AbstractRuntime 0.4.24__tar.gz → 0.4.25__tar.gz

{abstractruntime-0.4.24 → abstractruntime-0.4.25}/CHANGELOG.md

@@ -7,6 +7,18 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.4.25] - 2026-05-29
+
+### Added
+- File-backed artifact stores now expose `content_path(...)` for hosts that need a stable local path while in-memory stores continue to return `None`.
+
+### Changed
+- Minimum optional AbstractCore dependency floor is now `abstractcore>=2.13.30` (and matching `multimodal`, `mcp-worker`, and hardware-profile cascade extras), aligning Runtime with the latest Core media/plugin floors and image-to-image residency truth.
+
+### Fixed
+- Artifact-backed media resolution now preserves image roles such as `source` and `mask`, keeping image-edit and image-to-video requests wired correctly through AbstractCore.
+- Model-residency discovery now treats `image_to_image` as its own vision task and deduplicates shared loaded-model records when task is omitted.
+
 ## [0.4.24] - 2026-05-26
 
 ### Added
@@ -558,7 +570,8 @@ 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/v0.4.24...HEAD
+[Unreleased]: https://github.com/lpalbou/abstractruntime/compare/v0.4.25...HEAD
+[0.4.25]: https://github.com/lpalbou/abstractruntime/compare/v0.4.24...v0.4.25
 [0.4.24]: https://github.com/lpalbou/abstractruntime/compare/v0.4.23...v0.4.24
 [0.4.23]: https://github.com/lpalbou/abstractruntime/compare/v0.4.22...v0.4.23
 [0.4.22]: https://github.com/lpalbou/abstractruntime/compare/v0.4.21...v0.4.22

{abstractruntime-0.4.24 → abstractruntime-0.4.25}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: AbstractRuntime
-Version: 0.4.24
+Version: 0.4.25
 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
@@ -23,24 +23,24 @@ Requires-Python: >=3.10
 Requires-Dist: abstractmemory>=0.2.6
 Requires-Dist: abstractsemantics>=0.0.3
 Provides-Extra: abstractcore
-Requires-Dist: abstractcore>=2.13.29; extra == 'abstractcore'
+Requires-Dist: abstractcore>=2.13.30; extra == 'abstractcore'
 Requires-Dist: anyio<5.0.0,>=4.12.1; extra == 'abstractcore'
 Requires-Dist: httpx<1.0.0,>=0.28.1; extra == 'abstractcore'
 Requires-Dist: openai<2.0.0,>=1.109.1; extra == 'abstractcore'
 Provides-Extra: all-apple
-Requires-Dist: abstractcore[all-apple]>=2.13.29; extra == 'all-apple'
+Requires-Dist: abstractcore[all-apple]>=2.13.30; extra == 'all-apple'
 Requires-Dist: anyio<5.0.0,>=4.12.1; extra == 'all-apple'
 Requires-Dist: httpx<1.0.0,>=0.28.1; extra == 'all-apple'
 Requires-Dist: openai<2.0.0,>=1.109.1; extra == 'all-apple'
 Requires-Dist: setuptools<82.0.0,>=80.10.2; extra == 'all-apple'
 Provides-Extra: all-gpu
-Requires-Dist: abstractcore[all-gpu]>=2.13.29; extra == 'all-gpu'
+Requires-Dist: abstractcore[all-gpu]>=2.13.30; extra == 'all-gpu'
 Requires-Dist: anyio<5.0.0,>=4.12.1; extra == 'all-gpu'
 Requires-Dist: httpx<1.0.0,>=0.28.1; extra == 'all-gpu'
 Requires-Dist: openai<2.0.0,>=1.109.1; extra == 'all-gpu'
 Requires-Dist: setuptools<82.0.0,>=80.10.2; extra == 'all-gpu'
 Provides-Extra: apple
-Requires-Dist: abstractcore[apple]>=2.13.29; extra == 'apple'
+Requires-Dist: abstractcore[apple]>=2.13.30; extra == 'apple'
 Requires-Dist: anyio<5.0.0,>=4.12.1; extra == 'apple'
 Requires-Dist: httpx<1.0.0,>=0.28.1; extra == 'apple'
 Requires-Dist: openai<2.0.0,>=1.109.1; extra == 'apple'
@@ -50,18 +50,18 @@ 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: gpu
-Requires-Dist: abstractcore[gpu]>=2.13.29; extra == 'gpu'
+Requires-Dist: abstractcore[gpu]>=2.13.30; extra == 'gpu'
 Requires-Dist: anyio<5.0.0,>=4.12.1; extra == 'gpu'
 Requires-Dist: httpx<1.0.0,>=0.28.1; extra == 'gpu'
 Requires-Dist: openai<2.0.0,>=1.109.1; extra == 'gpu'
 Requires-Dist: setuptools<82.0.0,>=80.10.2; extra == 'gpu'
 Provides-Extra: mcp-worker
-Requires-Dist: abstractcore[tools]>=2.13.29; extra == 'mcp-worker'
+Requires-Dist: abstractcore[tools]>=2.13.30; extra == 'mcp-worker'
 Requires-Dist: anyio<5.0.0,>=4.12.1; extra == 'mcp-worker'
 Requires-Dist: httpx<1.0.0,>=0.28.1; extra == 'mcp-worker'
 Requires-Dist: openai<2.0.0,>=1.109.1; extra == 'mcp-worker'
 Provides-Extra: multimodal
-Requires-Dist: abstractcore[audio,music,remote,vision,voice]>=2.13.29; extra == 'multimodal'
+Requires-Dist: abstractcore[audio,music,remote,vision,voice]>=2.13.30; extra == 'multimodal'
 Requires-Dist: anyio<5.0.0,>=4.12.1; extra == 'multimodal'
 Requires-Dist: httpx<1.0.0,>=0.28.1; extra == 'multimodal'
 Requires-Dist: openai<2.0.0,>=1.109.1; extra == 'multimodal'
@@ -81,7 +81,7 @@ 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:** 0.4.24 • **Python:** 3.10+
+**Version:** 0.4.25 • **Python:** 3.10+
 
 **Status:** pre-1.0 (API may evolve). For production use, pin versions and follow `CHANGELOG.md`.
 
@@ -115,7 +115,7 @@ AbstractCore integration (LLM + tools):
 pip install "abstractruntime[abstractcore]"
 ```
 
-The `abstractcore` extra installs AbstractCore 2.13.29 or newer so the hardened server auth model, provider-key header routing, generated-media contracts, capability catalog, prompt-cache control plane, durable bloc prompt-cache helpers, bindings, lifecycle operations, public output-selector contract, async/sync text-generation output-selector parity, task-aware model residency for text/image/video/TTS/STT, video generation endpoints, and the public local vision-cache catalog helper used by Runtime discovery remain aligned. Use `abstractruntime[multimodal]` when you need common media dependencies and capability plugins (installs `abstractcore[remote,vision,voice,audio,music]>=2.13.29`, including `abstractmusic>=0.1.12`).
+The `abstractcore` extra installs AbstractCore 2.13.30 or newer so the hardened server auth model, provider-key header routing, generated-media contracts, capability catalog, prompt-cache control plane, durable bloc prompt-cache helpers, bindings, lifecycle operations, public output-selector contract, async/sync text-generation output-selector parity, task-aware model residency for text/image/video/TTS/STT, video generation endpoints, and the public local vision-cache catalog helper used by Runtime discovery remain aligned. Use `abstractruntime[multimodal]` when you need common media dependencies and capability plugins (installs `abstractcore[remote,vision,voice,audio,music]>=2.13.30`, including `abstractmusic>=0.1.12`).
 
 Hardware profile cascades are available for native Python installs:
 `abstractruntime[apple]`, `abstractruntime[gpu]`, `abstractruntime[all-apple]`,
@@ -169,7 +169,7 @@ state = rt.resume(
 assert state.status.value == "completed"
 ```
 
-## What’s included (v0.4.24)
+## What’s included (v0.4.25)
 
 Kernel (dependency-light):
 - workflow graphs: `WorkflowSpec` (`src/abstractruntime/core/spec.py`)

{abstractruntime-0.4.24 → abstractruntime-0.4.25}/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:** 0.4.24 • **Python:** 3.10+
+**Version:** 0.4.25 • **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 2.13.29 or newer so the hardened server auth model, provider-key header routing, generated-media contracts, capability catalog, prompt-cache control plane, durable bloc prompt-cache helpers, bindings, lifecycle operations, public output-selector contract, async/sync text-generation output-selector parity, task-aware model residency for text/image/video/TTS/STT, video generation endpoints, and the public local vision-cache catalog helper used by Runtime discovery remain aligned. Use `abstractruntime[multimodal]` when you need common media dependencies and capability plugins (installs `abstractcore[remote,vision,voice,audio,music]>=2.13.29`, including `abstractmusic>=0.1.12`).
+The `abstractcore` extra installs AbstractCore 2.13.30 or newer so the hardened server auth model, provider-key header routing, generated-media contracts, capability catalog, prompt-cache control plane, durable bloc prompt-cache helpers, bindings, lifecycle operations, public output-selector contract, async/sync text-generation output-selector parity, task-aware model residency for text/image/video/TTS/STT, video generation endpoints, and the public local vision-cache catalog helper used by Runtime discovery remain aligned. Use `abstractruntime[multimodal]` when you need common media dependencies and capability plugins (installs `abstractcore[remote,vision,voice,audio,music]>=2.13.30`, including `abstractmusic>=0.1.12`).
 
 Hardware profile cascades are available for native Python installs:
 `abstractruntime[apple]`, `abstractruntime[gpu]`, `abstractruntime[all-apple]`,
@@ -92,7 +92,7 @@ state = rt.resume(
 assert state.status.value == "completed"
 ```
 
-## What’s included (v0.4.24)
+## What’s included (v0.4.25)
 
 Kernel (dependency-light):
 - workflow graphs: `WorkflowSpec` (`src/abstractruntime/core/spec.py`)

{abstractruntime-0.4.24 → abstractruntime-0.4.25}/docs/api.md

@@ -180,7 +180,7 @@ This produces a portable record of a run’s state + ledger + artifacts suitable
 
 ### AbstractCore (LLM + tools)
 
-Requires: `pip install "abstractruntime[abstractcore]"` (AbstractCore 2.13.29 or newer).
+Requires: `pip install "abstractruntime[abstractcore]"` (AbstractCore 2.13.30 or newer).
 
 Implementation: `src/abstractruntime/integrations/abstractcore/*`.
 

{abstractruntime-0.4.24 → abstractruntime-0.4.25}/docs/getting-started.md

@@ -18,7 +18,7 @@ Optional (LLM + tools via AbstractCore):
 pip install "abstractruntime[abstractcore]"
 ```
 
-This installs AbstractCore 2.13.29 or newer, which matches the documented server auth, provider-key header routing, generated-media contracts, capability catalog, prompt-cache control plane, durable bloc prompt-cache helpers, bindings and lifecycle operations, task-aware model residency for text/image/video/TTS/STT, current tool behavior, public output-selector contract, async/sync text-generation output-selector parity, video generation endpoints, and the public local vision-cache catalog helper used by Runtime discovery. Use `abstractruntime[multimodal]` when your workflows need common media dependencies and capability plugins (installs `abstractcore[remote,vision,voice,audio,music]>=2.13.29`, including `abstractmusic>=0.1.12`).
+This installs AbstractCore 2.13.30 or newer, which matches the documented server auth, provider-key header routing, generated-media contracts, capability catalog, prompt-cache control plane, durable bloc prompt-cache helpers, bindings and lifecycle operations, task-aware model residency for text/image/video/TTS/STT, current tool behavior, public output-selector contract, async/sync text-generation output-selector parity, video generation endpoints, and the public local vision-cache catalog helper used by Runtime discovery. Use `abstractruntime[multimodal]` when your workflows need common media dependencies and capability plugins (installs `abstractcore[remote,vision,voice,audio,music]>=2.13.30`, including `abstractmusic>=0.1.12`).
 
 ## Mental model (source of truth)
 

{abstractruntime-0.4.24 → abstractruntime-0.4.25}/docs/integrations/abstractcore.md

@@ -16,7 +16,7 @@ Implementation pointers (this repo):
 pip install "abstractruntime[abstractcore]"
 ```
 
-This extra installs AbstractCore 2.13.29 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), generated-media contracts, capability catalog, prompt-cache control-plane endpoints, durable bloc prompt-cache helpers, bindings and lifecycle operations, task-aware model residency for text/image/video/TTS/STT, current tool catalog, AbstractCore's public output-selector contract, async/sync text-generation output-selector parity, video generation endpoints, and the public local vision-cache catalog helper used by Runtime discovery.
+This extra installs AbstractCore 2.13.30 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), generated-media contracts, capability catalog, prompt-cache control-plane endpoints, durable bloc prompt-cache helpers, bindings and lifecycle operations, task-aware model residency for text/image/video/TTS/STT, current tool catalog, AbstractCore's public output-selector contract, async/sync text-generation output-selector parity, video generation endpoints, and the public local vision-cache catalog helper used by Runtime discovery.
 
 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[remote,vision,voice,audio,music]>=2.13.29`. Local image/video/voice/music generation still depends on the configured AbstractCore capability backends (for example AbstractVision, AbstractVoice, and AbstractMusic, or OpenAI/OpenAI-compatible remote engines). With `abstractmusic>=0.1.12`, the base music extra includes the lightweight remote ACE Music backend without local model-runtime extras.
+This installs `abstractcore[remote,vision,voice,audio,music]>=2.13.30`. Local image/video/voice/music generation still depends on the configured AbstractCore capability backends (for example AbstractVision, AbstractVoice, and AbstractMusic, or OpenAI/OpenAI-compatible remote engines). With `abstractmusic>=0.1.12`, the base music extra includes the lightweight remote ACE Music backend without local model-runtime extras.
 
 The MCP worker entrypoint uses the `mcp-worker` extra:
 

{abstractruntime-0.4.24 → abstractruntime-0.4.25}/docs/troubleshooting.md

@@ -21,7 +21,7 @@ Fix:
   - `abstractruntime[abstractcore]` for LLM/tools integration.
   - `abstractruntime[multimodal]` for common image, voice, audio, and music dependencies.
   - `abstractruntime[mcp-worker]` for the MCP worker entry point.
-- The current AbstractCore integration expects `abstractcore>=2.13.29`.
+- The current AbstractCore integration expects `abstractcore>=2.13.30`.
 
 Verify:
 

{abstractruntime-0.4.24 → abstractruntime-0.4.25}/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: 0.4.24
+- Version: 0.4.25
 - 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>=2.13.29`
-- Multimodal extra: `abstractruntime[multimodal]` installs `abstractcore[remote,vision,voice,audio,music]>=2.13.29`
+- Optional AbstractCore baseline: `abstractruntime[abstractcore]` installs `abstractcore>=2.13.30`
+- Multimodal extra: `abstractruntime[multimodal]` installs `abstractcore[remote,vision,voice,audio,music]>=2.13.30`
 - Config boundary: Runtime does not read `ABSTRACTGATEWAY_*`; Gateway-owned env/config should be translated into explicit Runtime inputs or Runtime-owned env names.
 
 ```mermaid

{abstractruntime-0.4.24 → abstractruntime-0.4.25}/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: 0.4.24
+- Version: 0.4.25
 - 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>=2.13.29`
-- Multimodal extra: `abstractruntime[multimodal]` installs `abstractcore[remote,vision,voice,audio,music]>=2.13.29`
+- Current AbstractCore baseline: `abstractruntime[abstractcore]` installs `abstractcore>=2.13.30`
+- Multimodal extra: `abstractruntime[multimodal]` installs `abstractcore[remote,vision,voice,audio,music]>=2.13.30`
 - Config boundary: Runtime does not read `ABSTRACTGATEWAY_*`; Gateway-owned config should be translated into explicit Runtime inputs or Runtime-owned env names.
 
 ## Start here

{abstractruntime-0.4.24 → abstractruntime-0.4.25}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "AbstractRuntime"
-version = "0.4.24"
+version = "0.4.25"
 description = "AbstractRuntime: a durable graph runner designed to pair with AbstractCore."
 readme = "README.md"
 requires-python = ">=3.10"
@@ -46,14 +46,14 @@ dependencies = [
 [project.optional-dependencies]
 # Enables `abstractruntime.integrations.abstractcore.*` imports.
 abstractcore = [
-  "abstractcore>=2.13.29",
+  "abstractcore>=2.13.30",
   "openai<2.0.0,>=1.109.1",
   "httpx<1.0.0,>=0.28.1",
   "anyio<5.0.0,>=4.12.1",
 ]
 
 apple = [
-  "abstractcore[apple]>=2.13.29",
+  "abstractcore[apple]>=2.13.30",
   "openai<2.0.0,>=1.109.1",
   "httpx<1.0.0,>=0.28.1",
   "anyio<5.0.0,>=4.12.1",
@@ -61,7 +61,7 @@ apple = [
 ]
 
 gpu = [
-  "abstractcore[gpu]>=2.13.29",
+  "abstractcore[gpu]>=2.13.30",
   "openai<2.0.0,>=1.109.1",
   "httpx<1.0.0,>=0.28.1",
   "anyio<5.0.0,>=4.12.1",
@@ -69,7 +69,7 @@ gpu = [
 ]
 
 all-apple = [
-  "abstractcore[all-apple]>=2.13.29",
+  "abstractcore[all-apple]>=2.13.30",
   "openai<2.0.0,>=1.109.1",
   "httpx<1.0.0,>=0.28.1",
   "anyio<5.0.0,>=4.12.1",
@@ -77,7 +77,7 @@ all-apple = [
 ]
 
 all-gpu = [
-  "abstractcore[all-gpu]>=2.13.29",
+  "abstractcore[all-gpu]>=2.13.30",
   "openai<2.0.0,>=1.109.1",
   "httpx<1.0.0,>=0.28.1",
   "anyio<5.0.0,>=4.12.1",
@@ -87,7 +87,7 @@ all-gpu = [
 # Enables AbstractCore multimodal generation helpers with common image/voice/
 # audio/music capability packages.
 multimodal = [
-  "abstractcore[remote,vision,voice,audio,music]>=2.13.29",
+  "abstractcore[remote,vision,voice,audio,music]>=2.13.30",
   "openai<2.0.0,>=1.109.1",
   "httpx<1.0.0,>=0.28.1",
   "anyio<5.0.0,>=4.12.1",
@@ -101,7 +101,7 @@ multimodal = [
 
 # Enables `abstractruntime-mcp-worker` with the default toolsets (includes bs4/lxml).
 mcp-worker = [
-  "abstractcore[tools]>=2.13.29",
+  "abstractcore[tools]>=2.13.30",
   "openai<2.0.0,>=1.109.1",
   "httpx<1.0.0,>=0.28.1",
   "anyio<5.0.0,>=4.12.1",

abstractruntime-0.4.25/release-notes.md

@@ -0,0 +1,9 @@
+### Added
+- File-backed artifact stores now expose `content_path(...)` for hosts that need a stable local path while in-memory stores continue to return `None`.
+
+### Changed
+- Minimum optional AbstractCore dependency floor is now `abstractcore>=2.13.30` (and matching `multimodal`, `mcp-worker`, and hardware-profile cascade extras), aligning Runtime with the latest Core media/plugin floors and image-to-image residency truth.
+
+### Fixed
+- Artifact-backed media resolution now preserves image roles such as `source` and `mask`, keeping image-edit and image-to-video requests wired correctly through AbstractCore.
+- Model-residency discovery now treats `image_to_image` as its own vision task and deduplicates shared loaded-model records when task is omitted.

{abstractruntime-0.4.24 → abstractruntime-0.4.25}/src/abstractruntime/integrations/abstractcore/effect_handlers.py

@@ -780,6 +780,11 @@ def _resolve_llm_call_media(
         except Exception as e:
             return None, f"Failed to materialize artifact '{artifact_id}': {e}"
         resolved: Dict[str, Any] = {"file_path": str(p), "$artifact": str(artifact_id), "artifact_id": str(artifact_id)}
+        if isinstance(item, dict):
+            for key in ("role", "purpose", "kind"):
+                raw_role = item.get(key)
+                if isinstance(raw_role, str) and raw_role.strip():
+                    resolved[key] = raw_role.strip()
         if content_type:
             resolved["content_type"] = content_type
             base_type = content_type.split(";", 1)[0].strip().lower()

{abstractruntime-0.4.24 → abstractruntime-0.4.25}/src/abstractruntime/integrations/abstractcore/llm_client.py

@@ -2145,10 +2145,10 @@ def _normalize_residency_task(task: Any) -> str:
         "vision": "image_generation",
         "t2i": "image_generation",
         "text_to_image": "image_generation",
-        "i2i": "image_generation",
-        "image_to_image": "image_generation",
-        "image_edit": "image_generation",
-        "edit_image": "image_generation",
+        "i2i": "image_to_image",
+        "image_to_image": "image_to_image",
+        "image_edit": "image_to_image",
+        "edit_image": "image_to_image",
         "video": "video_generation",
         "videos": "video_generation",
         "video_generation": "video_generation",
@@ -2189,6 +2189,7 @@ def _residency_task_filter(task: Any) -> Optional[str]:
 
 _LOCAL_CAPABILITY_RESIDENCY_LIST_TASKS = (
     "image_generation",
+    "image_to_image",
     "video_generation",
     "text_to_video",
     "image_to_video",
@@ -2223,7 +2224,7 @@ def _model_residency_unsupported_payload(
         "diagnostics": {"source": "abstractruntime"},
         "affected_models": [],
     }
-    if task_s in {"image_generation", "video_generation", "text_to_video", "image_to_video"}:
+    if task_s in {"image_generation", "image_to_image", "video_generation", "text_to_video", "image_to_video"}:
         payload["execution_mode"] = "local_one_shot_subprocess"
         payload["local_media_residency_backend"] = "none"
         payload["requires_long_lived_core_backend"] = True
@@ -2285,6 +2286,16 @@ def _local_model_residency_capabilities(*, mode: str, source: str, text_loads_ot
                 "requires_installed_capability_plugin": True,
             },
         ),
+        "image_to_image": _model_residency_capability_task(
+            task="image_to_image",
+            supported=True,
+            truth_source="abstractcore.capability_plugin",
+            extra={
+                "local_media_residency_backend": "capability_plugin",
+                "requires_installed_capability_plugin": True,
+                "shares_backend_cache_with": "image_generation",
+            },
+        ),
         "text_to_video": _model_residency_capability_task(
             task="text_to_video",
             supported=True,
@@ -2680,7 +2691,7 @@ def _local_capability_residency_target(core: Any, task: str) -> Tuple[Any, str]:
         return getattr(core, "audio", None), "audio"
     if task_s == "music_generation":
         return getattr(core, "music", None), "music"
-    if task_s == "image_generation":
+    if task_s in {"image_generation", "image_to_image"}:
         return getattr(core, "vision", None), "vision"
     raise ValueError(f"Unsupported local capability residency task: {task!r}")
 
@@ -2762,7 +2773,22 @@ def _local_all_model_residency_result(
         if isinstance(result, dict) and result.get("ok") is False and result.get("error"):
             task_errors[task_s] = str(result.get("error"))
 
-    records = sorted(records, key=lambda item: str(item.get("runtime_id") or item.get("load_id") or ""))
+    deduped: List[Dict[str, Any]] = []
+    seen_record_keys: set[str] = set()
+    for record in records:
+        record_key = str(record.get("runtime_id") or record.get("load_id") or "").strip()
+        if not record_key:
+            record_key = "|".join(
+                str(record.get(key) or "").strip()
+                for key in ("task", "provider", "model")
+            )
+        if record_key and record_key in seen_record_keys:
+            continue
+        if record_key:
+            seen_record_keys.add(record_key)
+        deduped.append(record)
+
+    records = sorted(deduped, key=lambda item: str(item.get("runtime_id") or item.get("load_id") or ""))
     diagnostics: Dict[str, Any] = {"source": source, "count": len(records), "task_counts": task_counts}
     if task_errors:
         diagnostics["task_errors"] = task_errors
@@ -7085,6 +7111,12 @@ class RemoteAbstractCoreLLMClient:
                 supported=True,
                 truth_source="abstractcore.server./acore/models",
             ),
+            "image_to_image": _model_residency_capability_task(
+                task="image_to_image",
+                supported=True,
+                truth_source="abstractcore.server./acore/models",
+                extra={"shares_backend_cache_with": "image_generation"},
+            ),
             "text_to_video": _model_residency_capability_task(
                 task="text_to_video",
                 supported=True,

{abstractruntime-0.4.24 → abstractruntime-0.4.25}/src/abstractruntime/storage/artifacts.py

@@ -273,6 +273,14 @@ class ArtifactStore(ABC):
         candidates.sort(key=lambda m: m.created_at, reverse=True)
         return candidates[:limit]
 
+    def content_path(self, artifact_id: str) -> Optional[Path]:
+        """Return a local content path when this store is file-backed.
+
+        Stores that cannot expose a stable local file path return ``None``; callers
+        should fall back to ``load()``.
+        """
+        return None
+
     # Convenience methods
 
     def store_text(
@@ -453,6 +461,10 @@ class FileArtifactStore(ArtifactStore):
             return self._blob_path(blob_id.strip())
         return self._legacy_content_path(artifact_id)
 
+    def content_path(self, artifact_id: str) -> Optional[Path]:
+        path = self._content_path(artifact_id)
+        return path if path.exists() else None
+
     def _metadata_path(self, artifact_id: str) -> Path:
         validate_artifact_id(artifact_id)
         p = self._ref_metadata_path(artifact_id)

{abstractruntime-0.4.24 → abstractruntime-0.4.25}/tests/test_artifacts.py

@@ -235,6 +235,26 @@ class TestFileArtifactStore:
             artifact = store.load(metadata.artifact_id)
             assert artifact.content == content
 
+    def test_content_path_is_public_for_file_backed_store(self):
+        """File stores expose a stable content path; memory stores do not."""
+        memory_store = InMemoryArtifactStore()
+        memory_meta = memory_store.store(b"in memory", content_type="text/plain")
+        assert memory_store.content_path(memory_meta.artifact_id) is None
+
+        with tempfile.TemporaryDirectory() as tmpdir:
+            store = FileArtifactStore(tmpdir)
+            metadata = store.store(b"Persistent content", content_type="text/plain", run_id="run-1")
+            path = store.content_path(metadata.artifact_id)
+            assert path is not None
+            assert path.exists()
+            assert path.read_bytes() == b"Persistent content"
+
+            restarted = FileArtifactStore(tmpdir)
+            restarted_path = restarted.content_path(metadata.artifact_id)
+            assert restarted_path is not None
+            assert restarted_path.exists()
+            assert restarted_path.read_bytes() == b"Persistent content"
+
     def test_persistence_across_instances(self):
         """Artifacts persist across store instances."""
         with tempfile.TemporaryDirectory() as tmpdir:

{abstractruntime-0.4.24 → abstractruntime-0.4.25}/tests/test_media_artifact_resolution.py

@@ -64,3 +64,36 @@ def test_effect_handler_materialized_audio_artifact_preserves_content_type(tmp_p
     assert item["type"] == "audio"
     assert Path(item["file_path"]).suffix == ".wav"
     assert BaseProvider._media_type(item) == "audio"
+
+
+def test_effect_handler_materialized_image_artifacts_preserve_roles(tmp_path: Path) -> None:
+    from abstractruntime.integrations.abstractcore.effect_handlers import _resolve_llm_call_media
+
+    class Artifact:
+        content = PNG_1X1 = (
+            b"\x89PNG\r\n\x1a\n\x00\x00\x00\rIHDR"
+            b"\x00\x00\x00\x01\x00\x00\x00\x01\x08\x06\x00\x00\x00"
+            b"\x1f\x15\xc4\x89"
+        )
+        content_type = "image/png"
+        metadata = None
+
+    class Store:
+        def load(self, artifact_id: str) -> Artifact:
+            assert artifact_id in {"source-img", "mask-img"}
+            return Artifact()
+
+    resolved, error = _resolve_llm_call_media(
+        [
+            {"$artifact": "source-img", "content_type": "image/png", "role": "source"},
+            {"$artifact": "mask-img", "content_type": "image/png", "role": "mask"},
+        ],
+        artifact_store=Store(),
+        temp_dir=tmp_path,
+    )
+
+    assert error is None
+    assert isinstance(resolved, list)
+    assert [item.get("role") for item in resolved] == ["source", "mask"]
+    assert all(item.get("type") == "image" for item in resolved)
+    assert all(Path(str(item.get("file_path") or "")).is_file() for item in resolved)

{abstractruntime-0.4.24 → abstractruntime-0.4.25}/tests/test_model_residency_control_plane.py

@@ -872,6 +872,8 @@ def test_model_residency_capabilities_describe_core_backed_truth_by_task() -> No
     assert local_caps["tasks"]["text_generation"]["truth_source"] == "abstractcore.provider.get_model_residency"
     assert local_caps["tasks"]["image_generation"]["supported"] is True
     assert local_caps["tasks"]["image_generation"]["truth_source"] == "abstractcore.capability_plugin"
+    assert local_caps["tasks"]["image_to_image"]["supported"] is True
+    assert local_caps["tasks"]["image_to_image"]["shares_backend_cache_with"] == "image_generation"
     assert local_caps["tasks"]["video_generation"]["supported"] is True
     assert local_caps["tasks"]["text_to_video"]["supported"] is True
     assert local_caps["tasks"]["image_to_video"]["supported"] is True
@@ -882,6 +884,8 @@ def test_model_residency_capabilities_describe_core_backed_truth_by_task() -> No
     assert multi_caps["tasks"]["tts"]["local_media_residency_backend"] == "capability_plugin"
     assert remote_caps["relay_only"] is True
     assert remote_caps["tasks"]["image_generation"]["truth_source"] == "abstractcore.server./acore/models"
+    assert remote_caps["tasks"]["image_to_image"]["truth_source"] == "abstractcore.server./acore/models"
+    assert remote_caps["tasks"]["image_to_image"]["supported"] is True
     assert remote_caps["tasks"]["video_generation"]["truth_source"] == "abstractcore.server./acore/models"
     assert remote_caps["tasks"]["text_to_video"]["supported"] is True
     assert remote_caps["tasks"]["image_to_video"]["supported"] is True

{abstractruntime-0.4.24 → abstractruntime-0.4.25}/tests/test_visualflow_media_nodes.py

@@ -47,6 +47,8 @@ def test_generate_image_node_compiles_to_llm_call_output_selector() -> None:
             "width": 512,
             "height": 512,
             "steps": 8,
+            "seed": 1234,
+            "guidance_scale": 6.5,
         },
     )
 
@@ -65,6 +67,8 @@ def test_generate_image_node_compiles_to_llm_call_output_selector() -> None:
     assert output["width"] == 512
     assert output["height"] == 512
     assert output["steps"] == 8
+    assert output["seed"] == 1234
+    assert output["guidance_scale"] == 6.5
 
 
 def test_generate_image_legacy_provider_model_are_not_media_fallbacks() -> None:
@@ -112,6 +116,8 @@ def test_edit_image_node_compiles_to_llm_call_image_edit_selector() -> None:
             "format": "png",
             "size": "1024x1024",
             "strength": 0.65,
+            "seed": 1234,
+            "guidance_scale": 6.5,
         },
     )
 
@@ -127,6 +133,8 @@ def test_edit_image_node_compiles_to_llm_call_image_edit_selector() -> None:
     assert output["model"] == "gpt-image-1"
     assert output["size"] == "1024x1024"
     assert output["strength"] == 0.65
+    assert output["seed"] == 1234
+    assert output["guidance_scale"] == 6.5
     assert media[0]["$artifact"] == "source-img"
     assert media[0]["type"] == "image"
     assert media[0]["role"] == "source"
@@ -137,13 +145,15 @@ def test_edit_image_node_compiles_to_llm_call_image_edit_selector() -> None:
 def test_image_to_image_alias_compiles_to_image_edit_selector() -> None:
     plan = _plan_for_node(
         "image_to_image",
-        {"prompt": "Add clouds.", "source_image": "img-1"},
+        {"prompt": "Add clouds.", "source_image": "img-1", "seed": 42, "guidance_scale": 5.5},
     )
 
     assert plan.effect is not None
     payload = dict(plan.effect.payload or {})
     output = dict(payload.get("output") or {})
     assert output["task"] == "image_edit"
+    assert output["seed"] == 42
+    assert output["guidance_scale"] == 5.5
     assert payload["media"] == [{"type": "image", "role": "source", "$artifact": "img-1"}]
 
 
@@ -160,6 +170,7 @@ def test_generate_video_node_compiles_to_llm_call_video_selector() -> None:
             "frames": 121,
             "fps": 24,
             "steps": 50,
+            "seed": 4321,
             "guidance_scale": 5.0,
         },
     )
@@ -181,6 +192,7 @@ def test_generate_video_node_compiles_to_llm_call_video_selector() -> None:
     assert output["num_frames"] == 121
     assert output["fps"] == 24
     assert output["steps"] == 50
+    assert output["seed"] == 4321
     assert output["guidance_scale"] == 5.0
 
 
@@ -193,6 +205,8 @@ def test_image_to_video_node_compiles_to_llm_call_video_selector() -> None:
             "video_provider": "mlx-gen",
             "video_model": "Wan-AI/Wan2.2-TI2V-5B-Diffusers",
             "frames": 41,
+            "seed": 4321,
+            "guidance_scale": 5.0,
         },
     )
 
@@ -204,6 +218,8 @@ def test_image_to_video_node_compiles_to_llm_call_video_selector() -> None:
     assert output["provider"] == "mlx-gen"
     assert output["model"] == "Wan-AI/Wan2.2-TI2V-5B-Diffusers"
     assert output["num_frames"] == 41
+    assert output["seed"] == 4321
+    assert output["guidance_scale"] == 5.0
     assert payload["media"] == [{"type": "image", "role": "source", "$artifact": "img-1"}]
 
 

abstractruntime-0.4.24/release-notes.md

@@ -1,11 +0,0 @@
-### Added
-- Runtime now surfaces AbstractCore/AbstractVision video generation through the existing generated-media boundary:
-  - `LLM_CALL` output selectors for `{"modality":"video","task":"text_to_video"}` and `{"modality":"video","task":"image_to_video"}`
-  - remote Core Server routing for `/v1/videos/generations` and `/v1/videos/edits`
-  - durable run-facade helpers `generate_video(...)` and `image_to_video(...)`
-  - VisualFlow node lowering for `generate_video` / `text_to_video` and `image_to_video`
-- Provider progress callbacks are converted into JSON-safe `abstract.progress` ledger events during `LLM_CALL` execution without persisting Python callback objects.
-
-### Changed
-- Minimum optional AbstractCore dependency floor is now `abstractcore>=2.13.29` (and matching `multimodal`, `mcp-worker`, and hardware-profile cascade extras), aligning Runtime with Core video endpoints, video residency tasks, and AbstractVision 0.3.16 progress-capable generation.
-- Runtime docs and AI-readable `llms.txt` / `llms-full.txt` now document text-to-video, image-to-video, and generated-media progress events.