refactor(opencode): migrate workflow models to chat models

Update model identifiers across configuration files and commands to use
the new `duo-chat-*` model naming convention instead of
`duo-workflow-*`.
Also adds pricing configuration for new chat model variants
(gpt-5-4-mini and gpt-5-4-nano) and updates task reviewer type names to
use descriptive suffixes.

Author: Pedro Pombeiro

.config/dotfiles/gitlab/.opencode/commands/weekly-update.md

@@ -1,6 +1,6 @@
 ---
 description: Post weekly status updates on assigned milestone issues
-model: gitlab/duo-workflow-opus-4-6
+model: gitlab/duo-chat-opus-4-6
 ---
 
 Post weekly status updates on all GitLab issues assigned to me for the current milestone.

.config/opencode/agents/dotfiles.md

@@ -1,7 +1,7 @@
 ---
 description: "Use when the user mentions their dotfiles, dotfiles repo, dotfiles config, yadm, or references commits/changes in their personal configuration. Explores yadm-managed dotfiles in the home directory: find config files under ~/, search dotfile contents, look up agent docs, and inspect yadm git history (log, show, diff)."
 mode: subagent
-model: gitlab/duo-workflow-haiku-4-5
+model: gitlab/duo-chat-haiku-4-5
 hidden: true
 temperature: 0
 steps: 10

.config/opencode/commands/handoff.md

@@ -1,6 +1,6 @@
 ---
 description: Create handoff document for context transfer
-model: gitlab/duo-workflow-gpt-5-3-codex
+model: gitlab/duo-chat-gpt-5-3-codex
 ---
 
 Create a HANDOFF.md file in the current working directory to transfer context to a new agent session.

.config/opencode/commands/push.md

@@ -1,6 +1,6 @@
 ---
 description: Commit changes in logical commits and push
-model: gitlab/duo-workflow-haiku-4-5
+model: gitlab/duo-chat-haiku-4-5
 ---
 
 Commit all changes in discrete, logical commits and push to the remote.

.config/opencode/opencode.json##class.Work

@@ -27,7 +27,7 @@
     }
   },
   "enabled_providers": ["gitlab", "anthropic", "google"],
-  "small_model": "gitlab/duo-workflow-haiku-4-5",
+  "small_model": "gitlab/duo-chat-haiku-4-5",
   "provider": {
     "gitlab": {
       "models": {
@@ -72,11 +72,23 @@
         "duo-chat-haiku-4-5": {
           "cost": { "input": 1, "output": 5, "cache_read": 0.10, "cache_write": 1.25 }
         },
-        "duo-workflow-gpt-5-3-codex": {
+        "duo-chat-gpt-5-3-codex": {
           "cost": { "input": 1.75, "output": 14, "cache_read": 0.175 }
         },
-        "duo-workflow-gpt-5-4": {
+        "duo-chat-gpt-5-2-codex": {
+          "cost": { "input": 1.50, "output": 12, "cache_read": 0.15 }
+        },
+        "duo-chat-gpt-5-mini": {
+          "cost": { "input": 0.75, "output": 3, "cache_read": 0.075 }
+        },
+        "duo-chat-gpt-5-4": {
           "cost": { "input": 2.50, "output": 15, "cache_read": 0.25 }
+        },
+        "duo-chat-gpt-5-4-mini": {
+          "cost": { "input": 1.10, "output": 4.40, "cache_read": 0.11 }
+        },
+        "duo-chat-gpt-5-4-nano": {
+          "cost": { "input": 0.50, "output": 2.00, "cache_read": 0.05 }
         }
       }
     }
@@ -242,16 +254,19 @@
     "task": {
       "general": "allow",
       "explore": "allow",
-      "review-security": "allow",
-      "review-database": "allow",
-      "review-clickhouse": "allow",
-      "review-performance": "allow",
-      "review-qa": "allow",
-      "review-frontend": "allow",
-      "review-backend": "allow",
-      "review-docs": "allow",
-      "review-analytics": "allow",
-      "review-graphql": "allow"
+      "security-reviewer": "allow",
+      "database-reviewer": "allow",
+      "clickhouse-reviewer": "allow",
+      "performance-reviewer": "allow",
+      "qa-reviewer": "allow",
+      "frontend-reviewer": "allow",
+      "backend-reviewer": "allow",
+      "documentation-reviewer": "allow",
+      "analytics-reviewer": "allow",
+      "graphql-reviewer": "allow",
+      "rest-api-reviewer": "allow",
+      "workers-reviewer": "allow",
+      "feature-flags-reviewer": "allow"
     },
     "todowrite": "allow"
   }

.config/opencode/opencode.json##default

@@ -71,17 +71,23 @@
             "input": 15, "output": 75, "cache_read": 1.50, "cache_write": 18.75
           }
         },
-        "gitlab/duo-workflow-haiku-4-5": {
+        "duo-workflow-haiku-4-5": {
           "cost": { "input": 1, "output": 5, "cache_read": 0.10, "cache_write": 1.25 }
         },
         "duo-chat-haiku-4-5": {
           "cost": { "input": 1, "output": 5, "cache_read": 0.10, "cache_write": 1.25 }
         },
-        "duo-workflow-gpt-5-3-codex": {
+        "duo-chat-gpt-5-3-codex": {
           "cost": { "input": 1.75, "output": 14, "cache_read": 0.175 }
         },
-        "duo-workflow-gpt-5-4": {
+        "duo-chat-gpt-5-4": {
           "cost": { "input": 2.50, "output": 15, "cache_read": 0.25 }
+        },
+        "duo-chat-gpt-5-4-mini": {
+          "cost": { "input": 1.10, "output": 4.40, "cache_read": 0.11 }
+        },
+        "duo-chat-gpt-5-4-nano": {
+          "cost": { "input": 0.50, "output": 2.00, "cache_read": 0.05 }
         }
       }
     }

.config/yadm/scripts/update-work.zsh

@@ -143,7 +143,7 @@ ENABLE_SPRING = "1"
 GITLAB_USE_MODEL_LOAD_BALANCING = "1"
 GITLAB_VIM_URL = "https://gitlab.com"
 OP_BIOMETRIC_UNLOCK_ENABLED = "true"
-OPENCODE_MODEL = "gitlab/duo-workflow-opus-4-6"
+OPENCODE_MODEL = "gitlab/duo-chat-opus-4-6"
 PUMA_WORKER_TIMEOUT = "9999999"
 QA_GITLAB_URL = "http://gdk.test:3000"
 QA_LOG_LEVEL = "DEBUG"