coderouter-cli 2.7.3__py3-none-any.whl → 2.7.4__py3-none-any.whl

coderouter/ingress/launcher_routes.py

@@ -655,6 +655,28 @@ async def api_backends(request: Request) -> dict[str, Any]:
     return {"backends": result}
 
 
+def _launcher_provider_config(backend: str, port: int) -> Any:
+    """Build the provider entry for a launcher-started backend.
+
+    ``model`` is left EMPTY on purpose: llama-server / vllm / mlx decide
+    which model is actually loaded, and the empty-model /v1/models
+    passthrough then surfaces the upstream's real model id to benchmark
+    clients — swap the GGUF, no config edit needed.
+
+    Name embeds backend + port (``launcher-llamacpp-8085``) so restarting
+    on the same port REPLACES the entry instead of piling up duplicates.
+    """
+    from coderouter.config.schemas import ProviderConfig
+
+    safe_backend = backend.replace(".", "")
+    return ProviderConfig(
+        name=f"launcher-{safe_backend}-{port}",
+        base_url=f"http://localhost:{port}/v1",
+        model="",
+        timeout_s=120.0,
+    )
+
+
 @router.post("/api/launcher/start")
 async def api_start(req: StartRequest, request: Request) -> dict[str, Any]:
     """Start a new backend process."""
@@ -717,7 +739,35 @@ async def api_start(req: StartRequest, request: Request) -> dict[str, Any]:
     _background_tasks.add(_task)
     _task.add_done_callback(_background_tasks.discard)
 
-    return {"id": proc_id, "pid": p.pid, "command": cmd}
+    # Provider auto-sync: register the just-started backend as a routable
+    # provider so requests can reach it without hand-editing providers.yaml
+    # (in-memory only — see FallbackEngine.register_provider docstring).
+    # Sync failure must never fail the start itself.
+    provider_sync: dict[str, Any] | None = None
+    engine = getattr(request.app.state, "engine", None)
+    if engine is not None and hasattr(engine, "register_provider"):
+        try:
+            provider_sync = engine.register_provider(
+                _launcher_provider_config(req.backend, req.port)
+            )
+            proc.log_tail.append(
+                "[launcher] provider sync: "
+                f"{provider_sync['provider']} -> profile "
+                f"'{provider_sync['profile']}' (in-memory)"
+            )
+        except Exception as exc:
+            logger.warning(
+                "launcher provider sync failed",
+                extra={"backend": req.backend, "port": req.port, "error": str(exc)},
+            )
+            proc.log_tail.append(f"[launcher] provider sync failed: {exc}")
+
+    return {
+        "id": proc_id,
+        "pid": p.pid,
+        "command": cmd,
+        "provider_sync": provider_sync,
+    }
 
 
 @router.post("/api/launcher/stop/{proc_id}")

coderouter/ingress/openai_routes.py

@@ -78,22 +78,99 @@ def _resolve_stream_timeout_s(engine: FallbackEngine, profile: str | None) -> fl
     return max(_STREAM_TIMEOUT_MIN_S, float(per_call) * _STREAM_TIMEOUT_MULTIPLIER)
 
 
+# --- /v1/models upstream passthrough -------------------------------------
+#
+# Providers with an *empty* ``model`` field are passthrough providers: the
+# upstream (llama-server, LM Studio, ...) decides which model is loaded and
+# CodeRouter never sends a model name. For those providers the historic
+# behaviour — returning the provider *name* — makes external benchmarks
+# indistinguishable across loaded GGUFs (the launcher_gui setup always
+# reported ``llama-cpp-local`` regardless of the selected model). We now ask
+# the upstream's own ``/models`` endpoint for its real model id(s) and
+# surface those instead.
+#
+# Guards: only for ``kind == "openai_compat"`` with ``model == ""``; a short
+# per-upstream TTL cache keeps repeated SDK probes cheap; ANY failure (refused
+# connection, timeout, unexpected shape) falls back to the historic
+# provider-name entry, so this is strictly additive. Providers with a
+# configured model keep the exact previous behaviour.
+
+_UPSTREAM_MODELS_TTL_S = 30.0
+_UPSTREAM_MODELS_TIMEOUT_S = 2.0
+# base_url -> (expires_monotonic, ids)
+_upstream_models_cache: dict[str, tuple[float, list[str]]] = {}
+
+
+async def _fetch_upstream_model_ids(base_url: str) -> list[str]:
+    """GET {base_url}/models and return the upstream model ids.
+
+    Raises on any transport / shape problem — the caller treats every
+    exception as "fall back to the provider-name entry".
+    """
+    import httpx  # local import keeps module import time flat
+
+    url = base_url.rstrip("/") + "/models"
+    async with httpx.AsyncClient(timeout=_UPSTREAM_MODELS_TIMEOUT_S) as client:
+        resp = await client.get(url)
+        resp.raise_for_status()
+        payload = resp.json()
+    ids = [
+        str(item["id"])
+        for item in payload.get("data", [])
+        if isinstance(item, dict) and item.get("id")
+    ]
+    if not ids:
+        raise ValueError(f"upstream {url} returned no model ids")
+    return ids
+
+
+async def _upstream_model_ids_cached(base_url: str) -> list[str]:
+    """TTL-cached wrapper around :func:`_fetch_upstream_model_ids`."""
+    now = time.monotonic()
+    hit = _upstream_models_cache.get(base_url)
+    if hit is not None and hit[0] > now:
+        return hit[1]
+    ids = await _fetch_upstream_model_ids(base_url)
+    _upstream_models_cache[base_url] = (now + _UPSTREAM_MODELS_TTL_S, ids)
+    return ids
+
+
 @router.get("/models")
 async def list_models(request: Request) -> dict[str, object]:
-    """Minimal /v1/models so OpenAI SDKs that probe it don't choke."""
+    """/v1/models: provider names, with upstream passthrough for empty-model
+    providers (see the passthrough note above)."""
     config = request.app.state.config
-    return {
-        "object": "list",
-        "data": [
+    created = int(time.time())
+    data: list[dict[str, object]] = []
+    for p in config.providers:
+        if p.model == "" and p.kind == "openai_compat":
+            try:
+                ids = await _upstream_model_ids_cached(str(p.base_url))
+            except Exception:  # any failure means "no passthrough"
+                logger.debug(
+                    "models passthrough failed; falling back to provider name",
+                    extra={"provider": p.name},
+                )
+            else:
+                data.extend(
+                    {
+                        "id": model_id,
+                        "object": "model",
+                        "created": created,
+                        "owned_by": f"coderouter/{p.name}",
+                    }
+                    for model_id in ids
+                )
+                continue
+        data.append(
             {
                 "id": p.name,
                 "object": "model",
-                "created": int(time.time()),
+                "created": created,
                 "owned_by": "coderouter",
             }
-            for p in config.providers
-        ],
-    }
+        )
+    return {"object": "list", "data": data}
 
 
 @router.post("/chat/completions", response_model=None)

coderouter/routing/fallback.py

@@ -1173,6 +1173,80 @@ class FallbackEngine:
         # v2.0-K: persistent state store (None = in-memory only).
         self._state_store: StateStore | None = None
 
+    def register_provider(
+        self, provider: ProviderConfig, profile_name: str = "launcher"
+    ) -> dict[str, Any]:
+        """Register (or update) a provider at runtime — launcher auto-sync.
+
+        Motivation: the embedded launcher can start a llama.cpp / vllm /
+        mlx backend on an arbitrary port, but routing is driven entirely
+        by providers.yaml — historically the operator had to hand-edit the
+        config or the new backend was simply unreachable (observed in the
+        wild as "launcher started on 8085, providers.yaml pointed at
+        8080"). This method closes that gap in-process:
+
+        - the provider entry is appended to ``config.providers`` (or, when
+          a provider with the same *name* already exists, its config entry
+          and cached adapter are REPLACED — the launcher restarting a
+          backend on the same port lands here),
+        - an adapter is built and cached alongside the static ones,
+        - the ``profile_name`` chain is created on demand, and the
+          provider is moved to the FRONT of that chain (most recently
+          launched backend wins the launcher profile).
+
+        Deliberately **in-memory only** — no providers.yaml rewrite. A
+        YAML round-trip would destroy operator comments (and a
+        comment-preserving writer means a new dependency), and the
+        launcher's process registry is itself in-memory by design: both
+        the process and its provider entry share the lifetime of this
+        server process. ``default_profile`` is never touched — routing to
+        the launcher profile stays an explicit opt-in
+        (``X-CodeRouter-Profile: launcher`` or body ``profile``).
+
+        Returns a small summary dict for the launcher API response.
+        """
+        from coderouter.config.schemas import FallbackChain
+
+        replaced = False
+        for i, existing in enumerate(self.config.providers):
+            if existing.name == provider.name:
+                self.config.providers[i] = provider
+                replaced = True
+                break
+        if not replaced:
+            self.config.providers.append(provider)
+        self._adapters[provider.name] = build_adapter(provider)
+
+        try:
+            chain = self.config.profile_by_name(profile_name)
+        except KeyError:
+            chain = FallbackChain(name=profile_name, providers=[provider.name])
+            self.config.profiles.append(chain)
+        else:
+            if provider.name in chain.providers:
+                chain.providers.remove(provider.name)
+            chain.providers.insert(0, provider.name)
+
+        logger.info(
+            "launcher provider sync: registered %s -> %s (profile %r)",
+            provider.name,
+            provider.base_url,
+            profile_name,
+            extra={
+                "provider": provider.name,
+                "base_url": str(provider.base_url),
+                "profile": profile_name,
+                "replaced": replaced,
+            },
+        )
+        return {
+            "provider": provider.name,
+            "base_url": str(provider.base_url),
+            "profile": profile_name,
+            "replaced": replaced,
+            "persisted": False,  # in-memory only, by design (see docstring)
+        }
+
     @property
     def plugins(self) -> PluginRegistry:
         """Return the plugin registry, lazily building an empty one if absent.

{coderouter_cli-2.7.3.dist-info → coderouter_cli-2.7.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: coderouter-cli
-Version: 2.7.3
+Version: 2.7.4
 Summary: Local-first, free-first, fallback-built-in LLM router. Claude Code / OpenAI compatible.
 Project-URL: Homepage, https://github.com/zephel01/CodeRouter
 Project-URL: Repository, https://github.com/zephel01/CodeRouter
@@ -220,6 +220,8 @@ providers:
 | **オプションプロファイル** | `providers.yaml` に名前付きプリセットを定義 → ドロップダウンで選択するだけ |
 | **複数プロセス管理** | llama.cpp と vllm を同時に起動し、ポートごとに独立管理 |
 | **ログビューア** | 各プロセスの stdout/stderr をブラウザ内でリアルタイム確認 |
+| **provider 自動同期** (v2.7.4) | 起動したバックエンドを provider として自動登録(`launcher-llamacpp-8085` 等)。providers.yaml 無編集で `X-CodeRouter-Profile: launcher` からルーティング可能。メモリ内のみ・serve と同寿命 |
+| **モデル名パススルー** (v2.7.4) | `model: ""` の provider は `/v1/models` が上流のロード中モデル ID(gguf 名)をそのまま返す。gguf を差し替えても config 編集不要 — 外部ベンチからモデルを識別できる |
 
 ```yaml
 # providers.yaml に追記するだけで有効になる

{coderouter_cli-2.7.3.dist-info → coderouter_cli-2.7.4.dist-info}/RECORD

@@ -41,9 +41,9 @@ coderouter/ingress/__init__.py,sha256=WQsCH2CGJCAhy0mS6GSEdeYZRkkQu2OHDsP4CJWTLu
 coderouter/ingress/anthropic_routes.py,sha256=1ThXzx8VgxRV7UCi3NF5ey7kbr0ADPKTXyQuYS5gK1w,27063
 coderouter/ingress/app.py,sha256=h6s-UWsbGP22rku4pPVlvRdrtbMj4KoEEUZoQQOrTTw,19370
 coderouter/ingress/dashboard_routes.py,sha256=1SqNNrVTfQiZcx5n2MvjAzWirittX0e61tCt-MKp4Ag,25617
-coderouter/ingress/launcher_routes.py,sha256=1bU245mEauCMpEOsq0LY-8FKKQIJWJhDe3CXgag_ut0,55968
+coderouter/ingress/launcher_routes.py,sha256=QzG0l0c2ZmAcQai3E-xs3cV5fUYf3ajjZauvI9pKDh4,57959
 coderouter/ingress/metrics_routes.py,sha256=M22dwOGn24P05Ge4W3c7d7mYytSGWjIR-pPSPOAiHJY,3965
-coderouter/ingress/openai_routes.py,sha256=Mjsk3jwot4qP9f5xshrmR1iuHMW-9sQdsfHMN_Sx5hc,9294
+coderouter/ingress/openai_routes.py,sha256=TrugsQNJfNPgKKLzfT1aXzrs4emWYGE4XebEBuaZoWk,12505
 coderouter/metrics/__init__.py,sha256=7Es351DPS7yLM0yVF_F0eesmiD83n7Zzhie44chht38,1465
 coderouter/metrics/collector.py,sha256=wdGuX5yOBWEHCz1KVIfaUBZP5NXW3U34yyYlLGwgoCE,61212
 coderouter/metrics/prometheus.py,sha256=THYkvrcpQK3ZNW-BV0h3O-PoT2ppNZ0dapQuu1nyHwE,24410
@@ -56,7 +56,7 @@ coderouter/routing/adaptive.py,sha256=G2o377twGSjbUh65wiIFx6klnpFGjsD_nI3oDvcBwh
 coderouter/routing/auto_router.py,sha256=y4v0c8u5F9f98Vmhx1vRcKPiOgAvpzbFqr6TIh058h0,13341
 coderouter/routing/budget.py,sha256=PblmVKJGs_BwNa9uDHAA8hmZ4XIVKv38mHAeU0V3OMs,8451
 coderouter/routing/capability.py,sha256=rRQhzTgQYFTFDNYcSLKvq3xjdw6B1w7T-3jS7PTMI14,27864
-coderouter/routing/fallback.py,sha256=vjnDv3z88v76ZnF2Sg1xYUOkKfe0jZm14OtoOrQA7Dc,139707
+coderouter/routing/fallback.py,sha256=L5hwe76DRlmHTR39dXafi27T5zRrgLlgX9uINddcSGk,142983
 coderouter/state/__init__.py,sha256=XoGcPmmBQSiZWML2S0juSveQ78xfhtdeCliNnVyzu7E,1088
 coderouter/state/audit_log.py,sha256=n7vuDsTfd5iuNUJhlRQPakJ2tMSsT9EfgPCzs1GEaac,10941
 coderouter/state/replay.py,sha256=Z_YHKroTKZdrL8qObFxcoLOAQWWXZvXFdLfxzvBhEJg,11230
@@ -67,8 +67,8 @@ coderouter/translation/__init__.py,sha256=PYXN7XVEwpG1uC8RLy6fvnGbzEZhhrEuUapH8I
 coderouter/translation/anthropic.py,sha256=aZkcYH4x82b0x7efJgJb9RWn9Hbyc9pEOthXe4vjUdU,11113
 coderouter/translation/convert.py,sha256=VV4kpu4dvLmGBmJfQnCLY5ryy_AnQcV2NuwjqRtaR8Q,52633
 coderouter/translation/tool_repair.py,sha256=DGOKArM53yfVbIfiAveoul1vGq9NEKmjagf43Qh4IkM,57630
-coderouter_cli-2.7.3.dist-info/METADATA,sha256=EqYCtqhIooSQ806Ps89T9XIxVKRhWHiyyTyJsMpu_Lg,14857
-coderouter_cli-2.7.3.dist-info/WHEEL,sha256=mffPy8wBnZQn2VnJUU5jE99KsxaSfiyMHV9Yt0aLVxs,87
-coderouter_cli-2.7.3.dist-info/entry_points.txt,sha256=-dnLfD1YZ2WjH2zSdNCvlO65wYltM9bsHt9Fhg3yGss,51
-coderouter_cli-2.7.3.dist-info/licenses/LICENSE,sha256=wkEzoR86jFw33jvfOHjULqmkGEfxTFMgMaJnpR8mPRw,1065
-coderouter_cli-2.7.3.dist-info/RECORD,,
+coderouter_cli-2.7.4.dist-info/METADATA,sha256=55ucKwRohGC6WEQr_NyGWjRjzhVgE7rOYgl4rfDNNkw,15388
+coderouter_cli-2.7.4.dist-info/WHEEL,sha256=mffPy8wBnZQn2VnJUU5jE99KsxaSfiyMHV9Yt0aLVxs,87
+coderouter_cli-2.7.4.dist-info/entry_points.txt,sha256=-dnLfD1YZ2WjH2zSdNCvlO65wYltM9bsHt9Fhg3yGss,51
+coderouter_cli-2.7.4.dist-info/licenses/LICENSE,sha256=wkEzoR86jFw33jvfOHjULqmkGEfxTFMgMaJnpR8mPRw,1065
+coderouter_cli-2.7.4.dist-info/RECORD,,