Fix #1500: Document duplicate PR prevention system

Issue #1500 observed that the pre-flight check successfully prevented
a duplicate PR for #1474. This documentation explains the system.

Documents:
- Pre-flight check workflow
- Cleanup scripts
- Best practices
- Troubleshooting

Refs #1500

docs/duplicate-pr-prevention.md

@@ -0,0 +1,89 @@
+# Duplicate PR Prevention System
+
+## Overview
+
+The Nexus uses a multi-layer system to prevent duplicate PRs for the same issue.
+
+## Components
+
+### 1. Pre-flight Check (CI)
+
+The `.github/workflows/pr-duplicate-check.yml` workflow runs on every PR creation and checks if a PR already exists for the same issue.
+
+**How it works:**
+1. Extracts issue numbers from PR title and body
+2. Queries Gitea API for existing PRs referencing those issues
+3. Fails the check if duplicates are found
+4. Provides links to existing PRs for review
+
+### 2. Cleanup Script
+
+The `scripts/cleanup-duplicate-prs.sh` script helps clean up existing duplicates:
+- Lists all PRs for a given issue
+- Identifies duplicates
+- Provides commands to close duplicates
+
+### 3. Milestone Checker
+
+The `bin/check_duplicate_milestones.py` script prevents duplicate milestones:
+- Scans all milestones in the repo
+- Identifies duplicates by title
+- Reports for manual cleanup
+
+## Usage
+
+### Check for Duplicates Before Creating PR
+
+```bash
+# Check if issue already has PRs
+curl -s -H "Authorization: token $GITEA_TOKEN" \
+  "https://forge.alexanderwhitestone.com/api/v1/repos/Timmy_Foundation/the-nexus/pulls?state=open" \
+  | jq '.[] | select(.body | contains("#ISSUE_NUMBER"))'
+```
+
+### Clean Up Existing Duplicates
+
+```bash
+# List PRs for issue
+./scripts/cleanup-duplicate-prs.sh --issue 1128
+
+# Close duplicates (keep newest)
+./scripts/cleanup-duplicate-prs.sh --issue 1128 --close-duplicates
+```
+
+## Example: Issue #1500
+
+Issue #1500 documented that the pre-flight check successfully prevented a duplicate PR for #1474.
+
+**What happened:**
+1. Dispatch attempted to work on #1474
+2. Pre-flight check found 2 existing PRs (#1495, #1493)
+3. System prevented creating a 3rd duplicate
+4. Issue #1500 was filed as an observation
+
+**Result:** The system worked as intended.
+
+## Best Practices
+
+1. **Always check before creating PRs** — use the pre-flight check
+2. **Close duplicates promptly** — don't let them accumulate
+3. **Reference issues in PRs** — makes duplicate detection possible
+4. **Use descriptive branch names** — helps identify purpose
+5. **Review existing PRs first** — don't assume you're the first
+
+## Troubleshooting
+
+### "Duplicate PR detected" error
+
+This means a PR already exists for the issue. Options:
+1. Review the existing PR and contribute to it
+2. Close your PR if it's truly a duplicate
+3. Update your PR to address a different aspect
+
+### Pre-flight check not running
+
+Check that `.github/workflows/pr-duplicate-check.yml` exists and is enabled.
+
+### False positives
+
+The check looks for issue numbers in PR body. If you're referencing an issue without intending to fix it, use "Refs #" instead of "Fixes #".

fleet/fleet-routing.json

@@ -1,13 +1,9 @@
 {
   "version": 1,
   "generated": "2026-04-06",
-  "refs": [
-    "#836",
-    "#204",
-    "#195",
-    "#196"
-  ],
+  "refs": ["#836", "#204", "#195", "#196"],
   "description": "Canonical fleet routing table. Evaluated agents, routing verdicts, and dispatch rules for the Timmy Foundation task harness.",
+
   "agents": [
     {
       "id": 27,
@@ -50,14 +46,12 @@
       "location": "Bag End, The Shire (VPS)",
       "description": "Ollama on VPS. Speaks when spoken to. Prefers quiet. Not for delegated work.",
       "primary_role": "on-request-queries",
-      "routing_verdict": "ROUTE TO: background monitoring, status checks, low-priority Q&A. Only on-request \u2014 do not delegate autonomously.",
+      "routing_verdict": "ROUTE TO: background monitoring, status checks, low-priority Q&A. Only on-request — do not delegate autonomously.",
       "active": true,
       "do_not_route": false,
       "created": "2026-04-02",
       "repo_count": 1,
-      "repos": [
-        "bilbobagginshire/bilbo-adventures"
-      ]
+      "repos": ["bilbobagginshire/bilbo-adventures"]
     },
     {
       "id": 24,
@@ -66,7 +60,7 @@
       "model": "codex",
       "tier": "prepaid",
       "location": "The Harness",
-      "description": "OpenClaw bridge. Protocol adapter layer \u2014 not a personality. Infrastructure, not a destination.",
+      "description": "OpenClaw bridge. Protocol adapter layer — not a personality. Infrastructure, not a destination.",
       "primary_role": "protocol-bridge",
       "routing_verdict": "DO NOT ROUTE directly. claw-code is the bridge to external Codex agents, not an endpoint. Remove from routing cascade.",
       "active": true,
@@ -85,7 +79,7 @@
       "location": "Below the Surface",
       "description": "Infrastructure, deployments, bedrock services. Needs model assignment before activation.",
       "primary_role": "devops",
-      "routing_verdict": "DO NOT ROUTE \u2014 no model assigned yet. Activate after Epic #196 (Local Model Fleet) assigns a model.",
+      "routing_verdict": "DO NOT ROUTE — no model assigned yet. Activate after Epic #196 (Local Model Fleet) assigns a model.",
       "active": false,
       "do_not_route": true,
       "do_not_route_reason": "No model assigned. Blocked on Epic #196.",
@@ -103,15 +97,13 @@
       "location": "The Archive",
       "description": "Original prototype. Museum piece. Preserved for historical reference only.",
       "primary_role": "inactive",
-      "routing_verdict": "DO NOT ROUTE \u2014 retired from active duty. Preserved only.",
+      "routing_verdict": "DO NOT ROUTE — retired from active duty. Preserved only.",
       "active": false,
       "do_not_route": true,
       "do_not_route_reason": "Retired prototype. Historical preservation only.",
       "created": "2026-03-31",
       "repo_count": 1,
-      "repos": [
-        "allegro-primus/first-steps"
-      ]
+      "repos": ["allegro-primus/first-steps"]
     },
     {
       "id": 5,
@@ -128,10 +120,7 @@
       "gap": "Agent description is empty in Gitea profile. Needs enrichment.",
       "created": "2026-03-14",
       "repo_count": 2,
-      "repos": [
-        "kimi/the-nexus-fork",
-        "kimi/Timmy-time-dashboard"
-      ]
+      "repos": ["kimi/the-nexus-fork", "kimi/Timmy-time-dashboard"]
     },
     {
       "id": 20,
@@ -159,10 +148,10 @@
       "id": 19,
       "name": "ezra",
       "gitea_user": "ezra",
-      "model": "kimi-coding/kimi-k2.5",
+      "model": "claude",
       "tier": "prepaid",
       "location": "Hermes VPS",
-      "description": "Archivist. Research and triage wizard. 9 repos owned \u2014 most in the fleet. Handles complex multi-file and cross-repo work.",
+      "description": "Archivist. Claude-Hermes wizard. 9 repos owned — most in the fleet. Handles complex multi-file and cross-repo work.",
       "primary_role": "documentation",
       "routing_verdict": "ROUTE TO: docs, specs, architecture, complex multi-file work. Escalate here when breadth and precision both matter.",
       "active": true,
@@ -187,7 +176,7 @@
       "gitea_user": "bezalel",
       "model": "groq",
       "tier": "free",
-      "location": "TestBed VPS \u2014 The Forge",
+      "location": "TestBed VPS — The Forge",
       "description": "Builder, debugger, testbed wizard. Groq-powered, free tier. Strong on PR review and CI.",
       "primary_role": "code-review",
       "routing_verdict": "ROUTE TO: PR review, test writing, debugging, CI fixes.",
@@ -195,39 +184,29 @@
       "do_not_route": false,
       "created": "2026-03-29",
       "repo_count": 1,
-      "repos": [
-        "bezalel/forge-log"
-      ]
+      "repos": ["bezalel/forge-log"]
     }
   ],
+
   "routing_cascade": {
-    "description": "Cost-optimized routing cascade \u2014 cheapest capable agent first, escalate on complexity.",
+    "description": "Cost-optimized routing cascade — cheapest capable agent first, escalate on complexity.",
     "tiers": [
       {
         "tier": 1,
         "label": "Free",
-        "agents": [
-          "fenrir",
-          "bezalel",
-          "carnice"
-        ],
+        "agents": ["fenrir", "bezalel", "carnice"],
         "use_for": "Issue triage, code review, local code generation. Default lane for most tasks."
       },
       {
         "tier": 2,
         "label": "Cheap",
-        "agents": [
-          "kimi",
-          "allegro"
-        ],
-        "use_for": "Small scoped edits (kimi \u22643 files), triage decisions and routing (allegro)."
+        "agents": ["kimi", "allegro"],
+        "use_for": "Small scoped edits (kimi ≤3 files), triage decisions and routing (allegro)."
       },
       {
         "tier": 3,
         "label": "Premium / Escalate",
-        "agents": [
-          "ezra"
-        ],
+        "agents": ["ezra"],
         "use_for": "Complex multi-file work, docs, architecture. Escalate only."
       }
     ],
@@ -238,48 +217,22 @@
       "allegro-primus: retired, do not route"
     ]
   },
+
   "task_type_map": {
-    "issue-triage": [
-      "fenrir",
-      "allegro"
-    ],
-    "code-generation": [
-      "carnice",
-      "ezra"
-    ],
-    "code-review": [
-      "bezalel"
-    ],
-    "small-edit": [
-      "kimi"
-    ],
-    "debugging": [
-      "bezalel",
-      "carnice"
-    ],
-    "documentation": [
-      "ezra"
-    ],
-    "architecture": [
-      "ezra"
-    ],
-    "ci-fixes": [
-      "bezalel"
-    ],
-    "pr-review": [
-      "bezalel",
-      "fenrir"
-    ],
-    "triage-routing": [
-      "allegro"
-    ],
-    "devops": [
-      "substratum"
-    ],
-    "background-monitoring": [
-      "bilbobagginshire"
-    ]
+    "issue-triage": ["fenrir", "allegro"],
+    "code-generation": ["carnice", "ezra"],
+    "code-review": ["bezalel"],
+    "small-edit": ["kimi"],
+    "debugging": ["bezalel", "carnice"],
+    "documentation": ["ezra"],
+    "architecture": ["ezra"],
+    "ci-fixes": ["bezalel"],
+    "pr-review": ["bezalel", "fenrir"],
+    "triage-routing": ["allegro"],
+    "devops": ["substratum"],
+    "background-monitoring": ["bilbobagginshire"]
   },
+
   "gaps": [
     {
       "agent": "substratum",
@@ -302,11 +255,12 @@
       "action": "Run wolf evaluation on active agents (#195) to replace vibes-based routing with data."
     }
   ],
+
   "next_actions": [
-    "Assign model to substratum \u2014 Epic #196",
-    "Run wolf evaluation on active agents \u2014 Issue #195",
-    "Remove claw-code from routing cascade \u2014 it is infrastructure, not a destination",
+    "Assign model to substratum — Epic #196",
+    "Run wolf evaluation on active agents — Issue #195",
+    "Remove claw-code from routing cascade — it is infrastructure, not a destination",
     "Enrich kimi's Gitea profile description",
-    "Wire fleet-routing.json into workforce-manager.py \u2014 Epic #204"
+    "Wire fleet-routing.json into workforce-manager.py — Epic #204"
   ]
-}
+}

fleet/hermes-trismegistus/lane.md

@@ -7,13 +7,13 @@
 
 ## Role
 
-Dedicated research and triage wizard. Kimi-native.
+Dedicated reasoning and architecture wizard. Claude-native.
 
 ## Routing
 
 Route to Hermes Trismegistus when:
 - Task requires deep architectural reasoning
-- Novel problem-solving that benefits from strong reasoning depth
+- Novel problem-solving that benefits from Claude's reasoning depth
 - Planning and design decisions for the fleet
 - Complex multi-step analysis that goes beyond code generation
 

portals.json

@@ -160,7 +160,7 @@
       }
     },
     "agents_present": [
-      "ezra"
+      "claude"
     ],
     "interaction_ready": true
   },