drydock-cli 3.0.57__tar.gz → 3.0.59__tar.gz

{drydock_cli-3.0.57/drydock_cli.egg-info → drydock_cli-3.0.59}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: drydock-cli
-Version: 3.0.57
+Version: 3.0.59
 Summary: Drydock — a local, provider-agnostic terminal coding agent for local LLMs
 Author: Frank Bobe III
 License-Expression: Apache-2.0

{drydock_cli-3.0.57 → drydock_cli-3.0.59}/drydock/tools/__init__.py

@@ -11,9 +11,40 @@ import difflib
 import glob as _glob
 import signal
 import subprocess
+import threading
 import time
 from pathlib import Path
 
+# Hard ceiling on bytes read from a command's output. communicate() buffers ALL
+# stdout in RAM before we ever truncate for context, so a runaway/infinite-output
+# command (`yes`, `cat /dev/urandom`, a massive build log) could balloon memory
+# to gigabytes within the timeout. We stream with a byte cap and kill the command
+# once it's hit — bounding RAM regardless of how much it tries to produce.
+_MAX_BASH_OUTPUT_BYTES = 256 * 1024  # 256 KB — plenty of context, safe for RAM
+
+
+def _collapse_repeated_lines(text: str, run: int = 20) -> str:
+    """Collapse a run of >= `run` IDENTICAL consecutive lines into one line + a
+    count. Repetitive output (`yes`, a spinning progress log) tokenizes densely —
+    32 KB of "y\\n" is ~24k tokens — so even after byte-capping it can eat a big
+    slice of the context window. Collapsing makes it cheap without losing the
+    signal. Non-repetitive output (a normal build log) is left untouched."""
+    lines = text.split("\n")
+    out: list[str] = []
+    i, n = 0, len(lines)
+    while i < n:
+        j = i
+        while j < n and lines[j] == lines[i]:
+            j += 1
+        count = j - i
+        if count >= run:
+            out.append(lines[i])
+            out.append(f"[... {count - 1} more identical lines collapsed ...]")
+        else:
+            out.extend(lines[i:j])
+        i = j
+    return "\n".join(out)
+
 from drydock.tool_registry import ToolDef, register
 from drydock.guards import (
     conflict_marker_refusal,
@@ -728,30 +759,62 @@ def tool_bash(params: dict, config: dict) -> str:
             text=True, cwd=config.get("cwd"), start_new_session=True,
         )
         config.setdefault("_abort", {})["proc"] = proc
+        # Read output in a daemon thread with a HARD byte cap, so memory can't
+        # balloon on a runaway-output command. The thread stops (and we kill the
+        # process) once the cap is hit; the main loop polls cancel + timeout.
+        chunks: list[str] = []
+        total = [0]
+        capped = threading.Event()
+
+        def _drain():
+            assert proc.stdout is not None
+            while True:
+                block = proc.stdout.read(8192)
+                if not block:
+                    break
+                chunks.append(block)
+                total[0] += len(block)
+                if total[0] >= _MAX_BASH_OUTPUT_BYTES:
+                    capped.set()
+                    break
+
+        reader = threading.Thread(target=_drain, daemon=True)
+        reader.start()
         start = time.monotonic()
-        while True:
-            try:
-                out, _ = proc.communicate(timeout=0.5)
+        while reader.is_alive():
+            reader.join(0.3)
+            if capped.is_set():
+                kill_process_group(proc)  # stop it producing more
                 break
-            except subprocess.TimeoutExpired:
-                if cancel is not None and cancel.is_set():
-                    kill_process_group(proc)
-                    proc.communicate()
-                    return "[stopped by user]"
-                if time.monotonic() - start > timeout:
-                    kill_process_group(proc)
-                    proc.communicate()
-                    bigger = min(timeout * 4, 1800)
-                    msg = (
-                        f"Error: command timed out after {timeout}s. If it is "
-                        f"legitimately slow (a big query, build, download, or "
-                        f"test run), retry with a larger timeout — pass "
-                        f"timeout: {bigger}. Otherwise it may be hung."
-                    )
-                    if _is_network_command(cmd):
-                        msg += _OFFLINE_HINT
-                    return msg
-        output = out or ""
+            if cancel is not None and cancel.is_set():
+                kill_process_group(proc)
+                proc.wait()
+                return "[stopped by user]"
+            if time.monotonic() - start > timeout:
+                kill_process_group(proc)
+                proc.wait()
+                bigger = min(timeout * 4, 1800)
+                msg = (
+                    f"Error: command timed out after {timeout}s. If it is "
+                    f"legitimately slow (a big query, build, download, or "
+                    f"test run), retry with a larger timeout — pass "
+                    f"timeout: {bigger}. Otherwise it may be hung."
+                )
+                if _is_network_command(cmd):
+                    msg += _OFFLINE_HINT
+                return msg
+        proc.wait()
+        # Collapse repetitive runs FIRST (turns 256 KB of "y\n" into ~2 lines),
+        # then note if we hit the byte cap. Bounds both RAM (the cap) and context
+        # tokens (the collapse).
+        output = _collapse_repeated_lines("".join(chunks))
+        if capped.is_set():
+            return (
+                output.rstrip()
+                + f"\n[output truncated at {_MAX_BASH_OUTPUT_BYTES // 1024} KB — "
+                "the command produced more; redirect to a file and inspect it in "
+                "pieces (head/tail/grep) instead of dumping it all]"
+            )
         if proc.returncode != 0:
             output += f"\n[exit code: {proc.returncode}]"
             # Offline environments make downloads fail forever; the model tends

{drydock_cli-3.0.57 → drydock_cli-3.0.59/drydock_cli.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: drydock-cli
-Version: 3.0.57
+Version: 3.0.59
 Summary: Drydock — a local, provider-agnostic terminal coding agent for local LLMs
 Author: Frank Bobe III
 License-Expression: Apache-2.0

{drydock_cli-3.0.57 → drydock_cli-3.0.59}/drydock_cli.egg-info/SOURCES.txt

@@ -34,6 +34,7 @@ drydock_cli.egg-info/requires.txt
 drydock_cli.egg-info/top_level.txt
 tests/test_approval.py
 tests/test_back_command.py
+tests/test_bash_output_bounding.py
 tests/test_bash_process_group.py
 tests/test_bash_safety.py
 tests/test_bash_timeout_network.py

{drydock_cli-3.0.57 → drydock_cli-3.0.59}/pyproject.toml

@@ -7,7 +7,7 @@ build-backend = "setuptools.build_meta"
 # PyPI distribution name is drydock-cli (the established install name, continued
 # from the retired v2 fork); the import package + CLI command stay `drydock`.
 name = "drydock-cli"
-version = "3.0.57"
+version = "3.0.59"
 description = "Drydock — a local, provider-agnostic terminal coding agent for local LLMs"
 readme = "README.md"
 requires-python = ">=3.11"

drydock_cli-3.0.59/tests/test_bash_output_bounding.py

@@ -0,0 +1,49 @@
+"""Critical VRAM/RAM protection (PRD §3.B): tool_bash must bound a command's
+output DURING capture so a runaway/infinite-output command can't balloon memory
+before the context-truncation cap applies."""
+from __future__ import annotations
+
+import time
+
+from drydock.tools import tool_bash, _MAX_BASH_OUTPUT_BYTES
+
+
+def test_infinite_output_is_capped_and_fast(tmp_path):
+    cfg = {"cwd": str(tmp_path)}
+    t0 = time.monotonic()
+    out = tool_bash({"command": "yes"}, cfg)   # infinite stream
+    elapsed = time.monotonic() - t0
+    assert "truncated at" in out                      # capped, not dumped
+    assert len(out) < _MAX_BASH_OUTPUT_BYTES + 500     # bounded memory
+    assert elapsed < 20                                # killed promptly, no hang
+
+
+def test_large_finite_output_is_capped(tmp_path):
+    cfg = {"cwd": str(tmp_path)}
+    # ~1 MB of output → must come back truncated near the cap, not 1 MB.
+    out = tool_bash({"command": "head -c 1000000 /dev/zero | tr '\\0' 'a'"}, cfg)
+    assert len(out) < _MAX_BASH_OUTPUT_BYTES + 500
+
+
+def test_normal_output_untouched(tmp_path):
+    cfg = {"cwd": str(tmp_path)}
+    out = tool_bash({"command": "echo hello world"}, cfg)
+    assert out == "hello world" and "truncated" not in out
+
+
+def test_exit_code_still_reported(tmp_path):
+    cfg = {"cwd": str(tmp_path)}
+    out = tool_bash({"command": "echo oops; exit 3"}, cfg)
+    assert "oops" in out and "exit code: 3" in out
+
+
+def test_repetitive_output_is_collapsed(tmp_path):
+    # PRD "protect context size": a repetitive dump must not eat the window.
+    out = tool_bash({"command": "yes | head -c 2000000"}, {"cwd": str(tmp_path)})
+    assert len(out) < 500                       # ~24k chars before the collapse
+    assert "identical lines collapsed" in out
+
+
+def test_collapse_preserves_distinct_lines(tmp_path):
+    out = tool_bash({"command": "printf 'a\\nb\\nc\\n'"}, {"cwd": str(tmp_path)})
+    assert out == "a\nb\nc"                      # nothing collapsed

{drydock_cli-3.0.57 → drydock_cli-3.0.59}/tests/test_failure_loop.py

@@ -75,3 +75,26 @@ def test_polling_with_changing_result_not_tripped(monkeypatch):
     st = AgentState()
     list(run("go", st, {"model": "m", "cwd": tempfile.mkdtemp()}, "sys"))
     assert any(m.get("content") == "done" for m in st.messages)
+
+
+def test_infinite_distinct_tool_calls_terminate_at_max_turns(monkeypatch):
+    """PRD §3.D: a model that keeps calling tools (DIFFERENT, succeeding calls)
+    and never yields 'Task Complete' must be forcibly stopped at the hard
+    max-iteration ceiling — protecting VRAM/context from an unbounded loop."""
+    calls = {"n": 0}
+
+    def never_done(**kw):
+        calls["n"] += 1
+        # A unique, succeeding command each turn → the identical-repeat valve
+        # never trips, so only the hard max_turns cap can end it.
+        return iter([AssistantTurn(
+            "", [{"id": str(calls["n"]), "name": "Bash",
+                  "input": {"command": f"echo step {calls['n']}"}}], 1, 1)])
+
+    monkeypatch.setattr(agent_mod, "stream", never_done)
+    st = AgentState()
+    import tempfile
+    # Low cap so the test is fast; the real default is 200.
+    list(run("loop forever", st, {"model": "m", "max_turns": 12,
+                                  "cwd": tempfile.mkdtemp()}, "sys"))
+    assert calls["n"] == 12  # ran exactly to the ceiling, then terminated