✨ Stainless prepared a new release

0.13.0 (2026-06-10)

Full Changelog: agentex-client-v0.12.0...agentex-client-v0.13.0

⚠ BREAKING CHANGES

• packaging: release tag scheme changes from v* to -v*.

Features

• add AgentCard for self-describing agent capabilities (#296) (6509be1)
• add HTTP-proxy LangGraph checkpointer (19fae2f)
• add OCI Helm registry support for agent deployments (#255) (5f054b5)
• adk: allow all ClaudeAgentOptions in run_claude_agent_activity (25bbe24)
• adk: Revamp run_claude_agent_activity to use more streaming (#309) (0c16595)
• api: api update (7b1b642)
• api: api update (710c63f)
• api: api update (8abce2b)
• api: Switch target to -client (e741990)
• lib: Add task updates to adk (a58747f)
• openai_agents: expose real usage, response_id, plumb previous_response_id, opt-in prompt_cache_key for stateful responses and prompt caching (#335) (ba5d64b)
• packaging: introduce slim agentex-client + heavy agentex-sdk split (bbfb22e)
• pass AGENTEX_DEPLOYMENT_ID in registration metadata (#305) (31af8c6)
• tracing: Add background queue for async span processing (#303) (3a60add)

Bug Fixes

• add litellm retry with exponential backoff for rate limit errors (ccdb24a)
• adk: fix to queue drain (#327) (a862a06)
• api: remove agent_id and task_id parameters from states update method (a7cbaae)
• client: preserve hardcoded query params when merging with user params (d2c4788)
• ensure file data are only sent as 1 parameter (48fae27)
• render .env.example template in agentex init (#351) (6092595)
• Temporal Union deserialization causing tool_response messages to be lost (79ef4dd)
• temporal: allowing-ACP-temporal-telemetry (9b44eb0)
• tests: repair test_streaming_model so all 28 tests run and pass (#334) (7e5e69c)
• tracing: Fix memory leak in SGP tracing processors (#302) (f43dac4)
• tutorials: stop at130-langgraph workflow deadlock on graph compile (#399) (bd90a61)

Performance Improvements

• client: optimize file structure copying in multipart requests (f5064f9)
• tracing: larger span batch + linger_ms for high-volume ingest (#397) (c0d6330)
• tracing: skip span-start upsert by default (end-only ingest) (#394) (ae1c7ca)

Chores

• ci: upgrade actions/github-script (7c867e8)
• gitignore .claude/scheduled_tasks.lock (#400) (e186352)

Documentation

• api: clarify name parameter behavior in agent task creation (ce5af72)
• clarify task name is optional in adk.acp.create_task (#392) (bd41d9b)

Refactors

• config: promote deployment-config models to agentex.config.* (#396) (9825dba)

0.13.0 (2026-06-10)

Full Changelog: agentex-sdk-v0.12.0...agentex-sdk-v0.13.0

⚠ BREAKING CHANGES

• packaging: release tag scheme changes from v* to -v*.

Features

• packaging: introduce slim agentex-client + heavy agentex-sdk split (bbfb22e)

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

This release (v0.13.0) introduces two major structural changes: a slim/heavy package split (agentex-client for the pure REST client, agentex-sdk for the full ADK overlay) and a config module promotion that moves canonical deployment/agent config models from agentex.lib.sdk.config.* / agentex.lib.types.* into the new agentex.config.* namespace, with back-compat re-export shims keeping old import paths working.

• Package split: pyproject.toml becomes agentex-client (6 slim deps); the new adk/pyproject.toml becomes agentex-sdk with all ADK/CLI/LLM deps, pinning agentex-client>=0.12.0. A scripts/check-slim-deps CI guard prevents dep drift.
• Config promotion: All model classes are now in agentex.config.*; shims in the old paths re-export the identical class objects so isinstance checks remain correct across import styles. AgentEnvironmentsConfig.from_yaml() is replaced by the standalone load_environments_config() helper (kept in the shim module to preserve slim-safety).
• Tracing optimisations: span-start writes are skipped by default (end-only ingest via AGENTEX_TRACING_SKIP_SPAN_START), and the span-queue batch size / linger window are both increased for higher throughput. A tutorial deadlock caused by using LangGraph's ToolNode (a Runnable) inside a Temporal-wrapped workflow node is also fixed.

Confidence Score: 5/5

Safe to merge — all changes are well-tested, breaking changes are documented in the CHANGELOG, and the back-compat shims are covered by identity-checking tests.

The package split and config promotion are structural refactors with comprehensive shim tests confirming symbol parity and class identity. Tracing optimisations default to the new behaviour but are runtime-toggleable via env vars. The states.update parameter removal and from_yaml → load_environments_config migration are properly documented and all internal call sites are updated.

No files require special attention; the suggestion on sgp_tracing_processor.py is cosmetic.

Important Files Changed

Flowchart

%%{init: {'theme': 'neutral'}}%%
flowchart TD
    subgraph canonical["agentex.config.* (new canonical)"]
        CC[credentials.py\nCredentialMapping]
        AC[agent_configs.py\nTemporalConfig / WorkflowConfig]
        AGC[agent_config.py\nAgentConfig]
        BC[build_config.py\nBuildConfig]
        DC[deployment_config.py\nDeploymentConfig / Cluster...]
        EC[environment_config.py\nAgentEnvironmentsConfig]
        LDC[local_development_config.py\nLocalDevelopmentConfig]
        AM[agent_manifest.py\nAgentManifest]
    end

    subgraph shims["Back-compat shims (re-export only)"]
        S1[agentex.lib.types.credentials]
        S2[agentex.lib.types.agent_configs]
        S3[agentex.lib.sdk.config.agent_config]
        S4[agentex.lib.sdk.config.deployment_config]
        S5[agentex.lib.sdk.config.environment_config\n+ yaml loaders stay here]
        S6[agentex.lib.sdk.config.agent_manifest]
    end

    subgraph packages["Published packages"]
        CLIENT["agentex-client\n(slim REST client)"]
        SDK["agentex-sdk\n(heavy ADK overlay)\ndeps: agentex-client>=0.12.0"]
    end

    S1 -->|re-exports| CC
    S2 -->|re-exports| AC
    S3 -->|re-exports| AGC
    S4 -->|re-exports| DC
    S5 -->|re-exports models| EC
    S6 -->|re-exports| AM

    canonical -->|ships in| CLIENT
    shims -->|ships in| SDK

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/tracing/processors/sgp_tracing_processor.py:100-112
`_skip_span_start_enabled()` calls `os.environ.get(...)` on every `on_span_start` / `on_spans_start` invocation. The constructor already reads and logs the value at startup, and `AsyncSpanQueue` uses the same pattern of resolving env-tunable config once at construction (`_read_int_env` in `__init__`). Caching the flag as an instance attribute would be more consistent and avoids repeated dict lookups in the hot path.

```suggestion
        self.env_vars = EnvironmentVariables.refresh()
        self._skip_span_start = _skip_span_start_enabled()
        logger.info(
            "SGP tracing span-start upsert %s (%s)",
            "disabled — end-only ingest" if self._skip_span_start else "enabled",
            _SKIP_SPAN_START_ENV,
        )

    @override
    def on_span_start(self, span: Span) -> None:
        # End-only ingest: by default the start write is skipped (see
        # _skip_span_start_enabled) so each span is persisted once, on end.
        if self._skip_span_start:
            return
```

Reviews (13): Last reviewed commit: "chore: release main" | Re-trigger Greptile