optimclaw/CHANGELOG.md

Changelog

All notable changes to this project will be documented in this file.

The format is based on Keep a Changelog, and this project adheres to Semantic Versioning.

[Unreleased]

0.8.0 - 2026-02-20

Added

• extension registry with metadata catalog and onboarding integration (#238)
• (models) add GPT-5.3 Codex, full GPT-5.x family, Claude 4.x series, o4-mini (#197)
• wire memory hygiene into the heartbeat loop (#195)

Fixed

• persist WASM channel workspace writes across callbacks (#264)
• consolidate per-module ENV_MUTEX into crate-wide test lock (#246)
• remove auto-proceed fake user message injection from agent loop (#255)
• onboarding errors reset flow and remote server auth (#185, #186) (#248)
• parallelize tool call execution via JoinSet (#219) (#252)
• prevent pipe deadlock in shell command execution (#140)
• persist turns after approval and add agent-level tests (#250)

Other

• add automated PR labeling system (#253)
• update CLAUDE.md for recently merged features (#183)

0.7.0 - 2026-02-19

Added

• extend lifecycle hooks with declarative bundles (#176)
• support per-request model override in /v1/chat/completions (#103)

Fixed

• harden openai-compatible provider, approval replay, and embeddings defaults (#237)
• Network Security Findings (#201)

Added

• Refactored OpenAI-compatible chat completion routing to use the rig adapter and RetryProvider composition for custom base URL usage.
• Added Ollama embeddings provider support (EMBEDDING_PROVIDER=ollama, OLLAMA_BASE_URL) in workspace embeddings.
• Added migration V9__flexible_embedding_dimension.sql for flexible embedding vector dimensions.

Changed

• Changed default sandbox image to ironclaw-worker:latest in config/settings/sandbox defaults.
• Improved tool-message sanitization and provider compatibility handling across NEAR AI, rig adapter, and shared LLM provider code.

Fixed

• Fixed approval-input aliases (a, /approve, /always, /deny, etc.) in submission parsing.
• Fixed multi-tool approval resume flow by preserving and replaying deferred tool calls so all prior tool_use IDs receive matching tool_result messages.
• Fixed REPL quit/exit handling to route shutdown through the agent loop for graceful termination.

0.6.0 - 2026-02-19

Added

• add issue triage skill (#200)
• add PR triage dashboard skill (#196)
• add OpenRouter usage examples (#189)
• add Tinfoil private inference provider (#62)
• shell env scrubbing and command injection detection (#164)
• Add PR review tools, job monitor, and channel injection for E2E sandbox workflows (#57)
• Secure prompt-based skills system (Phases 1-4) (#51)
• Add benchmarking harness with spot suite (#10)
• 10 infrastructure improvements from zeroclaw (#126)

Fixed

• (rig) prevent OpenAI Responses API panic on tool call IDs (#182)
• (docs) correct settings storage path in README (#194)
• OpenAI tool calling — schema normalization, missing types, and Responses API panic (#132)
• (security) prevent path traversal bypass in WASM HTTP allowlist (#137)
• persist OpenAI-compatible provider and respect embeddings disable (#177)
• remove .expect() calls in FailoverProvider::try_providers (#156)
• sentinel value collision in FailoverProvider cooldown (#125) (#154)
• skills module audit cleanup (#173)

Other

• Fix division by zero panic in ValueEstimator::is_profitable (#139)
• audit feature parity matrix against codebase and recent commits (#202)
• architecture improvements for contributor velocity (#198)
• fix rustfmt formatting from PR #137
• add .env.example examples for Ollama and OpenAI-compatible (#110)

0.5.0 - 2026-02-17

Added

• add cooldown management to FailoverProvider (#114)

0.4.0 - 2026-02-17

Added

• move per-invocation approval check into Tool trait (#119)
• add polished boot screen on CLI startup (#118)
• Add lifecycle hooks system with 6 interception points (#18)

Other

• remove accidentally committed .sidecar and .todos directories (#123)

0.3.0 - 2026-02-17

Added

• direct api key and cheap model (#116)

0.2.0 - 2026-02-16

Added

• mark Ollama + OpenAI-compatible as implemented (#102)
• multi-provider inference + libSQL onboarding selection (#92)
• add multi-provider LLM failover with retry backoff (#28)
• add libSQL/Turso embedded database backend (#47)
• Move debug log truncation from agent loop to REPL channel (#65)

Fixed

• shell destructive-command check bypassed by Value::Object arguments (#72)
• propagate real tool_call_id instead of hardcoded placeholder (#73)
• Fix wasm tool schemas and runtime (#42)
• flatten tool messages for NEAR AI cloud-api compatibility (#41)
• security hardening across all layers (#35)

Other

• Explicitly enable cargo-dist caching for binary artifacts building
• Skip building binary artifacts on every PR
• add module specification rules to CLAUDE.md
• add setup/onboarding specification (src/setup/README.md)
• deduplicate tool code and remove dead stubs (#98)
• Reformat architecture diagram in README (#64)
• Add review discipline guidelines to CLAUDE.md (#68)
• Bump MSRV to 1.92, add GCP deployment files (#40)
• Add OpenAI-compatible HTTP API (/v1/chat/completions, /v1/models) (#31)

0.1.3 - 2026-02-12

Other

• Enabled builds caching during CI/CD
• Disabled npm publishing as the name is already taken

0.1.2 - 2026-02-12

Other

• Added Installation instructions for the pre-built binaries
• Disabled Windows ARM64 builds as auto-updater [provided by cargo-dist] does not support this platform yet and it is not a common platform for us to support

0.1.1 - 2026-02-12

Other

• Renamed the secrets in release-plz.yml to match the configuration
• Make sure that the binaries release CD it kicking in after release-plz

0.1.0 - 2026-02-12

Added

• Add multi-provider LLM support via rig-core adapter (#36)
• Sandbox jobs (#4)
• Add Google Suite & Telegram WASM tools (#9)
• Improve CLI (#5)

Fixed

• resolve runtime panic in Linux keychain integration (#32)

Other

• Skip release-plz on forks
• Upgraded release-plz CD pipeline
• Added CI/CD and release pipelines (#45)
• DM pairing + Telegram channel improvements (#17)
• Fixes build, adds missing sse event and correct command (#11)
• Codex/feature parity pr hook (#6)
• Add WebSocket gateway and control plane (#8)
• select bundled Telegram channel and auto-install (#3)
• Adding skills for reusable work
• Fix MCP tool calls, approval loop, shutdown, and improve web UI
• Add auth mode, fix MCP token handling, and parallelize startup loading
• Merge remote-tracking branch 'origin/main' into ui
• Adding web UI
• Rename setup CLI command to onboard for compatibility
• Add in-chat extension discovery, auth, and activation system
• Add Telegram typing indicator via WIT on-status callback
• Add proactivity features: memory CLI, session pruning, self-repair notifications, slash commands, status diagnostics, context warnings
• Add hosted MCP server support with OAuth 2.1 and token refresh
• Add interactive setup wizard and persistent settings
• Rebrand to IronClaw with security-first mission
• Fix build_software tool stuck in planning mode loop
• Enable sandbox by default
• Fix Telegram Markdown formatting and clarify tool/memory distinctions
• Simplify Telegram channel config with host-injected tunnel/webhook settings
• Apply Telegram channel learnings to WhatsApp implementation
• Merge remote-tracking branch 'origin/main'
• Docker file for sandbox
• Replace hardcoded intent patterns with job tools
• Fix router test to match intentional job creation patterns
• Add Docker execution sandbox for secure shell command isolation
• Move setup wizard credentials to database storage
• Add interactive setup wizard for first-run configuration
• Add Telegram Bot API channel as WASM module
• Add OpenClaw feature parity tracking matrix
• Add Chat Completions API support and expand REPL debugging
• Implementing channels to be handled in wasm
• Support non interactive mode and model selection
• Implement tool approval, fix tool definition refresh, and wire embeddings
• Tool use
• Wiring more
• Add heartbeat integration, planning phase, and auto-repair
• Login flow
• Extend support for session management
• Adding builder capability
• Load tools at launch
• Fix multiline message rendering in TUI
• Parse NEAR AI alternative response format with output field
• Handle NEAR AI plain text responses
• Disable mouse capture to allow text selection in TUI
• Add verbose logging to debug empty NEAR AI responses
• Improve NEAR AI response parsing for varying response formats
• Show status/thinking messages in chat window, debug empty responses
• Add timeout and logging to NEAR AI provider
• Add status updates to show agent thinking/processing state
• Add CLI subcommands for WASM tool management
• Fix TUI shutdown: send /shutdown message and handle in agent loop
• Remove SimpleCliChannel, add Ctrl+D twice quit, redirect logs to TUI
• Fix TuiChannel integration and enable in main.rs
• Integrate Codex patterns: task scheduler, TUI, sessions, compaction
• Adding LICENSE
• Add README with IronClaw branding
• Add WASM sandbox secure API extension
• Wire database Store into agent loop
• Implementing WASM runtime
• Add workspace integration tests
• Compact memory_tree output format
• Replace memory_list with memory_tree tool
• Simplify workspace to path-based storage, remove legacy code
• Add NEAR AI chat-api as default LLM provider
• Add CLAUDE.md project documentation
• Add workspace and memory system (OpenClaw-inspired)
• Initial implementation of the agent framework