kiapi 0.5.2__tar.gz → 0.6.0__tar.gz

{kiapi-0.5.2 → kiapi-0.6.0}/CHANGELOG.md

@@ -6,6 +6,18 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 
 ## [Unreleased]
 
+## [0.6.0] - 2026-09-01
+
+### Removed
+
+- **BREAKING**: Removed the relay transport. `kiapi run --relay`, the `relay-gcp` extra, the `relay` field of `/health`, and the `KIAPI_RELAY_*` settings are gone, and kiapi no longer depends on `kiapi-relay`. To reach kiapi from other machines, expose it over your own private network layer instead — for example, run `tailscale serve --bg --https=8500 8500` on the kiapi machine and point clients at `https://<machine>.<tailnet>.ts.net:8500`. Remove any `kiapi_relay*` and relay-related `kiarina.lib.google` sections from your `settings.yaml`.
+
+## [0.5.3] - 2026-07-30
+
+### Fixed
+
+- `kiapi service install` now preserves `PATH` in the launchd property list so background capabilities can find external tools such as Homebrew FFmpeg.
+
 ## [0.5.2] - 2026-07-29
 
 ### Fixed

{kiapi-0.5.2 → kiapi-0.6.0}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.4
+Metadata-Version: 2.5
 Name: kiapi
-Version: 0.5.2
+Version: 0.6.0
 Summary: Unified local inference API server for LLM agents on Apple Silicon (MLX): chat, embedding, image, music, sound-effect, and video — one process, one global memory budget, one single-flight queue, unified jobs and files.
 Project-URL: Homepage, https://github.com/kiarina/kiapi
 Project-URL: Repository, https://github.com/kiarina/kiapi
@@ -25,7 +25,6 @@ Requires-Python: <3.13,>=3.12
 Requires-Dist: click
 Requires-Dist: fastapi<0.137
 Requires-Dist: httpx
-Requires-Dist: kiapi-relay
 Requires-Dist: kiarina-utils-app>=2.3.0
 Requires-Dist: kiarina-utils-common>=2.2.0
 Requires-Dist: mflux>=0.18.0
@@ -45,8 +44,6 @@ Requires-Dist: torch
 Requires-Dist: torchaudio
 Requires-Dist: torchvision
 Requires-Dist: uvicorn[standard]
-Provides-Extra: relay-gcp
-Requires-Dist: kiapi-relay[gcp]; extra == 'relay-gcp'
 Description-Content-Type: text/markdown
 
 # kiapi
@@ -56,8 +53,6 @@ Description-Content-Type: text/markdown
 ![Platform](https://img.shields.io/badge/Platform-Apple%20Silicon-lightgrey.svg)
 [![API Docs](https://img.shields.io/badge/API%20Docs-GitHub%20Pages-green.svg)](https://kiarina.github.io/kiapi/)
 
-**English** | [日本語](README.ja.md)
-
 ## Summary
 
 kiapi is a local API server that uses Apple Silicon and MLX to provide generative AI capabilities for LLM agents.
@@ -66,19 +61,19 @@ kiapi is a local API server that uses Apple Silicon and MLX to provide generativ
 
 | Domain | Family | Endpoint | Description |
 |---|---|---|---|
-| chat |  | `POST /v1/chat` | [Chat API details](./kiapi/capabilities/chat/README.md) |
-| embedding |  | `POST /v1/embedding` | [Embedding API details](./kiapi/capabilities/embedding/README.md) |
-| image | zimage | `POST /v1/image/zimage` | [Z-Image API details](./kiapi/capabilities/zimage/README.md) |
-|  | flux2 | `POST /v1/image/flux2` | [FLUX.2 API details](./kiapi/capabilities/flux2/README.md) |
-|  | qwen | `POST /v1/image/qwen` | [Qwen Image API details](./kiapi/capabilities/qwen/README.md) |
-|  | ideogram4 | `POST /v1/image/ideogram4` | [Ideogram 4 API details](./kiapi/capabilities/ideogram4/README.md) |
-|  | ernie | `POST /v1/image/ernie` | [ERNIE-Image API details](./kiapi/capabilities/ernie/README.md) |
-|  | seedvr2 | `POST /v1/image/seedvr2` | [SeedVR2 API details](./kiapi/capabilities/seedvr2/README.md) |
-|  | depthpro | `POST /v1/image/depthpro` | [Depth Pro API details](./kiapi/capabilities/depthpro/README.md) |
-| audio | acestep | `POST /v1/audio/acestep` | [ACE-Step API details](./kiapi/capabilities/acestep/README.md) |
-|  | audiogen | `POST /v1/audio/audiogen` | [AudioGen API details](./kiapi/capabilities/audiogen/README.md) |
-| video | ltx2 | `POST /v1/video/ltx2` | [LTX-2 API details](./kiapi/capabilities/ltx2/README.md) |
-| web |  | `POST /v1/web` | [Web API details](./kiapi/capabilities/web/README.md) |
+| chat |  | `POST /v1/chat` | [Chat API details](./src/kiapi/capabilities/chat/README.md) |
+| embedding |  | `POST /v1/embedding` | [Embedding API details](./src/kiapi/capabilities/embedding/README.md) |
+| image | zimage | `POST /v1/image/zimage` | [Z-Image API details](./src/kiapi/capabilities/zimage/README.md) |
+|  | flux2 | `POST /v1/image/flux2` | [FLUX.2 API details](./src/kiapi/capabilities/flux2/README.md) |
+|  | qwen | `POST /v1/image/qwen` | [Qwen Image API details](./src/kiapi/capabilities/qwen/README.md) |
+|  | ideogram4 | `POST /v1/image/ideogram4` | [Ideogram 4 API details](./src/kiapi/capabilities/ideogram4/README.md) |
+|  | ernie | `POST /v1/image/ernie` | [ERNIE-Image API details](./src/kiapi/capabilities/ernie/README.md) |
+|  | seedvr2 | `POST /v1/image/seedvr2` | [SeedVR2 API details](./src/kiapi/capabilities/seedvr2/README.md) |
+|  | depthpro | `POST /v1/image/depthpro` | [Depth Pro API details](./src/kiapi/capabilities/depthpro/README.md) |
+| audio | acestep | `POST /v1/audio/acestep` | [ACE-Step API details](./src/kiapi/capabilities/acestep/README.md) |
+|  | audiogen | `POST /v1/audio/audiogen` | [AudioGen API details](./src/kiapi/capabilities/audiogen/README.md) |
+| video | ltx2 | `POST /v1/video/ltx2` | [LTX-2 API details](./src/kiapi/capabilities/ltx2/README.md) |
+| web |  | `POST /v1/web` | [Web API details](./src/kiapi/capabilities/web/README.md) |
 | core | files | `POST /v1/files` | Upload input files, LoRA adapters, and other files, then issue a `file_id`. |
 |  |  | `GET /v1/files` | Return a list of stored files. |
 |  |  | `GET /v1/files/{file_id}` | Return file metadata. |
@@ -115,69 +110,12 @@ return 503 as an insufficient memory budget error.
 model weights and Docker images. At first, it is recommended to use `kiapi activate`
 to set up only the capabilities you need.
 
-## Remote Job Relay
-
-The optional GCP relay lets a kiapi node inside a closed network receive API
-work without exposing an inbound socket. Firebase Realtime Database carries
-small notifications, while Cloud Storage carries request and response bodies.
-Install kiapi with the `relay-gcp` extra to enable it:
-
-```sh
-python3.12 -m pip install --upgrade "kiapi[relay-gcp]"
-uv tool install --python 3.12 "kiapi[relay-gcp]"
-```
-
-```sh
-export KIAPI_RELAY_GCP_DATABASE_URL="https://PROJECT.firebaseio.com"
-export KIAPI_RELAY_GCP_BUCKET="PRIVATE_RELAY_BUCKET"
-
-# Uses Application Default Credentials by default.
-kiapi run --relay gcp
-```
-
-Each node generates its own `node_id` on first start, persists it in the user
-data directory, and publishes a liveness heartbeat under `liveness`.
-A requester picks the most recently seen node and writes
-`sessions/{session_id}/request.json` in GCS, then writes a notification
-to `nodes/{node_id}/requests/{session_id}` in RTDB. The relay reports
-`queued`, `running`, and the terminal result below the requester node's
-`responses` path.
-
-- Requests are dispatched directly to the in-process FastAPI app and handled
-  one at a time by the relay.
-- JSON responses use `response.json`. Binary responses write `response.body`
-  before `response.json`.
-- `response.json` uses a GCS create-only generation precondition. A completed
-  response found after restart is reported without executing the API again.
-- The terminal RTDB response and request deletion use one atomic multi-location
-  update.
-- Startup installs a session-scoped lifecycle rule that deletes session objects
-  after one day. Set `KIAPI_RELAY_GCP_MANAGE_BUCKET_LIFECYCLE=false` when
-  infrastructure manages this rule.
-
-Use a dedicated bucket and narrowly scoped RTDB/GCS permissions. Google
-credentials are configured through
-[`kiarina-lib-google`](https://github.com/kiarina/kiarina-python/tree/main/packages/kiarina-lib-google).
-
-See [GCP Relay setup](../kiapi-relay/src/kiapi_relay/impl/gcp/README.md) for resource
-creation, IAM, authentication, configuration, and verification steps.
-
-For local relay verification without GCP, use `local`. It uses the same
-in-process dispatch path but stores notifications and payloads under a local
-directory:
-
-```sh
-export KIAPI_RELAY_LOCAL_ROOT="/tmp/kiapi/relay"
-export KIAPI_RELAY_LOCAL_PREFIX="private/kiapi"
-
-kiapi run --relay local
-```
-
-The requester writes `{root}/{prefix}/sessions/{session_id}/request.json`, then
-writes `{root}/{prefix}/nodes/{node_id}/requests/{session_id}.json` with
-`{"session_id":"...","source_node_id":"..."}`. The relay writes bridge status
-to `{root}/{prefix}/nodes/{source_node_id}/responses/{session_id}.json` and
-stores the committed response in the session directory.
+## Remote Access
+
+kiapi binds to `127.0.0.1` by default and does not expose an inbound socket.
+For access from other machines, put it behind your own private network layer —
+for example `tailscale serve` for a TLS endpoint reachable only inside your
+tailnet.
 
 ## Local Storage
 

{kiapi-0.5.2 → kiapi-0.6.0}/README.md

@@ -5,8 +5,6 @@
 ![Platform](https://img.shields.io/badge/Platform-Apple%20Silicon-lightgrey.svg)
 [![API Docs](https://img.shields.io/badge/API%20Docs-GitHub%20Pages-green.svg)](https://kiarina.github.io/kiapi/)
 
-**English** | [日本語](README.ja.md)
-
 ## Summary
 
 kiapi is a local API server that uses Apple Silicon and MLX to provide generative AI capabilities for LLM agents.
@@ -15,19 +13,19 @@ kiapi is a local API server that uses Apple Silicon and MLX to provide generativ
 
 | Domain | Family | Endpoint | Description |
 |---|---|---|---|
-| chat |  | `POST /v1/chat` | [Chat API details](./kiapi/capabilities/chat/README.md) |
-| embedding |  | `POST /v1/embedding` | [Embedding API details](./kiapi/capabilities/embedding/README.md) |
-| image | zimage | `POST /v1/image/zimage` | [Z-Image API details](./kiapi/capabilities/zimage/README.md) |
-|  | flux2 | `POST /v1/image/flux2` | [FLUX.2 API details](./kiapi/capabilities/flux2/README.md) |
-|  | qwen | `POST /v1/image/qwen` | [Qwen Image API details](./kiapi/capabilities/qwen/README.md) |
-|  | ideogram4 | `POST /v1/image/ideogram4` | [Ideogram 4 API details](./kiapi/capabilities/ideogram4/README.md) |
-|  | ernie | `POST /v1/image/ernie` | [ERNIE-Image API details](./kiapi/capabilities/ernie/README.md) |
-|  | seedvr2 | `POST /v1/image/seedvr2` | [SeedVR2 API details](./kiapi/capabilities/seedvr2/README.md) |
-|  | depthpro | `POST /v1/image/depthpro` | [Depth Pro API details](./kiapi/capabilities/depthpro/README.md) |
-| audio | acestep | `POST /v1/audio/acestep` | [ACE-Step API details](./kiapi/capabilities/acestep/README.md) |
-|  | audiogen | `POST /v1/audio/audiogen` | [AudioGen API details](./kiapi/capabilities/audiogen/README.md) |
-| video | ltx2 | `POST /v1/video/ltx2` | [LTX-2 API details](./kiapi/capabilities/ltx2/README.md) |
-| web |  | `POST /v1/web` | [Web API details](./kiapi/capabilities/web/README.md) |
+| chat |  | `POST /v1/chat` | [Chat API details](./src/kiapi/capabilities/chat/README.md) |
+| embedding |  | `POST /v1/embedding` | [Embedding API details](./src/kiapi/capabilities/embedding/README.md) |
+| image | zimage | `POST /v1/image/zimage` | [Z-Image API details](./src/kiapi/capabilities/zimage/README.md) |
+|  | flux2 | `POST /v1/image/flux2` | [FLUX.2 API details](./src/kiapi/capabilities/flux2/README.md) |
+|  | qwen | `POST /v1/image/qwen` | [Qwen Image API details](./src/kiapi/capabilities/qwen/README.md) |
+|  | ideogram4 | `POST /v1/image/ideogram4` | [Ideogram 4 API details](./src/kiapi/capabilities/ideogram4/README.md) |
+|  | ernie | `POST /v1/image/ernie` | [ERNIE-Image API details](./src/kiapi/capabilities/ernie/README.md) |
+|  | seedvr2 | `POST /v1/image/seedvr2` | [SeedVR2 API details](./src/kiapi/capabilities/seedvr2/README.md) |
+|  | depthpro | `POST /v1/image/depthpro` | [Depth Pro API details](./src/kiapi/capabilities/depthpro/README.md) |
+| audio | acestep | `POST /v1/audio/acestep` | [ACE-Step API details](./src/kiapi/capabilities/acestep/README.md) |
+|  | audiogen | `POST /v1/audio/audiogen` | [AudioGen API details](./src/kiapi/capabilities/audiogen/README.md) |
+| video | ltx2 | `POST /v1/video/ltx2` | [LTX-2 API details](./src/kiapi/capabilities/ltx2/README.md) |
+| web |  | `POST /v1/web` | [Web API details](./src/kiapi/capabilities/web/README.md) |
 | core | files | `POST /v1/files` | Upload input files, LoRA adapters, and other files, then issue a `file_id`. |
 |  |  | `GET /v1/files` | Return a list of stored files. |
 |  |  | `GET /v1/files/{file_id}` | Return file metadata. |
@@ -64,69 +62,12 @@ return 503 as an insufficient memory budget error.
 model weights and Docker images. At first, it is recommended to use `kiapi activate`
 to set up only the capabilities you need.
 
-## Remote Job Relay
-
-The optional GCP relay lets a kiapi node inside a closed network receive API
-work without exposing an inbound socket. Firebase Realtime Database carries
-small notifications, while Cloud Storage carries request and response bodies.
-Install kiapi with the `relay-gcp` extra to enable it:
-
-```sh
-python3.12 -m pip install --upgrade "kiapi[relay-gcp]"
-uv tool install --python 3.12 "kiapi[relay-gcp]"
-```
-
-```sh
-export KIAPI_RELAY_GCP_DATABASE_URL="https://PROJECT.firebaseio.com"
-export KIAPI_RELAY_GCP_BUCKET="PRIVATE_RELAY_BUCKET"
-
-# Uses Application Default Credentials by default.
-kiapi run --relay gcp
-```
-
-Each node generates its own `node_id` on first start, persists it in the user
-data directory, and publishes a liveness heartbeat under `liveness`.
-A requester picks the most recently seen node and writes
-`sessions/{session_id}/request.json` in GCS, then writes a notification
-to `nodes/{node_id}/requests/{session_id}` in RTDB. The relay reports
-`queued`, `running`, and the terminal result below the requester node's
-`responses` path.
-
-- Requests are dispatched directly to the in-process FastAPI app and handled
-  one at a time by the relay.
-- JSON responses use `response.json`. Binary responses write `response.body`
-  before `response.json`.
-- `response.json` uses a GCS create-only generation precondition. A completed
-  response found after restart is reported without executing the API again.
-- The terminal RTDB response and request deletion use one atomic multi-location
-  update.
-- Startup installs a session-scoped lifecycle rule that deletes session objects
-  after one day. Set `KIAPI_RELAY_GCP_MANAGE_BUCKET_LIFECYCLE=false` when
-  infrastructure manages this rule.
-
-Use a dedicated bucket and narrowly scoped RTDB/GCS permissions. Google
-credentials are configured through
-[`kiarina-lib-google`](https://github.com/kiarina/kiarina-python/tree/main/packages/kiarina-lib-google).
-
-See [GCP Relay setup](../kiapi-relay/src/kiapi_relay/impl/gcp/README.md) for resource
-creation, IAM, authentication, configuration, and verification steps.
-
-For local relay verification without GCP, use `local`. It uses the same
-in-process dispatch path but stores notifications and payloads under a local
-directory:
-
-```sh
-export KIAPI_RELAY_LOCAL_ROOT="/tmp/kiapi/relay"
-export KIAPI_RELAY_LOCAL_PREFIX="private/kiapi"
-
-kiapi run --relay local
-```
-
-The requester writes `{root}/{prefix}/sessions/{session_id}/request.json`, then
-writes `{root}/{prefix}/nodes/{node_id}/requests/{session_id}.json` with
-`{"session_id":"...","source_node_id":"..."}`. The relay writes bridge status
-to `{root}/{prefix}/nodes/{source_node_id}/responses/{session_id}.json` and
-stores the committed response in the session directory.
+## Remote Access
+
+kiapi binds to `127.0.0.1` by default and does not expose an inbound socket.
+For access from other machines, put it behind your own private network layer —
+for example `tailscale serve` for a TLS endpoint reachable only inside your
+tailnet.
 
 ## Local Storage
 

{kiapi-0.5.2 → kiapi-0.6.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "kiapi"
-version = "0.5.2"
+version = "0.6.0"
 description = "Unified local inference API server for LLM agents on Apple Silicon (MLX): chat, embedding, image, music, sound-effect, and video — one process, one global memory budget, one single-flight queue, unified jobs and files."
 readme = "README.md"
 requires-python = ">=3.12,<3.13"
@@ -47,8 +47,6 @@ dependencies = [
     "httpx", # web search capability: async HTTP client for the SearXNG backend
     "kiarina-utils-common>=2.2.0",
     "kiarina-utils-app>=2.3.0", # user directory resolution (replaces core/app internals)
-    # --- relay (shared request/response transport, split into its own package) ---
-    "kiapi-relay",
     # --- embedding capability (mlx-embeddings) ---
     "mlx-embeddings>=0.1.0",
     # --- sound-effect capability (mlx-audiocraft / AudioGen) ---
@@ -72,11 +70,6 @@ dependencies = [
     "pydantic-settings-manager>=3.8.0",
 ]
 
-[project.optional-dependencies]
-relay-gcp = [
-    "kiapi-relay[gcp]",
-]
-
 [project.scripts]
 kiapi = "kiapi.cli.cli:main"
 

{kiapi-0.5.2 → kiapi-0.6.0}/src/kiapi/api/__init__.py

@@ -8,7 +8,6 @@ if TYPE_CHECKING:
     from ._helpers.build_train_responses import build_train_responses
     from ._helpers.get_accept import get_accept
     from ._helpers.get_ctx import get_ctx
-    from ._helpers.get_relay_runner import get_relay_runner
     from ._helpers.get_worker import get_worker
     from ._helpers.register_capability_endpoints import register_capability_endpoints
     from ._helpers.submit_and_maybe_wait import submit_and_maybe_wait
@@ -21,7 +20,6 @@ __all__ = [
     "build_train_responses",
     "get_accept",
     "get_ctx",
-    "get_relay_runner",
     "get_worker",
     "register_capability_endpoints",
     "settings_manager",
@@ -40,7 +38,6 @@ def __getattr__(name: str) -> object:
         "build_train_responses": "._helpers.build_train_responses",
         "get_accept": "._helpers.get_accept",
         "get_ctx": "._helpers.get_ctx",
-        "get_relay_runner": "._helpers.get_relay_runner",
         "get_worker": "._helpers.get_worker",
         "register_capability_endpoints": "._helpers.register_capability_endpoints",
         "settings_manager": "._settings",

{kiapi-0.5.2 → kiapi-0.6.0}/src/kiapi/api/app.py

@@ -5,7 +5,7 @@ from contextlib import asynccontextmanager
 from fastapi import FastAPI
 from fastapi.openapi.docs import get_redoc_html, get_swagger_ui_html
 from fastapi.responses import HTMLResponse
-from kiarina.utils.app import single_instance, user_directory
+from kiarina.utils.app import single_instance
 
 from kiapi.api import build_openapi
 from kiapi.core.app import AppContext
@@ -13,12 +13,6 @@ from kiapi.core.capability import capability_spec_registry
 from kiapi.core.logging import setup_logger
 from kiapi.core.model import model_registry
 from kiapi.core.worker import create_worker
-from kiapi_relay import (
-    RelayRunner,
-    get_or_create_node_id,
-    relay_registry,
-)
-from kiapi_relay import settings_manager as relay_settings_manager
 
 from .audio.acestep.router import router as acestep_router
 from .audio.audiogen.router import router as audiogen_router
@@ -65,11 +59,7 @@ async def lifespan(app: FastAPI):  # type: ignore
             "Start the server with `kiapi run` instead of importing the ASGI app directly."
         )
 
-    # Prevent a second kiapi from sharing this node identity and double-consuming
-    # relay requests, then resolve the persistent node ID for this data dir.
     single_instance.acquire()
-    data_dir = user_directory.get_user_data_dir()
-    node_id = get_or_create_node_id(data_dir)
 
     ctx = AppContext.create()
     worker = create_worker(ctx)
@@ -80,20 +70,8 @@ async def lifespan(app: FastAPI):  # type: ignore
     worker.start()
     asyncio.create_task(worker.warmup())  # noqa: RUF006
 
-    relay_runner: RelayRunner | None = None
-
-    if relay_settings_manager.get_settings().default is not None:
-        relay = relay_registry.resolve()
-        relay.node_id = node_id
-        relay_runner = RelayRunner(relay, app)
-        relay_runner.start()
-        app.state.relay_runner = relay_runner
-
     yield
 
-    if relay_runner is not None:
-        await relay_runner.stop()
-
     await worker.stop()
     single_instance.release()
 

{kiapi-0.5.2 → kiapi-0.6.0}/src/kiapi/api/health/_views/health_response.py

@@ -1,7 +1,6 @@
 from pydantic import BaseModel, Field
 
 from kiapi.core.memory import MemoryStats
-from kiapi_relay import RelayHealth
 
 
 class HealthResponse(BaseModel):
@@ -25,10 +24,3 @@ class HealthResponse(BaseModel):
         ...,
         description="Resident model memory budget and loaded model snapshot.",
     )
-    relay: RelayHealth | None = Field(
-        default=None,
-        description=(
-            "Status of the relay started with the API server. "
-            "Null when no relay is configured."
-        ),
-    )

{kiapi-0.5.2 → kiapi-0.6.0}/src/kiapi/api/health/router.py

@@ -1,9 +1,8 @@
 from fastapi import APIRouter, Depends
 
-from kiapi.api import get_ctx, get_relay_runner, get_worker
+from kiapi.api import get_ctx, get_worker
 from kiapi.core.app import AppContext
 from kiapi.core.worker import Worker
-from kiapi_relay import RelayRunner
 
 from ._views.health_response import HealthResponse
 
@@ -14,19 +13,16 @@ router = APIRouter()
 async def health(
     ctx: AppContext = Depends(get_ctx),
     worker: Worker = Depends(get_worker),
-    relay_runner: RelayRunner | None = Depends(get_relay_runner),
 ) -> dict:
-    """Inspect server readiness, queue depth, resident model memory, and relay.
+    """Inspect server readiness, queue depth, and resident model memory.
 
     Use this endpoint to see whether warmup has finished, how many jobs are
-    queued behind the single-flight worker, which resident models currently
-    count against the global memory budget, and whether the relay started with
-    the server is running.
+    queued behind the single-flight worker, and which resident models currently
+    count against the global memory budget.
     """
     return {
         "status": "ok",
         "warm": worker.warm,
         "queue_len": worker.queue.qsize(),
         "memory": ctx.memory_manager.stats(),
-        "relay": relay_runner.status() if relay_runner is not None else None,
     }

{kiapi-0.5.2 → kiapi-0.6.0}/src/kiapi/capabilities/acestep/README.md

@@ -1,7 +1,5 @@
 # acestep
 
-**English** | [日本語](README.ja.md)
-
 [ACE-Step 1.5](https://github.com/ace-step/ACE-Step-1.5) provides the following functions.
 - Music generation
 - Style conversion of existing songs
@@ -159,7 +157,7 @@ curl -sS -X POST http://localhost:${PORT:-8000}/v1/audio/acestep/extract \
 --data-binary @-
 )
 
-# 各音源をダウンロード（stems[] にターゲット名が入る）
+# Download each stem (stems[] carries the target name)
 echo "$RESP" | jq -c '.result.stems[]' | while read -r s; do
   TARGET=$(echo "$s" | jq -r .target); FID=$(echo "$s" | jq -r .file_id)
   curl -o "${TARGET}.wav" http://localhost:${PORT:-8000}/v1/files/$FID/download

{kiapi-0.5.2 → kiapi-0.6.0}/src/kiapi/capabilities/audiogen/README.md

@@ -1,7 +1,5 @@
 # audiogen
 
-**English** | [日本語](README.ja.md)
-
 [AudioGen](https://huggingface.co/facebook/audiogen-medium) provides sound effect generation functionality.
 
 ## API

{kiapi-0.5.2 → kiapi-0.6.0}/src/kiapi/capabilities/chat/README.md

@@ -1,7 +1,5 @@
 # chat
 
-**English** | [日本語](README.ja.md)
-
 [mlx-vlm](https://github.com/Blaizzy/mlx-vlm) provides an OpenAI-compatible chat completion API.
 
 - **vlm** (text + image):

{kiapi-0.5.2 → kiapi-0.6.0}/src/kiapi/capabilities/depthpro/README.md

@@ -1,7 +1,5 @@
 # depthpro
 
-**English** | [日本語](README.ja.md)
-
 [mflux Depth Pro](https://github.com/filipstrand/mflux/blob/main/src/mflux/models/depth_pro/README.md) estimates a depth map from a single image and produces the following:
 
 - Depth map in grayscale PNG

{kiapi-0.5.2 → kiapi-0.6.0}/src/kiapi/capabilities/embedding/README.md

@@ -1,7 +1,5 @@
 # embedding
 
-**English** | [日本語](README.ja.md)
-
 [mlx-embeddings](https://github.com/Blaizzy/mlx-embeddings) provides a text/image embedding API.
 
 - **text embedding**:

{kiapi-0.5.2 → kiapi-0.6.0}/src/kiapi/capabilities/ernie/README.md

@@ -1,7 +1,5 @@
 # ernie
 
-**English** | [日本語](README.ja.md)
-
 [mflux ERNIE-Image](https://github.com/filipstrand/mflux/blob/main/src/mflux/models/ernie_image/README.md) provides image generation, image editing, and LoRA fine tuning functions.
 
 - **generate**: Generate image from text

{kiapi-0.5.2 → kiapi-0.6.0}/src/kiapi/capabilities/flux2/README.md

@@ -1,7 +1,5 @@
 # flux2
 
-**English** | [日本語](README.ja.md)
-
 [mflux FLUX.2 Klein](https://github.com/filipstrand/mflux/blob/main/src/mflux/models/flux2/README.md) provides image generation, image editing, and LoRA learning functions.
 
 - **generate**:

{kiapi-0.5.2 → kiapi-0.6.0}/src/kiapi/capabilities/ideogram4/README.md

@@ -1,7 +1,5 @@
 # ideogram4
 
-**English** | [日本語](README.ja.md)
-
 [mflux Ideogram 4 FP8](https://github.com/filipstrand/mflux/blob/main/src/mflux/models/ideogram4/README.md) provides typography-friendly text image generation functionality.
 Ideogram 4 is a model suitable for situations where you want to handle text, signs, labels, logo-like text, etc. in images.
 kiapi only exposes txt2img and saves the generated results as Files API artifacts.

{kiapi-0.5.2 → kiapi-0.6.0}/src/kiapi/capabilities/ltx2/README.md

@@ -1,7 +1,5 @@
 # ltx2
 
-**English** | [日本語](README.ja.md)
-
 [mlx-video LTX-2](https://github.com/Blaizzy/mlx-video) provides short video generation functionality.
 
 - **T2V**: Generate video from text

{kiapi-0.5.2 → kiapi-0.6.0}/src/kiapi/capabilities/qwen/README.md

@@ -1,7 +1,5 @@
 # qwen
 
-**English** | [日本語](README.ja.md)
-
 [mflux Qwen Image](https://github.com/filipstrand/mflux/blob/main/src/mflux/models/qwen/README.md) provides image generation and image editing functions.
 Qwen Image is a strong model for multilingual prompts and text in images.
 

{kiapi-0.5.2 → kiapi-0.6.0}/src/kiapi/capabilities/seedvr2/README.md

@@ -1,7 +1,5 @@
 # seedvr2
 
-**English** | [日本語](README.ja.md)
-
 [mflux SeedVR2](https://github.com/filipstrand/mflux/blob/main/src/mflux/models/seedvr2/README.md) provides single-image diffusion-based super-resolution/upscaling functionality.
 SeedVR2 is an image-to-image super-resolution model that reconstructs details based on input images rather than prompt-driven image generation.
 

{kiapi-0.5.2 → kiapi-0.6.0}/src/kiapi/capabilities/web/README.md

@@ -1,7 +1,5 @@
 # web
 
-**English** | [日本語](README.ja.md)
-
 **web capability** for using SearXNG and Crawl4AI from kiapi.
 
 - **search**: Search the web with SearXNG and return JSON search results.

{kiapi-0.5.2 → kiapi-0.6.0}/src/kiapi/capabilities/zimage/README.md

@@ -1,7 +1,5 @@
 # zimage
 
-**English** | [日本語](README.ja.md)
-
 [mflux Z-Image](https://github.com/filipstrand/mflux/blob/main/src/mflux/models/z_image/README.md) provides image generation and LoRA fine-tuning functionality.
 
 Z-Image is a relatively lightweight image generation model.

{kiapi-0.5.2 → kiapi-0.6.0}/src/kiapi/cli/config/template/cli.py

@@ -10,10 +10,6 @@ _SETTINGS_IMPORT_PATHS = [
     "kiapi.core.memory",
     "kiapi.core.worker",
     "kiapi.core.net",
-    "kiapi_relay",
-    "kiapi_relay.impl.gcp",
-    "kiapi_relay.impl.local",
-    "kiarina.lib.google",
     "kiapi.capabilities.chat",
     "kiapi.capabilities.embedding",
     "kiapi.capabilities.depthpro",

{kiapi-0.5.2 → kiapi-0.6.0}/src/kiapi/cli/run/cli.py

@@ -7,22 +7,15 @@ from kiapi.api import settings_manager as api_settings_manager
 from kiapi.cli import register_all_capabilities
 from kiapi.core.logging import get_log_level
 from kiapi.core.logging import settings_manager as logging_settings_manager
-from kiapi_relay import settings_manager as relay_settings_manager
 
 
 @click.command()
 @click.option("--host", type=str, help="Bind socket to this host")
 @click.option("--port", type=int, help="Bind socket to this port")
-@click.option(
-    "--relay",
-    type=str,
-    help="Start a relay, for example: gcp. Pass 'none' to disable the relay.",
-)
 @click.option("--debug", is_flag=True, help="Enable debug logging and hot reload")
 def run(
     host: str | None,
     port: int | None,
-    relay: str | None,
     debug: bool,
 ) -> None:
     """Run the kiapi API server."""
@@ -36,11 +29,6 @@ def run(
     if api_cli_args:
         api_settings_manager.cli_args = api_cli_args
 
-    if relay is not None:
-        relay_settings_manager.cli_args = {
-            "default": None if relay == "none" else relay
-        }
-
     settings = api_settings_manager.get_settings()
 
     if debug:
@@ -49,9 +37,6 @@ def run(
         # in-process cli_args, so propagate the log level via the environment.
         os.environ["KIAPI_LOG_LEVEL"] = "DEBUG"
 
-        if relay is not None:
-            os.environ["KIAPI_RELAY_DEFAULT"] = relay
-
         # Hot reload requires an import string (the worker subprocess
         # re-imports the app), so use the ASGI factory that registers
         # capabilities on import.

{kiapi-0.5.2 → kiapi-0.6.0}/src/kiapi/cli/service/_services/service_manager.py

@@ -62,7 +62,7 @@ def install() -> None:
 def _build_environment_variables() -> dict[str, str]:
     env = {"PYTHONUNBUFFERED": "1"}
 
-    for name in ("XDG_CACHE_HOME", "XDG_CONFIG_HOME", "XDG_DATA_HOME"):
+    for name in ("PATH", "XDG_CACHE_HOME", "XDG_CONFIG_HOME", "XDG_DATA_HOME"):
         value = os.environ.get(name)
         if value:
             env[name] = value