15 KiB
Document Project Workflow Router
The workflow execution engine is governed by: {project-root}/_bmad/core/tasks/workflow.md You MUST have already loaded and processed: {project-root}/_bmad/bmm/workflows/document-project/workflow.md Communicate all responses in {communication_language}
This router determines workflow mode and delegates to specialized sub-workflows
Initialize status defaults:
- Set status_exists = false
- Set status_file_found = false
- Set standalone_mode = true
- Set warning = ""
- Set status_load_error_reason = ""
- Set suggestion = ""
- Set next_workflow = ""
- Set next_agent = ""
- Set status_file_path = ""
- Set field_type = ""
- Set workflow_mode = ""
- Set scan_level = ""
- Set subworkflow_success = false
- Set status_update_success = false
- Set cached_project_types = ""
Attempt to load workflow status directly from {output_folder}/bmm-workflow-status.yaml:
- If file exists, is readable, and parses correctly:
- Set status_exists = true
- Set status_file_found = true
- Set standalone_mode = false
- Set status_file_path =
{output_folder}/bmm-workflow-status.yaml - Extract field_type, warning, suggestion, next_workflow, next_agent if present
- If file is missing, unreadable, or malformed:
- Keep defaults and continue in standalone mode
- Set status_load_error_reason from the caught file/parse error (e.g., missing file, permission denied, YAML parse error)
- Set warning = "Unable to load workflow status from {output_folder}/bmm-workflow-status.yaml: {{status_load_error_reason}}"
- Output warning and continue in standalone mode
Validate sequencing locally from loaded status fields: - If warning is empty, continue - If warning contains guidance, require explicit user confirmation before continuing
{{warning}} Note: This may be auto-invoked by prd for brownfield documentation. Continue with documentation? (y/n) {{suggestion}} Exit workflow SMART LOADING STRATEGY: Check state file FIRST before loading any CSV filesCheck for existing state file at: {project_knowledge}/project-scan-report.json Set resume_mode = false
Read state file and extract: timestamps, mode, scan_level, current_step, completed_steps, project_classification Validate last_updated from state file: - If last_updated is missing or invalid, set state_age_hours = 999 and mark state as stale - Otherwise parse last_updated into validated_last_updated Extract cached project_type_id(s) from state file if present Calculate state_age_hours: - If validated_last_updated exists, compute current time - validated_last_updated - Otherwise keep state_age_hours = 999 Display: "Found old state file (>24 hours). Starting fresh scan." Attempt to create archive directory: {project_knowledge}/.archive/ Failed to create archive directory at {project_knowledge}/.archive/. Keeping existing state and exiting to avoid data loss. Set resume_mode = true Exit workflow Attempt to archive old state file to: {project_knowledge}/.archive/project-scan-report-{{timestamp}}.json Failed to archive old state file. Keeping existing state and exiting to avoid data loss. Set resume_mode = true Exit workflow Set resume_mode = false Set workflow_mode = "" Set scan_level = "" Set cached_project_types = "" Set current_step = "" Set subworkflow_success = false Continue to Step 3I found an in-progress workflow state from {{last_updated}}.
Current Progress:
- Mode: {{mode}}
- Scan Level: {{scan_level}}
- Completed Steps: {{completed_steps_count}}/{{total_steps}}
- Last Step: {{current_step}}
- Project Type(s): {{cached_project_types}}
Would you like to:
- Resume from where we left off - Continue from step {{current_step}}
- Start fresh - Archive old state and begin new scan
- Cancel - Exit without changes
Your choice [1/2/3]:
Set resume_mode = true Validate persisted mode before assigning workflow_mode: - If mode is one of [deep_dive, initial_scan, full_rescan], set workflow_mode = {{mode}} - Otherwise set workflow_mode = "full_rescan", set resume_mode = false, and continue as fresh scan Set subworkflow_success = false Load findings summaries from state file Load cached project_type_id(s) from state file<critical>CONDITIONAL CSV LOADING FOR RESUME:</critical>
<check if="cached_project_types == ''">
<output>No cached project types found. Falling back to full CSV load.</output>
<action>Load project-types.csv and architecture_registry.csv</action>
<action>Load documentation_requirements_csv for active project classification</action>
</check>
<check if="cached_project_types != ''">
<action>For each cached project_type_id, load ONLY the corresponding row from: {documentation_requirements_csv}</action>
<action>Skip loading project-types.csv and architecture_registry.csv (not needed on resume)</action>
<action>Store loaded doc requirements for use in remaining steps</action>
</check>
<action>Display: "Resuming {{workflow_mode}} from {{current_step}} with cached project type(s): {{cached_project_types}}"</action>
<check if="workflow_mode == deep_dive">
<action>Read fully and follow: {installed_path}/workflows/deep-dive-instructions.md with resume context</action>
<action>Set subworkflow_success = true only if delegated workflow completed without HALT/error</action>
<check if="subworkflow_success != true">
<output>Sub-workflow failed or was aborted during resume deep-dive mode. Exiting without marking completion.</output>
<action>Exit workflow</action>
</check>
<action>After sub-workflow completes, continue to Step 4</action>
</check>
<check if="workflow_mode == initial_scan OR workflow_mode == full_rescan">
<action>Read fully and follow: {installed_path}/workflows/full-scan-instructions.md with resume context</action>
<action>Set subworkflow_success = true only if delegated workflow completed without HALT/error</action>
<check if="subworkflow_success != true">
<output>Sub-workflow failed or was aborted during resume full-scan mode. Exiting without marking completion.</output>
<action>Exit workflow</action>
</check>
<action>After sub-workflow completes, continue to Step 4</action>
</check>
<check if="workflow_mode != deep_dive AND workflow_mode != initial_scan AND workflow_mode != full_rescan">
<output>Invalid resume workflow mode '{{workflow_mode}}'. Exiting without marking completion.</output>
<action>Exit workflow</action>
</check>
Attempt to create archive directory: {project_knowledge}/.archive/
Failed to create archive directory. Keeping existing state and exiting to avoid data loss.
Set resume_mode = true
Exit workflow
Attempt to move old state file to: {project_knowledge}/.archive/project-scan-report-{{timestamp}}.json
Failed to archive old state file. Keeping existing state and exiting to avoid data loss.
Set resume_mode = true
Exit workflow
Set resume_mode = false
Reset workflow_mode, scan_level, cached_project_types, current_step to defaults
Set subworkflow_success = false
Continue to Step 3
Display: "Exiting workflow without changes."
Exit workflow
Invalid selection. Expected 1, 2, or 3. Exiting workflow without changes.
Exit workflow
Set resume_mode = false
Continue to Step 3
Check if {project_knowledge}/index.md exists
Read existing index.md to extract metadata (date, project structure, parts count)
Store as {{existing_doc_date}}, {{existing_structure}}
I found existing documentation generated on {{existing_doc_date}}.
What would you like to do?
- Re-scan entire project - Update all documentation with latest changes
- Deep-dive into specific area - Generate detailed documentation for a particular feature/module/folder
- Cancel - Keep existing documentation as-is
Your choice [1/2/3]:
Set workflow_mode = "full_rescan" Set scan_level = "standard" Display: "Starting full project rescan..." Read fully and follow: {installed_path}/workflows/full-scan-instructions.md Set subworkflow_success = true only if delegated workflow completed without HALT/error Sub-workflow failed or was aborted during full rescan. Exiting without marking completion. Exit workflow After sub-workflow completes, continue to Step 4 Set workflow_mode = "deep_dive" Set scan_level = "exhaustive" Display: "Starting deep-dive documentation mode..." Read fully and follow: {installed_path}/workflows/deep-dive-instructions.md Set subworkflow_success = true only if delegated workflow completed without HALT/error Sub-workflow failed or was aborted during deep-dive mode. Exiting without marking completion. Exit workflow After sub-workflow completes, continue to Step 4 Display message: "Keeping existing documentation. Exiting workflow." Exit workflow Invalid selection. Expected 1, 2, or 3. Exiting workflow without changes. Exit workflow Set workflow_mode = "initial_scan" Set scan_level = "initial" Display: "No existing documentation found. Starting initial project scan..." Read fully and follow: {installed_path}/workflows/full-scan-instructions.md Set subworkflow_success = true only if delegated workflow completed without HALT/error Sub-workflow failed or was aborted during initial scan. Exiting without marking completion. Exit workflow After sub-workflow completes, continue to Step 4 Resume flow did not complete a delegated sub-workflow successfully. Exiting without completion update. Exit workflow Attempt status update in {{status_file_path}}: - Mark workflow `document-project` as completed - Persist updated timestamp and completion metadata - Set status_update_success = true on success - If write fails, set status_update_success = false and capture status_update_error Status updated! ⚠️ Status update skipped: {{status_update_error}}✅ Document Project Workflow Complete, {user_name}!
Documentation Generated:
- Mode: {{workflow_mode}}
- Scan Level: {{scan_level}}
- Output: {project_knowledge}/index.md and related files
Next Steps:
- Run
bmad-helpif you need recommended next workflows. - Next required: {{next_workflow}} ({{next_agent}} agent) - Next required: not specified