- Refactored SSE stream parsing to use generic `readSseJson` utility instead of domain-specific handlers across multiple packages.
- Migrated from Node.js Buffer API to Web standard APIs (Uint8Array, TextDecoder, DataView) for cross-platform compatibility.
- Simplified stream transformation pipeline by consolidating multiple stream operations into unified `createTextLineSplitter` utility.
- Refactored `ptree.ts` to remove complex stream pumping infrastructure and simplify stderr handling with direct async iteration.
- Rewrote stream utilities to operate at binary level with byte-level parsing for improved efficiency and reduced string allocations.
- Updated TypeScript configuration to include DOM.AsyncIterable type definitions for async iterable DOM API support.
- Added `sortDiagnostics()` utility function to sort diagnostics by severity, location, and message for consistent output ordering.
- Changed diagnostic output to sort results by severity (errors first), then by file location and message for improved readability.
- Added `getSeverityRank()` helper function in render-utils to map diagnostic severity levels to numeric ranks for sorting.
- Integrated diagnostic sorting in LSP index module to apply consistent ordering before formatting diagnostics.
- Converted class properties to TypeScript parameter properties across 51 files to reduce boilerplate code.
- Removed explicit field declarations and manual assignments in constructors by using TypeScript's parameter property syntax with access modifiers.
- Applied consistent pattern of declaring private readonly and public readonly properties directly in constructor parameters.
- Migrated timing measurements from `performance.now()` to `Bun.nanoseconds()` for higher precision benchmarking across all benchmark and timing-sensitive code.
- Updated elapsed time calculations to convert nanoseconds to milliseconds using division by 1e6 to maintain consistent time units.
- Increased benchmark precision from 4 to 6 decimal places for per-operation timing measurements.
- Refactored grep benchmark to use averaged timing values instead of storing individual iteration times, reducing memory overhead.
- Migrated all environment variable access from Node.js `process.env` to Bun runtime `Bun.env` API across the entire codebase.
- Updated 71 files including source code, tests, documentation, and configuration to use Bun's native environment variable API.
- Added comprehensive environment variables documentation in `packages/coding-agent/docs/environment-variables.md` covering 100+ environment variables organized by category.
- Updated CHANGELOG entries to reflect migration from `process.env` to `Bun.env` and environment variable prefix changes (PI_* vs OMP_*).
- Maintained identical behavior and logic across all changes - only the environment variable access method was updated.
- Replaced nanoid and randomUUID with Snowflake ID generator across codebase for consistent distributed ID generation.
- Created new Snowflake utility module in packages/utils with support for 64-bit distributed ID generation with configurable epoch, machine ID, and sequence numbers.
- Updated session ID format documentation from nanoid to snowflake hex string format (16 hex characters).
- Removed nanoid dependency from package.json as it is now replaced by internal Snowflake implementation.
- Migrated environment variable access from function-based `getEnv()` API to object property-based `$env` API across 43 files in the monorepo.
- Simplified `packages/utils/src/env.ts` by removing scoped environment variable logic (EnvScope, getEnvMap, getEnv functions) and replacing with direct `process.env` reference exported as `$env`.
- Updated `packages/ai/src/stream.ts` to remove environment parameter from KeyResolver functions and use global `$env` object instead of passed-in env parameter.
- Migrated environment variable access from direct process.env to centralized getEnv() utility function across all packages.
- Renamed environment variable prefix from OMP_ to PI_ throughout codebase (e.g., OMP_CODING_AGENT_DIR -> PI_CODING_AGENT_DIR).
- Removed automatic environment variable migration from PI_ to OMP_ prefixes via migrate-env.ts module.
- Removed env setting from configuration schema and applyEnvironmentVariables() method from settings.
- Updated CI/CD build configuration to use PI_COMPILED flag instead of OMP_COMPILED.
- Changed venvPath property in PythonRuntime from nullable (string | null) to optional (string | undefined).
- Added terminal-capabilities module with NotifyProtocol enum and notification formatting/sending methods to TerminalInfo class.
- Renamed TERMINAL_INFO export to TERMINAL and consolidated terminal image/capability exports from terminal-image to terminal-capabilities module.
- Removed terminal-image module exports from public API with functionality migrated to terminal-capabilities.
- Simplified notification settings in coding-agent by removing protocol detection logic and delegating to TERMINAL.sendNotification().
- Removed terminal-notify.ts utility module from coding-agent, consolidating notification handling into pi-tui package.
- Added task.maxRecursionDepth setting to control how many levels deep subagents can spawn their own subagents (0=none, 1=one level, 2=two levels, -1=unlimited).
- Added nested task artifact naming with parent task prefixes (e.g., '0-Auth.1-Subtask') to support hierarchical task identification.
- Added taskDepth and parentTaskPrefix options to CreateAgentSessionOptions for supporting nested/subagent sessions.
- Changed task tool spawns configuration from 'explore' to '*' to allow spawning any type of subagent.
- Updated system prompt to unconditionally include parallel delegation guidance for all agent types instead of only coordinators.
- Implemented automatic task tool disabling at maximum recursion depth to prevent excessive task nesting.
- Extracted environment variable parsing logic from multiple packages into centralized @oh-my-pi/pi-utils package.
- Moved getEnv, getEnvMap, and parseEnvFile functions from local implementations to shared pi-utils/src/env.ts module.
- Updated all imports across ai, coding-agent packages to use getEnv from @oh-my-pi/pi-utils instead of local definitions.
- Replaced direct process.env accesses in azure-openai-responses.ts and openai-responses.ts with centralized getEnv utility calls.
- Implemented EnvScope type and proxy-based environment variable merging to support multiple scopes (global, project, process) with dynamic process.env integration.
- Consolidated environment variable parsing and caching logic into single reusable module with improved testability and abstraction.
- Removed WASM-specific naming conventions and terminology throughout the codebase, including import aliases, comments, and type aliases.
- Removed legacy type aliases 'WasmMatch' and 'WasmSearchResult' from grep types module.
- Removed TypeScript module declaration for '*.wasm?raw' file imports.
- Updated error handling in task executor to properly handle stopReason === 'error' case with exit code and error message capture.
- Simplified documentation comments to remove implementation details about WASM and Photon library internals.
- Updated README to reflect shift from WASM to N-API for pi-natives crate implementation.
- Removed `output_mode` parameter from grep tool, consolidating all output to content mode with file grouping and match headers.
- Renamed grep context parameters from `context_pre`/`context_post` to `pre`/`post` for improved clarity.
- Removed `n` (line numbers) parameter from grep tool as line numbers are now always displayed.
- Reformatted grep output to display numbered matches with file paths, line numbers, and context lines with consistent alignment.
- Introduced `SearchParams` struct in Rust grep implementation to simplify parameter passing and improve code maintainability.
- Made `normalize_env_key` function const-eligible for compile-time evaluation in shell module.
- Split grep context parameter into separate contextBefore and contextAfter options for more granular control over context lines displayed before and after matches.
- Added configurable grep context defaults via grep.contextBefore and grep.contextAfter settings with reduced default values (1 line before, 3 lines after).
- Updated grep tool schema to use context_pre and context_post parameters instead of unified context parameter.
- Maintained backward compatibility by keeping legacy context field in SearchOptions and GrepOptions structs.
- Added resolve_context() function to handle logic for choosing between separate before/after context values or legacy unified context value.
- Added device scale factor (1.25x) to browser viewport configuration for improved rendering on high-DPI displays.
- Enhanced device pixel ratio detection to use actual window.devicePixelRatio when available instead of hardcoded value.
- Improved WebGL stealth by masking additional WebGL parameter queries (VENDOR and RENDERER) beyond unmasked variants.
- Updated @anthropic-ai/sdk from ^0.71.2 to ^0.72.1 in packages/ai.
- Updated @aws-sdk/client-bedrock-runtime from ^3.975.0 to ^3.982.0 in packages/ai.
- Updated @google/genai from ^1.38.0 to ^1.39.0 in packages/ai.
- Updated @smithy/node-http-handler from ^4.4.8 to ^4.4.9 in packages/ai.
- Updated openai from ^6.16.0 to ^6.17.0 in packages/ai.
- Removed proxy-agent and undici dependencies from packages/ai.
- Updated system prompt guidance to state assumptions and proceed without asking for confirmation, reducing unnecessary round-trips.
- Tightened ask tool conditions to require multiple approaches with significantly different tradeoffs before prompting user.
- Strengthened ask tool guidance to default to action and only ask when genuinely blocked by decisions with materially different outcomes.
- Changed refactor workflow to automatically remove now-unused elements and note removals instead of asking for confirmation.
- Added exclusive concurrency mode enforcement to file-modifying tools (edit, write, bash, python, ssh, todo-write) by introducing a new public `concurrency` property set to "exclusive" on each tool class.
- Updated CHANGELOG.md to document the enforcement of exclusive concurrency mode for file-modifying tools.
- Cleaned up imports in tool-execution.ts by removing unused Theme type import and reordering imports for better organization.
- Extracted JSON tree rendering utilities into dedicated module for reuse across tool renderers.
- Moved formatArgsInline, renderJsonTreeLines, and related constants from mcp/render.ts to tools/json-tree.ts.
- Updated tool-execution.ts to import and use shared JSON tree rendering functions.
- Changed `ask` tool to require `questions` array parameter; single-question mode with `question`, `options`, `multi`, and `recommended` parameters is no longer supported.
- Updated `ask` tool guidance to prioritize proactive problem-solving and default to action, asking only when truly blocked by decisions that materially change scope or behavior.
- Refactored ask tool implementation to consolidate single and multi-question logic paths.
- Fixed timeout handling in LSP write-through operations to properly clear formatter and diagnostics results when operations exceed the 10-second timeout threshold.
- Added timeout detection mechanism in LSP index that sets a flag when the timeout signal is aborted.
- Added nonAbortable property to EditTool and WriteTool classes to prevent these operations from being aborted during execution.
- Externalized subagent submit reminder prompt to a separate template file for improved maintainability and dynamic retry tracking.
- Consolidated directory listing functionality from dedicated `ls` tool into the `read` tool.
- Removed the `ls` tool and all related exports, types, and configurations from the public API.
- Updated `read` tool to return formatted directory listings with modification times instead of redirecting to `ls` tool.
- Removed `bashInterceptor.simpleLs` setting and related interception logic from bash tool.
- Removed `ls.enabled` setting and related tool registration logic.
- Removed test cases for the `ls` tool and updated tool type definitions to remove `LsToolResultEvent`.
- Added enable/disable settings for specialized tools (find, grep, ls, notebook, fetch, web_search, lsp, calc) allowing fine-grained control over tool availability.
- Implemented conditional tool documentation in system prompt that dynamically lists only enabled specialized tools based on configuration.
- Updated tool filtering logic to respect enable/disable settings, preventing unavailable tools from being exposed to the agent.
- Reorganized todo-related settings from `todoCompletion.*` namespace to `todo.*` namespace with separate `todo.enabled` and `todo.reminders.*` properties.
- Updated settings access pattern in agent session from grouped settings object to flat dot-notation keys for improved consistency.
- Refactored todo_write tool availability check to independently gate on both `todo.enabled` setting and absence of submit_result.
- Removed 'strippedRedirect' field from NormalizedCommand interface returned by normalizeBashCommand().
- Removed automatic stripping of '2>&1' stderr redirections from bash command normalization.
- Updated bash-normalize function to only extract head/tail patterns and no longer process stderr redirection.
- Removed test cases for 2>&1 stripping and combined pattern handling in bash-normalize tests.
- Introduced new task scheduling system with CancelToken for cooperative cancellation, replacing Rayon-based work scheduling with libuv thread pool integration.
- Added Cancellable interface with timeoutMs and signal properties for unified timeout and abort signal handling across all async operations.
- Converted async functions (clipboard, html, image, shell, grep, glob) to synchronous functions returning task::Async wrappers for consistent cancellation semantics.
- Removed abortShellExecution() function and executionId tracking in favor of centralized CancelToken-based cancellation.
- Simplified htmlToMarkdown() signature by removing RequestOptions parameter and delegating cancellation to Cancellable interface.
- Fixed `find` tool to return a single match when given a file path instead of failing with 'not a directory' error.
- Added `hasGlobChars` helper function to detect glob patterns and distinguish file paths from glob patterns.
- Extended `FindOperations` interface with optional `stat` method for distinguishing files from directories.
- Added test case verifying that `find` tool correctly returns a single file when given a file path.
- Added native process tree killing and listing functions via new `ps` module in pi-natives crate with platform-specific implementations (Linux /proc, macOS libproc, Windows CreateToolhelp32Snapshot).
- Refactored process termination logic to prioritize native process tree killing when available, improving reliability of process cleanup across platforms.
- Removed detached process spawning across codebase (bash-executor, shell-session, kernel, lsp client, markitdown conversion) in favor of native process tree management.
- Simplified ptree module by removing managed children tracking and postmortem cleanup hooks, delegating process lifecycle management to native implementations.
- Added null check for match parameter in onMatch callback to prevent null reference errors.
- Updated match parameter type annotation from FindMatch to FindMatch | null to reflect actual usage.
- Renamed `EllipsisKind` enum to `Ellipsis` across all packages for clearer API naming.
- Refactored Rust text module from 356 to 155 lines with simplified state tracking using u32 ColorVal instead of enum ColorCode and named attribute constants.
- Removed `Env` parameter from public NAPI functions `truncate_to_width` and `extract_segments` to simplify API surface.
- Changed return type of `truncate_to_width` from `JsString` to `Either<JsString, Utf16String>` to support zero-copy returns.
- Removed early return optimization in `truncateToWidth()` function.
- Reordered native module search paths to prioritize repository build artifacts over system paths.
- Changed TextInput type parameter to string in truncateToWidth(), visibleWidth(), sliceWithWidth(), and extractSegments() functions in native bindings.
- Removed TextInput type export from public API of pi-natives package.
- Removed format.ellipsis symbol from theme configuration, replacing all theme-based ellipsis references with hardcoded Unicode ellipsis character (...).
- Removed ellipsis property from SymbolTheme interface in pi-tui package.
- Removed truncateToWidth, sliceWithWidth, and extractSegments wrapper functions from pi-tui public API, now re-exporting directly from pi-natives.
- Added early return optimizations in truncateToWidth() and sliceWithWidth() native functions to skip native calls when possible.
- Replaced SettingsManager class with new Settings singleton providing synchronous get/set API and background persistence.
- Introduced settings-schema.ts as single source of truth for all configuration definitions with 100+ settings organized into logical groups.
- Migrated from method-based settings access (getTheme(), setTheme()) to path-based access using dot notation (settings.get('theme'), settings.set('theme', value)).
- Removed 2035-line settings-manager.ts file and replaced with modular settings.ts (693 lines) and settings-schema.ts (836 lines) for improved maintainability.
- Unified settings schema into single source of truth eliminating duplicate definitions across settings-defs.ts and settings-manager.ts.
- Added sortByMtime option to FindOptions for native-level mtime-based sorting of file search results.
- Added streaming callback support (onMatch parameter) to grep() function for real-time match notifications.
- Added mtime field to FindMatch struct to expose file modification times in search results.
- Exported RequestOptions type from natives package for public API use.
- Implemented wrapRequestOptions utility for consistent timeout and abort signal handling across native functions.
- Fixed race condition in shell session where command completion could occur before stream data was fully processed.
- Added head and tail parameters to bash tool for native output limiting without piping.
- Implemented automatic normalization of bash commands to extract and strip head/tail pipes and stderr redirects.
- Created bash-normalize utility module with normalizeBashCommand and applyHeadTail functions for command processing.
- Updated bash tool documentation to recommend using head/tail parameters instead of piping through shell commands.
- Added comprehensive test coverage for bash command normalization and head/tail filtering functionality.
- Optimized grep search to use streaming readers instead of buffering entire files, reducing memory overhead for large files.
- Added thread-local caching to scope color computation in highlight module to avoid repeated prefix checks.
- Refactored text truncation from two-pass algorithm to single-pass streaming algorithm, eliminating intermediate vector allocations.
- Removed Arc overhead from image storage by storing DynamicImage directly and pre-allocating buffer capacity for encoding operations.
- Updated find tool to emit streaming match updates via callback and use native match metadata instead of redundant filesystem stats, improving performance.
- Added maxResults parameter to find tool to limit result set at the native layer.
- Migrated environment variable handling to use centralized getEnv() and getEnvApiKey() utilities from pi-ai package.
- Removed environment variable denylist that previously blocked API keys from being passed to subprocesses.
- Simplified web search error messages by removing provider-specific configuration hints.
- Eliminated duplicate environment variable and .env file parsing logic across web search providers by delegating to centralized utilities.
- Implemented caching in table and cell results renderers to avoid redundant recalculations when width or cell data hasn't changed.
- Added cache invalidation logic to clear cached render results when cell data or spinner state changes.
- Added getCompactContext() API to agent session for accessing parent conversation context.
- Implemented automatic submit_result tool injection for subagents with explicit tool lists.
- Added contextFile parameter to ExecutorOptions for passing parent conversation context to subagents.
- Enhanced subagent system prompt with conditional context file instructions and improved code formatting.
- Removed schema override notification from task summary prompt to simplify output.
- Implemented formatCompactContext() method to format conversation history for subagent consumption.
- Simplified find tool API by removing separate `path` parameter and consolidating pattern parsing into a single `pattern` parameter that includes the search path.
- Added automatic recursive search for simple patterns like `*.ts` by implicitly prefixing them with `**/` when no explicit path is provided.
- Implemented `parsePatternPath()` function to intelligently extract base directory and glob pattern from user input, supporting patterns like `src/**/*.tsx`, `lib/*.json`, and `*.md`.
packages/ai:
- fix: handle "sensitive" stop reason from Anthropic API
- fix: normalize tool call IDs with special characters for Responses API
- fix: add overflow detection for Bedrock, MiniMax, Kimi providers
- fix: 429 status is rate limiting, not context overflow
packages/tui:
- fix: refactored autocomplete state tracking
- fix: file autocomplete should not trigger on empty text
- fix: configurable autocomplete max visible items
- fix: improved table column width calculation with word-aware wrapping
packages/coding-agent:
- fix: preserve external config.yml edits on save (#1046 by @nicobailonMD)
- fix: resolve macOS NFD and curly quote variants in file paths
- Added `RequestOptions` interface to worker pool with support for `timeoutMs`, `signal`, and `transfer` properties.
- Added `stuckGracePeriodMs` configuration option to `WorkerPoolOptions` for graceful handling of stuck workers after timeout.
- Enhanced worker pool request method to accept `RequestOptions` object parameter instead of simple transfer array, enabling timeout and abort signal handling.
- Implemented comprehensive timeout and abort signal handling in worker pool with support for combined signals and grace period before force-terminating stuck workers.
- Removed html2text tool from coding agent in favor of native WASM html-to-markdown converter.
- Exported `RequestOptions` type from natives package public API.
- Added HTML to Markdown conversion functionality via new WASM binding in pi-natives crate with configurable options for content cleaning and image skipping.
- Exported htmlToMarkdown async function from @oh-my-pi/pi-natives package with worker pool support for efficient HTML to Markdown conversion.
- Integrated native WASM HTML to Markdown converter as the primary conversion method in fetch tool, replacing text-only rendering with markdown output.
- Added html-to-markdown-rs dependency to pi-natives crate for server-side HTML to Markdown conversion with preprocessing support.
- Added comprehensive test coverage for htmlToMarkdown function including headings, links, lists, code blocks, and conversion options.
- Consolidated signal and timeout handling by replacing custom createRequestSignal utility with ptree.combineSignals across all scrapers and tools.
- Refactored ensureTool function to accept signal parameter through options object, enabling cancellation of tool installation and execution.
- Migrated all tool execution calls from Bun's $ template syntax to ptree.exec with explicit signal and error handling options.
- Simplified HTML rendering strategy in fetch.ts to use ptree.combineSignals for timeout management and added jina.ai integration as primary rendering method.
- Removed redundant abort checks throughout youtube.ts scraper, consolidating signal handling to rely on ptree.exec signal-based timeout mechanism.
- Fixed incorrect byte and line limit calculations in file read tool that were applying user limits to total selected content instead of just user-limited content.
- Updated test to use SettingsManager.getGlobalShellConfig() instead of shell.getShellConfig() for consistent shell configuration access.
- Reorganized import statements across multiple files for consistency and alphabetical ordering.
- Changed firstLinePreviewChunks from let to const in read tool since it is only mutated via array methods.
- Refactored file reading logic to process bytes directly instead of decoding entire chunks into strings, improving memory efficiency and enabling better line boundary detection.
- Restructured line collection state management with dedicated helper functions (setupLineState, appendSegment, finalizeLine, decodeLine) for clearer control flow and byte tracking.
- Enhanced byte limit tracking to accurately count selected lines and bytes separately, fixing calculation of truncation metadata.
- Added firstLinePreview and firstLineByteLength fields to streamLinesFromFile return type to support better handling of oversized first lines.
- Improved firstLineExceedsLimit detection to use actual byte length instead of relying on empty collection state.
- Removed TUI layout engine exports from public API surface.
- Replaced Bun.file().stream() with fs/promises for manual buffer reading in file streaming.
- Added AbortSignal support to streamLinesFromFile for cancellation capability.
- Removed stdin monitoring feature that detected stalled input after 10 seconds.
- Removed cli-highlight and highlight.js dependencies from lock file.
- Rebuilt WASM module with reduced binary size (2.1% reduction).
can1357