fix: reject broken configs and improve accuracy feedback with isolated agent state

modelhub_submmit_api/failure_taxonomy.py

@@ -67,7 +67,7 @@ PLATFORM_PATTERNS = (
     (re.compile(r"welcome\.sh: No such file|data: command not found", re.I), "broken_platform_launch_script"),
     (re.compile(r"id_rsa.*No such file", re.I), "missing_platform_credential"),
     (re.compile(r"找不到空闲卡|no idle (?:gpu|card)", re.I), "no_idle_device"),
-    (re.compile(r"storage|download.*timed? out|connection reset", re.I), "platform_io_transient"),
+    (re.compile(r"no space left on device|download.*timed? out|connection reset", re.I), "platform_io_transient"),
 )
 
 DETERMINISTIC_LOG_PATTERNS = (
@@ -80,6 +80,8 @@ DETERMINISTIC_LOG_PATTERNS = (
 # semantics. Generic messages such as "attention backend not supported" or
 # "GPU type not supported" must not create an architecture blacklist.
 EXPLICIT_FRAMEWORK_MODEL_UNSUPPORTED_PATTERNS = (
+    re.compile(r"model type\s+[`'\"][^`'\"]+[`'\"].{0,100}does not recognize this architecture", re.I),
+    re.compile(r"Model architectures?\s*\[[^\]\n]+\]\s*(?:are|is) not supported", re.I),
     re.compile(
         r"(?:当前|该|此)(?:推理)?框架.{0,100}(?:不支持|暂不支持|无法支持|不兼容)"
         r".{0,100}(?:该|此|当前)?(?:模型架构|模型|架构)",
@@ -117,19 +119,16 @@ def classify_failure_report(report_code: str | None, log_lines: Iterable[str] =
     code = str(report_code or "").strip().upper()
     text = "\n".join(str(line) for line in log_lines)
 
-    # Infrastructure signatures override broad report codes such as
-    # EXECUTE_EMPTY_RESULT so they do not poison model compatibility feedback.
-    for pattern, reason in PLATFORM_PATTERNS:
-        if pattern.search(text):
-            return FailureClassification(
-                "platform_infrastructure",
-                "gpu_framework",
-                "open_short_gpu_framework_circuit_and_retry_other_models",
-                True,
-                False,
-                reason,
-            )
-
+    if re.search(r'exec:.*entrypoint.*(?:no such file|not found)', text, re.I):
+        return FailureClassification(
+            "configuration_launch", "configuration", "reject_broken_config", True, False,
+            "invalid_executable_argv",
+        )
+    if re.search(r'quantization method .*not supported for the current GPU', text, re.I):
+        return FailureClassification(
+            "quantization_compatibility", "model_gpu_framework", "reject_quantization_route",
+            True, False, "explicit_quantization_gpu_incompatibility",
+        )
     if code in DETERMINISTIC_POLICIES:
         return DETERMINISTIC_POLICIES[code]
     for pattern, inferred_code in DETERMINISTIC_LOG_PATTERNS:
@@ -149,6 +148,15 @@ def classify_failure_report(report_code: str | None, log_lines: Iterable[str] =
         )
     if code in SEMANTIC_POLICIES:
         return SEMANTIC_POLICIES[code]
+    # Fall back to infrastructure signatures only after specific root causes.
+    # Logs may include a transient allocation failure before a model starts.
+    for pattern, reason in PLATFORM_PATTERNS:
+        if pattern.search(text):
+            return FailureClassification(
+                "platform_infrastructure", "gpu_framework",
+                "open_short_gpu_framework_circuit_and_retry_other_models",
+                True, False, reason,
+            )
     return FailureClassification(
         "ambiguous_runtime",
         "unknown",