- Added stripInternalArgs() utility function to filter harness-internal keys from tool arguments.
- Hidden agent__intent parameter from UI and log displays across agent, session, MCP, and tool-execution components.
- Implemented HIDDEN_ARG_KEYS constant to centrally manage internal argument filtering.
- Updated formatArgsInline() to exclude internal keys when rendering tool arguments.
- Added async background job execution for bash and task tools with configurable concurrency limits and automatic result delivery.
- Added cancel_job tool and /jobs slash command to manage and inspect running background jobs with status display.
- Added jobs:// internal protocol handler for querying job status and retrieving job execution details.
- Added async.enabled and async.maxJobs settings to control background job execution behavior.
- Enhanced status line to display count of running background jobs with visual indicator.
- Implemented AsyncJobManager with exponential backoff retry delivery, job lifecycle tracking, and automatic eviction.
Fixes#56.
- Moved artifact management from ToolSession to SessionManager for centralized lifecycle control and caching.
- Replaced getArtifactManager() with allocateOutputArtifact() async method in ToolSession interface for simplified artifact allocation.
- Updated bash, fetch, python, and ssh tools to call session.allocateOutputArtifact() directly with optional chaining fallback.
- Fixed Lobsters scraper to handle user fields as strings instead of nested objects in API responses.
- Refactored byte truncation to use unified `truncateBytesWindowed` function supporting both head and tail modes, reducing code duplication.
- Optimized `truncateHead` and `truncateTail` to avoid full Buffer allocation by processing content incrementally with character-level scanning.
- Improved `TailBuffer.append()` to handle large incoming chunks more efficiently by detecting when a single chunk dominates the tail budget.
- Enhanced `OutputSink.push()` to avoid creating giant intermediate strings when spilling to files by windowing large chunks before concatenation.
- Refactored newline counting to use a constant `NL` for consistency across the module.
- Migrated AuthCredentialStore and AuthStorage to shared modules, standardizing credential management and soft deletion.
- Consolidated Anthropic authentication and various other formatting/utility helpers into shared modules.
- Improved unicode normalization in patch logic with regex for efficiency and correctness.
- Enhanced JTD type guards for robust schema validation.
- Extracted credential storage to shared @oh-my-pi/pi-ai package with AuthCredentialStore and AuthStorage classes.
- Consolidated UI formatting logic from ToolUIKit class into standalone utility functions across render-utils and output-meta modules.
- Moved utility functions (parseCommandArgs, substituteArgs, expandPath, normalizeUnicode) to dedicated modules for improved code reuse.
- Extracted JTD type definitions and type guards to jtd-utils module for shared use across schema conversion tools.
- Updated Claude model pricing and added cache read costs in models.json for accurate billing calculations.
- Refactored agent-storage to delegate credential management to AuthCredentialStore instead of direct SQLite operations.
- Added GitLab Duo provider with support for Claude, GPT-5, and Duo Chat models via GitLab AI Gateway.
- Added OAuth authentication for GitLab Duo with automatic token refresh, PKCE security, and 25-minute token caching.
- Added 16 new GitLab Duo models including Claude Opus/Sonnet/Haiku and GPT-5 variants with reasoning and multimodal support.
- Added `isOAuth` option to Anthropic provider for OAuth bearer token authentication mode.
- Exported `streamGitLabDuo`, `getGitLabDuoModels`, and `clearGitLabDuoDirectAccessCache` functions for GitLab Duo integration.
- Consolidated truncation and output utilities from tools/truncate.ts and tools/output-utils.ts into session/streaming-output.ts with improved UTF-8 boundary handling.
- Renamed formatSize() to formatBytes() across codebase for consistency and clarity in byte-level formatting.
- Refactored OutputSink to use windowed byte truncation instead of full-buffer encoding, improving memory efficiency on large outputs.
- Migrated from Buffer to Uint8Array in web scrapers for better cross-platform compatibility and native browser support.
- Added getArtifactManager() lazy-initialization method to ToolSession for deferred artifact manager instantiation.
- Simplified API surface with wildcard exports from tools and session modules, reducing import complexity.
- Exported readModelCache and writeModelCache functions for SQLite-backed model cache access.
- Migrated model cache storage from per-provider JSON files to unified SQLite database (models.db).
- Renamed cachePath option to cacheDbPath in ModelManagerOptions for database-backed storage.
- Improved non-authoritative cache handling with 5-minute retry backoff instead of per-startup retries.
- Added peekApiKey method to AuthStorage for non-blocking API key retrieval during model discovery.
- Added <turn_aborted> guidance marker as synthetic user message for aborted/errored assistant messages.
- Improved OAuth token refresh error messages to include provider-specific error details from API responses.
- Separated rate limit and usage limit error handling in OpenAI response handler with distinct error messages and retry timing.
- Enhanced error message propagation in OAuth refresh flow to preserve original error reasons for better debugging.
- Fixed regex pattern in auth storage to use word boundaries for accurate HTTP status code matching.
- Added `includeDisabled` parameter to `listAuthCredentials()` to optionally retrieve disabled credentials.
- Added `disableAuthCredential()` method for soft-deleting auth credentials while preserving database records.
- Changed auth credential removal to use soft-delete (disable) instead of hard-delete when OAuth refresh fails, keeping credentials in database for audit purposes.
- Added `disabled` column to auth_credentials table schema with automatic migration from v3 to v4.
- Added prepared statements for querying active (non-disabled) credentials with optional provider filtering.
- 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 'unable to connect' to transient error patterns in retry logic to properly handle connection failures.
- Updated retry error detection in coding-agent to match ai package pattern for consistency.
- Reorganized import statements in openai-compat.ts for consistency.
- Consolidated multi-line ternary expression into single line in openai-compat.ts.
- Simplified AgentBusyError instantiation to use default message.
- Updated test assertion to check error type instead of message content.
- Added support for 11 new AI providers (Hugging Face, NVIDIA, Together, Ollama, LiteLLM, Xiaomi, Moonshot, Venice, Qwen Portal, vLLM, Cloudflare AI Gateway) with API key authentication and login flows.
- Implemented $pickenv() utility for environment variable fallback chains, enabling multi-key resolution for providers with alternative credential names.
- Extended KnownProvider and OAuthProvider types to include all 11 new providers with corresponding model manager functions and OAuth handlers.
- Expanded models.json with thousands of new model entries across all new providers and replaced deprecated opencode provider with cloudflare-ai-gateway.
- Refactored model generation script to use unified fetchProviderModelsFromCatalog() and centralized API key resolution for all providers.
- 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 TTSR injection tracking with per-turn recording and deduplication to prevent repeated rule injections within the same turn.
- Changed TTSR message format to use custom message type with metadata fields for improved injection tracking and session persistence.
- Fixed TTSR repeat-after-gap mode to correctly restore injected rules from previous sessions and recalculate gap thresholds.
- Added test suite with 6 test cases covering TTSR repeat modes (once, after-gap, restored) and injection deduplication behavior.
- Added scoped TTSR rule matching with condition and scope fields supporting file globs and tool-specific filtering.
- Added ttsr.interruptMode setting to control when TTSR rules interrupt agent responses (never/prose-only/tool-only/always).
- Added support for loading rules, prompts, and commands from ~/.agent/ directory with fallback to ~/.agents/.
- Refactored rule discovery across all providers to use unified buildRuleFromMarkdown helper and per-stream-key buffering.
- Enhanced TTSR pattern matching to respect tool-specific scope filters and normalize file paths in glob matching.
- Exported `getTerminalId()` and `getTtyPath()` functions from tui package for obtaining stable terminal identifiers with support for TTY device paths and terminal multiplexers.
- Improved path display in status line to strip both `/work/` and `~/Projects/` prefixes when abbreviating paths.
- Refactored session directory naming to use single-dash format for home-relative paths and double-dash format for absolute paths, with automatic migration of legacy session directories on first access.
- Implemented TTY ID utilities in tui package with platform-specific TTY path resolution using /proc/self/fd/0 on Linux, dlopen on macOS/BSD, and libc on other Unix systems.
- Added macOS path standardization to strip `/private` prefix from paths when both original and stripped paths resolve to the same location.
- Changed context promotion to trigger on context overflow errors instead of a configurable threshold percentage.
- Removed the contextPromotion.thresholdPercent configuration setting.
- Updated context promotion to retry immediately on the promoted model without requiring compaction.
- Refactored context promotion logic to attempt promotion before compaction in the overflow handling flow.
- Updated agent session to merge context promotion checks into the compaction method for unified overflow handling.
- Updated tests to reflect overflow-based promotion triggering instead of threshold-based promotion.
- Added contextPromotionTarget model property to specify preferred fallback model when context promotion is triggered.
- Added automatic context promotion target assignment for Spark models to their base model equivalents.
- Updated Qwen model context window and max token limits for improved accuracy.
- Updated o1 model context window from 256000 to 262144 tokens and max tokens from 64000 to 65536 tokens.
- Implemented context promotion logic to use configured contextPromotionTarget when available instead of role-based model resolution.
- Added effectiveReserveTokens() function to enforce a minimum 15% context window floor for session compaction reserve calculations.
- Updated shouldCompact() to use effectiveReserveTokens() instead of raw configured reserve, ensuring more predictable compaction behavior regardless of configuration.
- Implemented file operation summary limiting to 20 files per category with indication of omitted files when exceeded.
- Added truncateFileList() helper function to limit file arrays and append ellipsis message showing omitted file count.
- Added stripFileOperationTags() helper function to remove XML file operation tags from summary strings.
- Introduced upsertFileOperations() function to merge base summary with file operations by stripping old tags and concatenating new ones.
- Refactored branch-summarization and compaction modules to use new upsertFileOperations() function instead of formatFileOperations().
- Added automatic context promotion feature that switches to larger-context models when approaching context limits.
- Added 'contextPromotion.enabled' setting to control automatic model promotion with default value of enabled.
- Added 'contextPromotion.thresholdPercent' setting to configure context usage threshold for triggering promotion with default value of 90%.
- Implemented context promotion logic in AgentSession that monitors token usage and automatically switches models when threshold is exceeded.
- Added provider session cleanup during model switches to properly handle session state transitions.
- Added comprehensive test coverage for context promotion functionality including threshold-based promotion and non-promotion scenarios.
Hashline prefixes (LINE:HASH|content) in read/grep output exist solely to
support the hashline edit mode. Agents that don't have the edit tool
(e.g. explore, plan, reviewer) gain nothing from them — they just waste
tokens and add noise.
resolveFileDisplayMode now takes a session-like object with an optional
hasEditTool flag. When false, hashlines are suppressed regardless of
settings. ToolSession gains hasEditTool (set from toolNames in the SDK),
and AgentSession exposes it as a getter over the tool registry.
- Fixes deferred `--model` resolution to match extension-provided models before fallback
- Fixes CLI `--api-key` handling to support deferred model selection
- Adds OAuth provider support for extensions with source-scoped registration cleanup
- Adds custom API registration helpers with built-in collision checks
- Expands `Api` type to support extension-defined identifiers
- Adds tests for runtime provider registration and model selection
Replace single `theme` setting with `theme.dark` and `theme.light`.
Auto-detection is always on — COLORFGBG determines which slot to use.
On SIGWINCH, re-check COLORFGBG and switch themes if background changed.
Old `theme` setting auto-migrated using luminance detection.
Fixes#65
New RPC command that atomically aborts the current turn and starts
a new one with the given message, avoiding the race condition of
separate abort + wait + prompt calls.
Fix session.abort() not clearing promptInFlight flag due to
microtask ordering (waitForIdle resolves before promptWithMessage
finally block), which left isStreaming true and blocked subsequent
prompts.
- Added `sanitizeText` function to pi-natives that strips ANSI escape sequences, removes control characters and lone surrogates, and normalizes line endings.
- Moved `sanitizeText` function from `@oh-my-pi/pi-utils` to `@oh-my-pi/pi-natives` for better code organization and native performance.
- Added line length clamping (4000 characters) to bash and Python execution output to prevent excessively long lines.
- Replaced internal `#normalizeOutput` methods with `sanitizeText` utility function in bash and Python execution components.
- Fixed bash interactive tool to gracefully handle malformed output chunks by normalizing them with `sanitizeText`.
- Simplified documentation by removing WASM terminology from package descriptions and comments.
- Added autonomous memory extraction and consolidation system with two-phase pipeline for extracting durable knowledge and consolidating into reusable skills.
- Added /memory slash command with subcommands (view, clear, reset, enqueue, rebuild) for inspecting and managing memory maintenance.
- Added configurable memory settings including concurrency limits, lease timeouts, token budgets, and rollout age constraints.
- Added memory injection payload that includes learned context in system prompts with operational rules for reading and using memory artifacts.
- Improved system prompt building to support memory guidance injection and enhanced error handling in resolvePromptInput function for multiline input.
- 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.
can1357