0.129.2

• Add support for gpt-5.5 variants
• Restore trust mode on chat resume: chat/open and the /resume slash command now emit config/updated with selectTrust reflecting the resumed chat's persisted trust toggle, so the client indicator stays in sync with the server's auto-approval behavior. #426

0.129.1

• Fix token usage not being reported in the UI for Google/Gemini (and other strict OpenAI-compat providers) by opting into stream_options.include_usage on streaming chat completion requests. #414

0.129.0

• Restore the model used at chat creation when resuming a chat: chat/open and the /resume slash command now emit config/updated to realign the client's selected model to the persisted chat's :model, and the next chat/prompt prefers that stored model over the agent/global default (stale models still fall through gracefully). #417
• Fix rewrite hanging on large files by windowing the inlined file context around the selection instead of sending the whole file; configurable via rewrite.fullFileMaxLines (default 2000). #418
• Prefix plugin-sourced commands and skills with their plugin name (/<plugin-name>:<name>) to avoid collisions across plugins. When the plugin name and the command/skill name are equal the prefix is dropped. #420
• Fix empty .sha256 for macOS aarch64 release artifact by using shasum -a 256 (portable across macOS runners) and enabling pipefail so silent pipe failures don't hide.
• Fix install page eca-desktop download buttons navigating to the wrong artifact (e.g. Linux/x86_64 AppImage leading to eca-mac-arm64.dmg) caused by hidden OS/arch panels still intercepting clicks on top of the visible panel; hidden primary tab and OS panels now use display: none so their nested :checked rules can't re-activate and leak clicks.
• Fix custom tools hanging on Windows by running them through the same platform-aware shell used by shell_command, respecting toolCall.shellCommand. #421

0.128.2

• Sign and notarize macOS native binaries in release CI.
• Disable ask_user tool for subagents since they run non-interactively. #416
• Fix low-quality chat titles on 3rd-message retitle (e.g. literal "Understand" on Opus) by flattening the conversation into a single user message so the title model can't mirror prior planning-mode section headers, adding negative rules/examples to the title prompt, and hardening sanitize-title to skip a bare leading markdown header when more content follows.

0.128.1

• Fix stale system prompt being reused after switching agent mid-chat by scoping the chat-level prompt cache and the OpenAI Responses prompt_cache_key per active agent. #411
• Improve chat title quality on 3rd-message retitle by filtering tool calls, tool results, reasoning and flag entries from the history passed to the title LLM, and by respecting the last compact marker.
• Add the /model command allowing the user to change the model directly from the chat.

0.128.0

• Add eca-desktop as an official client in docs and landing page.
• New chat/list JSON-RPC request returning a summary list of persisted chats for the current workspace (id, title, status, createdAt, updatedAt, model, messageCount). Supports optional limit and sortBy params. Lets clients populate a chat sidebar on startup without requiring the user to resume each chat manually.
• New chat/open JSON-RPC request that replays a persisted chat to the client by emitting chat/cleared (messages), chat/opened and the full sequence of chat/contentReceived notifications without mutating server state. Intended to be paired with chat/list to render a chat the user has not opened in the current client session.
• New mcp/addServer and mcp/removeServer JSON-RPC requests for managing MCP server definitions at runtime. The server persists entries to the owning config file (project .eca/config.json or global), preserving comments and formatting via rewrite-json, and broadcasts a new tool/serverRemoved notification on successful removal. Mirrored over REST via POST /api/v1/mcp and DELETE /api/v1/mcp/:name.
• Extend mcp/updateServer to accept env and headers params, and migrate its persistence off the cheshire round-trip that stripped comments from the user's config.

0.127.1

• Auto allow ask_user tool by default.
• Fix chat titles becoming empty when conversation history contains thinking blocks (Anthropic).
• Add Claude Opus 4.7 support with adaptive thinking, xhigh effort level, and summarized thinking display.

0.127.0

• Support ask_user tool allowing LLM to ask the user questions with optional selectable options. #338
• Remove redundant system message when background jobs finish or are killed.
• Fix Anthropic chat titles being empty or garbled on 3rd message retitle by passing conversation history as past-messages.

0.126.0

• Chat titles now re-generate at the 3rd user message using full conversation context for more accurate titles.
• Sanitize chat titles to remove newlines, control characters, and markdown header prefixes.
• Trust mode can now be toggled via chat/update and applies immediately to the next tool call without requiring a new prompt.

0.125.0

• Refresh auth token before each LLM API call, preventing stale tokens during long-running tool calls.
• Add background shell command support via background parameter on shell_command tool and new bg_job tool for managing long-running processes. #77
• Add disabled field to MCP server notifications, allowing clients to distinguish between stopped and config-disabled servers. #403