Commit Graph
13 Commits
Author SHA1 Message Date
f1425c8d5a feat(ai): add MiMo Code (mimo) agent support (#3500)
* feat(ai): add MiMo Code (mimo) agent support scaffolding

Registry/wiring only: discovery entry, managed-agent metadata, model presets, icon, i18n and Settings UI for Xiaomi's MiMo Code CLI (an OpenCode fork). The SDK driver is intentionally not wired yet - it depends on the pending @mimo-ai/sdk parity probe, so DRIVER_REGISTRY keeps a TODO and run-turn/list-models reject the mimo backend until then.

* feat(ai): add MiMo Code (mimo) agent support

Adds Xiaomi's MiMo Code CLI as a managed agent backend, mirroring the existing
OpenCode integration (discovery, managed-agent metadata, model presets, icon,
i18n, Settings UI) and adding the SDK driver that was left as a TODO in the
scaffolding commit.

Driver notes:
- New electron/bridges/aiBridge/sdk/mimoDriver.cjs reuses the pure translation
  helpers exported by opencodeDriver.cjs (config/prompt building, event
  translation, model mapping) because MiMo Code is an OpenCode fork and speaks
  the same wire protocol.
- It does NOT use @mimo-ai/sdk's createOpencode(). On 0.1.15 that helper spawns
  a binary named "opencode", waits for an "opencode server listening" banner,
  and passes config via OPENCODE_CONFIG_CONTENT; the mimo CLI prints
  "mimocode server listening on <url>", reads MIMOCODE_CONFIG_CONTENT, and ships
  as "mimo"/"mimo.exe". So createOpencode() can only ever time out. The driver
  runs "mimo serve" itself, parses the readiness URL, and attaches the SDK's
  createOpencodeClient({ baseUrl }).
- Binary resolution honours binPath, MIMOCODE_BIN and MIMOCODE_BIN_PATH, then
  falls back to PATH via resolveCliFromPath (the npm shim is mimo.cmd on
  Windows, which Node cannot spawn directly).
- @mimo-ai/sdk ^0.1.15 added as a dependency.

Verified on Windows against mimo 0.1.15 + @mimo-ai/sdk 0.1.15:
- "mimo serve --port" boots and reports its URL; driver parses it.
- SDK symbols used all exist: createOpencodeClient, client.config.providers(),
  client.global.event() (SSE stream), client.session.create/abort/promptAsync.
- Live provider catalog reads 2 providers (xiaomi, mimo); MIMO_MODEL_PRESETS
  updated to the real lower-case provider-prefixed ids and its TODO removed.
- Server process is killed on close (taskkill tree kill), no orphan processes.

Not yet verified at runtime:
- A full end-to-end turn (no prompt was sent, so no tokens were spent): text /
  reasoning / tool-part streaming and abort handling are untested against a
  live model.
- MIMOCODE_CONFIG_CONTENT accepting the OpenCode config schema (permission,
  mcp, model, share, autoupdate) end-to-end; only that the env var exists in
  the binary has been confirmed.
- Whether the loopback server needs MIMOCODE_SERVER_PASSWORD when the API
  client attaches.
- The placeholder public/ai/agents/mimo.svg still needs an official asset.
- Multi-turn resume (resumeSessionId) and MCP injection against the live CLI.

* feat(ai): inject MIMOCODE_BIN for discovered MiMo Code agents

Mirror the OpenCode OPENCODE_BIN handling so a discovered or re-detected
mimo binary path reaches the driver, and cover it with the same assertion
shape as the opencode managed-agent env test.

* fix(ai): use MiMo branding in the mimo driver

* test(ai): cover the mimo driver

Add a unit test file for the MiMo Code driver, matching the existing
opencode driver test in shape, runner (node:test via node --test) and
`.test.cjs` extension. It is the last driver in the registry without
one.

Coverage:
- spawn/launch: `mimo serve --hostname/--port` argv, binary resolution
  (explicit binPath / MIMOCODE_BIN / MIMOCODE_BIN_PATH), pass-through
  env and MIMOCODE_CONFIG_CONTENT; `child_process.spawn` is stubbed, so
  no real `mimo` process is ever started.
- readiness: parsing of `mimocode server listening on <url>` from
  stdout (including split chunks) and stderr, the OpenCode spelling,
  and the MIMO_SERVE_TIMEOUT_MS timeout path (asserts the rejection and
  that the child is killed).
- abort/cleanup: stopMimoProcess kill/idempotency/swallow, the Windows
  taskkill tree kill, server.close() teardown, and abort mid-turn with
  a throwing close().
- branding: OpenCode -> MiMo Code for the busy/idle/status, failed and
  tool-failure fallback strings, with tool output and non-brand
  technical errors left verbatim.
- happy path: session create -> streamed event translation -> done,
  plus listMimoModels catalog mapping and the empty/aborted paths.

* fix(ai): filter MiMo events by session and stop the server behind the npm shim

Address review on #3500:

- The global SSE stream carries every session on the server, and
  runMimoTurn translated all of them, so another session's text could leak
  into the reply and its session.idle could end the turn early. Skip events
  whose session id is not ours, reusing the OpenCode driver's
  getOpenCodeSessionIdFromEvent (now exported). Covered by a test with
  interleaved sessions.
- On macOS/Linux the official @mimo-ai/cli `mimo` is a Node shim that runs
  the native binary through spawnSync, so killing the shim left the server
  listening. `mimo serve` is now spawned detached on POSIX and
  stopMimoProcess signals its whole process group (SIGTERM, then SIGKILL
  after a grace period). Windows keeps taskkill /T.

Verified against the real @mimo-ai/cli@0.1.15 npm shim: on Linux (WSL
Ubuntu 22.04) the listener is the native .mimocode child; before this change
it was still listening 3s after close(), now the port is released within 1s
and no mimo process remains. On Windows the .cmd shim path also releases the
port within 1s.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* fix: harden MiMo CLI integration before merge

* fix: wait for MiMo events and handle setup cancellation

* fix: finish MiMo stream handling and scope skill access

* fix: preflight MiMo skill paths before one server startup

* fix: scope MiMo skill reads to trusted roots

* fix: allow MiMo skills from ancestor project roots

* fix: honor MiMo observer and confirm command permissions

* fix: clear MiMo approval when its service exits

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: bincxz <16399091+binaricat@users.noreply.github.com>
2026-09-29 14:51:22 +08:00
bincxz b2b79443af fix(ai): stop first-type hitch after expanding the chat panel
Opening the AI panel and typing a few characters hit a main-thread stall.
Streamdown warmup, panel remount, draft-store fan-out, and expand-time
IPC all raced the first keystrokes. import() cannot be cancelled, so the
heavy renderer must not start while the composer is busy.

Keep the composer mounted on hidden retained panels, ignore composer-text
store notifications, debounce draft flushes, and defer discovery/skills/
model IPC until the composer is idle. History stays plaintext until
Streamdown is warm, then hydrates a few rows at a time.
2026-08-14 23:06:21 +08:00
bincxz c1d88b2c8b fix(ai): persist Codex CLI version for custom-path installs
Store probed --version on ExternalAgentConfig from settings resolve-cli
and discovery enable, and prefer that when gating GPT-5.6 so custom
paths not on PATH still unlock Sol/Terra/Luna when compatible.
2026-07-14 12:06:41 +08:00
陈大猫 fd3de5c6c1 [codex] Lazy load OpenCode model catalogs
Lazy load OpenCode model catalogs for OpenCode.
2026-06-26 16:37:08 +08:00
陈大猫 324253f23a [codex] Optimize terminal side panel performance
Optimize terminal side panel performance, keep process status labels visible, and improve heavy panel loading behavior.
2026-06-12 00:47:17 +08:00
陈大猫 f5c4271a07 Polish AI settings integrations UI (#1409) 2026-06-11 17:07:11 +08:00
陈大猫 3408bba303 [codex] Add Cursor SDK agent support (#1399)
* feat(ai): add Cursor SDK agent support

* fix(ai): harden Cursor SDK support

* fix(ai): address Cursor SDK review findings

* fix(ai): refresh Cursor environment handling

* fix(ai): refresh Cursor discovery scans

* fix(ai): enable Cursor recheck without path

* Use official Cursor agent icon

* Clarify Cursor SDK setup requirements

* Split Cursor SDK setup status

* Simplify Cursor settings copy

* Improve Cursor API key error

* Add safe Cursor auth diagnostics

* Disable Cursor local sandbox by default

* Show Cursor MCP tool names in tool cards

* Add spacing inside tool call groups
2026-06-11 16:43:34 +08:00
陈大猫andCursor 36e5779d94 perf(terminal): reduce terminal tab-switch and layout jank (#1321)
* perf(terminal): smooth layout drags and faster tab switching

Defer xterm refit during split, sidebar, and host-tree drags while keeping pane containers in sync with live layout measurements. Refactor TerminalLayer into focused sections with TabBridge/memo optimizations and add the terminal host tree sidebar.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(terminal): keep side panels alive and guard session attach races

Prevent terminal boot unmount from leaking backend sessions, keep SFTP/scripts/theme/AI state when switching side tabs, and defer heavy SFTP UI mount so first entry stays responsive.

Co-authored-by: Cursor <cursoragent@cursor.com>

* perf(terminal): reduce tab switch jank

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-09 03:35:03 +08:00
陈大猫 3fc56df111 refactor(ai): migrate agent backends from ACP to official SDKs (claude/codex/copilot) (#1229) 2026-06-04 17:11:02 +08:00
陈大猫 7bd5d6465a fix claude system cli detection (#1033) 2026-05-21 00:11:51 +08:00
bincxzandClaude Opus 4.6 bcd44f0177 refactor: remove Claude Agent SDK integration in favor of ACP
All external agents now use ACP protocol exclusively. The Claude Agent
SDK flow was fully implemented but never wired into the UI.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-15 22:53:37 +08:00
bincxzandClaude Opus 4.6 8949394756 feat: add Claude Agent SDK streaming and Codex OAuth integration
Integrate Claude Agent SDK for direct streaming chat, add Codex login/logout
flow with OAuth support in settings, improve AI chat panel UI and agent
discovery, and update build config for new dependencies.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-14 21:27:41 +08:00
bincxzandClaude Opus 4.6 7f3214e088 feat: integrate external AI agents via ACP protocol
- Add auto-discovery of CLI agents (Claude Code, Codex, Gemini) from system PATH
- Integrate ACP (Agent Client Protocol) for real-time streaming with codex-acp
- Bundle @zed-industries/codex-acp binary for reliable agent spawning
- Add ThinkingBlock component with shimmer animation and auto-collapse
- Refactor chat UI: no avatars, bordered user bubbles, plain assistant text
- Support {prompt} placeholder in agent args for flexible invocation
- Add persistent ACP sessions with proper cleanup on app exit
- Detect auth errors and show actionable messages to users
- Fallback to raw process spawn for agents without ACP support

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-14 17:21:28 +08:00