Add LangSmith tracing sample by xumaple · Pull Request #292 · temporalio/samples-python

xumaple · 2026-04-17T20:18:00Z

Summary

Adds langsmith_tracing/ sample demonstrating temporalio.contrib.langsmith.LangSmithPlugin
basic/: one-shot LLM workflow (prompt → OpenAI activity → result)
chatbot/: conversational loop with save_note/read_note tools, signals, queries, and dynamic LangSmith trace names
Includes mocked tests, README, and langsmith-tracing dependency group
Declares langchain and langsmith-tracing as conflicting groups in [tool.uv] to avoid version conflicts

Test plan

poe format — passes
mypy on langsmith_tracing/ and tests/langsmith_tracing/ — passes
pytest tests/langsmith_tracing/ — basic test passes, chatbot tests skip (pending SDK plugin release)
Manual test: run worker + starter for both basic and chatbot examples

🤖 Generated with Claude Code

Demonstrates the LangSmithPlugin for automatic LangSmith tracing in Temporal workflows. Includes two examples: - basic/: one-shot LLM workflow (prompt → OpenAI → result) - chatbot/: conversational loop with save_note/read_note tools, signals, queries, and dynamic trace names Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

- Add @Traceable with metadata, tags, and run_type variety to workflows - Add client-side @Traceable on starters for end-to-end trace linking - Add --temporal-runs flag to workers and starters for add_temporal_runs toggle - Use run_type="llm" for OpenAI calls, "tool" for save_note, "chain" for orchestration - Add trace tree diagrams to README showing both add_temporal_runs modes - Add "Three Layers of Tracing" section to README (wrap_openai, @Traceable, Temporal plugin) - Skip all tests when temporalio.contrib.langsmith is unavailable (pending SDK release) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

- Split top-level README into per-sample READMEs (basic/ and chatbot/) with detailed trace structure diagrams and screenshot placeholders - Add replay safety comment on @workflow.run methods explaining why @Traceable must wrap an inner function - Make read_note a proper activity for LangSmith trace visibility - Change save_note/read_note to use NoteRequest dataclass (single arg) - Fix misplaced comments in activities (wrap_openai, run_type docs) - Add links to LangSmith docs and Temporal SDK plugin docs - Add add_temporal_runs explanation section to top-level README Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Audit findings addressed: - Remove max_cached_workflows=0 (debugging leftover, not needed) - Expand replay safety comment to explain why (I/O on replay) - Tighten type annotations: str|list[dict[str,Any]], dict[str,Any] - Clarify read_note docstring (passthrough for tracing visibility) - Clarify activity docstrings (retries handled by Temporal, not OpenAI) - Make trace tree annotations consistent across basic/chatbot READMEs - Extract shared test helpers (make_text_response, poll_last_response) - Add TimeoutError on poll failure instead of silent assertion - Fix "simplest possible" wording to "very simple" Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Changed from explaining internals (I/O on replay) to describing what the user would see: duplicate or orphaned traces. Also swept all other comments for outcome-focus — no further changes needed. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

- save_note and read_note are now @Traceable methods on ChatbotWorkflow, not activities. Notes live in workflow state (durable via event history). - Remove NoteRequest dataclass and activity registrations - Fix wrap_openai comment placement (describes child span, not parent) - Remove retry policy from basic workflow (unnecessary for simple example) - Add comment highlighting that non-@workflow.run methods can use @Traceable - Update chatbot README trace trees to reflect workflow methods vs activities Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

- Remove skip markers from tests — CI should fail loudly if deps missing - Pin temporalio[pydantic,langsmith]>=1.26.0 (plugin is released) - Rename kwargs to response_args in chatbot activity - Remove notes CLI command from chatbot starter - Update chatbot README trace trees for accuracy - Change input prompt from "You: " to "> " Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

- StartWorkflow/RunWorkflow are siblings, not parent-child - StartActivity/RunActivity are siblings under RunWorkflow - @Traceable activity spans nest under RunActivity - Signal/query traces are separate roots (or under client @Traceable) - Merge client-side and worker-side into unified trees - add_temporal_runs=False: only @Traceable spans, all under client root Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

temporalio>=1.26.0 requires openai-agents>=0.14.0 but the openai-agents group pins ==0.3.2, causing a resolution failure. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Without the group flag, uv resolves the base temporalio dep (1.23.0) which doesn't have contrib.langsmith. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

- Simplify basic/worker.py to use asyncio.run(main()) pattern - Basic activity now returns str instead of Response (drops pydantic dep) - Remove pydantic_data_converter from basic worker/starter - Replace chatbot signal+poll with update handler (message_from_user) - Wrap update handler body in @Traceable for input/output capture - Inline RetryPolicy in chatbot workflow (no separate RETRY constant) - Add comment about alternative traceable() function-call style - Make PROJECT_NAME a shared constant in starters, pass to client-side @Traceable so traces go to the right LangSmith project - Update READMEs with correct trace hierarchies based on real output - Fix wrap_openai span name (ChatOpenAI, not openai.responses.create) - Simplify tests (mocks match new str return type, use execute_update) - Remove poll_last_response helper Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

The langchain sample's langsmith<0.4 pin conflicts with langsmith-tracing's langsmith>=0.7.0. The langchain sample uses an older custom-interceptor approach that's superseded by the new LangSmithPlugin demonstrated in langsmith_tracing/. Removing it eliminates the dep conflict and the related [tool.uv] conflicts declaration. Also relax openai pin from <2 to no upper bound so it resolves alongside the openai-agents group (which now requires openai>=2.26.0). Add inline comment on max_retries=0 explaining Temporal handles retries. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

JasonSteving99 · 2026-04-22T17:44:07Z

+    @traceable(
+        name="Basic LLM Request",
+        run_type="chain",
+        # CRITICAL: Client-side @traceable runs outside the LangSmithPlugin's scope.
+        # Make sure client-side traces use the same project_name as what is given to
+        # # the plugin.
+        project_name=PROJECT_NAME,
+        tags=["client-side"],
+    )
+    async def run_workflow(prompt: str) -> str:
+        return await client.execute_workflow(
+            BasicLLMWorkflow.run,
+            prompt,
+            id="langsmith-basic-workflow-id",
+            task_queue="langsmith-basic-task-queue",
+        )


probably worth just making this func top-level since it doesn't require the @traceable(...) decorator closing over anything

JasonSteving99

Had one minor suggestion leftover, but LGTM!