- Added `onPayload` callback option to intercept and transform provider request payloads before transmission across agent and AI packages.
- Added structured text signature metadata with phase information to OpenAI and Azure OpenAI providers for enhanced response tracking.
- Added `before_provider_request` extension event to coding-agent for chaining payload transformations across multiple handlers.
- Improved error messages in `response.failed` events with detailed error codes, messages, and incomplete reasons from provider responses.
- Introduced Effort enum and ThinkingConfig metadata for per-model reasoning capabilities with min/max effort levels.
- Migrated thinking level API from string-based ThinkingLevel to structured Effort enum across agent and AI packages.
- Added model-thinking module with effort mapping, policy application, and semantic versioning utilities for provider-specific thinking modes.
- Removed supportsXhigh() function and replaced effort clamping with model-aware validation using ThinkingConfig metadata.
- Expanded models.json with thinking configuration objects for 50+ models including Claude, Gemini, and OpenAI variants.
- Added Python analysis scripts for edit tool usage patterns and tool invocation stream processing.
- Added serviceTier option to OpenAI providers for controlling processing priority and cost across agent, completions, responses, and codex APIs.
- Added providerPayload field to messages for transport-native history reconstruction in OpenAI Responses and Codex APIs.
- Added /fast slash command and serviceTier setting to coding-agent for toggling OpenAI priority mode with fast mode indicator.
- Added remote compaction support with encrypted reasoning preservation for OpenAI models in coding-agent.
- Removed usage caching layer across all providers and refactored UsageFetchContext to eliminate cache and now dependencies.
- Fixed OpenAI Codex streaming service_tier inclusion, provider retry logic with exponential backoff, and email-based credential deduplication.
- Extracted thinking module with ThinkingEffort, ThinkingLevel, and ThinkingMode types to centralize reasoning configuration across packages.
- Migrated ThinkingLevel type from pi-agent-core to pi-ai package with new validation functions parseThinkingLevel() and getAvailableThinkingLevel().
- Consolidated thinking level constants and descriptions into reusable exports (ALL_THINKING_LEVELS, THINKING_MODE_DESCRIPTIONS) for consistent UI display.
- Removed local thinking-effort-label utility and replaced formatThinkingEffortLabel() with centralized formatThinking() function from pi-ai.
- Refactored thinking mode handling to distinguish ThinkingSelector (user-facing with 'off' option) from ThinkingEffort (provider-level).
- Extracted tool result emission logic into dedicated emitToolResult function to eliminate duplication.
- Consolidated tool execution result handling to emit results immediately after execution rather than deferring to post-processing loop.
- Simplified post-execution loop by delegating result emission to emitToolResult and removing redundant message construction.
- Introduce `deferrable?: boolean` on AgentTool, CustomTool, and ToolDefinition.
AstEditTool sets it to true; resolve is now injected only when at least one
active tool is deferrable (previously unconditional).
- Replace single-slot PendingActionStore (set/get/clear) with a LIFO stack
(push/peek/pop/clear). Multiple deferrable tools can stage independent
preview actions; resolve always consumes the topmost one first.
- Wire pendingActionStore through discoverAndLoadCustomTools / loadCustomTools /
CustomToolLoader so custom tools can call pushPendingAction(action) to
register a resolve-compatible pending action with label, apply callback,
optional details, and optional sourceToolName.
- Export HIDDEN_TOOLS and ResolveTool from the SDK for manual tool composition.
- Add CustomToolPendingAction type and pushPendingAction to CustomToolAPI.
- Update createAgentSession to re-inject or remove resolve after the deferrable
audit, consistent with createTools behavior.
- Add LIFO resolve test, update existing tests (set -> push, get -> peek).
- Add docs/resolve-tool-runtime.md covering PendingActionStore internals,
built-in producer example, and custom tool usage guide.
- Removed normativeRewrite setting and buildNormativeUpdateInput() function from public API.
- Removed $normative property and TNormative generic parameter from ToolResultMessage and AgentToolResult interfaces.
- Deleted normative.ts patch normalization module and related helper functions for diff anchor processing.
- Removed rewriteAssistantToolCallArgs() and #rewriteToolCallArgs() methods that modified tool call arguments.
- Renamed intent field from `agent__intent` to `intent` in tool schemas for cleaner API contracts.
- Refined intent parameter guidance to require concise 2-6 word present participle sentences.
- Updated intentTracing documentation and test fixtures to reflect the new field naming convention.
- Added lenientArgValidation option to tools for graceful handling of argument validation errors.
- Refactored schema reference resolution to inline all $ref definitions instead of preserving them at root level.
- Added circular reference detection during schema resolution to prevent infinite loops.
- Added AJV compilation verification to catch unresolved $ref references before tool execution.
- Added topP, topK, minP, presencePenalty, and repetitionPenalty sampling control options to StreamOptions and AgentOptions interfaces.
- Implemented getter and setter properties on Agent class for runtime configuration of model sampling parameters.
- Added UI configuration and preset value providers for five new sampling parameters in coding-agent settings schema and components.
- Integrated sampling control parameters through proxy layer and agent session configuration for end-to-end provider support.
- Added fallback empty string for undefined tool descriptions across all AI providers to prevent runtime errors.
- Made `description` field required in CustomTool interface and normalized tool descriptions in agent-loop.
- Refactored tool normalization in agent-loop by renaming `injectIntentIntoTools()` to `normalizeTools()` with conditional intent injection.
- Added comprehensive description metadata to todo-write tool schema fields for improved clarity.
Move agent__intent description from per-tool JSON schema injection (repeated
once per tool) into a single conditional block in the system prompt template.
Token savings scale with tool count.
- agent-loop: remove description from intent schema injection
- system-prompt.md: add intentTracing/intentField template block
- sdk: compute intentField once, pass through to prompt builder
- system-prompt.ts: thread intentField option into template context
- Renamed `file` parameter to `path` in edit tool schemas and all test cases for consistency.
- Removed `file` property fallback from EditRenderArgs interface and path resolution methods.
- Refactored browser viewport schema to use snake_case `device_scale_factor` with explicit camelCase mapping for Puppeteer API.
- Added hashline edit rule requiring `end` tag to include closing braces/brackets when replacing blocks.
- Refactored INTENT_FIELD injection logic to conditionally reorder schema properties and update required array.
- Updated tool result messages to include error details when tool execution fails.
- Modified createAbortedToolResult() to accept optional errorMessage parameter for enhanced error reporting.
- Changed hashline format separator from pipe (|) to colon (:) for improved readability across all tools and output formats.
- Refactored hashline edit API with operation-based structure: renamed delete->rm, rename->mv, set->target/new_content, and added explicit op field for operation types.
- Updated hashline hash encoding from 4-character base36 to 2-character hexadecimal for more compact representation.
- Replaced anchor terminology with tags throughout hashline documentation and API for clearer semantics.
- Added streamed tool intent display in working message to show real-time intent tracking during agent execution.
- Changed intent tracing field name from `$intent` to `_intent` across tool schemas and agent core for consistency.
- Added support for file deletion and renaming operations in hashline edit mode.
- Renamed hashline edit operation fields: `set` to `target`/`new_content`, `set_range` to `first`/`last`/`new_content`, `insert` to `inserted_lines`.
- Added optional `intent` field to `ToolCall` interface for capturing harness-level intent metadata.
- Added `intentTracing` configuration option to enable intent goal extraction from tool calls with automatic `$intent` field injection and argument stripping.
- Implemented intent injection and extraction logic in agent-loop to populate tool call intent metadata when intentTracing is enabled.
- Added `tools.intentTracing` setting to coding-agent configuration schema with environment variable override support.
- 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.
- Added ModelManager API with createModelManager() factory for managing bundled and dynamically discovered models with configurable refresh strategies.
- Exported discovery utilities for fetching models from Antigravity, Codex, Cursor, Gemini, and OpenAI-compatible endpoints with provider-specific model manager configuration helpers.
- Renamed public API functions for clarity: getModel() -> getBundledModel(), getModels() -> getBundledModels(), getProviders() -> getBundledProviders().
- Added on-disk model caching with TTL-based invalidation and resolveProviderModels() function for runtime model resolution with source precedence.
- Refactored model discovery script to dynamically fetch models from Codex, Cursor, and Antigravity using OAuth credentials instead of hardcoded lists.
- Refactored tool wrapping logic from array-based function to per-tool wrapper with guard clause to prevent double-wrapping.
- Replaced Proxy-based tool wrapping with Object.defineProperties to preserve property access behavior and private fields on original tool objects.
- Consolidated tool wrapping into createTools function, removing intermediate wrapping step from sdk.ts.
- Extracted FETCH_DEFAULT_MAX_LINES constant to fetch.ts for local use instead of importing from truncate module.
- Converted else-if control flow to separate if statement for artifactId check in notice formatting logic.
- Added automatic retry logic for WebSocket stream closures before response completion with configurable retry budget.
- Changed `providers.openaiWebsockets` setting from boolean to enum with values 'auto', 'off', 'on' for more granular WebSocket policy control.
- Implemented WebSocket stream retry mechanism that attempts reconnection before falling back to SSE transport when retry budget is exhausted.
- Fixed WebSocket stream retry logic to properly handle mid-stream connection closures and preferWebsockets option handling.
- Added helper functions isCodexWebSocketTransportError() and isCodexWebSocketRetryableStreamError() to classify WebSocket errors.
- Reorganized imports across multiple files for better code organization and consistency.
- Added `providerSessionState` option to share provider state map for session-scoped transport and session caches.
- Added WebSocket retry logic with configurable retry budget and delays via environment variables.
- Added WebSocket idle timeout detection to prevent hanging connections.
- Added WebSocket v2 beta header support for newer protocol versions.
- Added WebSocket handshake header capture to extract and replay session metadata.
- Implemented automatic cleanup of provider session state resources on session disposal.
- Added WebSocket transport support for OpenAI Codex responses with automatic fallback to SSE on connection failure.
- Added preferWebsockets option to Agent and Model configurations to hint that WebSocket transport should be preferred when supported by provider implementations.
- Added prewarmOpenAICodexResponses() function to pre-establish WebSocket connections for improved performance.
- Added getProviderDetails() function and getOpenAICodexTransportDetails() function to expose transport state and provider configuration information.
- Added provider details display in session info showing active provider configuration and authentication details.
- Added OpenAI websockets setting to enable WebSocket transport preference for OpenAI Codex models in coding agent configuration.
- Added `temperature` configuration setting to control LLM sampling temperature with values from 0 (deterministic) to 1 (creative) to -1 (provider default).
- Added temperature option selector in settings UI with preset values: Default, 0, 0.2, 0.5, 0.7, 1.
- Renamed `settingsInstance` parameter to `settings` in `CreateAgentSessionOptions` for consistency.
- Updated all internal references from `settingsInstance` to `settings` throughout SDK and components.
- Integrated temperature setting into agent configuration and selector controller.
- Fixed handling of aborted requests to properly throw abort errors when stream terminates without a terminal event.
- Fixed exit error handling in ChildProcess.wait() to properly capture exit reasons and non-zero exit codes.
- Fixed stdout text conversion in ChildProcess.wait() to use Response API for proper text decoding.
- 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 default generic type parameter to Model interface, allowing Model to be used without explicit type argument.
- Removed explicit <any> generic type parameters from Model type annotations throughout codebase, leveraging new default parameter.
- Migrated from Node.js to Bun runtime by replacing @types/node with @types/bun and bun-types dependencies.
- Downgraded @types/diff from ^8.0.0 to ^7.0.2 in coding-agent package.
- Updated tsconfig.base.json to include DOM.AsyncIterable in lib configuration for async iterable DOM API support.
- Simplified stream handling in update-cli.ts by removing Readable.fromWeb() conversions and using response.body directly with pipeline().
- Simplified TextDecoderStream instantiation in stream.ts to use default parameters instead of explicit UTF-8 encoding configuration.
- Added defensive null/undefined handling in agent-loop.ts result assignment using nullish coalescing operator.
- Added `concurrency` option to `AgentTool` interface supporting 'shared' (default, parallel execution) and 'exclusive' (solo execution) modes.
- Implemented parallel execution of shared tools within a single agent turn with ordered result emission.
- Refactored tool execution to support concurrent scheduling with interrupt handling via steering messages and AbortSignal.
- Added steering message checking mechanism that interrupts tool execution when user messages arrive during tool processing.
- Removed HTTP proxy setup code from stream.ts that was conditionally setting up undici global dispatcher.
- Added Kimi Code provider with support for both OpenAI and Anthropic API formats.
- Added kimiApiFormat configuration option to allow users to select between 'openai' and 'anthropic' API formats for Kimi Code provider.
- Added Kimi API format setting in the tools configuration tab with descriptions for each format option.
- Refactored Anthropic provider authentication logic to support multiple API endpoints including Kimi's Anthropic-compatible API.
- Updated OpenAI completions provider to route direct Kimi models to dedicated Kimi provider implementation.
- 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.
- 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.
- 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.
- 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.
- Added Cursor OAuth provider support to CLI authentication flow.
- Fixed race conditions in OAuth callback handling and session picker cleanup.
- Improved JWT token parsing and error handling across OAuth providers.
- Replaced Bun.sleep() with abortable sleep for proper cancellation support.
- Enhanced process execution with concurrent stream reading and better timeout handling.
- Added cache cleanup mechanism for auth storage with 5-minute intervals.
- 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.
- Reformatted code indentation and spacing across multiple TypeScript files.
- Standardized export statements to single-line format in various modules.
- Fixed async/await precedence and corrected indentation in benchmark files.
- Added benchmark report files for GPT-5.1-codex-mini model performance.
- Added normative patch generation for canonicalizing edit tool output.
- Implemented tool call argument rewriting for session history persistence.
- Enhanced patch applicator to support normalized patch input processing.
- Updated agent and AI types to include normative input parameters.
- Removed tar-stream dependency and replaced with Bun.Archive for benchmark package.
- Converted all tool implementations from factory functions to class-based architecture.
- Updated SDK exports to expose tool classes instead of create*Tool factory functions.
- Refactored tool instantiation patterns across all built-in tools and test files.
- Added proper TypeScript typing with AgentToolResult and AgentToolUpdateCallback interfaces.
- Added ToolCallContext interface with batch execution metadata including batchId, index, and total.
- Enhanced getToolContext() to accept optional ToolCallContext parameter for batch-aware tool execution.
- Implemented LSP batching support to coalesce formatting and diagnostics operations on parallel edits.
- Added comprehensive tests for tool call batch context and LSP writethrough batching functionality.
- Added proper tool result messages for tool calls that are aborted or error out.
- Ensured tool_use/tool_result pairing is maintained when tool execution fails.
can1357