for config file access failures.
- Fixed model discovery to re-check file existence after JSON to YAML migration and improved file access error handling.
- Converted readdirSync, readFileSync, and statSync to async readdir, readFile, stat across skills and agent discovery.
- Made scanDirectoryForSkills async and refactored custom directory scanning to use Promise.all for concurrent processing.
- Updated agent discovery to use fs/promises for async file reading and refactored helper patterns.
- Added AgentParsingError exception class for better error handling during agent parsing.
- Added filesystem error type guards (isEnoent, isEacces, isPerm, etc.) to pi-utils for safe error checking.
- Added color manipulation utilities to pi-utils for accessibility features.
- Added color-blind mode setting to settings manager.
- Migrated plugins, settings, and config modules from sync to async file operations.
- Updated error handling to use new pi-utils type guards for type-safe checking.
- Removed WASM generation script; use Bun `wasm?raw` loader for imports.
- Added bunfig.toml with loaders for `.md`, `.py`, and `.wasm?raw` text imports.
- Added types/assets/index.d.ts for global TypeScript module declarations.
- Unified TypeScript configuration with tsgo-based checking across monorepo.
- Removed build and WASM steps from install and publish pipelines.
- Upgraded Perplexity search model from 'sonar' to 'sonar-pro' for improved search quality.
- Added 'high' search context size configuration to Perplexity API requests for enhanced context awareness.
can1357