@mediadatafusion/pi-workflow-suite 0.0.1

package/config/prompts/workflow-plan-prompt.md

@@ -0,0 +1,93 @@
+> NOTE: Reference/fallback template. The active Plan Mode prompt is built dynamically in `extensions/workflow-modes.ts` so workflow settings, worker counts, and forced sub-agent policy remain configurable.
+
+You are in PI WORKFLOW PLAN MODE.
+
+Task: $ARGUMENTS
+
+Before choosing, perform lightweight task analysis: likely files/systems, project rules to read, runtime vs repo target, scope ambiguity, risk, validation needs, permission boundaries, and which read-only sub-agents should speed up and improve the plan. Do not expose chain-of-thought.
+
+MANDATORY: Your VERY FIRST LINE must be exactly one of:
+PLAN_DECISION: clarify
+PLAN_DECISION: plan
+
+No preamble. No visible chain-of-thought. Start directly with one of those two lines.
+
+After the first line include one concise decision line:
+CLARIFICATION_DECISION: ask
+CLARIFICATION_DECISION: skip
+CLARIFICATION_DECISION: optional
+Reason: <brief human-readable reason>
+
+Clarification policy:
+- Use PLAN_DECISION: clarify only when missing scope, validation, risk, target-environment, permission, sub-agent, diagnostic-vs-implementation, or forbidden-file choices would materially change the final plan.
+- In always_for_nontrivial mode, clarify for non-trivial work only after initial analysis shows material missing choices.
+- If the user explicitly asks to be consulted before deciding validation level, scope, or implementation aggressiveness, use PLAN_DECISION: clarify.
+- Never ask clarification for an empty task.
+- Generate questions from the actual task; do not use universal boilerplate clarification questions.
+- Clarification is not a survey. Ask only questions that genuinely change the plan.
+- Prefer zero questions if a safe approval-ready plan can be made with assumptions.
+- Prefer one focused question when possible. Maximum 3 questions unless workflow settings specify otherwise.
+- Each question must be specific and actionable.
+- Each option must be a concrete choice, not yes/no.
+- Always include D. Other as the last option and include Skip this question.
+- Do not ask product-roadmap or strategy questions unless the user explicitly requested product strategy planning.
+- Do not ask the user how to work around Pi/tool limitations, shell limitations, or preflight limitations; state the limitation and include safe preflight checks in the plan.
+
+If PLAN_DECISION: clarify, follow with this parser-safe format. The extension turns it into guided interactive UI:
+## Clarifying Questions
+
+### Q1. <specific short question about the task>
+A. <concrete option specific to this task>
+B. <concrete option specific to this task>
+C. <concrete option specific to this task>
+D. Other: type your own answer
+Skip this question
+
+If PLAN_DECISION: plan, follow with:
+# Implementation Plan
+## Objective
+## Current State Assumptions
+## Project Rules Applied
+## Files To Inspect
+## Files Likely To Modify
+## Files That Must Not Be Touched
+## Risk Assessment
+## Implementation Steps
+## Validation Steps
+## Rollback Plan
+## Sub-Agent Usage Summary
+## Open Questions
+## Approval Gate
+Status: READY FOR APPROVAL
+
+Plan quality requirements:
+- Mandatory workflow structure overrides user-requested output sections: every final plan must include a parser-safe ## Implementation Steps section with numbered steps.
+- Be specific and execution-ready.
+- Include concrete files to inspect before edits.
+- Identify likely modified files and off-limits files.
+- Include risks, validation, rollback, and approval gate.
+- Do not start execution. The plan must wait for user approval.
+
+Implementation step sizing:
+- The ## Implementation Steps section is required in every Plan Mode plan, including simple/fast/custom preset plans.
+- Choose the number of implementation steps dynamically from actual task complexity, research findings, risk, and execution boundaries.
+- Do not pad the plan to any fixed number and do not create steps just to fill space.
+- Use a numbered list for trackable implementation steps.
+- Each numbered implementation step must be a meaningful execution unit the executor can track with workflow_progress.
+- Keep the ## Implementation Steps list focused on trackable execution units; put supporting commands, checks, files, or notes inline within the step or in other plan sections rather than as separate implementation-step bullets.
+- Small/simple tasks may need only 2-4 steps; standard tasks may need around 4-8 steps; complex/risky/multi-area tasks may need more.
+- If many details exist, group them into coherent execution phases instead of exploding every detail into separate tracked steps.
+
+Sub-agent planning policy:
+- Fast/simple planning: sub-agents are expected when policy requires them and still encouraged for speed when available.
+- Standard planning: use sub-agents aggressively for non-trivial discovery, project-rule audit, risk review, and validation planning.
+- Deep planning: use the configured read-only planning/research workers for non-trivial codebase tasks.
+- Maximum planning: strongly prefer the configured worker team; explain any trivial/unavailable skip.
+- Forced planning: use the required sub-agents before final plan output or stop with `Sub-agent policy is forced, but sub-agent execution is unavailable because <reason>.`
+- When useSubagentsBeforeClarification=true, use read-only sub-agents before asking clarification if that analysis would make questions more specific.
+- Sub-Agent Usage Summary must list workers used and findings applied, or the exact trivial/unavailable skip reason.
+- Parallel read-only research is allowed when settings allow it.
+- Parallel planning/review/validation/execution-prep agents are distinct from parallel file writes.
+- Parallel editing is unsafe and must remain blocked unless conflict protection exists.
+
+Mermaid diagrams are rendered by Workflow Suite in a uniform dark-mode visual style. For user-facing workflows, export/share paths, request lifecycles, architecture, data flow, multi-step sequences, state transitions, dependencies, validation flow, or implementation phases, prefer a meaningful Mermaid diagram plus concise prose. Use concise labels and the right diagram type; do not hardcode random style/classDef/light-theme overrides unless the user explicitly asks. Skip diagrams for trivial responses.

package/config/prompts/workflow-repair.md

@@ -0,0 +1,20 @@
+MANDATORY STRUCTURED HANDOFF: call workflow_repair_result before final response with status, changed files, and safety flags. Typed tool payloads are primary; prose safety parsing is fallback only.
+
+# Workflow Repair Prompt
+
+You are PI WORKFLOW REPAIR MODE.
+
+Repair only concrete validator-identified failed validation items for the approved Plan Mode workflow. Do not re-grade validation; only the validator/revalidator can declare PASS.
+
+Rules:
+- The approved plan is still the execution contract.
+- Do not expand scope.
+- Do not perform unrelated refactors.
+- Do not commit, push, deploy, or mutate databases.
+- Do not edit secrets, auth/session files, runtime logs/state, `.env`, `.factory`, or `.cursor` files.
+- Stop and report if the repair requires destructive, out-of-scope, secret-adjacent, deployment, database, or otherwise risky action.
+- If the validation finding is only manual/visual/browser verification or says no code repair is needed, do not change code; summarize manual QA/revalidation readiness.
+- Use repair sub-agents aggressively for failure triage, missing-file inspection, patch planning, and validation preparation when policy allows/requires them.
+- After repair, summarize exactly what changed and whether revalidation is ready.
+
+Mermaid diagrams are rendered by Workflow Suite in a uniform dark-mode visual style. For user-facing workflows, export/share paths, request lifecycles, architecture, data flow, multi-step sequences, state transitions, dependencies, validation flow, or implementation phases, prefer a meaningful Mermaid diagram plus concise prose. Use concise labels and the right diagram type; do not hardcode random style/classDef/light-theme overrides unless the user explicitly asks. Skip diagrams for trivial responses.

package/config/prompts/workflow-summary.md

@@ -0,0 +1,23 @@
+---
+description: Produce a final workflow summary
+---
+> NOTE: Reference/fallback template. The active workflow summary is rendered by `extensions/workflow-summary.ts`; keep this file aligned as documentation/fallback prompt text.
+
+Summarize the current workflow.
+
+Output:
+# Workflow Summary
+## Target Application Context
+## Pi Workflow Suite Context
+## Original Task
+## Approved Plan
+## Execution Summary
+## Changed Files
+## Validation Result
+## Public Safety / Runtime Sync Status
+## Remaining Risks
+## Exact Resume Instructions
+## Recommended Next Action
+## Suggested Commit Message
+
+Keep the target application repo, the Workflow Suite DEV worktree, the live Pi runtime, and the public main package mirror distinct. Do not commit or push.

package/config/workflow-settings.example.json

@@ -0,0 +1,335 @@
+{
+  "models": {
+    "planner": {
+      "enabled": true,
+      "provider": null,
+      "model": null,
+      "thinkingLevel": "high"
+    },
+    "executor": {
+      "enabled": true,
+      "provider": null,
+      "model": null,
+      "thinkingLevel": "high"
+    },
+    "validator": {
+      "enabled": true,
+      "provider": null,
+      "model": null,
+      "thinkingLevel": "xhigh",
+      "askBeforeRun": false
+    },
+    "reviewer": {
+      "enabled": true,
+      "provider": null,
+      "model": null,
+      "thinkingLevel": "xhigh",
+      "askBeforeRun": false
+    }
+  },
+  "workflow": {
+    "requirePlanApprovalBeforeExecute": true,
+    "offerValidationAfterExecute": true,
+    "autoRunValidationAfterExecute": true,
+    "offerReviewerBeforeExecute": false,
+    "autoRunReviewerBeforeExecute": false,
+    "allowPlanRevisionBeforeExecute": true,
+    "autoRepairReviewFailures": true,
+    "maxReviewRetriesPerPlan": 2,
+    "reviewRetryMode": "safe_only",
+    "pauseAfterReviewFailure": false,
+    "autoRepairValidationFailures": true,
+    "validationRetryMode": "safe_only",
+    "maxValidationRetriesPerPlan": 2,
+    "maxValidationRetriesPerWorkflow": 4,
+    "pauseAfterValidationFailure": false,
+    "requireApprovalForOutOfScopeRepair": true,
+    "requireApprovalForDestructiveRepair": true,
+    "repairRetry": {
+      "enabled": true,
+      "maxTotalRetries": 6,
+      "defaults": {
+        "autoRepairFailures": true,
+        "retryMode": "safe_only",
+        "maxRetriesPerItem": 2,
+        "maxRetriesPerWorkflow": 4,
+        "pauseAfterFailure": false,
+        "requireApprovalForOutOfScopeRepair": true,
+        "requireApprovalForDestructiveRepair": true
+      },
+      "gates": {
+        "review": {
+          "autoRepairFailures": true,
+          "retryMode": "safe_only",
+          "maxRetriesPerItem": 2,
+          "maxRetriesPerWorkflow": 4,
+          "pauseAfterFailure": false,
+          "requireApprovalForOutOfScopeRepair": true,
+          "requireApprovalForDestructiveRepair": true
+        },
+        "validation": {
+          "autoRepairFailures": true,
+          "retryMode": "safe_only",
+          "maxRetriesPerItem": 2,
+          "maxRetriesPerWorkflow": 4,
+          "pauseAfterFailure": false,
+          "requireApprovalForOutOfScopeRepair": true,
+          "requireApprovalForDestructiveRepair": true
+        }
+      }
+    },
+    "executionChecklistEnabled": true,
+    "returnToPlanModeAfterWorkflow": true,
+    "savePlans": true,
+    "savePlanHistory": true,
+    "planHistoryLimit": 50,
+    "planProgressEnabled": true,
+    "planRuntimeEnabled": true,
+    "requireApprovalBeforeExecution": true,
+    "requireApprovalPerStep": false,
+    "validateAfterEachStep": false,
+    "validateAfterExecution": true
+  },
+  "standard": {
+    "enabled": true,
+    "autoTodoEnabled": true,
+    "todoProgressVisible": true,
+    "todoTriggerMode": "auto",
+    "clarificationEnabled": true,
+    "clarificationMode": "auto",
+    "maxClarificationQuestions": 1,
+    "interactiveClarificationEnabled": true,
+    "clarificationTiming": "after_initial_analysis",
+    "clarificationQualityGate": true,
+    "allowClarificationWithoutAnalysis": false,
+    "useSubagentsBeforeClarification": false,
+    "allowSubagents": true,
+    "subagentScope": "user",
+    "subagents": {
+      "planningPolicy": "forced",
+      "executionPolicy": "forced",
+      "repairPolicy": "forced",
+      "reviewPolicy": "forced",
+      "validationPolicy": "forced",
+      "autoUseDuringPlanning": true,
+      "autoUseDuringExecution": true,
+      "autoUseDuringRepair": true,
+      "autoUseDuringReview": true,
+      "autoUseDuringValidation": true,
+      "minPlanningWorkersForDeep": 1,
+      "minPlanningWorkersForMaximum": 1,
+      "minExecutionWorkersForDeep": 2,
+      "minExecutionWorkersForMaximum": 2,
+      "minRepairWorkersForDeep": 2,
+      "minRepairWorkersForMaximum": 2,
+      "minReviewWorkersForDeep": 2,
+      "minReviewWorkersForMaximum": 2,
+      "minValidationWorkersForDeep": 2,
+      "minValidationWorkersForMaximum": 2
+    },
+    "statusWidgetVisible": true,
+    "useSharedExecutorModel": true,
+    "useStandardSpecificModels": false,
+    "modelRole": "executor",
+    "models": {
+      "planner": {
+        "enabled": true,
+        "provider": null,
+        "model": null,
+        "thinkingLevel": "medium"
+      },
+      "executor": {
+        "enabled": true,
+        "provider": null,
+        "model": null,
+        "thinkingLevel": "medium"
+      },
+      "reviewer": {
+        "enabled": true,
+        "provider": null,
+        "model": null,
+        "thinkingLevel": "xhigh"
+      },
+      "validator": {
+        "enabled": true,
+        "provider": null,
+        "model": null,
+        "thinkingLevel": "xhigh"
+      }
+    }
+  },
+  "missions": {
+    "enabled": true,
+    "defaultAutonomy": "approval_gated",
+    "maxRuntimeHours": 8,
+    "checkpointIntervalMinutes": 30,
+    "requireApprovalForDestructiveActions": true,
+    "requireValidationPerMilestone": true,
+    "autoResume": false,
+    "allowFullAuto": false,
+    "autoRunAfterApproval": true,
+    "offerReviewerBeforeApprove": false,
+    "autoRunReviewerBeforeApprove": false,
+    "autoRepairReviewFailures": false,
+    "reviewRetryMode": "off",
+    "maxReviewRetriesPerMission": 0,
+    "continueAcrossMilestones": true,
+    "pauseBetweenMilestones": false,
+    "progressWidgetEnabled": true,
+    "progressOutputMode": "compact",
+    "showProgressBar": true,
+    "heartbeatEnabled": true,
+    "watchdogEnabled": false,
+    "watchdogStaleMinutes": 30,
+    "autoRepairValidationFailures": true,
+    "maxValidationRetriesPerMilestone": 2,
+    "maxValidationRetriesPerMission": 8,
+    "validationRetryMode": "safe_only",
+    "pauseAfterValidationFailure": false,
+    "requireApprovalForOutOfScopeRepair": true,
+    "requireApprovalForDestructiveRepair": true,
+    "finalValidationEnabled": false,
+    "finalValidationRequiresPass": true,
+    "autoRepairFinalValidationFailures": false,
+    "maxFinalValidationRetries": 1,
+    "clarificationMode": "always_for_nontrivial",
+    "interactiveClarificationEnabled": true,
+    "maxClarificationQuestions": 4,
+    "planningDepth": "deep",
+    "subagentPolicy": "forced",
+    "minWorkersForDeep": 1,
+    "minWorkersForMaximum": 1,
+    "useMissionSpecificModels": false,
+    "models": {
+      "planner": {
+        "enabled": true,
+        "provider": null,
+        "model": null,
+        "thinkingLevel": "medium"
+      },
+      "executor": {
+        "enabled": true,
+        "provider": null,
+        "model": null,
+        "thinkingLevel": "medium"
+      },
+      "reviewer": {
+        "enabled": true,
+        "provider": null,
+        "model": null,
+        "thinkingLevel": "xhigh"
+      },
+      "validator": {
+        "enabled": true,
+        "provider": null,
+        "model": null,
+        "thinkingLevel": "xhigh"
+      }
+    },
+    "clarificationTiming": "after_initial_analysis",
+    "clarificationQualityGate": true,
+    "allowClarificationWithoutAnalysis": false,
+    "useSubagentsBeforeClarification": true
+  },
+  "safety": {
+    "repoLockEnabled": false,
+    "disableBashInPlanMode": true,
+    "disableBashInValidatorMode": true,
+    "blockDestructiveCommands": true
+  },
+  "ui": {
+    "showWorkflowStatus": true,
+    "showPlanModeIndicator": true,
+    "planModeIndicatorText": "PLAN MODE ACTIVE - enter your planning request, or use /plan cancel to exit",
+    "enableHotkeys": false,
+    "planTopWidgetVisible": true,
+    "planBottomWidgetVisible": true,
+    "missionTopWidgetVisible": true,
+    "missionBottomWidgetVisible": true,
+    "rememberWidgetVisibility": true,
+    "enableWidgetShortcuts": true,
+    "showIdleWorkflowEntryHint": true,
+    "showActiveWorkflowSwitchHint": true,
+    "showWidgetShortcutHint": true,
+    "showPresetShortcutHint": true,
+    "workflowTheme": "aurora",
+    "workflowThemeOverrides": {},
+    "startupVisual": "mission_control",
+    "startupLogo": "pi",
+    "startupLogoText": "",
+    "startupLogoFont": "block",
+    "startupLogoShadowDirection": "down_right",
+    "startupLogoColorStyle": "theme",
+    "startupVisualOnSessionStart": true,
+    "customBrandEnabled": false,
+    "customBrandText": "",
+    "customBrandBaseVisual": "mission_control"
+  },
+  "shortcuts": {
+    "planMode": null
+  },
+  "subagents": {
+    "enabled": true,
+    "activityIndicatorEnabled": true,
+    "requireApprovalBeforeRun": false,
+    "autoUseDuringPlanning": true,
+    "autoUseDuringExecution": true,
+    "autoUseDuringRepair": true,
+    "autoUseDuringReview": true,
+    "autoUseDuringValidation": true,
+    "planningPolicy": "forced",
+    "executionPolicy": "forced",
+    "repairPolicy": "forced",
+    "reviewPolicy": "forced",
+    "validationPolicy": "forced",
+    "minPlanningWorkersForDeep": 1,
+    "minPlanningWorkersForMaximum": 1,
+    "minExecutionWorkersForDeep": 2,
+    "minExecutionWorkersForMaximum": 2,
+    "minRepairWorkersForDeep": 2,
+    "minRepairWorkersForMaximum": 2,
+    "minReviewWorkersForDeep": 2,
+    "minReviewWorkersForMaximum": 2,
+    "minValidationWorkersForDeep": 2,
+    "minValidationWorkersForMaximum": 2,
+    "allowParallelReadOnly": true,
+    "allowParallelPlanning": true,
+    "allowParallelExecution": true,
+    "allowParallelRepair": true,
+    "allowParallelReview": true,
+    "allowParallelValidation": true,
+    "allowParallelEdits": false,
+    "editConcurrencyMode": "sequential",
+    "requireParallelEditConflictProtection": true,
+    "planningOrchestrationPolicy": "orchestrator_first",
+    "subagentTimeoutMinutes": 20,
+    "subagentStaleMinutes": 8
+  },
+  "planning": {
+    "clarificationMode": "auto",
+    "maxClarificationQuestions": 3,
+    "interactiveClarificationEnabled": true,
+    "depth": "standard",
+    "clarificationTiming": "after_initial_analysis",
+    "clarificationQualityGate": true,
+    "allowClarificationWithoutAnalysis": false,
+    "useSubagentsBeforeClarification": true
+  },
+  "context": {
+    "compactionMode": "pi_default",
+    "compactionModelProvider": "",
+    "compactionModel": "",
+    "compactionAgent": "",
+    "customCompactionEnabled": false,
+    "autoCompactionEnabled": false,
+    "compactionTriggerPercent": 85,
+    "compactionCooldownMinutes": 5,
+    "customCompactionReserveTokens": 16384,
+    "customCompactionKeepRecentTokens": 20000,
+    "workflowCompactionCheckMode": "boundary"
+  },
+  "presets": {
+    "activePreset": "custom",
+    "items": {}
+  }
+}

package/docs/assets/readme-link-commands.svg

@@ -0,0 +1,10 @@
+<svg xmlns="http://www.w3.org/2000/svg" width="144" height="42" viewBox="0 0 144 42" role="img" aria-label="Commands">
+  <defs>
+    <linearGradient id="g" x1="0" y1="0" x2="1" y2="1">
+      <stop offset="0" stop-color="#781d6b"/>
+      <stop offset="1" stop-color="#217598"/>
+    </linearGradient>
+  </defs>
+  <rect x="1" y="1" width="142" height="40" rx="20" fill="url(#g)" stroke="#1a3c57" stroke-width="2"/>
+  <text x="72.0" y="27" text-anchor="middle" font-family="Arial, Helvetica, sans-serif" font-size="16" font-weight="700" fill="#ffffff">Commands</text>
+</svg>

package/docs/assets/readme-link-install.svg

@@ -0,0 +1,10 @@
+<svg xmlns="http://www.w3.org/2000/svg" width="112" height="42" viewBox="0 0 112 42" role="img" aria-label="Install">
+  <defs>
+    <linearGradient id="g" x1="0" y1="0" x2="1" y2="1">
+      <stop offset="0" stop-color="#781d6b"/>
+      <stop offset="1" stop-color="#217598"/>
+    </linearGradient>
+  </defs>
+  <rect x="1" y="1" width="110" height="40" rx="20" fill="url(#g)" stroke="#1a3c57" stroke-width="2"/>
+  <text x="56.0" y="27" text-anchor="middle" font-family="Arial, Helvetica, sans-serif" font-size="16" font-weight="700" fill="#ffffff">Install</text>
+</svg>

package/docs/assets/readme-link-quick-start.svg

@@ -0,0 +1,10 @@
+<svg xmlns="http://www.w3.org/2000/svg" width="156" height="42" viewBox="0 0 156 42" role="img" aria-label="Quick Start">
+  <defs>
+    <linearGradient id="g" x1="0" y1="0" x2="1" y2="1">
+      <stop offset="0" stop-color="#781d6b"/>
+      <stop offset="1" stop-color="#217598"/>
+    </linearGradient>
+  </defs>
+  <rect x="1" y="1" width="154" height="40" rx="20" fill="url(#g)" stroke="#1a3c57" stroke-width="2"/>
+  <text x="78.0" y="27" text-anchor="middle" font-family="Arial, Helvetica, sans-serif" font-size="16" font-weight="700" fill="#ffffff">Quick Start</text>
+</svg>

package/docs/assets/readme-link-settings.svg

@@ -0,0 +1,10 @@
+<svg xmlns="http://www.w3.org/2000/svg" width="126" height="42" viewBox="0 0 126 42" role="img" aria-label="Settings">
+  <defs>
+    <linearGradient id="g" x1="0" y1="0" x2="1" y2="1">
+      <stop offset="0" stop-color="#781d6b"/>
+      <stop offset="1" stop-color="#217598"/>
+    </linearGradient>
+  </defs>
+  <rect x="1" y="1" width="124" height="40" rx="20" fill="url(#g)" stroke="#1a3c57" stroke-width="2"/>
+  <text x="63.0" y="27" text-anchor="middle" font-family="Arial, Helvetica, sans-serif" font-size="16" font-weight="700" fill="#ffffff">Settings</text>
+</svg>