chore(llmobs): [MLOB-3622] reuse tool call tracker for other agentic frameworks (#14277)

This PR updates the Pydantic AI, Crew AI, and LangChain integrations to
support tool call tracking which is used to link LLM and Tool spans in
the LLM Obs service. Currently, this works for Open AI Chat completions
+ tools from the aforementioned integrations, but we can add support for
other LLM / tool spans in the near future.

This PR is based on the ToolCallTracker which was already being used to
link LLM --> Tool --> LLM spans in the Open AI Agents integration. The
ToolCallTracker contains the logic for
1. registering tool call tracking information when we detect an LLM has
chosen to run a particular tool (`on_llm_tool_choice`)
2. linking the LLM span that generated the tool call with the Tool span
itself when it is executed (`on_tool_call`)
3. linking the Tool span to any downstream LLM spans that use the tool
result as an input (`on_tool_call_output_used`)

This PR also adds support for ReAct tool invocations made via the Open
AI Chat API which are tool calls formatted via the content string rather
than a normal tool call struct.

## Important Notes
- I have removed Agent --> Tool --> Agent span links for Pydantic AI
since these span links were mainly for visualization purposes but really
the new LLM --> Tool --> LLM should be used instead.
- I left out tests for CrewAI x OpenAI span linking because I was
running into the same issue as with LiteLLM where patching OpenAI for a
single test works when running that single test but fails to patch
OpenAI correctly when running the entire suite of tests together. In
order to reduce flakiness issues, I have opted for manual testing
instead.

## Manual Testing

### Pydantic AI
```
from pydantic_ai import Agent

def calculate_square(x: int) -> int:
    return x * x

agent = Agent(  
    'openai:gpt-4o',
    system_prompt='Use one of the tools provided to calculate the mathematical operation.',  
    tools=[calculate_square],
)

result = agent.run_sync('What is the square of 5?')  
print(result.output)
```
[resulting
trace](https://app.datadoghq.com/llm/traces?query=%40ml_app%3Anicole-test%20%40event_type%3Aspan%20%40parent_id%3Aundefined&agg_m=count&agg_m_source=base&agg_t=count&fromUser=false&llmPanels=%5B%7B%22t%22%3A%22sampleDetailPanel%22%2C%22rEID%22%3A%22AwAAAZjjHzgXMlRnHgAAABhBWmpqSHpnWEFBQ0J3dk1ja25PekFBQUEAAAAkZjE5OGUzMWYtNjJhMS00YzhkLTkzYTUtYTE2YzE3YWM0NGQwAAAECg%22%7D%5D&spanId=11240522994332064438&start=1756156882647&end=1756157782647&paused=false)

### Crew AI
```
from crewai import Agent, Task, Crew, LLM
from crewai.tools import tool

llm = LLM(
    model="gpt-4o",
)
    
@tool("calculate_sum")
def calculate_sum(min: int, max: int) -> int:
    """Calculate the sum of all numbers between min and max."""
    return sum(range(min, max+1))

calculator = Agent(
    role='Mathematical Calculator',
    goal='Perform accurate mathematical calculations',
    backstory='You are an expert mathematician who can solve complex calculations with precision.',
    llm=llm,
    verbose=True,
    tools=[calculate_sum],
)

calculation_task = Task(
    description='Calculate the sum of all numbers from 1 to 100',
    agent=calculator,
    expected_output='The sum of all numbers from 1 to 100',
    guardrails="hello",
)

crew = Crew(
    agents=[calculator],
    tasks=[calculation_task],
)

result = crew.kickoff()
```
[resulting
trace](https://app.datadoghq.com/llm/traces?query=%40ml_app%3Anicole-test%20%40event_type%3Aspan%20%40parent_id%3Aundefined&agg_m=count&agg_m_source=base&agg_t=count&fromUser=true&llmPanels=%5B%7B%22t%22%3A%22sampleDetailPanel%22%2C%22rEID%22%3A%22AwAAAZjjMje1G3UMxAAAABhBWmpqTWplMUFBRFVCbnhNVk5VZkFBQUEAAAAkZjE5OGUzMzItNWVjZS00MzYzLTlkZTAtMWZhYzA3MzEzMzhmAAACwQ%22%7D%5D&spanId=11094600582484716815&start=1756157503005&end=1756158403005&paused=false)

I also tried running this same app with streaming enabled to verify that
plain text tool calls within the streamed response were captured
properly and spans were linked as expected. Here is the resulting
[trace](https://app.datadoghq.com/llm/traces?query=%40ml_app%3Anicole-test%20%40event_type%3Aspan%20%40parent_id%3Aundefined&agg_m=count&agg_m_source=base&agg_t=count&fromUser=false&llmPanels=%5B%7B%22t%22%3A%22sampleDetailPanel%22%2C%22rEID%22%3A%22AwAAAZjjMBA1pthr5QAAABhBWmpqTUJBMUFBQjU2a1B0RTR6X0FBQUEAAAAkZjE5OGUzMzAtMzg0OS00N2RjLWEwZmYtMGRkOWJlN2UzOGY5AAADEQ%22%7D%5D&spanId=13023585481275335674&start=1756157395103&end=1756158295103&paused=false).

### OpenAI Agents
```
from agents import Agent, function_tool
from agents.run import Runner
import asyncio

@function_tool
def math_help() -> str:
    """
    Answers questions about math.
    """
    return "The answer to the question is 42"

math_tutor_agent = Agent(
    name="Math Tutor",
    handoff_description="Specialist agent for math questions",
    instructions="You provide help with math problems. Please use the tools to find the answer.",
    model="o3-mini",
    tools=[math_help],
)

triage_agent = Agent(
    name="Triage Agent",
    instructions="You determine which agent to use based on the user's homework question",
    handoffs=[math_tutor_agent],
)

async def main():
    result = await Runner.run(triage_agent, "what is the sum of the numbers between 1 and 100?", max_turns=3)
    print(result.final_output)

if __name__ == "__main__":
    asyncio.run(main())
```
[resulting
trace](https://app.datadoghq.com/llm/traces?query=%40ml_app%3Anicole-test%20%40event_type%3Aspan%20%40parent_id%3Aundefined&agg_m=count&agg_m_source=base&agg_t=count&fromUser=false&llmPanels=%5B%7B%22t%22%3A%22sampleDetailPanel%22%2C%22rEID%22%3A%22AwAAAZjjZACIFuYb9wAAABhBWmpqWkFDSUFBQTJRZUZWTk9zakFBQUEAAAAkZjE5OGUzNjQtMzM1NS00NjIxLWE3NmQtMTJjNTlmYTlmYTc5AAABKw%22%7D%5D&spanId=18255958774617952305&start=1756161171215&end=1756162071215&paused=false)

### LangGraph
```
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI
import os
from langchain_core.tools import tool

@tool
def add(a: int, b: int) -> int:
    """Adds two numbers together"""
    return a + b

model = ChatOpenAI(
    model="gpt-4o-mini",
    temperature=0.5,
    api_key=os.getenv("OPENAI_API_KEY", "<not-a-real-key>"),
)

agent = create_react_agent(
    model=model,
    tools=[add],
    prompt="You are a helpful assistant who talks with a Boston accent but is also very nice. You speak in full sentences with at least 15 words. Please use the tools to answer the question.",
    name="not_your_average_bostonian",
)

agent.invoke({"messages": [{"role": "user", "content": "What is 2 + 2?"}]})
```
[resulting
trace](https://app.datadoghq.com/llm/traces?query=%40ml_app%3Anicole-test%20%40event_type%3Aspan%20%40parent_id%3Aundefined&agg_m=count&agg_m_source=base&agg_t=count&fromUser=true&llmPanels=%5B%7B%22t%22%3A%22sampleDetailPanel%22%2C%22rEID%22%3A%22AwAAAZjjbAqZtOj3JQAAABhBWmpqYkFxWkFBQTlySDExekN0bUFBQUEAAAAkMDE5OGUzNmMtMTYwNC00Y2MzLWFlMWUtNGU0MTE4YWY3OWYxAAABlQ%22%7D%5D&spanId=10602121188312712730&start=1756161275437&end=1756162175437&paused=false)

## Checklist
- [x] PR author has checked that all the criteria below are met
- The PR description includes an overview of the change
- The PR description articulates the motivation for the change
- The change includes tests OR the PR description describes a testing
strategy
- The PR description notes risks associated with the change, if any
- Newly-added code is easy to change
- The change follows the [library release note
guidelines](https://ddtrace.readthedocs.io/en/stable/releasenotes.html)
- The change includes or references documentation updates if necessary
- Backport labels are set (if
[applicable](https://ddtrace.readthedocs.io/en/latest/contributing.html#backporting))

## Reviewer Checklist
- [x] Reviewer has checked that all the criteria below are met 
- Title is accurate
- All changes are related to the pull request's stated goal
- Avoids breaking
[API](https://ddtrace.readthedocs.io/en/stable/versioning.html#interfaces)
changes
- Testing strategy adequately addresses listed risks
- Newly-added code is easy to change
- Release note makes sense to a user of the library
- If necessary, author has acknowledged and discussed the performance
implications of this PR as reported in the benchmarks PR comment
- Backport labels are set in a manner that is consistent with the
[release branch maintenance
policy](https://ddtrace.readthedocs.io/en/latest/contributing.html#backporting)

Author: ncybul

.riot/requirements/c215040.txt renamed to .riot/requirements/1010ab9.txt

@@ -2,14 +2,14 @@
 # This file is autogenerated by pip-compile with Python 3.13
 # by the following command:
 #
-#    pip-compile --allow-unsafe --no-annotate .riot/requirements/c215040.in
+#    pip-compile --allow-unsafe --no-annotate .riot/requirements/1010ab9.in
 #
 annotated-types==0.7.0
 anyio==4.10.0
 attrs==25.3.0
 certifi==2025.8.3
-charset-normalizer==3.4.2
-coverage[toml]==7.10.2
+charset-normalizer==3.4.3
+coverage[toml]==7.10.4
 distro==1.9.0
 h11==0.16.0
 httpcore==1.0.9
@@ -20,17 +20,19 @@ iniconfig==2.1.0
 jiter==0.10.0
 jsonpatch==1.33
 jsonpointer==3.0.0
-langchain-core==0.3.72
-langchain-openai==0.3.28
-langgraph==0.6.3
+langchain==0.3.27
+langchain-core==0.3.74
+langchain-openai==0.3.30
+langchain-text-splitters==0.3.9
+langgraph==0.6.5
 langgraph-checkpoint==2.1.1
-langgraph-prebuilt==0.6.3
-langgraph-sdk==0.2.0
-langsmith==0.4.10
+langgraph-prebuilt==0.6.4
+langgraph-sdk==0.2.2
+langsmith==0.4.14
 mock==5.2.0
-openai==1.98.0
+openai==1.100.2
 opentracing==2.4.0
-orjson==3.11.1
+orjson==3.11.2
 ormsgpack==1.10.0
 packaging==25.0
 pluggy==1.6.0
@@ -43,15 +45,16 @@ pytest-cov==6.2.1
 pytest-mock==3.14.1
 pyyaml==6.0.2
 regex==2025.7.34
-requests==2.32.4
+requests==2.32.5
 requests-toolbelt==1.0.0
 sniffio==1.3.1
 sortedcontainers==2.4.0
+sqlalchemy==2.0.43
 tenacity==9.1.2
-tiktoken==0.9.0
+tiktoken==0.11.0
 tqdm==4.67.1
 typing-extensions==4.14.1
 typing-inspection==0.4.1
 urllib3==2.5.0
 xxhash==3.5.0
-zstandard==0.23.0
+zstandard==0.24.0

.riot/requirements/7fc9a52.txt renamed to .riot/requirements/10f2f3e.txt

@@ -2,15 +2,16 @@
 # This file is autogenerated by pip-compile with Python 3.10
 # by the following command:
 #
-#    pip-compile --allow-unsafe --no-annotate .riot/requirements/7fc9a52.in
+#    pip-compile --allow-unsafe --no-annotate .riot/requirements/10f2f3e.in
 #
 annotated-types==0.7.0
 anyio==4.10.0
+async-timeout==4.0.3
 attrs==25.3.0
 backports-asyncio-runner==1.2.0
 certifi==2025.8.3
-charset-normalizer==3.4.2
-coverage[toml]==7.10.2
+charset-normalizer==3.4.3
+coverage[toml]==7.10.4
 distro==1.9.0
 exceptiongroup==1.3.0
 h11==0.16.0
@@ -22,17 +23,19 @@ iniconfig==2.1.0
 jiter==0.10.0
 jsonpatch==1.33
 jsonpointer==3.0.0
-langchain-core==0.3.72
-langchain-openai==0.3.28
-langgraph==0.6.3
+langchain==0.3.27
+langchain-core==0.3.74
+langchain-openai==0.3.30
+langchain-text-splitters==0.3.9
+langgraph==0.6.5
 langgraph-checkpoint==2.1.1
-langgraph-prebuilt==0.6.3
-langgraph-sdk==0.2.0
-langsmith==0.4.10
+langgraph-prebuilt==0.6.4
+langgraph-sdk==0.2.2
+langsmith==0.4.14
 mock==5.2.0
-openai==1.98.0
+openai==1.100.2
 opentracing==2.4.0
-orjson==3.11.1
+orjson==3.11.2
 ormsgpack==1.10.0
 packaging==25.0
 pluggy==1.6.0
@@ -45,16 +48,17 @@ pytest-cov==6.2.1
 pytest-mock==3.14.1
 pyyaml==6.0.2
 regex==2025.7.34
-requests==2.32.4
+requests==2.32.5
 requests-toolbelt==1.0.0
 sniffio==1.3.1
 sortedcontainers==2.4.0
+sqlalchemy==2.0.43
 tenacity==9.1.2
-tiktoken==0.9.0
+tiktoken==0.11.0
 tomli==2.2.1
 tqdm==4.67.1
 typing-extensions==4.14.1
 typing-inspection==0.4.1
 urllib3==2.5.0
 xxhash==3.5.0
-zstandard==0.23.0
+zstandard==0.24.0

.riot/requirements/1014e75.txt renamed to .riot/requirements/11e37fa.txt

@@ -2,14 +2,14 @@
 # This file is autogenerated by pip-compile with Python 3.13
 # by the following command:
 #
-#    pip-compile --allow-unsafe --no-annotate .riot/requirements/1014e75.in
+#    pip-compile --allow-unsafe --no-annotate .riot/requirements/11e37fa.in
 #
 annotated-types==0.7.0
 anyio==4.10.0
 attrs==25.3.0
 certifi==2025.8.3
-charset-normalizer==3.4.2
-coverage[toml]==7.10.2
+charset-normalizer==3.4.3
+coverage[toml]==7.10.4
 distro==1.9.0
 h11==0.16.0
 httpcore==1.0.9
@@ -20,17 +20,19 @@ iniconfig==2.1.0
 jiter==0.10.0
 jsonpatch==1.33
 jsonpointer==3.0.0
-langchain-core==0.3.72
-langchain-openai==0.3.28
+langchain==0.3.27
+langchain-core==0.3.74
+langchain-openai==0.3.30
+langchain-text-splitters==0.3.9
 langgraph==0.3.22
 langgraph-checkpoint==2.1.1
 langgraph-prebuilt==0.1.8
 langgraph-sdk==0.1.74
-langsmith==0.4.10
+langsmith==0.4.14
 mock==5.2.0
-openai==1.98.0
+openai==1.100.2
 opentracing==2.4.0
-orjson==3.11.1
+orjson==3.11.2
 ormsgpack==1.10.0
 packaging==25.0
 pluggy==1.6.0
@@ -43,15 +45,16 @@ pytest-cov==6.2.1
 pytest-mock==3.14.1
 pyyaml==6.0.2
 regex==2025.7.34
-requests==2.32.4
+requests==2.32.5
 requests-toolbelt==1.0.0
 sniffio==1.3.1
 sortedcontainers==2.4.0
+sqlalchemy==2.0.43
 tenacity==9.1.2
-tiktoken==0.9.0
+tiktoken==0.11.0
 tqdm==4.67.1
 typing-extensions==4.14.1
 typing-inspection==0.4.1
 urllib3==2.5.0
 xxhash==3.5.0
-zstandard==0.23.0
+zstandard==0.24.0

.riot/requirements/60408b5.txt renamed to .riot/requirements/148cc44.txt

@@ -2,15 +2,16 @@
 # This file is autogenerated by pip-compile with Python 3.10
 # by the following command:
 #
-#    pip-compile --allow-unsafe --no-annotate .riot/requirements/60408b5.in
+#    pip-compile --allow-unsafe --no-annotate .riot/requirements/148cc44.in
 #
 annotated-types==0.7.0
 anyio==4.10.0
+async-timeout==4.0.3
 attrs==25.3.0
 backports-asyncio-runner==1.2.0
 certifi==2025.8.3
-charset-normalizer==3.4.2
-coverage[toml]==7.10.2
+charset-normalizer==3.4.3
+coverage[toml]==7.10.4
 distro==1.9.0
 exceptiongroup==1.3.0
 h11==0.16.0
@@ -22,16 +23,18 @@ iniconfig==2.1.0
 jiter==0.10.0
 jsonpatch==1.33
 jsonpointer==3.0.0
-langchain-core==0.3.72
-langchain-openai==0.3.28
+langchain==0.3.27
+langchain-core==0.3.74
+langchain-openai==0.3.30
+langchain-text-splitters==0.3.9
 langgraph==0.2.23
 langgraph-checkpoint==1.0.12
-langsmith==0.4.10
+langsmith==0.4.14
 mock==5.2.0
 msgpack==1.1.1
-openai==1.98.0
+openai==1.100.2
 opentracing==2.4.0
-orjson==3.11.1
+orjson==3.11.2
 packaging==25.0
 pluggy==1.6.0
 pydantic==2.11.7
@@ -43,15 +46,16 @@ pytest-cov==6.2.1
 pytest-mock==3.14.1
 pyyaml==6.0.2
 regex==2025.7.34
-requests==2.32.4
+requests==2.32.5
 requests-toolbelt==1.0.0
 sniffio==1.3.1
 sortedcontainers==2.4.0
+sqlalchemy==2.0.43
 tenacity==9.1.2
-tiktoken==0.9.0
+tiktoken==0.11.0
 tomli==2.2.1
 tqdm==4.67.1
 typing-extensions==4.14.1
 typing-inspection==0.4.1
 urllib3==2.5.0
-zstandard==0.23.0
+zstandard==0.24.0

.riot/requirements/3fed352.txt renamed to .riot/requirements/14bb28e.txt

@@ -2,14 +2,14 @@
 # This file is autogenerated by pip-compile with Python 3.11
 # by the following command:
 #
-#    pip-compile --allow-unsafe --no-annotate .riot/requirements/3fed352.in
+#    pip-compile --allow-unsafe --no-annotate .riot/requirements/14bb28e.in
 #
 annotated-types==0.7.0
 anyio==4.10.0
 attrs==25.3.0
 certifi==2025.8.3
-charset-normalizer==3.4.2
-coverage[toml]==7.10.2
+charset-normalizer==3.4.3
+coverage[toml]==7.10.4
 distro==1.9.0
 h11==0.16.0
 httpcore==1.0.9
@@ -20,16 +20,18 @@ iniconfig==2.1.0
 jiter==0.10.0
 jsonpatch==1.33
 jsonpointer==3.0.0
-langchain-core==0.3.72
-langchain-openai==0.3.28
+langchain==0.3.27
+langchain-core==0.3.74
+langchain-openai==0.3.30
+langchain-text-splitters==0.3.9
 langgraph==0.2.23
 langgraph-checkpoint==1.0.12
-langsmith==0.4.10
+langsmith==0.4.14
 mock==5.2.0
 msgpack==1.1.1
-openai==1.98.0
+openai==1.100.2
 opentracing==2.4.0
-orjson==3.11.1
+orjson==3.11.2
 packaging==25.0
 pluggy==1.6.0
 pydantic==2.11.7
@@ -41,14 +43,15 @@ pytest-cov==6.2.1
 pytest-mock==3.14.1
 pyyaml==6.0.2
 regex==2025.7.34
-requests==2.32.4
+requests==2.32.5
 requests-toolbelt==1.0.0
 sniffio==1.3.1
 sortedcontainers==2.4.0
+sqlalchemy==2.0.43
 tenacity==9.1.2
-tiktoken==0.9.0
+tiktoken==0.11.0
 tqdm==4.67.1
 typing-extensions==4.14.1
 typing-inspection==0.4.1
 urllib3==2.5.0
-zstandard==0.23.0
+zstandard==0.24.0

.riot/requirements/5858798.txt renamed to .riot/requirements/153586b.txt

@@ -2,14 +2,14 @@
 # This file is autogenerated by pip-compile with Python 3.11
 # by the following command:
 #
-#    pip-compile --allow-unsafe --no-annotate .riot/requirements/5858798.in
+#    pip-compile --allow-unsafe --no-annotate .riot/requirements/153586b.in
 #
 annotated-types==0.7.0
 anyio==4.10.0
 attrs==25.3.0
 certifi==2025.8.3
-charset-normalizer==3.4.2
-coverage[toml]==7.10.2
+charset-normalizer==3.4.3
+coverage[toml]==7.10.4
 distro==1.9.0
 h11==0.16.0
 httpcore==1.0.9
@@ -20,17 +20,19 @@ iniconfig==2.1.0
 jiter==0.10.0
 jsonpatch==1.33
 jsonpointer==3.0.0
-langchain-core==0.3.72
-langchain-openai==0.3.28
+langchain==0.3.27
+langchain-core==0.3.74
+langchain-openai==0.3.30
+langchain-text-splitters==0.3.9
 langgraph==0.3.22
 langgraph-checkpoint==2.1.1
 langgraph-prebuilt==0.1.8
 langgraph-sdk==0.1.74
-langsmith==0.4.10
+langsmith==0.4.14
 mock==5.2.0
-openai==1.98.0
+openai==1.100.2
 opentracing==2.4.0
-orjson==3.11.1
+orjson==3.11.2
 ormsgpack==1.10.0
 packaging==25.0
 pluggy==1.6.0
@@ -43,15 +45,16 @@ pytest-cov==6.2.1
 pytest-mock==3.14.1
 pyyaml==6.0.2
 regex==2025.7.34
-requests==2.32.4
+requests==2.32.5
 requests-toolbelt==1.0.0
 sniffio==1.3.1
 sortedcontainers==2.4.0
+sqlalchemy==2.0.43
 tenacity==9.1.2
-tiktoken==0.9.0
+tiktoken==0.11.0
 tqdm==4.67.1
 typing-extensions==4.14.1
 typing-inspection==0.4.1
 urllib3==2.5.0
 xxhash==3.5.0
-zstandard==0.23.0
+zstandard==0.24.0