feat(contrib/mark3labs/mcp-go): expose captured intent to tool handlers via context

[jboolean]

This PR stack ports functionality added in the clone of this contrib in dd-source back to dd-trace-go so that the clone can be removed.

Summary

The intent-capture middleware annotates the LLMObs span with the client-supplied telemetry.intent, but tool handlers had no way to read it without re-parsing the telemetry blob — which the same middleware strips before the handler runs.

This change:

• Stashes the captured intent on context.Context alongside the existing LLMObs annotation.
• Exports IntentFromContext(ctx) (string, bool) and ContextWithIntent(ctx, intent) context.Context so tool handlers can forward the intent downstream (e.g. to a search API for retrieval/ranking experiments).
• Refactors the previous processTelemetry into extractIntent + annotateIntentOnSpan for clarity; behavior is otherwise unchanged.

Ported from internal dd-source PR #443664.

Test plan

• TestIntentFromContext — round-trip + empty-intent + missing-key behavior.
• TestIntentCaptureStashesIntentOnContext — end-to-end: a tools/call with telemetry.intent makes the value visible to the handler via IntentFromContext.
• Existing intent-capture tests still pass.

Stacked on #4940.

[jboolean]

• feat(contrib/mark3labs/mcp-go): support redacting tool output in LLMObs traces #4945
• feat(contrib/mark3labs/mcp-go): support per-request intent capture #4944
• feat(contrib/mark3labs/mcp-go): set session ID on tool spans at start time #4943
• feat(contrib/mark3labs/mcp-go): skip telemetry injection for UI-only tools #4942
• feat(contrib/mark3labs/mcp-go): expose captured intent to tool handlers via context #4941 👈 (View in Graphite)
• fix(contrib/mark3labs/mcp-go): preserve raw input schema fields on intent injection #4946
• fix(contrib/mark3labs/mcp-go): avoid map race when normalizing RawInputSchema #4940
• feat(contrib/mark3labs/mcp-go): support intent capture for tools using RawInputSchema #4939
• main

This stack of pull requests is managed by Graphite. Learn more about stacking.

[datadog-datadog-prod-us1-2]

🎉 All green!

🧪 All tests passed
❄️ No new flaky tests detected

🎯 Code Coverage (details)
• Patch Coverage: 57.89%
• Overall Coverage: 62.80%

_{This comment will be updated automatically if new data arrives.
🔗 Commit SHA: 2de53a9 | Docs | Datadog PR Page | Give us feedback!}

[pr-commenter]

Benchmarks

Benchmark execution time: 2026-07-01 16:38:39

Comparing candidate commit 2de53a9 in PR branch jb/mcp-intent-from-context with baseline commit e46fd46 in branch jb/mcp-preserve-raw-schema-fields.

Found 0 performance improvements and 0 performance regressions! Performance is the same for 321 metrics, 2 unstable metrics, 1 flaky benchmarks without significant changes.

Explanation

This is an A/B test comparing a candidate commit's performance against that of a baseline commit. Performance changes are noted in the tables below as:

• 🟩 = significantly better candidate vs. baseline
• 🟥 = significantly worse candidate vs. baseline

We compute a confidence interval (CI) over the relative difference of means between metrics from the candidate and baseline commits, considering the baseline as the reference.

If the CI is entirely outside the configured SIGNIFICANT_IMPACT_THRESHOLD (or the deprecated UNCONFIDENCE_THRESHOLD), the change is considered significant.

Feel free to reach out to #apm-benchmarking-platform on Slack if you have any questions.

More details about the CI and significant changes

You can imagine this CI as a range of values that is likely to contain the true difference of means between the candidate and baseline commits.

CIs of the difference of means are often centered around 0%, because often changes are not that big:

---------------------------------(------|---^--------)-------------------------------->
                              -0.6%    0%  0.3%     +1.2%
                                 |          |        |
         lower bound of the CI --'          |        |
sample mean (center of the CI) -------------'        |
         upper bound of the CI ----------------------'

As described above, a change is considered significant if the CI is entirely outside the configured SIGNIFICANT_IMPACT_THRESHOLD (or the deprecated UNCONFIDENCE_THRESHOLD).

For instance, for an execution time metric, this confidence interval indicates a significantly worse performance:

----------------------------------------|---------|---(---------^---------)---------->
                                       0%        1%  1.3%      2.2%      3.1%
                                                  |   |         |         |
       significant impact threshold --------------'   |         |         |
                      lower bound of CI --------------'         |         |
       sample mean (center of the CI) --------------------------'         |
                      upper bound of CI ----------------------------------'

Known flaky benchmarks

These benchmarks are marked as flaky and will not trigger a failure. Modify FLAKY_BENCHMARKS_REGEX to control which benchmarks are marked as flaky.

Known flaky benchmarks without significant changes:

• scenario:BenchmarkOTLPTraceWriterFlush