* feat(env): migrate kimi-cli model request params and auto-update toggle
Migrate still-relevant environment variables from kimi-cli:
- KIMI_MODEL_TEMPERATURE / KIMI_MODEL_TOP_P: sampling params applied
globally to any kimi provider (not tied to KIMI_MODEL_NAME).
- KIMI_MODEL_THINKING_KEEP: Moonshot preserved-thinking passthrough
(thinking.keep), injected only while Thinking is on.
- KIMI_CODE_NO_AUTO_UPDATE (legacy alias KIMI_CLI_NO_AUTO_UPDATE):
fully disables the update preflight.
Wires env -> provider in Agent.get llm() via applyKimiEnvGenerationParams,
reusing kosong's existing GenerationKwargs / thinking.keep support.
KIMI_MODEL_MAX_TOKENS is intentionally untouched: it already flows through
the completion-budget path.
* fix(env): apply Kimi sampling params to compaction requests too
Sink KIMI_MODEL_TEMPERATURE / KIMI_MODEL_TOP_P into ConfigState.provider so
every request built from config.provider — main loop and full-history
compaction alike — carries them, matching kimi-cli where these live on the
shared create_llm provider. thinking.keep stays in Agent.llm because it
depends on the runtime thinking state (compaction runs thinking-off and
correctly skips it).
Splits applyKimiEnvGenerationParams into applyKimiEnvSamplingParams (applied
at provider construction) and applyKimiEnvThinkingKeep (applied in Agent.llm).
Addresses PR review feedback about compaction requests bypassing the wrapped
provider.
Add the published release date to every version heading on the
user-facing changelog pages (English half-width, Chinese full-width),
covering 0.2.0 through 0.9.0. Dates come from each version's published
release tag. Also update the sync-changelog skill so future syncs carry
the date convention forward.
* ci: deploy docs only on release to keep docs in sync with published versions
Previously docs were deployed on every push to main, which meant
unreleased features could appear in the public documentation.
This changes the trigger to release:published so that docs only
update when a new version is actually shipped, plus manual dispatch
for emergencies.
* ci: deploy docs from release workflow
---------
Co-authored-by: root <root@localhost.localdomain>
Co-authored-by: qer <wbxl2000@outlook.com>
Inline, model-invocable skill to inspect and safely edit kimi-code's own config.toml and tui.toml (copy to a candidate, Edit, validate with kimi doctor, timestamped backup, then overwrite). Also documents tui.toml on the config files page (en + zh).
* feat(cli): add doctor command for config validation
* fix(cli): format doctor validation errors
* fix(cli): validate doctor config through SDK RPC
* chore(changeset): simplify doctor release note
* fix(nix): expose ripgrep and fd to wrapped kimi
- make wrapper available to the Nix build
- wrap kimi binary with ripgrep and fd on PATH
- include rg and fd in the dev shell packages
* chore(nix): add changeset for ripgrep and fd
This commit scaffolds the @moonshot-ai/acp-adapter package and introduces
the full ACP (Agent Communication Protocol) server implementation for
Kimi Code CLI, including:
- Scaffold @moonshot-ai/acp-adapter workspace package with build skeleton
- `kimi acp` CLI subcommand and stdout-safe logging
- ACP version negotiation and AgentSideConnection wrapper
- Auth gate for session creation
- Session lifecycle: new, list, load with history replay
- Prompt content conversion (text, image, embedded resources, resource links)
- Assistant streaming with thinking support and end-turn handling
- Tool call streaming (started, delta, progress) with result conversion (text / diff)
- Approval handling with diff/text display blocks mapped to ACP options
- Kaos read/write interface (AcpKaos) for unsaved buffer access
- Session mode (yolo/auto) and model management
- Config options builder with thinking toggle
- MCP server forwarding from ACP to harness
- Agent plan updates and available commands updates
- AskUserQuestion bridged to session/request_permission
- Plan review options surfaced through requestPermission
- Error mapping, ext_method stubs, and graceful shutdown
- IDE integration guide (Zed + JetBrains)
- End-to-end tests against ACP TS SDK client
* feat(cli): unify TUI dialog interaction and visuals
Align every list dialog and selector to a single spec: shared selection
pointer and current-item marker, single-border header with a (type to
search) title suffix, consistent search line, and a uniform keyboard-hint
vocabulary. Replace ad-hoc exit wording (close/back/exit/dismiss) with
cancel, hardcoded pointers with the shared constant, and ▲▼ with ↑↓.
Also add fuzzy search to /provider, restyle the /model provider tabs, and
require a token with multi-field navigation in the custom-registry import.
Introduce the write-tui skill (carrying the DESIGN.md spec) and refresh
the apps/kimi-code development guide to match the current TUI architecture.
* feat(cli): drop arrow-key navigation in the plugins selector
The plugins overview and its marketplace/MCP sub-views used Left/Right to
enter and exit details. Remove that hierarchy navigation: Enter opens a
detail, Esc returns, and the arrow keys no longer jump between levels.
Update the sub-view hints from `←/Esc cancel` to `Esc cancel`.
* feat(cli): install marketplace plugins on Enter only
The marketplace install action also fired on Space, which collides with
the Space-toggle convention used elsewhere. Bind install to Enter only and
update the hint to `Enter install/update`.
* feat(cli): reword the plugin inline change hint
The inline badge shown on a changed plugin row read `pending /new`, which
was cryptic. Reword it to `require run /new to apply`. Also switch the
marketplace-install message-flow tests to Enter, matching the Enter-only
install binding.
* fix(cli): stop the editor flash when toggling a plugin
Each plugin picker's onSelect unconditionally restored the editor before
the handler re-mounted the refreshed picker, so an in-place action like
Space-toggling a plugin flashed: picker → editor → picker. Drop the
pre-restore from the overview/marketplace/MCP onSelect callbacks and let
each handler branch mount its next view; the two branches that close to the
editor (show-list, info) restore it themselves.
* feat(cli): drop /provider search and delete with D
Remove the fuzzy filter from the provider manager: no query state, search
line, or type-to-search title suffix, and Esc closes directly. With no
type-to-search to clash with, bind delete to the D key (matching /plugins)
instead of Del/Ctrl+D. Update the write-tui spec to specify D as the
delete shortcut.
* fix(cli): default thinking-capable models to thinking on
The model selector seeded a single thinking draft from the global thinking
flag, so highlighting a thinking-capable model showed Off whenever the
active model had thinking off (e.g. a non-thinking current model). Compute
the draft per model instead: the active model keeps its live state, any
other thinking-capable model defaults to On, and a ←/→ toggle is remembered
per model.
Run the external editor through Node's platform shell instead of spawning
/bin/sh directly. Quote the appended temp file path per platform so Ctrl+G
works on Windows while preserving shell-style editor commands.
Co-authored-by: liruifengv <liruifeng1024@gmail.com>
* feat(agent-core): add dead-end detection for repeated tool calls
- inject stronger dead-end reminder at streak 10 and force-stop turn at streak 15
- emit `tool_call_repeat` telemetry events for streak >= 2
- pass telemetry client from TurnFlow to ToolCallDeduplicator
- add comprehensive tests for dead-end stop and telemetry behavior
* fix(agent-core): tune tool-dedup thresholds and preserve isError state
- Lower repeat-reminder thresholds to 3, 5, 8 and force-stop to 12
- Force-stop no longer overrides successful tool results to isError
- Move stopTurn field into ExecutableToolSuccessResult for explicit loop-control without requiring isError
