feat(vis): faithful wire.jsonl rendering + built-in kimi vis command (#788)
Some checks are pending
CI / build (push) Waiting to run
CI / test (push) Waiting to run
CI / lint (push) Waiting to run
CI / typecheck (push) Waiting to run
Nix Build / Check flake.nix workspace sync (push) Waiting to run
Nix Build / nix build .#kimi-code (push) Blocked by required conditions
Release / Publish native release assets (push) Blocked by required conditions
Release / Deploy docs (push) Blocked by required conditions
Release / Native release artifact (push) Blocked by required conditions
Release / Release (push) Waiting to run

* feat: polish vis

* feat: add 'kimi vis' command for session visualization

* fix(vis): drop metadata app_version/resumed removed upstream

#786 stopped recording resume version metadata, so those fields no
longer exist on the metadata wire record. The vis-into-typecheck wiring
caught the stale field reads after merging main; drop them from the
metadata headline.

* fix(vis): drop unnecessary return-await in startVisServer

oxlint typescript-eslint(return-await) flags returning an awaited
promise outside try/catch; return the promise directly.

* fix(vis): green CI — tolerate unbuilt embedded asset + bump nix pnpmDeps hash

- handleVis: wrap the embedded-SPA dynamic import in try/catch. The value
  module is generated at build time (prebuild); in contexts without a build
  (tests run pnpm test, not build) only the .d.ts type stub exists, so the
  runtime import throws. Tolerate it and fall back to filesystem serving.
- flake.nix: update the fetchPnpmDeps hash after adding the vis-web /
  vis-server / vite-plugin-singlefile dependencies.

* refactor(vis): drop redundant alwaysBundle in tsdown config

#775's single-entry build (codeSplitting: false) already bundles
everything not declared in dependencies/peerDependencies. hono /
@hono/node-server (transitive via vis-server) and @moonshot-ai/vis-server
(a devDependency) are all undeclared there, so they bundle by default —
the explicit alwaysBundle was redundant. Verified the emitted main.mjs is
still fully self-contained and 'kimi vis' serves.

* fix(vis): address review — context-token resets, IPv6 url, marker-safe indexing

- contextTokens now mirrors agent-core on lifecycle records: 0 on
  context.clear, tokensAfter on context.apply_compaction (was only
  updated from step.end.usage, leaving a stale live fill after a
  clear/compaction).
- start.ts brackets IPv6 hosts in the returned url (http://[::1]:port/);
  hostForUrl moved to config.ts and shared with the startup banner.
- compaction slice + micro-compaction blanking now index over real
  history entries only, so synthetic undo/clear UI markers no longer
  offset agent-core's compactedCount / cutoff.

* chore: add changeset for kimi vis command

* fix(vis): cross-platform single-file build + history-count micro clamp

- build-vis-asset.mjs sets VIS_SINGLEFILE via the spawn env and runs
  'vite build' directly (cross-platform), instead of the POSIX-inline-env
  'build:single' script that broke on Windows cmd; removed the now-unused
  build:single script. Fixes the win32 build path (the asset generator
  runs in the kimi-code prebuild + native bundle).
- context.undo now clamps the micro-compaction cutoff by history-entry
  count (excluding synthetic undo/clear markers) instead of messages.length,
  mirroring agent-core undo() -> microCompaction.reset(_history.length); a
  surviving marker no longer leaves the cutoff one too high and wrongly
  blanks a later-appended tool result.

* fix(vis): run the single-file build through a shell for Windows pnpm

The win32 native binary is built on Windows runners
(.github/workflows/_native-build.yml), which run this generator. pnpm's
launcher there is pnpm.cmd, which a bare argv exec can't resolve without
a shell. Use execSync with a single command string so the platform shell
(cmd on Windows) resolves the shim; a command string (not an args array)
avoids the args+shell deprecation. Args are static.

* fix(vis): show model-facing tool result content in the context view

agent-core normalizes tool results via toolResultOutputForModel before
they enter history (error -> '<system>ERROR: ...' prefix, empty ->
'<system>Tool output is empty.' sentinel). The projector was using the
raw ev.result.output, so the Context tab's model view showed content the
model never saw for failed/empty tool calls. Replicate that normalization
(the upstream helper is module-private) so the projected tool message
matches what the model received.
This commit is contained in:
Kai 2026-06-16 16:54:14 +08:00 committed by GitHub
parent 7b5b818815
commit efdf8a1b2d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
60 changed files with 3197 additions and 909 deletions

View file

@ -142,7 +142,7 @@
inherit (finalAttrs) pname version src pnpmWorkspaces;
inherit pnpm;
fetcherVersion = 3;
hash = "sha256-XwkLwxWZtOaw1N1GKR9G3z0yhXO/lDB5+O+VKtgxKWo=";
hash = "sha256-X0ujM9le14IecKMOo8tqfU9YYWWkZzSkMbXMOk+r6/8=";
};
nativeBuildInputs = [