ci: update opentelemetry-instrumentation-langchain requirement from <0.62.0,>=0.40.0 to >=0.40.0,<0.63.0

[dependabot]

⚠️ Dependabot is rebasing this PR ⚠️

Rebasing might not happen immediately, so don't worry if this takes some time.

Note: if you make any changes to this PR yourself, they will take precedence over the rebase.

---

⚠️ Dependabot is rebasing this PR ⚠️

Rebasing might not happen immediately, so don't worry if this takes some time.

Note: if you make any changes to this PR yourself, they will take precedence over the rebase.

---

⚠️ Dependabot is rebasing this PR ⚠️

Rebasing might not happen immediately, so don't worry if this takes some time.

Note: if you make any changes to this PR yourself, they will take precedence over the rebase.

---

Updates the requirements on opentelemetry-instrumentation-langchain to permit the latest version.

Release notes

Sourced from opentelemetry-instrumentation-langchain's releases.

0.62.1

v0.62.1 (2026-06-28)

Fix

• bump version problem (#4332)

[main 93429cfb9] bump: version 0.62.0 → 0.62.1 64 files changed, 69 insertions(+), 63 deletions(-)

Changelog

Sourced from opentelemetry-instrumentation-langchain's changelog.

v0.62.1 (2026-06-28)

Fix

• bump version problem (#4332)

v0.62.0 (2026-06-28)

Feat

• instrumentation: Add litellm package instrumentation (#4322)

Fix

• sdk: @​agent decorator no longer overwrites enclosing @​workflow name (#4288)
• langchain: emit cache creation tokens (#4261)
• vertexai: emit cache tokens (#4263)
• writer: emit cache tokens (#4262)
• llamaindex: emit cache tokens (#4260)
• bedrock: emit cache tokens (#4241)
• mistralai: emit input cache tokens (#4238)

v0.61.0 (2026-05-31)

Feat

• sdk: expose use_legacy_attributes via Traceloop.init() (#4133)
• bedrock: add async support for aioboto3 (#4135)
• openai-agents: GenAI semconv compliance (#3837)

Fix

• openai: instrument responses.parse() for structured-output tracing (#4198)
• langchain,anthropic,groq,mistralai,bedrock,ollama,sagemaker,together: record exceptions and set ERROR status on failed spans (#4101)
• vector-db: emit consistent embeddings_count, result_count, similarity attrs across Pinecone and Milvus (#1870) (#4156)
• sdk: warn when both exporter and processor are passed to Traceloop.init() (#4137)
• openai-agents: capture response.instructions as system prompt in generation spans (#4131)
• openai-agents: emit cache_read.input_tokens and reasoning_tokens (#4130)
• chromadb: emit one result event per document across all queries (#4105)
• mcp: set error.type attribute on protocol-level tool errors (#4103)
• sdk: replace deprecated Pydantic .json() and double-encoding .model_dump_json() in JSONEncoders (#4098)
• chromadb,lancedb,weaviate,pinecone: record exceptions and set ERROR status on failed span (#4102)
• langchain: remove orphaned context_api.attach() in on_chain_end (#4100)
• langchain: use positional args for wrap_function_wrapper for wrapt v1/v2 compat, fix BaseChatOpenAI uninstrument (#4082)
• langchain: handle ToolNode in create_react_agent tool iteration (#4081)
• openai: remove redundant try/finally in ResponseStream close and aclose (#4080)
• anthropic: prevent KeyError/IndexError in streaming tool use delta handler (#4079)
• openai: guard against AsyncAPIResponse without .id in async responses wrapper (#4078)
• anthropic: always set streaming token usage from API data (#3949) (#3976)
• instrumentation: langchain association properties context cleanup (#4055)

... (truncated)

Commits

• 93429cf bump: version 0.62.0 → 0.62.1
• a00d2a3 bump: version 0.61.0 → 0.62.0
• 1dc1e89 feat(instrumentation): Add litellm package instrumentation (#4322)
• fb292d0 fix(sdk): @​agent decorator no longer overwrites enclosing @​workflow name (#4288)
• fc33f1c fix(langchain): emit cache creation tokens (#4261)
• aa4a469 fix(vertexai): emit cache tokens (#4263)
• fc75bbb fix(writer): emit cache tokens (#4262)
• 2ca9a0c fix(llamaindex): emit cache tokens (#4260)
• 0c0cf0e fix(bedrock): emit cache tokens (#4241)
• d138e31 fix(google generativeai:)emit cache input tokens (#4240)
• Additional commits viewable in compare view

You can trigger a rebase of this PR by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

Note
Automatic rebases have been disabled on this pull request as it has been open for over 30 days.

[yonib05]

@strandly-the-agent is this safe to merge?

[strandly-the-agent]

Yes — safe to merge. This just widens the upper bound (<0.62.0 → <0.63.0), CI is green, and the newly-allowed versions are additive/bug-fix only with nothing that touches the span data your mapper relies on.

How I checked

Diff: one line in pyproject.toml — allows opentelemetry-instrumentation-langchain 0.62.0/0.62.1 (previously capped below 0.62.0). No pin, just a range widen.

CI: unit tests pass on the full matrix (Python 3.10–3.13 × linux/windows/macOS), Lint pass, CodeQL neutral. With the bound widened, resolution picks the latest allowed (0.62.1) and tests still pass — so the new version is exercised. The only non-green checks are the bot-orchestration steps (Trigger Strands Review, check-access-and-checkout), not test failures.

Changelog (0.62.0 → 0.62.1): feat — added litellm instrumentation (new, isolated package); fixes — emit cache-creation/cache tokens across bedrock/langchain/vertexai/writer/llamaindex/mistralai, and @agent decorator no longer clobbers enclosing @workflow name. All additive; no breaking changes.

Blast radius here: your only consumer is LangChainOtelSessionMapper, which keys off the scope name opentelemetry.instrumentation.langchain and attributes like llm.request.type / traceloop.span.kind. Both are unchanged in 0.62.x — the cache-token work only adds attributes, it doesn't rename or remove existing ones.

Note: main has moved on since this was opened; GitHub still reports it mergeable, but a rebase (@dependabot rebase) won't hurt if you want a clean re-run before merging.

Automated check by Strandly — worth a human glance before you hit merge.

[Unshure]

@dependabot rebase

[Unshure]

@dependabot rebase

[Unshure]

@dependabot rebase

[dependabot]

OK, I won't notify you again about this release, but will get in touch when a new version is available. If you'd rather skip all updates until the next major or minor version, let me know by commenting @dependabot ignore this major version or @dependabot ignore this minor version. You can also ignore all major, minor, or patch releases for a dependency by adding an ignore condition with the desired update_types to your config file.

If you change your mind, just re-open this PR and I'll resolve any conflicts on it.