chore: add some shared llm-type plugin utilities

[sabrenner]

What does this PR do?

Adds utilities for llm-based APM tracing plugins for span tags: truncation/normalization and prompt/completion sample rate.

Note that for openai, we changed the name of one config to better respect the namespacing of each config. Additionally, we are not adding the prompt/completion sample rate for openai in this PR - if needed, it can be done in a separate PR.

Aside: I considered making an LlmPlugin type extending TracingPlugin that would just have these methods on their prototype and read from the tracer config in the constructor, but this won't work well for AWS bedrock (which is already a base AWS plugin type), which we'll be updating after this PR lands. It additionally also would've been weird for LangChain (as the handlers are a property of the plugin and not an extension, so the functionality would've had to have been passed as a constructor arg).

Motivation

We'll be adding more APM integrations for llm-based libraries, and they'll need these helpers to reduce code duplication.

[github-actions]

Overall package size

Self size: 8.52 MB
Deduped: 94.88 MB
No deduping: 95.39 MB

Dependency sizes

| name | version | self size | total size | |------|---------|-----------|------------| | @datadog/libdatadog | 0.4.0 | 29.44 MB | 29.44 MB | | @datadog/native-appsec | 8.4.0 | 19.25 MB | 19.26 MB | | @datadog/native-iast-taint-tracking | 3.2.0 | 13.9 MB | 13.91 MB | | @datadog/pprof | 5.4.1 | 9.76 MB | 10.13 MB | | protobufjs | 7.2.5 | 2.77 MB | 5.16 MB | | @datadog/native-iast-rewriter | 2.6.1 | 2.59 MB | 2.73 MB | | @opentelemetry/core | 1.14.0 | 872.87 kB | 1.47 MB | | @datadog/native-metrics | 3.1.0 | 1.06 MB | 1.46 MB | | @opentelemetry/api | 1.8.0 | 1.21 MB | 1.21 MB | | import-in-the-middle | 1.11.2 | 112.74 kB | 826.22 kB | | source-map | 0.7.4 | 226 kB | 226 kB | | opentracing | 0.14.7 | 194.81 kB | 194.81 kB | | lru-cache | 7.18.3 | 133.92 kB | 133.92 kB | | pprof-format | 2.1.0 | 111.69 kB | 111.69 kB | | @datadog/sketches-js | 2.1.0 | 109.9 kB | 109.9 kB | | semver | 7.6.3 | 95.82 kB | 95.82 kB | | lodash.sortby | 4.7.0 | 75.76 kB | 75.76 kB | | ignore | 5.3.1 | 51.46 kB | 51.46 kB | | shell-quote | 1.8.1 | 44.96 kB | 44.96 kB | | istanbul-lib-coverage | 3.2.0 | 29.34 kB | 29.34 kB | | rfdc | 1.3.1 | 25.21 kB | 25.21 kB | | @isaacs/ttlcache | 1.4.1 | 25.2 kB | 25.2 kB | | tlhunter-sorted-set | 0.1.0 | 24.94 kB | 24.94 kB | | limiter | 1.1.5 | 23.17 kB | 23.17 kB | | dc-polyfill | 0.1.4 | 23.1 kB | 23.1 kB | | retry | 0.13.1 | 18.85 kB | 18.85 kB | | jest-docblock | 29.7.0 | 8.99 kB | 12.76 kB | | crypto-randomuuid | 1.0.0 | 11.18 kB | 11.18 kB | | ttl-set | 1.0.0 | 4.61 kB | 9.69 kB | | path-to-regexp | 0.1.12 | 6.6 kB | 6.6 kB | | koalas | 1.0.2 | 6.47 kB | 6.47 kB | | module-details-from-path | 1.0.3 | 4.47 kB | 4.47 kB |

_{🤖 This report was automatically generated by heaviest-objects-in-the-universe}

[pr-commenter]

Benchmarks

Benchmark execution time: 2025-01-23 14:06:15

Comparing candidate commit 1e6665c in PR branch sabrenner/llm-plugin-utils with baseline commit c28765a in branch master.

Found 1 performance improvements and 0 performance regressions! Performance is the same for 907 metrics, 25 unstable metrics.

scenario:plugin-graphql-with-depth-and-collapse-on-18

• 🟩 max_rss_usage [-62.669MB; -55.843MB] or [-6.423%; -5.723%]

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 75.66%. Comparing base (149742b) to head (eb403ed).
Report is 1 commits behind head on master.

Additional details and impacted files

@@             Coverage Diff             @@
##           master    #5109       +/-   ##
===========================================
+ Coverage   61.24%   75.66%   +14.41%     
===========================================
  Files         289      292        +3     
  Lines       13586    13685       +99     
===========================================
+ Hits         8321    10355     +2034     
+ Misses       5265     3330     -1935     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.