test: fail the build when the six handlers drift apart again

[apucacao]

Adds the tests that fail when the six handlers drift apart again.

Every handler package tests its own spans, and each was correct on its own terms while a single run emitted chat spans that disagreed about what a finish reason or a cached token was. Nothing tested that the six agree, which is the property that actually matters and the one that broke.

These live outside the packages, because no package can own an invariant about all six.

Two kinds of check

Shape checks call each package's span constructors directly with a recording tracer, so they need no provider mocks and cannot be fooled by a handler that never reaches its own span code. They pin the three span names, the root's operation attribute, and the rule that the launchdarkly.* identity and the feature_flag event appear on the root and nowhere else.

Two of them exist because of specific mistakes this work nearly shipped: gen_ai.system on the LangChain handlers, and gen_ai.provider.name being a passthrough instead of the binary Anthropic-or-OpenAI choice. A passthrough reads as obviously correct and reports bedrock for a request an OpenAI client made.

A vocabulary lock reads every attribute key, event name and naming template out of the sources and compares it to a committed set of 42, verified to match the TypeScript SDK exactly. It fails when a key is added, and separately when one stops being emitted. The second direction is the one that earns its keep: a key silently disappearing is how a dashboard goes blank with nothing failing. It caught its own regex being wrong while I wrote it, because the feature_flag event's attributes are built as a plain dict and never appear inside a set_attribute call.

Changing an attribute now means editing that list and saying why, which is the right amount of friction for a public contract with whatever reads the traces.

Verified by mutation, not by passing

Four deliberate breakages, each failing exactly one test and nothing else:

1. renaming invoke_agent
2. adding an unlisted attribute key
3. turning the LangChain provider into a passthrough
4. leaking the LD identity onto a tool span

Where this sits

Needs all six handler PRs (#30 to #35), because it asserts across all of them.

Tests: 844 to 913.

---

Note

Overview
Adds cross-handler parity tests at the repo root so the six handlers cannot silently disagree on span shape or attribute vocabulary again.

Shape checks call each package's span constructors with a recording tracer and pin shared names (invoke_agent, chat {model}, execute_tool {name}), shared surface functions, LaunchDarkly identity only on the root, and LangChain-specific provider-key rules.

A vocabulary lock scans package sources for emitted attribute/event keys and compares them to a committed set aligned with the TypeScript SDK, failing on both unexpected new keys and silently dropped ones. Runtime checks also cover the indexed OpenLLMetry gen_ai.prompt / gen_ai.completion carrier.

CI now runs bare uv run pytest instead of packages/*/tests, so the new root tests/ directory is included.

^{Reviewed by Cursor Bugbot for commit 8eee53f. Bugbot is set up for automated code reviews on this repo. Configure here.}

[apucacao]

bugbot run

[apucacao]

bugbot run

[apucacao]

bugbot run

[cursor]

✅ Bugbot reviewed your changes and found no new issues!

Comment @cursor review or bugbot run to trigger another review on this PR

^{Reviewed by Cursor Bugbot for commit 2234b78. Configure here.}

[apucacao]

bugbot run

[cursor]

✅ Bugbot reviewed your changes and found no new issues!

Comment @cursor review or bugbot run to trigger another review on this PR

^{Reviewed by Cursor Bugbot for commit 8eee53f. Configure here.}

[apucacao]

bugbot run

[cursor]

✅ Bugbot reviewed your changes and found no new issues!

Comment @cursor review or bugbot run to trigger another review on this PR

^{Reviewed by Cursor Bugbot for commit 8eee53f. Configure here.}