feat(otlp): Improved support for OTLP JSON metrics serialization (NaN,Infinity,-Infinity)

[LorenzoTettamanti]

Updates #3442

Changes

• Added Serialize/Deserialization for NaN,Infinity,-Infinity to the following metrics fields:

Source	Field	Type
HistogramDataPoint	sum, min, max	Option<f64>
HistogramDataPoint	explicit_bounds	Vec<f64>
ExponentialHistogramDataPoint	sum, min, max	Option<f64>
ExponentialHistogramDataPoint	zero_threshold	f64
SummaryDataPoint	sum	f64
NumberDataPoint::Value	AsDouble	f64
Exemplar::Value	AsDouble	f64
AnyValue	DoubleValue	f64

• Added regression tests covering NaN/Infinity serialization/deserialization for each affected field

Merge requirement checklist

• CONTRIBUTING guidelines followed
• Unit tests added/updated (if applicable)
• Appropriate CHANGELOG.md files updated for non-trivial, user-facing changes
• Changes in public API reviewed (if applicable)

[linux-foundation-easycla]

The committers listed above are authorized under a signed CLA.

• ✅ login: LorenzoTettamanti / name: Lorenzo Tettamanti (0dea8f9, 21127ad, 2484305, 58e119c, 6fc8fb2, 9d5ab97, 9fe7423, b4468d6, c014dc0, d4be6f1, e0201d4, f163b45, fa705eb, fbb4f89)
• ✅ login: LorenzoTettamanti / name: LorenzoTettamanti (10011b6, 20e3925, 3595751, 5d092b4, 64b2d7f, 71bffa6, 84d4765, ac74194, afd9f8d, c9c6ec8, e0a62ff, e43e731, ed26090, f2f4fd9)
• ✅ login: lazureykis / name: Pavel Lazureykis (452f5e8)

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 84.2%. Comparing base (02b2f15) to head (9995858).

Additional details and impacted files

@@          Coverage Diff          @@
##            main   #3496   +/-   ##
=====================================
  Coverage   84.2%   84.2%           
=====================================
  Files        123     123           
  Lines      30484   30484           
=====================================
  Hits       25686   25686           
  Misses      4798    4798           

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

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[lazureykis]

Hi @LorenzoTettamanti — while reading the Option<f64> path I hit what looks like a round-trip regression for histograms and wanted to check it with you.

HistogramDataPoint/ExponentialHistogramDataPoint sum/min/max are Option<f64> with no skip_serializing_if, so when they're None the output contains "min":null (etc.). On serialize that's fine — serialize_option_f64_special emits null for None, same as main. But deserialize_option_f64_special calls deserialize_any, and its OptionF64Visitor only implements visit_f64/visit_u64/visit_i64/visit_str — there's no visit_unit/visit_none. serde_json routes JSON null to visit_unit, whose default impl errors, so the value fails to parse.

The effect is that the crate can no longer deserialize its own serialized output whenever a histogram leaves min/max/sum unset (a common case — min/max are optional and sum is omitted for non-monotonic histograms). On main this round-trips because the default Option<f64> deserializer handles null → None.

Minimal repro (serialize a HistogramDataPoint with min/max/sum = None, then deserialize the result): https://github.com/lazureykis/opentelemetry-rust/blob/58640d270b674ee03d9808ef210c454c379cf0fc/opentelemetry-proto/tests/histogram_none_f64_roundtrip_evidence.rs

It serializes to {...,"sum":null,...,"min":null,"max":null} and then panics on deserialize:
Error("invalid type: null, expected a float or a string representing NaN, Infinity, or -Infinity", line: 1, column: 82). The same test passes on main.

Would it make sense to have the visitor accept null — e.g. add visit_unit/visit_none returning Ok(None) (using deserialize_option so visit_none is reached)? Adding skip_serializing_if = "Option::is_none" to those fields would also stop emitting null, though that's a separate, pre-existing point and wouldn't cover external input that sends explicit null. What do you think?

[LorenzoTettamanti]

Hi @lazureykis , that's a great catch. I think that's a great idea to implement the visit_unit and visit_none in the OptionF64Visitor (using deserialize_option) so visit_none is reached for null values. Also adding skip_serializing_if = "Option::is_none" it's a great idea and would help to reduce the JSON

[opentelemetry-pr-dashboard]

Pull request dashboard status

Waiting on reviewers · refreshed 2026-10-17 22:31 UTC

Review the latest changes.

Status above doesn't look right?

• Just replied or pushed? Anything around or after the refresh time above may not be picked up yet — give it a few minutes.
• Anything look wrong? Report it with what you expected; it helps us improve the dashboard.

[LorenzoTettamanti]

/dashboard route:reviewers

[opentelemetry-pr-dashboard]

@LorenzoTettamanti, this pull request was routed to reviewers. The handoff remains active across pushes until newer actionable human feedback arrives. Top-level feedback through this request will not return; unresolved review threads remain open.

[LorenzoTettamanti]

/dashboard route:reviewers

[opentelemetry-pr-dashboard]

@LorenzoTettamanti, this pull request was routed to reviewers. The handoff remains active across pushes until newer actionable human feedback arrives. Top-level feedback through this request will not return; unresolved review threads remain open.

[LorenzoTettamanti]

/dashboard route:reviewers

[opentelemetry-pr-dashboard]

@LorenzoTettamanti, this pull request was routed to reviewers. The handoff remains active across pushes until newer actionable human feedback arrives. Top-level feedback through this request will not return; unresolved review threads remain open.

[LorenzoTettamanti]

Hi @darkraider01, thanks for the review! I applied your fixes. Let me know if something is missing!