mirror of
https://github.com/MoonshotAI/kimi-code.git
synced 2026-07-10 01:39:25 +00:00
* feat(agent-core): announce image compression and keep originals readable Every image ingestion point (ReadMediaFile, MCP tool results, clipboard paste, REST upload/inline base64, ACP) now places a <system> caption next to a compressed image stating the original vs. delivered dimensions, byte size, and format, so downsampling is never silent to the model. Originals stay readable: file uploads point at the stored blob, and in-memory images are persisted into the session's media-originals dir (content-addressed, size-capped, removed with the session; temp-dir fallback when no session is known). ReadMediaFile gains region (crop in original-image pixel coordinates, delivered at full fidelity) and full_resolution (skip downscaling, with an explicit error over the per-image byte limit), so the model can zoom into fine detail instead of silently degrading on large images. * fix(agent-core): exempt compression captions from the MCP text budget The caption announcing an image's compression was inserted before the shared 100K text budget was applied, so a chatty MCP result (page text + screenshot) consumed the budget first and the caption was evicted — or sliced mid-string into an unclosed <system> fragment — while the downsampled image survived, silently reintroducing the exact degradation the caption exists to report, and orphaning the persisted original. Split the size-limit pass in two and reorder the pipeline: the text budget now runs on the tool's own text BEFORE compression inserts captions (exempt by construction), and the per-part binary cap still runs after compression so compressible screenshots are kept. * fix(agent-core): harden crop error reporting and document readback semantics - cropImageForModel rejects non-finite region coordinates with a clean message instead of surfacing the codec's internal validation dump - the full_resolution and cropped-region over-budget errors now include exact byte counts alongside the rounded sizes, so a file a hair over budget no longer reads "is 3.8 MB, over the 3.8 MB limit" - read-media.md notes that re-reading a file without region or full_resolution reproduces the same downsampled image |
||
|---|---|---|
| .. | ||
| src | ||
| test | ||
| CHANGELOG.md | ||
| package.json | ||
| README.md | ||
| tsconfig.json | ||
| tsdown.config.ts | ||
| vitest.config.ts | ||
@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