From faf172a91dceee6303265b2739b21a20d5e2c249 Mon Sep 17 00:00:00 2001
From: YeonGyu-Kim <code.yeon.gyu@gmail.com>
Date: Sat, 24 Jan 2026 15:40:24 +0900
Subject: [PATCH] fix(multimodal-looker): update fallback chain order (#1050)

New order:
1. google/gemini-3-flash
2. openai/gpt-5.2
3. zai-coding-plan/glm-4.6v
4. anthropic/claude-haiku-4-5
5. opencode/gpt-5-nano (FREE, ultimate fallback)

Co-authored-by: justsisyphus <justsisyphus@users.noreply.github.com>
---
 docs/configurations.md                            | 2 +-
 docs/guide/overview.md                            | 8 ++++----
 src/cli/__snapshots__/model-fallback.test.ts.snap | 6 +++---
 src/shared/model-requirements.ts                  | 6 +++---
 4 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/docs/configurations.md b/docs/configurations.md
index d58d7234..af5236b9 100644
--- a/docs/configurations.md
+++ b/docs/configurations.md
@@ -405,7 +405,7 @@ Each agent has a defined provider priority chain. The system tries providers in
 | **oracle** | `gpt-5.2` | openai → anthropic → google → github-copilot → opencode |
 | **librarian** | `big-pickle` | opencode → github-copilot → anthropic |
 | **explore** | `gpt-5-nano` | opencode → anthropic → github-copilot |
-| **multimodal-looker** | `gemini-3-flash` | google → anthropic → zai → openai → github-copilot → opencode |
+| **multimodal-looker** | `gemini-3-flash` | google → openai → zai-coding-plan → anthropic → opencode |
 | **Prometheus (Planner)** | `claude-opus-4-5` | anthropic → github-copilot → opencode → antigravity → google |
 | **Metis (Plan Consultant)** | `claude-sonnet-4-5` | anthropic → github-copilot → opencode → antigravity → google |
 | **Momus (Plan Reviewer)** | `claude-opus-4-5` | anthropic → github-copilot → opencode → antigravity → google |
diff --git a/docs/guide/overview.md b/docs/guide/overview.md
index c5449cb3..1cc27108 100644
--- a/docs/guide/overview.md
+++ b/docs/guide/overview.md
@@ -112,9 +112,9 @@ Each agent has a **provider priority chain**. The system tries providers in orde
 
 ```
 Example: multimodal-looker
-google → anthropic → zai → openai → github-copilot → opencode
-   ↓         ↓         ↓        ↓           ↓            ↓
-gemini   haiku     glm-4.6  gpt-5.2    fallback     fallback
+google → openai → zai-coding-plan → anthropic → opencode
+   ↓        ↓           ↓              ↓           ↓
+gemini   gpt-5.2     glm-4.6v       haiku     gpt-5-nano
 ```
 
 If you have Gemini, it uses `google/gemini-3-flash`. No Gemini but have Claude? Uses `anthropic/claude-haiku-4-5`. And so on.
@@ -131,7 +131,7 @@ Here's a real-world config for a user with **Claude, OpenAI, Gemini, and Z.ai**
     "Atlas": { "model": "anthropic/claude-sonnet-4-5", "variant": "max" },
     "librarian": { "model": "zai-coding-plan/glm-4.7" },
     "explore": { "model": "opencode/gpt-5-nano" },
-    "multimodal-looker": { "model": "zai-coding-plan/glm-4.6" }
+    "multimodal-looker": { "model": "zai-coding-plan/glm-4.6v" }
   },
   "categories": {
     // Override categories for cost optimization
diff --git a/src/cli/__snapshots__/model-fallback.test.ts.snap b/src/cli/__snapshots__/model-fallback.test.ts.snap
index 062b0251..5e857114 100644
--- a/src/cli/__snapshots__/model-fallback.test.ts.snap
+++ b/src/cli/__snapshots__/model-fallback.test.ts.snap
@@ -854,7 +854,7 @@ exports[`generateModelConfig fallback providers uses ZAI model for librarian whe
       "model": "opencode/big-pickle",
     },
     "multimodal-looker": {
-      "model": "zai-coding-plan/glm-4.6",
+      "model": "zai-coding-plan/glm-4.6v",
     },
     "oracle": {
       "model": "opencode/big-pickle",
@@ -912,7 +912,7 @@ exports[`generateModelConfig fallback providers uses ZAI model for librarian wit
       "model": "opencode/big-pickle",
     },
     "multimodal-looker": {
-      "model": "zai-coding-plan/glm-4.6",
+      "model": "zai-coding-plan/glm-4.6v",
     },
     "oracle": {
       "model": "opencode/big-pickle",
@@ -1099,7 +1099,7 @@ exports[`generateModelConfig mixed provider scenarios uses Claude + ZAI combinat
       "model": "anthropic/claude-opus-4-5",
     },
     "multimodal-looker": {
-      "model": "anthropic/claude-haiku-4-5",
+      "model": "zai-coding-plan/glm-4.6v",
     },
     "oracle": {
       "model": "anthropic/claude-opus-4-5",
diff --git a/src/shared/model-requirements.ts b/src/shared/model-requirements.ts
index cbc3bedd..33004152 100644
--- a/src/shared/model-requirements.ts
+++ b/src/shared/model-requirements.ts
@@ -41,10 +41,10 @@ export const AGENT_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
   "multimodal-looker": {
     fallbackChain: [
       { providers: ["google", "github-copilot", "opencode"], model: "gemini-3-flash" },
-      { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-haiku-4-5" },
-      { providers: ["zai-coding-plan"], model: "glm-4.6v" },
-      { providers: ["opencode"], model: "gpt-5-nano" },
       { providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2" },
+      { providers: ["zai-coding-plan"], model: "glm-4.6v" },
+      { providers: ["anthropic", "github-copilot", "opencode"], model: "claude-haiku-4-5" },
+      { providers: ["opencode"], model: "gpt-5-nano" },
     ],
   },
   prometheus: {