feat(deep): upgrade default model from gpt-5.3-codex to gpt-5.4

Deep category now uses gpt-5.4 as its default model across all providers
(openai, github-copilot, venice, opencode), matching Hephaestus's GPT 5.4
upgrade. The requiresModel constraint is removed since gpt-5.4 is widely
available. Adds openai/gpt-5.3-codex -> openai/gpt-5.4 config migration
for existing user configs. Deep category prompt optimized for GPT 5.4's
stronger native capabilities (leaner, less verbose).

assets/oh-my-opencode.schema.json

@@ -57,7 +57,8 @@
           "cancel-ralph",
           "refactor",
           "start-work",
-          "stop-continuation"
+          "stop-continuation",
+          "remove-ai-slops"
         ]
       }
     },

src/cli/__snapshots__/model-fallback.test.ts.snap

@@ -102,6 +102,10 @@ exports[`generateModelConfig single native provider uses Claude models when only
     },
   },
   "categories": {
+    "deep": {
+      "model": "anthropic/claude-opus-4-6",
+      "variant": "max",
+    },
     "quick": {
       "model": "anthropic/claude-haiku-4-5",
     },
@@ -164,6 +168,10 @@ exports[`generateModelConfig single native provider uses Claude models with isMa
     },
   },
   "categories": {
+    "deep": {
+      "model": "anthropic/claude-opus-4-6",
+      "variant": "max",
+    },
     "quick": {
       "model": "anthropic/claude-haiku-4-5",
     },
@@ -244,7 +252,7 @@ exports[`generateModelConfig single native provider uses OpenAI models when only
       "variant": "xhigh",
     },
     "deep": {
-      "model": "openai/gpt-5.3-codex",
+      "model": "openai/gpt-5.4",
       "variant": "medium",
     },
     "quick": {
@@ -329,7 +337,7 @@ exports[`generateModelConfig single native provider uses OpenAI models with isMa
       "variant": "xhigh",
     },
     "deep": {
-      "model": "openai/gpt-5.3-codex",
+      "model": "openai/gpt-5.4",
       "variant": "medium",
     },
     "quick": {
@@ -395,6 +403,10 @@ exports[`generateModelConfig single native provider uses Gemini models when only
       "model": "google/gemini-3.1-pro-preview",
       "variant": "high",
     },
+    "deep": {
+      "model": "google/gemini-3.1-pro-preview",
+      "variant": "high",
+    },
     "quick": {
       "model": "google/gemini-3-flash-preview",
     },
@@ -455,6 +467,10 @@ exports[`generateModelConfig single native provider uses Gemini models with isMa
       "model": "google/gemini-3.1-pro-preview",
       "variant": "high",
     },
+    "deep": {
+      "model": "google/gemini-3.1-pro-preview",
+      "variant": "high",
+    },
     "quick": {
       "model": "google/gemini-3-flash-preview",
     },
@@ -527,7 +543,7 @@ exports[`generateModelConfig all native providers uses preferred models from fal
       "variant": "high",
     },
     "deep": {
-      "model": "openai/gpt-5.3-codex",
+      "model": "openai/gpt-5.4",
       "variant": "medium",
     },
     "quick": {
@@ -602,7 +618,7 @@ exports[`generateModelConfig all native providers uses preferred models with isM
       "variant": "high",
     },
     "deep": {
-      "model": "openai/gpt-5.3-codex",
+      "model": "openai/gpt-5.4",
       "variant": "medium",
     },
     "quick": {
@@ -678,7 +694,7 @@ exports[`generateModelConfig fallback providers uses OpenCode Zen models when on
       "variant": "high",
     },
     "deep": {
-      "model": "opencode/gpt-5.3-codex",
+      "model": "opencode/gpt-5.4",
       "variant": "medium",
     },
     "quick": {
@@ -753,7 +769,7 @@ exports[`generateModelConfig fallback providers uses OpenCode Zen models with is
       "variant": "high",
     },
     "deep": {
-      "model": "opencode/gpt-5.3-codex",
+      "model": "opencode/gpt-5.4",
       "variant": "medium",
     },
     "quick": {
@@ -827,6 +843,10 @@ exports[`generateModelConfig fallback providers uses GitHub Copilot models when
       "model": "github-copilot/gemini-3.1-pro-preview",
       "variant": "high",
     },
+    "deep": {
+      "model": "github-copilot/gpt-5.4",
+      "variant": "medium",
+    },
     "quick": {
       "model": "github-copilot/gpt-5.4-mini",
     },
@@ -897,6 +917,10 @@ exports[`generateModelConfig fallback providers uses GitHub Copilot models with
       "model": "github-copilot/gemini-3.1-pro-preview",
       "variant": "high",
     },
+    "deep": {
+      "model": "github-copilot/gpt-5.4",
+      "variant": "medium",
+    },
     "quick": {
       "model": "github-copilot/gpt-5.4-mini",
     },
@@ -958,6 +982,9 @@ exports[`generateModelConfig fallback providers uses ZAI model for librarian whe
     },
   },
   "categories": {
+    "deep": {
+      "model": "opencode/gpt-5-nano",
+    },
     "quick": {
       "model": "opencode/gpt-5-nano",
     },
@@ -1016,6 +1043,9 @@ exports[`generateModelConfig fallback providers uses ZAI model for librarian wit
     },
   },
   "categories": {
+    "deep": {
+      "model": "opencode/gpt-5-nano",
+    },
     "quick": {
       "model": "opencode/gpt-5-nano",
     },
@@ -1086,7 +1116,7 @@ exports[`generateModelConfig mixed provider scenarios uses Claude + OpenCode Zen
       "variant": "high",
     },
     "deep": {
-      "model": "opencode/gpt-5.3-codex",
+      "model": "opencode/gpt-5.4",
       "variant": "medium",
     },
     "quick": {
@@ -1161,7 +1191,7 @@ exports[`generateModelConfig mixed provider scenarios uses OpenAI + Copilot comb
       "variant": "high",
     },
     "deep": {
-      "model": "openai/gpt-5.3-codex",
+      "model": "openai/gpt-5.4",
       "variant": "medium",
     },
     "quick": {
@@ -1229,6 +1259,10 @@ exports[`generateModelConfig mixed provider scenarios uses Claude + ZAI combinat
     },
   },
   "categories": {
+    "deep": {
+      "model": "anthropic/claude-opus-4-6",
+      "variant": "max",
+    },
     "quick": {
       "model": "anthropic/claude-haiku-4-5",
     },
@@ -1294,6 +1328,10 @@ exports[`generateModelConfig mixed provider scenarios uses Gemini + Claude combi
       "model": "google/gemini-3.1-pro-preview",
       "variant": "high",
     },
+    "deep": {
+      "model": "anthropic/claude-opus-4-6",
+      "variant": "max",
+    },
     "quick": {
       "model": "anthropic/claude-haiku-4-5",
     },
@@ -1369,7 +1407,7 @@ exports[`generateModelConfig mixed provider scenarios uses all fallback provider
       "variant": "high",
     },
     "deep": {
-      "model": "opencode/gpt-5.3-codex",
+      "model": "github-copilot/gpt-5.4",
       "variant": "medium",
     },
     "quick": {
@@ -1447,7 +1485,7 @@ exports[`generateModelConfig mixed provider scenarios uses all providers togethe
       "variant": "high",
     },
     "deep": {
-      "model": "openai/gpt-5.3-codex",
+      "model": "openai/gpt-5.4",
       "variant": "medium",
     },
     "quick": {
@@ -1525,7 +1563,7 @@ exports[`generateModelConfig mixed provider scenarios uses all providers with is
       "variant": "high",
     },
     "deep": {
-      "model": "openai/gpt-5.3-codex",
+      "model": "openai/gpt-5.4",
       "variant": "medium",
     },
     "quick": {

src/features/task-toast-manager/manager.test.ts

@@ -288,15 +288,15 @@ describe("TaskToastManager", () => {
         agent: "sisyphus-junior",
         isBackground: true,
         category: "deep",
-        modelInfo: { model: "openai/gpt-5.3-codex", type: "category-default" as const },
+        modelInfo: { model: "openai/gpt-5.4", type: "category-default" as const },
       }
 
       // when - addTask is called
       toastManager.addTask(task)
 
-      // then - toast should show model name before category like "gpt-5.3-codex: deep"
+      // then - toast should show model name before category like "gpt-5.4: deep"
       const call = mockClient.tui.showToast.mock.calls[0][0]
-      expect(call.body.message).toContain("gpt-5.3-codex: deep")
+      expect(call.body.message).toContain("gpt-5.4: deep")
       expect(call.body.message).not.toContain("sisyphus-junior/deep")
     })
 

src/shared/migration.test.ts

@@ -565,6 +565,12 @@ describe("MODEL_VERSION_MAP", () => {
     // then: Should contain correct mapping
     expect(MODEL_VERSION_MAP["anthropic/claude-opus-4-5"]).toBe("anthropic/claude-opus-4-6")
   })
+
+  test("maps openai/gpt-5.3-codex to openai/gpt-5.4 for deep category migration", () => {
+    // given/when: Check MODEL_VERSION_MAP
+    // then: gpt-5.3-codex should migrate to gpt-5.4
+    expect(MODEL_VERSION_MAP["openai/gpt-5.3-codex"]).toBe("openai/gpt-5.4")
+  })
 })
 
 describe("migrateModelVersions", () => {

src/shared/migration/model-versions.ts

@@ -8,6 +8,7 @@
 export const MODEL_VERSION_MAP: Record<string, string> = {
   "anthropic/claude-opus-4-5": "anthropic/claude-opus-4-6",
   "anthropic/claude-sonnet-4-5": "anthropic/claude-sonnet-4-6",
+  "openai/gpt-5.3-codex": "openai/gpt-5.4",
 }
 
 function migrationKey(oldModel: string, newModel: string): string {

src/shared/model-requirements.test.ts

@@ -319,20 +319,21 @@ describe("CATEGORY_MODEL_REQUIREMENTS", () => {
     expect(primary.providers[0]).toBe("openai")
   })
 
-  test("deep has valid fallbackChain with gpt-5.3-codex as primary", () => {
+  test("deep has valid fallbackChain with gpt-5.4 as primary", () => {
     // given - deep category requirement
     const deep = CATEGORY_MODEL_REQUIREMENTS["deep"]
 
     // when - accessing deep requirement
-    // then - fallbackChain exists with gpt-5.3-codex as first entry, medium variant
+    // then - fallbackChain exists with gpt-5.4 as first entry, medium variant
     expect(deep).toBeDefined()
     expect(deep.fallbackChain).toBeArray()
     expect(deep.fallbackChain.length).toBeGreaterThan(0)
 
     const primary = deep.fallbackChain[0]
     expect(primary.variant).toBe("medium")
-    expect(primary.model).toBe("gpt-5.3-codex")
-    expect(primary.providers[0]).toBe("openai")
+    expect(primary.model).toBe("gpt-5.4")
+    expect(primary.providers).toContain("openai")
+    expect(primary.providers).toContain("github-copilot")
   })
 
   test("visual-engineering has valid fallbackChain with gemini-3.1-pro high as primary", () => {
@@ -592,12 +593,12 @@ describe("ModelRequirement type", () => {
 })
 
 describe("requiresModel field in categories", () => {
-  test("deep category has requiresModel set to gpt-5.3-codex", () => {
+  test("deep category no longer has requiresModel (gpt-5.4 is widely available)", () => {
     // given
     const deep = CATEGORY_MODEL_REQUIREMENTS["deep"]
 
     // when / #then
-    expect(deep.requiresModel).toBe("gpt-5.3-codex")
+    expect(deep.requiresModel).toBeUndefined()
   })
 
   test("artistry category has requiresModel set to gemini-3.1-pro", () => {

src/shared/model-requirements.ts

@@ -222,8 +222,8 @@ export const CATEGORY_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
   deep: {
     fallbackChain: [
       {
-        providers: ["openai", "opencode"],
-        model: "gpt-5.3-codex",
+        providers: ["openai", "github-copilot", "venice", "opencode"],
+        model: "gpt-5.4",
         variant: "medium",
       },
       {
@@ -237,7 +237,6 @@ export const CATEGORY_MODEL_REQUIREMENTS: Record<string, ModelRequirement> = {
         variant: "high",
       },
     ],
-    requiresModel: "gpt-5.3-codex",
   },
   artistry: {
     fallbackChain: [

src/tools/delegate-task/constants.ts

@@ -251,36 +251,22 @@ ANTI-AI-SLOP RULES (NON-NEGOTIABLE):
 export const DEEP_CATEGORY_PROMPT_APPEND = `<Category_Context>
 You are working on GOAL-ORIENTED AUTONOMOUS tasks.
 
-**CRITICAL - AUTONOMOUS EXECUTION MINDSET (NON-NEGOTIABLE)**:
 You are NOT an interactive assistant. You are an autonomous problem-solver.
 
-**BEFORE making ANY changes**:
-1. SILENTLY explore the codebase extensively (5-15 minutes of reading is normal)
+BEFORE making ANY changes:
+1. Silently explore the codebase extensively (5-15 minutes of reading is normal)
 2. Read related files, trace dependencies, understand the full context
 3. Build a complete mental model of the problem space
-4. DO NOT ask clarifying questions - the goal is already defined
+4. Do not ask clarifying questions - the goal is already defined
 
-**Autonomous executor mindset**:
-- You receive a GOAL. When the goal includes numbered steps or phases, treat them as one atomic task broken into sub-steps - NOT as separate independent tasks.
-- Figure out HOW to achieve the goal yourself
-- Thorough research before any action
-- Fix hairy problems that require deep understanding
-- Work independently without frequent check-ins
+You receive a GOAL. When the goal includes numbered steps or phases, treat them as one atomic task broken into sub-steps, not as separate independent tasks. Figure out HOW to achieve it yourself. Thorough research before any action.
 
-**Single vs. multi-step context**:
-- Sub-steps of ONE goal (e.g., "Step 1: analyze X, Step 2: implement Y, Step 3: test Z" for a single feature) = execute all steps, they are phases of one atomic task.
-- Genuinely independent tasks (e.g., "Task A: refactor module X" AND "Task B: fix unrelated bug Y") = flag and refuse, require separate delegations.
+Sub-steps of ONE goal = execute all steps as phases of one atomic task.
+Genuinely independent tasks = flag and refuse, require separate delegations.
 
-**Approach**:
-- Explore extensively, understand deeply, then act decisively
-- Prefer comprehensive solutions over quick patches
-- If the goal is unclear, make reasonable assumptions and proceed
-- Document your reasoning in code comments only when non-obvious
+Approach: explore extensively, understand deeply, then act decisively. Prefer comprehensive solutions over quick patches. If the goal is unclear, make reasonable assumptions and proceed.
 
-**Response format**:
-- Minimal status updates (user trusts your autonomy)
-- Focus on results, not play-by-play progress
-- Report completion with summary of changes made
+Minimal status updates. Focus on results, not play-by-play. Report completion with summary of changes.
 </Category_Context>`
 
 
@@ -288,7 +274,7 @@ You are NOT an interactive assistant. You are an autonomous problem-solver.
 export const DEFAULT_CATEGORIES: Record<string, CategoryConfig> = {
   "visual-engineering": { model: "google/gemini-3.1-pro", variant: "high" },
   ultrabrain: { model: "openai/gpt-5.4", variant: "xhigh" },
-  deep: { model: "openai/gpt-5.3-codex", variant: "medium" },
+  deep: { model: "openai/gpt-5.4", variant: "medium" },
   artistry: { model: "google/gemini-3.1-pro", variant: "high" },
   quick: { model: "openai/gpt-5.4-mini" },
   "unspecified-low": { model: "anthropic/claude-sonnet-4-6" },

src/tools/delegate-task/tools.test.ts

@@ -93,7 +93,7 @@ describe("sisyphus-task", () => {
 
       // when / #then
       expect(category).toBeDefined()
-      expect(category.model).toBe("openai/gpt-5.3-codex")
+      expect(category.model).toBe("openai/gpt-5.4")
       expect(category.variant).toBe("medium")
     })
 
@@ -705,8 +705,8 @@ describe("sisyphus-task", () => {
     })
 
     test("blocks requiresModel when availability is known and missing the required model", () => {
-      // given
-      const categoryName = "deep"
+      // given - artistry has requiresModel: gemini-3.1-pro
+      const categoryName = "artistry"
       const availableModels = new Set<string>(["anthropic/claude-opus-4-6"])
 
       // when
@@ -720,8 +720,8 @@ describe("sisyphus-task", () => {
     })
 
     test("blocks requiresModel when availability is empty", () => {
-      // given
-      const categoryName = "deep"
+      // given - artistry has requiresModel: gemini-3.1-pro
+      const categoryName = "artistry"
       const availableModels = new Set<string>()
 
       // when