AbstractRuntime 0.4.4__tar.gz → 0.4.6__tar.gz

{abstractruntime-0.4.4 → abstractruntime-0.4.6}/CHANGELOG.md

@@ -7,6 +7,23 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.4.6] - 2026-05-07
+
+### Changed
+- Minimum `abstractcore` optional dependency increased to `>=2.13.10` so Runtime picks up AbstractCore's async/sync text-generation output-selector parity in addition to the public output-selector contract.
+
+### Fixed
+- AbstractCore output-selector imports now fail fast when an older local AbstractCore install exposes the helper module but does not include the 2.13.10 async parity fix.
+
+## [0.4.5] - 2026-05-07
+
+### Changed
+- Minimum `abstractcore` optional dependency increased to `>=2.13.9` so Runtime can use AbstractCore's public output-selector contract instead of mirroring provider-private multimodal selector logic.
+- Runtime's AbstractCore output-spec adapter now delegates selector detection, normalization, generated-media detection, non-chat dispatch detection, and runtime metadata stripping to `abstractcore.core.output_specs`.
+
+### Fixed
+- Explicit `voice_clone` output specs no longer require a Runtime `ArtifactStore` before dispatch because AbstractCore exposes them as generated resources rather than binary media outputs.
+
 ## [0.4.4] - 2026-05-07
 
 ### Added
@@ -323,7 +340,9 @@ AbstractRuntime is the durable execution substrate designed to pair with Abstrac
 
 Initial development version with basic proof-of-concept features.
 
-[Unreleased]: https://github.com/lpalbou/abstractruntime/compare/v0.4.4...HEAD
+[Unreleased]: https://github.com/lpalbou/abstractruntime/compare/v0.4.6...HEAD
+[0.4.6]: https://github.com/lpalbou/abstractruntime/compare/v0.4.5...v0.4.6
+[0.4.5]: https://github.com/lpalbou/abstractruntime/compare/v0.4.4...v0.4.5
 [0.4.4]: https://github.com/lpalbou/abstractruntime/releases/tag/v0.4.4
 [0.4.3]: https://github.com/lpalbou/abstractruntime/releases/tag/v0.4.3
 [0.4.2]: https://github.com/lpalbou/abstractruntime/releases/tag/v0.4.2

{abstractruntime-0.4.4 → abstractruntime-0.4.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: AbstractRuntime
-Version: 0.4.4
+Version: 0.4.6
 Summary: AbstractRuntime: a durable graph runner designed to pair with AbstractCore.
 Project-URL: AbstractCore (website), https://www.abstractcore.ai/
 Project-URL: AbstractRuntime (GitHub), https://github.com/lpalbou/abstractruntime
@@ -22,15 +22,15 @@ Classifier: Programming Language :: Python :: 3.13
 Requires-Python: >=3.10
 Requires-Dist: abstractsemantics>=0.0.2
 Provides-Extra: abstractcore
-Requires-Dist: abstractcore>=2.13.8; extra == 'abstractcore'
+Requires-Dist: abstractcore>=2.13.10; extra == 'abstractcore'
 Provides-Extra: docs
 Requires-Dist: mkdocs-material>=9.0.0; extra == 'docs'
 Requires-Dist: mkdocs>=1.6.0; extra == 'docs'
 Requires-Dist: pymdown-extensions>=10.0; extra == 'docs'
 Provides-Extra: mcp-worker
-Requires-Dist: abstractcore[tools]>=2.13.8; extra == 'mcp-worker'
+Requires-Dist: abstractcore[tools]>=2.13.10; extra == 'mcp-worker'
 Provides-Extra: multimodal
-Requires-Dist: abstractcore[audio,media,openai,vision,voice]>=2.13.8; extra == 'multimodal'
+Requires-Dist: abstractcore[audio,media,openai,vision,voice]>=2.13.10; extra == 'multimodal'
 Provides-Extra: test
 Requires-Dist: pytest>=7.0.0; extra == 'test'
 Description-Content-Type: text/markdown
@@ -41,7 +41,7 @@ Description-Content-Type: text/markdown
 
 It is designed for long-running workflows that must survive restarts and explicitly model blocking (human input, timers, external events, subworkflows) without keeping Python stacks alive.
 
-**Version:** 0.4.4 • **Python:** 3.10+
+**Version:** 0.4.6 • **Python:** 3.10+
 
 **Status:** pre-1.0 (API may evolve). For production use, pin versions and follow `CHANGELOG.md`.
 
@@ -75,7 +75,7 @@ AbstractCore integration (LLM + tools):
 pip install "abstractruntime[abstractcore]"
 ```
 
-The `abstractcore` extra installs AbstractCore 2.13.8 or newer so the hardened server auth model, provider-key header routing, prompt-cache control plane, current tool catalog, and unified multimodal generation response types are available. Use `abstractruntime[multimodal]` when you need common media, vision, voice, and audio dependencies.
+The `abstractcore` extra installs AbstractCore 2.13.10 or newer so the hardened server auth model, provider-key header routing, prompt-cache control plane, current tool catalog, unified multimodal generation response types, public output-selector contract, and async/sync text-generation output-selector parity are available. Use `abstractruntime[multimodal]` when you need common media, vision, voice, and audio dependencies.
 
 MCP worker entrypoint (default toolsets over stdio):
 
@@ -124,7 +124,7 @@ state = rt.resume(
 assert state.status.value == "completed"
 ```
 
-## What’s included (v0.4.4)
+## What’s included (v0.4.6)
 
 Kernel (dependency-light):
 - workflow graphs: `WorkflowSpec` (`src/abstractruntime/core/spec.py`)

{abstractruntime-0.4.4 → abstractruntime-0.4.6}/README.md

@@ -4,7 +4,7 @@
 
 It is designed for long-running workflows that must survive restarts and explicitly model blocking (human input, timers, external events, subworkflows) without keeping Python stacks alive.
 
-**Version:** 0.4.4 • **Python:** 3.10+
+**Version:** 0.4.6 • **Python:** 3.10+
 
 **Status:** pre-1.0 (API may evolve). For production use, pin versions and follow `CHANGELOG.md`.
 
@@ -38,7 +38,7 @@ AbstractCore integration (LLM + tools):
 pip install "abstractruntime[abstractcore]"
 ```
 
-The `abstractcore` extra installs AbstractCore 2.13.8 or newer so the hardened server auth model, provider-key header routing, prompt-cache control plane, current tool catalog, and unified multimodal generation response types are available. Use `abstractruntime[multimodal]` when you need common media, vision, voice, and audio dependencies.
+The `abstractcore` extra installs AbstractCore 2.13.10 or newer so the hardened server auth model, provider-key header routing, prompt-cache control plane, current tool catalog, unified multimodal generation response types, public output-selector contract, and async/sync text-generation output-selector parity are available. Use `abstractruntime[multimodal]` when you need common media, vision, voice, and audio dependencies.
 
 MCP worker entrypoint (default toolsets over stdio):
 
@@ -87,7 +87,7 @@ state = rt.resume(
 assert state.status.value == "completed"
 ```
 
-## What’s included (v0.4.4)
+## What’s included (v0.4.6)
 
 Kernel (dependency-light):
 - workflow graphs: `WorkflowSpec` (`src/abstractruntime/core/spec.py`)

{abstractruntime-0.4.4 → abstractruntime-0.4.6}/docs/api.md

@@ -176,7 +176,7 @@ This produces a portable record of a run’s state + ledger + artifacts suitable
 
 ### AbstractCore (LLM + tools)
 
-Requires: `pip install "abstractruntime[abstractcore]"` (AbstractCore 2.13.8 or newer).
+Requires: `pip install "abstractruntime[abstractcore]"` (AbstractCore 2.13.10 or newer).
 
 Implementation: `src/abstractruntime/integrations/abstractcore/*`.
 

{abstractruntime-0.4.4 → abstractruntime-0.4.6}/docs/architecture.md

@@ -1,7 +1,7 @@
 # AbstractRuntime — Architecture
 
 > Updated: 2026-05-07
-> Version: 0.4.4
+> Version: 0.4.6
 > Scope: this describes **what is implemented in this repository**.
 
 AbstractRuntime is a **durable workflow runtime**: it executes workflow graphs as a persisted state machine with explicit waits (user, time, events, jobs, subworkflows). A run can pause for hours/days and resume **without** keeping Python stacks/coroutines alive.

{abstractruntime-0.4.4 → abstractruntime-0.4.6}/docs/getting-started.md

@@ -18,7 +18,7 @@ Optional (LLM + tools via AbstractCore):
 pip install "abstractruntime[abstractcore]"
 ```
 
-This installs AbstractCore 2.13.8 or newer, which matches the documented server auth, provider-key header routing, prompt-cache control plane, current tool behavior, and unified multimodal generation response types. Use `abstractruntime[multimodal]` when your workflows need common media, vision, voice, or audio dependencies.
+This installs AbstractCore 2.13.10 or newer, which matches the documented server auth, provider-key header routing, prompt-cache control plane, current tool behavior, unified multimodal generation response types, public output-selector contract, and async/sync text-generation output-selector parity. Use `abstractruntime[multimodal]` when your workflows need common media, vision, voice, or audio dependencies.
 
 ## Mental model (source of truth)
 

{abstractruntime-0.4.4 → abstractruntime-0.4.6}/docs/integrations/abstractcore.md

@@ -16,7 +16,7 @@ Implementation pointers (this repo):
 pip install "abstractruntime[abstractcore]"
 ```
 
-This extra installs AbstractCore 2.13.8 or newer. That is the supported baseline for the current server auth split (`Authorization` for server auth, `X-AbstractCore-Provider-API-Key` for provider overrides), prompt-cache control-plane endpoints, current tool catalog, and the unified multimodal `generate(..., output=...)` response types.
+This extra installs AbstractCore 2.13.10 or newer. That is the supported baseline for the current server auth split (`Authorization` for server auth, `X-AbstractCore-Provider-API-Key` for provider overrides), prompt-cache control-plane endpoints, current tool catalog, the unified multimodal `generate(..., output=...)` response types, AbstractCore's public output-selector contract, and async/sync text-generation output-selector parity.
 
 For AbstractCore's multimodal `generate(..., output=...)` path, use the newer baseline and optional media packages:
 
@@ -24,7 +24,7 @@ For AbstractCore's multimodal `generate(..., output=...)` path, use the newer ba
 pip install "abstractruntime[multimodal]"
 ```
 
-This installs `abstractcore[media,openai,vision,voice,audio]>=2.13.8`. Local image/voice generation still depends on the configured AbstractCore capability backends (for example AbstractVision and AbstractVoice, or OpenAI/OpenAI-compatible remote engines).
+This installs `abstractcore[media,openai,vision,voice,audio]>=2.13.10`. Local image/voice generation still depends on the configured AbstractCore capability backends (for example AbstractVision and AbstractVoice, or OpenAI/OpenAI-compatible remote engines).
 
 The MCP worker entrypoint uses the `mcp-worker` extra:
 

{abstractruntime-0.4.4 → abstractruntime-0.4.6}/docs/limits.md

@@ -62,7 +62,7 @@ Returns a structured dict for UI/status display. (`src/abstractruntime/core/runt
 
 Returns a list of `LimitWarning` objects for limits approaching/exceeded. (`src/abstractruntime/core/models.py`, `src/abstractruntime/core/runtime.py`)
 
-As of v0.4.4, warnings are computed for:
+As of v0.4.6, warnings are computed for:
 - `iterations` (`current_iteration` vs `max_iterations`)
 - `tokens` (`estimated_tokens_used` vs `max_tokens`)
 

{abstractruntime-0.4.4 → abstractruntime-0.4.6}/docs/proposal.md

@@ -79,7 +79,7 @@ AbstractRuntime stays dependency-light at the kernel level; concrete integration
 
 ## Status (implemented in this repository)
 
-As of v0.4.4:
+As of v0.4.6:
 - durable kernel: `RunState`, `WaitState`, `Runtime.start/tick/resume`
 - built-in waits + events: `WAIT_EVENT`, `WAIT_UNTIL`, `ASK_USER`, `EMIT_EVENT`
 - persistence backends: in-memory, JSON/JSONL, SQLite

{abstractruntime-0.4.4 → abstractruntime-0.4.6}/docs/provenance.md

@@ -8,7 +8,7 @@ Implementation pointers:
 - model fields: `src/abstractruntime/core/models.py` (`StepRecord.prev_hash`, `StepRecord.record_hash`, `StepRecord.signature`)
 - hash-chain decorator + verifier: `src/abstractruntime/storage/ledger_chain.py`
 
-## What is implemented (v0.4.4)
+## What is implemented (v0.4.6)
 
 - `HashChainedLedgerStore(inner_store)` — wraps any `LedgerStore` to compute hashes on append
 - `verify_ledger_chain(records)` — validates the chain and returns a verification report

{abstractruntime-0.4.4 → abstractruntime-0.4.6}/llms-full.txt

@@ -10,11 +10,11 @@ This file is an **agent-oriented build guide** for the AbstractRuntime *library*
 
 Quick facts:
 - Python: 3.10+ (`pyproject.toml`)
-- Version: 0.4.4
+- Version: 0.4.6
 - Ecosystem: [AbstractFramework](https://github.com/lpalbou/AbstractFramework) umbrella; pairs with [AbstractCore](https://github.com/lpalbou/abstractcore)
 - Public export surface (source of truth): `src/abstractruntime/__init__.py`
-- Optional AbstractCore baseline: `abstractruntime[abstractcore]` installs `abstractcore>=2.13.8`
-- Multimodal extra: `abstractruntime[multimodal]` installs `abstractcore[media,openai,vision,voice,audio]>=2.13.8`
+- Optional AbstractCore baseline: `abstractruntime[abstractcore]` installs `abstractcore>=2.13.10`
+- Multimodal extra: `abstractruntime[multimodal]` installs `abstractcore[media,openai,vision,voice,audio]>=2.13.10`
 
 ```mermaid
 flowchart LR

{abstractruntime-0.4.4 → abstractruntime-0.4.6}/llms.txt

@@ -3,11 +3,11 @@
 > Durable workflow runtime (interrupt → checkpoint → resume) with an append-only execution ledger.
 
 - Python: 3.10+ (see `pyproject.toml`)
-- Version: 0.4.4
+- Version: 0.4.6
 - Ecosystem: [AbstractFramework](https://github.com/lpalbou/AbstractFramework) umbrella, integrates with [AbstractCore](https://github.com/lpalbou/abstractcore)
 - Hard invariant: `RunState.vars` must be JSON-serializable (`src/abstractruntime/core/models.py`)
-- Current AbstractCore baseline: `abstractruntime[abstractcore]` installs `abstractcore>=2.13.8`
-- Multimodal extra: `abstractruntime[multimodal]` installs `abstractcore[media,openai,vision,voice,audio]>=2.13.8`
+- Current AbstractCore baseline: `abstractruntime[abstractcore]` installs `abstractcore>=2.13.10`
+- Multimodal extra: `abstractruntime[multimodal]` installs `abstractcore[media,openai,vision,voice,audio]>=2.13.10`
 
 ## Start here
 

{abstractruntime-0.4.4 → abstractruntime-0.4.6}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "AbstractRuntime"
-version = "0.4.4"
+version = "0.4.6"
 description = "AbstractRuntime: a durable graph runner designed to pair with AbstractCore."
 readme = "README.md"
 requires-python = ">=3.10"
@@ -42,18 +42,18 @@ dependencies = [
 [project.optional-dependencies]
 # Enables `abstractruntime.integrations.abstractcore.*` imports.
 abstractcore = [
-  "abstractcore>=2.13.8",
+  "abstractcore>=2.13.10",
 ]
 
 # Enables AbstractCore multimodal generation helpers with common OpenAI-backed
 # image/voice capability packages.
 multimodal = [
-  "abstractcore[media,openai,vision,voice,audio]>=2.13.8",
+  "abstractcore[media,openai,vision,voice,audio]>=2.13.10",
 ]
 
 # Enables `abstractruntime-mcp-worker` with the default toolsets (includes bs4/lxml).
 mcp-worker = [
-  "abstractcore[tools]>=2.13.8",
+  "abstractcore[tools]>=2.13.10",
 ]
 
 # CI/test dependencies. The workflow runs the basic contract suite plus focused

abstractruntime-0.4.6/release-notes.md

@@ -0,0 +1,5 @@
+### Changed
+- Minimum `abstractcore` optional dependency increased to `>=2.13.10` so Runtime picks up AbstractCore's async/sync text-generation output-selector parity in addition to the public output-selector contract.
+
+### Fixed
+- AbstractCore output-selector imports now fail fast when an older local AbstractCore install exposes the helper module but does not include the 2.13.10 async parity fix.

abstractruntime-0.4.6/src/abstractruntime/integrations/abstractcore/output_specs.py

@@ -0,0 +1,98 @@
+"""Runtime adapters around AbstractCore's public output-selector contract."""
+
+from __future__ import annotations
+
+from typing import Any, Dict, List, Optional
+
+_MIN_ABSTRACTCORE_VERSION = (2, 13, 10)
+_MIN_ABSTRACTCORE_VERSION_TEXT = "2.13.10"
+
+
+def _version_tuple(value: str) -> tuple[int, int, int]:
+    parts: list[int] = []
+    for raw in str(value or "").split(".")[:3]:
+        digits = []
+        for char in raw:
+            if not char.isdigit():
+                break
+            digits.append(char)
+        parts.append(int("".join(digits) or "0"))
+    while len(parts) < 3:
+        parts.append(0)
+    return parts[0], parts[1], parts[2]
+
+
+try:
+    from abstractcore.utils.version import __version__ as _abstractcore_version
+    from abstractcore.core.output_specs import (
+        is_output_request,
+        normalize_output_spec,
+        normalize_output_specs,
+        output_has_generated_media,
+        output_requires_non_chat_dispatch,
+        strip_runtime_output_metadata,
+    )
+except ImportError as exc:  # pragma: no cover - import-time dependency guard
+    raise ImportError(
+        f"abstractruntime.integrations.abstractcore requires abstractcore>={_MIN_ABSTRACTCORE_VERSION_TEXT} "
+        "for the public output selector contract."
+    ) from exc
+
+if _version_tuple(_abstractcore_version) < _MIN_ABSTRACTCORE_VERSION:  # pragma: no cover - environment guard
+    raise ImportError(
+        f"abstractruntime.integrations.abstractcore requires abstractcore>={_MIN_ABSTRACTCORE_VERSION_TEXT} "
+        f"for async/sync output-selector parity; found abstractcore {_abstractcore_version}."
+    )
+
+
+def is_abstractcore_output_request(output: Any) -> bool:
+    """Return True when `output` is AbstractCore's multimodal output selector."""
+
+    return is_output_request(output)
+
+
+def normalize_output_spec_for_runtime(output: Any) -> Dict[str, Any]:
+    """Normalize an AbstractCore output selector using the same public aliases as core."""
+
+    return normalize_output_spec(output)
+
+
+def normalize_output_specs_for_runtime(output: Any) -> List[Dict[str, Any]]:
+    return normalize_output_specs(output)
+
+
+def strip_runtime_output_metadata_for_core(output: Any) -> Any:
+    """Keep runtime artifact metadata out of AbstractCore capability kwargs."""
+
+    return strip_runtime_output_metadata(output)
+
+
+def output_runtime_metadata(output: Any) -> tuple[Optional[str], Dict[str, Any]]:
+    """Extract runtime storage metadata from an AbstractCore output selector."""
+
+    if not is_abstractcore_output_request(output):
+        return None, {}
+
+    specs = normalize_output_specs_for_runtime(output)
+    run_id: Optional[str] = None
+    tags: Dict[str, Any] = {}
+    for spec in specs:
+        raw_run_id = spec.get("run_id")
+        if run_id is None and isinstance(raw_run_id, str) and raw_run_id.strip():
+            run_id = raw_run_id.strip()
+
+        raw_tags = spec.get("tags")
+        if isinstance(raw_tags, dict):
+            tags.update({str(k): str(v) for k, v in raw_tags.items() if k is not None and v is not None})
+
+    return run_id, tags
+
+
+def output_request_has_generated_media(output: Any) -> bool:
+    """Return True when an output selector can produce generated binary media."""
+
+    return output_has_generated_media(output)
+
+
+def output_request_has_non_text_result(output: Any) -> bool:
+    return output_requires_non_chat_dispatch(output)

{abstractruntime-0.4.4 → abstractruntime-0.4.6}/tests/test_multimodal_abstractcore_integration.py

@@ -13,7 +13,12 @@ from abstractruntime.integrations.abstractcore.llm_client import (
     RemoteAbstractCoreLLMClient,
     _normalize_local_response,
 )
-from abstractruntime.integrations.abstractcore.output_specs import is_abstractcore_output_request
+from abstractruntime.integrations.abstractcore.output_specs import (
+    is_abstractcore_output_request,
+    normalize_output_specs_for_runtime,
+    output_request_has_generated_media,
+    output_request_has_non_text_result,
+)
 from abstractruntime.storage.artifacts import InMemoryArtifactStore
 from abstractruntime.storage.in_memory import InMemoryLedgerStore, InMemoryRunStore
 
@@ -239,8 +244,13 @@ def test_llm_call_generated_media_requires_artifact_store() -> None:
     assert "ArtifactStore" in str(state.error)
 
 
-def test_runtime_output_selector_detection_matches_abstractcore_for_known_shapes() -> None:
-    from abstractcore.providers.base import BaseProvider
+def test_runtime_output_selector_adapter_delegates_to_public_abstractcore_contract() -> None:
+    from abstractcore.core.output_specs import (
+        is_output_request,
+        normalize_output_specs,
+        output_has_generated_media,
+        output_requires_non_chat_dispatch,
+    )
 
     cases = [
         "text",
@@ -248,6 +258,7 @@ def test_runtime_output_selector_detection_matches_abstractcore_for_known_shapes
         {"modality": "audio"},
         {"modality": "voice"},
         {"task": "tts"},
+        {"task": "text_generation"},
         {"task": "image_edit"},
         [{"modality": "text"}, {"modality": "image"}],
         "json",
@@ -255,7 +266,55 @@ def test_runtime_output_selector_detection_matches_abstractcore_for_known_shapes
     ]
 
     for case in cases:
-        assert is_abstractcore_output_request(case) is BaseProvider._is_acore_output_request(case)
+        assert is_abstractcore_output_request(case) is is_output_request(case)
+
+    text_generation = {"task": "text_generation"}
+    assert normalize_output_specs_for_runtime(text_generation) == normalize_output_specs(text_generation)
+    assert output_request_has_generated_media("image") is output_has_generated_media("image")
+    assert output_request_has_generated_media(text_generation) is False
+    assert output_request_has_non_text_result(text_generation) is output_requires_non_chat_dispatch(text_generation)
+    assert output_request_has_non_text_result(text_generation) is False
+    assert output_request_has_generated_media({"task": "voice_clone"}) is False
+
+
+def test_local_voice_clone_resource_does_not_require_artifact_store() -> None:
+    from abstractcore.core.multimodal_generation import GeneratedResource, MultimodalGenerateResponse
+
+    seen = {}
+
+    class _FakeLLM:
+        def generate(self, **kwargs):
+            seen.update(kwargs)
+            return MultimodalGenerateResponse(
+                resources={
+                    "voice": [
+                        GeneratedResource(
+                            modality="voice",
+                            task="voice_clone",
+                            resource_type="voice",
+                            resource_id="voice-demo",
+                        )
+                    ]
+                }
+            )
+
+    client = object.__new__(LocalAbstractCoreLLMClient)
+    client._provider = "openai"
+    client._model = "gpt-4o-mini"
+    client._artifact_store = None
+    client._generate_lock = None
+    client._llm = _FakeLLM()
+    client._maybe_prepare_prompt_cache = lambda **_kwargs: None
+
+    out = client.generate(
+        prompt="Reference text.",
+        media=[{"type": "audio", "path": "reference.wav"}],
+        params={"output": {"task": "voice_clone", "run_id": "run-voice", "tags": {"node_id": "n-voice"}}},
+    )
+
+    assert seen["output"] == {"task": "voice_clone"}
+    resource = out["resources"]["voice"][0]
+    assert resource["resource_id"] == "voice-demo"
 
 
 class _RemoteImageSender:

{abstractruntime-0.4.4 → abstractruntime-0.4.6}/tests/test_packaging_extras.py

@@ -27,7 +27,8 @@ def test_runtime_exposes_abstractcore_and_worker_extras() -> None:
     assert "[project.optional-dependencies]" in text
     assert "abstractcore = [" in text
     assert "mcp-worker = [" in text
+    assert '"abstractcore>=2.13.10"' in text
+    assert '"abstractcore[media,openai,vision,voice,audio]>=2.13.10"' in text
 
     worker_block = _extract_optional_dependency_block(text, key="mcp-worker")
-    assert "abstractcore[tools]" in worker_block
-
+    assert '"abstractcore[tools]>=2.13.10"' in worker_block

abstractruntime-0.4.4/release-notes.md

@@ -1,35 +0,0 @@
-### Added
-- **AbstractCore multimodal generation integration**:
-  - `LLM_CALL` now forwards AbstractCore's unified `generate(..., output=...)` selector for image generation, TTS/voice output, and audio transcription
-  - generated binary outputs are normalized into JSON-safe runtime results with ArtifactStore-backed refs instead of inline bytes
-  - local runtimes can use AbstractCore capability plugins such as AbstractVision and AbstractVoice through the same runtime effect shape
-  - remote runtimes support AbstractCore Server image generation, speech, and transcription endpoints, plus OpenAI-compatible chat media content arrays
-- **Multimodal packaging extra**:
-  - new `abstractruntime[multimodal]` extra installs `abstractcore[media,openai,vision,voice,audio]>=2.13.8`
-- **VisualFlow LLM media selectors**:
-  - LLM nodes lowered from VisualFlow can request generated media through `output` / `outputs` from node config or input data
-
-### Changed
-- Minimum `abstractcore` optional dependency increased to `>=2.13.8` for the unified multimodal response types.
-- `LLM_CALL` accepts top-level `text`, top-level `output`, and top-level `outputs` as a runtime alias for AbstractCore `output`.
-- `LLM_CALL.media` accepts one media item or a list; artifact refs are materialized to provider-ready temporary files before model calls.
-- Remote AbstractCore clients now preserve existing OpenAI-style content arrays when adding media attachments.
-- Remote AbstractCore clients now resolve ArtifactStore-backed media refs for direct client use, matching the runtime effect-handler path.
-- VisualFlow LLM pending-call lowering now carries `output` / `outputs` selectors into runtime LLM effects.
-- VisualFlow LLM result syncing now projects generated media artifacts into node outputs such as `outputs`, `resources`, `artifact_ref`, `artifact_id`, and `meta.output_mode`.
-
-### Fixed
-- Runtime artifact metadata (`run_id`, tags, artifact ids) is kept out of AbstractCore provider/capability kwargs while still being applied to stored generated media artifacts.
-- Generated binary media now fails closed without an ArtifactStore instead of embedding base64 bytes in durable state.
-- Remote image/TTS/STT calls no longer reuse the chat model unless an output-specific media model is supplied.
-- Remote media inputs now either convert to a provider-ready content item or fail before dispatch; unsupported remote image edits, voice reference inputs, and non-file STT inputs are rejected explicitly.
-- Turn-grounding injection now preserves structured multimodal message content arrays instead of stringifying them.
-- Session-scoped prompt-cache key derivation now uses the effective AbstractCore client provider/model identity when an `LLM_CALL` payload omits explicit provider/model overrides.
-
-### Documentation
-- Documented multimodal `LLM_CALL` payloads, artifact-backed response shape, remote endpoint coverage, cached-session/prompt-cache boundaries, and the `abstractruntime[multimodal]` extra in the AbstractCore integration guide, API reference, architecture guide, FAQ, README, getting-started guide, docs index, and AI-ready `llms*.txt` files.
-- Added a planned workspace/media access policy item covering default workspace-only access, explicit user allow/deny paths, and a conscious full-machine access mode for long-running agency deployments.
-
-### Testing
-- Added focused coverage for multimodal response normalization, artifact-backed generated media, media-only transcription calls, remote image/TTS/STT endpoints, remote media guardrails, remote chat media content arrays, content-array prompt extraction, direct remote artifact-ref media resolution, text-alias routing, provider-request redaction, and runtime metadata/tag boundaries.
-- Added coverage for effective prompt-cache key identity and VisualFlow LLM media selector/result projection.