- Added support for provider-level OpenAI compatibility configuration enabling reasoning effort mapping and streaming usage fallback across models.
- Added 10 new AI models (DeepSeek V3.2, Llama 3.1 405B, Mistral Large 3, Pixtral Large, and others) with updated pricing and context windows.
- Fixed autocomplete to preserve ./ prefix in relative file/directory path completions and paste marker expansion to handle regex tokens literally.
- Changed system prompt date format to ISO 8601 and tool download timeout from 15s to 120s for improved cross-platform compatibility.
- Refactored OpenAI completions provider to extract token parsing logic and support choice-level usage fallback with improved message serialization.
* add llama.cpp as local provider
* use responses api instead of messages
* use api-keys correctly for llama.cpp provider
---------
Co-authored-by: Can Bölük <can1357@users.noreply.github.com>
- Added Tavily web search provider with API key authentication and credential discovery from environment or database.
- Integrated Tavily as highest-priority search provider in fallback chain with structured response mapping and error handling.
- Added Tavily OAuth login flow in CLI and auth-storage with manual API key input and validation.
- Added comprehensive test suite for Tavily provider covering registration, response mapping, error handling, and credential validation.
Fixes#313
* feat: Add LM Studio as a supported model provider with OpenAI-compatible API fetching and discovery.
Add LM Studio as a supported AI provider with optional API key, environment variables, and discovery.
* feat: Add rustup as a dev dependency.
* fix: Refine LM Studio API key handling to conditionally send authorization headers during model discovery based on whether the key is a default local token or a custom key, and add new tests.
* feat: Enhance OAuth token and account ID resolution for model providers in the model registry.
* rebase for packages/ai/CHANGELOG.md
* feat: improve implicit model discovery to independently auto-detect Ollama and LM Studio, and refine LM Studio base URL handling.
---------
Co-authored-by: Can Bölük <can1357@users.noreply.github.com>
PendingAction.apply() and reject() now receive the reason string that was
passed to resolve(). This lets custom tools surface the agent's rationale
in their apply/discard output or use it for logging.
- PendingAction interface: apply(reason) and reject?(reason)
- CustomToolPendingAction: same signatures, reject is optional
- CustomToolLoader: threads reject through when building PendingAction
- AstEditTool: accepts _reason (unused, reserved for future tracing)
- resolve.test: covers reason forwarding on apply and reject paths,
and verifies reject return value replaces the default discard message
- docs/resolve-tool-runtime.md: updated interface table, built-in
producer description, usage example, and developer guidance
- 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 per-task skill pinning feature; subagents now inherit session skill set instead of per-task selection.
- Removed `preloadedSkills` option from `CreateAgentSessionOptions` interface and related system prompt plumbing.
- Removed `skills` field from Task schema; task execution now passes available session skills directly to subagents.
- Simplified task execution pipeline by removing skill resolution logic and preloaded skills handling from system prompt templates.
- Consolidated @oh-my-pi/pi-utils subpath imports into single package root import across 100+ files.
- Moved tryParseJson utility from local web scrapers module to @oh-my-pi/pi-utils package for centralized JSON parsing.
- Renamed loadSkillsFromDir to scanSkillsFromDir and refactored skill discovery to use fs.promises.readdir instead of glob-based approach.
- Replaced custom parseJSON with tryParseJson across discovery modules for consistent error handling.
- Removed emitCustomToolSessionEvent method and cleanupSshResources function, consolidating shutdown logic into dispose method.
- Updated glob pattern construction to use GlobBuilder with literal_separator(true) for improved path handling.
- Standardized XML tag naming from snake_case to kebab-case across 50+ prompt files for consistency.
- Replaced imperative language with RFC 2119 keywords (MUST/SHOULD/MAY/MUST NOT) throughout system and tool prompts for clarity.
- Removed artifactsDir parameter from Python executor and simplified environment variable handling to use PI_SESSION_FILE only.
- Renamed read_path.md to read-path.md and updated memory guidance with hierarchy rules and conflict resolution workflow.
- Added noEscape option to bash URL expansion and extracted cwd parameter from leading cd commands for improved path handling.
- Exported NO_PAGER_ENV constant from bash-interactive module for centralized environment variable management.
- 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 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.
- 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.
- Moved documentation files from packages/coding-agent/docs/ to root docs/ directory to flatten the documentation structure.
- Updated all internal documentation links to account for the new file locations, adjusting relative paths to maintain correct references across the monorepo.
- Updated README.md and issue template configuration to reference documentation at the new root docs/ location instead of packages/coding-agent/docs/.
- Migrated models export from TypeScript module to JSON format, changing the public API from importing MODELS from './models.generated' to importing from './models.json' with JSON import assertion.
- Updated @anthropic-ai/sdk dependency from ^0.72.1 to ^0.74.0.
- Simplified model generation script by replacing 49 lines of TypeScript code generation with direct JSON serialization.
- Updated @types/bun devDependency from ^1.3.8 to ^1.3.9 across all packages.
- Removed models.generated.ts exclusion from biome.json linting configuration.
- Migrated authentication storage from JSON-based (auth.json) to database-based (agent.db) format across test files and configuration.
- Simplified auth storage discovery in sdk.ts by removing manual path construction and fallback logic in favor of centralized getAgentDbPath() function.
- Removed dbPath instance property from AuthStorage class as database path is now managed centrally.
- Updated environment variable precedence documentation to reflect agent.db instead of auth.json as the lowest priority source.
- Removed OAuth provider section header comments from multiple test files for cleaner test organization.
- Added support for JSON and JSONC configuration file formats without requiring migration to YAML.
- 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.
- Added comprehensive environment variables documentation including API keys for 11 new LLM providers (Groq, Cerebras, xAI, OpenRouter, Mistral, z.ai, MiniMax, OpenCode, Cursor, Vercel AI Gateway, Perplexity) and cloud provider configuration.
- Expanded CLI help text with detailed API keys section documenting all supported LLM providers, cloud providers, search services, and model override configuration variables.
- Fixed redundant fallback check in porting guide example by removing duplicate `Bun.env.HOME` reference.
- 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.
- 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).
- Updated documentation to reflect product name change from 'pi' to 'omp' throughout guides and API references.
- Restructured extension and hook documentation to clarify discovery mechanisms, loading behavior, and configuration across multiple config systems (.omp, .pi, .claude, .codex).
- Updated SDK API documentation with new method signatures: discoverHooks() -> discoverExtensions(), SessionManager methods now async, settings format changed to YAML.
- Expanded session architecture documentation with new entry types (TtsrInjectionEntry, SessionInitEntry), updated field names (fromHook -> fromExtension), and clarified session file format versioning.
- Simplified session-tree-plan.md from detailed implementation checklist to architecture summary, removing completed tasks and rollout details.
- Added support for cross-compilation via CARGO_BUILD_TARGET environment variable, enabling builds for non-native targets like ARM64 Linux.
- Added support for overriding platform and architecture detection via TARGET_PLATFORM and TARGET_ARCH environment variables.
- Modified native build script to search for release artifacts in target-specific directories when cross-compiling.
- Updated CI workflow to use cross-compilation toolchain for ARM64 Linux builds instead of native ARM64 runners.
- Created comprehensive porting guide documenting how to port hot paths to pi-natives with anatomy, checklist, and troubleshooting sections.
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
- 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.
- 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.
- Added automatic retry logic for OpenAI Codex responses with configurable delay and max retries.
- Added input event handlers for extensions to intercept user input and argument completion support.
- Added Emacs-style kill ring for text deletion operations with Alt+D and Ctrl+Y keybindings.
- Added configurable editor padding via editorPaddingX theme option and setMaxHeight() method.
- Fixed tool prefix handling in Claude provider to use case-insensitive comparison.
- Enhanced Kitty keyboard protocol support for better key detection and shifted symbol handling.
Provider additions:
- Added Amazon Bedrock provider with bedrock-converse-stream API
- Added MiniMax provider with OpenAI-compatible API
- Added EU cross-region inference model variants for Bedrock
Provider fixes:
- Fixed Gemini CLI retries with header parsing and empty stream retry logic
- Fixed Bedrock tool call transforms via transformMessages
- Fixed z.ai thinking/reasoning params
- Fixed OpenRouter+Anthropic cache control
- Fixed OpenAI responses timeout and service tier options
- Fixed tool call ID normalization for cross-provider switches
- Fixed thought signature validation for Google providers
- Fixed prompt cache key using session ID
TUI improvements:
- Added OverlayOptions API with CSS-like positioning (SizeValue, percentages)
- Added OverlayHandle for programmatic visibility control
- Added visible callback for responsive overlays
- Added pad parameter to truncateToWidth
- Added pageUp/pageDown key support
- Fixed numbered list items showing 1. when code blocks break continuity
- Fixed overlay width overflow crash with complex ANSI sequences
- Fixed light theme colors for WCAG AA compliance
Coding agent fixes:
- Fixed /new command to create new session file
- Fixed session selector to stay open when folder has no sessions
- Added session header emission in JSON print mode
- Added queued message hint with theme.tree.hook
- Exported highlightCode and getLanguageFromPath for extensions
Also renamed transorm-messages.ts to transform-messages.ts (typo fix)
can1357