thwip-cli 1.1.2__tar.gz → 1.2.0__tar.gz

{thwip_cli-1.1.2 → thwip_cli-1.2.0}/.github/workflows/publish.yml

@@ -4,17 +4,16 @@ on:
   push:
     tags:
       - 'v*'
-  workflow_dispatch:
 
 jobs:
   test:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
 
       - name: Install uv
-        uses: astral-sh/setup-uv@v5
+        uses: astral-sh/setup-uv@c771a70e6277c0a99b617c7a806ffedaca235ff9 # v9.0.0
 
       - name: Set up Python
         run: uv python install 3.13
@@ -33,14 +32,25 @@ jobs:
 
     steps:
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
 
       - name: Install uv
-        uses: astral-sh/setup-uv@v5
+        uses: astral-sh/setup-uv@c771a70e6277c0a99b617c7a806ffedaca235ff9 # v9.0.0
+
+      - name: Verify tag matches package version
+        run: |
+          PACKAGE_VERSION=$(uv run python -c "import tomllib; print(tomllib.load(open('pyproject.toml', 'rb'))['project']['version'])")
+          test "${GITHUB_REF_NAME}" = "v${PACKAGE_VERSION}" || {
+            echo "Tag ${GITHUB_REF_NAME} does not match package version v${PACKAGE_VERSION}."
+            exit 1
+          }
 
       - name: Build package
         run: uv build
 
+      - name: Verify package metadata
+        run: uvx twine check dist/*.whl dist/*.tar.gz
+
       - name: Publish to PyPI
         uses: pypa/gh-action-pypi-publish@release/v1
         with:
@@ -50,5 +60,7 @@ jobs:
         uses: softprops/action-gh-release@v2
         if: startsWith(github.ref, 'refs/tags/')
         with:
-          files: dist/*
+          files: |
+            dist/*.whl
+            dist/*.tar.gz
           generate_release_notes: true

{thwip_cli-1.1.2 → thwip_cli-1.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: thwip-cli
-Version: 1.1.2
+Version: 1.2.0
 Summary: Universal coding agent multiplexer: detect, switch, and route between AI coding agents seamlessly
 Project-URL: Homepage, https://github.com/tanmayhutt/thwip-cli
 Project-URL: Repository, https://github.com/tanmayhutt/thwip-cli
@@ -39,14 +39,15 @@ Description-Content-Type: text/markdown
 
 > Universal Coding Agent Multiplexer
 > 
-> Detect all installed AI coding agents on your device, combine them in a unified terminal interface, and hot-swap models mid-conversation when hitting rate limits without losing context.
+> Discover supported local AI tools, connect configured model providers in one terminal interface, and switch providers while preserving completed text conversation history.
 
 ---
 
 ## Features
 
 - **Auto-Detection**: Discovers installed AI coding agents (Claude Code, Antigravity, Gemini CLI, OpenAI/Codex, Aider, Copilot, Cursor, Windsurf, Cline, Ollama) and configured credentials.
-- **Context Portability**: Switch between Anthropic Claude, Google Gemini, OpenAI Codex, or local Ollama mid-project. Conversation history and working files transfer directly.
+- **Context Portability**: Switch providers with stored conversational text. Working files remain in the selected local project; they are not automatically uploaded.
+- **Handoff Preview**: Inspect text continuity, omitted state, capability changes, approximate context pressure, and a text fingerprint before switching. Runs locally without model calls.
 - **Dynamic UI**: Terminal interface adapts its status bar, capabilities, and theme based on the active provider.
 - **Capability Disclaimers**: Highlights when an agent lacks specific capabilities such as file editing or code execution.
 - **Rate Limit Failover**: Detects HTTP 429 errors or quota exhaustion and prompts instant switching to ready fallback models.
@@ -89,6 +90,7 @@ thwip
 | Command | Action |
 |:---|:---|
 | `/switch [agent] [model]` | Switch active agent or model mid-conversation |
+| `/handoff [agent] [model]` | Preview a target locally without switching or sending data |
 | `/agents` | Show all detected coding agents, company status, and capabilities |
 | `/models [agent]` | List available models for current or target agent |
 | `/key [provider]` | Enter an API key securely without placing it in prompt history |
@@ -111,6 +113,39 @@ Short aliases are available for frequent commands: `/a`, `/m`, `/s`, `/k`, `/g`,
 
 ---
 
+## Auditable handoffs
+
+```text
+/handoff
+/handoff google
+/handoff openai gpt-5.6-terra
+```
+
+`/handoff` previews the current target; specifying a provider uses its default model
+unless you supply a model ID. Targets can be inspected without credentials or an
+installed provider. `/switch` shows the same report before changing the active agent.
+
+The report includes:
+
+- Exact counts of transferred user/assistant text messages and excluded stored records.
+- A count of observed transient tool results that are not in portable history. New
+  sessions track from creation; older saved sessions explicitly report partial coverage.
+- Capability gains and losses using the local model catalog.
+- Approximate request size including tool schemas, with up to 4,096 tokens reserved
+  for an answer in the advisory calculation. This does not change generation settings.
+- SHA-256 of canonical system-prompt and conversational-text JSON. It stays the same
+  across targets when that text is unchanged. Tool schemas and attribution metadata
+  are intentionally outside this text fingerprint.
+
+The preview makes no model requests, saves no transcript exports, executes no tools,
+and does not trim or summarize history. Token sizing uses UTF-8 bytes divided by four
+plus per-message overhead, not a provider tokenizer. Catalog limits can be stale;
+an apparently fitting request can still fail. Warnings are advisory, not switch gates.
+Hidden reasoning and provider-native state do not transfer. The digest proves neither
+delivery nor semantic understanding, and is not a signature or privacy guarantee.
+
+See [research and prior art](docs/handoff-research.md) for the differentiation rationale.
+
 ## Supported Companies and Agents
 
 | Company | Agent | Capabilities |

{thwip_cli-1.1.2 → thwip_cli-1.2.0}/README.md

@@ -2,14 +2,15 @@
 
 > Universal Coding Agent Multiplexer
 > 
-> Detect all installed AI coding agents on your device, combine them in a unified terminal interface, and hot-swap models mid-conversation when hitting rate limits without losing context.
+> Discover supported local AI tools, connect configured model providers in one terminal interface, and switch providers while preserving completed text conversation history.
 
 ---
 
 ## Features
 
 - **Auto-Detection**: Discovers installed AI coding agents (Claude Code, Antigravity, Gemini CLI, OpenAI/Codex, Aider, Copilot, Cursor, Windsurf, Cline, Ollama) and configured credentials.
-- **Context Portability**: Switch between Anthropic Claude, Google Gemini, OpenAI Codex, or local Ollama mid-project. Conversation history and working files transfer directly.
+- **Context Portability**: Switch providers with stored conversational text. Working files remain in the selected local project; they are not automatically uploaded.
+- **Handoff Preview**: Inspect text continuity, omitted state, capability changes, approximate context pressure, and a text fingerprint before switching. Runs locally without model calls.
 - **Dynamic UI**: Terminal interface adapts its status bar, capabilities, and theme based on the active provider.
 - **Capability Disclaimers**: Highlights when an agent lacks specific capabilities such as file editing or code execution.
 - **Rate Limit Failover**: Detects HTTP 429 errors or quota exhaustion and prompts instant switching to ready fallback models.
@@ -52,6 +53,7 @@ thwip
 | Command | Action |
 |:---|:---|
 | `/switch [agent] [model]` | Switch active agent or model mid-conversation |
+| `/handoff [agent] [model]` | Preview a target locally without switching or sending data |
 | `/agents` | Show all detected coding agents, company status, and capabilities |
 | `/models [agent]` | List available models for current or target agent |
 | `/key [provider]` | Enter an API key securely without placing it in prompt history |
@@ -74,6 +76,39 @@ Short aliases are available for frequent commands: `/a`, `/m`, `/s`, `/k`, `/g`,
 
 ---
 
+## Auditable handoffs
+
+```text
+/handoff
+/handoff google
+/handoff openai gpt-5.6-terra
+```
+
+`/handoff` previews the current target; specifying a provider uses its default model
+unless you supply a model ID. Targets can be inspected without credentials or an
+installed provider. `/switch` shows the same report before changing the active agent.
+
+The report includes:
+
+- Exact counts of transferred user/assistant text messages and excluded stored records.
+- A count of observed transient tool results that are not in portable history. New
+  sessions track from creation; older saved sessions explicitly report partial coverage.
+- Capability gains and losses using the local model catalog.
+- Approximate request size including tool schemas, with up to 4,096 tokens reserved
+  for an answer in the advisory calculation. This does not change generation settings.
+- SHA-256 of canonical system-prompt and conversational-text JSON. It stays the same
+  across targets when that text is unchanged. Tool schemas and attribution metadata
+  are intentionally outside this text fingerprint.
+
+The preview makes no model requests, saves no transcript exports, executes no tools,
+and does not trim or summarize history. Token sizing uses UTF-8 bytes divided by four
+plus per-message overhead, not a provider tokenizer. Catalog limits can be stale;
+an apparently fitting request can still fail. Warnings are advisory, not switch gates.
+Hidden reasoning and provider-native state do not transfer. The digest proves neither
+delivery nor semantic understanding, and is not a signature or privacy guarantee.
+
+See [research and prior art](docs/handoff-research.md) for the differentiation rationale.
+
 ## Supported Companies and Agents
 
 | Company | Agent | Capabilities |

thwip_cli-1.2.0/docs/handoff-research.md

@@ -0,0 +1,50 @@
+# Handoff preview: research and scope
+
+Research date: 2026-09-04. This is a bounded public-source comparison, not a patent
+search or proof of worldwide novelty. Search indexes miss unpublished work, private
+products, and features documented under different names. No "world first" claim is made.
+
+## What already exists
+
+| Primary source | Existing approach | Implication for Thwip |
+| --- | --- | --- |
+| [Aider chat modes](https://aider.chat/docs/usage/modes.html) | Architect and editor model pairing | Multi-model collaboration alone is not novel. |
+| [Aider model warnings](https://aider.chat/docs/llms/warnings.html) and [token limits](https://aider.chat/docs/troubleshooting/token-limits.html) | Metadata warnings, token accounting, and overflow guidance | Model-fit diagnostics alone are not novel. |
+| [OpenCode compaction](https://opencode.ai/v2/docs/compaction) | Structured checkpoints plus recent context; durable messages retained separately | Summaries and checkpoints alone are not novel. |
+| [OpenRouter fallbacks](https://openrouter.ai/docs/guides/routing/model-fallbacks) | Ordered fallback models on request failures | Routing and failover alone are not novel. |
+| [OpenRouter message transforms](https://openrouter.ai/docs/guides/features/message-transforms) | Context compression by removing or truncating messages | Automatic fitting can trade away recall. |
+| [Agent Handoff](https://github.com/AniruddhaHumane/handoff) | Portable file-backed resume briefs across agents | Cross-agent memory alone is not novel. |
+| [rosehgal/handoff](https://github.com/rosehgal/handoff) | Append-only action log and rendered handoff document | Tool-action tracking and durable handoffs already exist. |
+
+Searches included combinations of "coding agent", "model switch", "handoff",
+"context loss report", "preflight", "capability loss", "fingerprint", and "receipt",
+as well as product-specific documentation queries. Sources were inspected through
+web search retrieval. No restricted pages or private data were scraped.
+
+## Chosen differentiation
+
+Thwip already owns the provider switch boundary. Put a local continuity report at
+that boundary: exact text-message coverage, explicit state omissions, capability
+differences, advisory context pressure, and a deterministic text fingerprint together.
+The examined sources establish prior art for the components; they did not establish
+the same integrated report. That is an opportunity hypothesis, not proof of uniqueness.
+
+## Implementation boundaries
+
+- `/handoff [provider] [model]` is a non-mutating dry run. `/switch` displays it too.
+- No new dependencies, model calls, summarization costs, or external data storage.
+- Only a result count is added to saved sessions, not raw tool inputs or outputs.
+- Legacy sessions explicitly show incomplete tool-result tracking.
+- SHA-256 covers canonical system prompt and portable text, not provider wire formats,
+  delivery, hidden reasoning, tool schemas, project file contents, or model comprehension.
+- Context estimates are heuristic and warnings advisory. Provider-native tool
+  continuation correctness remains a separate issue, not solved by this report.
+- Production deployment and other defects from the previous audit remain separate work.
+
+## Validation
+
+Offline tests cover stable/change-sensitive fingerprints, exclusions, capability
+gains/losses, context thresholds and unknown limits, unknown targets, private session
+persistence, legacy migration, clear commands, dry-run non-mutation, safe terminal
+rendering, switch integration, and command completion. Live generation is not needed
+to validate this diagnostic, and no claim about live provider success follows from it.

{thwip_cli-1.1.2 → thwip_cli-1.2.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "thwip-cli"
-version = "1.1.2"
+version = "1.2.0"
 description = "Universal coding agent multiplexer: detect, switch, and route between AI coding agents seamlessly"
 readme = "README.md"
 license = "MIT"

{thwip_cli-1.1.2 → thwip_cli-1.2.0}/tests/test_cli.py

@@ -7,7 +7,7 @@ from types import SimpleNamespace
 import pytest
 
 from thwip.agents.base import AgentDone, Capability, TextDelta, ToolUseStart
-from thwip.cli import ThwipCLI
+from thwip.cli import SafeFileHistory, ThwipCLI
 from thwip.session import Session
 from thwip.tools import ToolManager
 
@@ -44,6 +44,10 @@ class ToolCallingAgent:
             yield ToolUseStart(tool_id="read-1", tool_name="read_file", args={"file_path": "note.txt"})
             yield AgentDone()
         else:
+            assert messages[-2]["role"] == "assistant"
+            assert messages[-2]["tool_calls"][0]["id"] == "read-1"
+            assert messages[-1]["role"] == "tool"
+            assert messages[-1]["tool_call_id"] == "read-1"
             assert "known result" in messages[-1]["content"]
             yield TextDelta(content="Used the tool result.")
             yield AgentDone()
@@ -63,6 +67,7 @@ async def test_tool_results_are_returned_to_agent(tmp_path):
 
     assert len(cli.current_agent.calls) == 2
     assert cli.session.messages[-1].content == "Used the tool result."
+    assert cli.session.observed_tool_results == 1
 
 
 class UnconfiguredAgent(ToolCallingAgent):
@@ -94,3 +99,15 @@ def test_inline_api_key_is_rejected():
 
     assert cli.config.keys == {}
     assert cli.config.key_sources == {}
+
+
+def test_inline_api_key_is_not_stored_in_prompt_history(tmp_path):
+    history_path = tmp_path / "history.txt"
+    history = SafeFileHistory(str(history_path))
+
+    history.store_string("/key openai secret-value")
+    history.store_string("/key openai")
+
+    contents = history_path.read_text()
+    assert "secret-value" not in contents
+    assert "/key openai" in contents

thwip_cli-1.2.0/tests/test_config.py

@@ -0,0 +1,21 @@
+"""Regression tests for secure configuration persistence."""
+
+from __future__ import annotations
+
+import tomllib
+
+from thwip.config import ThwipConfig
+
+
+def test_save_does_not_persist_environment_or_discovered_keys(tmp_path, monkeypatch):
+    monkeypatch.setenv("THWIP_CONFIG_DIR", str(tmp_path))
+    config = ThwipConfig(
+        keys={"openai": "from-env", "anthropic": "explicit"},
+        key_sources={"openai": "env:OPENAI_API_KEY", "anthropic": "config.toml"},
+    )
+
+    config.save()
+
+    data = tomllib.loads((tmp_path / "config.toml").read_text())
+    assert data["keys"] == {"anthropic": "explicit"}
+    assert (tmp_path / "config.toml").stat().st_mode & 0o777 == 0o600

thwip_cli-1.2.0/tests/test_handoff.py

@@ -0,0 +1,222 @@
+"""Offline regression coverage for auditable text handoffs."""
+
+import importlib
+import json
+from copy import deepcopy
+from io import StringIO
+from types import SimpleNamespace
+
+import pytest
+from prompt_toolkit.document import Document
+from rich.console import Console
+
+from thwip.agents.base import Capability, ModelInfo
+from thwip.cli import ThwipCLI
+from thwip.handoff import build_handoff_report
+from thwip.session import Message, Session
+from thwip.shortcuts import ThwipCompleter
+from thwip.tools import ToolManager
+
+
+class OfflineAgent:
+    name = "offline"
+    company = "Test"
+    display_name = "Offline Agent"
+    capabilities = {Capability.CHAT, Capability.FILE_EDIT}
+
+    def __init__(self, window=100_000, tools=True):
+        self.model = ModelInfo(id="test-model", name="Test", context_window=window,
+                               max_output=4096, supports_tools=tools)
+        self.available_models = [self.model]
+
+    def get_model_info(self, model):
+        return self.model if model == self.model.id else None
+
+    def get_default_model(self):
+        return self.model.id
+
+    def get_handoff_models(self):
+        return self.available_models
+
+    def get_capabilities_for_model(self, model):
+        return {Capability.CHAT, Capability.FILE_EDIT} if self.model.supports_tools else {Capability.CHAT}
+
+    def is_installed(self):
+        return True
+
+    def is_configured(self):
+        return False
+
+
+def test_fingerprint_is_stable_and_does_not_mutate_session():
+    session = Session(current_model="test-model")
+    session.add_user_message("Keep Unicode: नमस्ते")
+    session.add_assistant_message("Understood", "offline", "test-model")
+    before = deepcopy(session)
+    agent = OfflineAgent()
+    first = build_handoff_report(session, agent, agent, "test-model")
+    second = build_handoff_report(session, agent, agent, "test-model", [{"name": "read"}])
+    assert first.text_fingerprint == second.text_fingerprint
+    assert second.estimated_input_tokens > first.estimated_input_tokens
+    assert session == before
+    assert first.transferred_messages == 2
+    session.system_prompt += "Changed instruction"
+    assert build_handoff_report(session, agent, agent, "test-model").text_fingerprint != first.text_fingerprint
+
+
+@pytest.mark.parametrize("change", ["text", "order"])
+def test_fingerprint_changes_with_payload(change):
+    session = Session()
+    session.add_user_message("one")
+    session.add_user_message("two")
+    agent = OfflineAgent()
+    initial = build_handoff_report(session, agent, agent, "test-model")
+    if change == "text":
+        session.messages[0].content = "different"
+    else:
+        session.messages.reverse()
+    assert build_handoff_report(session, agent, agent, "test-model").text_fingerprint != initial.text_fingerprint
+
+
+def test_exclusions_and_capability_changes_are_explicit():
+    session = Session(current_model="test-model")
+    session.messages = [Message(role="assistant", content="text", tool_calls=[{"id": "one"}]),
+                        Message(role="tool", content="private result")]
+    session.record_tool_result()
+    source, target = OfflineAgent(), OfflineAgent(tools=False)
+    report = build_handoff_report(session, source, target, "test-model")
+    assert report.transferred_messages == 1
+    assert report.excluded_messages == report.excluded_tool_calls == report.observed_tool_results == 1
+    assert report.lost_capabilities == (Capability.FILE_EDIT.display_name,)
+    assert report.gained_capabilities == ()
+    reverse = build_handoff_report(session, target, source, "test-model")
+    assert reverse.gained_capabilities == report.lost_capabilities
+    assert "private result" not in repr(report)
+
+
+@pytest.mark.parametrize("window,expected", [(0, "unknown"), (100, "likely over budget"),
+                                             (5000, "near limit"), (100000, "below advisory budget")])
+def test_advisory_pressure(window, expected):
+    agent = OfflineAgent(window=window)
+    report = build_handoff_report(Session(), agent, agent, "test-model")
+    assert report.context_pressure == expected
+
+
+def test_unknown_model_is_not_silently_assumed():
+    with pytest.raises(ValueError, match="Unknown model"):
+        build_handoff_report(Session(), OfflineAgent(), OfflineAgent(), "missing")
+
+
+def test_tracking_survives_save_and_legacy_load(tmp_path, monkeypatch):
+    monkeypatch.setenv("THWIP_CONFIG_DIR", str(tmp_path))
+    session = Session(name="tracking")
+    session.record_tool_result()
+    path = session.save()
+    loaded = Session.load("tracking")
+    assert loaded.observed_tool_results == 1
+    assert loaded.tool_tracking_complete
+    assert path.stat().st_mode & 0o777 == 0o600
+    data = json.loads(path.read_text())
+    del data["observed_tool_results"]
+    del data["tool_tracking_complete"]
+    path.write_text(json.dumps(data))
+    legacy = Session.load("tracking")
+    assert not legacy.tool_tracking_complete
+    legacy.record_tool_result()
+    assert legacy.observed_tool_results == 1
+    legacy.clear_context()
+    assert legacy.observed_tool_results == 0
+    assert legacy.tool_tracking_complete
+
+
+@pytest.mark.asyncio
+async def test_cli_preview_is_offline_non_mutating_and_safe_to_render(tmp_path, monkeypatch):
+    agent = OfflineAgent()
+    agent.name = "[red]offline[/red]"
+    cli = ThwipCLI.__new__(ThwipCLI)
+    cli.current_agent = agent
+    cli.registry = SimpleNamespace(get_agent=lambda name: agent if name == "offline" else None)
+    cli.session = Session(current_model="test-model")
+    cli.session.add_user_message("PRIVATE USER TEXT")
+    cli.tool_manager = ToolManager(tmp_path)
+    buffer = StringIO()
+    monkeypatch.setattr("thwip.cli.console", Console(file=buffer, width=140, color_system=None))
+    before = deepcopy(cli.session)
+    await cli.handle_command("/handoff offline test-model")
+    assert cli.session == before
+    assert "PRIVATE USER TEXT" not in buffer.getvalue()
+    assert "[red]offline[/red]" in buffer.getvalue()
+    assert "No model calls" in " ".join(buffer.getvalue().split())
+
+
+@pytest.mark.asyncio
+async def test_switch_previews_before_mutating(tmp_path, monkeypatch):
+    source, target = OfflineAgent(), OfflineAgent(tools=False)
+    cli = ThwipCLI.__new__(ThwipCLI)
+    cli.current_agent = source
+    cli.registry = SimpleNamespace(get_agent=lambda name: target)
+    cli.session = Session(current_model="test-model")
+    cli.tool_manager = ToolManager(tmp_path)
+    calls = []
+
+    def preview(*args):
+        assert cli.current_agent is source
+        calls.append(args)
+
+    monkeypatch.setattr(cli, "cmd_handoff", preview)
+    await cli.cmd_switch("offline", "test-model")
+    assert calls == [("offline", "test-model")]
+    assert cli.current_agent is target
+
+
+@pytest.mark.parametrize("command", ["/clear", "/session clear"])
+@pytest.mark.asyncio
+async def test_clear_commands_reset_tracking(command):
+    cli = ThwipCLI.__new__(ThwipCLI)
+    cli.session = Session(observed_tool_results=2, tool_tracking_complete=False)
+    await cli.handle_command(command)
+    assert cli.session.observed_tool_results == 0
+    assert cli.session.tool_tracking_complete
+
+
+def test_handoff_completion():
+    matches = list(ThwipCompleter(["claude"]).get_completions(Document("/handoff cl"), None))
+    assert [match.text for match in matches] == ["/handoff claude"]
+
+
+def test_ollama_preview_never_discovers_models_over_network(monkeypatch):
+    from thwip.agents.ollama_agent import OllamaAgent
+
+    def forbidden(*args, **kwargs):
+        pytest.fail("Preview must not access the network")
+
+    monkeypatch.setattr("urllib.request.urlopen", forbidden)
+    agent = OllamaAgent(host="https://example.invalid")
+    session = Session(current_agent="ollama", current_model="llama3.3")
+    report = build_handoff_report(session, agent, agent, "llama3.3")
+    assert report.context_pressure == "unknown"
+    assert agent._cached_models is None
+
+
+@pytest.mark.parametrize("module,class_name", [
+    ("claude", "ClaudeAgent"), ("google", "GoogleAgent"), ("openai", "OpenAIAgent"),
+    ("deepseek", "DeepSeekAgent"), ("groq", "GroqAgent"), ("ollama", "OllamaAgent"),
+    ("openrouter", "OpenRouterAgent"),
+])
+def test_every_adapter_supports_offline_catalog_reports(module, class_name, monkeypatch):
+    def forbidden(*args, **kwargs):
+        pytest.fail("Handoff must not discover providers or generate responses")
+
+    adapter = getattr(importlib.import_module(f"thwip.agents.{module}_agent"), class_name)
+    agent = adapter.__new__(adapter)
+    if module == "ollama":
+        agent._cached_models = None
+    monkeypatch.setattr(agent, "chat", forbidden)
+    monkeypatch.setattr(agent, "is_installed", forbidden)
+    monkeypatch.setattr(agent, "is_configured", forbidden)
+    monkeypatch.setattr("urllib.request.urlopen", forbidden)
+    model = agent.get_handoff_models()[0]
+    session = Session(current_agent=agent.name, current_model=model.id)
+    report = build_handoff_report(session, agent, agent, model.id)
+    assert report.lost_capabilities == report.gained_capabilities == ()
+    assert len(report.text_fingerprint) == 64

{thwip_cli-1.1.2 → thwip_cli-1.2.0}/tests/test_tools.py

@@ -6,7 +6,10 @@ from __future__ import annotations
 
 import tempfile
 
+import pytest
+
 from thwip.tools import ToolManager
+from thwip.tools.terminal import TerminalRunner
 
 
 def test_file_editor_operations():
@@ -49,3 +52,21 @@ def test_file_editor_blocks_paths_outside_workspace(tmp_path):
     assert "outside the project workspace" in manager.file_editor.read_file(str(outside))
     assert "outside the project workspace" in manager.file_editor.write_file("../outside.txt", "changed")
     assert outside.read_text() == "private"
+
+
+def test_tool_output_is_bounded(tmp_path):
+    manager = ToolManager(project_path=tmp_path)
+    (tmp_path / "large.txt").write_text("x" * 25_000)
+
+    result = manager.execute_tool("read_file", {"file_path": "large.txt", "max_lines": 1})
+
+    assert len(result) <= 20_100
+    assert "Output truncated" in result
+
+
+@pytest.mark.asyncio
+async def test_async_command_timeout_terminates_process(tmp_path):
+    runner = TerminalRunner(tmp_path)
+    result = await runner.run_command_async("sleep 5", timeout=0.01)
+
+    assert "timed out" in result

{thwip_cli-1.1.2 → thwip_cli-1.2.0}/thwip/__init__.py

@@ -1,4 +1,4 @@
 """thwip: Universal Coding Agent Multiplexer."""
 
-__version__ = "1.1.2"
+__version__ = "1.2.0"
 __app_name__ = "thwip"

{thwip_cli-1.1.2 → thwip_cli-1.2.0}/thwip/agents/base.py

@@ -298,6 +298,10 @@ class BaseAgent(ABC):
                 return m
         return None
 
+    def get_handoff_models(self) -> list[ModelInfo]:
+        """Return local catalog metadata without requesting provider discovery."""
+        return list(self.available_models)
+
     def has_capability(self, cap: Capability) -> bool:
         """Check if this agent supports a capability."""
         return cap in self.capabilities

{thwip_cli-1.1.2 → thwip_cli-1.2.0}/thwip/agents/claude_agent.py

@@ -313,11 +313,37 @@ class ClaudeAgent(BaseAgent):
         if tools:
             stream = False
 
+        # Convert the portable OpenAI-style tool transcript into Anthropic blocks.
+        anthropic_messages: list[dict[str, Any]] = []
+        for message in messages:
+            if message.get("tool_calls"):
+                blocks: list[dict[str, Any]] = []
+                if message.get("content"):
+                    blocks.append({"type": "text", "text": message["content"]})
+                for call in message["tool_calls"]:
+                    function = call["function"]
+                    arguments = function.get("arguments", {})
+                    blocks.append({
+                        "type": "tool_use", "id": call["id"], "name": function["name"],
+                        "input": json.loads(arguments) if isinstance(arguments, str) else arguments,
+                    })
+                anthropic_messages.append({"role": "assistant", "content": blocks})
+            elif message.get("role") == "tool":
+                anthropic_messages.append({
+                    "role": "user",
+                    "content": [{
+                        "type": "tool_result", "tool_use_id": message["tool_call_id"],
+                        "content": message.get("content", ""),
+                    }],
+                })
+            else:
+                anthropic_messages.append(message)
+
         # Build request kwargs
         model_info = self.get_model_info(model)
         kwargs: dict[str, Any] = {
             "model": model,
-            "messages": messages,
+            "messages": anthropic_messages,
             "max_tokens": model_info.max_output if model_info else 16_384,
         }