fix(llm): isolate invalid output failures and trace argument streams

artemis/llm/argument_fingerprint.py

@@ -0,0 +1,53 @@
+"""Bounded fingerprints of received argument deltas, without retaining text."""
+
+import hashlib
+
+
+PREFIX_BYTES = 4096
+MAX_PREFIXES = 16
+MAX_TRACKED_TOOLS = 64
+
+
+class ArgumentFingerprint:
+    def __init__(self):
+        self.characters = 0
+        self.bytes = 0
+        self.deltas = 0
+        self.encoding_valid = True
+        self.digest = hashlib.sha256()
+        self.prefixes: list[dict] = []
+
+    def observe(self, arguments: str) -> None:
+        self.characters += len(arguments)
+        if not arguments:
+            return
+        self.deltas += 1
+        if not self.encoding_valid:
+            return
+        try:
+            encoded = arguments.encode("utf-8")
+        except UnicodeEncodeError:
+            # Diagnostics must not repair, reject or otherwise alter the stream.
+            self.encoding_valid = False
+            return
+        offset = 0
+        while offset < len(encoded) and len(self.prefixes) < MAX_PREFIXES:
+            size = min(PREFIX_BYTES - self.bytes % PREFIX_BYTES, len(encoded) - offset)
+            self.digest.update(encoded[offset : offset + size])
+            self.bytes += size
+            offset += size
+            if self.bytes % PREFIX_BYTES == 0:
+                self.prefixes.append({"bytes": self.bytes, "sha256": self.digest.hexdigest()})
+        if offset < len(encoded):
+            self.digest.update(encoded[offset:])
+            self.bytes += len(encoded) - offset
+
+    def snapshot(self) -> dict:
+        return {
+            "argument_chars": self.characters,
+            "argument_bytes": self.bytes if self.encoding_valid else None,
+            "argument_sha256": self.digest.hexdigest() if self.encoding_valid else None,
+            "argument_deltas": self.deltas,
+            "argument_prefixes": [dict(prefix) for prefix in self.prefixes],
+            "argument_encoding_valid": self.encoding_valid,
+        }

artemis/llm/diagnostics.py

@@ -13,6 +13,7 @@ from uuid import uuid4
 from PIL import Image
 
 from artemis.data_engine.context_vars import CURRENT_NODE_NAME, CURRENT_TRACE_ID
+from artemis.llm.argument_fingerprint import ArgumentFingerprint, MAX_TRACKED_TOOLS
 from artemis.llm.final_review import ACTIVE_FINAL_REVIEW, FinalReviewBudgetExceeded
 from artemis.llm.reliability import LLMExhaustedError
 from artemis.llm.usage import usage_from_message
@@ -107,6 +108,7 @@ class RequestAttempt:
         self.clock = time.monotonic()
         self.last_publish = self.clock
         self.tools: dict[int | str, dict] = {}
+        self.tool_fingerprints: dict[int | str, ArgumentFingerprint] = {}
         self.review = ACTIVE_FINAL_REVIEW.get()
         if self.review:
             self.review.request_started(request_id, attempt)
@@ -126,6 +128,9 @@ class RequestAttempt:
             "usage": None,
             "output_chunks": 0,
             "tool_argument_chars": 0,
+            "tool_observation_layer": "langchain_tool_call_chunks",
+            "argument_fingerprint_version": 1,
+            "tool_stats_truncated": False,
             "tools": [],
             "step_id": str(self.step_id) if self.step_id else None,
             "parent_trace_id": str(self.parent_id) if self.parent_id else None,
@@ -167,9 +172,10 @@ class RequestAttempt:
         self.data.update(
             headers_at=time.time(),
             http_status=response.status_code,
-            server_request_id=_identifier(
-                response.headers.get("x-request-id") or response.headers.get("request-id")
-            ),
+            server_request_id=_identifier(response.headers.get("x-oneapi-request-id"))
+            or _identifier(response.headers.get("x-request-id"))
+            or _identifier(response.headers.get("request-id")),
+            response_x_request_id=_identifier(response.headers.get("x-request-id")),
             server_trace_id=_identifier(response.headers.get("x-trace-id")),
             phase="waiting_output",
         )
@@ -196,18 +202,31 @@ class RequestAttempt:
             self.data["usage"] = usage
         tool_chunks = getattr(chunk, "tool_call_chunks", None) or []
         # Responses exposes the same argument delta in content and tool_call_chunks.
-        # Count only the latter; retain lengths/names, never argument bodies.
+        # Count only the latter; retain bounded fingerprints, never argument bodies.
         for tool in tool_chunks:
+            arguments = tool.get("args")
+            if isinstance(arguments, str):
+                self.data["tool_argument_chars"] += len(arguments)
             index = tool.get("index")
-            key = index if index is not None else tool.get("id") or "unknown"
-            stats = self.tools.setdefault(key, {"name": None, "argument_chars": 0})
+            call_id = _identifier(tool.get("id"))
+            key = index if index is not None else call_id or "unknown"
+            if key not in self.tools and len(self.tools) >= MAX_TRACKED_TOOLS:
+                self.data["tool_stats_truncated"] = True
+                continue
+            stats = self.tools.setdefault(key, {"name": None})
+            if call_id:
+                stats["call_id"] = call_id
+            if index is not None:
+                stats["chunk_index"] = index
             name = tool.get("name")
             if isinstance(name, str) and re.fullmatch(r"[\w.:-]{1,128}", name):
                 stats["name"] = name
-            arguments = tool.get("args")
+            fingerprint = self.tool_fingerprints.get(key)
+            if fingerprint is None:
+                fingerprint = self.tool_fingerprints[key] = ArgumentFingerprint()
             if isinstance(arguments, str):
-                stats["argument_chars"] += len(arguments)
-                self.data["tool_argument_chars"] += len(arguments)
+                fingerprint.observe(arguments)
+            stats.update(fingerprint.snapshot())
         self.data["tools"] = list(self.tools.values())
         content = getattr(chunk, "content", None)
         substantive = isinstance(content, str) and bool(content)
@@ -252,7 +271,9 @@ class RequestAttempt:
             if isinstance(status, int):
                 self.data["http_status"] = status
             if request_id := _identifier(getattr(error, "request_id", None)):
-                self.data["server_request_id"] = request_id
+                self.data["error_request_id"] = request_id
+                if not self.data.get("server_request_id"):
+                    self.data["server_request_id"] = request_id
             if category == "timeout":
                 self.data.setdefault("timeout_scope", "transport")
         if response is not None:
@@ -301,6 +322,7 @@ async def observe_request_headers(request):
     if attempt is None:
         return
     request.headers.setdefault("X-Client-Request-Id", attempt.data["request_id"])
+    request.headers.setdefault("X-Client-Attempt-Id", attempt.data["attempt_id"])
     routing = {}
     for name in ("thread-id", "thread_id", "session-id", "session_id"):
         value = request.headers.get(name)
@@ -309,9 +331,12 @@ async def observe_request_headers(request):
     attempt.data.update(
         request_sent_at=time.time(),
         client_request_id=_identifier(request.headers.get("X-Client-Request-Id")),
+        client_attempt_id=_identifier(request.headers.get("X-Client-Attempt-Id")),
         routing_header_fingerprints=routing,
         client_request_id_matches=request.headers.get("X-Client-Request-Id")
         == attempt.data["request_id"],
+        client_attempt_id_matches=request.headers.get("X-Client-Attempt-Id")
+        == attempt.data["attempt_id"],
     )
     attempt.publish()
 

artemis/llm/reliability.py

@@ -153,7 +153,7 @@ class LLMPermanentError(LLMCallError):
 
 
 class LLMExhaustedError(LLMCallError):
-    """Retryable failures exhausted every attempt and the pause deadline."""
+    """Retryable failures exhausted attempts and any applicable pause deadline."""
 
 
 # ---------------------------------------------------------------------------

artemis/llm/stream_guard.py

@@ -23,7 +23,7 @@ class ToolArgumentOverflow(ValueError):
             "limit_chars": SMALL_ACTION_ARGUMENT_LIMIT,
         }
         super().__init__(
-            f"模型生成的 {name} 参数异常膨胀（{characters} 字符，"
+            f"收到的 {name} 参数流超出安全限制（{characters} 字符，"
             f"保护上限 {SMALL_ACTION_ARGUMENT_LIMIT}）；已关闭输出流，未执行本次动作。"
         )