fixes#560
When the CLI input has provider/id format (e.g. zai/glm-5), the exact
match now checks decomposed provider+id first (provider=zai, id=glm-5)
before falling back to flat model.id string match. This prevents
vercel-ai-gateway's 'zai/glm-5' model from winning over the zai
provider's 'glm-5' model due to Array.find catalog ordering.
Keeps getAll() rather than switching to getAvailable() to preserve
the --api-key ephemeral flow, where auth is injected after resolution.
- Added task model role configuration enabling dedicated subtask execution with independent model selection.
- Changed default agent model from 'default' to 'pi/task' for independent subtask model configuration.
- Added single-pattern inheritance fallback allowing pi/task agents to inherit session model when unconfigured.
- Refactored model resolution logic into resolveAgentModelPatterns() function with structured fallback handling.
- Added resolveConfiguredModelPatterns() and helper functions for improved model pattern resolution.
- 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.
- 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).
parseModelString now extracts valid thinking level suffixes (e.g.,
"anthropic/claude-opus-4-6:high") instead of treating them as part of
the model ID. This enables per-role thinking levels in config:
modelRoles:
slow: anthropic/claude-opus-4-6:high
default: anthropic/claude-opus-4-6:low
smol: google/gemini-3-flash:medium
The thinking level is applied at startup, in SDK fallback resolution,
and during Ctrl+P role cycling. The original config string is preserved
on role cycle so the suffix round-trips correctly.
- 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.
- Extracted model priority configuration from TypeScript constants to external priority.json file.
- Updated agent prompts (reviewer, explore, plan) to reference new model tier aliases (pi/slow, pi/smol, pi/plan).
- Removed hardcoded SMOL_MODEL_PRIORITY and SLOW_MODEL_PRIORITY constants from model-resolver.ts.
- Improved prompt formatting with consistent newlines and whitespace in agent configuration files.
- Updated SMOL_MODEL_PRIORITY to include additional model variants (gpt-5.3-spark, cerebras/zai-glm-4.7, haiku-4-5, haiku-4.5) for improved fast model discovery.
- Updated SLOW_MODEL_PRIORITY to include additional model variants (gpt-5.3-codex, gpt-5.3, gpt-5.1-codex, gpt-5.1, opus-4.6, opus-4-6, opus-4.5, opus-4-5, opus-4.1, opus-4-1) for improved comprehensive model discovery.
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.
- Added 'commit' model role for dedicated commit message generation.
- Exported 'resolveModelOverride' function from model-resolver module for public use.
- Refactored model role system to centralize role configuration in MODEL_ROLES registry.
- Extracted model resolution utilities into dedicated model-resolver module for improved code organization.
- Made 'tag' and 'color' properties optional in ModelRoleInfo interface to support roles without visual indicators.
- Enhanced model selector with defensive null/undefined checks for optional role properties.
- 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 model preference matching system with ModelMatchPreferences and ModelPreferenceContext interfaces to enable intelligent model selection based on usage history and provider preferences.
- Implemented buildPreferenceContext and pickPreferredModel functions to rank and select models based on usage order, provider history, and deprioritization settings.
- Enhanced parseModelPattern function to accept optional ModelMatchPreferences parameter, enabling model resolution to consider user preferences and usage history.
- Updated model matching logic to prioritize models based on historical usage patterns and provider preferences when multiple candidates match a pattern.
- 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.
- 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.
- 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.
