🚀 Major Enhancement: Workflow-Based Tool Architecture v5.5.0 (#95)
* WIP: new workflow architecture * WIP: further improvements and cleanup * WIP: cleanup and docks, replace old tool with new * WIP: cleanup and docks, replace old tool with new * WIP: new planner implementation using workflow * WIP: precommit tool working as a workflow instead of a basic tool Support for passing False to use_assistant_model to skip external models completely and use Claude only * WIP: precommit workflow version swapped with old * WIP: codereview * WIP: replaced codereview * WIP: replaced codereview * WIP: replaced refactor * WIP: workflow for thinkdeep * WIP: ensure files get embedded correctly * WIP: thinkdeep replaced with workflow version * WIP: improved messaging when an external model's response is received * WIP: analyze tool swapped * WIP: updated tests * Extract only the content when building history * Use "relevant_files" for workflow tools only * WIP: updated tests * Extract only the content when building history * Use "relevant_files" for workflow tools only * WIP: fixed get_completion_next_steps_message missing param * Fixed tests Request for files consistently * Fixed tests Request for files consistently * Fixed tests * New testgen workflow tool Updated docs * Swap testgen workflow * Fix CI test failures by excluding API-dependent tests - Update GitHub Actions workflow to exclude simulation tests that require API keys - Fix collaboration tests to properly mock workflow tool expert analysis calls - Update test assertions to handle new workflow tool response format - Ensure unit tests run without external API dependencies in CI 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com> * WIP - Update tests to match new tools * WIP - Update tests to match new tools --------- Co-authored-by: Claude <noreply@anthropic.com>
This commit is contained in:
Beehive Innovations
committed by
GitHub
GitHub
parent
4dae6e457e
commit
69a3121452
@@ -62,7 +62,7 @@ class CrossToolContinuationTest(ConversationBaseTest):
|
||||
self.logger.info(" 1: Testing chat -> thinkdeep -> codereview")
|
||||
|
||||
# Start with chat
|
||||
chat_response, chat_id = self.call_mcp_tool_direct(
|
||||
chat_response, chat_id = self.call_mcp_tool(
|
||||
"chat",
|
||||
{
|
||||
"prompt": "Please use low thinking mode. Look at this Python code and tell me what you think about it",
|
||||
@@ -76,11 +76,15 @@ class CrossToolContinuationTest(ConversationBaseTest):
|
||||
return False
|
||||
|
||||
# Continue with thinkdeep
|
||||
thinkdeep_response, _ = self.call_mcp_tool_direct(
|
||||
thinkdeep_response, _ = self.call_mcp_tool(
|
||||
"thinkdeep",
|
||||
{
|
||||
"prompt": "Please use low thinking mode. Think deeply about potential performance issues in this code",
|
||||
"files": [self.test_files["python"]], # Same file should be deduplicated
|
||||
"step": "Think deeply about potential performance issues in this code. Please use low thinking mode.",
|
||||
"step_number": 1,
|
||||
"total_steps": 1,
|
||||
"next_step_required": False,
|
||||
"findings": "Building on previous chat analysis to examine performance issues",
|
||||
"relevant_files": [self.test_files["python"]], # Same file should be deduplicated
|
||||
"continuation_id": chat_id,
|
||||
"model": "flash",
|
||||
},
|
||||
@@ -91,11 +95,15 @@ class CrossToolContinuationTest(ConversationBaseTest):
|
||||
return False
|
||||
|
||||
# Continue with codereview
|
||||
codereview_response, _ = self.call_mcp_tool_direct(
|
||||
codereview_response, _ = self.call_mcp_tool(
|
||||
"codereview",
|
||||
{
|
||||
"files": [self.test_files["python"]], # Same file should be deduplicated
|
||||
"prompt": "Building on our previous analysis, provide a comprehensive code review",
|
||||
"step": "Building on our previous analysis, provide a comprehensive code review",
|
||||
"step_number": 1,
|
||||
"total_steps": 1,
|
||||
"next_step_required": False,
|
||||
"findings": "Continuing from previous chat and thinkdeep analysis for comprehensive review",
|
||||
"relevant_files": [self.test_files["python"]], # Same file should be deduplicated
|
||||
"continuation_id": chat_id,
|
||||
"model": "flash",
|
||||
},
|
||||
@@ -118,11 +126,15 @@ class CrossToolContinuationTest(ConversationBaseTest):
|
||||
self.logger.info(" 2: Testing analyze -> debug -> thinkdeep")
|
||||
|
||||
# Start with analyze
|
||||
analyze_response, analyze_id = self.call_mcp_tool_direct(
|
||||
analyze_response, analyze_id = self.call_mcp_tool(
|
||||
"analyze",
|
||||
{
|
||||
"files": [self.test_files["python"]],
|
||||
"prompt": "Analyze this code for quality and performance issues",
|
||||
"step": "Analyze this code for quality and performance issues",
|
||||
"step_number": 1,
|
||||
"total_steps": 1,
|
||||
"next_step_required": False,
|
||||
"findings": "Starting analysis of Python code for quality and performance issues",
|
||||
"relevant_files": [self.test_files["python"]],
|
||||
"model": "flash",
|
||||
},
|
||||
)
|
||||
@@ -132,11 +144,15 @@ class CrossToolContinuationTest(ConversationBaseTest):
|
||||
return False
|
||||
|
||||
# Continue with debug
|
||||
debug_response, _ = self.call_mcp_tool_direct(
|
||||
debug_response, _ = self.call_mcp_tool(
|
||||
"debug",
|
||||
{
|
||||
"files": [self.test_files["python"]], # Same file should be deduplicated
|
||||
"prompt": "Based on our analysis, help debug the performance issue in fibonacci",
|
||||
"step": "Based on our analysis, help debug the performance issue in fibonacci",
|
||||
"step_number": 1,
|
||||
"total_steps": 1,
|
||||
"next_step_required": False,
|
||||
"findings": "Building on previous analysis to debug specific performance issue",
|
||||
"relevant_files": [self.test_files["python"]], # Same file should be deduplicated
|
||||
"continuation_id": analyze_id,
|
||||
"model": "flash",
|
||||
},
|
||||
@@ -147,11 +163,15 @@ class CrossToolContinuationTest(ConversationBaseTest):
|
||||
return False
|
||||
|
||||
# Continue with thinkdeep
|
||||
final_response, _ = self.call_mcp_tool_direct(
|
||||
final_response, _ = self.call_mcp_tool(
|
||||
"thinkdeep",
|
||||
{
|
||||
"prompt": "Please use low thinking mode. Think deeply about the architectural implications of the issues we've found",
|
||||
"files": [self.test_files["python"]], # Same file should be deduplicated
|
||||
"step": "Think deeply about the architectural implications of the issues we've found. Please use low thinking mode.",
|
||||
"step_number": 1,
|
||||
"total_steps": 1,
|
||||
"next_step_required": False,
|
||||
"findings": "Building on analysis and debug findings to explore architectural implications",
|
||||
"relevant_files": [self.test_files["python"]], # Same file should be deduplicated
|
||||
"continuation_id": analyze_id,
|
||||
"model": "flash",
|
||||
},
|
||||
@@ -174,7 +194,7 @@ class CrossToolContinuationTest(ConversationBaseTest):
|
||||
self.logger.info(" 3: Testing multi-file cross-tool continuation")
|
||||
|
||||
# Start with both files
|
||||
multi_response, multi_id = self.call_mcp_tool_direct(
|
||||
multi_response, multi_id = self.call_mcp_tool(
|
||||
"chat",
|
||||
{
|
||||
"prompt": "Please use low thinking mode. Analyze both the Python code and configuration file",
|
||||
@@ -188,11 +208,15 @@ class CrossToolContinuationTest(ConversationBaseTest):
|
||||
return False
|
||||
|
||||
# Switch to codereview with same files (should use conversation history)
|
||||
multi_review, _ = self.call_mcp_tool_direct(
|
||||
multi_review, _ = self.call_mcp_tool(
|
||||
"codereview",
|
||||
{
|
||||
"files": [self.test_files["python"], self.test_files["config"]], # Same files
|
||||
"prompt": "Review both files in the context of our previous discussion",
|
||||
"step": "Review both files in the context of our previous discussion",
|
||||
"step_number": 1,
|
||||
"total_steps": 1,
|
||||
"next_step_required": False,
|
||||
"findings": "Continuing multi-file analysis with code review perspective",
|
||||
"relevant_files": [self.test_files["python"], self.test_files["config"]], # Same files
|
||||
"continuation_id": multi_id,
|
||||
"model": "flash",
|
||||
},
|
||||
|
||||
Reference in New Issue
Block a user