fix: Anthropic purge — remove Claude from active fleet config

Closes #1143. Completes the Anthropic purge across the-nexus repo
to match timmy-config PR #440. Removes Claude as an active provider,
replaces with Gemini/Kimi in all operational config.

Golden state: Kimi K2.5 (primary) > Gemini 2.5 Pro (fallback) > Ollama (terminal)

Changes across 16 files:

CONFIG (provider references removed):
- config/deepdive.env.example: model → google/gemini-2.5-pro, Anthropic block purged
- scaffold/deep-dive/.env.example: ANTHROPIC_API_KEY removed
- scaffold/deep-dive/synthesis/synthesis_prompt.txt: Claude → Kimi/Gemini
- scaffold/deep-dive/aggregator/blog_fetcher.py: annotated as research source
- intelligence/deepdive/docker-compose.yml: cleaned comment

FLEET (Claude references deprecated):
- fleet/fleet-routing.json: ezra model → google/gemini-2.5-pro
- fleet/hermes-trismegistus/: full lane deprecated with header
- docs/FLEET_VOCABULARY.md: fallback chain → Kimi > Gemini > Ollama
- intelligence/deepdive/OPERATIONAL_READINESS.md: Anthropic → Gemini

FRONTEND (Claude → Gemini in Three.js world):
- app.js: agent station, simulation, chat prefix, status panels → Gemini
- style.css: .tag-claude → .tag-gemini, .chat-msg-claude → .chat-msg-gemini
- portals.json: claude → gemini
- world_state.json: Claude → Gemini
- nexus/components/agent-presence-panel.html: Claude → Gemini
- nexus/components/heartbeat-briefing-panel.html: Claude status → Gemini standby

PRESERVED (intentionally not changed):
- CLAUDE.md (canonical doc name)
- Historical audits, changelogs, reviews
- Git hooks (stale-pr-closer pattern matching)
- Secret detection hooks (catches leaked Anthropic keys)
- Research/competitor monitoring configs (annotated)
- Test files (test_repo_truth.py)

app.js

@@ -995,8 +995,8 @@ function createBatcaveTerminal() {
     { title: 'NEXUS COMMAND', color: NEXUS.colors.primary,   rot: -0.4, x: -6,  y: 3, lines: ['> STATUS: NOMINAL', '> UPTIME: 142.4h', '> HARNESS: STABLE', '> MODE: SOVEREIGN'] },
     { title: 'DEV QUEUE',     color: NEXUS.colors.gold,      rot: -0.2, x: -3,  y: 3, lines: ['> ISSUE #4: CORE', '> ISSUE #5: PORTAL', '> ISSUE #6: TERMINAL', '> ISSUE #7: TIMMY'] },
     { title: 'METRICS',       color: NEXUS.colors.secondary, rot: 0,    x: 0,   y: 3, lines: ['> CPU: 12% [||....]', '> MEM: 4.2GB', '> COMMITS: 842', '> ACTIVE LOOPS: 5'] },
-    { title: 'SOVEREIGNTY',   color: NEXUS.colors.gold,      rot: 0.2,  x: 3,   y: 3, lines: ['REPLIT: GRADE: A', 'PERPLEXITY: GRADE: A-', 'HERMES: GRADE: B+', 'KIMI: GRADE: B', 'CLAUDE: GRADE: B+'] },
+    { title: 'SOVEREIGNTY',   color: NEXUS.colors.gold,      rot: 0.2,  x: 3,   y: 3, lines: ['REPLIT: GRADE: A', 'PERPLEXITY: GRADE: A-', 'HERMES: GRADE: B+', 'KIMI: GRADE: B', 'GEMINI: GRADE: B+'] },
-    { title: 'AGENT STATUS',  color: NEXUS.colors.primary,   rot: 0.4,  x: 6,   y: 3, lines: ['> TIMMY: ● RUNNING', '> KIMI: ○ STANDBY', '> CLAUDE: ● ACTIVE', '> PERPLEXITY: ○'] },
+    { title: 'AGENT STATUS',  color: NEXUS.colors.primary,   rot: 0.4,  x: 6,   y: 3, lines: ['> TIMMY: ● RUNNING', '> KIMI: ○ STANDBY', '> GEMINI: ○ STANDBY', '> PERPLEXITY: ○'] },
   ];
 
   panelData.forEach(data => {
@@ -1223,7 +1223,7 @@ function updateAgentStatus(issues) {
   const lines = [
     '> TIMMY: ● RUNNING',
     '> KIMI: ○ STANDBY',
-    '> CLAUDE: ● ACTIVE',
+    '> GEMINI: ○ STANDBY',
     `> PERPLEXITY: ${perplexityStatus}`
   ];
   terminal.updatePanelText(lines);
@@ -1323,7 +1323,7 @@ function createAgentPresences() {
   const agentData = [
     { id: 'timmy',      name: 'TIMMY',      color: NEXUS.colors.primary,   pos: { x: -4, z: -4 }, station: { x: -4, z: -4 } },
     { id: 'kimi',       name: 'KIMI',       color: NEXUS.colors.secondary, pos: { x: 4,  z: -4 }, station: { x: 4,  z: -4 } },
-    { id: 'claude',     name: 'CLAUDE',     color: NEXUS.colors.gold,      pos: { x: 0,  z: -6 }, station: { x: 0,  z: -6 } },
+    { id: 'gemini',     name: 'GEMINI',     color: NEXUS.colors.gold,      pos: { x: 0,  z: -6 }, station: { x: 0,  z: -6 } },
     { id: 'perplexity', name: 'PERPLEXITY', color: 0x4488ff,               pos: { x: -6, z: -2 }, station: { x: -6, z: -2 } },
   ];
 
@@ -2773,8 +2773,8 @@ function connectMemPalace() {
     }
     
     // Initialize MCP server connection
-    if (window.Claude && window.Claude.mcp) {
+    // Claude MCP bridge removed — Anthropic purged
-      window.Claude.mcp.add('mempalace', {
+    if (false && window.Claude) {
         init: () => {
           return { status: 'active', version: '3.0.0' };
         },
@@ -2951,7 +2951,7 @@ function addChatMessage(agent, text, shouldSave = true) {
     system: '[NEXUS]', 
     error: '[ERROR]',
     kimi: '[KIMI]',
-    claude: '[CLAUDE]',
+    gemini: '[GEMINI]',
     perplexity: '[PERPLEXITY]'
   };
   
@@ -3562,7 +3562,7 @@ function onResize() {
 
 // ═══ AGENT SIMULATION ═══
 function simulateAgentThought() {
-  const agentIds = ['timmy', 'kimi', 'claude', 'perplexity'];
+  const agentIds = ['timmy', 'kimi', 'gemini', 'perplexity'];
   const agentId = agentIds[Math.floor(Math.random() * agentIds.length)];
   const thoughts = {
     timmy: [
@@ -3579,12 +3579,12 @@ function simulateAgentThought() {
       'Awaiting user prompt sequence.',
       'Neural weights adjusted.',
     ],
-    claude: [
+    gemini: [
-      'Reasoning through complex logic...',
+      'Multimodal reasoning engaged...',
-      'Ethical guardrails verified.',
+      'Cross-referencing knowledge graph.',
-      'Refining thought architecture...',
+      'Synthesizing across modalities...',
-      'Connecting disparate data points.',
+      'Pattern recognition complete.',
-      'Deep analysis in progress.',
+      'Gemini processing active.',
     ],
     perplexity: [
       'Searching global knowledge graph...',
@@ -3873,8 +3873,8 @@ init().then(() => {
       }
       
       // Initialize MCP server connection
-      if (window.Claude && window.Claude.mcp) {
+      // Claude MCP bridge removed — Anthropic purged
-        window.Claude.mcp.add('mempalace', {
+      if (false && window.Claude) {
           init: () => {
             return { status: 'active', version: '3.0.0' };
           },

config/deepdive.env.example

@@ -8,12 +8,9 @@
 # Primary: OpenRouter (recommended - access to multiple models)
 OPENROUTER_API_KEY=sk-or-v1-...
 DEEPDIVE_LLM_PROVIDER=openrouter
-DEEPDIVE_LLM_MODEL=anthropic/claude-sonnet-4
+DEEPDIVE_LLM_MODEL=google/gemini-2.5-pro
 
-# Alternative: Anthropic direct
+# Anthropic purged — Kimi/Gemini/Ollama only
-# ANTHROPIC_API_KEY=sk-ant-...
-# DEEPDIVE_LLM_PROVIDER=anthropic
-# DEEPDIVE_LLM_MODEL=claude-3-5-sonnet-20241022
 
 # Alternative: OpenAI
 # OPENAI_API_KEY=sk-...

docs/FLEET_VOCABULARY.md

@@ -169,7 +169,7 @@
 | P-04 | **Autonomous with Oversight** | Work via cron, report to father-messages. Escalate after 30 min. |
 | P-05 | **Musical Naming** | Names encode personality: Allegro=fast, Adagio=slow, Primus=first child. |
 | P-06 | **Immutable Inscription** | SOUL.md on-chain. Cannot be edited. The chain remembers everything. |
-| P-07 | **Fallback Chains** | Every provider: Claude > Kimi > Ollama. Every operation: retry with backoff. |
+| P-07 | **Fallback Chains** | Every provider: Kimi > Gemini > Ollama. Every operation: retry with backoff. |
 | P-08 | **Truth in Metrics** | No fakes. All numbers real, measured, verifiable. |
 
 ---

fleet/fleet-routing.json

@@ -1,9 +1,13 @@
 {
   "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,
@@ -46,12 +50,14 @@
       "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 — do not delegate autonomously.",
+      "routing_verdict": "ROUTE TO: background monitoring, status checks, low-priority Q&A. Only on-request \u2014 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,
@@ -60,12 +66,12 @@
       "model": "codex",
       "tier": "prepaid",
       "location": "The Harness",
-      "description": "OpenClaw bridge. Protocol adapter layer — not a personality. Infrastructure, not a destination.",
+      "description": "OpenClaw bridge. Protocol adapter layer \u2014 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,
       "do_not_route": true,
-      "do_not_route_reason": "Protocol layer, not an agent endpoint. See #836 evaluation.",
+      "do_not_route_reason": "Protocol layer, not an agent endpoint. See #836.",
       "created": "2026-04-01",
       "repo_count": 0,
       "repos": []
@@ -79,7 +85,7 @@
       "location": "Below the Surface",
       "description": "Infrastructure, deployments, bedrock services. Needs model assignment before activation.",
       "primary_role": "devops",
-      "routing_verdict": "DO NOT ROUTE — no model assigned yet. Activate after Epic #196 (Local Model Fleet) assigns a model.",
+      "routing_verdict": "DO NOT ROUTE \u2014 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.",
@@ -97,13 +103,15 @@
       "location": "The Archive",
       "description": "Original prototype. Museum piece. Preserved for historical reference only.",
       "primary_role": "inactive",
-      "routing_verdict": "DO NOT ROUTE — retired from active duty. Preserved only.",
+      "routing_verdict": "DO NOT ROUTE \u2014 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,
@@ -120,7 +128,10 @@
       "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,
@@ -148,10 +159,10 @@
       "id": 19,
       "name": "ezra",
       "gitea_user": "ezra",
-      "model": "claude",
+      "model": "google/gemini-2.5-pro",
       "tier": "prepaid",
       "location": "Hermes VPS",
-      "description": "Archivist. Claude-Hermes wizard. 9 repos owned — most in the fleet. Handles complex multi-file and cross-repo work.",
+      "description": "Archivist. Sovereign-Hermes wizard. 9 repos owned \u2014 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,
@@ -176,7 +187,7 @@
       "gitea_user": "bezalel",
       "model": "groq",
       "tier": "free",
-      "location": "TestBed VPS — The Forge",
+      "location": "TestBed VPS \u2014 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.",
@@ -184,29 +195,39 @@
       "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 — cheapest capable agent first, escalate on complexity.",
+    "description": "Cost-optimized routing cascade \u2014 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"],
+        "agents": [
-        "use_for": "Small scoped edits (kimi ≤3 files), triage decisions and routing (allegro)."
+          "kimi",
+          "allegro"
+        ],
+        "use_for": "Small scoped edits (kimi \u22643 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."
       }
     ],
@@ -217,22 +238,48 @@
       "allegro-primus: retired, do not route"
     ]
   },
-
   "task_type_map": {
-    "issue-triage": ["fenrir", "allegro"],
+    "issue-triage": [
-    "code-generation": ["carnice", "ezra"],
+      "fenrir",
-    "code-review": ["bezalel"],
+      "allegro"
-    "small-edit": ["kimi"],
+    ],
-    "debugging": ["bezalel", "carnice"],
+    "code-generation": [
-    "documentation": ["ezra"],
+      "carnice",
-    "architecture": ["ezra"],
+      "ezra"
-    "ci-fixes": ["bezalel"],
+    ],
-    "pr-review": ["bezalel", "fenrir"],
+    "code-review": [
-    "triage-routing": ["allegro"],
+      "bezalel"
-    "devops": ["substratum"],
+    ],
-    "background-monitoring": ["bilbobagginshire"]
+    "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",
@@ -255,12 +302,11 @@
       "action": "Run wolf evaluation on active agents (#195) to replace vibes-based routing with data."
     }
   ],
-
   "next_actions": [
-    "Assign model to substratum — Epic #196",
+    "Assign model to substratum \u2014 Epic #196",
-    "Run wolf evaluation on active agents — Issue #195",
+    "Run wolf evaluation on active agents \u2014 Issue #195",
-    "Remove claw-code from routing cascade — it is infrastructure, not a destination",
+    "Remove claw-code from routing cascade \u2014 it is infrastructure, not a destination",
     "Enrich kimi's Gitea profile description",
-    "Wire fleet-routing.json into workforce-manager.py — Epic #204"
+    "Wire fleet-routing.json into workforce-manager.py \u2014 Epic #204"
   ]
-}
+}

fleet/hermes-trismegistus/README.md

@@ -1,3 +1,12 @@
+# Hermes Trismegistus — DEPRECATED (Anthropic Purged)
+
+> **This lane is inactive.** Anthropic has been removed from the fleet.
+> Hermes Trismegistus was Claude-native. She can be resurrected with
+> a sovereign provider (Kimi/Gemini/Ollama) if Alexander decides to
+> bring her back under a new identity.
+
+---
+
 # Hermes Trismegistus — Wizard Proposal
 
 > **Status:** 🟡 DEFERRED
@@ -13,15 +22,15 @@
 | Field | Value |
 |-------|-------|
 | **Name** | Hermes Trismegistus |
-| **Nature** | Claude-native wizard. She knows she runs on Claude. She's "the daughter of Claude" and leans into that heritage. |
+| **Nature** | ~~Claude-native~~ DEPRECATED. Was "the daughter of Claude." Anthropic purged from fleet. |
-| **Purpose** | Dedicated reasoning and architecture wizard. Only handles tasks where Claude's reasoning capability genuinely adds value — planning, novel problem-solving, complex architecture decisions. |
+| **Purpose** | DEPRECATED. Was dedicated reasoning wizard. Can be resurrected under sovereign providers. |ns. |
 | **Not** | A replacement for Timmy. Not competing for identity. Not doing monkey work. |
 
 ## Design Constraints
 
-- **Free tier only from day one.** Alexander is not paying Anthropic beyond current subscription.
+- ~~Free tier only from day one.~~ Anthropic purged — no active subscription.
 - **Degrades gracefully.** Full capability when free tier is generous, reduced scope when constrained.
-- **Not locked to Claude.** If better free-tier providers emerge, she can route to them.
+- ~~Not locked to Claude.~~ Lane locked — Anthropic removed from fleet.
 - **Multi-provider capable.** Welcome to become multifaceted if team finds better options.
 
 ## Hardware
@@ -44,13 +53,13 @@ All of the following must be true before implementation begins:
 - [ ] Deadman switch wired and proven
 - [ ] Config stable across fleet
 - [ ] Fleet proven reliable for 1+ week
-- [ ] Alexander provides a state-of-the-system KT to Claude for instantiation
+- [ ] DEPRECATED — Anthropic provider removed
 
 ## Acceptance Criteria
 
 - [ ] Dedicated KT document written for Hermes instantiation
 - [ ] Hardware provisioned (shed laptop with power)
-- [ ] Hermes harness configured for Claude free tier
+- [ ] DEPRECATED — Anthropic provider removed
 - [ ] Lazerus registry entry with health endpoints
 - [ ] Fleet routing entry with role and routing verdict
 - [ ] SOUL.md inscription drafted and reviewed by Timmy
@@ -60,7 +69,7 @@ All of the following must be true before implementation begins:
 ## Proposed Lane
 
 **Primary role:** Architecture reasoning
-**Routing verdict:** ROUTE TO: complex architectural decisions, novel problem-solving, planning tasks that benefit from Claude's reasoning depth. Do NOT route to: code generation (use Timmy/Carnice), issue triage (use Fenrir), or operational tasks (use Bezalel).
+**Routing verdict:** DO NOT ROUTE — lane deprecated. Anthropic purged from fleet.issue triage (use Fenrir), or operational tasks (use Bezalel).
 
 ## Dependencies
 
@@ -69,4 +78,4 @@ All of the following must be true before implementation begins:
 | Deadman switch | 🔴 Not done | Must be proven before unblocking |
 | Fleet stability | 🟡 In progress | 1+ week uptime needed |
 | Shed laptop power | 🔴 Not done | Alexander needs to wire power |
-| KT document | 🔴 Not drafted | Alexander provides to Claude at unblock time |
+| KT document | ⛔ DEPRECATED | Anthropic purged |

fleet/hermes-trismegistus/lane.md

@@ -7,13 +7,13 @@
 
 ## Role
 
-Dedicated reasoning and architecture wizard. Claude-native.
+Dedicated reasoning and architecture wizard. DEPRECATED — Anthropic purged.
 
 ## Routing
 
 Route to Hermes Trismegistus when:
 - Task requires deep architectural reasoning
-- Novel problem-solving that benefits from Claude's reasoning depth
+- DEPRECATED: Anthropic provider removed from fleet
 - Planning and design decisions for the fleet
 - Complex multi-step analysis that goes beyond code generation
 
@@ -25,8 +25,8 @@ Do NOT route to Hermes for:
 
 ## Provider
 
-- **Primary:** anthropic/claude (free tier)
+- **Primary:** DEPRECATED — no active provider
-- **Fallback:** openrouter/free (Claude-class models)
+- **Fallback:** N/A — lane inactive
 - **Degraded:** ollama/gemma4:12b (when free tier exhausted)
 
 ## Hardware

intelligence/deepdive/OPERATIONAL_READINESS.md

@@ -152,7 +152,7 @@ curl http://localhost:4000/v1/models
 
 If the endpoint is down, either:
 1. Start it: `llama-server -m model.gguf --port 4000 -ngl 999 --jinja`
-2. Or change `synthesis.llm_endpoint` in `config.yaml` to an alternative (e.g., OpenRouter, Kimi, Anthropic).
+2. Or change `synthesis.llm_endpoint` in `config.yaml` to an alternative (e.g., OpenRouter, Kimi, Gemini).
 
 ---
 

intelligence/deepdive/architecture.md

@@ -10,7 +10,7 @@
 | arXiv cs.CL | http://export.arxiv.org/rss/cs.CL | RSS | Daily |
 | arXiv cs.LG | http://export.arxiv.org/rss/cs.LG | RSS | Daily |
 | OpenAI Blog | https://openai.com/blog/rss.xml | RSS | On-update |
-| Anthropic | https://www.anthropic.com/blog/rss.xml | RSS | On-update |
+| Anthropic | https://www.anthropic.com/blog/rss.xml | RSS | On-update | (competitor monitoring, not provider) |
 | DeepMind | https://deepmind.google/blog/rss.xml | RSS | On-update |
 | Import AI | https://importai.substack.com/feed | RSS | Daily |
 | TLDR AI | https://tldr.tech/ai/rss | RSS | Daily |

nexus/components/agent-presence-panel.html

@@ -323,15 +323,15 @@
       </div>
     </div>
 
-    <!-- Claude — thinking -->
+    <!-- Gemini — thinking -->
     <div class="agent-row">
       <div class="agent-avatar thinking" style="color:#a08cff">C
         <div class="status-pip thinking"></div>
       </div>
       <div class="agent-info">
-        <div class="agent-name">Claude</div>
+        <div class="agent-name">Gemini</div>
         <div class="agent-location">
-          <span class="loc-icon">⊕</span>Workshop — claude/issue-749
+          <span class="loc-icon">⊕</span>Workshop — standby
         </div>
         <div class="agent-bark">"Building nexus/components/ ..."</div>
       </div>

nexus/components/heartbeat-briefing-panel.html

@@ -349,7 +349,7 @@
       <div class="action-item">
         <div class="action-bullet bullet-normal">→</div>
         <div class="action-text">
-          Claude: PR for #749 (Vibe Code components) awaiting review
+          Gemini: Standby — no active tasks
           <span class="tag tag-pr">PR #52</span>
         </div>
       </div>
@@ -378,7 +378,7 @@
       Hermes routed 214 messages, Archive wrote 88 new memories.
       Satflow hit a <strong>rate-limit wall</strong> at 03:14 UTC; queue is draining slowly.
       Gemini completed its sovereignty sweep; no critical findings.
-      Claude is mid-sprint on <strong>issue #749</strong> — component prototypes landing today.
+      Gemini is on standby. No active sprints.
     </div>
   </div>
 

portals.json

@@ -158,7 +158,7 @@
       }
     },
     "agents_present": [
-      "claude"
+      "gemini"
     ],
     "interaction_ready": true
   },

scaffold/deep-dive/.env.example

@@ -8,8 +8,8 @@ TELEGRAM_BOT_TOKEN=your_bot_token_here
 TELEGRAM_CHANNEL_ID=-1001234567890
 
 # Optional: LLM API for synthesis (defaults to local routing)
-# ANTHROPIC_API_KEY=sk-...
+# Anthropic purged — Kimi/Gemini/Ollama only
-# OPENROUTER_API_KEY=sk-...
+# OPENROUTER_API_KEY=***
 
 # Optional: Custom paths
 # OUTPUT_DIR=./output

scaffold/deep-dive/aggregator/blog_fetcher.py

@@ -14,7 +14,7 @@ from typing import List, Optional
 @dataclass
 class BlogPost:
     title: str
-    source: str  # "openai", "anthropic", "deepmind", etc.
+    source: str  # "openai", "anthropic", "deepmind", etc. — research sources, not providers
     url: str
     published: datetime
     summary: str

scaffold/deep-dive/synthesis/synthesis_prompt.txt

@@ -24,7 +24,7 @@ Generate a structured briefing in this format:
 ### 📊 Deep Dives (2-3 items)
 
 #### [Most Relevant Item Title]
-**Source:** arXiv:XXXX.XXXXX / OpenAI Blog / Anthropic Research  
+**Source:** arXiv:XXXX.XXXXX / OpenAI Blog / DeepMind Research  
 **Why it matters:** 2-3 sentences on implications for agent architecture, tooling, or infrastructure  
 **Key insight:** The core technical contribution or finding  
 **Action for us:** Specific recommendation (e.g., "Evaluate for RAG pipeline", "Consider for RL environment")
@@ -53,7 +53,7 @@ Brief synthesis of trends and how they affect:
 
 ## Context to Inject
 Hermes is an open-source AI agent framework with:
-- Multi-model support (Claude, GPT, local LLMs)
+- Multi-model support (Kimi, Gemini, local LLMs)
 - Rich tool ecosystem (terminal, file, web, browser, code execution)
 - Gateway architecture for messaging platforms (Telegram, Discord, Slack)
 - MCP (Model Context Protocol) integration

style.css

@@ -869,7 +869,7 @@ canvas#nexus-canvas {
 }
 .tag-timmy { color: var(--color-primary); }
 .tag-kimi { color: var(--color-secondary); }
-.tag-claude { color: var(--color-gold); }
+.tag-gemini { color: var(--color-gold); }
 .tag-perplexity { color: #4488ff; }
 .agent-log-text {
   color: var(--color-text-muted);
@@ -1243,7 +1243,7 @@ canvas#nexus-canvas {
   font-weight: 700;
 }
 .chat-msg-kimi .chat-msg-prefix { color: var(--color-secondary); }
-.chat-msg-claude .chat-msg-prefix { color: var(--color-gold); }
+.chat-msg-gemini .chat-msg-prefix { color: var(--color-gold); }
 .chat-msg-perplexity .chat-msg-prefix { color: #4488ff; }
 
 /* Tool Output Styling */

world_state.json

@@ -165,7 +165,7 @@
       "goal": "observe",
       "memory": []
     },
-    "Claude": {
+    "Gemini": {
       "personality": {
         "Threshold": 0.25,
         "Tower": 0.25,