- Updated OpenAI context-promotion linking to handle `-spark` variants and base `gpt-5.5` models.
- Adjusted model generation data so OpenAI-like models now promote first to `gpt-5.5` and then to `gpt-5.4` where configured.
- Updated unit tests to assert context-promotion targets for both spark and `gpt-5.5` model variants.
Copilot's /models endpoint exposes token limits under capabilities.limits.
max_prompt_tokens is the actual prompt capacity (what OMP calls contextWindow),
while max_context_window_tokens is the total window (prompt + output budget).
Using the latter inflates contextWindow, which breaks compaction thresholds,
overflow detection, and context promotion.
Three changes:
1. mapModel reference selection: always prefer the Copilot-specific bundled
reference over the global cross-provider reference. Copilot imposes its
own limits that are strictly lower than native provider limits.
2. mapModel contextWindow chain: remove max_context_window_tokens from the
fallback. New chain: context_length -> max_prompt_tokens -> reference.
3. generate-models: stop overwriting contextWindow/maxTokens in
applyGlobalModelsDevFallback. These are provider-specific and should not
be replaced with cross-provider models.dev global references.
Also fixes bundled values: github-copilot/gpt-5.4 (400k -> 272k) and
github-copilot/gpt-5.2 (264k -> 128k) to match live API max_prompt_tokens.
Refs: #225, #226
- Fixed thinking configuration format by replacing `levels` array with `minLevel`/`maxLevel` properties across 100+ model definitions.
- Corrected GPT-5.4 mini/nano context window from 400000 to 272000 tokens for accurate token limit reporting.
- Normalized GPT-5.4 variant priority handling to use parsed variant instead of raw model IDs for consistent behavior.
- Added "mini" variant support to OpenAI model parsing regex and updated thinking mode configuration for Claude models.
- Fixed test robustness by replacing exact string matching with numeric range comparison to handle BSD seq notation on macOS.
- Corrected model generation script execution order to apply policy overrides before promotion target linking.
- 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.
- Updated dev dependencies including biome, TypeScript native preview, and lint-staged to latest versions.
- Updated AI package dependencies for Anthropic SDK, AWS Bedrock, and Zod with relaxed version constraints.
- Updated models.json with new model entries, removed premiumMultiplier fields from GitHub Copilot models, and corrected maxTokens and cost values for various providers.
- Added appearance and projfs export paths to natives package and updated peer dependency version for swarm-extension.
- 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.
- Added configurable model refresh strategies (online, online-if-uncached) to control model discovery behavior.
- Implemented global model.dev fallback resolution with context window and token prioritization for improved model attribute consistency.
- Incremented model cache schema version to support improved global model fallback resolution.
- Enhanced model generation script with dedicated functions for building model reference maps and applying fallback attributes.
- Extracted provider descriptor helper functions (descriptor, catalog, catalogDescriptor, simpleModelsDevDescriptor, openAiCompletionsDescriptor, anthropicMessagesDescriptor) to reduce boilerplate across 47+ provider definitions.
- Refactored model generation script to simplify OAuth credential lifecycle by moving storage cleanup to finally block and parallelizing special discovery sources with Promise.all().
- Consolidated provider validation logic in model registry into reusable validateProviderConfiguration() function with context-aware validation modes.
- Reorganized models.json structure to place contextWindow and maxTokens before compat field for consistency across all provider entries.
- Unified provider descriptors into single source of truth in descriptors.ts module for runtime and catalog discovery.
- Consolidated model generation script to use declarative CatalogProviderDescriptor interface, reducing code duplication.
- Refactored model registry and selector to use descriptor pattern with priority-based sorting and version extraction.
- Added priority field to Model interface enabling provider-assigned model prioritization in discovery and selection.
- Added support for Synthetic model provider in web search command and improved model sorting by priority and version.
- Extracted model post-processing policies into dedicated model-policies module for improved testability and maintainability.
- Refactored model generation script to use declarative provider descriptors instead of 620+ lines of inline provider-specific logic.
- Consolidated provider model manager initialization to use descriptor-driven iteration, eliminating 29+ individual conditional blocks.
- Removed static bundled models for Ollama and vLLM from models.json to rely on dynamic discovery instead.
- 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.
- Added Claude Sonnet 4.6 and Claude Sonnet 4.6 Thinking models to Antigravity provider.
- Added GLM-5 Free model via OpenCode provider.
- Added GLM-4.7-FlashX model via ZAI provider.
- Added MiniMax-M2.5-highspeed model across four providers (minimax-code, minimax-code-cn, minimax, minimax-cn).
- Added Claude Sonnet 4.6 model to OpenRouter and Vercel AI Gateway providers.
- Updated pricing and token limits for deepseek-v3, mistral-large-2411, and Qwen models across OpenRouter and Together AI providers.
- Expanded EU cross-region inference variant support to all Claude models on Bedrock (previously limited to Haiku, Sonnet, and Opus 4.5).
- Updated context window handling for Sonnet 4.6 models to enforce 200K limit across all providers.
- 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 DeepSeek-V3.2 model support via Amazon Bedrock.
- Added GLM-5 model support via OpenCode.
- Added MiniMax M2.5 model support via OpenCode.
- Updated GLM models to use anthropic-messages API instead of openai-completions and changed base URL from https://api.z.ai/api/coding/paas/v4 to https://api.z.ai/api/anthropic.
- Removed compat field with supportsDeveloperRole and thinkingFormat properties from GLM models.
- Updated pricing and context window specifications for multiple models including Mistral, Moonshot, and Qwen variants.
- Added sorting of models by ID across multiple model fetch functions (OpenRouter, AI Gateway, Kimi Code, and dev data) using localeCompare for consistent ordering.
- 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 GPT-5.3 Codex Spark model with 128K context window and extended reasoning capabilities.
- Added MiniMax M2.5 and M2.5 Lightning models via OpenAI-compatible API (minimax-code and minimax-code-cn providers).
- Added MiniMax M2.5 and M2.5 Lightning models via Anthropic API (minimax and minimax-cn providers).
- Added Llama 3.1 8B model via Cerebras API.
- Added MiniMax M2.5 model via OpenRouter and Vercel AI Gateway.
- Added Qwen3 VL 32B Instruct multimodal model via OpenRouter.
- show help instead of crashing on `omp setup` with no args
- show runtime-discovered MCP servers in `/mcp list`
- remove deprecated Anthropic model entries from models.json
- sort models by recency in model selector
- Sorted Antigravity models alphabetically in generated models.json and generation script.
- Updated Antigravity model configurations with corrected model IDs, names, and parameters.
- Fixed qwen/qwen3-max-thinking maxTokens from 4096 to 202752 to match context window.
Add support for MiniMax Coding Plan with OpenAI-compatible API:
- New providers: minimax-code (international) and minimax-code-cn (China)
- Environment variables: MINIMAX_CODE_API_KEY and MINIMAX_CODE_CN_API_KEY
- Uses thinkingFormat: 'zai' for reasoning compatibility
- Models: MiniMax-M2, MiniMax-M2.1, MiniMax-M2.1-lightning
- Base URLs: https://api.minimax.io/v1 (intl), https://api.minimaxi.com/v1 (CN)
The Coding Plan is a subscription-based service separate from regular MiniMax API.
- 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.
- Added support for Kimi K2, K2 Turbo Preview, and K2.5 models with reasoning capabilities.
- Fixed Claude Opus 4.6 context window to 200K across all providers (was incorrectly set to 1M).
- Fixed Claude Sonnet 4 context window to 200K across multiple providers (was incorrectly set to 1M).
- Improved Kimi Code model fetching to merge fallback models not returned by the API endpoint.
- Added dynamic Antigravity model fetching from API when credentials are available, with hardcoded fallback models for offline use.
- Updated Antigravity models to use free tier pricing (0 cost) across all models.
- Extracted Antigravity model loading into separate functions (fetchAntigravityModels, getAntigravityFallbackModels, getAntigravityToken) for better maintainability.
- Added support for fetching recommended models from Antigravity API response and filtering internal models.
- Added Claude Opus 4.6 Thinking model for Antigravity provider.
- Added Gemini 2.5 Flash, Gemini 2.5 Flash Thinking, and Gemini 2.5 Pro models for Antigravity provider.
- Added Pony Alpha model via OpenRouter.
- Updated Claude Opus 4.6 context window from 200,000 to 1,000,000 tokens across Bedrock regions.
- Updated Claude Opus 4.6 cache pricing and Antigravity model pricing to free tier across multiple models.
- Fixed Claude Opus 4.6 model ID format by removing version suffix (:0) in Bedrock configurations.
- Extracted stream parsing utilities into reusable functions in pi-utils package (readLines, readJsonl, parseJsonlLenient, readSseJson).
- Replaced manual buffer management with ConcatSink class for efficient stream handling across multiple modules.
- Simplified SSE stream parsing in google-gemini-cli provider by using readSseJson utility instead of manual reader setup.
- Refactored MCP stdio transport to use readLines utility for cleaner line-based stream processing.
- Updated RPC client and mode to use readJsonl utility, removing duplicate JSONL parsing logic.
- Optimized buffer allocations by using allocUnsafe where data is immediately populated and reusing empty buffer instances.
- 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 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.
- Added Kimi Code provider integration with OAuth device authorization flow and token management.
- Added four new Kimi Code models (kimi-for-coding, kimi-k2, kimi-k2-turbo-preview, kimi-k2.5) with reasoning support and 262K context window.
- Added kimiUsageProvider for fetching and caching Kimi Code API usage quota information.
- Added kimi-code login command to CLI for OAuth authentication with Kimi Code.
- Updated openai-completions provider to support Kimi-specific headers and cached token formats.
- Updated MiniMax-M2 model pricing: input 1.2->0.6, output 1.2->3, cacheRead 0.6->0.1.
- 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.
- Updated model data generation script to reference 'zai-coding-plan' instead of 'zai' for model configuration.
- Regenerated models configuration with updated pricing data and floating-point precision corrections.
- Added GLM-4.7-Flash model to generated models list.
- 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 Vercel AI Gateway model fetching with 100+ model configurations.
- Updated Amazon Bedrock models with new Claude 4.5 EU variants.
- Added GPT-5.2-codex model across OpenAI, GitHub Copilot, and OpenCode providers.
- Changed MiniMax models to use anthropic-messages API format.
- Added thinkingFormat support to ZAI provider models.
- Improved LSP diagnostic output by stripping clippy URLs and noise.
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)
- Added conversation state caching to persist context across multiple Cursor API requests in the same session.
- Added cursor-log.py script for filtering and displaying Cursor debug logs with follow mode, verbose mode, and delta coalescing support.
- Changed Cursor debug logging to use structured JSONL format with automatic MCP argument decoding.
- Moved proto-extractor.py from provider-specific directory to centralized scripts directory.
- Added model generation script to automatically fetch and update AI model definitions from models.dev and OpenRouter APIs.
- Implemented support for multiple providers including Anthropic, Google, OpenAI, Groq, Cerebras, xAI, Mistral, OpenCode, GitHub Copilot, OpenRouter, Google Vertex, and Cursor.
- Updated generated file comment to reference bun instead of npm for running the script.
- Co-located tool renderers with their respective tool implementations across 14 tool modules.
- Added render-utils module with shared formatting helpers for diagnostics, diffs, paths, and metadata.
- Removed ~800 lines of inline renderer implementations from centralized renderers.ts file.
- Added Google Vertex AI provider with 11 Gemini model configurations.
- Added OpenAI Codex provider with 13 GPT-5 model configurations.
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.
can1357