fable-engine 1.3.6__tar.gz → 1.3.8__tar.gz

{fable_engine-1.3.6/fable_engine.egg-info → fable_engine-1.3.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: fable-engine
-Version: 1.3.6
+Version: 1.3.8
 Summary: Independent deterministic System 2 cognitive engine and mechanical time-lock MCP server
 Author: REX-codebase
 License: MIT License
@@ -133,56 +133,73 @@ red-team swarm for code, and a sealed record of what was verified.
 
 <br/>
 
-### Install
+### One package, two agent environments
+
+Fable ships as one PyPI package. The same package contains the runtime, stdio
+MCP server, and complete Agent Skill. Setup is explicit so installing an MCP
+server never silently activates workspace instructions.
+
+Run setup from the project the agent will work in:
 
 ```bash
-pip install fable-engine
+uvx --from fable-engine==1.3.8 fable-mode setup --yes
 ```
 
-Or install the MCP server in your editor:
+This resolves the pinned package in an isolated uv environment and copies the
+bundled skill to `.agents/skills/fable-mode`. Use `--dry-run` to preview or
+`--target <dir>` for another skill directory. For a persistent install, use:
 
-[![Install MCP server in VS Code](https://img.shields.io/badge/VS_Code-Install_MCP_server-007ACC?logo=visualstudiocode&logoColor=white)](vscode:mcp/install?%7B%22name%22%3A%22fable-engine%22%2C%22command%22%3A%22uvx%22%2C%22args%22%3A%5B%22--from%22%2C%22fable-engine%3D%3D1.3.6%22%2C%22fable-engine%22%5D%7D)
-[![Add to Cursor](https://img.shields.io/badge/Cursor-Add_MCP_server-black)](cursor://anysphere.cursor-deeplink/mcp/install?name=fable-engine&config=eyJjb21tYW5kIjoidXZ4IiwiYXJncyI6WyItLWZyb20iLCJmYWJsZS1lbmdpbmU9PTEuMy4zIiwiZmFibGUtZW5naW5lIl19)
+```bash
+python -m pip install fable-engine
+fable-mode setup --yes
+```
 
-These links configure Fable Engine for AI agents in VS Code Chat or Cursor. They do not install a standalone editor extension. Both use `uvx`, which downloads and runs the pinned PyPI release in an isolated environment.
+Then choose only the invocation that matches the agent environment.
 
-Point your agent at the MCP server manually:
+#### Native MCP client
+
+Run `fable-engine` as the stdio server. For example:
 
 ```jsonc
-// Claude Code: claude mcp add fable-engine -- uvx --from fable-engine==1.3.6 fable-engine
-// Cursor: ~/.cursor/mcp.json
+// Claude Code: claude mcp add fable-engine -- uvx --from fable-engine==1.3.8 fable-engine
+// Cursor or another JSON-configured client:
 {
   "mcpServers": {
     "fable-engine": {
       "command": "uvx",
-      "args": ["--from", "fable-engine==1.3.6", "fable-engine"]
+      "args": ["--from", "fable-engine==1.3.8", "fable-engine"]
     }
   }
 }
 ```
 
-Python 3.10+, zero runtime dependencies. Published on [PyPI as `fable-engine`](https://pypi.org/project/fable-engine/).
+[![Install MCP server in VS Code](https://img.shields.io/badge/VS_Code-Install_MCP_server-007ACC?logo=visualstudiocode&logoColor=white)](vscode:mcp/install?%7B%22name%22%3A%22fable-engine%22%2C%22command%22%3A%22uvx%22%2C%22args%22%3A%5B%22--from%22%2C%22fable-engine%3D%3D1.3.8%22%2C%22fable-engine%22%5D%7D)
 
-<br/>
+#### Shell sandbox with internet, no MCP host
 
-### Optional: the Agent Skill
-
-Installing `fable-engine` gives your agent the MCP tools. It does not install
-or activate the Fable Mode Agent Skill - the prompt-side workflow in
-[`skills/fable-mode`](./skills/fable-mode/SKILL.md). Nothing in the package
-activates those instructions on its own; the skill is always a separate,
-explicit opt-in.
-
-The complete skill tree ships inside the wheel. To install it into your
-project's skills directory (the cross-client `.agents/skills/` convention):
+The same package exposes a direct JSON transport. Pipe one `fable_session`
+argument object to `fable-mode call`:
 
 ```bash
-uvx --from fable-engine==1.3.6 fable-mode install-skill --yes
+printf '%s\n' '{"action":"create_session","session_name":"demo","objective":"Verify this change","time_budget_minutes":2}' \
+  | uvx --from fable-engine==1.3.8 fable-mode call
 ```
 
-This copies the skill to `.agents/skills/fable-mode`. Preview first with
-`--dry-run`, choose another location with `--target <dir>`, and reload your
-agent afterwards so it picks up the skill.
+The command uses JSON Lines: one `fable_session` argument object per input line
+and one JSON result per output line. Keep that process open for a full workflow so
+the authority timer and session stay in the same trusted runtime. A one-line pipe
+is useful for a single inspection call. Each uvx command can resolve an
+isolated environment; `pip install` is better when the sandbox keeps a Python
+environment between calls. Session data persists outside that environment in
+Fable's data directory (`FABLE_DATA_DIR` can override it).
+
+Python 3.10+, zero runtime dependencies. Published on [PyPI as `fable-engine`](https://pypi.org/project/fable-engine/).
+
+#### Skill activation remains explicit
+
+`setup` is the unified path. The older `install-skill` command remains as a
+compatible alias for skill-only installation. Neither `fable-engine` nor
+`pip install fable-engine` writes instructions into a workspace on its own.
 
 <br/>
 

{fable_engine-1.3.6 → fable_engine-1.3.8}/README.md

@@ -90,56 +90,73 @@ red-team swarm for code, and a sealed record of what was verified.
 
 <br/>
 
-### Install
+### One package, two agent environments
+
+Fable ships as one PyPI package. The same package contains the runtime, stdio
+MCP server, and complete Agent Skill. Setup is explicit so installing an MCP
+server never silently activates workspace instructions.
+
+Run setup from the project the agent will work in:
 
 ```bash
-pip install fable-engine
+uvx --from fable-engine==1.3.8 fable-mode setup --yes
 ```
 
-Or install the MCP server in your editor:
+This resolves the pinned package in an isolated uv environment and copies the
+bundled skill to `.agents/skills/fable-mode`. Use `--dry-run` to preview or
+`--target <dir>` for another skill directory. For a persistent install, use:
 
-[![Install MCP server in VS Code](https://img.shields.io/badge/VS_Code-Install_MCP_server-007ACC?logo=visualstudiocode&logoColor=white)](vscode:mcp/install?%7B%22name%22%3A%22fable-engine%22%2C%22command%22%3A%22uvx%22%2C%22args%22%3A%5B%22--from%22%2C%22fable-engine%3D%3D1.3.6%22%2C%22fable-engine%22%5D%7D)
-[![Add to Cursor](https://img.shields.io/badge/Cursor-Add_MCP_server-black)](cursor://anysphere.cursor-deeplink/mcp/install?name=fable-engine&config=eyJjb21tYW5kIjoidXZ4IiwiYXJncyI6WyItLWZyb20iLCJmYWJsZS1lbmdpbmU9PTEuMy4zIiwiZmFibGUtZW5naW5lIl19)
+```bash
+python -m pip install fable-engine
+fable-mode setup --yes
+```
 
-These links configure Fable Engine for AI agents in VS Code Chat or Cursor. They do not install a standalone editor extension. Both use `uvx`, which downloads and runs the pinned PyPI release in an isolated environment.
+Then choose only the invocation that matches the agent environment.
 
-Point your agent at the MCP server manually:
+#### Native MCP client
+
+Run `fable-engine` as the stdio server. For example:
 
 ```jsonc
-// Claude Code: claude mcp add fable-engine -- uvx --from fable-engine==1.3.6 fable-engine
-// Cursor: ~/.cursor/mcp.json
+// Claude Code: claude mcp add fable-engine -- uvx --from fable-engine==1.3.8 fable-engine
+// Cursor or another JSON-configured client:
 {
   "mcpServers": {
     "fable-engine": {
       "command": "uvx",
-      "args": ["--from", "fable-engine==1.3.6", "fable-engine"]
+      "args": ["--from", "fable-engine==1.3.8", "fable-engine"]
     }
   }
 }
 ```
 
-Python 3.10+, zero runtime dependencies. Published on [PyPI as `fable-engine`](https://pypi.org/project/fable-engine/).
+[![Install MCP server in VS Code](https://img.shields.io/badge/VS_Code-Install_MCP_server-007ACC?logo=visualstudiocode&logoColor=white)](vscode:mcp/install?%7B%22name%22%3A%22fable-engine%22%2C%22command%22%3A%22uvx%22%2C%22args%22%3A%5B%22--from%22%2C%22fable-engine%3D%3D1.3.8%22%2C%22fable-engine%22%5D%7D)
 
-<br/>
+#### Shell sandbox with internet, no MCP host
 
-### Optional: the Agent Skill
-
-Installing `fable-engine` gives your agent the MCP tools. It does not install
-or activate the Fable Mode Agent Skill - the prompt-side workflow in
-[`skills/fable-mode`](./skills/fable-mode/SKILL.md). Nothing in the package
-activates those instructions on its own; the skill is always a separate,
-explicit opt-in.
-
-The complete skill tree ships inside the wheel. To install it into your
-project's skills directory (the cross-client `.agents/skills/` convention):
+The same package exposes a direct JSON transport. Pipe one `fable_session`
+argument object to `fable-mode call`:
 
 ```bash
-uvx --from fable-engine==1.3.6 fable-mode install-skill --yes
+printf '%s\n' '{"action":"create_session","session_name":"demo","objective":"Verify this change","time_budget_minutes":2}' \
+  | uvx --from fable-engine==1.3.8 fable-mode call
 ```
 
-This copies the skill to `.agents/skills/fable-mode`. Preview first with
-`--dry-run`, choose another location with `--target <dir>`, and reload your
-agent afterwards so it picks up the skill.
+The command uses JSON Lines: one `fable_session` argument object per input line
+and one JSON result per output line. Keep that process open for a full workflow so
+the authority timer and session stay in the same trusted runtime. A one-line pipe
+is useful for a single inspection call. Each uvx command can resolve an
+isolated environment; `pip install` is better when the sandbox keeps a Python
+environment between calls. Session data persists outside that environment in
+Fable's data directory (`FABLE_DATA_DIR` can override it).
+
+Python 3.10+, zero runtime dependencies. Published on [PyPI as `fable-engine`](https://pypi.org/project/fable-engine/).
+
+#### Skill activation remains explicit
+
+`setup` is the unified path. The older `install-skill` command remains as a
+compatible alias for skill-only installation. Neither `fable-engine` nor
+`pip install fable-engine` writes instructions into a workspace on its own.
 
 <br/>
 

{fable_engine-1.3.6 → fable_engine-1.3.8}/docs/stop-ai-agents-writing-too-early.md

@@ -2,27 +2,45 @@
 
 AI coding agents often move from a plausible plan to editing files before they have gathered enough evidence. Fable Mode adds a mechanical session gate: the agent can inspect and reason, but the Fable Engine will not report write permission until the configured authority timer and proof prerequisites pass.
 
-Fable Mode is two separate pieces:
+Fable Mode ships as one package with three parts:
 
-- **Fable Engine** is the MCP server that stores session state and enforces its gates.
-- **The Fable Mode Agent Skill** is the optional workflow that tells a compatible agent how to use those gates.
+- **Fable Engine** is the stdio MCP server that stores session state and enforces its gates.
+- **The Fable Mode Agent Skill** is the bundled workflow for compatible agents.
+- **The shell transport** calls the same `fable_session` API when an agent has a shell and internet but no MCP host.
 
-Installing one does not silently activate the other.
+The package is unified; activation stays explicit. Installing or launching the
+server does not silently write Agent Skill instructions into a project.
 
-## Install the engine
+## Set up from one package
 
-You need Python 3.10+ and [uv](https://docs.astral.sh/uv/getting-started/installation/).
+You need Python 3.10+ and either [uv](https://docs.astral.sh/uv/getting-started/installation/) or pip.
 
-Run the pinned release without changing your global Python environment:
+From the project the agent will work in:
 
 ```bash
-uvx --from fable-engine==1.3.6 fable-engine
+uvx --from fable-engine==1.3.8 fable-mode setup --dry-run
+uvx --from fable-engine==1.3.8 fable-mode setup --yes
 ```
 
+`setup` copies the complete bundled skill to `.agents/skills/fable-mode`. Use
+`--target <dir>` for another skill directory. The installer refuses to
+overwrite local edits unless you pass `--force`.
+
+For a persistent environment, install the same package once:
+
+```bash
+python -m pip install fable-engine
+fable-mode setup --yes
+```
+
+## Route A: an agent with native MCP access
+
+Run `fable-engine` as its stdio MCP server.
+
 ### Claude Code
 
 ```bash
-claude mcp add fable-engine -- uvx --from fable-engine==1.3.6 fable-engine
+claude mcp add fable-engine -- uvx --from fable-engine==1.3.8 fable-engine
 ```
 
 ### Cursor or another JSON-configured MCP client
@@ -32,26 +50,33 @@ claude mcp add fable-engine -- uvx --from fable-engine==1.3.6 fable-engine
   "mcpServers": {
     "fable-engine": {
       "command": "uvx",
-      "args": ["--from", "fable-engine==1.3.6", "fable-engine"]
+      "args": ["--from", "fable-engine==1.3.8", "fable-engine"]
     }
   }
 }
 ```
 
-Restart or reload the client, then inspect its MCP tools. You should see `fable_session` plus the browser tools exposed by the server.
+Restart or reload the client. Its tool list should include `fable_session`.
 
-## Install the optional Agent Skill
+## Route B: an internet-enabled shell sandbox without MCP access
 
-From the root of the project where you want the skill:
+Pipe one `fable_session` argument object to `fable-mode call`:
 
 ```bash
-uvx --from fable-engine==1.3.6 fable-mode install-skill --dry-run
-uvx --from fable-engine==1.3.6 fable-mode install-skill --yes
+printf '%s\n' '{"action":"create_session","session_name":"parser-refactor","objective":"Refactor the parser without changing its public behavior","time_budget_minutes":2}' \
+  | uvx --from fable-engine==1.3.8 fable-mode call
 ```
 
-The default destination is `.agents/skills/fable-mode`. Use `--target <dir>` for a different skill directory. The installer refuses to overwrite local edits unless you pass `--force`.
+The command uses JSON Lines and passes each object to the same Fable handler used
+by MCP. It prints one machine-readable result per input line. Keep one process
+open for the full Think -> Prove -> Attack -> Write workflow; restarting the
+process intentionally starts a fresh authority clock. Invalid, empty, non-object,
+or over-1-MiB requests fail with a nonzero exit code and write the error to stderr.
 
-Reload the agent after installation.
+For later calls, send the same argument objects shown below. When repeated uvx
+calls are undesirable, use the persistent pip installation and replace the
+command after the pipe with `fable-mode call`. Session files live outside the
+uvx environment; set `FABLE_DATA_DIR` to choose their location.
 
 ## Run a first session
 

{fable_engine-1.3.6 → fable_engine-1.3.8}/fable_engine/scrapers/base.py

@@ -25,7 +25,7 @@ from typing import Any, Dict, List, Optional, Tuple
 
 logger = logging.getLogger("fable-engine.scrapers.base")
 
-USER_AGENT = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36 FableResearch/1.3.6"
+USER_AGENT = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36 FableResearch/1.3.8"
 
 MAX_RETRY_DELAY_SECONDS = 10.0
 

{fable_engine-1.3.6 → fable_engine-1.3.8}/fable_engine/server.py

@@ -237,7 +237,7 @@ def main():
                     },
                     "serverInfo": {
                         "name": "fable-engine",
-                        "version": "1.3.6"
+                        "version": "1.3.8"
                     }
                 }
             })

{fable_engine-1.3.6 → fable_engine-1.3.8}/fable_engine/session.py

@@ -1567,7 +1567,7 @@ class FableSession:
     def to_dict(self) -> Dict[str, Any]:
         """Serializes session to dictionary."""
         return {
-            "version": "1.3.6",
+            "version": "1.3.8",
             "session_name": self.session_name,
             "session_id": self.session_id,
             "objective": self.objective,

{fable_engine-1.3.6 → fable_engine-1.3.8/fable_engine.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: fable-engine
-Version: 1.3.6
+Version: 1.3.8
 Summary: Independent deterministic System 2 cognitive engine and mechanical time-lock MCP server
 Author: REX-codebase
 License: MIT License
@@ -133,56 +133,73 @@ red-team swarm for code, and a sealed record of what was verified.
 
 <br/>
 
-### Install
+### One package, two agent environments
+
+Fable ships as one PyPI package. The same package contains the runtime, stdio
+MCP server, and complete Agent Skill. Setup is explicit so installing an MCP
+server never silently activates workspace instructions.
+
+Run setup from the project the agent will work in:
 
 ```bash
-pip install fable-engine
+uvx --from fable-engine==1.3.8 fable-mode setup --yes
 ```
 
-Or install the MCP server in your editor:
+This resolves the pinned package in an isolated uv environment and copies the
+bundled skill to `.agents/skills/fable-mode`. Use `--dry-run` to preview or
+`--target <dir>` for another skill directory. For a persistent install, use:
 
-[![Install MCP server in VS Code](https://img.shields.io/badge/VS_Code-Install_MCP_server-007ACC?logo=visualstudiocode&logoColor=white)](vscode:mcp/install?%7B%22name%22%3A%22fable-engine%22%2C%22command%22%3A%22uvx%22%2C%22args%22%3A%5B%22--from%22%2C%22fable-engine%3D%3D1.3.6%22%2C%22fable-engine%22%5D%7D)
-[![Add to Cursor](https://img.shields.io/badge/Cursor-Add_MCP_server-black)](cursor://anysphere.cursor-deeplink/mcp/install?name=fable-engine&config=eyJjb21tYW5kIjoidXZ4IiwiYXJncyI6WyItLWZyb20iLCJmYWJsZS1lbmdpbmU9PTEuMy4zIiwiZmFibGUtZW5naW5lIl19)
+```bash
+python -m pip install fable-engine
+fable-mode setup --yes
+```
 
-These links configure Fable Engine for AI agents in VS Code Chat or Cursor. They do not install a standalone editor extension. Both use `uvx`, which downloads and runs the pinned PyPI release in an isolated environment.
+Then choose only the invocation that matches the agent environment.
 
-Point your agent at the MCP server manually:
+#### Native MCP client
+
+Run `fable-engine` as the stdio server. For example:
 
 ```jsonc
-// Claude Code: claude mcp add fable-engine -- uvx --from fable-engine==1.3.6 fable-engine
-// Cursor: ~/.cursor/mcp.json
+// Claude Code: claude mcp add fable-engine -- uvx --from fable-engine==1.3.8 fable-engine
+// Cursor or another JSON-configured client:
 {
   "mcpServers": {
     "fable-engine": {
       "command": "uvx",
-      "args": ["--from", "fable-engine==1.3.6", "fable-engine"]
+      "args": ["--from", "fable-engine==1.3.8", "fable-engine"]
     }
   }
 }
 ```
 
-Python 3.10+, zero runtime dependencies. Published on [PyPI as `fable-engine`](https://pypi.org/project/fable-engine/).
+[![Install MCP server in VS Code](https://img.shields.io/badge/VS_Code-Install_MCP_server-007ACC?logo=visualstudiocode&logoColor=white)](vscode:mcp/install?%7B%22name%22%3A%22fable-engine%22%2C%22command%22%3A%22uvx%22%2C%22args%22%3A%5B%22--from%22%2C%22fable-engine%3D%3D1.3.8%22%2C%22fable-engine%22%5D%7D)
 
-<br/>
+#### Shell sandbox with internet, no MCP host
 
-### Optional: the Agent Skill
-
-Installing `fable-engine` gives your agent the MCP tools. It does not install
-or activate the Fable Mode Agent Skill - the prompt-side workflow in
-[`skills/fable-mode`](./skills/fable-mode/SKILL.md). Nothing in the package
-activates those instructions on its own; the skill is always a separate,
-explicit opt-in.
-
-The complete skill tree ships inside the wheel. To install it into your
-project's skills directory (the cross-client `.agents/skills/` convention):
+The same package exposes a direct JSON transport. Pipe one `fable_session`
+argument object to `fable-mode call`:
 
 ```bash
-uvx --from fable-engine==1.3.6 fable-mode install-skill --yes
+printf '%s\n' '{"action":"create_session","session_name":"demo","objective":"Verify this change","time_budget_minutes":2}' \
+  | uvx --from fable-engine==1.3.8 fable-mode call
 ```
 
-This copies the skill to `.agents/skills/fable-mode`. Preview first with
-`--dry-run`, choose another location with `--target <dir>`, and reload your
-agent afterwards so it picks up the skill.
+The command uses JSON Lines: one `fable_session` argument object per input line
+and one JSON result per output line. Keep that process open for a full workflow so
+the authority timer and session stay in the same trusted runtime. A one-line pipe
+is useful for a single inspection call. Each uvx command can resolve an
+isolated environment; `pip install` is better when the sandbox keeps a Python
+environment between calls. Session data persists outside that environment in
+Fable's data directory (`FABLE_DATA_DIR` can override it).
+
+Python 3.10+, zero runtime dependencies. Published on [PyPI as `fable-engine`](https://pypi.org/project/fable-engine/).
+
+#### Skill activation remains explicit
+
+`setup` is the unified path. The older `install-skill` command remains as a
+compatible alias for skill-only installation. Neither `fable-engine` nor
+`pip install fable-engine` writes instructions into a workspace on its own.
 
 <br/>
 

{fable_engine-1.3.6 → fable_engine-1.3.8}/fable_engine.egg-info/SOURCES.txt

@@ -154,6 +154,7 @@ tests/test_scrapers.py
 tests/test_server_actions.py
 tests/test_server_frontier_actions.py
 tests/test_server_protocol.py
+tests/test_shell_call.py
 tests/test_skill_distribution.py
 tests/test_stealth_browser.py
 tests/test_system3.py

{fable_engine-1.3.6 → fable_engine-1.3.8}/fable_mode/__init__.py

@@ -1,3 +1,3 @@
 """Fable Mode portable runtime and transactional installer."""
 
-__version__ = "1.3.6"
+__version__ = "1.3.8"

{fable_engine-1.3.6 → fable_engine-1.3.8}/fable_mode/launcher.py

@@ -249,10 +249,59 @@ def _is_frozen() -> bool:
     return bool(getattr(sys, "frozen", False) or getattr(sys, "_MEIPASS", None))
 
 
+MAX_SHELL_REQUEST_BYTES = 1 * 1024 * 1024
+
+
+def _shell_call() -> int:
+    """Call fable_session over bounded JSON Lines without an MCP host."""
+    from fable_engine.server import handle_fable_session
+
+    # JSON Lines is a UTF-8 protocol. Session text can contain characters the
+    # platform default encoding (cp1252 on Windows pipes) cannot encode, so
+    # pin both output streams to UTF-8 instead of inheriting the locale.
+    for std in (sys.stdout, sys.stderr):
+        reconfigure = getattr(std, "reconfigure", None)
+        if callable(reconfigure):
+            reconfigure(encoding="utf-8", errors="replace")
+
+    stream = getattr(sys.stdin, "buffer", sys.stdin)
+    handled = 0
+    while True:
+        raw = stream.readline(MAX_SHELL_REQUEST_BYTES + 1)
+        if not raw:
+            break
+        if isinstance(raw, str):
+            raw = raw.encode("utf-8")
+        if len(raw) > MAX_SHELL_REQUEST_BYTES or (len(raw) == MAX_SHELL_REQUEST_BYTES + 1 and not raw.endswith(b"\n")):
+            print("call: request exceeds 1 MiB", file=sys.stderr)
+            return 2
+        if not raw.strip():
+            continue
+        try:
+            request = json.loads(raw.decode("utf-8"))
+            if not isinstance(request, dict):
+                raise ValueError("request must be a JSON object")
+            if not isinstance(request.get("action"), str) or not request["action"]:
+                raise ValueError("request must include a non-empty string action")
+            result = handle_fable_session(request)
+        except (UnicodeDecodeError, json.JSONDecodeError, ValueError, TypeError, OSError) as exc:
+            print(f"call: {exc}", file=sys.stderr)
+            return 2
+        except Exception as exc:
+            print(f"call: {exc}", file=sys.stderr)
+            return 1
+        print(json.dumps({"ok": True, "result": result}, ensure_ascii=False), flush=True)
+        handled += 1
+    if not handled:
+        print("call: expected at least one JSON object on stdin", file=sys.stderr)
+        return 2
+    return 0
+
+
 def _parser() -> argparse.ArgumentParser:
     p = argparse.ArgumentParser(prog="fable-mode")
     p.add_argument("--version", action="version", version=__version__)
-    p.add_argument("mode", nargs="?", choices=("install", "serve", "verify", "version", "uninstall", "install-skill"), default="install")
+    p.add_argument("mode", nargs="?", choices=("install", "serve", "verify", "version", "uninstall", "install-skill", "setup", "call"), default="install")
     p.add_argument("--yes", action="store_true", help="confirm unattended installation")
     p.add_argument("--register-hosts", action="store_true")
     p.add_argument("--aliases", action="store_true", help="also probe legacy cc/antigravity aliases")
@@ -305,7 +354,9 @@ def main(argv: list[str] | None = None) -> int:
         except (OSError, RuntimeError, ValueError) as exc:
             print(f"serve: {exc}", file=sys.stderr)
             return 1
-    if args.mode == "install-skill":
+    if args.mode == "call":
+        return _shell_call()
+    if args.mode in {"install-skill", "setup"}:
         target = (Path(args.target).expanduser() if args.target
                   else Path.cwd() / ".agents" / "skills" / SKILL_NAME)
         if not args.dry_run and not args.yes:
@@ -329,6 +380,9 @@ def main(argv: list[str] | None = None) -> int:
         print(f"{verb} the Fable Mode Agent Skill ({result.planned} files: {changes}) to {result.target}")
         if not result.dry_run:
             print("Restart or reload your agent to pick up the skill.")
+        if args.mode == "setup":
+            print("Native MCP: run `fable-engine` as a stdio server.")
+            print("Shell sandbox: pipe one fable_session argument object to `fable-mode call`.")
         return 0
     installer = Installer(Path(args.install_dir) if args.install_dir else None)
     if args.mode == "verify":

{fable_engine-1.3.6 → fable_engine-1.3.8}/fable_v2/coder_fleet/sandbox_executor.py

@@ -100,7 +100,10 @@ class SandboxedTarget:
             if not ready:
                 raise TimeoutError(f"sandbox worker did not respond within {timeout:.1f}s")
             line = self._proc.stdout.readline()
-        except (ImportError, AttributeError):
+        except (ImportError, AttributeError, OSError):
+            # ImportError/AttributeError: no select module or fileno.
+            # OSError: Windows select() only accepts sockets and raises on
+            # pipe handles (WinError 10038) - use the thread fallback.
             result: Dict[str, Any] = {}
 
             def _reader() -> None:

{fable_engine-1.3.6 → fable_engine-1.3.8}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "fable-engine"
-version = "1.3.6"
+version = "1.3.8"
 description = "Independent deterministic System 2 cognitive engine and mechanical time-lock MCP server"
 readme = "README.md"
 authors = [{ name = "REX-codebase" }]

{fable_engine-1.3.6 → fable_engine-1.3.8}/setup.py

@@ -40,7 +40,7 @@ class build_py(_build_py):
 
 setup(
     name="fable-engine",
-    version="1.3.6",
+    version="1.3.8",
     description="Independent deterministic System 2 cognitive engine and mechanical time-lock MCP server",
     long_description=README,
     long_description_content_type="text/markdown",

fable_engine-1.3.8/tests/test_shell_call.py

@@ -0,0 +1,58 @@
+"""Direct shell transport for agents without native MCP access."""
+import io
+import json
+import sys
+import unittest
+from unittest import mock
+
+from fable_mode.launcher import MAX_SHELL_REQUEST_BYTES, _shell_call
+
+
+class ShellCallTests(unittest.TestCase):
+    def _call(self, payload: bytes):
+        stdin = io.TextIOWrapper(io.BytesIO(payload), encoding="utf-8")
+        stdout, stderr = io.StringIO(), io.StringIO()
+        with mock.patch.object(sys, "stdin", stdin), mock.patch.object(sys, "stdout", stdout), mock.patch.object(sys, "stderr", stderr):
+            status = _shell_call()
+        return status, stdout.getvalue(), stderr.getvalue()
+
+    def test_valid_json_lines_share_one_runtime_and_emit_one_result_each(self):
+        requests = [{"action": "list_sessions"}, {"action": "list_sessions"}]
+        payload = "".join(json.dumps(item) + "\n" for item in requests).encode()
+        with mock.patch("fable_engine.server.handle_fable_session", side_effect=["first", "second"]) as handle:
+            status, stdout, stderr = self._call(payload)
+        self.assertEqual(status, 0)
+        self.assertEqual(stderr, "")
+        self.assertEqual([json.loads(line) for line in stdout.splitlines()],
+                         [{"ok": True, "result": "first"}, {"ok": True, "result": "second"}])
+        self.assertEqual([call.args[0] for call in handle.call_args_list], requests)
+
+    def test_empty_invalid_and_non_object_requests_fail(self):
+        for payload in (b"", b"not json", b"[]", b'{}', b'{"action": ""}'):
+            with self.subTest(payload=payload):
+                status, stdout, stderr = self._call(payload)
+                self.assertEqual(status, 2)
+                self.assertEqual(stdout, "")
+                self.assertTrue(stderr.startswith("call: "))
+
+    def test_oversized_request_is_rejected_before_json_parse(self):
+        status, stdout, stderr = self._call(b"{" + b"x" * MAX_SHELL_REQUEST_BYTES)
+        self.assertEqual(status, 2)
+        self.assertEqual(stdout, "")
+        self.assertIn("exceeds 1 MiB", stderr)
+
+    def test_output_stays_utf8_when_pipe_encoding_is_not(self):
+        # Windows pipes default to cp1252: session text with emoji must still
+        # reach the caller as decodable UTF-8 JSON instead of crashing.
+        buffer = io.BytesIO()
+        narrow_stdout = io.TextIOWrapper(buffer, encoding="cp1252")
+        stdin = io.TextIOWrapper(io.BytesIO(b'{"action": "list_sessions"}\n'), encoding="utf-8")
+        with mock.patch.object(sys, "stdin", stdin), mock.patch.object(sys, "stdout", narrow_stdout), \
+                mock.patch("fable_engine.server.handle_fable_session",
+                           return_value="### \U0001f5c2\ufe0f Available Fable Sessions"):
+            status = _shell_call()
+        narrow_stdout.flush()
+        self.assertEqual(status, 0)
+        payload = json.loads(buffer.getvalue().decode("utf-8"))
+        self.assertTrue(payload["ok"])
+        self.assertIn("\U0001f5c2\ufe0f", payload["result"])