From 900e848522091bcdc82bdc33ebd6055be04bc1e2 Mon Sep 17 00:00:00 2001
From: Test <test@test.com>
Date: Fri, 20 Mar 2026 11:57:24 -0700
Subject: [PATCH] fix: infer provider from base URL for models.dev context
 length lookup

Custom endpoint users (DashScope/Alibaba, Z.AI, Kimi, DeepSeek, etc.)
get wrong context lengths because their provider resolves as "openrouter"
or "custom", skipping the models.dev lookup entirely. For example,
qwen3.5-plus on DashScope falls to the generic "qwen" hardcoded default
(131K) instead of the correct 1M.

Add _infer_provider_from_url() that maps known API hostnames to their
models.dev provider IDs. When the explicit provider is generic
(openrouter/custom/empty), infer from the base URL before the models.dev
lookup. This resolves context lengths correctly for DashScope, Z.AI,
Kimi, MiniMax, DeepSeek, and Nous endpoints without requiring users to
manually set context_length in config.

Also refactors _is_known_provider_base_url() to use the same URL mapping,
removing the duplicated hostname list.
---
 agent/model_metadata.py | 57 ++++++++++++++++++++++++++++++-----------
 1 file changed, 42 insertions(+), 15 deletions(-)

diff --git a/agent/model_metadata.py b/agent/model_metadata.py
index be63719e2..bea53611a 100644
--- a/agent/model_metadata.py
+++ b/agent/model_metadata.py
@@ -151,22 +151,41 @@ def _is_custom_endpoint(base_url: str) -> bool:
     return bool(normalized) and not _is_openrouter_base_url(normalized)
 
 
-def _is_known_provider_base_url(base_url: str) -> bool:
+_URL_TO_PROVIDER: Dict[str, str] = {
+    "api.openai.com": "openai",
+    "chatgpt.com": "openai",
+    "api.anthropic.com": "anthropic",
+    "api.z.ai": "zai",
+    "api.moonshot.ai": "kimi-coding",
+    "api.kimi.com": "kimi-coding",
+    "api.minimax": "minimax",
+    "dashscope.aliyuncs.com": "alibaba",
+    "openrouter.ai": "openrouter",
+    "inference-api.nousresearch.com": "nous",
+    "api.deepseek.com": "deepseek",
+}
+
+
+def _infer_provider_from_url(base_url: str) -> Optional[str]:
+    """Infer the models.dev provider name from a base URL.
+
+    This allows context length resolution via models.dev for custom endpoints
+    like DashScope (Alibaba), Z.AI, Kimi, etc. without requiring the user to
+    explicitly set the provider name in config.
+    """
     normalized = _normalize_base_url(base_url)
     if not normalized:
-        return False
+        return None
     parsed = urlparse(normalized if "://" in normalized else f"https://{normalized}")
     host = parsed.netloc.lower() or parsed.path.lower()
-    known_hosts = (
-        "api.openai.com",
-        "chatgpt.com",
-        "api.anthropic.com",
-        "api.z.ai",
-        "api.moonshot.ai",
-        "api.kimi.com",
-        "api.minimax",
-    )
-    return any(known_host in host for known_host in known_hosts)
+    for url_part, provider in _URL_TO_PROVIDER.items():
+        if url_part in host:
+            return provider
+    return None
+
+
+def _is_known_provider_base_url(base_url: str) -> bool:
+    return _infer_provider_from_url(base_url) is not None
 
 
 def is_local_endpoint(base_url: str) -> bool:
@@ -808,13 +827,21 @@ def get_model_context_length(
     # These are provider-specific and take priority over the generic OR cache,
     # since the same model can have different context limits per provider
     # (e.g. claude-opus-4.6 is 1M on Anthropic but 128K on GitHub Copilot).
-    if provider == "nous":
+    # If provider is generic (openrouter/custom/empty), try to infer from URL.
+    effective_provider = provider
+    if not effective_provider or effective_provider in ("openrouter", "custom"):
+        if base_url:
+            inferred = _infer_provider_from_url(base_url)
+            if inferred:
+                effective_provider = inferred
+
+    if effective_provider == "nous":
         ctx = _resolve_nous_context_length(model)
         if ctx:
             return ctx
-    if provider:
+    if effective_provider:
         from agent.models_dev import lookup_models_dev_context
-        ctx = lookup_models_dev_context(provider, model)
+        ctx = lookup_models_dev_context(effective_provider, model)
         if ctx:
             return ctx