feat(kimi): Kimi K3 provider on the official kimi-code CLI (#713)

* feat(kimi): Kimi K3 provider on the official kimi-code CLI (Wave 1)

ModelProvider.KIMI routes through KimiCliProvider driving Moonshot's kimi
CLI on a Kimi subscription (OAuth device-code, no metered key). One-shot
delivery roles only (V1), interactive ban wired in both guard lists.

Auth: one shared RW auth mount; containers symlink credentials/ and
oauth/ (the CLI's cross-process refresh-lock dir) into a container-local
KIMI_CODE_HOME so every container and the host redeem the SAME rotating
refresh chain - live-verified that per-copy chains cross-invalidate after
the reuse-grace window. No orchestrator refresh daemon; an expires_at
preflight exits 78.

Config renderer mirrors the login-managed provider/model blocks
field-for-field (live-captured; the model value is the CLI-side name,
never the raw API id), plus per-role deny rules and the bash-guard as a
PreToolUse hook via a wrapper script (an env key on a hooks entry makes
the CLI silently drop ALL hooks - live-verified). Usage capture sums
wire.jsonl usage.record 4-bucket events; sniff classifies rate-limit/auth
from structured error text only, mapped to the shared 75/78 park
contract. Image installs the CLI latest-at-build (no version pin, by
policy) with the resolved version stamped as provenance, binary split to
/usr/local away from mutable state.

Migrations 090 (enum) + 091 (provider seed); catalog, pricing, routing
mode, and orchestrator park/usage wiring mirror the codex integration.

* feat(kimi): surface sweep + fleet-wide pin drop (Wave 2)

Compose x3 gain the agent-kimi-image service and the orchestrator's
read-write ~/.kimi-code mount + kimi-usage dir; .env.example documents
the Kimi block. Panel mirrors ModelProvider.KIMI and adds the kimi
routing mode (catalog filter, mode button, mix-picker group, badge) with
tests; provider routes gain the kimi remediation entry. CLAUDE.md and
docs/map document the runtime. Per the no-pins policy, agent-grok/
gemini/codex Dockerfiles drop their version pins for latest-at-build
with resolved-version provenance stamps (grok resolves 0.2.112 vs the
old 0.2.56 pin - verified by real builds of all four images).

---------

Co-authored-by: Renn F <rennf93@users.noreply.github.com>

tests/unit/runtime/test_interactive_provider_guard.py

@@ -1,8 +1,9 @@
-"""Codex (OPENAI) and Gemini (GEMINI) are V1 delivery-roles-only — neither has
-an interactive-session driver image (unlike GROK's dedicated
-GROK_PROMPTER_IMAGE / GROK_SECRETARY_IMAGE). Routing either to the persistent
-Intake/Secretary agent must refuse loudly instead of silently falling through
-to the plain Claude SDK-driver image with a mismatched provider env.
+"""Codex (OPENAI), Gemini (GEMINI), and Kimi (KIMI) are V1 delivery-roles-only
+— none has an interactive-session driver image (unlike GROK's dedicated
+GROK_PROMPTER_IMAGE / GROK_SECRETARY_IMAGE). Routing any of them to the
+persistent Intake/Secretary agent must refuse loudly instead of silently
+falling through to the plain Claude SDK-driver image with a mismatched
+provider env.
 """
 
 from __future__ import annotations
@@ -67,7 +68,9 @@ class TestRejectInteractiveUnsupportedProvider:
         un-exempt a chat."""
         assert set(INTERACTIVE_AGENT_SLUGS) == {INTAKE_AGENT_ID, SECRETARY_AGENT_ID}
 
-    @pytest.mark.parametrize("provider", [ModelProvider.OPENAI, ModelProvider.GEMINI])
+    @pytest.mark.parametrize(
+        "provider", [ModelProvider.OPENAI, ModelProvider.GEMINI, ModelProvider.KIMI]
+    )
     def test_raises_for_delivery_only_providers(self, provider: ModelProvider) -> None:
         with pytest.raises(RuntimeError, match="delivery-roles-only"):
             _reject_interactive_unsupported_provider(INTAKE_AGENT_ID, provider)
@@ -93,7 +96,9 @@ class TestRejectInteractiveUnsupportedProvider:
 
 
 class TestIntakeSpawnRefusesDeliveryOnlyProvider:
-    @pytest.mark.parametrize("provider", [ModelProvider.OPENAI, ModelProvider.GEMINI])
+    @pytest.mark.parametrize(
+        "provider", [ModelProvider.OPENAI, ModelProvider.GEMINI, ModelProvider.KIMI]
+    )
     @pytest.mark.asyncio
     async def test_refuses_before_any_container_work(
         self, monkeypatch: pytest.MonkeyPatch, provider: ModelProvider
@@ -149,7 +154,9 @@ class TestIntakeSpawnRefusesDeliveryOnlyProvider:
 
 
 class TestSecretarySpawnRefusesDeliveryOnlyProvider:
-    @pytest.mark.parametrize("provider", [ModelProvider.OPENAI, ModelProvider.GEMINI])
+    @pytest.mark.parametrize(
+        "provider", [ModelProvider.OPENAI, ModelProvider.GEMINI, ModelProvider.KIMI]
+    )
     @pytest.mark.asyncio
     async def test_refuses_before_any_container_work(
         self, monkeypatch: pytest.MonkeyPatch, provider: ModelProvider