- Added streaming text preview during agent specification generation with real-time text delta updates.
- Added `onRequestRender` callback to agent dashboard for async UI re-renders on state changes.
- Improved system prompt preview rendering with text wrapping and line count indicators.
- Enhanced agent creation flow to display generation status hint and reordered spec review before input form.
- Added AI-powered agent creation flow with architect model for generating custom agent specifications from natural language requests.
- Added keyboard shortcuts (N for new agent, R for regenerate) and scope selection (project/user) for agent creation workflow.
- Added model suggestions UI and success/error notices to agent dashboard for improved creation feedback.
- Added system prompts for agent-creation-architect and agent-creation-user roles with 6-step methodology and JSON schema validation.
- Added file persistence with YAML frontmatter for storing agent specifications at project or user scope.
Handle plain Enter/Return in HookEditorComponent as newline input so the editor no longer triggers the submit-reset path when no onSubmit handler is wired.
Ctrl+Enter submit behavior remains unchanged.
Fixes#100
Puppeteer uses cosmiconfig to search for its configuration at import time. cosmiconfig walks up from CWD parsing every package.json it finds. If any package.json in the search path has invalid JSON, the strict parse-json parser throws synchronously
during module evaluation, surfacing as an uncaught exception that crashes the entire process.
- 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.
- Implemented API client for the Synthetic web search provider.
- Configured Synthetic as a selectable option for web searches.
- Integrated Synthetic into the automatic provider fallback chain.
Fixes#102
- Set Authorization: Bearer header in buildAnthropicHeaders when using OAuth
(raw fetch path was sending no credentials)
- Use plain web_search tool name instead of prefixed web_search_20250305
(Anthropic API rejects the prefixed name)
- Remove dead applySearchToolPrefix function and unused import
Fixes#102
- 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.
- 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.
- 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.
Wire the existing TUI autocompleteMaxVisible plumbing into the
declarative settings system so it appears in /settings under the
Input tab. Users can pick from 3/5/7/10/15/20 items; the TUI editor
clamps to 3-20 regardless.
- Add autocompleteMaxVisible to SETTINGS_SCHEMA (number, default 5)
- Add OPTION_PROVIDERS entry for the submenu dropdown
- Handle runtime side-effect in selector-controller
- Set initial value from settings on editor construction
- Add tests for default, runtime, persistence, and config loading
- Added `--no-rules` CLI flag to coding-agent to disable rules discovery and loading.
- Added `rules` option to CreateAgentSessionOptions to allow custom rules configuration.
- Added `sessionDir` option to RpcClientOptions and implemented Symbol.dispose() for resource cleanup.
- Removed tarball-based task loading; migrated to directory-based fixtures with required inputDir and expectedDir properties.
- Refactored runner to use RpcClient resource management with `using` statement and simplified fixture handling.
- Consolidated type definitions and removed tarball.ts module in favor of streamlined task interface.
- Improved cache authority logic for dynamic model fetching.
- Added model filtering for OpenAI-compatible non-response endpoints.
- Updated `ModelRegistry` auth sentinel from `""` to `kNoAuth` (`"N/A"`).
- Made API response parsing more robust across multiple providers.
- 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 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 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.
- 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 OpenCode discovery provider that loads configuration from ~/.config/opencode/ and .opencode/ directories.
- Added support for loading MCP servers from opencode.json mcp key with stdio and HTTP transport types.
- Added support for loading skills from ~/.config/opencode/skills/ and .opencode/skills/ directories.
- Added support for loading slash commands from ~/.config/opencode/commands/ and .opencode/commands/ directories with frontmatter parsing.
- Added support for loading extension modules (plugins) from ~/.config/opencode/plugins/ and .opencode/plugins/ directories.
- Added support for loading context files (AGENTS.md) and settings from OpenCode configuration.
- 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.
- Removed the `getSystemInfo` API and `SystemInfo` type from package exports by deleting the `system-info` Rust/TS modules, dropping the `system_info` crate module, and removing top-level `system-info` re-exports.
- Updated environment information generation to no longer rely on native system-info data, sourcing distro and kernel values from built-in `os` APIs instead and removing the `Disk` field from produced environment entries.
- Adjusted native binding validation to stop requiring `getSystemInfo`, reflecting the new binding contract after API removal.
- Added startup-debug instrumentation behind `PI_DEBUG_STARTUP` that traces native addon loading, extraction, AVX2 detection, and environment info/GPU caching steps for diagnostics.
- Added support for braced escape sequences (\p{...}, \P{...}, \x{...}, \u{...}) in regex pattern sanitization to properly preserve unicode property escapes and hex escapes.
- Improved LSP client message writing by simplifying header encoding and refactoring abort signal handling with the untilAborted utility.
- Enhanced native addon installation script to dynamically fetch release tags from GitHub API instead of using hardcoded versions.
- Relaxed native addon validation to only error when no addons are found rather than when any are missing, improving flexibility in addon availability.
- 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 abort signal support to LSP file operations (ensureFileOpen, refreshFile) enabling cancellation of long-running file operations.
- Added abort signal propagation through LSP request handlers (definition, references, hover, symbols, rename) with $/cancelRequest notification support.
- Added shouldBypassAutocompleteOnEscape callback to custom editor allowing parent components to override escape key handling behavior.
- Changed escape key handling in custom editor to respect bypass callback, enabling global escape handling during active operations.
- Fixed LSP operations to properly handle abort signals and throw ToolAbortError when operations are cancelled, with input controller bypassing autocomplete during streaming/loading states.
- 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.
can1357