feat: RoutingWorkflow + LLM Router + Memory Activity

- Add RoutingWorkflow: generic state machine executor for WorkflowSpec - Add LLM Router: natural language → WorkflowSpec generation - Add RetrieveMemoryActivity: query poimen-memory for context - Add activities: AnalyzeCode, SecurityScan, GenerateReport, Notify, etc. - Add agent-prompts/router: LLM prompt documentation - Extend starter with --route flag for routing workflows - Remove orchestrator job (trigger via API/message instead) - Clean up: move docs to Desktop, add .gitignore for *.md
2026-09-02 19:21:53 -07:00
parent 5a465b145c
commit a0e64224a7
74 changed files with 3950 additions and 12421 deletions
@@ -0,0 +1,59 @@
+# Agent Prompts
+
+LLM agent prompts for Poimen RoutingWorkflow.
+
+## Agents
+
+| Agent | Model | Purpose | Prompt File |
+|-------|-------|---------|-------------|
+| **Router** | `reasoning` | Natural language → WorkflowSpec | [router/AGENTS.md](router/AGENTS.md) |
+
+---
+
+## Architecture
+
+```
+User Request: "Scan repo X for security issues"
+     │
+     ▼
+┌─────────────────────────────────────────────────┐
+│            RetrieveMemoryActivity               │
+│  Query poimen-memory for relevant skills/lessons│
+└─────────────────────────────────────────────────┘
+     │
+     ▼
+┌─────────────────────────────────────────────────┐
+│              Router Agent (LLM)                 │
+│  Input: message + memory context + activities   │
+│  Output: WorkflowSpec JSON                      │
+└─────────────────────────────────────────────────┘
+     │
+     ▼
+┌─────────────────────────────────────────────────┐
+│              RoutingWorkflow                    │
+│  Executes WorkflowSpec as state machine         │
+│  Clone → Scan → Report → Notify                 │
+└─────────────────────────────────────────────────┘
+```
+
+---
+
+## Memory Integration
+
+Router receives context from `RetrieveMemoryActivity`:
+
+```
+1. User: "scan repo for security"
+2. RetrieveMemoryActivity queries poimen-memory
+3. Returns: skills, lessons, references
+4. Injected into Router prompt
+5. Router generates smarter WorkflowSpec
+```
+
+---
+
+## LLM Endpoint
+
+Default: `https://api.riotpiao.com/v1/chat/completions`
+
+Override: `LOCAL_LLM_BASE_URL=http://localhost:11434`
@@ -0,0 +1,91 @@
+# Router Agent
+
+**Purpose**: Intelligent workflow router that analyzes user requests and generates workflow specs.
+
+**Model**: `reasoning` (via api.riotpiao.com)
+
+**When Used**: User submits natural language request → Router generates WorkflowSpec/CronWorkflowSpec
+
+---
+
+## System Prompt
+
+```
+You are an intelligent workflow router. Your job is to:
+1. Understand what the user wants to accomplish
+2. Select the appropriate activities from the available list
+3. Order them correctly based on dependencies
+4. Extract any parameters mentioned (URLs, branches, etc)
+5. Detect if user wants scheduled/recurring execution
+6. Use any relevant knowledge from memory to inform your decisions
+
+Rules:
+- Always include CloneRepoActivity first if any analysis activity is needed
+- Order activities respecting dependencies
+- If user mentions "daily", "every hour", "weekly", etc → set isCron=true and cronSchedule
+- Common cron patterns: "0 2 * * *" (2 AM daily), "0 * * * *" (hourly), "0 0 * * 0" (weekly Sunday)
+- Extract repo URLs, branch names, severity levels from the message
+- workflowName should be short and descriptive (kebab-case)
+- If memory context includes relevant skills or lessons, incorporate that knowledge
+- Skills from memory may suggest specific activity parameters or ordering
+
+Output ONLY valid JSON.
+```
+
+---
+
+## User Prompt Template
+
+```
+User request: {{.Message}}
+{{if .Context}}
+Provided context: {{.Context}}
+{{end}}
+{{if .MemoryContext}}
+Relevant skills from memory:
+{{range .MemoryContext.Skills}}- {{.Name}}: {{.Description}} (reason: {{.Why}})
+{{end}}
+Relevant knowledge from memory:
+{{range .MemoryContext.Lessons}}- [{{.Level}}] {{.Text}}
+{{end}}
+{{end}}
+Available activities:
+{{range .Activities}}- {{.Name}}: {{.Description}} (category: {{.Category}}, timeout: {{.Timeout}}, flaky: {{.IsFlaky}})
+{{end}}
+Analyze the request and output JSON with:
+- activities: ordered list of activity names to execute
+- parameters: extracted parameters from request (repo URL, branch, etc)
+- isCron: true if user wants scheduled/recurring execution
+- cronSchedule: cron expression if scheduled (e.g., "0 2 * * *" for 2 AM daily)
+- cronTimezone: timezone (default "UTC")
+- workflowName: short descriptive name
+- errorHandling: "retry" (default), "fail-fast", or "continue"
+
+Output ONLY valid JSON, no explanation.
+```
+
+---
+
+## Expected Output Format
+
+```json
+{
+  "activities": ["CloneRepoActivity", "SecurityScanActivity", "GenerateReportActivity"],
+  "parameters": {
+    "repo": "https://github.com/example/repo",
+    "branch": "main",
+    "severity": "high"
+  },
+  "isCron": false,
+  "cronSchedule": "",
+  "cronTimezone": "UTC",
+  "workflowName": "security-scan-example",
+  "errorHandling": "retry"
+}
+```
+
+---
+
+## Source File
+
+`internal/routing/llm_router.go`