aiscript 1.0.0__tar.gz → 1.2.0__tar.gz

{aiscript-1.0.0 → aiscript-1.2.0}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: aiscript
-Version: 1.0.0
-Summary: JIT-compile plain-English intents into cached, reviewed shell scripts via an LLM.
+Version: 1.2.0
+Summary: JIT-compile plain-English intents into cached, reviewed shell or Python scripts via an LLM.
 Author: Daniel Illescas Romero
 Author-email: Daniel Illescas Romero <illescas.daniel@protonmail.com>
 License-Expression: MIT
@@ -17,11 +17,14 @@ Description-Content-Type: text/markdown
 [![PyPI version](https://img.shields.io/pypi/v/aiscript)](https://pypi.org/project/aiscript/)
 [![Python versions](https://img.shields.io/pypi/pyversions/aiscript)](https://pypi.org/project/aiscript/)
 
-Describe what you want in plain English and `aiscript` asks an LLM to write a shell script
-(Bash on Linux/macOS, PowerShell on Windows), caches it, and runs it. The next run is instant:
+Describe what you want in plain English and `aiscript` asks an LLM to write a script, caches
+it, and runs it. The model picks the language: your native shell (Bash on Linux/macOS, PowerShell
+on Windows) or Python when that fits better. Python scripts that need third-party packages get
+their own virtual environment. The next run is instant:
 no network, no config. Before anything risky is saved or run, every generated script is checked
 by a built-in static scan and, optionally, by a decision model: [Jev](https://docs.typesafe.ai)
-by TypeSafe AI (hosted) or a local model served by [Ollaya](https://ollaya.dev). Risky scripts
+by TypeSafe AI (hosted), [OpenAI Decisions](https://developers.openai.com/api/docs/guides/decisions),
+or a local model served by [Ollaya](https://ollaya.dev). Risky scripts
 are shown to you and need an explicit `[y/N]` approval.
 
 ## Install
@@ -34,7 +37,19 @@ pipx install aiscript
 pip install aiscript
 ```
 
-Requires Python 3.10+. To work on aiscript itself, see [docs/development.md](docs/development.md).
+Requires Python 3.10+.
+
+To upgrade to the latest version, use the same tool you installed with:
+
+```sh
+uv tool upgrade aiscript
+# or
+pipx upgrade aiscript
+# or
+pip install --upgrade aiscript
+```
+
+Your config, prompts and cached scripts in `~/.config/aiscript/` are kept. To work on aiscript itself, see [docs/development.md](docs/development.md).
 
 ## Quickstart
 
@@ -72,7 +87,7 @@ Every generated script is reviewed **before it is saved**:
 - A **static regex scan** (always on) flags privilege escalation, recursive or system-wide file
   changes, networking/firewall changes and remote code execution (`curl | sh`, `iex`).
 - A **decision model** (`reviewer_provider`) gives a second opinion: **Jev** (hosted; key from
-  <https://console.typesafe.ai/keys>) or **Ollaya** (local and keyless; set
+  <https://console.typesafe.ai/keys>), **OpenAI Decisions** (see below), or **Ollaya** (local and keyless; set
   `reviewer_provider: ollaya`, default model `jevk5:4b` on `localhost:11435`; see
   <https://ollaya.dev>). Comment `reviewer_provider` out to use only the static scan.
 
@@ -87,7 +102,8 @@ a best-effort safety net, not a sandbox: read what you approve. Details: [docs/s
 
 ```yaml
 # aiscript config. Contains API keys: keep it private (chmod 600) and out of git.
-# Keys can also come from the environment: OPENAI_API_KEY, TYPESAFE_API_KEY, <PROVIDER>_API_KEY.
+# Keys can also come from the environment: OPENAI_API_KEY, OPENAI_DECISIONS_API_KEY,
+# TYPESAFE_API_KEY, <PROVIDER>_API_KEY.
 
 # Provider that writes the scripts (override with $AISCRIPT_PROVIDER).
 default_provider: openai
@@ -103,6 +119,13 @@ providers:
     model: "gpt-6-luna"
     # reasoning_effort: low    # none | low | medium | high | xhigh | max (model-dependent)
 
+  # OpenAI Decisions API reviewer provider.
+  # openai_decisions:
+  #   kind: openai
+  #   api: decisions
+  #   api_key: "..."
+  #   model: "gpt-6-luna"
+
   # Jev (TypeSafe AI) safety reviewer. API key: https://console.typesafe.ai/keys
   jev:
     api_key: "..."
@@ -121,6 +144,22 @@ Placeholder keys (`"..."`) are ignored, so if you leave them, the environment va
 All options (provider kinds, `api`, `temperature`, key and model resolution, every environment
 variable, the legacy `secrets.yaml`): [docs/configuration.md](docs/configuration.md).
 
+### OpenAI Decisions reviewer
+
+To use OpenAI Decisions instead of Jev, select `reviewer_provider: openai_decisions` and
+uncomment the corresponding provider block above. Supply its own `api_key`, or export
+`OPENAI_DECISIONS_API_KEY`; this named reviewer does not fall back to `OPENAI_API_KEY`.
+The default model is `gpt-6-luna`, and `model` remains configurable for future models.
+
+Decisions uses the official OpenAI endpoint only. One request checks the same four hazards,
+flagging probabilities **>= 0.5**. Requests use a 30-second transport timeout with zero retries.
+Errors, refusals and malformed answers require the existing risk confirmation; they are refused
+in noninteractive builds. Static findings and dependency warnings always remain effective.
+
+Existing reviewers and cached scripts keep working. To roll back, restore your previous
+`reviewer_provider` before downgrading aiscript. See [configuration](docs/configuration.md#openai-decisions)
+and [safety](docs/safety.md#openai-decisions) for the full contract.
+
 ## Usage
 
 | Command | Action |
@@ -135,17 +174,43 @@ variable, the legacy `secrets.yaml`): [docs/configuration.md](docs/configuration
 
 Command names must match `[A-Za-z0-9][A-Za-z0-9_-]*`.
 
+## Shell or Python
+
+The model is told your OS, architecture, native shell, the Python version it will run under and
+whether [uv](https://docs.astral.sh/uv/) is installed, and chooses the language: the shell for thin
+wrappers around CLI tools and pipelines, Python for parsing JSON/CSV/HTML, data processing, HTTP
+APIs and anything that would be fragile in shell. Say "in python" or "as a shell script" in your
+description to ask for one; the model follows it unless it is clearly a poor fit (and then notes
+why in the script header). `aiscript --list` shows each command's language.
+
+- **Standard-library Python** is saved as `functions/NAME.py` and run with the system `python3`
+  (`py -3` on Windows), or with aiscript's own interpreter if there is none.
+- **Python with dependencies** declares them in an inline
+  [PEP 723](https://peps.python.org/pep-0723/) block. After you approve (any dependency requires a
+  `[y/N]` approval that lists the packages), aiscript creates `functions/NAME/` with `main.py` and
+  a private `.venv`: with uv (`pyproject.toml` + `uv.lock`, `uv sync`) or otherwise with
+  `python -m venv` + `pip install -r requirements.txt`. The script always runs with that venv's
+  interpreter, so later runs are offline. A rebuild with the same dependencies reuses the venv; a
+  failed install keeps the previous version. Without uv, Debian/Ubuntu need `python3-venv`.
+
 ## How it works
 
 ```
 ~/.config/aiscript/          # or $XDG_CONFIG_HOME/aiscript, or $AISCRIPT_HOME
 ├── config.yaml              # providers and keys
 ├── prompts/<name>.txt       # your intent for each command
-└── functions/<name>.sh      # generated, reviewed scripts (.ps1 on Windows)
+└── functions/
+    ├── <name>.sh            # generated, reviewed scripts (.ps1 on Windows)
+    ├── <name>.py            # standard-library Python
+    └── <name>/              # Python with dependencies
+        ├── main.py
+        ├── .venv/
+        └── pyproject.toml + uv.lock  (or requirements.txt)
 ```
 
 The first run of `NAME` saves your description to `prompts/NAME.txt`, asks the LLM for a script,
-reviews it, and stores it in `functions/`. Later runs just execute the cached script. If the
+reviews it, and stores it in `functions/` (only one build per command: switching language
+replaces the old one). Later runs just execute the cached script. If the
 prompt is newer than the script (after `--edit` or a manual change), the script is rebuilt on the
 next run. A `--rebuild` that fails or is rejected keeps the previous script.
 

{aiscript-1.0.0 → aiscript-1.2.0}/README.md

@@ -3,11 +3,14 @@
 [![PyPI version](https://img.shields.io/pypi/v/aiscript)](https://pypi.org/project/aiscript/)
 [![Python versions](https://img.shields.io/pypi/pyversions/aiscript)](https://pypi.org/project/aiscript/)
 
-Describe what you want in plain English and `aiscript` asks an LLM to write a shell script
-(Bash on Linux/macOS, PowerShell on Windows), caches it, and runs it. The next run is instant:
+Describe what you want in plain English and `aiscript` asks an LLM to write a script, caches
+it, and runs it. The model picks the language: your native shell (Bash on Linux/macOS, PowerShell
+on Windows) or Python when that fits better. Python scripts that need third-party packages get
+their own virtual environment. The next run is instant:
 no network, no config. Before anything risky is saved or run, every generated script is checked
 by a built-in static scan and, optionally, by a decision model: [Jev](https://docs.typesafe.ai)
-by TypeSafe AI (hosted) or a local model served by [Ollaya](https://ollaya.dev). Risky scripts
+by TypeSafe AI (hosted), [OpenAI Decisions](https://developers.openai.com/api/docs/guides/decisions),
+or a local model served by [Ollaya](https://ollaya.dev). Risky scripts
 are shown to you and need an explicit `[y/N]` approval.
 
 ## Install
@@ -20,7 +23,19 @@ pipx install aiscript
 pip install aiscript
 ```
 
-Requires Python 3.10+. To work on aiscript itself, see [docs/development.md](docs/development.md).
+Requires Python 3.10+.
+
+To upgrade to the latest version, use the same tool you installed with:
+
+```sh
+uv tool upgrade aiscript
+# or
+pipx upgrade aiscript
+# or
+pip install --upgrade aiscript
+```
+
+Your config, prompts and cached scripts in `~/.config/aiscript/` are kept. To work on aiscript itself, see [docs/development.md](docs/development.md).
 
 ## Quickstart
 
@@ -58,7 +73,7 @@ Every generated script is reviewed **before it is saved**:
 - A **static regex scan** (always on) flags privilege escalation, recursive or system-wide file
   changes, networking/firewall changes and remote code execution (`curl | sh`, `iex`).
 - A **decision model** (`reviewer_provider`) gives a second opinion: **Jev** (hosted; key from
-  <https://console.typesafe.ai/keys>) or **Ollaya** (local and keyless; set
+  <https://console.typesafe.ai/keys>), **OpenAI Decisions** (see below), or **Ollaya** (local and keyless; set
   `reviewer_provider: ollaya`, default model `jevk5:4b` on `localhost:11435`; see
   <https://ollaya.dev>). Comment `reviewer_provider` out to use only the static scan.
 
@@ -73,7 +88,8 @@ a best-effort safety net, not a sandbox: read what you approve. Details: [docs/s
 
 ```yaml
 # aiscript config. Contains API keys: keep it private (chmod 600) and out of git.
-# Keys can also come from the environment: OPENAI_API_KEY, TYPESAFE_API_KEY, <PROVIDER>_API_KEY.
+# Keys can also come from the environment: OPENAI_API_KEY, OPENAI_DECISIONS_API_KEY,
+# TYPESAFE_API_KEY, <PROVIDER>_API_KEY.
 
 # Provider that writes the scripts (override with $AISCRIPT_PROVIDER).
 default_provider: openai
@@ -89,6 +105,13 @@ providers:
     model: "gpt-6-luna"
     # reasoning_effort: low    # none | low | medium | high | xhigh | max (model-dependent)
 
+  # OpenAI Decisions API reviewer provider.
+  # openai_decisions:
+  #   kind: openai
+  #   api: decisions
+  #   api_key: "..."
+  #   model: "gpt-6-luna"
+
   # Jev (TypeSafe AI) safety reviewer. API key: https://console.typesafe.ai/keys
   jev:
     api_key: "..."
@@ -107,6 +130,22 @@ Placeholder keys (`"..."`) are ignored, so if you leave them, the environment va
 All options (provider kinds, `api`, `temperature`, key and model resolution, every environment
 variable, the legacy `secrets.yaml`): [docs/configuration.md](docs/configuration.md).
 
+### OpenAI Decisions reviewer
+
+To use OpenAI Decisions instead of Jev, select `reviewer_provider: openai_decisions` and
+uncomment the corresponding provider block above. Supply its own `api_key`, or export
+`OPENAI_DECISIONS_API_KEY`; this named reviewer does not fall back to `OPENAI_API_KEY`.
+The default model is `gpt-6-luna`, and `model` remains configurable for future models.
+
+Decisions uses the official OpenAI endpoint only. One request checks the same four hazards,
+flagging probabilities **>= 0.5**. Requests use a 30-second transport timeout with zero retries.
+Errors, refusals and malformed answers require the existing risk confirmation; they are refused
+in noninteractive builds. Static findings and dependency warnings always remain effective.
+
+Existing reviewers and cached scripts keep working. To roll back, restore your previous
+`reviewer_provider` before downgrading aiscript. See [configuration](docs/configuration.md#openai-decisions)
+and [safety](docs/safety.md#openai-decisions) for the full contract.
+
 ## Usage
 
 | Command | Action |
@@ -121,17 +160,43 @@ variable, the legacy `secrets.yaml`): [docs/configuration.md](docs/configuration
 
 Command names must match `[A-Za-z0-9][A-Za-z0-9_-]*`.
 
+## Shell or Python
+
+The model is told your OS, architecture, native shell, the Python version it will run under and
+whether [uv](https://docs.astral.sh/uv/) is installed, and chooses the language: the shell for thin
+wrappers around CLI tools and pipelines, Python for parsing JSON/CSV/HTML, data processing, HTTP
+APIs and anything that would be fragile in shell. Say "in python" or "as a shell script" in your
+description to ask for one; the model follows it unless it is clearly a poor fit (and then notes
+why in the script header). `aiscript --list` shows each command's language.
+
+- **Standard-library Python** is saved as `functions/NAME.py` and run with the system `python3`
+  (`py -3` on Windows), or with aiscript's own interpreter if there is none.
+- **Python with dependencies** declares them in an inline
+  [PEP 723](https://peps.python.org/pep-0723/) block. After you approve (any dependency requires a
+  `[y/N]` approval that lists the packages), aiscript creates `functions/NAME/` with `main.py` and
+  a private `.venv`: with uv (`pyproject.toml` + `uv.lock`, `uv sync`) or otherwise with
+  `python -m venv` + `pip install -r requirements.txt`. The script always runs with that venv's
+  interpreter, so later runs are offline. A rebuild with the same dependencies reuses the venv; a
+  failed install keeps the previous version. Without uv, Debian/Ubuntu need `python3-venv`.
+
 ## How it works
 
 ```
 ~/.config/aiscript/          # or $XDG_CONFIG_HOME/aiscript, or $AISCRIPT_HOME
 ├── config.yaml              # providers and keys
 ├── prompts/<name>.txt       # your intent for each command
-└── functions/<name>.sh      # generated, reviewed scripts (.ps1 on Windows)
+└── functions/
+    ├── <name>.sh            # generated, reviewed scripts (.ps1 on Windows)
+    ├── <name>.py            # standard-library Python
+    └── <name>/              # Python with dependencies
+        ├── main.py
+        ├── .venv/
+        └── pyproject.toml + uv.lock  (or requirements.txt)
 ```
 
 The first run of `NAME` saves your description to `prompts/NAME.txt`, asks the LLM for a script,
-reviews it, and stores it in `functions/`. Later runs just execute the cached script. If the
+reviews it, and stores it in `functions/` (only one build per command: switching language
+replaces the old one). Later runs just execute the cached script. If the
 prompt is newer than the script (after `--edit` or a manual change), the script is rebuilt on the
 next run. A `--rebuild` that fails or is rejected keeps the previous script.
 

{aiscript-1.0.0 → aiscript-1.2.0}/pyproject.toml

@@ -1,7 +1,7 @@
 [project]
 name = "aiscript"
-version = "1.0.0"
-description = "JIT-compile plain-English intents into cached, reviewed shell scripts via an LLM."
+version = "1.2.0"
+description = "JIT-compile plain-English intents into cached, reviewed shell or Python scripts via an LLM."
 readme = "README.md"
 license = "MIT"
 license-files = ["LICENSE"]
@@ -33,6 +33,12 @@ dev = [
 [tool.ruff]
 line-length = 100
 target-version = "py310"
+extend-exclude = [
+    ".agents/skills",
+    ".claude/skills",
+    ".cursor/skills",
+    ".codex/skills",
+]
 
 [tool.ruff.lint]
 select = [

{aiscript-1.0.0 → aiscript-1.2.0}/pyproject.toml.orig

@@ -1,7 +1,7 @@
 [project]
 name = "aiscript"
-version = "1.0.0"
-description = "JIT-compile plain-English intents into cached, reviewed shell scripts via an LLM."
+version = "1.2.0"
+description = "JIT-compile plain-English intents into cached, reviewed shell or Python scripts via an LLM."
 readme = "README.md"
 license = "MIT"
 license-files = ["LICENSE"]
@@ -32,6 +32,8 @@ dev = [
 [tool.ruff]
 line-length = 100
 target-version = "py310"
+# Installed skills carry supporting code with their own style conventions.
+extend-exclude = [".agents/skills", ".claude/skills", ".cursor/skills", ".codex/skills"]
 
 [tool.ruff.lint]
 select = ["E", "F", "I", "UP", "B", "ANN"]

{aiscript-1.0.0 → aiscript-1.2.0}/src/aiscript/__init__.py

@@ -1,3 +1,3 @@
 """aiscript: JIT-compile plain-English intents into cached shell scripts."""
 
-__version__ = "1.0.0"
+__version__ = "1.2.0"

{aiscript-1.0.0 → aiscript-1.2.0}/src/aiscript/builder.py

@@ -4,11 +4,12 @@ from __future__ import annotations
 
 import contextlib
 import os
+import shutil
 import sys
 import tempfile
 from pathlib import Path
 
-from aiscript import llm, paths, reviewer
+from aiscript import llm, paths, pysetup, reviewer
 from aiscript.config import Settings
 from aiscript.errors import AiscriptError
 
@@ -44,17 +45,26 @@ def build(name: str, settings: Settings) -> Path:
     print(f"Generating {name!r} with {gen.name}/{gen.model}...", file=sys.stderr)
     script = llm.generate_script(gen, name, intent)
 
-    shell = paths.shell_kind()
-    result = reviewer.review(script, shell, settings.reviewer)
-    if not reviewer.confirm(script, result):
+    result = reviewer.review(script.code, script.language, settings.reviewer, script.dependencies)
+    if not reviewer.confirm(script.code, result):
         raise AiscriptError("Script rejected; nothing saved.")
 
     paths.ensure_dirs()
-    target = paths.function_path(name)
+    if script.dependencies:
+        target = pysetup.install(name, script.code, script.dependencies)
+    else:
+        target = paths.function_target(name, script.language, has_deps=False)
+        _write_file(name, target, script.code)
+    _remove_other_artifacts(name, target)
+    print(f"Saved {target}", file=sys.stderr)
+    return target
+
+
+def _write_file(name: str, target: Path, code: str) -> None:
     fd, tmp_name = tempfile.mkstemp(dir=paths.functions_dir(), prefix=f".{name}.", suffix=".tmp")
     try:
         with os.fdopen(fd, "w", encoding="utf-8", newline="\n") as fh:
-            fh.write(script)
+            fh.write(code)
         if not paths.is_windows():
             os.chmod(tmp_name, 0o755)
         os.replace(tmp_name, target)
@@ -62,5 +72,17 @@ def build(name: str, settings: Settings) -> Path:
         with contextlib.suppress(OSError):
             os.unlink(tmp_name)
         raise
-    print(f"Saved {target}", file=sys.stderr)
-    return target
+
+
+def _remove_other_artifacts(name: str, target: Path) -> None:
+    """Drop builds of ``name`` in another language or layout, so only ``target`` remains."""
+    for path in paths.function_artifacts(name):
+        if path == target or path in target.parents:
+            continue
+        try:
+            if path.is_dir():
+                shutil.rmtree(path)
+            else:
+                path.unlink()
+        except OSError as exc:
+            print(f"aiscript: warning: could not remove old build {path}: {exc}", file=sys.stderr)

{aiscript-1.0.0 → aiscript-1.2.0}/src/aiscript/cli.py

@@ -22,7 +22,7 @@ usage: aiscript NAME [args...]       run a command (created/built on first use)
        aiscript --list               list commands
        aiscript --edit NAME          edit a command's prompt (rebuilds on next run)
        aiscript --rebuild NAME       regenerate a command's script (does not run it)
-       aiscript --remove NAME        delete a command's prompt and script
+       aiscript --remove NAME        delete a command's prompt and script(s)
        aiscript --help | --version
 
 Everything after NAME is passed untouched to the generated script.
@@ -92,12 +92,15 @@ def _rebuild(name: str) -> int:
 
 def _remove(name: str) -> int:
     paths.validate_command_name(name)
-    targets = [p for p in (paths.prompt_path(name), paths.function_path(name)) if p.exists()]
+    targets = [p for p in (paths.prompt_path(name), *paths.function_artifacts(name)) if p.exists()]
     if not targets:
         raise AiscriptError(f"No command named {name!r}.")
     for path in targets:
         try:
-            path.unlink()
+            if path.is_dir():
+                shutil.rmtree(path)
+            else:
+                path.unlink()
         except OSError as exc:
             raise AiscriptError(f"Could not remove {path}: {exc}") from exc
         _err(f"Removed {path}")

{aiscript-1.0.0 → aiscript-1.2.0}/src/aiscript/config.py

@@ -21,7 +21,7 @@ class ProviderConfig:
     base_url: str | None
     model: str
     kind: str = "openai"  # "openai" (OpenAI-compatible) or "jev" (TypeSafe System One; Ollaya too)
-    api: str = "chat"  # for kind "openai": "responses" or "chat" (completions)
+    api: str = "chat"  # for kind "openai": "responses", "chat", or reviewer-only "decisions"
     reasoning_effort: str | None = None  # sent only when set
     temperature: float | None = None  # sent only when set (GPT-6 rejects it unless effort=none)
 
@@ -34,11 +34,12 @@ class Settings:
 
 DEFAULT_PROVIDER = "openai"
 DEFAULT_MODEL = "gpt-6-luna"
+DECISIONS_DEFAULT_MODEL = "gpt-6-luna"
 JEV_DEFAULT_MODEL = "jev-latest"
 OLLAYA_DEFAULT_MODEL = "jevk5:4b"
 OLLAYA_DEFAULT_URL = "http://localhost:11435"
 _KINDS = {"openai", "jev", "ollaya"}
-_APIS = {"responses", "chat"}
+_APIS = {"responses", "chat", "decisions"}
 _OPENAI_HOSTS = {"api.openai.com"}
 _JEV_NAMES = {"jev", "typesafe"}
 _OLLAYA_NAMES = {"ollaya"}
@@ -157,6 +158,50 @@ def _resolve_provider(
             f"Provider '{name}' in {path} has unknown kind '{kind}' "
             "(expected: openai, jev, ollaya)."
         )
+    if (_clean(entry.get("api")) or "").lower() == "decisions":
+        if generator:
+            raise ConfigError(
+                f"Provider '{name}' in {path}: Decisions is only supported as a reviewer. "
+                "Select it with `reviewer_provider` and use another generator."
+            )
+        if kind != "openai":
+            raise ConfigError(f"Provider '{name}' in {path}: Decisions requires kind 'openai'.")
+        for setting in ("temperature", "reasoning_effort"):
+            if setting in entry:
+                raise ConfigError(
+                    f"Provider '{name}' in {path}: {setting} is not supported by Decisions. "
+                    "Remove that setting."
+                )
+
+        official_url = "https://api.openai.com/v1"
+        for alias in ("base_url", "endpoint"):
+            if alias in entry and _clean(entry[alias]) not in (official_url, official_url + "/"):
+                raise ConfigError(
+                    f"Provider '{name}' in {path}: Decisions {alias} must be "
+                    f"{official_url} (an optional trailing slash is accepted)."
+                )
+
+        api_key = None
+        env_name = _env_key_name(name)
+        for candidate in (entry.get("api_key"), os.environ.get(env_name)):
+            cleaned_key = _clean(candidate)
+            if cleaned_key is not None and not cleaned_key.endswith("..."):
+                api_key = cleaned_key
+                break
+        if api_key is None:
+            raise ConfigError(
+                f"No API key for provider '{name}'. Set `api_key` for it in {path} "
+                f"or export {env_name}; Decisions requires a dedicated reviewer credential."
+            )
+        return ProviderConfig(
+            name=name,
+            api_key=api_key,
+            base_url=official_url,
+            model=_clean(entry.get("model")) or DECISIONS_DEFAULT_MODEL,
+            kind="openai",
+            api="decisions",
+        )
+
     # Ollaya speaks the Jev wire protocol: only its defaults differ, so it becomes kind "jev".
     ollaya = kind == "ollaya"
     if ollaya:
@@ -222,7 +267,8 @@ def _resolve_provider(
     )
     if api not in _APIS:
         raise ConfigError(
-            f"Provider '{name}' in {path} has unknown api '{api}' (expected: responses, chat)."
+            f"Provider '{name}' in {path} has unknown api '{api}' "
+            "(expected: responses, chat, decisions)."
         )
     reasoning_effort = _clean(entry.get("reasoning_effort"))
     temperature = entry.get("temperature")

aiscript-1.2.0/src/aiscript/decisions.py

@@ -0,0 +1,48 @@
+"""Domain values and gateway contract for Decisions safety review."""
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+from typing import Literal, Protocol
+
+HazardName = Literal["privilege_escalation", "filesystem", "networking", "remote_code_execution"]
+
+
+@dataclass(frozen=True)
+class ReviewInput:
+    """Script and metadata supplied as untrusted review data."""
+
+    script: str
+    language: str
+    dependencies: tuple[str, ...]
+
+
+@dataclass(frozen=True)
+class HazardQuestion:
+    """Fixed hazard definition shared by reviewer adapters."""
+
+    name: HazardName
+    category: str
+    instructions: str
+    true_criteria: str
+    false_criteria: str
+
+
+@dataclass
+class DecisionsCallError(Exception):
+    """Bounded failure metadata without a provider payload."""
+
+    kind: Literal["client", "connection", "timeout", "http", "unexpected"]
+    status_code: int | None = None
+
+
+class DecisionsGateway(Protocol):
+    """Port returning untrusted decoded response data."""
+
+    def classify(
+        self,
+        *,
+        model: str,
+        review_input: ReviewInput,
+        questions: tuple[HazardQuestion, ...],
+    ) -> object: ...