feat(llmobs): store function name for function call cases

[Yun-Kim]

This PR adds two small changes as a follow up to #8950:

1. Perform the same formatting [tool: <function_name>]\n\n<function_args> for non-streamed cases as streamed cases
2. Add function names for the deprecated function_call feature (as opposed to the tool_call option)

This only affects LLMObs payloads (not APM traces), so this doesn't need a changelog.

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: yunkim/llmobs-openai-tool-call-stream
Commit report: cd1ceda
Test service: dd-trace-py

✅ 0 Failed, 950 Passed, 2242 Skipped, 20m 37.82s Total duration (58m 0.61s time saved)

[pr-commenter]

Benchmarks

Benchmark execution time: 2024-04-15 21:07:35

Comparing candidate commit 587c96d in PR branch yunkim/llmobs-openai-tool-call-stream with baseline commit 60763e1 in branch main.

Found 7 performance improvements and 1 performance regressions! Performance is the same for 193 metrics, 9 unstable metrics.

scenario:flasksimple-appsec-telemetry

• 🟩 execution_time [-261.509µs; -211.720µs] or [-4.019%; -3.254%]

scenario:httppropagationextract-datadog_tracecontext_tracestate_not_propagated_on_trace_id_no_match

• 🟥 max_rss_usage [+692.972KB; +768.072KB] or [+3.275%; +3.630%]

scenario:httppropagationinject-ids_only

• 🟩 max_rss_usage [-772.821KB; -722.628KB] or [-3.531%; -3.301%]

scenario:httppropagationinject-with_dd_origin

• 🟩 max_rss_usage [-1.073MB; -1.024MB] or [-4.909%; -4.687%]

scenario:httppropagationinject-with_sampling_priority

• 🟩 max_rss_usage [-771.830KB; -714.198KB] or [-3.529%; -3.265%]

scenario:httppropagationinject-with_tags

• 🟩 max_rss_usage [-675.301KB; -624.360KB] or [-3.085%; -2.852%]

scenario:httppropagationinject-with_tags_invalid

• 🟩 max_rss_usage [-613.182KB; -561.551KB] or [-2.807%; -2.571%]

scenario:httppropagationinject-with_tags_max_size

• 🟩 max_rss_usage [-627.663KB; -578.609KB] or [-2.873%; -2.648%]

[sabrenner]

lgtm