- 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.
- 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.
- 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.
- 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.
- Added tsconfig.publish.json files to all packages with optimized publish-time configuration.
- Updated all package.json scripts with prepublishOnly hooks for correct type checking during publish.
- Added @oh-my-pi/omp-stats path mappings to root tsconfig.json for consistent imports.
- Added WASM generation script for photon module and integrated into install:dev script.
- Fixed OpenAI Responses API 400 error when switching between models
(same provider, different model). Omits fc_ prefixed IDs from different
models to avoid reasoning/function_call pairing validation errors.
(ported from d327b9c7)
- Fixed 400 errors when reading multiple images via GitHub Copilot's
Claude models. Batches images from consecutive tool results into a
single user message to maintain tool_use -> tool_result adjacency.
(ported from 6289c144)
- 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 headers option to all providers for custom request headers.
- Added onPayload hook to observe provider request payloads before sending.
- Added strictResponsesPairing option for Azure OpenAI Responses API compatibility.
- Added originator option to loginOpenAICodex for custom OAuth flow identification.
- Enhanced AWS credential detection to support ECS task roles and IRSA web identity tokens.
- Created new @oh-my-pi/pi-utils workspace package with shared utilities for logging, process management, stream handling, and temporary directory management.
- Migrated all packages to use centralized logger from @oh-my-pi/pi-utils instead of local winston implementations.
- Replaced custom process spawning and stream reading implementations with standardized cspawn and readLines utilities across all modules.
- Converted synchronous file operations and process spawning to async patterns using Bun shell syntax and fs/promises.
- Added streaming edit abort functionality with configurable setting to abort on patch preview failures.
- Updated test framework from vitest to bun:test across all test suites.
- Added new @oh-my-pi/react-edit-benchmark package for React source code mutation testing.
- Added --no-title flag to disable automatic session title generation in coding-agent.
- Changed default behavior of read tool to omit line numbers by default.
- Added environment variable support for edit tool configuration and fuzzy matching.
- Updated test files to use import.meta.dir for ES module compatibility.
- Added Prettier configuration and CI improvements for private package handling.
- Prevented duplicate tool results for errored or aborted messages when results already exist.
- Added comprehensive test coverage for duplicate tool results edge cases.
- 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.
The sanitizeSchemaForGoogle function was incorrectly stripping property
names like "pattern" and "format" from tool schemas because they matched
JSON Schema keywords in UNSUPPORTED_SCHEMA_FIELDS. This caused errors
like "required fields ['pattern'] are not defined in the schema properties"
when using tools like grep/find with Google's Cloud Code Assist API.
Modified the sanitization to track when processing inside a "properties"
object, only stripping schema keywords at the schema level, not when
they appear as property names.
- Fixed incorrect classification of thought signatures in Google Gemini responses by clarifying that `thought: true` is the definitive marker for thinking content, not `thoughtSignature`.
- Fixed thought signature handling in Google Gemini CLI and Vertex AI streaming to properly preserve signatures across text deltas using `retainThoughtSignature()` function.
- Simplified `isThinkingPart()` function to only check `part.thought === true`, removing incorrect `thoughtSignature` length check.
- Updated protocol documentation to clarify that `thoughtSignature` is an encrypted representation used for context replay across multi-turn interactions and can appear on any part type.
- Updated Claude Code version from 1.0.83 to 2.1.2 in Anthropic provider configuration.
- 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.
- Switched OpenAI Codex to use bundled system prompt matching opencode upstream.
- Changed OpenAI Codex originator identifier from 'codex_cli_rs' to 'opencode'.
- Added User-Agent header with version, platform, and architecture information to Codex requests.
- Removed dynamic GitHub-based instruction fetching and caching logic in favor of static inline instructions.
- Removed buildCodexPiBridge function and pi-codex-bridge module, replacing with inline BRIDGE constant.
- Removed Codex injection info from HTML session exports.
- Added automatic type coercion for tool arguments when LLMs return JSON-encoded strings instead of native types.
- Changed tool argument validation to attempt JSON parsing and type coercion before rejecting mismatched types.
- Changed validation error messages to include both original and normalized arguments when coercion was attempted.
- Added JSON Pointer utilities for reading and writing values at RFC 6901 paths.
- Added comprehensive test suite for tool argument coercion scenarios.
- Port pi-ai from upstream with Bun-first approach (source files, no dist)
- Add cli_ prefix to tool names in OAuth mode to avoid collisions
- Improve beta header handling with proper deduplication
- Convert codex-instructions.md to Bun text embed
- Strip .js extensions from all imports
- Changed isError property from required to optional across ToolResultMessage and tool event interfaces.
- Added SpinnerType variants with distinct animation frames per symbol preset.
- Fixed spinner animation crash when frames array is empty by adding guard clause.
- Refactored agent-loop tool execution to consolidate toolCallId, toolName, and isError into details object.
- Renamed CLI binary and package from 'pi' to 'omp' across all platforms and installers.
- Changed environment variable prefix from PI_* to OMP_* with automatic migration support.
- Changed configuration directory from ~/.pi/ to ~/.omp/ with multi-path fallback discovery.
- Added getConfigDirPaths(), findConfigFile(), and readConfigFile() functions for config resolution across .omp, .pi, and .claude directories.
Merged 53 commits from pi/main including:
- Export HTML rewrite with tree sidebar and /share command
- Hooks API enhancements (custom status, editor, session management)
- Edit diff preview before tool execution
- TUI fixes (Unicode format chars, OSC 8 hyperlinks, emoji optimization)
- Gemini CLI rate limit retry with server-provided delay
- Various bug fixes and documentation updates
Resolved conflicts by preserving Bun migration (spawn→Bun.spawn,
fs→Bun.file) while accepting upstream's new features and APIs.
- Migrated from Node.js to Bun runtime to leverage native TypeScript execution and faster startup times.
- Replaced npm with bun package manager and updated lockfile format.
- Converted Node.js APIs (child_process, fs, readline) to Bun equivalents across all packages.
- Updated shebang lines from node/tsx to bun for CLI entry points.
- Removed TypeScript build step by using source files directly as package entry points.
- Updated CI workflows to use Bun instead of Node.js for installation and testing.
- Removed Agent API section from pi-ai README (moved to agent package)
- Rewrote agent package README for new architecture:
- No more transports (ProviderTransport, AppTransport removed)
- Uses streamFn directly with streamProxy for proxy usage
- Documents convertToLlm and transformContext
- Documents low-level agentLoop/agentLoopContinue API
- Updated custom message types documentation
- Renamed AppMessage to AgentMessage throughout
- New agent-loop.ts with AgentLoopContext, AgentLoopConfig
- Removed transport abstraction, Agent now takes streamFn directly
- Extracted streamProxy to proxy.ts utility
- Removed agent-loop from pi-ai (now in agent package)
- Updated consumers (coding-agent, mom) for AgentMessage rename
- Tests updated but some consumers still need migration
Known issues:
- AgentTool, AgentToolResult not exported from pi-ai
- Attachment not exported from pi-agent-core
- ProviderTransport removed but still referenced
- messageTransformer -> convertToLlm migration incomplete
- CustomMessages declaration merging not working properly
- Migrate glm-4.5, glm-4.5-air, glm-4.5-flash, glm-4.6, glm-4.7 from anthropic-messages to openai-completions API
- Updated baseUrl from https://api.z.ai/api/anthropic to https://api.z.ai/api/coding/paas/v4
- Added compat setting to disable developer role for zai models
- Filter empty text blocks in openai-completions to avoid zai API validation errors
- Fixed zai provider tests to use OpenAI-style options (reasoningEffort)
- Change all zai models from anthropic-messages to openai-completions API
- Update baseUrl from https://api.z.ai/api/anthropic to https://api.z.ai/api/coding/paas/v4
- Add compat setting to disable developer role for zai
- Update zai provider tests to use OpenAI-style options (reasoningEffort instead of thinkingEnabled/thinkingBudgetTokens)
- Enable previously disabled thinking and image input tests for zai models
- Remove setApiKey, resolveApiKey, and global apiKeys Map from stream.ts
- Rename getApiKey to getApiKeyFromEnv (only checks env vars)
- Remove OAuth storage layer (storage.ts deleted)
- OAuth login/refresh functions now return credentials instead of saving
- getOAuthApiKey/refreshOAuthToken now take credentials as params
- Add test/oauth.ts helper for ai package tests
- Simplify root npm run check (single biome + tsgo pass)
- Remove redundant check scripts from most packages
- Add web-ui and coding-agent examples to biome/tsgo includes
coding-agent still has compile errors - needs refactoring for new API
When a user interrupts a tool call flow (sends a message without providing
tool results), APIs like OpenAI Responses and Anthropic fail because:
- OpenAI requires tool outputs for function calls
- OpenAI requires reasoning items to have their following items
- Anthropic requires non-empty content for error tool results
Instead of filtering out orphaned tool calls (which breaks thinking signatures),
we now insert synthetic empty tool results with isError: true and content
'No result provided'. This preserves the conversation structure and satisfies
all API requirements.
can1357