Runtime: native Kimi Code CLI alongside Claude (kimi_cli provider, live)

Runtime image now installs Node 22 (nodesource) + both agent CLIs —
@anthropic-ai/claude-code and @moonshot-ai/kimi-code — so the zeroclaw
daemon can spawn `kimi -p` for the new kimi_cli provider on a Kimi
membership, parallel to `claude -p` (claude_cli). Kimi needs Node >=22.19;
the image was on Node 18.

Documents the kimi_cli worker recipe in agent.config.example.toml (the
coding endpoint is User-Agent gated → drive Kimi through its own CLI, not a
raw OpenAI-compat client) and keeps GLM via the registry family.

Deployed & verified on gw-04: coordinator (claude_cli) answers "Anthropic
built me", worker_kimi (kimi_cli) answers "I am Kimi, built by Moonshot AI"
— heterogeneous Claude + Kimi on one runtime, over /ws/chat.

Co-Authored-By: Claude Opus 4.8 <[email protected]>

deploy/clawmates-runtime/Dockerfile

@@ -20,14 +20,15 @@ RUN --mount=type=cache,id=cm-cargo-registry,target=/usr/local/cargo/registry,sha
     && cp target/release/zeroclaw /usr/local/bin/zeroclaw
 
 FROM debian:bookworm-slim
-# ca-certificates for TLS; nodejs+npm to install the Claude Code CLI, which the
+# ca-certificates for TLS; Node 22 (Kimi Code needs >=22.19; Claude Code is fine
-# zeroclaw `claude_cli` model provider spawns (`claude -p`) to drive turns on a
+# on it too) to install BOTH agent CLIs that the subprocess providers spawn:
-# Claude subscription / CLAUDE_CODE_OAUTH_TOKEN — no per-minute API TPM ceiling.
+# `claude -p` (claude_cli, Claude subscription) and `kimi -p` (kimi_cli, Kimi
-RUN apt-get update && apt-get install -y --no-install-recommends \
+# membership) — subscription-backed, no per-minute API TPM ceiling.
-        ca-certificates curl nodejs npm \
+RUN apt-get update && apt-get install -y --no-install-recommends ca-certificates curl gnupg \
-    && npm install -g @anthropic-ai/claude-code \
+    && curl -fsSL https://deb.nodesource.com/setup_22.x | bash - \
+    && apt-get install -y --no-install-recommends nodejs \
+    && npm install -g @anthropic-ai/claude-code @moonshot-ai/kimi-code \
     && npm cache clean --force \
-    && apt-get purge -y npm && apt-get autoremove -y \
     && rm -rf /var/lib/apt/lists/* /root/.npm
 COPY --from=build /usr/local/bin/zeroclaw /usr/local/bin/zeroclaw
 ENV HOME=/zeroclaw-data \

deploy/clawmates-runtime/agent.config.example.toml

@@ -42,23 +42,31 @@ mcp_config = "/zeroclaw-data/clawmates-mcp.json"
 # model_provider = "claude_cli.door"
 # risk_profile = "toolfree"
 
-# --- Extra worker LLMs: Kimi Code and GLM (Zhipu) ---
+# --- Extra worker LLMs: Kimi Code (native CLI) and GLM (Zhipu) ---
-# Run a topology WORKER on another model. Kimi Code is subscription-billed and
+# Run a topology WORKER on another model.
-# OpenAI-compatible at https://api.kimi.com/coding/v1 (model "kimi-for-coding")
+#
-# with a Kimi Code Console API key — use the `custom` provider for it. GLM is a
+# Kimi Code: subscription-billed. Its coding endpoint (api.kimi.com/coding) is
-# first-class ZeroClaw family. Set model + key via env (TOML sub-tables parse
+# coding-AGENT gated (User-Agent enforced) — a raw OpenAI-compat client gets 403,
-# empty); point an agent at the alias; the orchestrator's role→alias map
+# so we drive Kimi through its OWN CLI via the `kimi_cli` provider (mirrors
+# `claude_cli`): it spawns `kimi -p` headless on the Kimi membership, with Kimi's
+# own agent loop + sub-agents. Auth is the CLI's own ~/.kimi-code/config.toml
+# (default_model + [providers."managed:kimi-code"] type="kimi" with the key) or
+# `kimi login` — no key is passed by ZeroClaw. (HOME=/zeroclaw-data, so the file
+# lives at /zeroclaw-data/.kimi-code/config.toml in the runtime volume.)
+# [providers.models.kimi_cli.default]
+# # binary_path = "kimi"   # default; resolved on PATH
+# # yolo = true            # -y: auto-approve tool calls (needed for a door agent
+# #                        #     that acts via Kimi's own MCP client, mcp.json)
+# [agents.worker_kimi]
+# model_provider = "kimi_cli.default"
+# risk_profile = "toolfree"
+#
+# GLM is a first-class ZeroClaw family (OpenAI-compat, separate key). Set model +
+# key via env (TOML sub-tables parse empty); the orchestrator's role→alias map
 # (ZEROCLAW_AGENT_MAP) selects e.g. researcher=worker_kimi, analyst=worker_glm.
-#   ZEROCLAW_providers__models__custom__kimi__model=kimi-for-coding
-#   ZEROCLAW_providers__models__custom__kimi__api_key=<Kimi Code Console key>
 #   ZEROCLAW_providers__models__glm__default__model=glm-4.6
 #   ZEROCLAW_providers__models__glm__default__api_key=<GLM key>
-# [providers.models.custom.kimi]
-# uri = "https://api.kimi.com/coding/v1"
 # [providers.models.glm.default]
-# [agents.worker_kimi]
-# model_provider = "custom.kimi"
-# risk_profile = "toolfree"
 # [agents.worker_glm]
 # model_provider = "glm.default"
 # risk_profile = "toolfree"