Skip to content

Latest commit

 

History

History
155 lines (102 loc) · 9.77 KB

File metadata and controls

155 lines (102 loc) · 9.77 KB

Changelog

0.5.0

Minor Changes

  • 7cf01b9 Thanks @coopbri! - Record AI token usage to Aether for billing after each LLM completion

  • a94576a Thanks @coopbri! - Add @file mention expansion to inline file contents as a fenced code block in the prompt

  • 7cf01b9 Thanks @coopbri! - Add omni auth login and omni auth logout commands for cloud Synapse authentication

  • a94576a Thanks @coopbri! - Add /compact slash command to summarize old messages and free context window space

  • a94576a Thanks @coopbri! - Add /cost slash command to display per-session token usage and estimated cost

  • 7cf01b9 Thanks @coopbri! - Add knowledge pack support with Manifold resolver, local caching, and tag-based chunk selection for persona system prompts

  • 11cd883 Thanks @coopbri! - Add MCP STDIO reconnect-and-retry on transport failure, and animated braille spinner for tool calls in the TUI (inline block + status bar)

  • 9ece8de Thanks @coopbri! - Add multi_search tool for parallel multi-source web search and TUI display for tool call activity

  • 65d45be Thanks @coopbri! - Add Synapse client integration, agent-core provider registry, and Beacon browser tool

  • a94576a Thanks @coopbri! - Add /undo slash command to revert last agent file changes using shadow git snapshots

Patch Changes

  • 1ddde64 Thanks @coopbri! - Fix hardcoded Sonnet pricing with model-aware cost lookup, add auth token extraction fallback chain, and add missing tests

0.4.0

Minor Changes

  • 7923c3c Thanks @coopbri! - Add Kimi 2.5 (Moonshot AI) provider support

    • Add kimi provider with OpenAI-compatible API at api.moonshot.cn
    • Add models: kimi-k2.5, moonshot-v1-128k, moonshot-v1-32k
    • Add prefix detection for kimi-* and moonshot-* model names
    • Set MOONSHOT_API_KEY environment variable to use

0.3.0

Minor Changes

  • 0783ebd Thanks @coopbri! - Add unified LLM provider, session sharing, skill system, and LSP integration

    • Add unified LLM provider via llm crate supporting Anthropic, OpenAI, Google Gemini, Groq, and Mistral
    • Add session sharing with URL tokens, secrets, and optional TTL expiration
    • Add CLI commands: omni session share and omni session unshare
    • Add skill system for loading reusable instructions from SKILL.md files
    • Discover skills from .omni/skill/, .opencode/skill/, and .claude/skills/ directories
    • Add skill tool for agents to load specialized instructions on demand
    • Add LSP integration with support for 13 language servers
    • Add lsp tool for code intelligence (hover, definition, references, symbols)
    • Add agent loop detection to prevent infinite tool call loops
    • Add secret masking for API keys, tokens, and credentials in tool output
    • Add MCP server integration to discover and execute external tools
    • Add plugin auto-discovery and integration into agent tool registry
  • 80a07eb Thanks @coopbri! - Add GitHub integration tools

    • Add github_pr tool for creating pull requests
    • Add github_issue tool for creating, viewing, listing, and closing issues
    • Add github_pr_review tool for viewing PRs, diffs, checks, and adding comments
    • All tools use the gh CLI and respect plan mode restrictions
  • 46bedb3 Thanks @coopbri! - Add persistent memory system for cross-session context

    • Add memory_add tool for storing facts about user preferences, project patterns, and corrections
    • Add memory_search tool for finding relevant memories by query or category
    • Add memory_delete tool for removing outdated memories
    • Memories persist across sessions and can be injected into system prompts
    • Support for pinned memories that are always included in context
  • 08b5595 Thanks @coopbri! - Add sandboxed execution tool

    • Add sandbox_exec tool for running untrusted code safely
    • Uses Docker containers with resource limits when available
    • Falls back to timeout + restricted env when Docker not present
    • Supports Python, Node, Ruby, and shell execution
    • Configurable timeout, network access, and workdir mounting
  • 761b54a Thanks @coopbri! - Add session continuity flags for resuming conversations

    • Add --continue / -c flag to resume most recent session
    • Add --session / -s flag to resume specific session by ID or slug
    • Works with both tui and agent commands
    • Session list now shows slugs for easier CLI use
    • Fail fast with clear error for invalid session IDs
  • 6e4f1ac Thanks @coopbri! - Add new agent tools and LLM providers

    • Add apply_patch tool for applying unified diffs to files
    • Add multi_edit tool for editing multiple files in a single operation
    • Add support for Groq, Google Gemini, Mistral, LMStudio, OpenRouter, and Together AI providers

Patch Changes

  • 761b54a Thanks @coopbri! - Wrap command palette selection at top/bottom for better UX

0.2.1

Patch Changes

  • ccaf64f Thanks @coopbri! - Improve terminal compatibility and provider configuration UX

    • Fix key event handling for Termux and other terminals that don't report KeyEventKind correctly
    • Show provider-agnostic messages when no provider is configured
    • Update placeholder text to guide users toward configuration
  • 5820f20 Thanks @coopbri! - Improve TUI experience

    • Fix message cutoff by removing bottom padding and correcting height calculations
    • Show activity status (e.g., "Using Bash...") instead of just "Thinking..."
    • Add vertical and horizontal padding to user messages for better visual separation
    • Lighten user message background color for a "previous message" look
    • Implement smooth line-by-line scrolling for messages
    • Allow typing while agent is responding (can prepare next message)
    • Add rich diff rendering for all tool output (muted green/red for diff-like content)
    • Fix paste behavior: pasted text now inserts without auto-submitting
    • Add Ctrl+Left/Right for word-by-word cursor movement

0.2.0

Minor Changes

  • 04e91f8 Thanks @coopbri! - Add model autocomplete dropdown with automatic provider switching

    • Type /model to see available models with provider info
    • Arrow keys navigate, Tab/Enter to select
    • Automatically switches provider when model requires it (e.g., gpt-4o switches to OpenAI)
  • 7b14e8f Thanks @coopbri! - Add session management to TUI

    • Switch between sessions with Ctrl+S and Enter
    • Create new sessions with 'n' key
    • Delete sessions with 'd' key
    • Session list blocked while streaming

Patch Changes

  • 770af7a Thanks @coopbri! - Fix autoscroll, text wrapping, and model identity

    • Fix autoscroll during streaming responses
    • Fix text wrapping in tool output (was overflowing on long lines)
    • Fix model self-identification when switching models mid-conversation
  • f87c14d Thanks @coopbri! - Make clipboard support optional via clipboard feature flag for Termux/Android compatibility

0.1.0

Minor Changes