feat(core,partners): add package version tracking to tracing metadata

[Mason Daugherty (mdrxy)]

Following on the heels of #35293

TODO:

• Packages outside of this repo (e.g. LiteLLM, Nvidia, Google, AWS)

---

Summary

Surface partner package versions in metadata.versions on LangSmith traces. Mirrors the JS SDK's _addVersion() pattern (langchainjs#10106).

Each model constructor records its package version via _add_version() on BaseLanguageModel. The version dict accumulates through the class hierarchy — langchain-core is added in BaseLanguageModel.model_post_init, langchain-openai in BaseChatOpenAI._set_openai_chat_version, and each leaf partner in its uniquely-named model_validator. Traces end up with:

{
  "metadata": {
    "versions": {
      "langchain-core": "1.4.5",
      "langchain-openai": "1.3.0",
      "langchain-xai": "1.2.2"
    }
  }
}

Changes

• BaseLanguageModel._add_version(pkg, version) — appends to self.metadata["versions"]; accepts any Mapping type; emits a warning if a non-mapping value is found and replaced
• BaseLanguageModel.model_post_init — adds langchain-core version; calls super() for MRO safety
• _merge_metadata_dicts — one-level-deep (non-recursive) merge for nested dict metadata keys
• CallbackManager.add_metadata — uses _merge_metadata_dicts instead of flat dict.update() so nested metadata dicts (like versions) coexist rather than clobber
• merge_configs — uses _merge_metadata_dicts for config merging

Partners:

• Each now calls self._add_version("langchain-<pkg>", __version__)

Design decisions

• Constructor-based, not _get_ls_params-based — versions flow through self.metadata (local metadata on traces), not through LangSmithParams. This matches JS and makes child-class version inheritance automatic (no merge/clobber issues).
• versions is local (non-inheritable) metadata — self.metadata is passed to CallbackManager.configure as local_metadata (add_metadata(..., inherit=False)), so versions is attached once per chat-model run and is not propagated to child runs or duplicated onto every streaming chunk. This is intentionally the opposite of the inheritable-per-chunk metadata that chore(core): reduce streaming metadata / perf #36588 was reducing for performance — versions does not regress that path.
• add_metadata deep-merge is a correctness fix, not just for versions — previously add_metadata/merge_configs did a flat top-level dict.update/spread, so any nested metadata dict baked into a config (e.g. via .with_config({"metadata": {...}})) would be wholly replaced when a caller also passed metadata. _merge_metadata_dicts merges one level deep so user-provided config.metadata.versions and model-set versions coexist instead of clobbering. The merge runs once per configure (not per chunk), so it is off the streaming hot path.
• One level deep only — _merge_metadata_dicts is deliberately not a recursive deep merge; values nested more than one level are last-writer-wins. This covers the versions case without the ambiguity/cost of arbitrary-depth merging.
• Warn on non-dict metadata["versions"] — if a user sets metadata={"versions": "some-string"}, _add_version emits a warning and replaces the value with the version dict rather than silently discarding user data or crashing. This is a soft breaking change for anyone who previously stored non-dict values at this key.

Follow-ups (tracked separately, out of scope here)

• JS mergeConfigs still flat-spreads nested metadata, so metadata.versions can still clobber on the JS side until an equivalent deep-merge lands.

---

Made by Open SWE

[codspeed-hq]

Merging this PR will degrade performance by 84.24%

⚠️ Unknown Walltime execution environment detected

Using the Walltime instrument on standard Hosted Runners will lead to inconsistent data.

For the most accurate results, we recommend using CodSpeed Macro Runners: bare-metal machines fine-tuned for performance measurement consistency.

⚠️ Different runtime environments detected

Some benchmarks with significant performance changes were compared across different runtime environments,
which may affect the accuracy of the results.

Open the report in CodSpeed to investigate

⚡ 8 improved benchmarks
❌ 6 regressed benchmarks
✅ 12 untouched benchmarks
⏩ 14 skipped benchmarks¹

⚠️ Please fix the performance issues or acknowledge them on CodSpeed.

Performance Changes

	Mode	Benchmark	BASE	HEAD	Efficiency
⚡	WallTime	test_import_time[HumanMessage]	232.4 ms	207.3 ms	+12.09%
⚡	WallTime	test_import_time[RunnableLambda]	452.3 ms	394.1 ms	+14.77%
⚡	WallTime	test_import_time[LangChainTracer]	404.5 ms	361.3 ms	+11.96%
⚡	WallTime	test_import_time[tool]	485.6 ms	422.3 ms	+14.99%
⚡	WallTime	test_async_callbacks_in_sync	20.1 ms	14.8 ms	+35.15%
⚡	WallTime	test_import_time[InMemoryVectorStore]	547 ms	496.2 ms	+10.23%
⚡	WallTime	test_import_time[PydanticOutputParser]	495.7 ms	440.5 ms	+12.54%
⚡	WallTime	test_import_time[ChatPromptTemplate]	583.1 ms	490.1 ms	+18.97%
❌	WallTime	test_init_time	3.6 ms	10.2 ms	-65.29%
❌	WallTime	test_init_time	3.5 ms	10.3 ms	-65.48%
❌	Simulation	test_init_time_with_client	3 ms	12.8 ms	-76.33%
❌	Simulation	test_init_time	1.9 ms	11.8 ms	-84.24%
❌	WallTime	test_init_time	453.7 ms	529.4 ms	-14.29%
❌	Simulation	test_init_time	7.3 ms	9.1 ms	-19.49%

---

_{Comparing mdrxy/versioning (4d77e2b) with master (2f64d80)}

Footnotes

1. 14 benchmarks were skipped, so the baseline results were used instead. If they were deleted from the codebase, click here and archive them to remove them from the performance reports. ↩