Add back AgentOps as Optional Dependency (#543)

* implements agentops with a langchain handler, agent tracking and tool call recording

* track tool usage

* end session after completion

* track tool usage time

* better tool and llm tracking

* code cleanup

* make agentops optional

* optional dependency usage

* remove telemetry code

* optional agentops

* agentops version bump

* remove org key

* true dependency

* add crew org key to agentops

* cleanup

* Update pyproject.toml

* Revert "true dependency"

This reverts commit e52e8e9568.

* Revert "cleanup"

This reverts commit 7f5635fb9e.

* optional parent key

* agentops 0.1.5

* Revert "Revert "cleanup""

This reverts commit cea33d9a5d.

* Revert "Revert "true dependency""

This reverts commit 4d1b460b

* cleanup

* Forcing version 0.1.5

* Update pyproject.toml

* agentops update

* noop

* add crew tag

* black formatting

* use langchain callback handler to support all LLMs

* agentops version bump

* track task evaluator

* merge upstream

* Fix typo in instruction en.json (#676)

* Enable search in docs (#663)

* Clarify text in docstring (#662)

* Update agent.py (#655)

Changed default model value from gpt-4 to gpt-4o.
Reasoning.
gpt-4 costs 30$ per million tokens while gpt-4o costs 5$.
This is more cost friendly for default option.

* Update README.md (#652)

Rework example so that if you use a custom LLM it doesn't throw code errors by uncommenting.

* Update BrowserbaseLoadTool.md (#647)

* Update crew.py (#644)

Fixed Type on line 53

* fixes #665 (#666)

* Added timestamp to logger (#646)

* Added timestamp to logger

Updated the logger.py file to include timestamps when logging output. For example:

 [2024-05-20 15:32:48][DEBUG]: == Working Agent: Researcher
 [2024-05-20 15:32:48][INFO]: == Starting Task: Research the topic
 [2024-05-20 15:33:22][DEBUG]: == [Researcher] Task output:

* Update tool_usage.py

* Revert "Update tool_usage.py"

This reverts commit 95d18d5b6f.

incorrect bramch for this commit

* support skip auto end session

* conditional protect agentops use

* fix crew logger bug

* fix crew logger bug

* Update crew.py

* Update tool_usage.py

---------

Co-authored-by: João Moura <joaomdmoura@gmail.com>
Co-authored-by: Howard Gil <howardbgil@gmail.com>
Co-authored-by: Olivier Roberdet <niox5199@gmail.com>
Co-authored-by: Paul Sanders <psanders1@gmail.com>
Co-authored-by: Anudeep Kolluri <50168940+Anudeep-Kolluri@users.noreply.github.com>
Co-authored-by: Mike Heavers <heaversm@users.noreply.github.com>
Co-authored-by: Mish Ushakov <10400064+mishushakov@users.noreply.github.com>
Co-authored-by: theCyberTech - Rip&Tear <84775494+theCyberTech@users.noreply.github.com>
Co-authored-by: Saif Mahmud <60409889+vmsaif@users.noreply.github.com>

src/crewai/agent.py

@@ -19,7 +19,20 @@ from crewai.utilities.token_counter_callback import TokenCalcHandler
 from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.utilities.training_handler import CrewTrainingHandler
 
+agentops = None
+try:
+    import agentops
+    from agentops import track_agent
+except ImportError:
 
+    def track_agent():
+        def noop(f):
+            return f
+
+        return noop
+
+
+@track_agent()
 class Agent(BaseAgent):
     """Represents an agent in a system.
 
@@ -48,6 +61,8 @@ class Agent(BaseAgent):
         default=None,
         description="Maximum execution time for an agent to execute a task",
     )
+    agent_ops_agent_name: str = None
+    agent_ops_agent_id: str = None
     cache_handler: InstanceOf[CacheHandler] = Field(
         default=None, description="An instance of the CacheHandler class."
     )
@@ -84,6 +99,7 @@ class Agent(BaseAgent):
     def __init__(__pydantic_self__, **data):
         config = data.pop("config", {})
         super().__init__(**config, **data)
+        __pydantic_self__.agent_ops_agent_name = __pydantic_self__.role
 
     @model_validator(mode="after")
     def set_agent_executor(self) -> "Agent":
@@ -101,6 +117,12 @@ class Agent(BaseAgent):
             ):
                 self.llm.callbacks.append(token_handler)
 
+            if agentops and not any(
+                isinstance(handler, agentops.LangchainCallbackHandler) for handler in self.llm.callbacks
+            ):
+                agentops.stop_instrumenting()
+                self.llm.callbacks.append(agentops.LangchainCallbackHandler())
+
         if not self.agent_executor:
             if not self.cache_handler:
                 self.cache_handler = CacheHandler()