Implements regex-based response parser to extract file creation actions
and artifacts from LLM text responses. Agents can now produce actual
work products (files, PRs) instead of just returning instructions.
Changes:
- pkg/ai/response_parser.go: New parser with 4 extraction patterns
* Markdown code blocks with filename comments
* Inline backtick filenames followed by "content:" and code blocks
* File header notation (--- filename: ---)
* Shell heredoc syntax (cat > file << EOF)
- pkg/execution/engine.go: Skip sandbox when SandboxType empty/none
* Prevents Docker container errors during testing
* Preserves artifacts from AI response without sandbox execution
- pkg/ai/{ollama,resetdata}.go: Integrate response parser
* Both providers now parse LLM output for extractable artifacts
* Fallback to task_analysis action if no artifacts found
- internal/runtime/agent_support.go: Fix AI provider initialization
* Set DefaultProvider in RoleModelMapping (prevents "provider not found")
- prompts/defaults.md: Add Rule O for output format guidance
* Instructs LLMs to format responses for artifact extraction
* Provides examples and patterns for file creation/modification
* Explains pipeline: extraction → workspace → tests → PR → review
Test results:
- Before: 0 artifacts, 0 files generated
- After: 2 artifacts extracted successfully from LLM response
- hello.sh (60 bytes) with correct shell script content
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Add processBriefs() polling loop that checks for assigned council briefs
and executes them using the ExecutionEngine infrastructure.
Changes:
- Add GetCurrentAssignment() public method to council.Manager
- Make HTTPServer.CouncilManager public for brief access
- Add processBriefs() 15-second polling loop in agent_support.go
- Add executeBrief() to initialize and run ExecutionEngine
- Add buildExecutionRequest() to convert briefs to execution requests
- Add uploadResults() to send completed work to WHOOSH
- Wire processBriefs() into StartAgentMode() as background goroutine
This addresses the root cause of task execution not happening: briefs
were being stored but never polled or executed. The execution
infrastructure (ExecutionEngine, AI providers, prompt system) was
complete but not connected to the council workflow.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
