Automated Release PR

0.11.1 (2026-05-13)

Full Changelog: v0.11.0...v0.11.1

⚠ BREAKING CHANGES

• remove AgentexTracingProcessor from default tracing processors (#349)

Features

• api: add models for event requests, surface created_at for messages (1998d73)
• api: api update (da06505)
• api: revert model additions (a02c15b)
• internal/types: support eagerly validating pydantic iterators (2c528c6)
• remove AgentexTracingProcessor from default tracing processors (#349) (73eca7a)
• streaming: emit OTel metrics for ttft, tps, token counts (#347) (3bf7d1f)

Bug Fixes

• client: add missing f-string prefix in file type error message (dcb1cb4)
• render .env.example template in agentex init (#351) (6092595)
• tracing: make SGP processor stateless to stop dropping span closes (#354) (5e9f28d)
• wire SGP_CLIENT_BASE_URL and silence openai-agents tracer in templates (#352) (870324e)

This pull request is managed by Stainless's GitHub App.

The semver version number is based on included commit messages. Alternatively, you can manually set the version number in the title of this pull request.

For a better experience, it is recommended to use either rebase-merge or squash-merge when merging this pull request.

🔗 Stainless website
📚 Read the docs
🙋 Reach out for help or questions

Greptile Summary

• Adds OTel LLM metrics (ttft, ttat, tps, token counters, request counter with status) centralized in llm_metrics.py; TemporalStreamingHooks now extends LLMMetricsHooks so token/request metrics fire consistently across streaming and (future) sync paths.
• Refactors SGPSyncTracingProcessor and SGPAsyncTracingProcessor to be stateless — per-span _spans dict removed and replaced with an idempotent _build_sgp_span() helper, fixing a silent span-drop bug on Temporal cross-pod deployments where START and END land on different workers.
• API surface additions: created_at parameter on messages.create and messages.batch.create; set_tracing_disabled(True) added to generated templates to stop the openai-agents SDK from shipping traces to api.openai.com via OPENAI_API_KEY.

Important Files Changed

Fix the following 1 code review issue. Work through them one at a time, proposing concise fixes.

---

### Issue 1 of 1
src/agentex/lib/core/observability/llm_metrics_hooks.py:18-57
**No error-path hook for sync ACP**

`LLMMetricsHooks` only overrides `on_llm_end`, which fires on success. For the temporal streaming path, failures are covered by the `record_llm_failure` call in `temporal_streaming_model.py`'s except block. The sync ACP path (per the module docstring: "Used by the sync ACP path") has no equivalent wiring, so failed LLM calls will silently go uncounted in `agentex.llm.requests` there. Consider adding an `on_error` / `on_llm_error` override to `LLMMetricsHooks` that calls `record_llm_failure`, or ensure the sync ACP runner wraps LLM exceptions similarly.

_{Reviews (9): Last reviewed commit: "release: 0.11.1" | Re-trigger Greptile}