AbstractRuntime 0.7.0__tar.gz → 0.7.2__tar.gz

{abstractruntime-0.7.0 → abstractruntime-0.7.2}/ACKNOWLEDGMENTS.md

@@ -11,7 +11,7 @@ The canonical dependency list lives in `pyproject.toml`.
 - **AbstractMemory** (`>=0.3.0`) — TripleStore models and store contract used by Runtime's `MEMORY_KG_*` effects. Durable/vector backend dependencies such as LanceDB remain selected by hosts.
 
 ## Runtime integrations
-- **abstractcore** (`abstractcore[remote,tools,vision,voice,audio,music]>=2.15.1`) — LLM, tools, media, and capability integration used by the base `abstractruntime` install; the `apple` and `gpu` extras select `abstractcore[all-apple]` / `abstractcore[all-gpu]` at the same floor (declared in `pyproject.toml`, implementation under `src/abstractruntime/integrations/abstractcore/*`, docs: `docs/integrations/abstractcore.md`).
+- **abstractcore** (`abstractcore>=2.19.0`) — LLM, tools, media, and capability integration used by the base `abstractruntime` install (AbstractCore's light install); the `apple` and `gpu` extras select `abstractcore[apple]` / `abstractcore[gpu]` at the same floor (declared in `pyproject.toml`, implementation under `src/abstractruntime/integrations/abstractcore/*`, docs: `docs/integrations/abstractcore.md`).
   - The AbstractCore integration uses **httpx** for remote mode (`src/abstractruntime/integrations/abstractcore/llm_client.py`) and **pydantic** for structured validation (`src/abstractruntime/integrations/abstractcore/effect_handlers.py`). These are provided by AbstractCore’s dependency set.
   - The `tools` extra of AbstractCore backs the base Runtime toolset and the `abstractruntime-mcp-worker` entry point.
 - **RestrictedPython** (`>=7.0`, core install) — sandbox for VisualFlow “Code” nodes and pin expressions (`src/abstractruntime/visualflow_compiler/visual/code_executor.py`).

{abstractruntime-0.7.0 → abstractruntime-0.7.2}/CHANGELOG.md

@@ -7,6 +7,50 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.7.2] - 2026-09-29
+
+### Changed
+
+- **Dependencies follow AbstractCore's three install settings.** The base install requires
+  `abstractcore>=2.19.0` (its light install: remote providers, built-in tools and the MCP worker's
+  web tools, media inputs, and the voice/vision/music plugins), `abstractruntime[apple]` requires
+  `abstractcore[apple]>=2.19.0` and `abstractruntime[gpu]` requires `abstractcore[gpu]>=2.19.0`.
+  What gets installed is unchanged; the deprecated AbstractCore extras (`remote`, `tools`, `voice`,
+  `all-apple`, `all-gpu`, ...) are no longer named.
+- **`openai` may be 2.x (`openai<3.0.0,>=1.109.1`).** The `<2.0.0` cap held vLLM at an old release
+  in the `gpu` setting (newer vLLM needs `openai>=2`), and that release does not start with
+  Transformers 5.
+- **The MCP worker's startup tip names the right install.** When `abstractruntime-mcp-worker` fails
+  to start, its tip says that the web tools come with AbstractCore's light install and suggests
+  `pip install -U abstractcore` to repair it, instead of pointing to the deprecated
+  `abstractcore[tools]` extra.
+
+### Fixed
+
+- **The local STT model catalog lists each engine's own models.** When AbstractVoice's catalog
+  carried no per-provider STT map (for example with no OpenAI key),
+  `GET /api/gateway/audio/transcriptions/models` listed OpenAI's `gpt-4o-transcribe` as a
+  faster-whisper model and reported it as `active_model`. `local_list_stt_models()` now asks each
+  STT provider for its own list (without loading an engine) and takes `active_model` from the active
+  provider's list.
+
+## [0.7.1] - 2026-09-28
+
+### Fixed
+
+- **Images in replayed history stay images.** When the history window drops older turns, it writes a
+  `[#TRUNCATION: ...]` notice at the start of the oldest kept message. If that message held a list of content parts
+  (text plus an image, `[{"type": "text", ...}, {"type": "image_url", ...}]`), the notice turned the whole list into
+  one string, so the model received the image's base64 as text. The notice is now added as one text part and every
+  other part is left exactly as it was. A message that starts with its `<runtime_metadata>` envelope keeps it first.
+  This affects `announce_dropped` and `window_transcript`, and so the gateway's `/runs/start` client-context window and
+  any replay that keeps images. Content of any other type is left untouched and a warning is logged.
+- **An image no longer counts as tens of thousands of tokens in the window.** `estimate_message_tokens` turned a
+  content-part list into a string, so a 150 KB inline image counted about 50,000 tokens and pushed every older turn out
+  of the history window. Text parts now count their text, and each media part (image, audio, file) counts a flat 512
+  tokens (`MEDIA_PART_TOKEN_ESTIMATE`, AbstractCore's per-image fallback). The input-budget trim
+  (`trim_messages_to_max_input_tokens`) uses the same estimate.
+
 ## [0.7.0] - 2026-09-28
 
 Replayed session history is one window: the most recent 50,000 tokens of whole turns, recorded in the run.

{abstractruntime-0.7.0 → abstractruntime-0.7.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: AbstractRuntime
-Version: 0.7.0
+Version: 0.7.2
 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
@@ -20,12 +20,12 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
 Requires-Python: >=3.10
-Requires-Dist: abstractcore[audio,music,remote,tools,vision,voice]>=2.18.0
+Requires-Dist: abstractcore>=2.19.0
 Requires-Dist: abstractmemory>=0.3.0
 Requires-Dist: abstractsemantics>=0.0.5
 Requires-Dist: anyio<5.0.0,>=4.12.1
 Requires-Dist: httpx<1.0.0,>=0.28.1
-Requires-Dist: openai<2.0.0,>=1.109.1
+Requires-Dist: openai<3.0.0,>=1.109.1
 Requires-Dist: pandas<3.0.0,>=1.0.0
 Requires-Dist: pillow<13.0.0,>=10.0.0
 Requires-Dist: pypdf<7.0.0,>=6.0.0
@@ -35,14 +35,14 @@ Requires-Dist: reportlab<5.0.0,>=4.0.0
 Requires-Dist: restrictedpython>=7.0
 Requires-Dist: unstructured[docx,odt,pptx,rtf,xlsx]<0.19.0,>=0.18.32
 Provides-Extra: apple
-Requires-Dist: abstractcore[all-apple]>=2.18.0; extra == 'apple'
+Requires-Dist: abstractcore[apple]>=2.19.0; extra == 'apple'
 Requires-Dist: setuptools<82.0.0,>=80.10.2; extra == 'apple'
 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: gpu
-Requires-Dist: abstractcore[all-gpu]>=2.18.0; extra == 'gpu'
+Requires-Dist: abstractcore[gpu]>=2.19.0; extra == 'gpu'
 Requires-Dist: setuptools<82.0.0,>=77.0.3; extra == 'gpu'
 Provides-Extra: test
 Requires-Dist: pytest>=7.0.0; extra == 'test'
@@ -54,7 +54,7 @@ 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:** 0.7.0 • **Python:** 3.10+
+**Version:** 0.7.2 • **Python:** 3.10+
 
 **Status:** pre-1.0 (API may evolve). For production use, pin versions and follow `CHANGELOG.md`.
 
@@ -82,8 +82,8 @@ Remote-light runtime:
 pip install abstractruntime
 ```
 
-The base install includes AbstractCore 2.18.0 or newer with remote provider,
-tool, vision, voice, audio, and music integration, plus the
+The base install includes AbstractCore 2.19.0 or newer (its light install:
+remote providers, tools, vision, voice, audio, and music integration), plus the
 `abstractruntime-mcp-worker` entry point. It keeps inference remote/light by
 default: local engines such as MLX, vLLM, HuggingFace/Torch, Diffusers, and
 sentence-transformer embeddings are not selected unless you choose a hardware
@@ -146,7 +146,7 @@ state = rt.resume(
 assert state.status.value == "completed"
 ```
 
-## What’s included (v0.7.0)
+## What’s included (v0.7.2)
 
 Kernel (import-light):
 - workflow graphs: `WorkflowSpec` (`src/abstractruntime/core/spec.py`)

{abstractruntime-0.7.0 → abstractruntime-0.7.2}/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:** 0.7.0 • **Python:** 3.10+
+**Version:** 0.7.2 • **Python:** 3.10+
 
 **Status:** pre-1.0 (API may evolve). For production use, pin versions and follow `CHANGELOG.md`.
 
@@ -32,8 +32,8 @@ Remote-light runtime:
 pip install abstractruntime
 ```
 
-The base install includes AbstractCore 2.18.0 or newer with remote provider,
-tool, vision, voice, audio, and music integration, plus the
+The base install includes AbstractCore 2.19.0 or newer (its light install:
+remote providers, tools, vision, voice, audio, and music integration), plus the
 `abstractruntime-mcp-worker` entry point. It keeps inference remote/light by
 default: local engines such as MLX, vLLM, HuggingFace/Torch, Diffusers, and
 sentence-transformer embeddings are not selected unless you choose a hardware
@@ -96,7 +96,7 @@ state = rt.resume(
 assert state.status.value == "completed"
 ```
 
-## What’s included (v0.7.0)
+## What’s included (v0.7.2)
 
 Kernel (import-light):
 - workflow graphs: `WorkflowSpec` (`src/abstractruntime/core/spec.py`)

{abstractruntime-0.7.0 → abstractruntime-0.7.2}/docs/api.md

@@ -252,10 +252,10 @@ Implementation: `src/abstractruntime/session_turns.py`, `src/abstractruntime/ses
 
 - `select_session_turns(run_store, session_id, *, include_occurrences=True, until_ms=None, automation_id=None, through_occurrence=None, include_drafts=False, limit=50)` (package root): a session's turns, oldest first. Turns are parent-less runs except automation controllers, plus automation occurrences (a retried occurrence counts once, as its newest attempt); child runs, runtime-internal runs, legacy scheduled wrappers and draft-test runs are left out
 - `session_chat_messages(run_store=, ledger_store=, artifact_store=, session_id=, max_tokens=HISTORY_REPLAY_MAX_TOKENS, until_ms=None, exclude_run_ids=None, automation_id=None, through_occurrence=None, strict=False)` (package root): the session's completed turns as user/assistant message pairs; in a discussion session the discussion's seed comes first. Returns a `ReplayedHistory` (a list of messages) whose `.report` says what was replayed and dropped. `strict=True` raises `SessionHistoryError` (`reason_code = "history_unavailable"`) instead of returning a partial history. `max_messages`, `max_total_chars` and `max_chars_per_message` (keyword-only, default `None`) are the caps retired in 0.7.0: they are accepted so hosts built against 0.6 (AbstractGateway 0.6.0) still get their history, and ignored. Passing any of them logs one warning and names them in `report["ignored_inputs"]`
-- The history window: `HISTORY_REPLAY_MAX_TOKENS = 50_000` (package root). Replay keeps the most recent turns that fit 50,000 estimated tokens, newest first, as whole messages. There is no message-count cap and no character cap, and no message is ever cut. The fold stops at the first older turn that does not fit, so the window has no gaps. A total of exactly 50,000 tokens fits. One exception: when the newest turn alone is larger than the window, it is kept whole (`oversize_turn_kept: true`), because cutting it would lose content and dropping it would replay nothing. The model can use the rest of its context window; if a turn is too large for the model, the provider reports the error. Tokens are counted with `abstractruntime.memory.token_budget.estimate_message_tokens`. `max_tokens` must be a positive int
+- The history window: `HISTORY_REPLAY_MAX_TOKENS = 50_000` (package root). Replay keeps the most recent turns that fit 50,000 estimated tokens, newest first, as whole messages. There is no message-count cap and no character cap, and no message is ever cut. The fold stops at the first older turn that does not fit, so the window has no gaps. A total of exactly 50,000 tokens fits. One exception: when the newest turn alone is larger than the window, it is kept whole (`oversize_turn_kept: true`), because cutting it would lose content and dropping it would replay nothing. The model can use the rest of its context window; if a turn is too large for the model, the provider reports the error. Tokens are counted with `abstractruntime.memory.token_budget.estimate_message_tokens`: for a content-part list it counts the text parts' text plus `MEDIA_PART_TOKEN_ESTIMATE` (512) for each media part (`MEDIA_PART_TYPES`: image, audio, file), never the part's base64; any other part (a tool result, a thinking block) counts by its text (0.7.1). `max_tokens` must be a positive int
 - `ReplayedHistory.report`: `{policy: "most_recent_whole_turns", max_tokens, token_estimator, replayed_messages, replayed_tokens, dropped_messages, dropped_tokens, dropped_counts_complete, oversize_turn_kept}`. Replay stops reading once the window is full, so in a long session `dropped_counts_complete` is `false` and the dropped counts cover only the turns it read. When turns were dropped, the oldest replayed message starts with a `[#TRUNCATION: N earlier message(s) ... were dropped from replay by the history window ...]` line (ADR-0026). Hosts record the report in the run as `vars._runtime.session_history`
 - `fold_history_window(pairs, *, max_tokens=HISTORY_REPLAY_MAX_TOKENS)` (package root): the window itself, applied to chronological turns (lists of whole messages); returns `(kept, report)`
-- `announce_dropped(messages, report, *, stamp_metadata=True)` (package root): writes the window's `[#TRUNCATION: ...]` notice at the start of the oldest kept message, in place, when `report` says turns were dropped. Use it after your own `fold_history_window` call (for example on client-sent history) so the notice matches session replay. `stamp_metadata=True` also adds `metadata.replay_truncated` and `metadata.history_window` to that message; pass `False` for plain role/content messages. `_announce_dropped` is kept as an alias of the pre-0.7.0 private name
+- `announce_dropped(messages, report, *, stamp_metadata=True)` (package root): writes the window's `[#TRUNCATION: ...]` notice at the start of the oldest kept message, in place, when `report` says turns were dropped. Use it after your own `fold_history_window` call (for example on client-sent history) so the notice matches session replay. `stamp_metadata=True` also adds `metadata.replay_truncated` and `metadata.history_window` to that message; pass `False` for plain role/content messages. When the message's content is a content-part list (`[{"type": "text", ...}, {"type": "image_url", ...}]`), the notice is added as one `{"type": "text"}` part and every other part is left as it is, so images stay images (0.7.1); a stamped head keeps its `<runtime_metadata>` envelope first. Content of any other type is left untouched and a warning is logged. `_announce_dropped` is kept as an alias of the pre-0.7.0 private name
 - `window_transcript(messages, *, max_tokens=HISTORY_REPLAY_MAX_TOKENS, current_turn_start=None)` (package root): the same window over a transcript you already hold (a turn is a user message and the messages after it). `current_turn_start` is the index of the message that opened the turn in progress: from there on everything is one turn, the newest, always kept whole (`oversize_turn_kept` when it alone exceeds the window), whatever user-role messages a loop adds inside it; an index out of range raises `ValueError`. Returns a `ReplayedHistory` of copies with the notice written by `announce_dropped(..., stamp_metadata=False)`. The entity chat driver and the entity visit workflow use it for their prompts. The visit records the report in `vars._runtime.session_history`; the chat driver puts it on `TurnReport.history_window`. On the react visit arm, BRIDGE sets `_runtime.history_window_tokens` (50,000) and `_runtime.history_window_turn_start` (the visitor's message) and the AbstractAgent react loop (0.3.17 or newer) sends `window_transcript(context.messages)` on each call and records the report; the stored transcript stays whole. The report carries `window_applied: true`; with an older AbstractAgent that records no window the turn still completes, a warning is logged and the report is `{"window_applied": false, "reason": "agent_too_old", ...}` (the whole transcript was sent). When the oldest kept message carries a `<runtime_metadata>` envelope, the notice is written after it
 - `session_attribution(run_store, session_id)` (`abstractruntime.core.run_attribution`): `None` or `{"kind": "chat" | "automation" | "occurrence" | "discussion", ...}`; a discussion adds its validated root, automation, occurrence and workspace. Raises `SessionAttributionError` when the lookup cannot be completed
 - `is_draft_lifecycle(run_lifecycle)` (package root): whether a run's lifecycle value marks a draft test run
@@ -277,7 +277,7 @@ from Core route resolution and persisted from `LLM_CALL` results.
 
 ### AbstractCore (LLM + tools)
 
-Requires: `pip install abstractruntime` (AbstractCore 2.18.0 or newer is part of the base install).
+Requires: `pip install abstractruntime` (AbstractCore 2.19.0 or newer is part of the base install).
 
 Implementation: `src/abstractruntime/integrations/abstractcore/*`.
 

{abstractruntime-0.7.0 → abstractruntime-0.7.2}/docs/architecture.md

@@ -1,7 +1,7 @@
 # AbstractRuntime — Architecture
 
-> Updated: 2026-09-28
-> Version: 0.7.0
+> Updated: 2026-09-29
+> Version: 0.7.2
 > 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-0.7.0 → abstractruntime-0.7.2}/docs/troubleshooting.md

@@ -20,7 +20,7 @@ Fix:
 - Install or upgrade the base Runtime package. LLM/tools integration, common
   remote-light multimodal dependencies, and the MCP worker entry point are part
   of the base install.
-- The current AbstractCore integration expects `abstractcore>=2.18.0`.
+- The current AbstractCore integration expects `abstractcore>=2.19.0`.
 
 Verify:
 

{abstractruntime-0.7.0 → abstractruntime-0.7.2}/llms-full.txt

@@ -52,7 +52,7 @@ See llms.txt for the linked index.
 
 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:** 0.7.0 • **Python:** 3.10+
+**Version:** 0.7.2 • **Python:** 3.10+
 
 **Status:** pre-1.0 (API may evolve). For production use, pin versions and follow `CHANGELOG.md`.
 
@@ -80,8 +80,8 @@ Remote-light runtime:
 pip install abstractruntime
 ```
 
-The base install includes AbstractCore 2.18.0 or newer with remote provider,
-tool, vision, voice, audio, and music integration, plus the
+The base install includes AbstractCore 2.19.0 or newer (its light install:
+remote providers, tools, vision, voice, audio, and music integration), plus the
 `abstractruntime-mcp-worker` entry point. It keeps inference remote/light by
 default: local engines such as MLX, vLLM, HuggingFace/Torch, Diffusers, and
 sentence-transformer embeddings are not selected unless you choose a hardware
@@ -144,7 +144,7 @@ state = rt.resume(
 assert state.status.value == "completed"
 ```
 
-## What’s included (v0.7.0)
+## What’s included (v0.7.2)
 
 Kernel (import-light):
 - workflow graphs: `WorkflowSpec` (`src/abstractruntime/core/spec.py`)
@@ -429,8 +429,8 @@ rt = create_local_runtime(provider="ollama", model="qwen3:4b")
 
 # AbstractRuntime — Architecture
 
-> Updated: 2026-09-28
-> Version: 0.7.0
+> Updated: 2026-09-29
+> Version: 0.7.2
 > 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.
@@ -1107,10 +1107,10 @@ Implementation: `src/abstractruntime/session_turns.py`, `src/abstractruntime/ses
 
 - `select_session_turns(run_store, session_id, *, include_occurrences=True, until_ms=None, automation_id=None, through_occurrence=None, include_drafts=False, limit=50)` (package root): a session's turns, oldest first. Turns are parent-less runs except automation controllers, plus automation occurrences (a retried occurrence counts once, as its newest attempt); child runs, runtime-internal runs, legacy scheduled wrappers and draft-test runs are left out
 - `session_chat_messages(run_store=, ledger_store=, artifact_store=, session_id=, max_tokens=HISTORY_REPLAY_MAX_TOKENS, until_ms=None, exclude_run_ids=None, automation_id=None, through_occurrence=None, strict=False)` (package root): the session's completed turns as user/assistant message pairs; in a discussion session the discussion's seed comes first. Returns a `ReplayedHistory` (a list of messages) whose `.report` says what was replayed and dropped. `strict=True` raises `SessionHistoryError` (`reason_code = "history_unavailable"`) instead of returning a partial history. `max_messages`, `max_total_chars` and `max_chars_per_message` (keyword-only, default `None`) are the caps retired in 0.7.0: they are accepted so hosts built against 0.6 (AbstractGateway 0.6.0) still get their history, and ignored. Passing any of them logs one warning and names them in `report["ignored_inputs"]`
-- The history window: `HISTORY_REPLAY_MAX_TOKENS = 50_000` (package root). Replay keeps the most recent turns that fit 50,000 estimated tokens, newest first, as whole messages. There is no message-count cap and no character cap, and no message is ever cut. The fold stops at the first older turn that does not fit, so the window has no gaps. A total of exactly 50,000 tokens fits. One exception: when the newest turn alone is larger than the window, it is kept whole (`oversize_turn_kept: true`), because cutting it would lose content and dropping it would replay nothing. The model can use the rest of its context window; if a turn is too large for the model, the provider reports the error. Tokens are counted with `abstractruntime.memory.token_budget.estimate_message_tokens`. `max_tokens` must be a positive int
+- The history window: `HISTORY_REPLAY_MAX_TOKENS = 50_000` (package root). Replay keeps the most recent turns that fit 50,000 estimated tokens, newest first, as whole messages. There is no message-count cap and no character cap, and no message is ever cut. The fold stops at the first older turn that does not fit, so the window has no gaps. A total of exactly 50,000 tokens fits. One exception: when the newest turn alone is larger than the window, it is kept whole (`oversize_turn_kept: true`), because cutting it would lose content and dropping it would replay nothing. The model can use the rest of its context window; if a turn is too large for the model, the provider reports the error. Tokens are counted with `abstractruntime.memory.token_budget.estimate_message_tokens`: for a content-part list it counts the text parts' text plus `MEDIA_PART_TOKEN_ESTIMATE` (512) for each media part (`MEDIA_PART_TYPES`: image, audio, file), never the part's base64; any other part (a tool result, a thinking block) counts by its text (0.7.1). `max_tokens` must be a positive int
 - `ReplayedHistory.report`: `{policy: "most_recent_whole_turns", max_tokens, token_estimator, replayed_messages, replayed_tokens, dropped_messages, dropped_tokens, dropped_counts_complete, oversize_turn_kept}`. Replay stops reading once the window is full, so in a long session `dropped_counts_complete` is `false` and the dropped counts cover only the turns it read. When turns were dropped, the oldest replayed message starts with a `[#TRUNCATION: N earlier message(s) ... were dropped from replay by the history window ...]` line (ADR-0026). Hosts record the report in the run as `vars._runtime.session_history`
 - `fold_history_window(pairs, *, max_tokens=HISTORY_REPLAY_MAX_TOKENS)` (package root): the window itself, applied to chronological turns (lists of whole messages); returns `(kept, report)`
-- `announce_dropped(messages, report, *, stamp_metadata=True)` (package root): writes the window's `[#TRUNCATION: ...]` notice at the start of the oldest kept message, in place, when `report` says turns were dropped. Use it after your own `fold_history_window` call (for example on client-sent history) so the notice matches session replay. `stamp_metadata=True` also adds `metadata.replay_truncated` and `metadata.history_window` to that message; pass `False` for plain role/content messages. `_announce_dropped` is kept as an alias of the pre-0.7.0 private name
+- `announce_dropped(messages, report, *, stamp_metadata=True)` (package root): writes the window's `[#TRUNCATION: ...]` notice at the start of the oldest kept message, in place, when `report` says turns were dropped. Use it after your own `fold_history_window` call (for example on client-sent history) so the notice matches session replay. `stamp_metadata=True` also adds `metadata.replay_truncated` and `metadata.history_window` to that message; pass `False` for plain role/content messages. When the message's content is a content-part list (`[{"type": "text", ...}, {"type": "image_url", ...}]`), the notice is added as one `{"type": "text"}` part and every other part is left as it is, so images stay images (0.7.1); a stamped head keeps its `<runtime_metadata>` envelope first. Content of any other type is left untouched and a warning is logged. `_announce_dropped` is kept as an alias of the pre-0.7.0 private name
 - `window_transcript(messages, *, max_tokens=HISTORY_REPLAY_MAX_TOKENS, current_turn_start=None)` (package root): the same window over a transcript you already hold (a turn is a user message and the messages after it). `current_turn_start` is the index of the message that opened the turn in progress: from there on everything is one turn, the newest, always kept whole (`oversize_turn_kept` when it alone exceeds the window), whatever user-role messages a loop adds inside it; an index out of range raises `ValueError`. Returns a `ReplayedHistory` of copies with the notice written by `announce_dropped(..., stamp_metadata=False)`. The entity chat driver and the entity visit workflow use it for their prompts. The visit records the report in `vars._runtime.session_history`; the chat driver puts it on `TurnReport.history_window`. On the react visit arm, BRIDGE sets `_runtime.history_window_tokens` (50,000) and `_runtime.history_window_turn_start` (the visitor's message) and the AbstractAgent react loop (0.3.17 or newer) sends `window_transcript(context.messages)` on each call and records the report; the stored transcript stays whole. The report carries `window_applied: true`; with an older AbstractAgent that records no window the turn still completes, a warning is logged and the report is `{"window_applied": false, "reason": "agent_too_old", ...}` (the whole transcript was sent). When the oldest kept message carries a `<runtime_metadata>` envelope, the notice is written after it
 - `session_attribution(run_store, session_id)` (`abstractruntime.core.run_attribution`): `None` or `{"kind": "chat" | "automation" | "occurrence" | "discussion", ...}`; a discussion adds its validated root, automation, occurrence and workspace. Raises `SessionAttributionError` when the lookup cannot be completed
 - `is_draft_lifecycle(run_lifecycle)` (package root): whether a run's lifecycle value marks a draft test run
@@ -1132,7 +1132,7 @@ from Core route resolution and persisted from `LLM_CALL` results.
 
 ### AbstractCore (LLM + tools)
 
-Requires: `pip install abstractruntime` (AbstractCore 2.18.0 or newer is part of the base install).
+Requires: `pip install abstractruntime` (AbstractCore 2.19.0 or newer is part of the base install).
 
 Implementation: `src/abstractruntime/integrations/abstractcore/*`.
 
@@ -1633,7 +1633,7 @@ Fix:
 - Install or upgrade the base Runtime package. LLM/tools integration, common
   remote-light multimodal dependencies, and the MCP worker entry point are part
   of the base install.
-- The current AbstractCore integration expects `abstractcore>=2.18.0`.
+- The current AbstractCore integration expects `abstractcore>=2.19.0`.
 
 Verify:
 
@@ -5266,7 +5266,7 @@ The canonical dependency list lives in `pyproject.toml`.
 - **AbstractMemory** (`>=0.3.0`) — TripleStore models and store contract used by Runtime's `MEMORY_KG_*` effects. Durable/vector backend dependencies such as LanceDB remain selected by hosts.
 
 ## Runtime integrations
-- **abstractcore** (`abstractcore[remote,tools,vision,voice,audio,music]>=2.15.1`) — LLM, tools, media, and capability integration used by the base `abstractruntime` install; the `apple` and `gpu` extras select `abstractcore[all-apple]` / `abstractcore[all-gpu]` at the same floor (declared in `pyproject.toml`, implementation under `src/abstractruntime/integrations/abstractcore/*`, docs: `docs/integrations/abstractcore.md`).
+- **abstractcore** (`abstractcore>=2.19.0`) — LLM, tools, media, and capability integration used by the base `abstractruntime` install (AbstractCore's light install); the `apple` and `gpu` extras select `abstractcore[apple]` / `abstractcore[gpu]` at the same floor (declared in `pyproject.toml`, implementation under `src/abstractruntime/integrations/abstractcore/*`, docs: `docs/integrations/abstractcore.md`).
   - The AbstractCore integration uses **httpx** for remote mode (`src/abstractruntime/integrations/abstractcore/llm_client.py`) and **pydantic** for structured validation (`src/abstractruntime/integrations/abstractcore/effect_handlers.py`). These are provided by AbstractCore’s dependency set.
   - The `tools` extra of AbstractCore backs the base Runtime toolset and the `abstractruntime-mcp-worker` entry point.
 - **RestrictedPython** (`>=7.0`, core install) — sandbox for VisualFlow “Code” nodes and pin expressions (`src/abstractruntime/visualflow_compiler/visual/code_executor.py`).

{abstractruntime-0.7.0 → abstractruntime-0.7.2}/llms.txt

@@ -3,10 +3,10 @@
 > Durable workflow runtime (interrupt → checkpoint → resume) with an append-only execution ledger.
 
 - Python: 3.10+ (see `pyproject.toml`)
-- Version: 0.7.0
+- Version: 0.7.2
 - 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: base `abstractruntime` installs `abstractcore[remote,tools,vision,voice,audio,music]>=2.18.0`
+- Current AbstractCore baseline: base `abstractruntime` requires AbstractCore 2.19.0 or newer with its light install (remote providers, tools and the MCP worker, media routing); `abstractruntime[apple]` and `abstractruntime[gpu]` require AbstractCore's `apple` and `gpu` settings (`pyproject.toml`)
 - Install profiles: base `abstractruntime` is remote-light with MCP, generated media routing, and Runtime-owned permissive PDF read/write nodes; `abstractruntime[apple]` and `abstractruntime[gpu]` add local inferencer stacks.
 - Config boundary: Runtime does not read `ABSTRACTGATEWAY_*`; Gateway-owned config should be translated into explicit Runtime inputs or Runtime-owned env names. Hosts can attach `resolve_provider_endpoint_profile(provider_id)` to the LLM client; Runtime treats it as an optional resolver hook, injects transient provider/base URL/key params for the call, and redacts secret-like params from persisted observability.
 

{abstractruntime-0.7.0 → abstractruntime-0.7.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "AbstractRuntime"
-version = "0.7.0"
+version = "0.7.2"
 description = "AbstractRuntime: a durable graph runner designed to pair with AbstractCore."
 readme = "README.md"
 requires-python = ">=3.10"
@@ -48,10 +48,11 @@ dependencies = [
   # package extras owned by AbstractMemory and selected by hosts such as Gateway.
   "AbstractMemory>=0.3.0",
   # Runtime's base install is the remote-light workflow host: LLM/tool effects,
-  # MCP worker support, and multimodal routing are available without selecting
-  # local inference engines.
-  "abstractcore[remote,tools,vision,voice,audio,music]>=2.18.0",
-  "openai<2.0.0,>=1.109.1",
+  # MCP worker support, and multimodal routing come with AbstractCore's light
+  # install (remote providers, built-in tools, media inputs, voice/vision/music
+  # plugins) without selecting local inference engines.
+  "abstractcore>=2.19.0",
+  "openai<3.0.0,>=1.109.1",
   "httpx<1.0.0,>=0.28.1",
   "anyio<5.0.0,>=4.12.1",
   "Pillow<13.0.0,>=10.0.0",
@@ -67,12 +68,12 @@ dependencies = [
 
 [project.optional-dependencies]
 apple = [
-  "abstractcore[all-apple]>=2.18.0",
+  "abstractcore[apple]>=2.19.0",
   "setuptools<82.0.0,>=80.10.2",
 ]
 
 gpu = [
-  "abstractcore[all-gpu]>=2.18.0",
+  "abstractcore[gpu]>=2.19.0",
   # vLLM 0.9-0.19 caps setuptools below 80; 77.0.3 is still a modern floor.
   "setuptools<82.0.0,>=77.0.3",
 ]

abstractruntime-0.7.2/release-notes.md

@@ -0,0 +1,24 @@
+### Changed
+
+- **Dependencies follow AbstractCore's three install settings.** The base install requires
+  `abstractcore>=2.19.0` (its light install: remote providers, built-in tools and the MCP worker's
+  web tools, media inputs, and the voice/vision/music plugins), `abstractruntime[apple]` requires
+  `abstractcore[apple]>=2.19.0` and `abstractruntime[gpu]` requires `abstractcore[gpu]>=2.19.0`.
+  What gets installed is unchanged; the deprecated AbstractCore extras (`remote`, `tools`, `voice`,
+  `all-apple`, `all-gpu`, ...) are no longer named.
+- **`openai` may be 2.x (`openai<3.0.0,>=1.109.1`).** The `<2.0.0` cap held vLLM at an old release
+  in the `gpu` setting (newer vLLM needs `openai>=2`), and that release does not start with
+  Transformers 5.
+- **The MCP worker's startup tip names the right install.** When `abstractruntime-mcp-worker` fails
+  to start, its tip says that the web tools come with AbstractCore's light install and suggests
+  `pip install -U abstractcore` to repair it, instead of pointing to the deprecated
+  `abstractcore[tools]` extra.
+
+### Fixed
+
+- **The local STT model catalog lists each engine's own models.** When AbstractVoice's catalog
+  carried no per-provider STT map (for example with no OpenAI key),
+  `GET /api/gateway/audio/transcriptions/models` listed OpenAI's `gpt-4o-transcribe` as a
+  faster-whisper model and reported it as `active_model`. `local_list_stt_models()` now asks each
+  STT provider for its own list (without loading an engine) and takes `active_model` from the active
+  provider's list.

{abstractruntime-0.7.0 → abstractruntime-0.7.2}/src/abstractruntime/integrations/abstractcore/discovery_queries.py

@@ -1295,16 +1295,35 @@ def local_list_stt_models(
     )
     active_provider = str(catalog.get("active_stt_provider") or "").strip()
     if cleaned and not models_by_provider and (active_provider or providers):
-        models_by_provider[active_provider or providers[0]] = cleaned
+        # The catalog carried no per-provider STT map (AbstractVoice's light
+        # catalog, e.g. when the default OpenAI engine has no key). The flat
+        # list spans every engine, so attributing it to the active provider
+        # advertised OpenAI's gpt-4o-transcribe as a faster-whisper model and
+        # as the active model (framework backlog 0989). Ask each provider for
+        # its own list instead; that call is engine-free.
+        for provider_id in _dedupe_strings(([active_provider] if active_provider else []) + providers):
+            try:
+                provider_models = voice.list_stt_models(provider=provider_id)
+            except Exception:
+                continue
+            provider_cleaned = _dedupe_strings([str(item) for item in list(provider_models or [])])
+            if provider_cleaned:
+                models_by_provider[provider_id] = provider_cleaned
+    active_provider_value = active_provider or (providers[0] if providers else None)
+    if active_provider_value and models_by_provider:
+        active_provider_models = models_by_provider.get(active_provider_value) or []
+        active_model = active_provider_models[0] if active_provider_models else None
+    else:
+        active_model = cleaned[0] if cleaned else None
     payload = _with_status(
         {
             "models": cleaned,
-            "active_model": cleaned[0] if cleaned else None,
+            "active_model": active_model,
             "providers": providers,
             "available_providers": list(catalog.get("available_stt_providers") or providers)
             if isinstance(catalog.get("available_stt_providers"), list)
             else providers,
-            "active_provider": active_provider or (providers[0] if providers else None),
+            "active_provider": active_provider_value,
             "models_by_provider": models_by_provider,
             "stt_models_by_provider": models_by_provider,
             "provider_models": _provider_models_from_mapping(models_by_provider),

{abstractruntime-0.7.0 → abstractruntime-0.7.2}/src/abstractruntime/integrations/abstractcore/mcp_worker.py

@@ -536,7 +536,8 @@ def main(argv: Optional[Sequence[str]] = None) -> int:
             "Failed to start MCP worker.\n\n"
             f"Error: {e}\n\n"
             "Tips:\n"
-            "- Ensure AbstractCore is installed (and, for web tools, `abstractcore[tools]`).\n"
+            "- Ensure AbstractCore is installed; the web tools are part of its light install "
+            "(repair with `pip install -U abstractcore`).\n"
             "- Choose toolsets explicitly (e.g. `--toolsets files` or `--toolsets files,system`).\n"
         )
         return 1

{abstractruntime-0.7.0 → abstractruntime-0.7.2}/src/abstractruntime/memory/token_budget.py

@@ -10,6 +10,7 @@ budget (ADR-0008) even when the underlying model supports much larger contexts.
 
 from __future__ import annotations
 
+import json
 import logging
 from typing import Any, Dict, Iterable, List, Optional
 
@@ -35,15 +36,50 @@ def estimate_tokens(text: str, *, model: Optional[str] = None) -> int:
         return max(1, int(len(s) / 4))
 
 
+# Flat estimate for one non-text content part (an image, a file) — AbstractCore's
+# own fallback per image (`VLMTokenCalculator` base_tokens). The real cost depends
+# on the model and the image size; what matters here is that it is a bounded
+# per-part cost, not the length of the part's base64 payload.
+MEDIA_PART_TOKEN_ESTIMATE = 512
+# Content-part types that carry media (an image, audio or a file), counted at the flat estimate.
+# Every other part (tool_result, thinking, ...) is counted by its text, never flat.
+MEDIA_PART_TYPES = frozenset({"image_url", "image", "input_image", "input_audio", "audio", "file"})
+
+
 def estimate_message_tokens(message: Dict[str, Any], *, model: Optional[str] = None) -> int:
-    """Estimate tokens for a chat message dict (role+content)."""
+    """Estimate tokens for a chat message dict (role+content).
+
+    A content-part list (OpenAI-style `[{"type": "text", ...}, {"type":
+    "image_url", ...}]`) counts the text of its text parts, plus
+    `MEDIA_PART_TOKEN_ESTIMATE` for each media part (`MEDIA_PART_TYPES`); any
+    other part is counted by its serialized text. Before 0.7.1 the list
+    was stringified, so an inline image counted as its base64 text (~50,000
+    tokens for a 150 KB image) and pushed every older turn out of the window.
+    """
     if not isinstance(message, dict):
         return 0
     role = str(message.get("role") or "").strip()
-    content = "" if message.get("content") is None else str(message.get("content"))
+    raw = message.get("content")
+    media_parts = 0
+    if isinstance(raw, list):
+        texts: List[str] = []
+        for part in raw:
+            if isinstance(part, dict) and isinstance(part.get("text"), str) and "text" in str(part.get("type") or "text"):
+                texts.append(part["text"])
+            elif isinstance(part, str):
+                texts.append(part)
+            elif isinstance(part, dict) and str(part.get("type") or "") in MEDIA_PART_TYPES:
+                media_parts += 1
+            elif isinstance(part, dict) and part.get("type") == "text":
+                continue  # an empty or non-string text part carries nothing
+            else:
+                texts.append(json.dumps(part, ensure_ascii=False, default=str))
+        content = "\n".join(texts)
+    else:
+        content = "" if raw is None else str(raw)
     # Include a small role prefix so token estimation reflects chat formatting overhead.
     text = f"{role}: {content}" if role else content
-    return estimate_tokens(text, model=model)
+    return estimate_tokens(text, model=model) + media_parts * MEDIA_PART_TOKEN_ESTIMATE
 
 
 def trim_messages_to_max_input_tokens(

{abstractruntime-0.7.0 → abstractruntime-0.7.2}/src/abstractruntime/session_history.py

@@ -236,6 +236,23 @@ def announce_dropped(messages: List[Dict[str, Any]], report: Dict[str, Any], *,
     `stamp_metadata=False` leaves the message's keys as they were (plain
     role/content transcripts that go straight to a model client); the notice
     in the content is the same.
+
+    Content shapes (0.7.1):
+    - a string (or empty/None): the notice is a prefix line, after the
+      message's own `<runtime_metadata>` envelope when it has one;
+    - a content-part list (OpenAI-style `[{"type": "text", ...},
+      {"type": "image_url", ...}]`, the shape AbstractCore accepts): the
+      notice is inserted as ONE `{"type": "text"}` part and every other part
+      is kept as is (images byte-identical). Prefixing it to the list used to
+      turn the whole content into a string, so the model read the image's
+      base64 as text. Without an envelope the notice part goes first. With
+      one (it heads the first text part, where the payload boundary looks
+      for it), that part is split: the envelope stays alone in it, the
+      notice part follows, then the part's remaining text as its own text
+      part — joined with newlines, the text reads exactly as the string path;
+    - anything else: the content is left untouched (rewriting an unknown
+      shape could corrupt it) and a warning is logged; with
+      `stamp_metadata=True` the metadata still records the drop.
     """
     if not messages or int(report.get("dropped_messages") or 0) <= 0:
         return
@@ -257,7 +274,19 @@ def announce_dropped(messages: List[Dict[str, Any]], report: Dict[str, Any], *,
     # payload boundary would otherwise stack a second one in front).
     from .turn_grounding import split_head_grounding  # lazy: the grounding helpers load AbstractCore
 
-    envelope, rest = split_head_grounding(head.get("content") or "")
+    content = head.get("content")
+    if isinstance(content, list):
+        head["content"] = _notice_into_parts(content, notice, split_head_grounding)
+        return
+    if content is not None and not isinstance(content, str):
+        logger.warning(
+            "history window: the oldest kept message has %s content; the #TRUNCATION notice "
+            "was not written into it (%s message(s) dropped)",
+            type(content).__name__,
+            report["dropped_messages"],
+        )
+        return
+    envelope, rest = split_head_grounding(content or "")
     if envelope:
         sep = "" if envelope.endswith("\n") else "\n"
         head["content"] = f"{envelope}{sep}{notice}\n{rest.lstrip(chr(10))}"
@@ -265,6 +294,25 @@ def announce_dropped(messages: List[Dict[str, Any]], report: Dict[str, Any], *,
         head["content"] = f"{notice}\n{rest}"
 
 
+def _is_text_part(part: Any) -> bool:
+    return isinstance(part, dict) and str(part.get("type") or "").strip().lower() == "text"
+
+
+def _notice_into_parts(parts: List[Any], notice: str, split_head_grounding: Any) -> List[Any]:
+    """A new part list with the notice as one text part (see `announce_dropped`)."""
+    out = list(parts)
+    notice_part = {"type": "text", "text": notice}
+    first = next((i for i, part in enumerate(out) if _is_text_part(part)), None)
+    if first is not None:
+        envelope, rest = split_head_grounding(out[first].get("text"))
+        if envelope:
+            head_part = {**out[first], "text": envelope.rstrip("\n")}
+            tail = rest.lstrip("\n")
+            replacement = [head_part, notice_part] + ([{**out[first], "text": tail}] if tail else [])
+            return out[:first] + replacement + out[first + 1 :]
+    return [notice_part] + out
+
+
 # The pre-0.7.0 private name, kept for callers that imported it.
 _announce_dropped = announce_dropped
 

{abstractruntime-0.7.0 → abstractruntime-0.7.2}/tests/test_abstractcore_discovery_facade.py

@@ -1478,3 +1478,45 @@ def test_remote_discovery_marks_transport_failures_as_route_unavailable() -> Non
     assert payload["available"] is False
     assert payload["route_available"] is False
     assert payload["error"] == "connection refused"
+
+
+def test_local_stt_catalog_without_provider_map_asks_each_provider(monkeypatch) -> None:
+    """Framework backlog 0989: AbstractVoice's light catalog carries no per-provider STT
+    map; the flat model list spans every engine and was attributed wholesale to the
+    active provider, advertising OpenAI's gpt-4o-transcribe as faster-whisper's model
+    and as the active model."""
+
+    from abstractruntime.integrations.abstractcore import discovery_queries
+
+    per_provider = {
+        None: ["gpt-4o-transcribe", "whisper-1", "tiny", "base", "Qwen/Qwen3-ASR-1.7B"],
+        "faster-whisper": ["tiny", "base"],
+        "transformers-asr": ["Qwen/Qwen3-ASR-1.7B"],
+    }
+
+    class _FakeVoice:
+        def voice_catalog(self, *args: Any, **kwargs: Any) -> Dict[str, Any]:
+            _ = args, kwargs
+            return {
+                "active_stt_provider": "faster-whisper",
+                "stt_providers": ["faster-whisper", "transformers-asr"],
+                "stt_models_by_provider": {},
+            }
+
+        def list_stt_models(self, provider: str | None = None) -> List[str]:
+            return list(per_provider.get(provider, []))
+
+    class _FakeRegistry:
+        voice = _FakeVoice()
+
+    monkeypatch.setattr(discovery_queries, "_runtime_capability_registry", lambda **_kwargs: _FakeRegistry())
+
+    payload = discovery_queries.local_list_stt_models()
+
+    assert payload["active_provider"] == "faster-whisper"
+    assert payload["active_model"] == "tiny"
+    assert payload["stt_models_by_provider"] == {
+        "faster-whisper": ["tiny", "base"],
+        "transformers-asr": ["Qwen/Qwen3-ASR-1.7B"],
+    }
+    assert "gpt-4o-transcribe" not in payload["stt_models_by_provider"]["faster-whisper"]

{abstractruntime-0.7.0 → abstractruntime-0.7.2}/tests/test_discovery_tts_unavailable_reason.py

@@ -14,7 +14,7 @@ import pytest
 
 from abstractruntime.integrations.abstractcore import discovery_queries as dq
 
-# AbstractVoice is a declared dependency (abstractcore[voice] in the base install):
+# AbstractVoice is a declared dependency (through AbstractCore's light install):
 # the first two tests run the real catalog, engine-free, with no key configured.