- Refactored environment variable access to use dedicated getter/setter functions in test suite.
- Simplified configuration constants by removing ompConfig dependency and using hardcoded values.
- Introduced module-level caching for agent directory and subdirectory paths to improve performance.
- Added setAgentDir() function to manage agent directory updates and cache invalidation.
- Reorganized dirs.ts with logical section headers and consolidated subdirectory functions using helper utilities.
- Updated directory accessor functions to accept optional agentDir parameter for flexibility.
- Refactored filesystem scan cache integration to use pre-scanned entries from fs_cache module instead of manual directory walking in grep.rs.
- Extracted filesystem scan cache invalidation helpers into dedicated fs-cache-invalidation.ts module with three functions: invalidateFsScanAfterWrite, invalidateFsScanAfterDelete, and invalidateFsScanAfterRename.
- Centralized file mention discovery profile configuration into getMentionCandidateDiscoveryProfile() function for improved maintainability.
- Added comprehensive documentation of filesystem-scan cache architecture contract including cache key specifications, TTL policies, and invalidation patterns.
- Updated CHANGELOG.md to document filesystem scan cache invalidation helpers and named discovery profile for file mention candidates.
- Extracted directory path utilities from multiple packages into a centralized '@oh-my-pi/pi-utils/dirs' module.
- Moved 30+ path helper functions (getAgentDir, getConfigRootDir, getPluginsDir, getMCPConfigPath, etc.) from scattered locations into a single shared utility module.
- Consolidated APP_NAME, CONFIG_DIR_NAME, and VERSION constants into the centralized dirs module for reuse across packages.
- Updated 70+ import statements across packages/ai, packages/coding-agent, packages/stats, and packages/tui to use the new centralized module.
- Removed local path construction logic and replaced with utility function calls for improved maintainability and consistency.
- Deleted packages/coding-agent/src/extensibility/plugins/paths.ts as its functions were moved to the centralized dirs module.
- Extracted shared fs_cache.rs from glob.rs: global TTL policy (env-configurable),
cache-aware scanning, empty-result fast recheck (~200ms), explicit invalidation API
- Moved fuzzyFind from grep.rs into dedicated fd.rs module using shared scan cache
- Removed per-call cacheTtlMs from GlobOptions and FuzzyFindOptions (global policy)
- Added invalidateFsScanCache NAPI export, wired into write/edit tools after mutations
- Cleaned up TS callers: file-mentions, autocomplete, tests no longer own cache semantics
- Enhanced bash execution environment with comprehensive non-interactive defaults for pagers, editors, package managers, and tooling to prevent command blocking and interactive prompts.
- Updated interactive bash terminal UI label from 'InteractiveTerm' to 'Console' for improved clarity.
- Added comprehensive `models.yml` provider integration guide documenting custom model registration, provider overrides, API adapters, merge behavior, and practical integration patterns for Ollama, vLLM, LM Studio, and proxy endpoints.
- Updated README to reference new `models.yml` documentation and clarified that `models.json` is still supported for legacy configurations.
- Updated CHANGELOG to document the new models.yml guide and configuration format migration.
When store is false, OpenAI does not persist response items server-side.
Previously, encrypted_content was only requested when reasoningEffort or
reasoningSummary options were explicitly set. Without it, reasoning items
are serialized with just their ID, causing 404 errors on subsequent turns
when OpenAI cannot resolve the ID reference.
Fixes#41
- P1: Use root.scope instead of hardcoded 'user' level in claude-plugins provider
- P2: Iterate all registry entries per plugin ID, not just first one
- P3: Add home parameter to discoverAgents() for test isolation
- P4: Add test coverage for claude-plugins discovery (12 tests)
- P5: Cache listClaudePluginRoots results to avoid repeated parsing
Addresses issues found in adversarial review of PR #49
Add discovery provider that loads skills, commands, hooks, tools, and
agents from ~/.claude/plugins/cache/ based on installed_plugins.json.
- Add parseClaudePluginsRegistry() and listClaudePluginRoots() helpers
- Create claude-plugins.ts provider with priority 70 (below claude.ts)
- Register provider for skills, slash-commands, hooks, and tools
- Integrate plugin agents into task/discovery.ts
Closes#48
- Changed default edit mode from `patch` to `hashline` for more precise code modifications.
- Changed `readHashLines` setting default from false to true to enable hash line reading by default.
- Added three new benchmark run reports for GPT-5.3 Codex model with different edit variants (hashline, patch, replace).
- Recorded performance metrics across 60 tasks per variant with success rates ranging from 80-83.3%.
- 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
The Z.AI login flow was hardcoded to validate API keys using the 'glm-5'
model. However, the Z.AI Coding Plan, which this login is for, currently
provides access to 'glm-4.7', with 'glm-5' being rolled out incrementally.
This caused login to fail for users who did not yet have 'glm-5' access.
This change updates the validation model to 'glm-4.7' to match the model
available in the Coding Plan.
Fixes#39
Detects known Bun.stringWidth mishandling of OSC sequences at startup
and exits with a clear upgrade message instead of crashing in the TUI
render path.
Fixes#31
- Fixed incorrect path resolution for CLI module by using Bun.fileURLToPath() to convert import.meta.resolve() result to a proper file path.
- Reordered constant declarations to ensure TMP_DIR is initialized before CLI_PATH which depends on it.
- Updated scripts/repro-stuck.ts to use consistent CLI path resolution with Bun.fileURLToPath().
- Replaced jsdom with linkedom for HTML parsing in browser tool, improving performance and reducing memory footprint.
- Removed @types/jsdom from devDependencies as jsdom is no longer used.
- Simplified HTML document parsing by removing VirtualConsole error handling and direct window cleanup.
- Removed unused yaml dependency from swarm-extension package.
- Updated pi-coding-agent peer dependency constraint from wildcard to ^11.
- Removed pi-coding-agent from devDependencies, keeping only in peerDependencies.
- Exported renderPromptTemplate function from config/prompt-templates module for programmatic prompt template rendering.
- Exported computeLineHash function from patch/hashline module for external patch utility access.
- Added ./cli export path in package.json for direct CLI module access.
Adds a standalone extension that orchestrates multi-agent workflows
defined in YAML. Supports pipeline (iterative), parallel (fan-in/out),
sequential, and arbitrary DAG execution patterns.
Each agent runs as a full oh-my-pi subagent with complete tool access.
Agents communicate through the shared workspace filesystem. The
orchestrator handles lifecycle, dependency ordering, and state tracking.
Key components:
- YAML schema parser with validation and cycle detection
- DAG builder with topological sort into execution waves
- Pipeline controller with iteration loop and wave execution
- Filesystem state persistence for monitoring and resumability
- Standalone runner (run-pipeline.ts) for long-running unattended work
- TUI integration via /swarm command
Designed for any task type: research, coding, data processing, content
creation, analysis workflows, or any multi-step objective that benefits
from specialized agents working in coordination.
- Updated Claude Code version header to 2.1.39 and runtime version to v24.13.1.
- Increased request timeout from 60s to 600s for improved reliability on slower connections.
- Reordered Accept-Encoding header values to prioritize Brotli compression.
- Updated OAuth endpoints to use platform.claude.com and expanded scopes to include user:sessions:claude_code and user:mcp_servers.
- Removed deprecated beta features claude-code-20250219 and fine-grained-tool-streaming-2025-05-14.
- Improved Bun binary detection and update process with version verification and environment variable checking.
can1357