coderouter-cli 2.9.2__py3-none-any.whl → 2.9.4__py3-none-any.whl

coderouter/config/schemas.py

@@ -1460,6 +1460,49 @@ class LauncherOptionProfile(BaseModel):
     )
 
 
+class LauncherBenchConfig(BaseModel):
+    """The ``launcher.bench:`` block — defaults for the bench sweep feature.
+
+    設計 §4.1。デバイス構成スイープ(起動→readiness→外部ベンチ→停止→次)の
+    既定値を providers.yaml から供給する。未設定(``LauncherConfig.bench`` が
+    None)ならスイープ UI はハードコード既定を使う(完全後方互換)。すべての
+    フィールドに ``default`` があるので、既存 YAML は無改変で通過する。
+    """
+
+    model_config = ConfigDict(extra="forbid")
+
+    command_template: str = Field(
+        default="llmbench run --model local-openai --runs {runs}",
+        description=(
+            "外部ベンチコマンドのテンプレ。``{port}`` ``{config}`` "
+            "``{base_url}`` ``{results_dir}`` ``{runs}`` を単純置換で展開して "
+            "argv 化する(``str.format`` ではないので JSON 波括弧で誤爆しない)。"
+        ),
+    )
+    runs: int = Field(
+        default=5,
+        ge=1,
+        le=1000,
+        description="1 構成あたりのベンチ実行回数。``{runs}`` に展開される。",
+    )
+    results_dir: str | None = Field(
+        default=None,
+        description=(
+            "llmbench の results/ ディレクトリ。相対はサーバ CWD 基準。"
+            "設定時のみスイープ結果 JSON を読み比較サマリを付与する。"
+        ),
+    )
+    readiness_timeout_s: float = Field(
+        default=300.0,
+        ge=5.0,
+        le=3600.0,
+        description=(
+            "スイープの各構成でサーバが ready になるのを待つ最大秒数。"
+            "大きな GGUF ロードを考慮した既定 5 分。"
+        ),
+    )
+
+
 class SwapModelSpec(BaseModel):
     """One entry in ``launcher.swap.models`` (docs/designs/launcher-model-swap.md).
 
@@ -1518,10 +1561,25 @@ class SwapModelSpec(BaseModel):
         le=65535,
         description=(
             "Fixed port (recommended — §10 Q2). When unset, the swap "
-            "manager picks an OS-assigned ephemeral port and retries "
-            "once on a different port if the backend fails to become "
-            "ready. Best-effort only — no strong TOCTOU guarantee "
-            "(§6.6 known-trap #4)."
+            "manager picks an OS-assigned ephemeral port and retries, "
+            "each time on a freshly picked port, up to "
+            "``LauncherSwapConfig.port_retry_attempts`` additional "
+            "times if the backend fails to become ready. Best-effort "
+            "only — no strong TOCTOU guarantee (§6.6 known-trap #4)."
+        ),
+    )
+    ttl_seconds: float | None = Field(
+        default=None,
+        ge=0.0,
+        description=(
+            "[Unreleased] Per-model override of "
+            "``LauncherSwapConfig.ttl_seconds``. ``None`` (default) = "
+            "use the global value. ``0`` = unload as soon as the last "
+            "in-flight lease for THIS model releases — same meaning as "
+            "the global field's ``0``, just scoped to one catalog "
+            "entry. Lets a large/expensive model unload sooner (or "
+            "stay resident longer) than the rest of the catalog "
+            "without changing the global default."
         ),
     )
     option_profile: str | None = Field(
@@ -1611,8 +1669,10 @@ class LauncherSwapConfig(BaseModel):
             "Seconds of no in-flight requests after which an idle swap "
             "process is auto-stopped. None = TTL disabled (runs until "
             "explicitly stopped). 0 = unload as soon as the last "
-            "in-flight lease releases. §10 Q1: one GLOBAL value for "
-            "Phase 1 — no per-model override yet."
+            "in-flight lease releases. §10 Q1: this is the GLOBAL "
+            "default; a catalog entry's ``SwapModelSpec.ttl_seconds`` "
+            "overrides it for that one model when set "
+            "([Unreleased] per-model TTL override)."
         ),
     )
     readiness_timeout_s: float = Field(
@@ -1631,6 +1691,24 @@ class LauncherSwapConfig(BaseModel):
         le=600.0,
         description="How often the TTL sweeper background task scans for idle processes.",
     )
+    port_retry_attempts: int = Field(
+        default=2,
+        ge=0,
+        le=5,
+        description=(
+            "[Unreleased] Number of ADDITIONAL spawn attempts (each on a "
+            "freshly picked ephemeral port) after the first, used only "
+            "when a catalog entry's ``port`` is unset and the previous "
+            "attempt fails to become ready. 0 = no retry. Ignored when "
+            "``port`` is set — a fixed port never retries (a second "
+            "attempt would just collide on the same port again). This "
+            "does not close the pick-then-bind TOCTOU window (see "
+            "``coderouter.launcher_swap._pick_ephemeral_port``); it only "
+            "bounds how many times the swap manager re-rolls the dice. "
+            "A fixed ``port`` remains the recommended way to eliminate "
+            "the race entirely (§10 Q2)."
+        ),
+    )
     inject_auto_router_rules: bool = Field(
         default=True,
         description=(
@@ -1828,6 +1906,13 @@ class LauncherConfig(BaseModel):
             "behavior."
         ),
     )
+    bench: LauncherBenchConfig | None = Field(
+        default=None,
+        description=(
+            "デバイス構成ベンチスイープ(設計 §4)の既定値。None(既定)なら "
+            "スイープ UI はハードコード既定を使う=完全後方互換。"
+        ),
+    )
 
     @model_validator(mode="after")
     def _check_auto_restart_backoff_ordered(self) -> LauncherConfig: