posthog 7.4.2__tar.gz → 7.5.0__tar.gz

{posthog-7.4.2/posthog.egg-info → posthog-7.5.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: posthog
-Version: 7.4.2
+Version: 7.5.0
 Summary: Integrate PostHog into any python application.
 Home-page: https://github.com/posthog/posthog-python
 Author: Posthog

{posthog-7.4.2 → posthog-7.5.0}/posthog/__init__.py

@@ -29,6 +29,9 @@ from posthog.contexts import (
 from posthog.contexts import (
     tag as inner_tag,
 )
+from posthog.contexts import (
+    get_tags as inner_get_tags,
+)
 from posthog.exception_utils import (
     DEFAULT_CODE_VARIABLES_IGNORE_PATTERNS,
     DEFAULT_CODE_VARIABLES_MASK_PATTERNS,
@@ -190,6 +193,19 @@ def tag(name: str, value: Any):
     return inner_tag(name, value)
 
 
+def get_tags() -> Dict[str, Any]:
+    """
+    Get all tags from the current context.
+
+    Returns:
+        Dict of all tags in the current context
+
+    Category:
+        Contexts
+    """
+    return inner_get_tags()
+
+
 """Settings."""
 api_key = None  # type: Optional[str]
 host = None  # type: Optional[str]

{posthog-7.4.2 → posthog-7.5.0}/posthog/ai/langchain/callbacks.py

@@ -22,8 +22,8 @@ from uuid import UUID
 
 try:
     # LangChain 1.0+ and modern 0.x with langchain-core
-    from langchain_core.callbacks.base import BaseCallbackHandler
     from langchain_core.agents import AgentAction, AgentFinish
+    from langchain_core.callbacks.base import BaseCallbackHandler
 except (ImportError, ModuleNotFoundError):
     # Fallback for older LangChain versions
     from langchain.callbacks.base import BaseCallbackHandler
@@ -35,15 +35,15 @@ from langchain_core.messages import (
     FunctionMessage,
     HumanMessage,
     SystemMessage,
-    ToolMessage,
     ToolCall,
+    ToolMessage,
 )
 from langchain_core.outputs import ChatGeneration, LLMResult
 from pydantic import BaseModel
 
 from posthog import setup
-from posthog.ai.utils import get_model_params, with_privacy_mode
 from posthog.ai.sanitization import sanitize_langchain
+from posthog.ai.utils import get_model_params, with_privacy_mode
 from posthog.client import Client
 
 log = logging.getLogger("posthog")
@@ -506,6 +506,14 @@ class CallbackHandler(BaseCallbackHandler):
         if isinstance(outputs, BaseException):
             event_properties["$ai_error"] = _stringify_exception(outputs)
             event_properties["$ai_is_error"] = True
+            event_properties = _capture_exception_and_update_properties(
+                self._ph_client,
+                outputs,
+                self._distinct_id,
+                self._groups,
+                event_properties,
+            )
+
         elif outputs is not None:
             event_properties["$ai_output_state"] = with_privacy_mode(
                 self._ph_client, self._privacy_mode, outputs
@@ -576,10 +584,24 @@ class CallbackHandler(BaseCallbackHandler):
         if run.tools:
             event_properties["$ai_tools"] = run.tools
 
+        if self._properties:
+            event_properties.update(self._properties)
+
+        if self._distinct_id is None:
+            event_properties["$process_person_profile"] = False
+
         if isinstance(output, BaseException):
             event_properties["$ai_http_status"] = _get_http_status(output)
             event_properties["$ai_error"] = _stringify_exception(output)
             event_properties["$ai_is_error"] = True
+
+            event_properties = _capture_exception_and_update_properties(
+                self._ph_client,
+                output,
+                self._distinct_id,
+                self._groups,
+                event_properties,
+            )
         else:
             # Add usage
             usage = _parse_usage(output, run.provider, run.model)
@@ -607,12 +629,6 @@ class CallbackHandler(BaseCallbackHandler):
                 self._ph_client, self._privacy_mode, completions
             )
 
-        if self._properties:
-            event_properties.update(self._properties)
-
-        if self._distinct_id is None:
-            event_properties["$process_person_profile"] = False
-
         self._ph_client.capture(
             distinct_id=self._distinct_id or trace_id,
             event="$ai_generation",
@@ -773,9 +789,11 @@ def _parse_usage_model(
             for mapped_key, dataclass_key in field_mapping.items()
         },
     )
-    # For Anthropic providers, LangChain reports input_tokens as the sum of input and cache read tokens.
+    # For Anthropic providers, LangChain reports input_tokens as the sum of all input tokens.
     # Our cost calculation expects them to be separate for Anthropic, so we subtract cache tokens.
-    # For other providers (OpenAI, etc.), input_tokens already includes cache tokens as expected.
+    # Both cache_read and cache_write tokens should be subtracted since Anthropic's raw API
+    # reports input_tokens as tokens NOT read from or used to create a cache.
+    # For other providers (OpenAI, etc.), input_tokens already excludes cache tokens as expected.
     # Match logic consistent with plugin-server: exact match on provider OR substring match on model
     is_anthropic = False
     if provider and provider.lower() == "anthropic":
@@ -783,14 +801,14 @@ def _parse_usage_model(
     elif model and "anthropic" in model.lower():
         is_anthropic = True
 
-    if (
-        is_anthropic
-        and normalized_usage.input_tokens
-        and normalized_usage.cache_read_tokens
-    ):
-        normalized_usage.input_tokens = max(
-            normalized_usage.input_tokens - normalized_usage.cache_read_tokens, 0
+    if is_anthropic and normalized_usage.input_tokens:
+        cache_tokens = (normalized_usage.cache_read_tokens or 0) + (
+            normalized_usage.cache_write_tokens or 0
         )
+        if cache_tokens > 0:
+            normalized_usage.input_tokens = max(
+                normalized_usage.input_tokens - cache_tokens, 0
+            )
     return normalized_usage
 
 
@@ -861,6 +879,27 @@ def _parse_usage(
     return llm_usage
 
 
+def _capture_exception_and_update_properties(
+    client: Client,
+    exception: BaseException,
+    distinct_id: Optional[Union[str, int, UUID]],
+    groups: Optional[Dict[str, Any]],
+    event_properties: Dict[str, Any],
+):
+    if client.enable_exception_autocapture:
+        exception_id = client.capture_exception(
+            exception,
+            distinct_id=distinct_id,
+            groups=groups,
+            properties=event_properties,
+        )
+
+        if exception_id:
+            event_properties["$exception_event_id"] = exception_id
+
+    return event_properties
+
+
 def _get_http_status(error: BaseException) -> int:
     # OpenAI: https://github.com/openai/openai-python/blob/main/src/openai/_exceptions.py
     # Anthropic: https://github.com/anthropics/anthropic-sdk-python/blob/main/src/anthropic/_exceptions.py

{posthog-7.4.2 → posthog-7.5.0}/posthog/ai/utils.py

@@ -2,14 +2,15 @@ import time
 import uuid
 from typing import Any, Callable, Dict, List, Optional, cast
 
-from posthog.client import Client as PostHogClient
-from posthog.ai.types import FormattedMessage, StreamingEventData, TokenUsage
+from posthog import get_tags, identify_context, new_context, tag
 from posthog.ai.sanitization import (
-    sanitize_openai,
     sanitize_anthropic,
     sanitize_gemini,
     sanitize_langchain,
+    sanitize_openai,
 )
+from posthog.ai.types import FormattedMessage, StreamingEventData, TokenUsage
+from posthog.client import Client as PostHogClient
 
 
 def merge_usage_stats(
@@ -256,94 +257,108 @@ def call_llm_and_track_usage(
     usage: TokenUsage = TokenUsage()
     error_params: Dict[str, Any] = {}
 
-    try:
-        response = call_method(**kwargs)
-    except Exception as exc:
-        error = exc
-        http_status = getattr(
-            exc, "status_code", 0
-        )  # default to 0 becuase its likely an SDK error
-        error_params = {
-            "$ai_is_error": True,
-            "$ai_error": exc.__str__(),
-        }
-    finally:
-        end_time = time.time()
-        latency = end_time - start_time
-
-        if posthog_trace_id is None:
-            posthog_trace_id = str(uuid.uuid4())
-
-        if response and (
-            hasattr(response, "usage")
-            or (provider == "gemini" and hasattr(response, "usage_metadata"))
-        ):
-            usage = get_usage(response, provider)
-
-        messages = merge_system_prompt(kwargs, provider)
-        sanitized_messages = sanitize_messages(messages, provider)
-
-        event_properties = {
-            "$ai_provider": provider,
-            "$ai_model": kwargs.get("model") or getattr(response, "model", None),
-            "$ai_model_parameters": get_model_params(kwargs),
-            "$ai_input": with_privacy_mode(
-                ph_client, posthog_privacy_mode, sanitized_messages
-            ),
-            "$ai_output_choices": with_privacy_mode(
-                ph_client, posthog_privacy_mode, format_response(response, provider)
-            ),
-            "$ai_http_status": http_status,
-            "$ai_input_tokens": usage.get("input_tokens", 0),
-            "$ai_output_tokens": usage.get("output_tokens", 0),
-            "$ai_latency": latency,
-            "$ai_trace_id": posthog_trace_id,
-            "$ai_base_url": str(base_url),
-            **(posthog_properties or {}),
-            **(error_params or {}),
-        }
-
-        available_tool_calls = extract_available_tool_calls(provider, kwargs)
-
-        if available_tool_calls:
-            event_properties["$ai_tools"] = available_tool_calls
-
-        cache_read = usage.get("cache_read_input_tokens")
-        if cache_read is not None and cache_read > 0:
-            event_properties["$ai_cache_read_input_tokens"] = cache_read
-
-        cache_creation = usage.get("cache_creation_input_tokens")
-        if cache_creation is not None and cache_creation > 0:
-            event_properties["$ai_cache_creation_input_tokens"] = cache_creation
-
-        reasoning = usage.get("reasoning_tokens")
-        if reasoning is not None and reasoning > 0:
-            event_properties["$ai_reasoning_tokens"] = reasoning
-
-        web_search_count = usage.get("web_search_count")
-        if web_search_count is not None and web_search_count > 0:
-            event_properties["$ai_web_search_count"] = web_search_count
-
-        if posthog_distinct_id is None:
-            event_properties["$process_person_profile"] = False
-
-        # Process instructions for Responses API
-        if provider == "openai" and kwargs.get("instructions") is not None:
-            event_properties["$ai_instructions"] = with_privacy_mode(
-                ph_client, posthog_privacy_mode, kwargs.get("instructions")
+    with new_context(client=ph_client, capture_exceptions=False):
+        if posthog_distinct_id:
+            identify_context(posthog_distinct_id)
+
+        try:
+            response = call_method(**kwargs)
+        except Exception as exc:
+            error = exc
+            http_status = getattr(
+                exc, "status_code", 0
+            )  # default to 0 becuase its likely an SDK error
+            error_params = {
+                "$ai_is_error": True,
+                "$ai_error": exc.__str__(),
+            }
+            # TODO: Add exception capture for OpenAI/Anthropic/Gemini wrappers when
+            # enable_exception_autocapture is True, similar to LangChain callbacks.
+            # See _capture_exception_and_update_properties in langchain/callbacks.py
+        finally:
+            end_time = time.time()
+            latency = end_time - start_time
+
+            if posthog_trace_id is None:
+                posthog_trace_id = str(uuid.uuid4())
+
+            if response and (
+                hasattr(response, "usage")
+                or (provider == "gemini" and hasattr(response, "usage_metadata"))
+            ):
+                usage = get_usage(response, provider)
+
+            messages = merge_system_prompt(kwargs, provider)
+            sanitized_messages = sanitize_messages(messages, provider)
+
+            tag("$ai_provider", provider)
+            tag("$ai_model", kwargs.get("model") or getattr(response, "model", None))
+            tag("$ai_model_parameters", get_model_params(kwargs))
+            tag(
+                "$ai_input",
+                with_privacy_mode(ph_client, posthog_privacy_mode, sanitized_messages),
             )
-
-        # send the event to posthog
-        if hasattr(ph_client, "capture") and callable(ph_client.capture):
-            ph_client.capture(
-                distinct_id=posthog_distinct_id or posthog_trace_id,
-                event="$ai_generation",
-                properties=event_properties,
-                groups=posthog_groups,
+            tag(
+                "$ai_output_choices",
+                with_privacy_mode(
+                    ph_client, posthog_privacy_mode, format_response(response, provider)
+                ),
             )
+            tag("$ai_http_status", http_status)
+            tag("$ai_input_tokens", usage.get("input_tokens", 0))
+            tag("$ai_output_tokens", usage.get("output_tokens", 0))
+            tag("$ai_latency", latency)
+            tag("$ai_trace_id", posthog_trace_id)
+            tag("$ai_base_url", str(base_url))
+
+            available_tool_calls = extract_available_tool_calls(provider, kwargs)
+
+            if available_tool_calls:
+                tag("$ai_tools", available_tool_calls)
+
+            cache_read = usage.get("cache_read_input_tokens")
+            if cache_read is not None and cache_read > 0:
+                tag("$ai_cache_read_input_tokens", cache_read)
+
+            cache_creation = usage.get("cache_creation_input_tokens")
+            if cache_creation is not None and cache_creation > 0:
+                tag("$ai_cache_creation_input_tokens", cache_creation)
+
+            reasoning = usage.get("reasoning_tokens")
+            if reasoning is not None and reasoning > 0:
+                tag("$ai_reasoning_tokens", reasoning)
+
+            web_search_count = usage.get("web_search_count")
+            if web_search_count is not None and web_search_count > 0:
+                tag("$ai_web_search_count", web_search_count)
+
+            if posthog_distinct_id is None:
+                tag("$process_person_profile", False)
+
+            # Process instructions for Responses API
+            if provider == "openai" and kwargs.get("instructions") is not None:
+                tag(
+                    "$ai_instructions",
+                    with_privacy_mode(
+                        ph_client, posthog_privacy_mode, kwargs.get("instructions")
+                    ),
+                )
+
+            # send the event to posthog
+            if hasattr(ph_client, "capture") and callable(ph_client.capture):
+                ph_client.capture(
+                    distinct_id=posthog_distinct_id or posthog_trace_id,
+                    event="$ai_generation",
+                    properties={
+                        **get_tags(),
+                        **(posthog_properties or {}),
+                        **(error_params or {}),
+                    },
+                    groups=posthog_groups,
+                )
 
-    if error:
-        raise error
+        if error:
+            raise error
 
     return response
 
@@ -367,94 +382,108 @@ async def call_llm_and_track_usage_async(
     usage: TokenUsage = TokenUsage()
     error_params: Dict[str, Any] = {}
 
-    try:
-        response = await call_async_method(**kwargs)
-    except Exception as exc:
-        error = exc
-        http_status = getattr(
-            exc, "status_code", 0
-        )  # default to 0 because its likely an SDK error
-        error_params = {
-            "$ai_is_error": True,
-            "$ai_error": exc.__str__(),
-        }
-    finally:
-        end_time = time.time()
-        latency = end_time - start_time
-
-        if posthog_trace_id is None:
-            posthog_trace_id = str(uuid.uuid4())
-
-        if response and (
-            hasattr(response, "usage")
-            or (provider == "gemini" and hasattr(response, "usage_metadata"))
-        ):
-            usage = get_usage(response, provider)
-
-        messages = merge_system_prompt(kwargs, provider)
-        sanitized_messages = sanitize_messages(messages, provider)
-
-        event_properties = {
-            "$ai_provider": provider,
-            "$ai_model": kwargs.get("model") or getattr(response, "model", None),
-            "$ai_model_parameters": get_model_params(kwargs),
-            "$ai_input": with_privacy_mode(
-                ph_client, posthog_privacy_mode, sanitized_messages
-            ),
-            "$ai_output_choices": with_privacy_mode(
-                ph_client, posthog_privacy_mode, format_response(response, provider)
-            ),
-            "$ai_http_status": http_status,
-            "$ai_input_tokens": usage.get("input_tokens", 0),
-            "$ai_output_tokens": usage.get("output_tokens", 0),
-            "$ai_latency": latency,
-            "$ai_trace_id": posthog_trace_id,
-            "$ai_base_url": str(base_url),
-            **(posthog_properties or {}),
-            **(error_params or {}),
-        }
-
-        available_tool_calls = extract_available_tool_calls(provider, kwargs)
-
-        if available_tool_calls:
-            event_properties["$ai_tools"] = available_tool_calls
-
-        cache_read = usage.get("cache_read_input_tokens")
-        if cache_read is not None and cache_read > 0:
-            event_properties["$ai_cache_read_input_tokens"] = cache_read
-
-        cache_creation = usage.get("cache_creation_input_tokens")
-        if cache_creation is not None and cache_creation > 0:
-            event_properties["$ai_cache_creation_input_tokens"] = cache_creation
-
-        reasoning = usage.get("reasoning_tokens")
-        if reasoning is not None and reasoning > 0:
-            event_properties["$ai_reasoning_tokens"] = reasoning
-
-        web_search_count = usage.get("web_search_count")
-        if web_search_count is not None and web_search_count > 0:
-            event_properties["$ai_web_search_count"] = web_search_count
-
-        if posthog_distinct_id is None:
-            event_properties["$process_person_profile"] = False
-
-        # Process instructions for Responses API
-        if provider == "openai" and kwargs.get("instructions") is not None:
-            event_properties["$ai_instructions"] = with_privacy_mode(
-                ph_client, posthog_privacy_mode, kwargs.get("instructions")
+    with new_context(client=ph_client, capture_exceptions=False):
+        if posthog_distinct_id:
+            identify_context(posthog_distinct_id)
+
+        try:
+            response = await call_async_method(**kwargs)
+        except Exception as exc:
+            error = exc
+            http_status = getattr(
+                exc, "status_code", 0
+            )  # default to 0 because its likely an SDK error
+            error_params = {
+                "$ai_is_error": True,
+                "$ai_error": exc.__str__(),
+            }
+            # TODO: Add exception capture for OpenAI/Anthropic/Gemini wrappers when
+            # enable_exception_autocapture is True, similar to LangChain callbacks.
+            # See _capture_exception_and_update_properties in langchain/callbacks.py
+        finally:
+            end_time = time.time()
+            latency = end_time - start_time
+
+            if posthog_trace_id is None:
+                posthog_trace_id = str(uuid.uuid4())
+
+            if response and (
+                hasattr(response, "usage")
+                or (provider == "gemini" and hasattr(response, "usage_metadata"))
+            ):
+                usage = get_usage(response, provider)
+
+            messages = merge_system_prompt(kwargs, provider)
+            sanitized_messages = sanitize_messages(messages, provider)
+
+            tag("$ai_provider", provider)
+            tag("$ai_model", kwargs.get("model") or getattr(response, "model", None))
+            tag("$ai_model_parameters", get_model_params(kwargs))
+            tag(
+                "$ai_input",
+                with_privacy_mode(ph_client, posthog_privacy_mode, sanitized_messages),
             )
-
-        # send the event to posthog
-        if hasattr(ph_client, "capture") and callable(ph_client.capture):
-            ph_client.capture(
-                distinct_id=posthog_distinct_id or posthog_trace_id,
-                event="$ai_generation",
-                properties=event_properties,
-                groups=posthog_groups,
+            tag(
+                "$ai_output_choices",
+                with_privacy_mode(
+                    ph_client, posthog_privacy_mode, format_response(response, provider)
+                ),
             )
+            tag("$ai_http_status", http_status)
+            tag("$ai_input_tokens", usage.get("input_tokens", 0))
+            tag("$ai_output_tokens", usage.get("output_tokens", 0))
+            tag("$ai_latency", latency)
+            tag("$ai_trace_id", posthog_trace_id)
+            tag("$ai_base_url", str(base_url))
+
+            available_tool_calls = extract_available_tool_calls(provider, kwargs)
+
+            if available_tool_calls:
+                tag("$ai_tools", available_tool_calls)
+
+            cache_read = usage.get("cache_read_input_tokens")
+            if cache_read is not None and cache_read > 0:
+                tag("$ai_cache_read_input_tokens", cache_read)
+
+            cache_creation = usage.get("cache_creation_input_tokens")
+            if cache_creation is not None and cache_creation > 0:
+                tag("$ai_cache_creation_input_tokens", cache_creation)
+
+            reasoning = usage.get("reasoning_tokens")
+            if reasoning is not None and reasoning > 0:
+                tag("$ai_reasoning_tokens", reasoning)
+
+            web_search_count = usage.get("web_search_count")
+            if web_search_count is not None and web_search_count > 0:
+                tag("$ai_web_search_count", web_search_count)
+
+            if posthog_distinct_id is None:
+                tag("$process_person_profile", False)
+
+            # Process instructions for Responses API
+            if provider == "openai" and kwargs.get("instructions") is not None:
+                tag(
+                    "$ai_instructions",
+                    with_privacy_mode(
+                        ph_client, posthog_privacy_mode, kwargs.get("instructions")
+                    ),
+                )
+
+            # send the event to posthog
+            if hasattr(ph_client, "capture") and callable(ph_client.capture):
+                ph_client.capture(
+                    distinct_id=posthog_distinct_id or posthog_trace_id,
+                    event="$ai_generation",
+                    properties={
+                        **get_tags(),
+                        **(posthog_properties or {}),
+                        **(error_params or {}),
+                    },
+                    groups=posthog_groups,
+                )
 
-    if error:
-        raise error
+        if error:
+            raise error
 
     return response
 

{posthog-7.4.2 → posthog-7.5.0}/posthog/contexts.py

@@ -62,14 +62,13 @@ class ContextScope:
         return None
 
     def collect_tags(self) -> Dict[str, Any]:
-        tags = self.tags.copy()
         if self.parent and not self.fresh:
             # We want child tags to take precedence over parent tags,
-            # so we can't use a simple update here, instead collecting
-            # the parent tags and then updating with the child tags.
-            new_tags = self.parent.collect_tags()
-            tags.update(new_tags)
-        return tags
+            # so collect parent tags first, then update with child tags.
+            tags = self.parent.collect_tags()
+            tags.update(self.tags)
+            return tags
+        return self.tags.copy()
 
     def get_capture_exception_code_variables(self) -> Optional[bool]:
         if self.capture_exception_code_variables is not None:

{posthog-7.4.2 → posthog-7.5.0}/posthog/test/test_contexts.py

@@ -191,6 +191,32 @@ class TestContexts(unittest.TestCase):
             assert get_context_distinct_id() == "user123"
             assert get_context_session_id() == "session456"
 
+    def test_child_tags_override_parent_tags_in_non_fresh_context(self):
+        with new_context(fresh=True):
+            tag("shared_key", "parent_value")
+            tag("parent_only", "parent")
+
+            with new_context(fresh=False):
+                # Child should inherit parent tags
+                assert get_tags()["parent_only"] == "parent"
+
+                # Child sets same key - should override parent
+                tag("shared_key", "child_value")
+                tag("child_only", "child")
+
+                tags = get_tags()
+                # Child value should win for shared key
+                assert tags["shared_key"] == "child_value"
+                # Both parent and child tags should be present
+                assert tags["parent_only"] == "parent"
+                assert tags["child_only"] == "child"
+
+            # Parent context should be unchanged
+            parent_tags = get_tags()
+            assert parent_tags["shared_key"] == "parent_value"
+            assert parent_tags["parent_only"] == "parent"
+            assert "child_only" not in parent_tags
+
     def test_scoped_decorator_with_context_ids(self):
         @scoped()
         def function_with_context():

{posthog-7.4.2 → posthog-7.5.0}/posthog/version.py

@@ -1,4 +1,4 @@
-VERSION = "7.4.2"
+VERSION = "7.5.0"
 
 if __name__ == "__main__":
     print(VERSION, end="")  # noqa: T201

{posthog-7.4.2 → posthog-7.5.0/posthog.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: posthog
-Version: 7.4.2
+Version: 7.5.0
 Summary: Integrate PostHog into any python application.
 Home-page: https://github.com/posthog/posthog-python
 Author: Posthog