eggpool 0.7.1__tar.gz → 0.7.2__tar.gz

{eggpool-0.7.1 → eggpool-0.7.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: eggpool
-Version: 0.7.1
+Version: 0.7.2
 Summary: A lightweight proxy that aggregates multiple LLM provider accounts behind an OpenAI Chat Completions-compatible endpoint
 Project-URL: Homepage, https://github.com/eggstack/eggpool
 Project-URL: Repository, https://github.com/eggstack/eggpool

{eggpool-0.7.1 → eggpool-0.7.2}/config.example.toml

@@ -109,6 +109,11 @@ catalog_withdrawal_policy = "preserve_until_health"
 loss_policy = "warn"      # "warn" or "reject" for loss-of-information
 prefer_native = true      # prefer native-protocol accounts in routing
 
+# Thinking/reasoning transcoding is enabled by default. Set this to false to
+# drop thinking controls and content instead of translating them.
+# [transcoder.features]
+# thinking = false
+
 # Global effort→budget token mapping for thinking/reasoning.
 # Values are used when the model's capability does not carry a
 # per-model effort_to_budget_tokens mapping.
@@ -449,7 +454,8 @@ enabled = false
 # header = "Authorization"
 # scheme = "Bearer"
 #
-# # OpenCode Go exposes low/medium/high thinking controls for mimo-v2.5.
+# # OpenCode Go exposes low/medium/high thinking controls for mimo-v2.5 and
+# # minimal/low/medium/high/xhigh for muse-spark-1.2-contributor.
 # [providers.opencode-go.model_capabilities."mimo-v2.5".thinking]
 # status = "supported"
 # source = "provider_catalog"

{eggpool-0.7.1 → eggpool-0.7.2}/docs/thinking.md

@@ -28,16 +28,19 @@ Status values (`CapabilityStatus`):
 
 Source: `src/eggpool/catalog/capabilities.py:36-44`
 
-## 2. Enabling Thinking Transcoding
+## 2. Thinking Transcoding
 
-Thinking transcoding is **off by default**. The feature gate lives in `[transcoder.features]`:
+Thinking transcoding is **enabled by default**. No configuration is required.
+To disable it, set the feature gate in `[transcoder.features]`:
 
 ```toml
 [transcoder.features]
-thinking = true
+thinking = false
 ```
 
-When `thinking = false` (the default), the transcoder **drops** thinking-related fields with a structured `reasoning_content_dropped` warning rather than forwarding them. Specifically:
+When `thinking = false`, the transcoder **drops** thinking-related fields with a
+structured `reasoning_content_dropped` warning rather than forwarding them.
+Specifically:
 
 - **OpenAI → Anthropic**: `reasoning_content` in assistant messages is dropped.
 - **Anthropic → OpenAI**: `thinking` content blocks are dropped.
@@ -63,7 +66,7 @@ Source: `src/eggpool/transcoder/policy.py:217-225`
 
 ```toml
 [transcoder.features]
-thinking = true          # Enable thinking/reasoning transcoding (default: false)
+thinking = true          # Enable thinking/reasoning transcoding (default: true)
 ```
 
 ### Budget Defaults
@@ -500,9 +503,10 @@ Source: `src/eggpool/metrics/thinking.py`, `src/eggpool/api/stats.py:452-463`, `
 
 **Symptoms:** Client sends `reasoning_effort` but the upstream receives no thinking controls.
 
-**Cause:** Thinking transcoding is disabled. The feature gate `[transcoder.features]` defaults to `thinking = false`.
+**Cause:** Thinking transcoding was explicitly disabled with
+`[transcoder.features].thinking = false`.
 
-**Fix:** Enable the feature:
+**Fix:** Remove the override or enable the feature:
 
 ```toml
 [transcoder.features]
@@ -562,7 +566,7 @@ native_protocols = ["anthropic"]
 
 **Cause:** Thinking transcoding is likely disabled for streaming. The feature gate affects both streaming and non-streaming paths.
 
-**Fix:** Ensure `[transcoder.features] thinking = true` is set. Check `[transcoder.openai_reasoning_fields]` to verify the streaming delta field name matches your client's expectations (default: `"reasoning"`).
+**Fix:** Remove the disabling override or ensure `[transcoder.features] thinking = true` is set. Check `[transcoder.openai_reasoning_fields]` to verify the streaming delta field name matches your client's expectations (default: `"reasoning"`).
 
 ---
 

{eggpool-0.7.1 → eggpool-0.7.2}/docs/transcoding.md

@@ -59,8 +59,8 @@ prefer_native = true
 tools = true
 # Image / document content parts (default: false)
 vision = false
-# Extended thinking blocks ↔ reasoning_content (default: false)
-thinking = false
+# Extended thinking blocks ↔ reasoning_content (default: true)
+thinking = true
 # OpenAI response_format / json_schema coercion (default: false)
 structured_outputs = false
 # Anthropic-only primitives explicit handling (default: false)

{eggpool-0.7.1 → eggpool-0.7.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "eggpool"
-version = "0.7.1"
+version = "0.7.2"
 description = "A lightweight proxy that aggregates multiple LLM provider accounts behind an OpenAI Chat Completions-compatible endpoint"
 readme = "README.md"
 requires-python = ">=3.11"

{eggpool-0.7.1 → eggpool-0.7.2}/src/eggpool/_share/config.example.toml

@@ -104,6 +104,11 @@ catalog_withdrawal_policy = "preserve_until_health"
 loss_policy = "warn"      # "warn" or "reject" for loss-of-information
 prefer_native = true      # prefer native-protocol accounts in routing
 
+# Thinking/reasoning transcoding is enabled by default. Set this to false to
+# drop thinking controls and content instead of translating them.
+# [transcoder.features]
+# thinking = false
+
 # Global effort→budget token mapping for thinking/reasoning.
 # Values are used when the model's capability does not carry a
 # per-model effort_to_budget_tokens mapping.
@@ -435,7 +440,8 @@ enabled = false
 # header = "Authorization"
 # scheme = "Bearer"
 #
-# # OpenCode Go exposes low/medium/high thinking controls for mimo-v2.5.
+# # OpenCode Go exposes low/medium/high thinking controls for mimo-v2.5 and
+# # minimal/low/medium/high/xhigh for muse-spark-1.2-contributor.
 # [providers.opencode-go.model_capabilities."mimo-v2.5".thinking]
 # status = "supported"
 # source = "provider_catalog"
@@ -914,4 +920,3 @@ protocol = "anthropic"
 
 [model_overrides."claude-sonnet-4"]
 protocol = "anthropic"
-

{eggpool-0.7.1 → eggpool-0.7.2}/src/eggpool/catalog/models_dev.py

@@ -21,6 +21,7 @@ MODELS_DEV_BASE_URL = "https://models.dev"
 OPENCODE_GO_MODELS_DEV_PROVIDER_ID = "opencode-go"
 OPENCODE_COMPATIBLE_EFFORTS = ["low", "medium", "high"]
 _EFFORT_BUDGET_DEFAULTS = {
+    "minimal": 1024,
     "low": 1024,
     "medium": 4096,
     "high": 16384,
@@ -116,6 +117,33 @@ def derive_opencode_go_supported_efforts(
     """
     if metadata.get("reasoning") is not True:
         return []
+
+    # models.dev mirrors OpenCode's provider catalog and can carry the exact
+    # effort set for newer models. Prefer it when present so newly released
+    # levels (for example Muse Spark's ``xhigh``) are not silently dropped.
+    reasoning_options = metadata.get("reasoning_options")
+    if isinstance(reasoning_options, list):
+        efforts: list[str] = []
+        for option in cast("list[object]", reasoning_options):
+            if not isinstance(option, dict):
+                continue
+            option_dict = cast("dict[str, object]", option)
+            if option_dict.get("type") != "effort":
+                continue
+            values = option_dict.get("values")
+            if not isinstance(values, list):
+                continue
+            for value in cast("list[object]", values):
+                if not isinstance(value, str):
+                    continue
+                effort = value.strip().lower()
+                if effort == "med":
+                    effort = "medium"
+                if effort and effort not in efforts:
+                    efforts.append(effort)
+        if efforts:
+            return efforts
+
     lowered = model_id.lower()
     if "deepseek-v4" in lowered:
         return [*OPENCODE_COMPATIBLE_EFFORTS, "max"]

{eggpool-0.7.1 → eggpool-0.7.2}/src/eggpool/models/config.py

@@ -1174,31 +1174,64 @@ class ModelCapabilitiesOverrideConfig(BaseModel):
 
 
 _OPENCODE_GO_BASE_URL = "https://opencode.ai/zen/go/v1"
-_OPENCODE_GO_THINKING_MODELS: frozenset[str] = frozenset({"mimo-v2.5", "minimax-m3"})
+_OPENCODE_GO_THINKING_MODELS: frozenset[str] = frozenset(
+    {"mimo-v2.5", "minimax-m3", "muse-spark-1.2-contributor"}
+)
+_OPENCODE_GO_THINKING_EFFORTS: dict[str, list[str]] = {
+    "muse-spark-1.2-contributor": ["minimal", "low", "medium", "high", "xhigh"],
+}
+_OPENCODE_GO_EFFORT_BUDGETS: dict[str, int] = {
+    "minimal": 1024,
+    "low": 1024,
+    "med": 4096,
+    "medium": 4096,
+    "high": 16384,
+    "xhigh": 24576,
+}
 
 
 def _default_opencode_go_thinking_capabilities() -> dict[
     str, ModelCapabilitiesOverrideConfig
 ]:
     """Return built-in capability metadata for the canonical OpenCode Go host."""
-    return {
-        model_id: ModelCapabilitiesOverrideConfig(
+    model_efforts = {
+        model_id: _OPENCODE_GO_THINKING_EFFORTS.get(
+            model_id,
+            ["low", "medium", "high"],
+        )
+        for model_id in _OPENCODE_GO_THINKING_MODELS
+    }
+    result: dict[str, ModelCapabilitiesOverrideConfig] = {}
+    for model_id, efforts in model_efforts.items():
+        effort_to_budget = {
+            effort: _OPENCODE_GO_EFFORT_BUDGETS[effort]
+            for effort in efforts
+            if effort in _OPENCODE_GO_EFFORT_BUDGETS
+        }
+        # Keep the historical ``med`` alias for the original built-in
+        # contracts. Muse's advertised set uses the canonical ``medium``.
+        if model_id != "muse-spark-1.2-contributor":
+            effort_to_budget["med"] = _OPENCODE_GO_EFFORT_BUDGETS["med"]
+        result[model_id] = ModelCapabilitiesOverrideConfig(
             thinking=ThinkingCapabilityOverrideConfig(
                 status="supported",
                 source="provider_catalog",
-                native_protocols=["openai", "anthropic"],
-                supported_efforts=["low", "medium", "high"],
-                effort_to_budget_tokens={
-                    "low": 1024,
-                    "med": 4096,
-                    "medium": 4096,
-                    "high": 16384,
-                },
-                notes="OpenCode Go exposes low/medium/high thinking controls.",
+                native_protocols=(
+                    ["anthropic"]
+                    if model_id == "muse-spark-1.2-contributor"
+                    else ["openai", "anthropic"]
+                ),
+                supported_efforts=efforts,
+                effort_to_budget_tokens=effort_to_budget,
+                notes=(
+                    "OpenCode Go exposes minimal/low/medium/high/xhigh thinking "
+                    "controls."
+                    if model_id == "muse-spark-1.2-contributor"
+                    else "OpenCode Go exposes low/medium/high thinking controls."
+                ),
             )
         )
-        for model_id in _OPENCODE_GO_THINKING_MODELS
-    }
+    return result
 
 
 def _provider_is_canonical_opencode_go(provider: ProviderConfig) -> bool:

{eggpool-0.7.1 → eggpool-0.7.2}/src/eggpool/request/provider_bound_request.py

@@ -162,6 +162,28 @@ class ProviderBoundRequest:
     _serialized_generation: int | None = field(default=None, repr=False)
     _frozen: bool = field(default=False, repr=False)
 
+    def __post_init__(self) -> None:
+        """Normalize EggPool's provider namespace out of the model field.
+
+        The public ``/v1/models`` surface exposes provider-scoped IDs such as
+        ``minimax-m3/opencode-go``. That suffix belongs to EggPool's routing
+        namespace; upstream providers only receive the base model ID. Keep
+        this invariant on the shared provider-bound object so native requests
+        (which do not run a transcode preflight) are protected as well as
+        translated and legacy requests.
+
+        ``client_payload`` remains untouched so the original client request
+        is still available for diagnostics and response adaptation.
+        """
+        model_value = self.client_payload.get("model")
+        if not isinstance(model_value, str) or not self.model_id:
+            return
+        if not model_value.startswith(f"{self.model_id}/"):
+            return
+        normalized = dict(self.client_payload)
+        normalized["model"] = self.model_id
+        self.set_provider_payload(normalized, increment_generation=False)
+
     @property
     def provider_payload(self) -> Mapping[str, Any]:
         """Return the decoded provider-bound payload.

{eggpool-0.7.1 → eggpool-0.7.2}/src/eggpool/transcoder/builtin_contracts.py

@@ -61,6 +61,48 @@ class BuiltinProviderContract:
     contract: ThinkingControlContract
 
 
+# ---------------------------------------------------------------------------
+# OpenCode Go Muse Spark 1.2 Contributor contract
+# ---------------------------------------------------------------------------
+# The OpenCode Go model list does not include capability metadata, so this
+# endpoint needs a curated contract for the Anthropic Messages path. The
+# effort vocabulary is mirrored from the current models.dev/OpenCode model
+# record, including the newer ``minimal`` and ``xhigh`` levels.
+_OPENCODE_GO_MUSE_CONTRACT = BuiltinProviderContract(
+    key=ProviderContractKey(
+        provider_id_pattern=r"^opencode-go$",
+        model_id_pattern=r"^muse-spark-1\.2-contributor$",
+        protocol="anthropic",
+        priority=10,
+    ),
+    contract=ThinkingControlContract(
+        mode="effort_or_budget",
+        request_fields=["thinking", "reasoning_effort"],
+        accepted_efforts=["minimal", "low", "medium", "high", "xhigh"],
+        effort_to_budget_tokens={
+            "minimal": 1024,
+            "low": 1024,
+            "medium": 4096,
+            "high": 16384,
+            "xhigh": 24576,
+        },
+        explicit_budget_min=1024,
+        explicit_budget_max=131072,
+        historical_reasoning_content="accepted",
+        source="provider_catalog",
+    ),
+)
+
+_OPENCODE_GO_MUSE_URL_COMPAT_CONTRACT = BuiltinProviderContract(
+    key=ProviderContractKey(
+        provider_base_url_pattern=r".*opencode\.ai/zen/go/v1.*",
+        model_id_pattern=r"^muse-spark-1\.2-contributor$",
+        protocol="anthropic",
+        priority=10,
+    ),
+    contract=_OPENCODE_GO_MUSE_CONTRACT.contract,
+)
+
 # ---------------------------------------------------------------------------
 # OpenCode Go MiniMax-M3 contract
 # ---------------------------------------------------------------------------
@@ -171,6 +213,8 @@ _OPENAI_NATIVE_CONTRACT = BuiltinProviderContract(
 
 # All built-in contracts, in declaration order (used for iteration).
 BUILTIN_CONTRACTS: tuple[BuiltinProviderContract, ...] = (
+    _OPENCODE_GO_MUSE_CONTRACT,
+    _OPENCODE_GO_MUSE_URL_COMPAT_CONTRACT,
     _OPENCODE_GO_MINIMAX_CONTRACT,
     _MINIMAX_NATIVE_CONTRACT,
     _OPENCODE_GO_URL_COMPAT_CONTRACT,

{eggpool-0.7.1 → eggpool-0.7.2}/src/eggpool/transcoder/policy.py

@@ -97,12 +97,14 @@ class CapabilityPolicy(BaseModel):
 
 
 class TranscoderFeatures(BaseModel):
-    """Per-feature opt-in flags for Phase 6 sub-phases.
-
-    Optional semantic extensions are **off** by default. Tool calling is
-    baseline protocol compatibility and is always translated when a
-    cross-protocol request is selected; its legacy ``tools`` switch is kept
-    only so old configuration files continue to parse.
+    """Per-feature flags for Phase 6 sub-phases.
+
+    Thinking is enabled by default because it is part of the supported
+    cross-protocol reasoning path. Other optional semantic extensions remain
+    off by default. Tool calling is baseline protocol compatibility and is
+    always translated when a cross-protocol request is selected; its legacy
+    ``tools`` switch is kept only so old configuration files continue to
+    parse.
     """
 
     model_config = ConfigDict(extra="forbid")
@@ -123,11 +125,12 @@ class TranscoderFeatures(BaseModel):
         ),
     )
     thinking: bool = Field(
-        default=False,
+        default=True,
         description=(
             "Extended thinking / reasoning blocks. When enabled, Anthropic "
             "thinking blocks are translated to OpenAI reasoning_content and "
-            "vice versa."
+            "vice versa. Enabled by default; set false to drop thinking "
+            "controls and content."
         ),
     )
     structured_outputs: bool = Field(
@@ -277,8 +280,8 @@ class TranscoderPolicy(BaseModel):
     features: TranscoderFeatures = Field(
         default_factory=TranscoderFeatures,
         description=(
-            "Per-feature opt-in flags for Phase 6 sub-phases. Each flag "
-            "defaults to false; enable individual features as needed."
+            "Per-feature flags for Phase 6 sub-phases. Thinking is enabled "
+            "by default; other optional features remain opt-in."
         ),
     )
 

{eggpool-0.7.1 → eggpool-0.7.2}/uv.lock

@@ -178,7 +178,7 @@ toml = [
 
 [[package]]
 name = "eggpool"
-version = "0.7.1"
+version = "0.7.2"
 source = { editable = "." }
 dependencies = [
     { name = "aiosqlite" },