support Anthropic chat models

[wconti27]

Fixes #6055.

Checklist

• Change(s) are motivated and described in the PR description
• Testing strategy is described if automated tests are not included in the PR
• Risks are described (performance impact, potential for breakage, maintainability)
• Change is maintainable (easy to change, telemetry, documentation)
• Library release note guidelines are followed or label changelog/no-changelog is set
• Documentation is included (in-code, generated user docs, public corp docs)
• Backport labels are set (if applicable)
• If this PR changes the public interface, I've notified @DataDog/apm-tees.

Reviewer Checklist

• Title is accurate
• All changes are related to the pull request's stated goal
• Description motivates each change
• Avoids breaking API changes
• Testing strategy adequately addresses listed risks
• Change is maintainable (easy to change, telemetry, documentation)
• Release note makes sense to a user of the library
• 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

[datadog-dd-trace-py-rkomorn]

Datadog Report

Branch report: conti/support-anthropic
Commit report: c118944
Test service: dd-trace-py

❌ 1 Failed (0 Known Flaky), 171831 Passed, 1139 Skipped, 11h 16m 6.38s Total duration (24m 50.11s time saved)

❌ Failed Tests (1)

• test_anthropic_llm_error - test_anthropic.py - Details

  Expand for error

   At request <Request GET /test/session/snapshot >:
      At snapshot (token='tests.contrib.anthropic.test_anthropic.test_anthropic_llm_error'):
       - Directory: /snapshots
       - CI mode: 1
       - Trace File: /snapshots/tests.contrib.anthropic.test_anthropic.test_anthropic_llm_error.json
       - Stats File: /snapshots/tests.contrib.anthropic.test_anthropic.test_anthropic_llm_error_tracestats.json
       At compare of 1 expected trace(s) to 1 received trace(s):
        At trace 'anthropic.request' (1 spans):
         At snapshot compare of span 'anthropic.request' at position 1 in trace:
          - Expected span:
   ...
  

[Yun-Kim]

Looking great! Added some comments to help clear some context / suggestions.

[Yun-Kim]

Suggested change

	for token_type in ("prompt", "completion"):
	for token_type in ("input", "output"):

[wconti27]

why? I thought we were going with prompt and completion for the tag names?

[Yun-Kim]

AnthropicIntegration.record_usage() should be used to tag span metrics for the input/output/total token counts. We should have a separate AnthropicIntegration._set_llmobs_metrics_tags() to return the recorded span metric values, i.e.

def _get_llmobs_metrics_tags(span):
    return {"input_tokens": span.get_metric("anthropic.response.usage.input_tokens"), "output_tokens": ..., "total_tokens": ...}

And set that on the span, i.e. span.set_tag_str(METRICS, json.dumps(self._get_llmobs_metrics_tags(span))

[wconti27]

and we set this tag in the LLMObs Integration correct?