fix(ci): resolve all test failures + complete rename compat layer

Sisyphus-authored fixes across 15 files:

- plugin-identity: align CONFIG_BASENAME with actual config file name
- add-plugin-to-opencode-config: handle legacy→canonical name migration
- plugin-detection tests: update expectations for new identity constants
- doctor/system: fix legacy name warning test assertions
- install tests: align with new plugin name
- chat-params tests: fix mock isolation
- model-capabilities tests: fix snapshot expectations
- image-converter: fix platform-dependent test assertions (Linux CI)
- example configs: expanded with more detailed comments

Full suite: 4484 pass, 0 fail, typecheck clean.

docs/examples/planning-focused.jsonc

@@ -1,56 +1,112 @@
-// oh-my-openagent planning-focused configuration
-// Optimized for large projects: Prometheus planning → Atlas orchestration.
-// Uses Opus for planning and review, Sonnet for implementation.
 {
+  "$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/dev/assets/oh-my-opencode.schema.json",
+
+  // Optimized for strategic planning, architecture, and complex project design.
+  // Prioritizes deep thinking agents and thorough analysis before execution.
+
   "agents": {
-    // Sisyphus with Sonnet — reliable implementation
+    // Orchestrator: delegates to planning agents first
     "sisyphus": {
-      "model": "anthropic/claude-sonnet-4-6",
-      "variant": "max"
-    },
-
-    // Hephaestus as alternative worker
-    "hephaestus": {
-      "model": "openai/gpt-5.3-codex"
-    },
-
-    // Atlas with Opus — strong orchestration and task decomposition
-    "atlas": {
       "model": "anthropic/claude-opus-4-6",
-      "variant": "max",
-      "prompt_append": "Leverage quick & deep agents in parallel when tasks are independent."
+      "ultrawork": { "model": "anthropic/claude-opus-4-6", "variant": "max" },
+      "prompt_append": "Always consult prometheus and atlas for planning. Never rush to implementation.",
     },
 
-    // Prometheus with Opus — best planning quality
+    // Implementation: uses planning outputs
+    "hephaestus": {
+      "model": "openai/gpt-5.3-codex",
+      "prompt_append": "Follow established plans precisely. Ask for clarification when plans are ambiguous.",
+    },
+
+    // Primary planner: deep interview mode
     "prometheus": {
       "model": "anthropic/claude-opus-4-6",
-      "variant": "max",
-      "prompt_append": "Leverage quick & deep agents in parallel when tasks are independent."
+      "thinking": { "type": "enabled", "budgetTokens": 160000 },
+      "prompt_append": "Interview extensively. Question assumptions. Build exhaustive plans with milestones, risks, and contingencies. Use deep & quick agents heavily in parallel for research.",
     },
 
-    // Support agents
-    "explore": {
-      "model": "anthropic/claude-haiku-4-5"
+    // Architecture consultant
+    "oracle": {
+      "model": "openai/gpt-5.4",
+      "variant": "xhigh",
+      "thinking": { "type": "enabled", "budgetTokens": 120000 },
     },
-    "librarian": {
-      "model": "anthropic/claude-haiku-4-5"
-    }
+
+    // Research and documentation
+    "librarian": { "model": "google/gemini-3-flash" },
+
+    // Exploration for research phase
+    "explore": { "model": "github-copilot/grok-code-fast-1" },
+
+    // Visual planning and diagrams
+    "multimodal-looker": { "model": "google/gemini-3.1-pro", "variant": "high" },
+
+    // Plan review and refinement: heavily utilized
+    "metis": {
+      "model": "anthropic/claude-opus-4-6",
+      "prompt_append": "Critically evaluate plans. Identify gaps, risks, and improvements. Be thorough.",
+    },
+
+    // Critic: challenges assumptions
+    "momus": {
+      "model": "openai/gpt-5.4",
+      "prompt_append": "Challenge all assumptions in plans. Look for edge cases, failure modes, and overlooked requirements.",
+    },
+
+    // Long-running planning sessions
+    "atlas": {
+      "prompt_append": "Preserve context across long planning sessions. Track evolving decisions.",
+    },
+
+    // Quick research tasks
+    "sisyphus-junior": { "model": "opencode/gpt-5-nano" },
   },
 
   "categories": {
-    "quick": {
-      "model": "anthropic/claude-sonnet-4-6",
-      "description": "Scaffolding, config changes, simple fixes"
-    },
-    "deep": {
-      "model": "anthropic/claude-sonnet-4-6",
-      "variant": "max",
-      "description": "Core module implementation, refactoring"
-    },
+    "quick": { "model": "opencode/gpt-5-nano" },
+
+    "unspecified-low": { "model": "anthropic/claude-sonnet-4-6" },
+
+    // High-effort planning tasks: maximum reasoning
     "unspecified-high": {
-      "model": "anthropic/claude-opus-4-6",
-      "variant": "max",
-      "description": "High-stakes tasks requiring maximum quality"
-    }
-  }
+      "model": "openai/gpt-5.4",
+      "variant": "xhigh",
+    },
+
+    // Documentation from plans
+    "writing": { "model": "google/gemini-3-flash" },
+
+    // Visual architecture
+    "visual-engineering": { "model": "google/gemini-3.1-pro", "variant": "high" },
+
+    // Deep research and analysis
+    "deep": { "model": "openai/gpt-5.3-codex" },
+
+    // Strategic reasoning
+    "ultrabrain": { "model": "openai/gpt-5.4", "variant": "xhigh" },
+
+    // Creative approaches to problems
+    "artistry": { "model": "google/gemini-3.1-pro", "variant": "high" },
+  },
+
+  // Moderate concurrency: planning is sequential by nature
+  "background_task": {
+    "defaultConcurrency": 5,
+    "staleTimeoutMs": 300000,
+    "providerConcurrency": {
+      "anthropic": 3,
+      "openai": 3,
+    },
+    "modelConcurrency": {
+      "anthropic/claude-opus-4-6": 2,
+      "openai/gpt-5.4": 2,
+    },
+  },
+
+  "sisyphus_agent": {
+    "planner_enabled": true,
+    "replace_plan": true,
+  },
+
+  "experimental": { "aggressive_truncation": true },
 }