diff --git a/packages/opentelemetry-instrumentation-langchain/opentelemetry/instrumentation/langchain/__init__.py b/packages/opentelemetry-instrumentation-langchain/opentelemetry/instrumentation/langchain/__init__.py
index 395e6a98ac..9897884bbb 100644
--- a/packages/opentelemetry-instrumentation-langchain/opentelemetry/instrumentation/langchain/__init__.py
+++ b/packages/opentelemetry-instrumentation-langchain/opentelemetry/instrumentation/langchain/__init__.py
@@ -17,6 +17,7 @@
 from opentelemetry.instrumentation.utils import unwrap
 from opentelemetry.metrics import get_meter
 from opentelemetry.semconv_ai import Meters, SUPPRESS_LANGUAGE_MODEL_INSTRUMENTATION_KEY
+from opentelemetry.semconv._incubating.metrics import gen_ai_metrics as GenAIMetrics
 from opentelemetry.trace import get_tracer
 from opentelemetry.trace.propagation import set_span_in_context
 from opentelemetry.trace.propagation.tracecontext import (
@@ -68,6 +69,34 @@ def _instrument(self, **kwargs):
             description="Measures number of input and output tokens used",
         )
 
+        # Create streaming time to first token histogram
+        ttft_histogram = meter.create_histogram(
+            name=GenAIMetrics.GEN_AI_SERVER_TIME_TO_FIRST_TOKEN,
+            unit="s",
+            description="Time to first token in streaming responses",
+        )
+
+        # Create streaming time to generate histogram
+        streaming_time_histogram = meter.create_histogram(
+            name=Meters.LLM_STREAMING_TIME_TO_GENERATE,
+            unit="s",
+            description="Time between first token and completion in streaming responses",
+        )
+
+        # Create generation choices counter
+        choices_counter = meter.create_counter(
+            name=Meters.LLM_GENERATION_CHOICES,
+            unit="choice",
+            description="Number of choices returned by completions call",
+        )
+
+        # Create exception counter
+        exception_counter = meter.create_counter(
+            name="llm.langchain.completions.exceptions",
+            unit="time",
+            description="Number of exceptions occurred during LangChain completions",
+        )
+
         if not Config.use_legacy_attributes:
             event_logger_provider = kwargs.get("event_logger_provider")
             Config.event_logger = get_event_logger(
@@ -75,7 +104,8 @@ def _instrument(self, **kwargs):
             )
 
         traceloopCallbackHandler = TraceloopCallbackHandler(
-            tracer, duration_histogram, token_histogram
+            tracer, duration_histogram, token_histogram, ttft_histogram,
+            streaming_time_histogram, choices_counter, exception_counter
         )
         wrap_function_wrapper(
             module="langchain_core.callbacks",
diff --git a/packages/opentelemetry-instrumentation-langchain/opentelemetry/instrumentation/langchain/callback_handler.py b/packages/opentelemetry-instrumentation-langchain/opentelemetry/instrumentation/langchain/callback_handler.py
index c50a0cff6c..66229b59a6 100644
--- a/packages/opentelemetry-instrumentation-langchain/opentelemetry/instrumentation/langchain/callback_handler.py
+++ b/packages/opentelemetry-instrumentation-langchain/opentelemetry/instrumentation/langchain/callback_handler.py
@@ -54,7 +54,7 @@
     should_send_prompts,
 )
 from opentelemetry.instrumentation.utils import _SUPPRESS_INSTRUMENTATION_KEY
-from opentelemetry.metrics import Histogram
+from opentelemetry.metrics import Histogram, Counter
 from opentelemetry.semconv._incubating.attributes.gen_ai_attributes import (
     GEN_AI_RESPONSE_ID,
 )
@@ -146,16 +146,65 @@ def _extract_tool_call_data(
 
 class TraceloopCallbackHandler(BaseCallbackHandler):
     def __init__(
-        self, tracer: Tracer, duration_histogram: Histogram, token_histogram: Histogram
+        self,
+        tracer: Tracer,
+        duration_histogram: Histogram,
+        token_histogram: Histogram,
+        ttft_histogram: Histogram,
+        streaming_time_histogram: Histogram,
+        choices_counter: Counter,
+        exception_counter: Counter
     ) -> None:
         super().__init__()
         self.tracer = tracer
         self.duration_histogram = duration_histogram
         self.token_histogram = token_histogram
+        self.ttft_histogram = ttft_histogram
+        self.streaming_time_histogram = streaming_time_histogram
+        self.choices_counter = choices_counter
+        self.exception_counter = exception_counter
         self.spans: dict[UUID, SpanHolder] = {}
         self.run_inline = True
         self._callback_manager: CallbackManager | AsyncCallbackManager = None
 
+    def _create_shared_attributes(
+        self, span, model_name: str, operation_type: str = None, is_streaming: bool = False
+    ) -> dict:
+        """Create shared attributes for metrics matching OpenAI SDK structure."""
+        vendor = span.attributes.get(SpanAttributes.LLM_SYSTEM, "Langchain")
+        attributes = {
+            SpanAttributes.LLM_SYSTEM: vendor,
+            SpanAttributes.LLM_RESPONSE_MODEL: model_name,
+        }
+        # Add operation name if available
+        if operation_type:
+            attributes["gen_ai.operation.name"] = operation_type
+        elif span.attributes.get(SpanAttributes.LLM_REQUEST_TYPE):
+            attributes["gen_ai.operation.name"] = span.attributes.get(SpanAttributes.LLM_REQUEST_TYPE)
+        server_address = None
+        try:
+            association_properties = context_api.get_value("association_properties") or {}
+            server_address = (
+                association_properties.get("api_base") or
+                association_properties.get("endpoint") or
+                association_properties.get("base_url") or
+                association_properties.get("server_address")
+            )
+        except (AttributeError, KeyError, TypeError):
+            pass
+
+        if not server_address:
+            # Check if we can get it from span attributes
+            server_address = span.attributes.get("server.address")
+
+        if server_address:
+            attributes["server.address"] = server_address
+
+        if is_streaming:
+            attributes["stream"] = True
+
+        return attributes
+
     @staticmethod
     def _get_name_from_callback(
         serialized: dict[str, Any],
@@ -494,7 +543,7 @@ def on_chat_model_start(
             metadata=metadata,
             serialized=serialized,
         )
-        set_request_params(span, kwargs, self.spans[run_id])
+        set_request_params(span, kwargs, self.spans[run_id], serialized, metadata)
         if should_emit_events():
             self._emit_chat_input_events(messages)
         else:
@@ -524,13 +573,53 @@ def on_llm_start(
             LLMRequestTypeValues.COMPLETION,
             serialized=serialized,
         )
-        set_request_params(span, kwargs, self.spans[run_id])
+        set_request_params(span, kwargs, self.spans[run_id], serialized, metadata)
         if should_emit_events():
             for prompt in prompts:
                 emit_event(MessageEvent(content=prompt, role="user"))
         else:
             set_llm_request(span, serialized, prompts, kwargs, self.spans[run_id])
 
+    @dont_throw
+    def on_llm_new_token(
+        self,
+        token: str,
+        *,
+        chunk: Optional[Union[GenerationChunk, ChatGenerationChunk]] = None,
+        run_id: UUID,
+        parent_run_id: Optional[UUID] = None,
+        **kwargs: Any,
+    ) -> Any:
+        """Run on new LLM token. Track TTFT and streaming metrics."""
+        if context_api.get_value(_SUPPRESS_INSTRUMENTATION_KEY):
+            return
+
+        if run_id not in self.spans:
+            return
+
+        span_holder = self.spans[run_id]
+        current_time = time.time()
+
+        # Track time to first token
+        if span_holder.first_token_time is None:
+            span_holder.first_token_time = current_time
+            ttft = current_time - span_holder.start_time
+
+            # Record TTFT metric
+            span = span_holder.span
+            from opentelemetry.instrumentation.langchain.span_utils import _get_unified_unknown_model
+
+            model_name = (
+                span.attributes.get(SpanAttributes.LLM_RESPONSE_MODEL) or
+                span_holder.request_model or
+                _get_unified_unknown_model(existing_model=span_holder.request_model)
+            )
+
+            self.ttft_histogram.record(
+                ttft,
+                attributes=self._create_shared_attributes(span, model_name, is_streaming=True)
+            )
+
     @dont_throw
     def on_llm_end(
         self,
@@ -552,7 +641,7 @@ def on_llm_end(
             ) or response.llm_output.get("model_id")
             if model_name is not None:
                 _set_span_attribute(
-                    span, SpanAttributes.LLM_RESPONSE_MODEL, model_name or "unknown"
+                    span, SpanAttributes.LLM_RESPONSE_MODEL, model_name
                 )
 
                 if self.spans[run_id].request_model is None:
@@ -571,6 +660,20 @@ def on_llm_end(
             model_name = _extract_model_name_from_association_metadata(
                 association_properties
             )
+
+        # Final fallback: use model name from request if all else fails
+        if model_name is None and run_id in self.spans and self.spans[run_id].request_model:
+            model_name = self.spans[run_id].request_model
+
+        # Ensure model_name is never None for downstream usage
+        if model_name is None:
+            from opentelemetry.instrumentation.langchain.span_utils import _get_unified_unknown_model
+            existing_model = self.spans[run_id].request_model if run_id in self.spans else None
+            model_name = _get_unified_unknown_model(existing_model=existing_model)
+
+        # Update span attribute with final resolved model name
+        _set_span_attribute(span, SpanAttributes.LLM_RESPONSE_MODEL, model_name)
+
         token_usage = (response.llm_output or {}).get("token_usage") or (
             response.llm_output or {}
         ).get("usage")
@@ -600,26 +703,17 @@ def on_llm_end(
             )
 
             # Record token usage metrics
-            vendor = span.attributes.get(SpanAttributes.LLM_SYSTEM, "Langchain")
+            base_attrs = self._create_shared_attributes(span, model_name)
+
             if prompt_tokens > 0:
-                self.token_histogram.record(
-                    prompt_tokens,
-                    attributes={
-                        SpanAttributes.LLM_SYSTEM: vendor,
-                        SpanAttributes.LLM_TOKEN_TYPE: "input",
-                        SpanAttributes.LLM_RESPONSE_MODEL: model_name or "unknown",
-                    },
-                )
+                input_attrs = {**base_attrs, SpanAttributes.LLM_TOKEN_TYPE: "input"}
+                self.token_histogram.record(prompt_tokens, attributes=input_attrs)
 
             if completion_tokens > 0:
-                self.token_histogram.record(
-                    completion_tokens,
-                    attributes={
-                        SpanAttributes.LLM_SYSTEM: vendor,
-                        SpanAttributes.LLM_TOKEN_TYPE: "output",
-                        SpanAttributes.LLM_RESPONSE_MODEL: model_name or "unknown",
-                    },
-                )
+                output_attrs = {**base_attrs, SpanAttributes.LLM_TOKEN_TYPE: "output"}
+                self.token_histogram.record(completion_tokens, attributes=output_attrs)
+        # Always call set_chat_response_usage for complete usage metadata extraction
+        # The function handles duplicate recording prevention internally
         set_chat_response_usage(
             span, response, self.token_histogram, token_usage is None, model_name
         )
@@ -628,16 +722,27 @@ def on_llm_end(
         else:
             set_chat_response(span, response)
 
-        # Record duration before ending span
-        duration = time.time() - self.spans[run_id].start_time
-        vendor = span.attributes.get(SpanAttributes.LLM_SYSTEM, "Langchain")
-        self.duration_histogram.record(
-            duration,
-            attributes={
-                SpanAttributes.LLM_SYSTEM: vendor,
-                SpanAttributes.LLM_RESPONSE_MODEL: model_name or "unknown",
-            },
-        )
+        # Record generation choices count
+        total_choices = 0
+        for generation_list in response.generations:
+            total_choices += len(generation_list)
+
+        span_holder = self.spans[run_id]
+        current_time = time.time()
+        is_streaming_request = span_holder.first_token_time is not None
+
+        shared_attrs = self._create_shared_attributes(span, model_name, is_streaming=is_streaming_request)
+
+        if total_choices > 0:
+            self.choices_counter.add(total_choices, attributes=shared_attrs)
+
+        # Record streaming time to generate if TTFT was tracked
+        if span_holder.first_token_time is not None:
+            streaming_time = current_time - span_holder.first_token_time
+            self.streaming_time_histogram.record(streaming_time, attributes=shared_attrs)
+
+        duration = current_time - span_holder.start_time
+        self.duration_histogram.record(duration, attributes=shared_attrs)
 
         self._end_span(span, run_id)
 
@@ -752,6 +857,23 @@ def _handle_error(
         span = self._get_span(run_id)
         span.set_status(Status(StatusCode.ERROR))
         span.record_exception(error)
+
+        # Record exception metric for LLM errors
+        if run_id in self.spans:
+            span_holder = self.spans[run_id]
+            from opentelemetry.instrumentation.langchain.span_utils import _get_unified_unknown_model
+
+            model_name = (
+                span.attributes.get(SpanAttributes.LLM_RESPONSE_MODEL) or
+                span_holder.request_model or
+                _get_unified_unknown_model(existing_model=span_holder.request_model)
+            )
+
+            exception_attrs = self._create_shared_attributes(span, model_name)
+            exception_attrs[ERROR_TYPE] = type(error).__name__
+
+            self.exception_counter.add(1, attributes=exception_attrs)
+
         self._end_span(span, run_id)
 
     @dont_throw
diff --git a/packages/opentelemetry-instrumentation-langchain/opentelemetry/instrumentation/langchain/span_utils.py b/packages/opentelemetry-instrumentation-langchain/opentelemetry/instrumentation/langchain/span_utils.py
index 5469aad680..859bbfa171 100644
--- a/packages/opentelemetry-instrumentation-langchain/opentelemetry/instrumentation/langchain/span_utils.py
+++ b/packages/opentelemetry-instrumentation-langchain/opentelemetry/instrumentation/langchain/span_utils.py
@@ -34,6 +34,7 @@ class SpanHolder:
     entity_path: str
     start_time: float = field(default_factory=time.time)
     request_model: Optional[str] = None
+    first_token_time: Optional[float] = None
 
 
 def _message_type_to_role(message_type: str) -> str:
@@ -54,21 +55,133 @@ def _set_span_attribute(span: Span, name: str, value: AttributeValue):
         span.set_attribute(name, value)
 
 
-def set_request_params(span, kwargs, span_holder: SpanHolder):
-    if not span.is_recording():
-        return
+def _get_unified_unknown_model(
+    class_name: Optional[str] = None, existing_model: Optional[str] = None
+) -> str:
+    """Get unified unknown model name to ensure consistency across all fallbacks."""
+
+    if existing_model:
+        existing_lower = existing_model.lower()
+        if existing_lower.startswith("deepseek"):
+            return "deepseek-unknown"
+        elif existing_lower.startswith("gpt"):
+            return "gpt-unknown"
+        elif existing_lower.startswith("claude"):
+            return "claude-unknown"
+        elif existing_lower.startswith("command"):
+            return "command-unknown"
+        elif ("ollama" in existing_lower or "llama" in existing_lower):
+            return "ollama-unknown"
+
+    # Fallback to class name-based inference
+    if class_name:
+        if "ChatDeepSeek" in class_name:
+            return "deepseek-unknown"
+        elif "ChatOpenAI" in class_name:
+            return "gpt-unknown"
+        elif "ChatAnthropic" in class_name:
+            return "claude-unknown"
+        elif "ChatCohere" in class_name:
+            return "command-unknown"
+        elif "ChatOllama" in class_name:
+            return "ollama-unknown"
+
+    return "unknown"
+
+
+def _extract_model_name_from_request(
+    kwargs, span_holder: SpanHolder, serialized: Optional[dict] = None, metadata: Optional[dict] = None
+) -> str:
+    """Enhanced model extraction supporting third-party LangChain integrations."""
 
     for model_tag in ("model", "model_id", "model_name"):
         if (model := kwargs.get(model_tag)) is not None:
-            span_holder.request_model = model
-            break
+            return model
         elif (
             model := (kwargs.get("invocation_params") or {}).get(model_tag)
         ) is not None:
-            span_holder.request_model = model
-            break
-    else:
-        model = "unknown"
+            return model
+
+    # Enhanced extraction for third-party models
+    # Check nested kwargs structures
+    if "kwargs" in kwargs:
+        nested_kwargs = kwargs["kwargs"]
+        for model_tag in ("model", "model_id", "model_name"):
+            if (model := nested_kwargs.get(model_tag)) is not None:
+                return model
+
+    # Try to extract from model configuration passed through kwargs
+    if "model_kwargs" in kwargs:
+        model_kwargs = kwargs["model_kwargs"]
+        for model_tag in ("model", "model_id", "model_name"):
+            if (model := model_kwargs.get(model_tag)) is not None:
+                return model
+
+    # Check association metadata which is important for ChatDeepSeek and similar integrations
+    if metadata:
+        if (model := metadata.get("ls_model_name")) is not None:
+            return model
+        # Check other potential metadata fields
+        for model_tag in ("model", "model_id", "model_name"):
+            if (model := metadata.get(model_tag)) is not None:
+                return model
+
+    # Try to get association properties from context
+    try:
+        from opentelemetry import context as context_api
+        association_properties = context_api.get_value("association_properties") or {}
+        if (model := association_properties.get("ls_model_name")) is not None:
+            return model
+    except (AttributeError, KeyError, TypeError):
+        pass
+
+    # Extract from serialized information for third-party integrations
+    if serialized:
+        if "kwargs" in serialized:
+            ser_kwargs = serialized["kwargs"]
+            for model_tag in ("model", "model_id", "model_name"):
+                if (model := ser_kwargs.get(model_tag)) is not None:
+                    return model
+
+        for model_tag in ("model", "model_id", "model_name"):
+            if (model := serialized.get(model_tag)) is not None:
+                return model
+
+        if "id" in serialized and serialized["id"]:
+            class_name = serialized["id"][-1] if isinstance(serialized["id"], list) else str(serialized["id"])
+            return _infer_model_from_class_name(class_name, serialized)
+
+    return _get_unified_unknown_model()
+
+
+def _infer_model_from_class_name(class_name: str, serialized: dict) -> str:
+    """Infer model name from LangChain model class name for known third-party integrations."""
+
+    # For ChatDeepSeek, try to extract actual model from serialized kwargs
+    if "ChatDeepSeek" in class_name:
+        # Check if serialized contains the actual model name
+        if "kwargs" in serialized:
+            ser_kwargs = serialized["kwargs"]
+            # ChatDeepSeek might store model in different fields
+            for model_field in ("model", "_model", "model_name"):
+                if model_field in ser_kwargs and ser_kwargs[model_field]:
+                    return ser_kwargs[model_field]
+        return _get_unified_unknown_model(class_name)
+
+    if any(model_class in class_name for model_class in ["ChatOpenAI", "ChatAnthropic", "ChatCohere", "ChatOllama"]):
+        return _get_unified_unknown_model(class_name)
+
+    return _get_unified_unknown_model()
+
+
+def set_request_params(
+    span, kwargs, span_holder: SpanHolder, serialized: Optional[dict] = None, metadata: Optional[dict] = None
+):
+    if not span.is_recording():
+        return
+
+    model = _extract_model_name_from_request(kwargs, span_holder, serialized, metadata)
+    span_holder.request_model = model
 
     _set_span_attribute(span, SpanAttributes.LLM_REQUEST_MODEL, model)
     # response is not available for LLM requests (as opposed to chat)
@@ -118,7 +231,7 @@ def set_llm_request(
     kwargs: Any,
     span_holder: SpanHolder,
 ) -> None:
-    set_request_params(span, kwargs, span_holder)
+    set_request_params(span, kwargs, span_holder, serialized)
 
     if should_send_prompts():
         for i, msg in enumerate(prompts):
@@ -141,7 +254,8 @@ def set_chat_request(
     kwargs: Any,
     span_holder: SpanHolder,
 ) -> None:
-    set_request_params(span, serialized.get("kwargs", {}), span_holder)
+    metadata = kwargs.get("metadata")
+    set_request_params(span, kwargs, span_holder, serialized, metadata)
 
     if should_send_prompts():
         for i, function in enumerate(
@@ -359,21 +473,44 @@ def set_chat_response_usage(
                 )
 
 
-def extract_model_name_from_response_metadata(response: LLMResult) -> str:
+def extract_model_name_from_response_metadata(response: LLMResult) -> Optional[str]:
+    """Enhanced model name extraction from response metadata with third-party support."""
+
+    # Standard extraction from response metadata
     for generations in response.generations:
         for generation in generations:
             if (
                 getattr(generation, "message", None)
                 and getattr(generation.message, "response_metadata", None)
-                and (model_name := generation.message.response_metadata.get("model_name"))
             ):
+                metadata = generation.message.response_metadata
+                # Try multiple possible model name fields
+                for model_field in ("model_name", "model", "model_id"):
+                    if (model_name := metadata.get(model_field)):
+                        return model_name
+
+    # Enhanced extraction for third-party models
+    # Check if llm_output contains model information
+    if response.llm_output:
+        for model_field in ("model", "model_name", "model_id"):
+            if (model_name := response.llm_output.get(model_field)):
                 return model_name
 
+    # Check generation_info for model information
+    for generations in response.generations:
+        for generation in generations:
+            if hasattr(generation, "generation_info") and generation.generation_info:
+                for model_field in ("model", "model_name", "model_id"):
+                    if (model_name := generation.generation_info.get(model_field)):
+                        return model_name
+
+    return None
 
-def _extract_model_name_from_association_metadata(metadata: Optional[dict[str, Any]] = None) -> str:
+
+def _extract_model_name_from_association_metadata(metadata: Optional[dict[str, Any]] = None) -> Optional[str]:
     if metadata:
-        return metadata.get("ls_model_name") or "unknown"
-    return "unknown"
+        return metadata.get("ls_model_name")
+    return None
 
 
 def _set_chat_tool_calls(
diff --git a/packages/opentelemetry-instrumentation-langchain/poetry.lock b/packages/opentelemetry-instrumentation-langchain/poetry.lock
index 22f468d079..3ea99903a3 100644
--- a/packages/opentelemetry-instrumentation-langchain/poetry.lock
+++ b/packages/opentelemetry-instrumentation-langchain/poetry.lock
@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 2.1.1 and should not be changed by hand.
+# This file is automatically @generated by Poetry 2.1.2 and should not be changed by hand.
 
 [[package]]
 name = "aiohappyeyeballs"
@@ -207,7 +207,7 @@ description = "Timeout context manager for asyncio programs"
 optional = false
 python-versions = ">=3.7"
 groups = ["test"]
-markers = "python_version <= \"3.10\""
+markers = "python_version < \"3.11\""
 files = [
     {file = "async-timeout-4.0.3.tar.gz", hash = "sha256:4640d96be84d82d02ed59ea2b7105a0f7b33abe8703703cd0ab0bf87c427522f"},
     {file = "async_timeout-4.0.3-py3-none-any.whl", hash = "sha256:7405140ff1230c310e51dc27b3145b9092d659ce68ff733fb0cefe3ee42be028"},
@@ -285,8 +285,8 @@ files = [
 jmespath = ">=0.7.1,<2.0.0"
 python-dateutil = ">=2.1,<3.0.0"
 urllib3 = [
-    {version = ">=1.25.4,<2.2.0 || >2.2.0,<3", markers = "python_version >= \"3.10\""},
     {version = ">=1.25.4,<1.27", markers = "python_version < \"3.10\""},
+    {version = ">=1.25.4,<2.2.0 || >2.2.0,<3", markers = "python_version >= \"3.10\""},
 ]
 
 [package.extras]
@@ -304,6 +304,104 @@ files = [
     {file = "certifi-2024.8.30.tar.gz", hash = "sha256:bec941d2aa8195e248a60b31ff9f0558284cf01a52591ceda73ea9afffd69fd9"},
 ]
 
+[[package]]
+name = "cffi"
+version = "2.0.0"
+description = "Foreign Function Interface for Python calling C code."
+optional = false
+python-versions = ">=3.9"
+groups = ["test"]
+markers = "platform_python_implementation == \"PyPy\""
+files = [
+    {file = "cffi-2.0.0-cp310-cp310-macosx_10_13_x86_64.whl", hash = "sha256:0cf2d91ecc3fcc0625c2c530fe004f82c110405f101548512cce44322fa8ac44"},
+    {file = "cffi-2.0.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:f73b96c41e3b2adedc34a7356e64c8eb96e03a3782b535e043a986276ce12a49"},
+    {file = "cffi-2.0.0-cp310-cp310-manylinux1_i686.manylinux2014_i686.manylinux_2_17_i686.manylinux_2_5_i686.whl", hash = "sha256:53f77cbe57044e88bbd5ed26ac1d0514d2acf0591dd6bb02a3ae37f76811b80c"},
+    {file = "cffi-2.0.0-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:3e837e369566884707ddaf85fc1744b47575005c0a229de3327f8f9a20f4efeb"},
+    {file = "cffi-2.0.0-cp310-cp310-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:5eda85d6d1879e692d546a078b44251cdd08dd1cfb98dfb77b670c97cee49ea0"},
+    {file = "cffi-2.0.0-cp310-cp310-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:9332088d75dc3241c702d852d4671613136d90fa6881da7d770a483fd05248b4"},
+    {file = "cffi-2.0.0-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:fc7de24befaeae77ba923797c7c87834c73648a05a4bde34b3b7e5588973a453"},
+    {file = "cffi-2.0.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:cf364028c016c03078a23b503f02058f1814320a56ad535686f90565636a9495"},
+    {file = "cffi-2.0.0-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:e11e82b744887154b182fd3e7e8512418446501191994dbf9c9fc1f32cc8efd5"},
+    {file = "cffi-2.0.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:8ea985900c5c95ce9db1745f7933eeef5d314f0565b27625d9a10ec9881e1bfb"},
+    {file = "cffi-2.0.0-cp310-cp310-win32.whl", hash = "sha256:1f72fb8906754ac8a2cc3f9f5aaa298070652a0ffae577e0ea9bd480dc3c931a"},
+    {file = "cffi-2.0.0-cp310-cp310-win_amd64.whl", hash = "sha256:b18a3ed7d5b3bd8d9ef7a8cb226502c6bf8308df1525e1cc676c3680e7176739"},
+    {file = "cffi-2.0.0-cp311-cp311-macosx_10_13_x86_64.whl", hash = "sha256:b4c854ef3adc177950a8dfc81a86f5115d2abd545751a304c5bcf2c2c7283cfe"},
+    {file = "cffi-2.0.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:2de9a304e27f7596cd03d16f1b7c72219bd944e99cc52b84d0145aefb07cbd3c"},
+    {file = "cffi-2.0.0-cp311-cp311-manylinux1_i686.manylinux2014_i686.manylinux_2_17_i686.manylinux_2_5_i686.whl", hash = "sha256:baf5215e0ab74c16e2dd324e8ec067ef59e41125d3eade2b863d294fd5035c92"},
+    {file = "cffi-2.0.0-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:730cacb21e1bdff3ce90babf007d0a0917cc3e6492f336c2f0134101e0944f93"},
+    {file = "cffi-2.0.0-cp311-cp311-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:6824f87845e3396029f3820c206e459ccc91760e8fa24422f8b0c3d1731cbec5"},
+    {file = "cffi-2.0.0-cp311-cp311-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:9de40a7b0323d889cf8d23d1ef214f565ab154443c42737dfe52ff82cf857664"},
+    {file = "cffi-2.0.0-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:8941aaadaf67246224cee8c3803777eed332a19d909b47e29c9842ef1e79ac26"},
+    {file = "cffi-2.0.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:a05d0c237b3349096d3981b727493e22147f934b20f6f125a3eba8f994bec4a9"},
+    {file = "cffi-2.0.0-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:94698a9c5f91f9d138526b48fe26a199609544591f859c870d477351dc7b2414"},
+    {file = "cffi-2.0.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:5fed36fccc0612a53f1d4d9a816b50a36702c28a2aa880cb8a122b3466638743"},
+    {file = "cffi-2.0.0-cp311-cp311-win32.whl", hash = "sha256:c649e3a33450ec82378822b3dad03cc228b8f5963c0c12fc3b1e0ab940f768a5"},
+    {file = "cffi-2.0.0-cp311-cp311-win_amd64.whl", hash = "sha256:66f011380d0e49ed280c789fbd08ff0d40968ee7b665575489afa95c98196ab5"},
+    {file = "cffi-2.0.0-cp311-cp311-win_arm64.whl", hash = "sha256:c6638687455baf640e37344fe26d37c404db8b80d037c3d29f58fe8d1c3b194d"},
+    {file = "cffi-2.0.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:6d02d6655b0e54f54c4ef0b94eb6be0607b70853c45ce98bd278dc7de718be5d"},
+    {file = "cffi-2.0.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:8eca2a813c1cb7ad4fb74d368c2ffbbb4789d377ee5bb8df98373c2cc0dee76c"},
+    {file = "cffi-2.0.0-cp312-cp312-manylinux1_i686.manylinux2014_i686.manylinux_2_17_i686.manylinux_2_5_i686.whl", hash = "sha256:21d1152871b019407d8ac3985f6775c079416c282e431a4da6afe7aefd2bccbe"},
+    {file = "cffi-2.0.0-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:b21e08af67b8a103c71a250401c78d5e0893beff75e28c53c98f4de42f774062"},
+    {file = "cffi-2.0.0-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:1e3a615586f05fc4065a8b22b8152f0c1b00cdbc60596d187c2a74f9e3036e4e"},
+    {file = "cffi-2.0.0-cp312-cp312-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:81afed14892743bbe14dacb9e36d9e0e504cd204e0b165062c488942b9718037"},
+    {file = "cffi-2.0.0-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:3e17ed538242334bf70832644a32a7aae3d83b57567f9fd60a26257e992b79ba"},
+    {file = "cffi-2.0.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:3925dd22fa2b7699ed2617149842d2e6adde22b262fcbfada50e3d195e4b3a94"},
+    {file = "cffi-2.0.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:2c8f814d84194c9ea681642fd164267891702542f028a15fc97d4674b6206187"},
+    {file = "cffi-2.0.0-cp312-cp312-win32.whl", hash = "sha256:da902562c3e9c550df360bfa53c035b2f241fed6d9aef119048073680ace4a18"},
+    {file = "cffi-2.0.0-cp312-cp312-win_amd64.whl", hash = "sha256:da68248800ad6320861f129cd9c1bf96ca849a2771a59e0344e88681905916f5"},
+    {file = "cffi-2.0.0-cp312-cp312-win_arm64.whl", hash = "sha256:4671d9dd5ec934cb9a73e7ee9676f9362aba54f7f34910956b84d727b0d73fb6"},
+    {file = "cffi-2.0.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:00bdf7acc5f795150faa6957054fbbca2439db2f775ce831222b66f192f03beb"},
+    {file = "cffi-2.0.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:45d5e886156860dc35862657e1494b9bae8dfa63bf56796f2fb56e1679fc0bca"},
+    {file = "cffi-2.0.0-cp313-cp313-manylinux1_i686.manylinux2014_i686.manylinux_2_17_i686.manylinux_2_5_i686.whl", hash = "sha256:07b271772c100085dd28b74fa0cd81c8fb1a3ba18b21e03d7c27f3436a10606b"},
+    {file = "cffi-2.0.0-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:d48a880098c96020b02d5a1f7d9251308510ce8858940e6fa99ece33f610838b"},
+    {file = "cffi-2.0.0-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:f93fd8e5c8c0a4aa1f424d6173f14a892044054871c771f8566e4008eaa359d2"},
+    {file = "cffi-2.0.0-cp313-cp313-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:dd4f05f54a52fb558f1ba9f528228066954fee3ebe629fc1660d874d040ae5a3"},
+    {file = "cffi-2.0.0-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:c8d3b5532fc71b7a77c09192b4a5a200ea992702734a2e9279a37f2478236f26"},
+    {file = "cffi-2.0.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:d9b29c1f0ae438d5ee9acb31cadee00a58c46cc9c0b2f9038c6b0b3470877a8c"},
+    {file = "cffi-2.0.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:6d50360be4546678fc1b79ffe7a66265e28667840010348dd69a314145807a1b"},
+    {file = "cffi-2.0.0-cp313-cp313-win32.whl", hash = "sha256:74a03b9698e198d47562765773b4a8309919089150a0bb17d829ad7b44b60d27"},
+    {file = "cffi-2.0.0-cp313-cp313-win_amd64.whl", hash = "sha256:19f705ada2530c1167abacb171925dd886168931e0a7b78f5bffcae5c6b5be75"},
+    {file = "cffi-2.0.0-cp313-cp313-win_arm64.whl", hash = "sha256:256f80b80ca3853f90c21b23ee78cd008713787b1b1e93eae9f3d6a7134abd91"},
+    {file = "cffi-2.0.0-cp314-cp314-macosx_10_13_x86_64.whl", hash = "sha256:fc33c5141b55ed366cfaad382df24fe7dcbc686de5be719b207bb248e3053dc5"},
+    {file = "cffi-2.0.0-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:c654de545946e0db659b3400168c9ad31b5d29593291482c43e3564effbcee13"},
+    {file = "cffi-2.0.0-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:24b6f81f1983e6df8db3adc38562c83f7d4a0c36162885ec7f7b77c7dcbec97b"},
+    {file = "cffi-2.0.0-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:12873ca6cb9b0f0d3a0da705d6086fe911591737a59f28b7936bdfed27c0d47c"},
+    {file = "cffi-2.0.0-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:d9b97165e8aed9272a6bb17c01e3cc5871a594a446ebedc996e2397a1c1ea8ef"},
+    {file = "cffi-2.0.0-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:afb8db5439b81cf9c9d0c80404b60c3cc9c3add93e114dcae767f1477cb53775"},
+    {file = "cffi-2.0.0-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:737fe7d37e1a1bffe70bd5754ea763a62a066dc5913ca57e957824b72a85e205"},
+    {file = "cffi-2.0.0-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:38100abb9d1b1435bc4cc340bb4489635dc2f0da7456590877030c9b3d40b0c1"},
+    {file = "cffi-2.0.0-cp314-cp314-win32.whl", hash = "sha256:087067fa8953339c723661eda6b54bc98c5625757ea62e95eb4898ad5e776e9f"},
+    {file = "cffi-2.0.0-cp314-cp314-win_amd64.whl", hash = "sha256:203a48d1fb583fc7d78a4c6655692963b860a417c0528492a6bc21f1aaefab25"},
+    {file = "cffi-2.0.0-cp314-cp314-win_arm64.whl", hash = "sha256:dbd5c7a25a7cb98f5ca55d258b103a2054f859a46ae11aaf23134f9cc0d356ad"},
+    {file = "cffi-2.0.0-cp314-cp314t-macosx_10_13_x86_64.whl", hash = "sha256:9a67fc9e8eb39039280526379fb3a70023d77caec1852002b4da7e8b270c4dd9"},
+    {file = "cffi-2.0.0-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:7a66c7204d8869299919db4d5069a82f1561581af12b11b3c9f48c584eb8743d"},
+    {file = "cffi-2.0.0-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:7cc09976e8b56f8cebd752f7113ad07752461f48a58cbba644139015ac24954c"},
+    {file = "cffi-2.0.0-cp314-cp314t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:92b68146a71df78564e4ef48af17551a5ddd142e5190cdf2c5624d0c3ff5b2e8"},
+    {file = "cffi-2.0.0-cp314-cp314t-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:b1e74d11748e7e98e2f426ab176d4ed720a64412b6a15054378afdb71e0f37dc"},
+    {file = "cffi-2.0.0-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:28a3a209b96630bca57cce802da70c266eb08c6e97e5afd61a75611ee6c64592"},
+    {file = "cffi-2.0.0-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:7553fb2090d71822f02c629afe6042c299edf91ba1bf94951165613553984512"},
+    {file = "cffi-2.0.0-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:6c6c373cfc5c83a975506110d17457138c8c63016b563cc9ed6e056a82f13ce4"},
+    {file = "cffi-2.0.0-cp314-cp314t-win32.whl", hash = "sha256:1fc9ea04857caf665289b7a75923f2c6ed559b8298a1b8c49e59f7dd95c8481e"},
+    {file = "cffi-2.0.0-cp314-cp314t-win_amd64.whl", hash = "sha256:d68b6cef7827e8641e8ef16f4494edda8b36104d79773a334beaa1e3521430f6"},
+    {file = "cffi-2.0.0-cp314-cp314t-win_arm64.whl", hash = "sha256:0a1527a803f0a659de1af2e1fd700213caba79377e27e4693648c2923da066f9"},
+    {file = "cffi-2.0.0-cp39-cp39-macosx_10_13_x86_64.whl", hash = "sha256:fe562eb1a64e67dd297ccc4f5addea2501664954f2692b69a76449ec7913ecbf"},
+    {file = "cffi-2.0.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:de8dad4425a6ca6e4e5e297b27b5c824ecc7581910bf9aee86cb6835e6812aa7"},
+    {file = "cffi-2.0.0-cp39-cp39-manylinux1_i686.manylinux2014_i686.manylinux_2_17_i686.manylinux_2_5_i686.whl", hash = "sha256:4647afc2f90d1ddd33441e5b0e85b16b12ddec4fca55f0d9671fef036ecca27c"},
+    {file = "cffi-2.0.0-cp39-cp39-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:3f4d46d8b35698056ec29bca21546e1551a205058ae1a181d871e278b0b28165"},
+    {file = "cffi-2.0.0-cp39-cp39-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:e6e73b9e02893c764e7e8d5bb5ce277f1a009cd5243f8228f75f842bf937c534"},
+    {file = "cffi-2.0.0-cp39-cp39-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:cb527a79772e5ef98fb1d700678fe031e353e765d1ca2d409c92263c6d43e09f"},
+    {file = "cffi-2.0.0-cp39-cp39-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:61d028e90346df14fedc3d1e5441df818d095f3b87d286825dfcbd6459b7ef63"},
+    {file = "cffi-2.0.0-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:0f6084a0ea23d05d20c3edcda20c3d006f9b6f3fefeac38f59262e10cef47ee2"},
+    {file = "cffi-2.0.0-cp39-cp39-musllinux_1_2_i686.whl", hash = "sha256:1cd13c99ce269b3ed80b417dcd591415d3372bcac067009b6e0f59c7d4015e65"},
+    {file = "cffi-2.0.0-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:89472c9762729b5ae1ad974b777416bfda4ac5642423fa93bd57a09204712322"},
+    {file = "cffi-2.0.0-cp39-cp39-win32.whl", hash = "sha256:2081580ebb843f759b9f617314a24ed5738c51d2aee65d31e02f6f7a2b97707a"},
+    {file = "cffi-2.0.0-cp39-cp39-win_amd64.whl", hash = "sha256:b882b3df248017dba09d6b16defe9b5c407fe32fc7c65a9c69798e6175601be9"},
+    {file = "cffi-2.0.0.tar.gz", hash = "sha256:44d1b5909021139fe36001ae048dbdde8214afa20200eda0f64c068cac5d5529"},
+]
+
+[package.dependencies]
+pycparser = {version = "*", markers = "implementation_name != \"PyPy\""}
+
 [[package]]
 name = "charset-normalizer"
 version = "3.4.0"
@@ -494,7 +592,7 @@ description = "Backport of PEP 654 (exception groups)"
 optional = false
 python-versions = ">=3.7"
 groups = ["dev", "test"]
-markers = "python_version <= \"3.10\""
+markers = "python_version < \"3.11\""
 files = [
     {file = "exceptiongroup-1.2.2-py3-none-any.whl", hash = "sha256:3111b9d131c238bec2f8f516e123e14ba243563fb135d3fe885990585aa7795b"},
     {file = "exceptiongroup-1.2.2.tar.gz", hash = "sha256:47c2edf7c6738fafb49fd34290706d1a1a2f4d1c6df275526b62cbb4aa5393cc"},
@@ -733,7 +831,7 @@ description = "Lightweight in-process concurrent programming"
 optional = false
 python-versions = ">=3.7"
 groups = ["test"]
-markers = "python_version <= \"3.12\" and (platform_machine == \"aarch64\" or platform_machine == \"ppc64le\" or platform_machine == \"x86_64\" or platform_machine == \"amd64\" or platform_machine == \"AMD64\" or platform_machine == \"win32\" or platform_machine == \"WIN32\")"
+markers = "(platform_machine == \"aarch64\" or platform_machine == \"ppc64le\" or platform_machine == \"x86_64\" or platform_machine == \"amd64\" or platform_machine == \"AMD64\" or platform_machine == \"win32\" or platform_machine == \"WIN32\") and python_version < \"3.13\""
 files = [
     {file = "greenlet-3.1.1-cp310-cp310-macosx_11_0_universal2.whl", hash = "sha256:0bbae94a29c9e5c7e4a2b7f0aae5c17e8e90acbfd3bf6270eeba60c39fce3563"},
     {file = "greenlet-3.1.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0fde093fb93f35ca72a556cf72c92ea3ebfda3d79fc35bb19fbe685853869a83"},
@@ -1254,25 +1352,41 @@ tenacity = ">=8.1.0,<8.4.0 || >8.4.0,<10"
 
 [[package]]
 name = "langchain-core"
-version = "0.3.63"
+version = "0.3.76"
 description = "Building applications with LLMs through composability"
 optional = false
 python-versions = ">=3.9"
 groups = ["test"]
 files = [
-    {file = "langchain_core-0.3.63-py3-none-any.whl", hash = "sha256:f91db8221b1bc6808f70b2e72fded1a94d50ee3f1dff1636fb5a5a514c64b7f5"},
-    {file = "langchain_core-0.3.63.tar.gz", hash = "sha256:e2e30cfbb7684a5a0319f6cbf065fc3c438bfd1060302f085a122527890fb01e"},
+    {file = "langchain_core-0.3.76-py3-none-any.whl", hash = "sha256:46e0eb48c7ac532432d51f8ca1ece1804c82afe9ae3dcf027b867edadf82b3ec"},
+    {file = "langchain_core-0.3.76.tar.gz", hash = "sha256:71136a122dd1abae2c289c5809d035cf12b5f2bb682d8a4c1078cd94feae7419"},
 ]
 
 [package.dependencies]
 jsonpatch = ">=1.33,<2.0"
-langsmith = ">=0.1.126,<0.4"
-packaging = ">=23.2,<25"
+langsmith = ">=0.3.45"
+packaging = ">=23.2"
 pydantic = ">=2.7.4"
 PyYAML = ">=5.3"
 tenacity = ">=8.1.0,<8.4.0 || >8.4.0,<10.0.0"
 typing-extensions = ">=4.7"
 
+[[package]]
+name = "langchain-deepseek"
+version = "0.1.4"
+description = "An integration package connecting DeepSeek and LangChain"
+optional = false
+python-versions = ">=3.9"
+groups = ["test"]
+files = [
+    {file = "langchain_deepseek-0.1.4-py3-none-any.whl", hash = "sha256:9ce3dbfc7a40f221657ffe31e8623ea6e397f6c90de2a58d38204ac63e8f41ff"},
+    {file = "langchain_deepseek-0.1.4.tar.gz", hash = "sha256:dc105138aee4fce03badd0521e69d5508b37f5c087d92b3e8481ffb8f9563d33"},
+]
+
+[package.dependencies]
+langchain-core = ">=0.3.70,<1.0.0"
+langchain-openai = ">=0.3.28,<1.0.0"
+
 [[package]]
 name = "langchain-experimental"
 version = "0.3.2"
@@ -1310,19 +1424,19 @@ transformers = ">=4.39.0"
 
 [[package]]
 name = "langchain-openai"
-version = "0.3.14"
+version = "0.3.33"
 description = "An integration package connecting OpenAI and LangChain"
 optional = false
-python-versions = "<4.0,>=3.9"
+python-versions = ">=3.9"
 groups = ["test"]
 files = [
-    {file = "langchain_openai-0.3.14-py3-none-any.whl", hash = "sha256:b8e648d2d7678a5540818199d141ff727c6f1514294b3e1e999a95357c9d66a0"},
-    {file = "langchain_openai-0.3.14.tar.gz", hash = "sha256:0662db78620c2e5c3ccfc1c36dc959c0ddc80e6bdf7ef81632cbf4b2cc9b9461"},
+    {file = "langchain_openai-0.3.33-py3-none-any.whl", hash = "sha256:2d52aab6d2af61da9bb9470616ce782128f4be59df965caee3dece30ae6b2bc4"},
+    {file = "langchain_openai-0.3.33.tar.gz", hash = "sha256:2dec058332ea9e8977cd91df6515b95952e187ac7484f349c3fe91d936a92375"},
 ]
 
 [package.dependencies]
-langchain-core = ">=0.3.53,<1.0.0"
-openai = ">=1.68.2,<2.0.0"
+langchain-core = ">=0.3.76,<1.0.0"
+openai = ">=1.104.2,<2.0.0"
 tiktoken = ">=0.7,<1"
 
 [[package]]
@@ -1427,25 +1541,33 @@ orjson = ">=3.10.1"
 
 [[package]]
 name = "langsmith"
-version = "0.1.137"
+version = "0.3.45"
 description = "Client library to connect to the LangSmith LLM Tracing and Evaluation Platform."
 optional = false
-python-versions = "<4.0,>=3.8.1"
+python-versions = ">=3.9"
 groups = ["test"]
 files = [
-    {file = "langsmith-0.1.137-py3-none-any.whl", hash = "sha256:4256d5c61133749890f7b5c88321dbb133ce0f440c621ea28e76513285859b81"},
-    {file = "langsmith-0.1.137.tar.gz", hash = "sha256:56cdfcc6c74cb20a3f437d5bd144feb5bf93f54c5a2918d1e568cbd084a372d4"},
+    {file = "langsmith-0.3.45-py3-none-any.whl", hash = "sha256:5b55f0518601fa65f3bb6b1a3100379a96aa7b3ed5e9380581615ba9c65ed8ed"},
+    {file = "langsmith-0.3.45.tar.gz", hash = "sha256:1df3c6820c73ed210b2c7bc5cdb7bfa19ddc9126cd03fdf0da54e2e171e6094d"},
 ]
 
 [package.dependencies]
 httpx = ">=0.23.0,<1"
-orjson = ">=3.9.14,<4.0.0"
+orjson = {version = ">=3.9.14,<4.0.0", markers = "platform_python_implementation != \"PyPy\""}
+packaging = ">=23.2"
 pydantic = [
     {version = ">=1,<3", markers = "python_full_version < \"3.12.4\""},
     {version = ">=2.7.4,<3.0.0", markers = "python_full_version >= \"3.12.4\""},
 ]
 requests = ">=2,<3"
 requests-toolbelt = ">=1.0.0,<2.0.0"
+zstandard = ">=0.23.0,<0.24.0"
+
+[package.extras]
+langsmith-pyo3 = ["langsmith-pyo3 (>=0.1.0rc2,<0.2.0)"]
+openai-agents = ["openai-agents (>=0.0.3,<0.1)"]
+otel = ["opentelemetry-api (>=1.30.0,<2.0.0)", "opentelemetry-exporter-otlp-proto-http (>=1.30.0,<2.0.0)", "opentelemetry-sdk (>=1.30.0,<2.0.0)"]
+pytest = ["pytest (>=7.0.0)", "rich (>=13.9.4,<14.0.0)"]
 
 [[package]]
 name = "markupsafe"
@@ -1824,7 +1946,7 @@ description = "CUBLAS native runtime libraries"
 optional = false
 python-versions = ">=3"
 groups = ["test"]
-markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
+markers = "platform_machine == \"x86_64\" and platform_system == \"Linux\""
 files = [
     {file = "nvidia_cublas_cu12-12.6.4.1-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:08ed2686e9875d01b58e3cb379c6896df8e76c75e0d4a7f7dace3d7b6d9ef8eb"},
     {file = "nvidia_cublas_cu12-12.6.4.1-py3-none-manylinux_2_27_aarch64.whl", hash = "sha256:235f728d6e2a409eddf1df58d5b0921cf80cfa9e72b9f2775ccb7b4a87984668"},
@@ -1838,7 +1960,7 @@ description = "CUDA profiling tools runtime libs."
 optional = false
 python-versions = ">=3"
 groups = ["test"]
-markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
+markers = "platform_machine == \"x86_64\" and platform_system == \"Linux\""
 files = [
     {file = "nvidia_cuda_cupti_cu12-12.6.80-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:166ee35a3ff1587f2490364f90eeeb8da06cd867bd5b701bf7f9a02b78bc63fc"},
     {file = "nvidia_cuda_cupti_cu12-12.6.80-py3-none-manylinux2014_aarch64.whl", hash = "sha256:358b4a1d35370353d52e12f0a7d1769fc01ff74a191689d3870b2123156184c4"},
@@ -1854,7 +1976,7 @@ description = "NVRTC native runtime libraries"
 optional = false
 python-versions = ">=3"
 groups = ["test"]
-markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
+markers = "platform_machine == \"x86_64\" and platform_system == \"Linux\""
 files = [
     {file = "nvidia_cuda_nvrtc_cu12-12.6.77-py3-none-manylinux2014_aarch64.whl", hash = "sha256:5847f1d6e5b757f1d2b3991a01082a44aad6f10ab3c5c0213fa3e25bddc25a13"},
     {file = "nvidia_cuda_nvrtc_cu12-12.6.77-py3-none-manylinux2014_x86_64.whl", hash = "sha256:35b0cc6ee3a9636d5409133e79273ce1f3fd087abb0532d2d2e8fff1fe9efc53"},
@@ -1868,7 +1990,7 @@ description = "CUDA Runtime native Libraries"
 optional = false
 python-versions = ">=3"
 groups = ["test"]
-markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
+markers = "platform_machine == \"x86_64\" and platform_system == \"Linux\""
 files = [
     {file = "nvidia_cuda_runtime_cu12-12.6.77-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:6116fad3e049e04791c0256a9778c16237837c08b27ed8c8401e2e45de8d60cd"},
     {file = "nvidia_cuda_runtime_cu12-12.6.77-py3-none-manylinux2014_aarch64.whl", hash = "sha256:d461264ecb429c84c8879a7153499ddc7b19b5f8d84c204307491989a365588e"},
@@ -1884,7 +2006,7 @@ description = "cuDNN runtime libraries"
 optional = false
 python-versions = ">=3"
 groups = ["test"]
-markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
+markers = "platform_machine == \"x86_64\" and platform_system == \"Linux\""
 files = [
     {file = "nvidia_cudnn_cu12-9.5.1.17-py3-none-manylinux_2_28_aarch64.whl", hash = "sha256:9fd4584468533c61873e5fda8ca41bac3a38bcb2d12350830c69b0a96a7e4def"},
     {file = "nvidia_cudnn_cu12-9.5.1.17-py3-none-manylinux_2_28_x86_64.whl", hash = "sha256:30ac3869f6db17d170e0e556dd6cc5eee02647abc31ca856634d5a40f82c15b2"},
@@ -1901,7 +2023,7 @@ description = "CUFFT native runtime libraries"
 optional = false
 python-versions = ">=3"
 groups = ["test"]
-markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
+markers = "platform_machine == \"x86_64\" and platform_system == \"Linux\""
 files = [
     {file = "nvidia_cufft_cu12-11.3.0.4-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:d16079550df460376455cba121db6564089176d9bac9e4f360493ca4741b22a6"},
     {file = "nvidia_cufft_cu12-11.3.0.4-py3-none-manylinux2014_aarch64.whl", hash = "sha256:8510990de9f96c803a051822618d42bf6cb8f069ff3f48d93a8486efdacb48fb"},
@@ -1920,7 +2042,7 @@ description = "cuFile GPUDirect libraries"
 optional = false
 python-versions = ">=3"
 groups = ["test"]
-markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
+markers = "platform_machine == \"x86_64\" and platform_system == \"Linux\""
 files = [
     {file = "nvidia_cufile_cu12-1.11.1.6-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:cc23469d1c7e52ce6c1d55253273d32c565dd22068647f3aa59b3c6b005bf159"},
     {file = "nvidia_cufile_cu12-1.11.1.6-py3-none-manylinux_2_27_aarch64.whl", hash = "sha256:8f57a0051dcf2543f6dc2b98a98cb2719c37d3cee1baba8965d57f3bbc90d4db"},
@@ -1933,7 +2055,7 @@ description = "CURAND native runtime libraries"
 optional = false
 python-versions = ">=3"
 groups = ["test"]
-markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
+markers = "platform_machine == \"x86_64\" and platform_system == \"Linux\""
 files = [
     {file = "nvidia_curand_cu12-10.3.7.77-py3-none-manylinux2014_aarch64.whl", hash = "sha256:6e82df077060ea28e37f48a3ec442a8f47690c7499bff392a5938614b56c98d8"},
     {file = "nvidia_curand_cu12-10.3.7.77-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:a42cd1344297f70b9e39a1e4f467a4e1c10f1da54ff7a85c12197f6c652c8bdf"},
@@ -1949,7 +2071,7 @@ description = "CUDA solver native runtime libraries"
 optional = false
 python-versions = ">=3"
 groups = ["test"]
-markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
+markers = "platform_machine == \"x86_64\" and platform_system == \"Linux\""
 files = [
     {file = "nvidia_cusolver_cu12-11.7.1.2-py3-none-manylinux2014_aarch64.whl", hash = "sha256:0ce237ef60acde1efc457335a2ddadfd7610b892d94efee7b776c64bb1cac9e0"},
     {file = "nvidia_cusolver_cu12-11.7.1.2-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:e9e49843a7707e42022babb9bcfa33c29857a93b88020c4e4434656a655b698c"},
@@ -1970,7 +2092,7 @@ description = "CUSPARSE native runtime libraries"
 optional = false
 python-versions = ">=3"
 groups = ["test"]
-markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
+markers = "platform_machine == \"x86_64\" and platform_system == \"Linux\""
 files = [
     {file = "nvidia_cusparse_cu12-12.5.4.2-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:d25b62fb18751758fe3c93a4a08eff08effedfe4edf1c6bb5afd0890fe88f887"},
     {file = "nvidia_cusparse_cu12-12.5.4.2-py3-none-manylinux2014_aarch64.whl", hash = "sha256:7aa32fa5470cf754f72d1116c7cbc300b4e638d3ae5304cfa4a638a5b87161b1"},
@@ -1989,7 +2111,7 @@ description = "NVIDIA cuSPARSELt"
 optional = false
 python-versions = "*"
 groups = ["test"]
-markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
+markers = "platform_machine == \"x86_64\" and platform_system == \"Linux\""
 files = [
     {file = "nvidia_cusparselt_cu12-0.6.3-py3-none-manylinux2014_aarch64.whl", hash = "sha256:8371549623ba601a06322af2133c4a44350575f5a3108fb75f3ef20b822ad5f1"},
     {file = "nvidia_cusparselt_cu12-0.6.3-py3-none-manylinux2014_x86_64.whl", hash = "sha256:e5c8a26c36445dd2e6812f1177978a24e2d37cacce7e090f297a688d1ec44f46"},
@@ -2003,7 +2125,7 @@ description = "NVIDIA Collective Communication Library (NCCL) Runtime"
 optional = false
 python-versions = ">=3"
 groups = ["test"]
-markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
+markers = "platform_machine == \"x86_64\" and platform_system == \"Linux\""
 files = [
     {file = "nvidia_nccl_cu12-2.26.2-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:5c196e95e832ad30fbbb50381eb3cbd1fadd5675e587a548563993609af19522"},
     {file = "nvidia_nccl_cu12-2.26.2-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:694cf3879a206553cc9d7dbda76b13efaf610fdb70a50cba303de1b0d1530ac6"},
@@ -2016,7 +2138,7 @@ description = "Nvidia JIT LTO Library"
 optional = false
 python-versions = ">=3"
 groups = ["test"]
-markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
+markers = "platform_machine == \"x86_64\" and platform_system == \"Linux\""
 files = [
     {file = "nvidia_nvjitlink_cu12-12.6.85-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl", hash = "sha256:eedc36df9e88b682efe4309aa16b5b4e78c2407eac59e8c10a6a47535164369a"},
     {file = "nvidia_nvjitlink_cu12-12.6.85-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:cf4eaa7d4b6b543ffd69d6abfb11efdeb2db48270d94dfd3a452c24150829e41"},
@@ -2030,7 +2152,7 @@ description = "NVIDIA Tools Extension"
 optional = false
 python-versions = ">=3"
 groups = ["test"]
-markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
+markers = "platform_machine == \"x86_64\" and platform_system == \"Linux\""
 files = [
     {file = "nvidia_nvtx_cu12-12.6.77-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:f44f8d86bb7d5629988d61c8d3ae61dddb2015dee142740536bc7481b022fe4b"},
     {file = "nvidia_nvtx_cu12-12.6.77-py3-none-manylinux2014_aarch64.whl", hash = "sha256:adcaabb9d436c9761fca2b13959a2d237c5f9fd406c8e4b723c695409ff88059"},
@@ -2041,14 +2163,14 @@ files = [
 
 [[package]]
 name = "openai"
-version = "1.78.1"
+version = "1.108.1"
 description = "The official Python library for the openai API"
 optional = false
 python-versions = ">=3.8"
 groups = ["test"]
 files = [
-    {file = "openai-1.78.1-py3-none-any.whl", hash = "sha256:7368bf147ca499804cc408fe68cdb6866a060f38dec961bbc97b04f9d917907e"},
-    {file = "openai-1.78.1.tar.gz", hash = "sha256:8b26b364531b100df1b961d03560042e5f5be11301d7d49a6cd1a2b9af824dca"},
+    {file = "openai-1.108.1-py3-none-any.whl", hash = "sha256:952fc027e300b2ac23be92b064eac136a2bc58274cec16f5d2906c361340d59b"},
+    {file = "openai-1.108.1.tar.gz", hash = "sha256:6648468c1aec4eacfa554001e933a9fa075f57bacfc27588c2e34456cee9fef9"},
 ]
 
 [package.dependencies]
@@ -2062,6 +2184,7 @@ tqdm = ">4"
 typing-extensions = ">=4.11,<5"
 
 [package.extras]
+aiohttp = ["aiohttp", "httpx-aiohttp (>=0.1.8)"]
 datalib = ["numpy (>=1)", "pandas (>=1.2.3)", "pandas-stubs (>=1.1.0.11)"]
 realtime = ["websockets (>=13,<16)"]
 voice-helpers = ["numpy (>=2.0.2)", "sounddevice (>=0.5.1)"]
@@ -2102,7 +2225,7 @@ wrapt = ">=1.0.0,<2.0.0"
 
 [[package]]
 name = "opentelemetry-instrumentation-bedrock"
-version = "0.45.6"
+version = "0.47.2"
 description = "OpenTelemetry Bedrock instrumentation"
 optional = false
 python-versions = ">=3.9,<4"
@@ -2124,7 +2247,7 @@ url = "../opentelemetry-instrumentation-bedrock"
 
 [[package]]
 name = "opentelemetry-instrumentation-openai"
-version = "0.45.6"
+version = "0.47.2"
 description = "OpenTelemetry OpenAI instrumentation"
 optional = false
 python-versions = ">=3.9,<4"
@@ -2648,6 +2771,19 @@ files = [
     {file = "pycodestyle-2.12.1.tar.gz", hash = "sha256:6838eae08bbce4f6accd5d5572075c63626a15ee3e6f842df996bf62f6d73521"},
 ]
 
+[[package]]
+name = "pycparser"
+version = "2.23"
+description = "C parser in Python"
+optional = false
+python-versions = ">=3.8"
+groups = ["test"]
+markers = "implementation_name != \"PyPy\" and platform_python_implementation == \"PyPy\""
+files = [
+    {file = "pycparser-2.23-py3-none-any.whl", hash = "sha256:e5c6e8d3fbad53479cab09ac03729e0a9faf2bee3db8208a550daf5af81a5934"},
+    {file = "pycparser-2.23.tar.gz", hash = "sha256:78816d4f24add8f10a06d6f05b4d424ad9e96cfebf68a4ddc99c65c0720d00c2"},
+]
+
 [[package]]
 name = "pydantic"
 version = "2.10.5"
@@ -3648,7 +3784,7 @@ description = "A lil' TOML parser"
 optional = false
 python-versions = ">=3.8"
 groups = ["dev", "test"]
-markers = "python_version <= \"3.10\""
+markers = "python_version < \"3.11\""
 files = [
     {file = "tomli-2.0.2-py3-none-any.whl", hash = "sha256:2ebe24485c53d303f690b0ec092806a085f07af5a5aa1464f3931eec36caaa38"},
     {file = "tomli-2.0.2.tar.gz", hash = "sha256:d46d457a85337051c36524bc5349dd91b1877838e2979ac5ced3e710ed8a60ed"},
@@ -3817,7 +3953,7 @@ description = "A language and compiler for custom Deep Learning operations"
 optional = false
 python-versions = "*"
 groups = ["test"]
-markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""
+markers = "platform_machine == \"x86_64\" and platform_system == \"Linux\""
 files = [
     {file = "triton-3.3.0-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:fad99beafc860501d7fcc1fb7045d9496cbe2c882b1674640304949165a916e7"},
     {file = "triton-3.3.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:3161a2bf073d6b22c4e2f33f951f3e5e3001462b2570e6df9cd57565bdec2984"},
@@ -3842,7 +3978,7 @@ description = "Typing stubs for requests"
 optional = false
 python-versions = ">=3.7"
 groups = ["test"]
-markers = "platform_python_implementation == \"PyPy\" or python_version < \"3.10\""
+markers = "platform_python_implementation == \"PyPy\" or python_version == \"3.9\""
 files = [
     {file = "types-requests-2.31.0.6.tar.gz", hash = "sha256:cd74ce3b53c461f1228a9b783929ac73a666658f223e28ed29753771477b3bd0"},
     {file = "types_requests-2.31.0.6-py3-none-any.whl", hash = "sha256:a2db9cb228a81da8348b49ad6db3f5519452dd20a9c1e1a868c83c5fe88fd1a9"},
@@ -3858,7 +3994,7 @@ description = "Typing stubs for requests"
 optional = false
 python-versions = ">=3.8"
 groups = ["test"]
-markers = "platform_python_implementation != \"PyPy\" and python_version >= \"3.10\""
+markers = "python_version >= \"3.10\" and platform_python_implementation != \"PyPy\""
 files = [
     {file = "types-requests-2.32.0.20241016.tar.gz", hash = "sha256:0d9cad2f27515d0e3e3da7134a1b6f28fb97129d86b867f24d9c726452634d95"},
     {file = "types_requests-2.32.0.20241016-py3-none-any.whl", hash = "sha256:4195d62d6d3e043a4eaaf08ff8a62184584d2e8684e9d2aa178c7915a7da3747"},
@@ -3874,7 +4010,7 @@ description = "Typing stubs for urllib3"
 optional = false
 python-versions = "*"
 groups = ["test"]
-markers = "platform_python_implementation == \"PyPy\" or python_version < \"3.10\""
+markers = "platform_python_implementation == \"PyPy\" or python_version == \"3.9\""
 files = [
     {file = "types-urllib3-1.26.25.14.tar.gz", hash = "sha256:229b7f577c951b8c1b92c1bc2b2fdb0b49847bd2af6d1cc2a2e3dd340f3bda8f"},
     {file = "types_urllib3-1.26.25.14-py3-none-any.whl", hash = "sha256:9683bbb7fb72e32bfe9d2be6e04875fbe1b3eeec3cbb4ea231435aa7fd6b4f0e"},
@@ -3927,7 +4063,7 @@ description = "HTTP library with thread-safe connection pooling, file post, and
 optional = false
 python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,>=2.7"
 groups = ["test"]
-markers = "platform_python_implementation == \"PyPy\" or python_version < \"3.10\""
+markers = "platform_python_implementation == \"PyPy\" or python_version == \"3.9\""
 files = [
     {file = "urllib3-1.26.20-py2.py3-none-any.whl", hash = "sha256:0ed14ccfbf1c30a9072c7ca157e4319b70d65f623e91e7b32fadb2853431016e"},
     {file = "urllib3-1.26.20.tar.gz", hash = "sha256:40c2dc0c681e47eb8f90e7e27bf6ff7df2e677421fd46756da1161c39ca70d32"},
@@ -3945,7 +4081,7 @@ description = "HTTP library with thread-safe connection pooling, file post, and
 optional = false
 python-versions = ">=3.8"
 groups = ["test"]
-markers = "platform_python_implementation != \"PyPy\" and python_version >= \"3.10\""
+markers = "python_version >= \"3.10\" and platform_python_implementation != \"PyPy\""
 files = [
     {file = "urllib3-2.2.3-py3-none-any.whl", hash = "sha256:ca899ca043dcb1bafa3e262d73aa25c465bfb49e0bd9dd5d59f1d0acba2f8fac"},
     {file = "urllib3-2.2.3.tar.gz", hash = "sha256:e7d814a81dad81e6caf2ec9fdedb284ecc9c73076b62654547cc64ccdcae26e9"},
@@ -3972,8 +4108,8 @@ files = [
 [package.dependencies]
 PyYAML = "*"
 urllib3 = [
-    {version = "*", markers = "platform_python_implementation != \"PyPy\" and python_version >= \"3.10\""},
     {version = "<2", markers = "platform_python_implementation == \"PyPy\" or python_version < \"3.10\""},
+    {version = "*", markers = "platform_python_implementation != \"PyPy\" and python_version >= \"3.10\""},
 ]
 wrapt = "*"
 yarl = "*"
@@ -4311,10 +4447,123 @@ enabler = ["pytest-enabler (>=2.2)"]
 test = ["big-O", "importlib-resources ; python_version < \"3.9\"", "jaraco.functools", "jaraco.itertools", "jaraco.test", "more-itertools", "pytest (>=6,!=8.1.*)", "pytest-ignore-flaky"]
 type = ["pytest-mypy"]
 
+[[package]]
+name = "zstandard"
+version = "0.23.0"
+description = "Zstandard bindings for Python"
+optional = false
+python-versions = ">=3.8"
+groups = ["test"]
+files = [
+    {file = "zstandard-0.23.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:bf0a05b6059c0528477fba9054d09179beb63744355cab9f38059548fedd46a9"},
+    {file = "zstandard-0.23.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:fc9ca1c9718cb3b06634c7c8dec57d24e9438b2aa9a0f02b8bb36bf478538880"},
+    {file = "zstandard-0.23.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:77da4c6bfa20dd5ea25cbf12c76f181a8e8cd7ea231c673828d0386b1740b8dc"},
+    {file = "zstandard-0.23.0-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b2170c7e0367dde86a2647ed5b6f57394ea7f53545746104c6b09fc1f4223573"},
+    {file = "zstandard-0.23.0-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c16842b846a8d2a145223f520b7e18b57c8f476924bda92aeee3a88d11cfc391"},
+    {file = "zstandard-0.23.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:157e89ceb4054029a289fb504c98c6a9fe8010f1680de0201b3eb5dc20aa6d9e"},
+    {file = "zstandard-0.23.0-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:203d236f4c94cd8379d1ea61db2fce20730b4c38d7f1c34506a31b34edc87bdd"},
+    {file = "zstandard-0.23.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:dc5d1a49d3f8262be192589a4b72f0d03b72dcf46c51ad5852a4fdc67be7b9e4"},
+    {file = "zstandard-0.23.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:752bf8a74412b9892f4e5b58f2f890a039f57037f52c89a740757ebd807f33ea"},
+    {file = "zstandard-0.23.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:80080816b4f52a9d886e67f1f96912891074903238fe54f2de8b786f86baded2"},
+    {file = "zstandard-0.23.0-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:84433dddea68571a6d6bd4fbf8ff398236031149116a7fff6f777ff95cad3df9"},
+    {file = "zstandard-0.23.0-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:ab19a2d91963ed9e42b4e8d77cd847ae8381576585bad79dbd0a8837a9f6620a"},
+    {file = "zstandard-0.23.0-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:59556bf80a7094d0cfb9f5e50bb2db27fefb75d5138bb16fb052b61b0e0eeeb0"},
+    {file = "zstandard-0.23.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:27d3ef2252d2e62476389ca8f9b0cf2bbafb082a3b6bfe9d90cbcbb5529ecf7c"},
+    {file = "zstandard-0.23.0-cp310-cp310-win32.whl", hash = "sha256:5d41d5e025f1e0bccae4928981e71b2334c60f580bdc8345f824e7c0a4c2a813"},
+    {file = "zstandard-0.23.0-cp310-cp310-win_amd64.whl", hash = "sha256:519fbf169dfac1222a76ba8861ef4ac7f0530c35dd79ba5727014613f91613d4"},
+    {file = "zstandard-0.23.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:34895a41273ad33347b2fc70e1bff4240556de3c46c6ea430a7ed91f9042aa4e"},
+    {file = "zstandard-0.23.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:77ea385f7dd5b5676d7fd943292ffa18fbf5c72ba98f7d09fc1fb9e819b34c23"},
+    {file = "zstandard-0.23.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:983b6efd649723474f29ed42e1467f90a35a74793437d0bc64a5bf482bedfa0a"},
+    {file = "zstandard-0.23.0-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:80a539906390591dd39ebb8d773771dc4db82ace6372c4d41e2d293f8e32b8db"},
+    {file = "zstandard-0.23.0-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:445e4cb5048b04e90ce96a79b4b63140e3f4ab5f662321975679b5f6360b90e2"},
+    {file = "zstandard-0.23.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fd30d9c67d13d891f2360b2a120186729c111238ac63b43dbd37a5a40670b8ca"},
+    {file = "zstandard-0.23.0-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d20fd853fbb5807c8e84c136c278827b6167ded66c72ec6f9a14b863d809211c"},
+    {file = "zstandard-0.23.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:ed1708dbf4d2e3a1c5c69110ba2b4eb6678262028afd6c6fbcc5a8dac9cda68e"},
+    {file = "zstandard-0.23.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:be9b5b8659dff1f913039c2feee1aca499cfbc19e98fa12bc85e037c17ec6ca5"},
+    {file = "zstandard-0.23.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:65308f4b4890aa12d9b6ad9f2844b7ee42c7f7a4fd3390425b242ffc57498f48"},
+    {file = "zstandard-0.23.0-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:98da17ce9cbf3bfe4617e836d561e433f871129e3a7ac16d6ef4c680f13a839c"},
+    {file = "zstandard-0.23.0-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:8ed7d27cb56b3e058d3cf684d7200703bcae623e1dcc06ed1e18ecda39fee003"},
+    {file = "zstandard-0.23.0-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:b69bb4f51daf461b15e7b3db033160937d3ff88303a7bc808c67bbc1eaf98c78"},
+    {file = "zstandard-0.23.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:034b88913ecc1b097f528e42b539453fa82c3557e414b3de9d5632c80439a473"},
+    {file = "zstandard-0.23.0-cp311-cp311-win32.whl", hash = "sha256:f2d4380bf5f62daabd7b751ea2339c1a21d1c9463f1feb7fc2bdcea2c29c3160"},
+    {file = "zstandard-0.23.0-cp311-cp311-win_amd64.whl", hash = "sha256:62136da96a973bd2557f06ddd4e8e807f9e13cbb0bfb9cc06cfe6d98ea90dfe0"},
+    {file = "zstandard-0.23.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:b4567955a6bc1b20e9c31612e615af6b53733491aeaa19a6b3b37f3b65477094"},
+    {file = "zstandard-0.23.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:1e172f57cd78c20f13a3415cc8dfe24bf388614324d25539146594c16d78fcc8"},
+    {file = "zstandard-0.23.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b0e166f698c5a3e914947388c162be2583e0c638a4703fc6a543e23a88dea3c1"},
+    {file = "zstandard-0.23.0-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:12a289832e520c6bd4dcaad68e944b86da3bad0d339ef7989fb7e88f92e96072"},
+    {file = "zstandard-0.23.0-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d50d31bfedd53a928fed6707b15a8dbeef011bb6366297cc435accc888b27c20"},
+    {file = "zstandard-0.23.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:72c68dda124a1a138340fb62fa21b9bf4848437d9ca60bd35db36f2d3345f373"},
+    {file = "zstandard-0.23.0-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:53dd9d5e3d29f95acd5de6802e909ada8d8d8cfa37a3ac64836f3bc4bc5512db"},
+    {file = "zstandard-0.23.0-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:6a41c120c3dbc0d81a8e8adc73312d668cd34acd7725f036992b1b72d22c1772"},
+    {file = "zstandard-0.23.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:40b33d93c6eddf02d2c19f5773196068d875c41ca25730e8288e9b672897c105"},
+    {file = "zstandard-0.23.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:9206649ec587e6b02bd124fb7799b86cddec350f6f6c14bc82a2b70183e708ba"},
+    {file = "zstandard-0.23.0-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:76e79bc28a65f467e0409098fa2c4376931fd3207fbeb6b956c7c476d53746dd"},
+    {file = "zstandard-0.23.0-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:66b689c107857eceabf2cf3d3fc699c3c0fe8ccd18df2219d978c0283e4c508a"},
+    {file = "zstandard-0.23.0-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:9c236e635582742fee16603042553d276cca506e824fa2e6489db04039521e90"},
+    {file = "zstandard-0.23.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:a8fffdbd9d1408006baaf02f1068d7dd1f016c6bcb7538682622c556e7b68e35"},
+    {file = "zstandard-0.23.0-cp312-cp312-win32.whl", hash = "sha256:dc1d33abb8a0d754ea4763bad944fd965d3d95b5baef6b121c0c9013eaf1907d"},
+    {file = "zstandard-0.23.0-cp312-cp312-win_amd64.whl", hash = "sha256:64585e1dba664dc67c7cdabd56c1e5685233fbb1fc1966cfba2a340ec0dfff7b"},
+    {file = "zstandard-0.23.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:576856e8594e6649aee06ddbfc738fec6a834f7c85bf7cadd1c53d4a58186ef9"},
+    {file = "zstandard-0.23.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:38302b78a850ff82656beaddeb0bb989a0322a8bbb1bf1ab10c17506681d772a"},
+    {file = "zstandard-0.23.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d2240ddc86b74966c34554c49d00eaafa8200a18d3a5b6ffbf7da63b11d74ee2"},
+    {file = "zstandard-0.23.0-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:2ef230a8fd217a2015bc91b74f6b3b7d6522ba48be29ad4ea0ca3a3775bf7dd5"},
+    {file = "zstandard-0.23.0-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:774d45b1fac1461f48698a9d4b5fa19a69d47ece02fa469825b442263f04021f"},
+    {file = "zstandard-0.23.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6f77fa49079891a4aab203d0b1744acc85577ed16d767b52fc089d83faf8d8ed"},
+    {file = "zstandard-0.23.0-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ac184f87ff521f4840e6ea0b10c0ec90c6b1dcd0bad2f1e4a9a1b4fa177982ea"},
+    {file = "zstandard-0.23.0-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:c363b53e257246a954ebc7c488304b5592b9c53fbe74d03bc1c64dda153fb847"},
+    {file = "zstandard-0.23.0-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:e7792606d606c8df5277c32ccb58f29b9b8603bf83b48639b7aedf6df4fe8171"},
+    {file = "zstandard-0.23.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:a0817825b900fcd43ac5d05b8b3079937073d2b1ff9cf89427590718b70dd840"},
+    {file = "zstandard-0.23.0-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:9da6bc32faac9a293ddfdcb9108d4b20416219461e4ec64dfea8383cac186690"},
+    {file = "zstandard-0.23.0-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:fd7699e8fd9969f455ef2926221e0233f81a2542921471382e77a9e2f2b57f4b"},
+    {file = "zstandard-0.23.0-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:d477ed829077cd945b01fc3115edd132c47e6540ddcd96ca169facff28173057"},
+    {file = "zstandard-0.23.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:fa6ce8b52c5987b3e34d5674b0ab529a4602b632ebab0a93b07bfb4dfc8f8a33"},
+    {file = "zstandard-0.23.0-cp313-cp313-win32.whl", hash = "sha256:a9b07268d0c3ca5c170a385a0ab9fb7fdd9f5fd866be004c4ea39e44edce47dd"},
+    {file = "zstandard-0.23.0-cp313-cp313-win_amd64.whl", hash = "sha256:f3513916e8c645d0610815c257cbfd3242adfd5c4cfa78be514e5a3ebb42a41b"},
+    {file = "zstandard-0.23.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:2ef3775758346d9ac6214123887d25c7061c92afe1f2b354f9388e9e4d48acfc"},
+    {file = "zstandard-0.23.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:4051e406288b8cdbb993798b9a45c59a4896b6ecee2f875424ec10276a895740"},
+    {file = "zstandard-0.23.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e2d1a054f8f0a191004675755448d12be47fa9bebbcffa3cdf01db19f2d30a54"},
+    {file = "zstandard-0.23.0-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f83fa6cae3fff8e98691248c9320356971b59678a17f20656a9e59cd32cee6d8"},
+    {file = "zstandard-0.23.0-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:32ba3b5ccde2d581b1e6aa952c836a6291e8435d788f656fe5976445865ae045"},
+    {file = "zstandard-0.23.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2f146f50723defec2975fb7e388ae3a024eb7151542d1599527ec2aa9cacb152"},
+    {file = "zstandard-0.23.0-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1bfe8de1da6d104f15a60d4a8a768288f66aa953bbe00d027398b93fb9680b26"},
+    {file = "zstandard-0.23.0-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:29a2bc7c1b09b0af938b7a8343174b987ae021705acabcbae560166567f5a8db"},
+    {file = "zstandard-0.23.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:61f89436cbfede4bc4e91b4397eaa3e2108ebe96d05e93d6ccc95ab5714be512"},
+    {file = "zstandard-0.23.0-cp38-cp38-musllinux_1_2_aarch64.whl", hash = "sha256:53ea7cdc96c6eb56e76bb06894bcfb5dfa93b7adcf59d61c6b92674e24e2dd5e"},
+    {file = "zstandard-0.23.0-cp38-cp38-musllinux_1_2_i686.whl", hash = "sha256:a4ae99c57668ca1e78597d8b06d5af837f377f340f4cce993b551b2d7731778d"},
+    {file = "zstandard-0.23.0-cp38-cp38-musllinux_1_2_ppc64le.whl", hash = "sha256:379b378ae694ba78cef921581ebd420c938936a153ded602c4fea612b7eaa90d"},
+    {file = "zstandard-0.23.0-cp38-cp38-musllinux_1_2_s390x.whl", hash = "sha256:50a80baba0285386f97ea36239855f6020ce452456605f262b2d33ac35c7770b"},
+    {file = "zstandard-0.23.0-cp38-cp38-musllinux_1_2_x86_64.whl", hash = "sha256:61062387ad820c654b6a6b5f0b94484fa19515e0c5116faf29f41a6bc91ded6e"},
+    {file = "zstandard-0.23.0-cp38-cp38-win32.whl", hash = "sha256:b8c0bd73aeac689beacd4e7667d48c299f61b959475cdbb91e7d3d88d27c56b9"},
+    {file = "zstandard-0.23.0-cp38-cp38-win_amd64.whl", hash = "sha256:a05e6d6218461eb1b4771d973728f0133b2a4613a6779995df557f70794fd60f"},
+    {file = "zstandard-0.23.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:3aa014d55c3af933c1315eb4bb06dd0459661cc0b15cd61077afa6489bec63bb"},
+    {file = "zstandard-0.23.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:0a7f0804bb3799414af278e9ad51be25edf67f78f916e08afdb983e74161b916"},
+    {file = "zstandard-0.23.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fb2b1ecfef1e67897d336de3a0e3f52478182d6a47eda86cbd42504c5cbd009a"},
+    {file = "zstandard-0.23.0-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:837bb6764be6919963ef41235fd56a6486b132ea64afe5fafb4cb279ac44f259"},
+    {file = "zstandard-0.23.0-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:1516c8c37d3a053b01c1c15b182f3b5f5eef19ced9b930b684a73bad121addf4"},
+    {file = "zstandard-0.23.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:48ef6a43b1846f6025dde6ed9fee0c24e1149c1c25f7fb0a0585572b2f3adc58"},
+    {file = "zstandard-0.23.0-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:11e3bf3c924853a2d5835b24f03eeba7fc9b07d8ca499e247e06ff5676461a15"},
+    {file = "zstandard-0.23.0-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:2fb4535137de7e244c230e24f9d1ec194f61721c86ebea04e1581d9d06ea1269"},
+    {file = "zstandard-0.23.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:8c24f21fa2af4bb9f2c492a86fe0c34e6d2c63812a839590edaf177b7398f700"},
+    {file = "zstandard-0.23.0-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:a8c86881813a78a6f4508ef9daf9d4995b8ac2d147dcb1a450448941398091c9"},
+    {file = "zstandard-0.23.0-cp39-cp39-musllinux_1_2_i686.whl", hash = "sha256:fe3b385d996ee0822fd46528d9f0443b880d4d05528fd26a9119a54ec3f91c69"},
+    {file = "zstandard-0.23.0-cp39-cp39-musllinux_1_2_ppc64le.whl", hash = "sha256:82d17e94d735c99621bf8ebf9995f870a6b3e6d14543b99e201ae046dfe7de70"},
+    {file = "zstandard-0.23.0-cp39-cp39-musllinux_1_2_s390x.whl", hash = "sha256:c7c517d74bea1a6afd39aa612fa025e6b8011982a0897768a2f7c8ab4ebb78a2"},
+    {file = "zstandard-0.23.0-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:1fd7e0f1cfb70eb2f95a19b472ee7ad6d9a0a992ec0ae53286870c104ca939e5"},
+    {file = "zstandard-0.23.0-cp39-cp39-win32.whl", hash = "sha256:43da0f0092281bf501f9c5f6f3b4c975a8a0ea82de49ba3f7100e64d422a1274"},
+    {file = "zstandard-0.23.0-cp39-cp39-win_amd64.whl", hash = "sha256:f8346bfa098532bc1fb6c7ef06783e969d87a99dd1d2a5a18a892c1d7a643c58"},
+    {file = "zstandard-0.23.0.tar.gz", hash = "sha256:b2d8c62d08e7255f68f7a740bae85b3c9b8e5466baa9cbf7f57f1cde0ac6bc09"},
+]
+
+[package.dependencies]
+cffi = {version = ">=1.11", markers = "platform_python_implementation == \"PyPy\""}
+
+[package.extras]
+cffi = ["cffi (>=1.11)"]
+
 [extras]
 instruments = []
 
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.9,<4"
-content-hash = "e80cc2e8dce5dabf8955c32872f48ce503e27dfb1dedc36801bd607f68ba0cd1"
+content-hash = "adfa324f3f8ae7d1437a646f9d392f64244defe52cc8aa822bfb88d09d69c88d"
diff --git a/packages/opentelemetry-instrumentation-langchain/pyproject.toml b/packages/opentelemetry-instrumentation-langchain/pyproject.toml
index 56d0c963ef..a893e9bd01 100644
--- a/packages/opentelemetry-instrumentation-langchain/pyproject.toml
+++ b/packages/opentelemetry-instrumentation-langchain/pyproject.toml
@@ -54,6 +54,7 @@ boto3 = "^1.35.49"
 langchain-anthropic = "^0.3.13"
 langchain-aws = "^0.2.11"
 langchain-openai = "^0.3.1"
+langchain-deepseek = "^0.1.4"
 langchain-cohere = "0.3.1"
 langchain-huggingface = "^0.1.2"
 pydantic = "^2.10.5"
diff --git a/packages/opentelemetry-instrumentation-langchain/tests/conftest.py b/packages/opentelemetry-instrumentation-langchain/tests/conftest.py
index 01930dca3d..fa01420d66 100644
--- a/packages/opentelemetry-instrumentation-langchain/tests/conftest.py
+++ b/packages/opentelemetry-instrumentation-langchain/tests/conftest.py
@@ -26,7 +26,7 @@
 from opentelemetry.sdk.trace.export import SimpleSpanProcessor
 from opentelemetry.sdk.trace.export.in_memory_span_exporter import InMemorySpanExporter
 
-pytest_plugins = []
+pytest_plugins = ["pytest_recording"]
 
 
 @pytest.fixture(scope="session", name="span_exporter")
diff --git a/packages/opentelemetry-instrumentation-langchain/tests/metrics/cassettes/test_langchain_metrics/test_streaming_with_ttft_and_generation_time_metrics.yaml b/packages/opentelemetry-instrumentation-langchain/tests/metrics/cassettes/test_langchain_metrics/test_streaming_with_ttft_and_generation_time_metrics.yaml
new file mode 100644
index 0000000000..607cf66b2c
--- /dev/null
+++ b/packages/opentelemetry-instrumentation-langchain/tests/metrics/cassettes/test_langchain_metrics/test_streaming_with_ttft_and_generation_time_metrics.yaml
@@ -0,0 +1,219 @@
+interactions:
+- request:
+    body: '{"messages": [{"content": "Tell me about machine learning in one sentence",
+      "role": "user"}], "model": "deepseek-chat", "stream": true, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '155'
+      content-type:
+      - application/json
+      host:
+      - api.deepseek.com
+      user-agent:
+      - OpenAI/Python 1.107.3
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.107.3
+      x-stainless-read-timeout:
+      - '600'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.4
+    method: POST
+    uri: https://api.deepseek.com/beta/chat/completions
+  response:
+    body:
+      string: 'data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"content":"Machine"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"content":"
+        learning"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"content":"
+        is"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"content":"
+        the"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"content":"
+        science"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"content":"
+        of"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"content":"
+        getting"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"content":"
+        computers"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"content":"
+        to"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"content":"
+        learn"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"content":"
+        and"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"content":"
+        act"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"content":"
+        like"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"content":"
+        humans"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"content":"
+        do"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"content":"
+        by"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"content":"
+        feeding"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"content":"
+        them"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"content":"
+        data"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"content":"
+        so"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"content":"
+        they"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"content":"
+        can"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"content":"
+        improve"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"content":"
+        their"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"content":"
+        skills"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"content":"
+        over"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"content":"
+        time"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"content":"
+        without"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"content":"
+        being"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"content":"
+        explicitly"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"content":"
+        programmed"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"content":"
+        for"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"content":"
+        every"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"content":"
+        task"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"307419a8-2192-4989-84e7-65af318648c6","object":"chat.completion.chunk","created":1758412658,"model":"deepseek-chat","system_fingerprint":"fp_08f168e49b_prod0820_fp8_kvcache","choices":[{"index":0,"delta":{"content":""},"logprobs":null,"finish_reason":"stop"}],"usage":{"prompt_tokens":12,"completion_tokens":35,"total_tokens":47,"prompt_tokens_details":{"cached_tokens":0},"prompt_cache_hit_tokens":0,"prompt_cache_miss_tokens":12}}
+
+
+        data: [DONE]
+
+
+        '
+    headers:
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Sat, 20 Sep 2025 23:57:38 GMT
+      Server:
+      - CW
+      Set-Cookie:
+      - HWWAFSESTIME=1758412658203; path=/
+      - HWWAFSESID=c458276dfb3ffd1fc4; path=/
+      Strict-Transport-Security:
+      - max-age=31536000; includeSubDomains; preload
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-allow-credentials:
+      - 'true'
+      cache-control:
+      - no-cache
+      vary:
+      - origin, access-control-request-method, access-control-request-headers
+      x-ds-trace-id:
+      - 3e038ffe3306315e3455c2328e839ce7
+    status:
+      code: 200
+      message: OK
+version: 1
diff --git a/packages/opentelemetry-instrumentation-langchain/tests/metrics/test_langchain_metrics.py b/packages/opentelemetry-instrumentation-langchain/tests/metrics/test_langchain_metrics.py
index 22963ce9a3..655fb2acc0 100644
--- a/packages/opentelemetry-instrumentation-langchain/tests/metrics/test_langchain_metrics.py
+++ b/packages/opentelemetry-instrumentation-langchain/tests/metrics/test_langchain_metrics.py
@@ -5,6 +5,8 @@
 from langchain.prompts import PromptTemplate
 from langchain_openai import ChatOpenAI
 from opentelemetry.semconv_ai import Meters, SpanAttributes
+from opentelemetry.semconv.attributes.error_attributes import ERROR_TYPE
+from opentelemetry.semconv._incubating.metrics import gen_ai_metrics as GenAIMetrics
 from langgraph.graph import StateGraph
 from openai import OpenAI
 
@@ -121,6 +123,42 @@ def test_llm_chain_streaming_metrics(instrument_legacy, reader, llm):
                             == "openai"
                         )
 
+                if metric.name == Meters.LLM_GENERATION_CHOICES:
+                    assert any(
+                        data_point.value >= 1 for data_point in metric.data.data_points
+                    )
+                    for data_point in metric.data.data_points:
+                        assert (
+                            data_point.attributes[SpanAttributes.LLM_SYSTEM]
+                            == "openai"
+                        )
+
+                if metric.name == GenAIMetrics.GEN_AI_SERVER_TIME_TO_FIRST_TOKEN:
+                    assert any(
+                        data_point.count > 0 for data_point in metric.data.data_points
+                    )
+                    assert any(
+                        data_point.sum > 0 for data_point in metric.data.data_points
+                    )
+                    for data_point in metric.data.data_points:
+                        assert (
+                            data_point.attributes[SpanAttributes.LLM_SYSTEM]
+                            == "openai"
+                        )
+
+                if metric.name == Meters.LLM_STREAMING_TIME_TO_GENERATE:
+                    assert any(
+                        data_point.count > 0 for data_point in metric.data.data_points
+                    )
+                    assert any(
+                        data_point.sum > 0 for data_point in metric.data.data_points
+                    )
+                    for data_point in metric.data.data_points:
+                        assert (
+                            data_point.attributes[SpanAttributes.LLM_SYSTEM]
+                            == "openai"
+                        )
+
     assert found_token_metric is True
     assert found_duration_metric is True
 
@@ -265,3 +303,148 @@ def calculate(state: State):
             == "openai"
         )
         assert data_point.value > 0
+
+
+@pytest.mark.vcr
+def test_streaming_with_ttft_and_generation_time_metrics(instrument_legacy, reader):
+    """Test streaming metrics with ChatDeepSeek to validate our third-party model fixes."""
+    from langchain_core.prompts import ChatPromptTemplate
+    from langchain_deepseek import ChatDeepSeek
+
+    llm = ChatDeepSeek(
+        api_key="",
+        api_base="https://api.deepseek.com/beta",
+        model="deepseek-chat",
+        temperature=0.7,
+        streaming=True
+    )
+
+    prompt = ChatPromptTemplate.from_template("Tell me about {topic} in one sentence")
+    chain = prompt | llm
+
+    # Stream the response to trigger on_llm_new_token calls
+    response_chunks = []
+    for chunk in chain.stream({"topic": "machine learning"}):
+        response_chunks.append(chunk)
+
+    # Verify we got streaming chunks
+    assert len(response_chunks) > 1, "Should have multiple chunks for streaming"
+
+    metrics_data = reader.get_metrics_data()
+    resource_metrics = metrics_data.resource_metrics
+    assert len(resource_metrics) > 0
+
+    found_token_metric = False
+    found_duration_metric = False
+    found_choices_metric = False
+    found_ttft_metric = False
+    found_streaming_time_metric = False
+
+    for rm in resource_metrics:
+        for sm in rm.scope_metrics:
+            for metric in sm.metrics:
+                if metric.name == Meters.LLM_TOKEN_USAGE:
+                    found_token_metric = True
+                    # Verify ChatDeepSeek model name is correctly extracted
+                    for data_point in metric.data.data_points:
+                        assert data_point.attributes[SpanAttributes.LLM_SYSTEM] == "Langchain"
+                        assert data_point.attributes[SpanAttributes.LLM_RESPONSE_MODEL] == "deepseek-chat"
+                        assert data_point.attributes[SpanAttributes.LLM_TOKEN_TYPE] in ["input", "output"]
+
+                elif metric.name == Meters.LLM_OPERATION_DURATION:
+                    found_duration_metric = True
+                    assert any(
+                        data_point.sum > 0 for data_point in metric.data.data_points
+                    )
+                    # Verify ChatDeepSeek model name
+                    for data_point in metric.data.data_points:
+                        assert data_point.attributes[SpanAttributes.LLM_SYSTEM] == "Langchain"
+                        assert data_point.attributes[SpanAttributes.LLM_RESPONSE_MODEL] == "deepseek-chat"
+
+                elif metric.name == Meters.LLM_GENERATION_CHOICES:
+                    found_choices_metric = True
+                    assert any(
+                        data_point.value >= 1 for data_point in metric.data.data_points
+                    )
+                    # Verify ChatDeepSeek model name
+                    for data_point in metric.data.data_points:
+                        assert data_point.attributes[SpanAttributes.LLM_SYSTEM] == "Langchain"
+                        assert data_point.attributes[SpanAttributes.LLM_RESPONSE_MODEL] == "deepseek-chat"
+
+                elif metric.name == GenAIMetrics.GEN_AI_SERVER_TIME_TO_FIRST_TOKEN:
+                    found_ttft_metric = True
+                    assert any(
+                        data_point.count > 0 for data_point in metric.data.data_points
+                    )
+                    assert any(
+                        data_point.sum > 0 for data_point in metric.data.data_points
+                    )
+                    # Verify our ChatDeepSeek fixes work
+                    for data_point in metric.data.data_points:
+                        assert data_point.attributes[SpanAttributes.LLM_SYSTEM] == "Langchain"
+                        assert data_point.attributes[SpanAttributes.LLM_RESPONSE_MODEL] == "deepseek-chat"
+
+                elif metric.name == Meters.LLM_STREAMING_TIME_TO_GENERATE:
+                    found_streaming_time_metric = True
+                    assert any(
+                        data_point.count > 0 for data_point in metric.data.data_points
+                    )
+                    # Verify our ChatDeepSeek fixes work
+                    for data_point in metric.data.data_points:
+                        assert data_point.attributes[SpanAttributes.LLM_SYSTEM] == "Langchain"
+                        assert data_point.attributes[SpanAttributes.LLM_RESPONSE_MODEL] == "deepseek-chat"
+
+                elif metric.name == "llm.langchain.completions.exceptions":
+                    pass
+
+    assert found_token_metric is True
+    assert found_duration_metric is True
+    assert found_choices_metric is True
+
+    # Since this test specifically uses ChatDeepSeek with streaming=True to validate
+    # our TTFT implementation, these metrics MUST be present
+    assert found_ttft_metric is True, "TTFT metric should be present with ChatDeepSeek streaming"
+    assert found_streaming_time_metric is True, "Streaming time metric should be present with ChatDeepSeek streaming"
+
+    print("All ChatDeepSeek streaming metrics validated successfully")
+
+
+def test_exception_metrics(instrument_legacy, reader):
+    """Test that exception metrics are recorded when LLM calls fail."""
+    from unittest.mock import patch
+
+    llm = ChatOpenAI(model="gpt-3.5-turbo")
+    chain = LLMChain(
+        llm=llm,
+        prompt=PromptTemplate(
+            input_variables=["product"],
+            template="What is a good name for a company that makes {product}?",
+        )
+    )
+
+    # Mock the LLM to raise an exception
+    with patch.object(llm, '_generate', side_effect=Exception("API Error")):
+        try:
+            chain.run(product="test")
+        except Exception:
+            pass  # Expected to fail
+
+    metrics_data = reader.get_metrics_data()
+    resource_metrics = metrics_data.resource_metrics
+    assert len(resource_metrics) > 0
+
+    found_exception_metric = False
+
+    for rm in resource_metrics:
+        for sm in rm.scope_metrics:
+            for metric in sm.metrics:
+                if metric.name == "llm.langchain.completions.exceptions":
+                    found_exception_metric = True
+                    assert any(
+                        data_point.value >= 1 for data_point in metric.data.data_points
+                    )
+                    # Check that error attributes are set
+                    for data_point in metric.data.data_points:
+                        assert "error.type" in data_point.attributes or ERROR_TYPE in data_point.attributes
+
+    assert found_exception_metric is True
diff --git a/packages/opentelemetry-instrumentation-langchain/tests/test_model_extraction.py b/packages/opentelemetry-instrumentation-langchain/tests/test_model_extraction.py
new file mode 100644
index 0000000000..d9b3120640
--- /dev/null
+++ b/packages/opentelemetry-instrumentation-langchain/tests/test_model_extraction.py
@@ -0,0 +1,203 @@
+from unittest.mock import Mock
+from opentelemetry.instrumentation.langchain.span_utils import (
+    _extract_model_name_from_request,
+    _infer_model_from_class_name,
+    extract_model_name_from_response_metadata,
+    SpanHolder,
+)
+from langchain_core.outputs import LLMResult, Generation, ChatGeneration
+from langchain_core.messages import AIMessage
+
+
+class TestModelExtraction:
+    """Test enhanced model name extraction for third-party integrations."""
+
+    def setup_method(self):
+        """Set up test fixtures."""
+        self.mock_span = Mock()
+        self.span_holder = SpanHolder(
+            span=self.mock_span,
+            token=None,
+            context=None,
+            children=[],
+            workflow_name="test",
+            entity_name="test",
+            entity_path="test"
+        )
+
+    def test_standard_model_extraction_from_kwargs(self):
+        """Test standard model extraction from kwargs."""
+        kwargs = {"model": "gpt-4"}
+
+        result = _extract_model_name_from_request(kwargs, self.span_holder)
+        assert result == "gpt-4"
+
+    def test_model_extraction_from_invocation_params(self):
+        """Test model extraction from invocation_params."""
+        kwargs = {
+            "invocation_params": {
+                "model": "claude-3-sonnet"
+            }
+        }
+
+        result = _extract_model_name_from_request(kwargs, self.span_holder)
+        assert result == "claude-3-sonnet"
+
+    def test_deepseek_model_extraction_from_serialized(self):
+        """Test ChatDeepSeek model extraction from serialized data."""
+        kwargs = {}
+        serialized = {
+            "id": ["langchain", "chat_models", "ChatDeepSeek"],
+            "kwargs": {
+                "model": "deepseek-coder",
+                "api_base": "https://api.deepseek.com/beta"
+            }
+        }
+
+        result = _extract_model_name_from_request(kwargs, self.span_holder, serialized)
+        assert result == "deepseek-coder"
+
+    def test_deepseek_fallback_when_no_model_in_serialized(self):
+        """Test ChatDeepSeek fallback to default model."""
+        kwargs = {}
+        serialized = {
+            "id": ["langchain", "chat_models", "ChatDeepSeek"],
+            "kwargs": {
+                "api_base": "https://api.deepseek.com/beta"
+                # No model field
+            }
+        }
+
+        result = _extract_model_name_from_request(kwargs, self.span_holder, serialized)
+        assert result == "deepseek-unknown"
+
+    def test_class_name_inference_for_known_models(self):
+        """Test model inference from class names for known integrations."""
+        test_cases = [
+            ("ChatOpenAI", {}, "gpt-unknown"),
+            ("ChatAnthropic", {}, "claude-unknown"),
+            ("ChatCohere", {}, "command-unknown"),
+            ("ChatOllama", {}, "ollama-unknown"),
+        ]
+
+        for class_name, serialized, expected in test_cases:
+            result = _infer_model_from_class_name(class_name, serialized)
+            assert result == expected, f"Failed for {class_name}"
+
+    def test_unknown_class_returns_unknown(self):
+        """Test that unknown class names return unknown."""
+        result = _infer_model_from_class_name("SomeUnknownModel", {})
+        assert result == "unknown"
+
+    def test_enhanced_response_metadata_extraction(self):
+        """Test enhanced response metadata extraction."""
+
+        # Test with response_metadata
+        message = AIMessage(
+            content="Test response",
+            response_metadata={"model": "deepseek-v2"}
+        )
+        generation = ChatGeneration(message=message)
+        response = LLMResult(generations=[[generation]])
+
+        result = extract_model_name_from_response_metadata(response)
+        assert result == "deepseek-v2"
+
+    def test_response_extraction_from_llm_output(self):
+        """Test model extraction from llm_output."""
+        response = LLMResult(
+            generations=[[Generation(text="Test")]],
+            llm_output={"model": "deepseek-coder-v2"}
+        )
+
+        result = extract_model_name_from_response_metadata(response)
+        assert result == "deepseek-coder-v2"
+
+    def test_response_extraction_from_generation_info(self):
+        """Test model extraction from generation_info."""
+        generation = Generation(
+            text="Test response",
+            generation_info={"model_name": "deepseek-reasoner"}
+        )
+        response = LLMResult(generations=[[generation]])
+
+        result = extract_model_name_from_response_metadata(response)
+        assert result == "deepseek-reasoner"
+
+    def test_model_extraction_priority_order(self):
+        """Test that model extraction follows correct priority order."""
+        # kwargs should have highest priority
+        kwargs = {"model": "from-kwargs"}
+        serialized = {
+            "id": ["ChatDeepSeek"],
+            "kwargs": {"model": "from-serialized"}
+        }
+
+        result = _extract_model_name_from_request(kwargs, self.span_holder, serialized)
+        assert result == "from-kwargs"
+
+        # invocation_params should be second priority
+        kwargs = {
+            "invocation_params": {"model": "from-invocation-params"},
+            "kwargs": {"model": "from-nested-kwargs"}
+        }
+
+        result = _extract_model_name_from_request(kwargs, self.span_holder, serialized)
+        assert result == "from-invocation-params"
+
+    def test_nested_kwargs_extraction(self):
+        """Test extraction from nested kwargs structures."""
+        kwargs = {
+            "kwargs": {"model": "nested-model"}
+        }
+
+        result = _extract_model_name_from_request(kwargs, self.span_holder)
+        assert result == "nested-model"
+
+    def test_model_kwargs_extraction(self):
+        """Test extraction from model_kwargs."""
+        kwargs = {
+            "model_kwargs": {"model_name": "model-from-kwargs"}
+        }
+
+        result = _extract_model_name_from_request(kwargs, self.span_holder)
+        assert result == "model-from-kwargs"
+
+    def test_no_model_info_returns_unknown(self):
+        """Test that missing model info returns unknown."""
+        kwargs = {}
+        serialized = {"id": ["UnknownModel"]}
+
+        result = _extract_model_name_from_request(kwargs, self.span_holder, serialized)
+        assert result == "unknown"
+
+    def test_association_metadata_extraction(self):
+        """Test model extraction from association metadata (ChatDeepSeek pattern)."""
+        kwargs = {}
+        metadata = {"ls_model_name": "deepseek-reasoner"}
+
+        result = _extract_model_name_from_request(kwargs, self.span_holder, None, metadata)
+        assert result == "deepseek-reasoner"
+
+    def test_metadata_has_priority_over_class_inference(self):
+        """Test that association metadata has higher priority than class inference."""
+        kwargs = {}
+        serialized = {
+            "id": ["ChatDeepSeek"],
+            "kwargs": {}  # No model in serialized kwargs
+        }
+        metadata = {"ls_model_name": "deepseek-v3"}
+
+        result = _extract_model_name_from_request(kwargs, self.span_holder, serialized, metadata)
+        assert result == "deepseek-v3"  # Should use metadata, not fallback to "deepseek-chat"
+
+    def test_response_metadata_extraction_returns_none_when_no_model_found(self):
+        """Test that extract_model_name_from_response_metadata returns None when no model info is found."""
+        # Response with no model information anywhere
+        response = LLMResult(
+            generations=[[Generation(text="Response without model info")]],
+            llm_output={"other_field": "value"}  # No model-related fields
+        )
+
+        result = extract_model_name_from_response_metadata(response)
+        assert result is None, "Should return None when no model information is found"
diff --git a/packages/opentelemetry-instrumentation-langchain/tests/test_streaming_metrics.py b/packages/opentelemetry-instrumentation-langchain/tests/test_streaming_metrics.py
new file mode 100644
index 0000000000..10ccfa8c76
--- /dev/null
+++ b/packages/opentelemetry-instrumentation-langchain/tests/test_streaming_metrics.py
@@ -0,0 +1,242 @@
+import time
+from unittest.mock import Mock, patch
+from uuid import uuid4
+from langchain_core.outputs import LLMResult, Generation
+from opentelemetry.instrumentation.langchain.callback_handler import TraceloopCallbackHandler
+from opentelemetry.instrumentation.langchain.span_utils import SpanHolder
+from opentelemetry.semconv_ai import SpanAttributes
+from opentelemetry.trace import Span
+
+
+class TestStreamingMetrics:
+    """Test the new streaming metrics functionality."""
+
+    def setup_method(self):
+        """Set up test fixtures."""
+        self.tracer = Mock()
+        self.duration_histogram = Mock()
+        self.token_histogram = Mock()
+        self.ttft_histogram = Mock()
+        self.streaming_time_histogram = Mock()
+        self.choices_counter = Mock()
+        self.exception_counter = Mock()
+
+        self.handler = TraceloopCallbackHandler(
+            self.tracer,
+            self.duration_histogram,
+            self.token_histogram,
+            self.ttft_histogram,
+            self.streaming_time_histogram,
+            self.choices_counter,
+            self.exception_counter,
+        )
+
+    def test_ttft_metric_recorded_on_first_token(self):
+        """Test that TTFT metric is recorded when first token arrives."""
+        run_id = uuid4()
+        mock_span = Mock(spec=Span)
+        mock_span.attributes = {SpanAttributes.LLM_SYSTEM: "Langchain"}
+
+        # Use mock time for stable testing
+        with patch('opentelemetry.instrumentation.langchain.callback_handler.time.time') as mock_time, \
+             patch('opentelemetry.instrumentation.langchain.span_utils.time.time') as mock_span_time:
+
+            start_time = 1000.0
+            mock_time.return_value = start_time
+            mock_span_time.return_value = start_time
+
+            span_holder = SpanHolder(
+                span=mock_span,
+                token=None,
+                context=None,
+                children=[],
+                workflow_name="test",
+                entity_name="test",
+                entity_path="test",
+                start_time=start_time
+            )
+            self.handler.spans[run_id] = span_holder
+
+            mock_time.return_value = start_time + 0.1
+            mock_span_time.return_value = start_time + 0.1
+            self.handler.on_llm_new_token("Hello", run_id=run_id)
+
+            self.ttft_histogram.record.assert_called_once()
+            args = self.ttft_histogram.record.call_args
+            ttft_value = args[0][0]
+            assert abs(ttft_value - 0.1) < 0.001, f"TTFT should be approximately 0.1 seconds, got {ttft_value}"
+
+            attributes = args[1]["attributes"]
+            assert attributes[SpanAttributes.LLM_SYSTEM] == "Langchain"
+
+    def test_ttft_metric_not_recorded_on_subsequent_tokens(self):
+        """Test that TTFT metric is only recorded once."""
+        run_id = uuid4()
+        mock_span = Mock(spec=Span)
+        mock_span.attributes = {SpanAttributes.LLM_SYSTEM: "Langchain"}
+
+        span_holder = SpanHolder(
+            span=mock_span,
+            token=None,
+            context=None,
+            children=[],
+            workflow_name="test",
+            entity_name="test",
+            entity_path="test",
+            start_time=time.time()
+        )
+        self.handler.spans[run_id] = span_holder
+
+        # First token
+        self.handler.on_llm_new_token("Hello", run_id=run_id)
+        # Second token
+        self.handler.on_llm_new_token(" world", run_id=run_id)
+
+        # TTFT should only be recorded once
+        assert self.ttft_histogram.record.call_count == 1
+
+    def test_generation_choices_metric_recorded(self):
+        """Test that generation choices metric is recorded."""
+        run_id = uuid4()
+        mock_span = Mock(spec=Span)
+        mock_span.attributes = {SpanAttributes.LLM_SYSTEM: "Langchain"}
+
+        span_holder = SpanHolder(
+            span=mock_span,
+            token=None,
+            context=None,
+            children=[],
+            workflow_name="test",
+            entity_name="test",
+            entity_path="test",
+            start_time=time.time()
+        )
+        self.handler.spans[run_id] = span_holder
+
+        # Mock LLMResult with multiple generations
+        generation1 = Generation(text="Response 1")
+        generation2 = Generation(text="Response 2")
+        llm_result = LLMResult(
+            generations=[[generation1, generation2]],
+            llm_output={"model_name": "test-model"}
+        )
+
+        self.handler.on_llm_end(llm_result, run_id=run_id)
+
+        # Verify choices counter was called
+        self.choices_counter.add.assert_called_once_with(
+            2,  # Two choices
+            attributes={
+                SpanAttributes.LLM_SYSTEM: "Langchain",
+                SpanAttributes.LLM_RESPONSE_MODEL: "test-model",
+            }
+        )
+
+    def test_streaming_time_to_generate_metric(self):
+        """Test that streaming time to generate metric is recorded."""
+        run_id = uuid4()
+        mock_span = Mock(spec=Span)
+        mock_span.attributes = {SpanAttributes.LLM_SYSTEM: "Langchain"}
+
+        with patch('opentelemetry.instrumentation.langchain.callback_handler.time.time') as mock_time, \
+             patch('opentelemetry.instrumentation.langchain.span_utils.time.time') as mock_span_time:
+
+            start_time = 1000.0
+            mock_time.return_value = start_time
+            mock_span_time.return_value = start_time
+
+            span_holder = SpanHolder(
+                span=mock_span,
+                token=None,
+                context=None,
+                children=[],
+                workflow_name="test",
+                entity_name="test",
+                entity_path="test",
+                start_time=start_time
+            )
+            self.handler.spans[run_id] = span_holder
+
+            first_token_time = start_time + 0.05
+            mock_time.return_value = first_token_time
+            mock_span_time.return_value = first_token_time
+            self.handler.on_llm_new_token("Hello", run_id=run_id)
+
+            completion_time = first_token_time + 0.05
+            mock_time.return_value = completion_time
+            mock_span_time.return_value = completion_time
+            llm_result = LLMResult(
+                generations=[[Generation(text="Hello world")]],
+                llm_output={"model_name": "test-model"}
+            )
+
+            self.handler.on_llm_end(llm_result, run_id=run_id)
+
+            self.streaming_time_histogram.record.assert_called_once()
+            args = self.streaming_time_histogram.record.call_args
+            streaming_time = args[0][0]
+            assert abs(streaming_time - 0.05) < 0.001, (
+                f"Streaming time should be approximately 0.05 seconds, "
+                f"got {streaming_time}"
+            )
+
+    def test_exception_metric_recorded_on_error(self):
+        """Test that exception metric is recorded on LLM errors."""
+        run_id = uuid4()
+        mock_span = Mock(spec=Span)
+        mock_span.attributes = {SpanAttributes.LLM_SYSTEM: "Langchain"}
+
+        span_holder = SpanHolder(
+            span=mock_span,
+            token=None,
+            context=None,
+            children=[],
+            workflow_name="test",
+            entity_name="test",
+            entity_path="test",
+            start_time=time.time()
+        )
+        self.handler.spans[run_id] = span_holder
+
+        # Simulate error
+        error = ValueError("API Error")
+        self.handler.on_llm_error(error, run_id=run_id)
+
+        # Verify exception counter was called
+        self.exception_counter.add.assert_called_once_with(
+            1,
+            attributes={
+                SpanAttributes.LLM_SYSTEM: "Langchain",
+                SpanAttributes.LLM_RESPONSE_MODEL: "unknown",
+                "error.type": "ValueError",
+            }
+        )
+
+    def test_no_ttft_when_no_first_token_time(self):
+        """Test streaming time metric is not recorded without first token."""
+        run_id = uuid4()
+        mock_span = Mock(spec=Span)
+        mock_span.attributes = {SpanAttributes.LLM_SYSTEM: "Langchain"}
+
+        span_holder = SpanHolder(
+            span=mock_span,
+            token=None,
+            context=None,
+            children=[],
+            workflow_name="test",
+            entity_name="test",
+            entity_path="test",
+            start_time=time.time()
+        )
+        # No first_token_time set
+        self.handler.spans[run_id] = span_holder
+
+        llm_result = LLMResult(
+            generations=[[Generation(text="Response")]],
+            llm_output={"model_name": "test-model"}
+        )
+
+        self.handler.on_llm_end(llm_result, run_id=run_id)
+
+        # Streaming time metric should not be recorded
+        self.streaming_time_histogram.record.assert_not_called()
diff --git a/packages/opentelemetry-instrumentation-langchain/tests/test_third_party_models.py b/packages/opentelemetry-instrumentation-langchain/tests/test_third_party_models.py
new file mode 100644
index 0000000000..ed1fc0dbbc
--- /dev/null
+++ b/packages/opentelemetry-instrumentation-langchain/tests/test_third_party_models.py
@@ -0,0 +1,143 @@
+from unittest.mock import Mock
+from uuid import uuid4
+from opentelemetry.instrumentation.langchain.callback_handler import TraceloopCallbackHandler
+from opentelemetry.instrumentation.langchain.span_utils import SpanHolder
+from opentelemetry.semconv_ai import SpanAttributes
+from langchain_core.outputs import LLMResult, Generation
+
+
+class TestThirdPartyModels:
+    """Test enhanced model extraction for third-party LangChain integrations like ChatDeepSeek."""
+
+    def setup_method(self):
+        self.tracer = Mock()
+        self.duration_histogram = Mock()
+        self.token_histogram = Mock()
+        self.ttft_histogram = Mock()
+        self.streaming_time_histogram = Mock()
+        self.choices_counter = Mock()
+        self.exception_counter = Mock()
+
+        self.handler = TraceloopCallbackHandler(
+            self.tracer,
+            self.duration_histogram,
+            self.token_histogram,
+            self.ttft_histogram,
+            self.streaming_time_histogram,
+            self.choices_counter,
+            self.exception_counter,
+        )
+
+    def test_chatdeepseek_support(self):
+        """Test model extraction and streaming metrics for models that store info in serialized kwargs."""
+        run_id = uuid4()
+
+        # Test model extraction from serialized kwargs
+        serialized = {
+            "id": ["langchain_deepseek", "chat_models", "ChatDeepSeek"],
+            "kwargs": {
+                "model": "deepseek-reasoner",
+                "api_base": "https://api.deepseek.com/beta",
+                "temperature": 0.7
+            }
+        }
+
+        kwargs = {
+            "invocation_params": {
+                "temperature": 0.7
+            }
+        }
+
+        # Start chat model
+        self.handler.on_chat_model_start(
+            serialized=serialized,
+            messages=[],
+            run_id=run_id,
+            kwargs=kwargs
+        )
+
+        # Verify model extraction
+        assert run_id in self.handler.spans
+        span_holder = self.handler.spans[run_id]
+        assert span_holder.request_model == "deepseek-reasoner"
+
+        span = span_holder.span
+        span.set_attribute.assert_any_call(SpanAttributes.LLM_REQUEST_MODEL, "deepseek-reasoner")
+
+        span_attrs = {
+            SpanAttributes.LLM_SYSTEM: "Langchain",
+            SpanAttributes.LLM_REQUEST_TYPE: "chat"
+        }
+        span.attributes = Mock()
+        span.attributes.get = lambda key, default=None: span_attrs.get(key, default)
+
+        # Test fallback behavior when no model in serialized kwargs
+        fallback_serialized = {
+            "id": ["langchain_deepseek", "chat_models", "ChatDeepSeek"],
+            "kwargs": {
+                "api_base": "https://api.deepseek.com/beta"
+                # No model field
+            }
+        }
+
+        run_id_fallback = uuid4()
+        self.handler.on_chat_model_start(
+            serialized=fallback_serialized,
+            messages=[],
+            run_id=run_id_fallback,
+            kwargs={}
+        )
+
+        span_holder_fallback = self.handler.spans[run_id_fallback]
+        assert span_holder_fallback.request_model == "deepseek-unknown"
+
+        # Test response processing without model info in llm_output
+        response = LLMResult(
+            generations=[[Generation(text="Response")]],
+            llm_output={
+                "token_usage": {
+                    "prompt_tokens": 10,
+                    "completion_tokens": 15,
+                    "total_tokens": 25
+                }
+            }
+        )
+
+        self.handler.on_llm_end(response, run_id=run_id)
+
+        # Verify that metrics use correct model name from request fallback
+        token_calls = self.token_histogram.record.call_args_list
+
+        # Verify both calls use correct model name from request fallback
+        assert len(token_calls) == 2, f"Expected 2 token calls, got {len(token_calls)}"
+
+        for call in token_calls:
+            attributes = call[1]["attributes"]
+            assert attributes[SpanAttributes.LLM_RESPONSE_MODEL] == "deepseek-reasoner"
+
+        # Test model variant extraction
+        from opentelemetry.instrumentation.langchain.span_utils import _extract_model_name_from_request
+
+        variant_serialized = {
+            "id": ["langchain_deepseek", "ChatDeepSeek"],
+            "kwargs": {
+                "model": "deepseek-coder-v2",
+                "api_base": "https://api.deepseek.com/beta"
+            }
+        }
+
+        test_span_holder = SpanHolder(
+            span=Mock(),
+            token=None,
+            context=None,
+            children=[],
+            workflow_name="test",
+            entity_name="test",
+            entity_path="test"
+        )
+
+        test_models = ["deepseek-chat", "deepseek-coder", "deepseek-reasoner", "deepseek-coder-v2"]
+        for model in test_models:
+            variant_serialized["kwargs"]["model"] = model
+            result = _extract_model_name_from_request({}, test_span_holder, variant_serialized)
+            assert result == model, f"Failed to extract {model}"