mirror of https://github.com/MoonshotAI/kimi-code.git synced 2026-08-01 04:26:01 +00:00

History

Kai 3086e47039 Some checks are pending CI / test-windows (push) Waiting to run Details CI / lint (push) Waiting to run Details CI / test (1) (push) Waiting to run Details CI / test (2) (push) Waiting to run Details CI / test (3) (push) Waiting to run Details CI / test (4) (push) Waiting to run Details CI / test (5) (push) Waiting to run Details CI / test-pi-tui (push) Waiting to run Details CI / build (push) Waiting to run Details CI / typecheck (push) Waiting to run Details Nix Build / Check flake.nix workspace sync (push) Waiting to run Details Nix Build / nix build .#kimi-code (push) Blocked by required conditions Details Release / Release (push) Waiting to run Details Release / Deploy docs (push) Blocked by required conditions Details Release / Native release artifact (push) Blocked by required conditions Details Release / Publish native release assets (push) Blocked by required conditions Details fix: unify YOLO and Auto permission mode descriptions across surfaces (#1867 ) * fix(tui): correct YOLO and Auto permission mode descriptions * fix: unify YOLO and Auto permission mode descriptions across CLI, ACP, web, and docs * docs: correct YOLO and Auto mode descriptions in the interaction guide * fix: correct YOLO mode notices in session replay and vscode extension * feat(vscode): rename /afk command to /auto, keeping afk as hidden alias Also correct the stale 'afk' mode reference in the built-in MCP config skill guidance of both agent engines. * fix(vscode): forward engine approval requests instead of blanket-approving them The extension-level approval handler auto-approved every request when legacy yolo/afk was on, silently swallowing the sensitive-file, plan-review, and ask-rule prompts the engine yolo mode still sends. Forward every request to the user and let the engine permission mode do the auto-approving, matching TUI and web behavior.		2026-07-18 02:09:31 +08:00
..
src	fix: unify YOLO and Auto permission mode descriptions across surfaces (#1867 )	2026-07-18 02:09:31 +08:00
test	fix: scope Anthropic effort fallback profile to non-Kimi providers (#1765 )	2026-07-16 17:30:20 +08:00
CHANGELOG.md	ci: release packages (#1378 )	2026-07-06 23:18:32 +08:00
package.json	chore: drop #/ import array fallbacks and custom resolution plugins (#1594 )	2026-07-13 16:37:35 +08:00
README.md	feat(acp): implement ACP server with session lifecycle, tool streaming, and IDE integration (#368 )	2026-06-03 21:11:30 +08:00
tsconfig.json	feat(acp): implement ACP server with session lifecycle, tool streaming, and IDE integration (#368 )	2026-06-03 21:11:30 +08:00
tsdown.config.ts	feat(acp): implement ACP server with session lifecycle, tool streaming, and IDE integration (#368 )	2026-06-03 21:11:30 +08:00
vitest.config.ts	chore: use raw query imports for prompt sources (#682 )	2026-06-12 11:47:44 +08:00

README.md

@moonshot-ai/acp-adapter

Agent Client Protocol adapter for kimi-code. Exposes the kimi-code agent over the Agent Client Protocol so that ACP-compatible clients (editors, IDEs, custom front-ends) can drive a kimi-code session over stdio.

Part of the Kimi Code monorepo.

Minimum usage

import { createKimiHarness } from '@moonshot-ai/kimi-code-sdk';
import { runAcpServer } from '@moonshot-ai/acp-adapter';

const harness = await createKimiHarness();
await runAcpServer(harness);

runAcpServer reads JSON-RPC from process.stdin, writes to process.stdout, and resolves when the client closes the connection. SIGINT and SIGTERM trigger a graceful drain that calls harness.close() before the process exits.

See docs/zh/reference/kimi-acp.md for the full capability matrix (which Agent methods are wired, which extensions are stubbed, image / MCP support) and docs/zh/guides/ides.md for Zed and JetBrains setup.

License

MIT