chore: release main (#443)

Co-authored-by: Declan Brady <declan.brady@scale.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: OpenAI <openai@example.com>
Co-authored-by: stainless-app[bot] <142633134+stainless-app[bot]@users.noreply.github.com>

Author: 4 people

.github/workflows/harness-integration.yml

@@ -7,8 +7,7 @@ on:
     paths:
       - "src/agentex/lib/core/harness/**"
       - "src/agentex/lib/adk/_modules/**"
-      - "tests/lib/core/harness/test_harness_pydantic_ai_*.py"
-      - "tests/lib/core/harness/test_harness_langgraph_*.py"
+      - "tests/lib/core/harness/test_harness_*.py"
       - ".github/workflows/harness-integration.yml"
 
 jobs:
@@ -34,14 +33,15 @@ jobs:
         run: ./scripts/test tests/lib/core/harness/ -v
 
   # Offline harness integration tests (sync / async / temporal channels) for each
-  # migrated harness. These use fake streams / TestModel + fake streaming/tracing
-  # and require no live infrastructure. Future harness migration PRs (6-8) add
-  # their harness to the matrix below and their test paths to the triggers above.
+  # harness. These use fake streams / TestModel + fake streaming/tracing and
+  # require no live infrastructure. All five harnesses are now covered; the
+  # trigger above uses a `test_harness_*.py` glob so new suites are picked up
+  # automatically.
   live-matrix:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        harness: [pydantic_ai, langgraph]
+        harness: [pydantic_ai, langgraph, openai, claude_code, codex]
         channel: [sync, async, temporal]
       fail-fast: false
     name: ${{ matrix.harness }}-${{ matrix.channel }}

.release-please-manifest.json

@@ -1,4 +1,4 @@
 {
-  ".": "0.15.0",
-  "adk": "0.14.0"
+  ".": "0.16.0",
+  "adk": "0.15.0"
 }

CHANGELOG.md

@@ -2,10 +2,46 @@
 
 ## Unreleased
 
+### ⚠ BREAKING CHANGES
+
+* **harness:** removed the deprecated bespoke LangGraph tracing handler `create_langgraph_tracing_handler` (and its `AgentexLangGraphTracingHandler` class) from the public `agentex.lib.adk` surface. Span tracing is now derived from the canonical `StreamTaskMessage*` stream by `UnifiedEmitter` — wrap your run in the harness `*Turn` and drive `UnifiedEmitter.yield_turn` / `auto_send_turn`. The `agentex init` templates were migrated accordingly.
+* **harness:** removed the deprecated bespoke Pydantic-AI tracing handler `create_pydantic_ai_tracing_handler` (and its `AgentexPydanticAITracingHandler` class) from the public `agentex.lib.adk` surface. Span tracing is now derived from the canonical `StreamTaskMessage*` stream by `UnifiedEmitter` — wrap your run in `PydanticAITurn` and drive `UnifiedEmitter.yield_turn` / `auto_send_turn`. The `agentex init` templates were migrated accordingly.
+* **harness:** each harness now exposes exactly `_<harness>_sync.py` + `_<harness>_turn.py` under `agentex.lib.adk._modules`. The OpenAI harness `OpenAITurn` and `convert_openai_to_agentex_events` moved to `agentex.lib.adk._modules._openai_turn` / `_openai_sync`; back-compat shims remain at `agentex.lib.adk.providers._modules.{openai_turn,sync_provider}` for one release. Public facade names (`stream_pydantic_ai_events`, `stream_langgraph_events`, `emit_langgraph_messages`, etc.) are unchanged.
+
 ### Features
 
 * **tracing:** emit OTel metrics for async span queue depth, batch drain, and SGP export success/failure (HTTP status labels). Disable SDK-side recording with ``AGENTEX_TRACING_METRICS=0``.
 
+## 0.16.0 (2026-06-24)
+
+Full Changelog: [agentex-client-v0.15.0...agentex-client-v0.16.0](https://github.com/scaleapi/scale-agentex-python/compare/agentex-client-v0.15.0...agentex-client-v0.16.0)
+
+### ⚠ BREAKING CHANGES
+
+* **harness:** consolidate the Pydantic-AI harness + remove tracing handler ([#431](https://github.com/scaleapi/scale-agentex-python/issues/431))
+* **harness:** consolidate the LangGraph harness + remove tracing handler ([#430](https://github.com/scaleapi/scale-agentex-python/issues/430))
+
+### Features
+
+* **cli:** add claude-code init templates (sync / async / temporal) ([#435](https://github.com/scaleapi/scale-agentex-python/issues/435)) ([fd9bc4a](https://github.com/scaleapi/scale-agentex-python/commit/fd9bc4a81417b9d75ad692b779293720f8435d37))
+* **cli:** add codex init templates (sync / async / temporal) ([#436](https://github.com/scaleapi/scale-agentex-python/issues/436)) ([0fadfd7](https://github.com/scaleapi/scale-agentex-python/commit/0fadfd7a113536d49a99894a3b80ed0915a0e0fb))
+* **cli:** add default-openai-agents init template (async base) ([#434](https://github.com/scaleapi/scale-agentex-python/issues/434)) ([624e9c8](https://github.com/scaleapi/scale-agentex-python/commit/624e9c8f3b4c4288a7037bc83651970cfb02e6b0))
+* **openai-agents:** single-emit + input-bearing tool spans + run_turn ([#445](https://github.com/scaleapi/scale-agentex-python/issues/445)) ([53ab8ef](https://github.com/scaleapi/scale-agentex-python/commit/53ab8efaaf65590e71abe07149582ea59814921b))
+* **openai-temporal:** render hosted/server-side tool calls in TemporalStreamingModel ([#442](https://github.com/scaleapi/scale-agentex-python/issues/442)) ([5dce9f0](https://github.com/scaleapi/scale-agentex-python/commit/5dce9f097723d3436a0e40277139e7cce68580ef))
+
+
+### Bug Fixes
+
+* **cli:** harden init templates per Greptile feedback (suite-wide) ([#444](https://github.com/scaleapi/scale-agentex-python/issues/444)) ([2d85eb0](https://github.com/scaleapi/scale-agentex-python/commit/2d85eb0952f2298e6c412ab44b9c59255431cb84))
+* **harness:** harden Claude Code + OpenAI taps and span tracing ([#446](https://github.com/scaleapi/scale-agentex-python/issues/446)) ([5b4359d](https://github.com/scaleapi/scale-agentex-python/commit/5b4359dcf28f390f780215ed954fa52e8cb4dd7c))
+
+
+### Refactors
+
+* **harness:** consolidate the LangGraph harness + remove tracing handler ([#430](https://github.com/scaleapi/scale-agentex-python/issues/430)) ([a3fb5ad](https://github.com/scaleapi/scale-agentex-python/commit/a3fb5ad51f6392a48cbb8324f15c9619f10244b6))
+* **harness:** consolidate the Pydantic-AI harness + remove tracing handler ([#431](https://github.com/scaleapi/scale-agentex-python/issues/431)) ([48c3da8](https://github.com/scaleapi/scale-agentex-python/commit/48c3da8777ae20a9ca6d544238dccd64d6c62c2b))
+* **harness:** move OpenAI harness into adk/_modules + facade export ([#432](https://github.com/scaleapi/scale-agentex-python/issues/432)) ([58bdb16](https://github.com/scaleapi/scale-agentex-python/commit/58bdb16b4b18db22188a29d5d1b31759f9d0dd4e))
+
 ## 0.15.0 (2026-06-23)
 
 Full Changelog: [agentex-client-v0.14.0...agentex-client-v0.15.0](https://github.com/scaleapi/scale-agentex-python/compare/agentex-client-v0.14.0...agentex-client-v0.15.0)

adk/CHANGELOG.md

@@ -1,5 +1,22 @@
 # Changelog
 
+## 0.15.0 (2026-06-24)
+
+Full Changelog: [agentex-sdk-v0.14.0...agentex-sdk-v0.15.0](https://github.com/scaleapi/scale-agentex-python/compare/agentex-sdk-v0.14.0...agentex-sdk-v0.15.0)
+
+### ⚠ BREAKING CHANGES
+
+* **harness:** consolidate the LangGraph harness + remove tracing handler ([#430](https://github.com/scaleapi/scale-agentex-python/issues/430))
+
+### Bug Fixes
+
+* **harness:** harden Claude Code + OpenAI taps and span tracing ([#446](https://github.com/scaleapi/scale-agentex-python/issues/446)) ([5b4359d](https://github.com/scaleapi/scale-agentex-python/commit/5b4359dcf28f390f780215ed954fa52e8cb4dd7c))
+
+
+### Refactors
+
+* **harness:** consolidate the LangGraph harness + remove tracing handler ([#430](https://github.com/scaleapi/scale-agentex-python/issues/430)) ([a3fb5ad](https://github.com/scaleapi/scale-agentex-python/commit/a3fb5ad51f6392a48cbb8324f15c9619f10244b6))
+
 ## 0.14.0 (2026-06-23)
 
 Full Changelog: [agentex-sdk-v0.13.2...agentex-sdk-v0.14.0](https://github.com/scaleapi/scale-agentex-python/compare/agentex-sdk-v0.13.2...agentex-sdk-v0.14.0)

adk/docs/harness.md

@@ -39,14 +39,17 @@ Every harness tap produces a sequence of these. Everything downstream (delivery,
 
 ## Per-harness taps: `convert_<harness>_to_agentex_events`
 
-A tap is an async generator that translates the harness's native event stream into `StreamTaskMessage*` events. The currently shipped taps are:
+A tap is an async generator that translates the harness's native event stream into `StreamTaskMessage*` events. The shipped taps are:
 
 | Harness | Tap function | Exported from |
 |---|---|---|
 | pydantic-ai | `convert_pydantic_ai_to_agentex_events` | `agentex.lib.adk` |
 | LangGraph | `convert_langgraph_to_agentex_events` | `agentex.lib.adk` |
+| claude-code | `convert_claude_code_to_agentex_events` | `agentex.lib.adk` |
+| codex | `convert_codex_to_agentex_events` | `agentex.lib.adk` |
+| OpenAI Agents | `convert_openai_to_agentex_events` | `agentex.lib.adk.providers._modules.sync_provider` |
 
-Taps for claude-code and codex will be added in subsequent PRs (AGX1-420, AGX1-421) and exported from `agentex.lib.adk` in the same way.
+Each harness also provides a `HarnessTurn` wrapper that pairs its tap's event stream with usage extraction: `PydanticAITurn`, `LangGraphTurn`, `ClaudeCodeTurn`, `CodexTurn`, and `OpenAITurn`.
 
 ---
 
@@ -157,11 +160,13 @@ Spans are derived from the canonical stream by `SpanDeriver` (pure, no `adk` dep
 
 ## Usage examples by channel
 
-### Sync ACP (pydantic-ai tap)
+### Sync ACP (`yield_turn`)
+
+Build the harness's `HarnessTurn` wrapper and iterate `emitter.yield_turn(turn)` — the emitter forwards each event to the caller and traces spans as a side effect:
 
 ```python
 import agentex.lib.adk as adk
-from agentex.lib.adk import UnifiedEmitter, convert_pydantic_ai_to_agentex_events
+from agentex.lib.adk import UnifiedEmitter, ClaudeCodeTurn
 
 @acp.on_message_send
 async def handle(params):
@@ -172,13 +177,12 @@ async def handle(params):
             trace_id=task_id,
             parent_span_id=turn_span.id if turn_span else None,
         )
-        tap = convert_pydantic_ai_to_agentex_events(pydantic_stream)
-        # wrap tap in a HarnessTurn then yield_turn, or yield directly:
-        async for event in tap:
+        turn = ClaudeCodeTurn(claude_code_stream)   # any HarnessTurn
+        async for event in emitter.yield_turn(turn):
             yield event
 ```
 
-For the pre-unified sync path the tap is still yielded directly; `UnifiedEmitter.yield_turn` is the forward-looking integration point when a `HarnessTurn` wrapper is available.
+Every harness follows the same shape — swap `ClaudeCodeTurn` for `PydanticAITurn`, `LangGraphTurn`, `CodexTurn`, or `OpenAITurn` and feed it that harness's native stream.
 
 ### Async Temporal (auto-send)
 
@@ -194,3 +198,9 @@ result = await emitter.auto_send_turn(turn, created_at=workflow.now())
 # result.final_text — last text segment
 # result.usage     — TurnUsage (tokens, cost, ...)
 ```
+
+---
+
+## Migration
+
+- [Migrating to `agentex-client` 0.16.0 / `agentex-sdk` 0.15.0](./migration-0.16.0.md) — removed LangGraph/Pydantic-AI tracing handlers (tracing is now derived from the canonical stream), private `_modules` path moves, the OpenAI harness facade relocation, and the new `run_turn` Temporal entry point.