docs: update hephaestus default model references from gpt-5.3-codex to gpt-5.4

Updated across README (all locales), docs/guide/, docs/reference/,
docs/examples/, AGENTS.md files, and test expectations/snapshots.

The deep category and multimodal-looker still use gpt-5.3-codex as
those are separate from the hephaestus agent.

README.ja.md

@@ -168,7 +168,7 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
 
 **Sisyphus** (`claude-opus-4-6` / **`kimi-k2.5`** / **`glm-5`**) はあなたのメインのオーケストレーターです。計画を立て、専門家に委任し、攻撃的な並列実行でタスクを完了まで推進します。途中で投げ出すことはありません。
 
-**Hephaestus** (`gpt-5.3-codex`) はあなたの自律的なディープワーカーです。レシピではなく、目標を与えてください。手取り足取り教えなくても、コードベースを探索し、パターンを研究し、端から端まで実行します。*正当なる職人 (The Legitimate Craftsman).*
+**Hephaestus** (`gpt-5.4`) はあなたの自律的なディープワーカーです。レシピではなく、目標を与えてください。手取り足取り教えなくても、コードベースを探索し、パターンを研究し、端から端まで実行します。*正当なる職人 (The Legitimate Craftsman).*
 
 **Prometheus** (`claude-opus-4-6` / **`kimi-k2.5`** / **`glm-5`**) はあなたの戦略プランナーです。インタビューモードで動作し、コードに触れる前に質問をしてスコープを特定し、詳細な計画を構築します。
 
@@ -176,7 +176,7 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
 
 > Anthropicが[私たちのせいでOpenCodeをブロックしました。](https://x.com/thdxr/status/2010149530486911014) だからこそHephaestusは「正当なる職人 (The Legitimate Craftsman)」と呼ばれているのです。皮肉を込めています。
 >
-> Opusで最もよく動きますが、Kimi K2.5 + GPT-5.3 Codexの組み合わせだけでも、バニラのClaude Codeを軽く凌駕します。設定は一切不要です。
+> Opusで最もよく動きますが、Kimi K2.5 + GPT-5.4の組み合わせだけでも、バニラのClaude Codeを軽く凌駕します。設定は一切不要です。
 
 ### エージェントの<E38388><E381AE>ーケストレーション
 

README.ko.md

@@ -162,7 +162,7 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
 
 **Sisyphus** (`claude-opus-4-6` / **`kimi-k2.5`** / **`glm-5`**)는 당신의 메인 오케스트레이터입니다. 공격적인 병렬 실행으로 계획을 세우고, 전문가들에게 위임하며, 완료될 때까지 밀어붙입니다. 중간에 포기하는 법이 없습니다.
 
-**Hephaestus** (`gpt-5.3-codex`)는 당신의 자율 딥 워커입니다. 레시피가 아니라 목표를 주세요. 베이비시터 없이 알아서 코드베이스를 탐색하고, 패턴을 연구하며, 끝에서 끝까지 전부 해냅니다. *진정한 장인(The Legitimate Craftsman).*
+**Hephaestus** (`gpt-5.4`)는 당신의 자율 딥 워커입니다. 레시피가 아니라 목표를 주세요. 베이비시터 없이 알아서 코드베이스를 탐색하고, 패턴을 연구하며, 끝에서 끝까지 전부 해냅니다. *진정한 장인(The Legitimate Craftsman).*
 
 **Prometheus** (`claude-opus-4-6` / **`kimi-k2.5`** / **`glm-5`**)는 당신의 전략 플래너입니다. 인터뷰 모드로 작동합니다. 코드 한 줄 만지기 전에 질문을 던져 스코프를 파악하고 상세한 계획부터 세웁니다.
 
@@ -170,7 +170,7 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
 
 > Anthropic이 [우리 때문에 OpenCode를 막아버렸습니다.](https://x.com/thdxr/status/2010149530486911014) 그래서 Hephaestus의 별명이 "진정한 장인(The Legitimate Craftsman)"인 겁니다. (어디서 많이 들어본 이름이죠?) 아이러니를 노렸습니다.
 >
-> Opus에서 제일 잘 돌아가긴 하지만, Kimi K2.5 + GPT-5.3 Codex 조합만으로도 바닐라 Claude Code는 가볍게 바릅니다. 설정도 필요 없습니다.
+> Opus에서 제일 잘 돌아가긴 하지만, Kimi K2.5 + GPT-5.4 조합만으로도 바닐라 Claude Code는 가볍게 바릅니다. 설정도 필요 없습니다.
 
 ### 에이전트 오케스트레이션
 

README.md

@@ -164,7 +164,7 @@ Even only with following subscriptions, ultrawork will work well (this project i
 
 **Sisyphus** (`claude-opus-4-6` / **`kimi-k2.5`** / **`glm-5`** ) is your main orchestrator. He plans, delegates to specialists, and drives tasks to completion with aggressive parallel execution. He does not stop halfway.
 
-**Hephaestus** (`gpt-5.3-codex`) is your autonomous deep worker. Give him a goal, not a recipe. He explores the codebase, researches patterns, and executes end-to-end without hand-holding. *The Legitimate Craftsman.*
+**Hephaestus** (`gpt-5.4`) is your autonomous deep worker. Give him a goal, not a recipe. He explores the codebase, researches patterns, and executes end-to-end without hand-holding. *The Legitimate Craftsman.*
 
 **Prometheus** (`claude-opus-4-6` / **`kimi-k2.5`** / **`glm-5`** ) is your strategic planner. Interview mode: it questions, identifies scope, and builds a detailed plan before a single line of code is touched.
 
@@ -172,7 +172,7 @@ Every agent is tuned to its model's specific strengths. No manual model-juggling
 
 > Anthropic [blocked OpenCode because of us.](https://x.com/thdxr/status/2010149530486911014) That's why Hephaestus is called "The Legitimate Craftsman." The irony is intentional.
 >
-> We run best on Opus, but Kimi K2.5 + GPT-5.3 Codex already beats vanilla Claude Code. Zero config needed.
+> We run best on Opus, but Kimi K2.5 + GPT-5.4 already beats vanilla Claude Code. Zero config needed.
 
 ### Agent Orchestration
 

README.ru.md

@@ -152,7 +152,7 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
 
 **Sisyphus** (`claude-opus-4-6` / **`kimi-k2.5`** / **`glm-5`**) — главный оркестратор. Он планирует, делегирует задачи специалистам и доводит их до завершения с агрессивным параллельным выполнением. Он не останавливается на полпути.
 
-**Hephaestus** (`gpt-5.3-codex`) — автономный глубокий исполнитель. Дайте ему цель, а не рецепт. Он исследует кодовую базу, изучает паттерны и выполняет задачи сквозным образом без лишних подсказок. *Законный Мастер.*
+**Hephaestus** (`gpt-5.4`) — автономный глубокий исполнитель. Дайте ему цель, а не рецепт. Он исследует кодовую базу, изучает паттерны и выполняет задачи сквозным образом без лишних подсказок. *Законный Мастер.*
 
 **Prometheus** (`claude-opus-4-6` / **`kimi-k2.5`** / **`glm-5`**) — стратегический планировщик. Режим интервью: задаёт вопросы, определяет объём работ и формирует детальный план до того, как написана хотя бы одна строка кода.
 
@@ -160,7 +160,7 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
 
 > Anthropic [заблокировал OpenCode из-за нас.](https://x.com/thdxr/status/2010149530486911014) Именно поэтому Hephaestus зовётся «Законным Мастером». Ирония намеренная.
 >
-> Мы работаем лучше всего на Opus, но Kimi K2.5 + GPT-5.3 Codex уже превосходят ванильный Claude Code. Никакой настройки не требуется.
+> Мы работаем лучше всего на Opus, но Kimi K2.5 + GPT-5.4 уже превосходят ванильный Claude Code. Никакой настройки не требуется.
 
 ### Оркестрация агентов
 

README.zh-cn.md

@@ -169,7 +169,7 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
 
 **Sisyphus** (`claude-opus-4-6` / **`kimi-k2.5`** / **`glm-5`**) 是你的主指挥官。他负责制定计划、分配任务给专家团队，并以极其激进的并行策略推动任务直至完成。他从不半途而废。
 
-**Hephaestus** (`gpt-5.3-codex`) 是你的自主深度工作者。你只需要给他目标，不要给他具体做法。他会自动探索代码库模式，从头到尾独立执行任务，绝不会中途要你当保姆。*名副其实的正牌工匠。*
+**Hephaestus** (`gpt-5.4`) 是你的自主深度工作者。你只需要给他目标，不要给他具体做法。他会自动探索代码库模式，从头到尾独立执行任务，绝不会中途要你当保姆。*名副其实的正牌工匠。*
 
 **Prometheus** (`claude-opus-4-6` / **`kimi-k2.5`** / **`glm-5`**) 是你的战略规划师。他通过访谈模式，在动一行代码之前，先通过提问确定范围并构建详尽的执行计划。
 
@@ -177,7 +177,7 @@ Read this and tell me why it's not just another boilerplate: https://raw.githubu
 
 > Anthropic [因为我们屏蔽了 OpenCode](https://x.com/thdxr/status/2010149530486911014)。这就是为什么我们将 Hephaestus 命名为“正牌工匠 (The Legitimate Craftsman)”。这是一个故意的讽刺。
 >
-> 我们在 Opus 上运行得最好，但仅仅使用 Kimi K2.5 + GPT-5.3 Codex 就足以碾压原版的 Claude Code。完全不需要配置。
+> 我们在 Opus 上运行得最好，但仅仅使用 Kimi K2.5 + GPT-5.4 就足以碾压原版的 Claude Code。完全不需要配置。
 
 ### 智能体调度机制
 

docs/examples/coding-focused.jsonc

@@ -14,7 +14,7 @@
 
     // Heavy lifter: maximum autonomy for coding tasks
     "hephaestus": {
-      "model": "openai/gpt-5.3-codex",
+      "model": "openai/gpt-5.4",
       "prompt_append": "You are the primary implementation agent. Own the codebase. Explore, decide, execute. Use LSP and AST-grep aggressively.",
       "permission": { "edit": "allow", "bash": { "git": "allow", "test": "allow" } },
     },

docs/examples/default.jsonc

@@ -13,7 +13,7 @@
 
     // Deep autonomous worker: end-to-end implementation
     "hephaestus": {
-      "model": "openai/gpt-5.3-codex",
+      "model": "openai/gpt-5.4",
       "prompt_append": "Explore thoroughly, then implement. Prefer small, testable changes.",
     },
 

docs/examples/planning-focused.jsonc

@@ -14,7 +14,7 @@
 
     // Implementation: uses planning outputs
     "hephaestus": {
-      "model": "openai/gpt-5.3-codex",
+      "model": "openai/gpt-5.4",
       "prompt_append": "Follow established plans precisely. Ask for clarification when plans are ambiguous.",
     },
 

docs/guide/agent-model-matching.md

@@ -27,7 +27,7 @@ Using Sisyphus with older GPT models would be like taking your best project mana
 
 Hephaestus is the developer who stays in their room coding all day. Doesn't talk much. Might seem socially awkward. But give them a hard technical problem and they'll emerge three hours later with a solution nobody else could have found.
 
-**This is why Hephaestus uses GPT-5.3 Codex.** Codex is built for exactly this:
+**This is why Hephaestus uses GPT-5.4.** GPT-5.4 is built for exactly this:
 
 - Deep, autonomous exploration without hand-holding
 - Multi-file reasoning across complex codebases
@@ -82,7 +82,7 @@ These agents are built for GPT's principle-driven style. Their prompts assume au
 
 | Agent          | Role                    | Fallback Chain                         | Notes                                            |
 | -------------- | ----------------------- | -------------------------------------- | ------------------------------------------------ |
-| **Hephaestus** | Autonomous deep worker  | GPT-5.3 Codex → GPT-5.4 (Copilot)     | Requires GPT access. GPT-5.4 via Copilot as fallback. The craftsman. |
+| **Hephaestus** | Autonomous deep worker  | GPT-5.4                               | Requires GPT access. The craftsman. |
 | **Oracle**     | Architecture consultant | GPT-5.4 → Gemini 3.1 Pro → Claude Opus → opencode-go/glm-5 | Read-only high-IQ consultation.                  |
 | **Momus**      | Ruthless reviewer       | GPT-5.4 → Claude Opus → Gemini 3.1 Pro → opencode-go/glm-5 | Verification and plan review. GPT-5.4 uses xhigh variant. |
 
@@ -119,7 +119,7 @@ Principle-driven, explicit reasoning, deep technical capability. Best for agents
 
 | Model             | Strengths                                                                                       |
 | ----------------- | ----------------------------------------------------------------------------------------------- |
-| **GPT-5.3 Codex** | Deep coding powerhouse. Autonomous exploration. Required for Hephaestus.                        |
+| **GPT-5.3 Codex** | Deep coding powerhouse. Autonomous exploration. Still available for deep category and explicit overrides. |
 | **GPT-5.4**       | High intelligence, strategic reasoning. Default for Oracle, Momus, and a key fallback for Prometheus / Atlas. Uses xhigh variant for Momus. |
 | **GPT-5.4 Mini**  | Fast + strong reasoning. Good for lightweight autonomous tasks. Default for quick category. |
 | **GPT-5-Nano**    | Ultra-cheap, fast. Good for simple utility tasks.                                               |

docs/guide/installation.md

@@ -285,7 +285,7 @@ Not all models behave the same way. Understanding which models are "similar" hel
 
 | Model             | Provider(s)                      | Notes                                             |
 | ----------------- | -------------------------------- | ------------------------------------------------- |
-| **GPT-5.3-codex** | openai, github-copilot, opencode | Deep coding powerhouse. Required for Hephaestus.  |
+| **GPT-5.3-codex** | openai, github-copilot, opencode | Deep coding powerhouse. Still available for deep category and explicit overrides. |
 | **GPT-5.4**       | openai, github-copilot, opencode | High intelligence. Default for Oracle.            |
 | **GPT-5.4 Mini**  | openai, github-copilot, opencode | Fast + strong reasoning. Default for quick category.     |
 | **GPT-5-Nano**    | opencode                         | Ultra-cheap, fast. Good for simple utility tasks. |
@@ -334,7 +334,7 @@ Priority: **Claude > GPT > Claude-like models**
 
 | Agent          | Role                   | Default Chain                          | Notes                                                  |
 | -------------- | ---------------------- | -------------------------------------- | ------------------------------------------------------ |
-| **Hephaestus** | Deep autonomous worker | GPT-5.3-codex (medium) only            | "Codex on steroids." No fallback. Requires GPT access. |
+| **Hephaestus** | Deep autonomous worker | GPT-5.4 (medium) only                  | "Codex on steroids." No fallback. Requires GPT access. |
 | **Oracle**     | Architecture/debugging | GPT-5.4 (high) → Gemini 3.1 Pro → Opus  | High-IQ strategic backup. GPT preferred.               |
 | **Momus**      | High-accuracy reviewer | GPT-5.4 (medium) → Opus → Gemini 3.1 Pro | Verification agent. GPT preferred.                     |
 

docs/guide/orchestration.md

@@ -420,7 +420,7 @@ Atlas is automatically activated when you run `/start-work`. You don't need to m
 
 | Aspect          | Hephaestus                                 | Sisyphus + `ulw` / `ultrawork`                       |
 | --------------- | ------------------------------------------ | ---------------------------------------------------- |
-| **Model**       | GPT-5.3 Codex (medium reasoning)           | Claude Opus 4.6 / GPT-5.4 / GLM 5 depending on setup |
+| **Model**       | GPT-5.4 (medium reasoning)                 | Claude Opus 4.6 / GPT-5.4 / GLM 5 depending on setup |
 | **Approach**    | Autonomous deep worker                     | Keyword-activated ultrawork mode                     |
 | **Best For**    | Complex architectural work, deep reasoning | General complex tasks, "just do it" scenarios        |
 | **Planning**    | Self-plans during execution                | Uses Prometheus plans if available                   |
@@ -443,8 +443,8 @@ Switch to Hephaestus (Tab → Select Hephaestus) when:
    - "Integrate our Rust core with the TypeScript frontend"
    - "Migrate from MongoDB to PostgreSQL with zero downtime"
 
-4. **You specifically want GPT-5.3 Codex reasoning**
+4. **You specifically want GPT-5.4 reasoning**
-   - Some problems benefit from GPT-5.3 Codex's training characteristics
+   - Some problems benefit from GPT-5.4's training characteristics
 
 **When to Use Sisyphus + `ulw`:**
 
@@ -469,7 +469,7 @@ Use the `ulw` keyword in Sisyphus when:
 **Recommendation:**
 
 - **For most users**: Use `ulw` keyword in Sisyphus. It's the default path and works excellently for 90% of complex tasks.
-- **For power users**: Switch to Hephaestus when you specifically need GPT-5.3 Codex's reasoning style or want the "AmpCode deep mode" experience of fully autonomous exploration and execution.
+- **For power users**: Switch to Hephaestus when you specifically need GPT-5.4's reasoning style or want the "AmpCode deep mode" experience of fully autonomous exploration and execution.
 
 ---
 
@@ -520,7 +520,7 @@ Type `exit` or start a new session. Atlas is primarily entered via `/start-work`
 
 **For most tasks**: Type `ulw` in Sisyphus.
 
-**Use Hephaestus when**: You specifically need GPT-5.3 Codex's reasoning style for deep architectural work or complex debugging.
+**Use Hephaestus when**: You specifically need GPT-5.4's reasoning style for deep architectural work or complex debugging.
 
 ---
 

docs/guide/overview.md

@@ -93,9 +93,9 @@ Sisyphus still works best on Claude-family models, Kimi, and GLM. GPT-5.4 now ha
 
 Named with intentional irony. Anthropic blocked OpenCode from using their API because of this project. So the team built an autonomous GPT-native agent instead.
 
-Hephaestus runs on GPT-5.3 Codex. Give him a goal, not a recipe. He explores the codebase, researches patterns, and executes end-to-end without hand-holding. He is the legitimate craftsman because he was born from necessity, not privilege.
+Hephaestus runs on GPT-5.4. Give him a goal, not a recipe. He explores the codebase, researches patterns, and executes end-to-end without hand-holding. He is the legitimate craftsman because he was born from necessity, not privilege.
 
-Use Hephaestus when you need deep architectural reasoning, complex debugging across many files, or cross-domain knowledge synthesis. Switch to him explicitly when the work demands GPT-5.3 Codex's particular strengths.
+Use Hephaestus when you need deep architectural reasoning, complex debugging across many files, or cross-domain knowledge synthesis. Switch to him explicitly when the work demands GPT-5.4's particular strengths.
 
 **Why this beats vanilla Codex CLI:**
 
@@ -214,8 +214,7 @@ You can override specific agents or categories in your config:
 
 **GPT models** (explicit reasoning, principle-driven):
 
-- GPT-5.3-codex — deep coding powerhouse, required for Hephaestus
+- GPT-5.4 — deep coding powerhouse, required for Hephaestus and default for Oracle
-- GPT-5.4 — high intelligence, default for Oracle
 - GPT-5-Nano — ultra-cheap, fast utility tasks
 
 **Different-behavior models**:

docs/reference/configuration.md

@@ -268,7 +268,7 @@ Disable categories: `{ "disabled_categories": ["ultrabrain"] }`
 | Agent                 | Default Model       | Provider Priority                                                            |
 | --------------------- | ------------------- | ---------------------------------------------------------------------------- |
 | **Sisyphus**          | `claude-opus-4-6`   | `claude-opus-4-6` → `glm-5` → `big-pickle`                                   |
-| **Hephaestus**        | `gpt-5.3-codex`     | `gpt-5.3-codex` → `gpt-5.4` (GitHub Copilot fallback)                        |
+| **Hephaestus**        | `gpt-5.4`           | `gpt-5.4`                                                                    |
 | **oracle**            | `gpt-5.4`           | `gpt-5.4` → `gemini-3.1-pro` → `claude-opus-4-6`                             |
 | **librarian**         | `minimax-m2.7`      | `minimax-m2.7` → `minimax-m2.7-highspeed` → `claude-haiku-4-5` → `gpt-5-nano` |
 | **explore**           | `grok-code-fast-1`  | `grok-code-fast-1` → `minimax-m2.7-highspeed` → `minimax-m2.7` → `claude-haiku-4-5` → `gpt-5-nano` |

docs/reference/features.md

@@ -9,7 +9,7 @@ Oh-My-OpenAgent provides 11 specialized AI agents. Each has distinct expertise,
 | Agent                 | Model              | Purpose                                                                                                                                                                                                                                                                                                                                                          |
 | --------------------- | ------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | **Sisyphus**          | `claude-opus-4-6`  | The default orchestrator. Plans, delegates, and executes complex tasks using specialized subagents with aggressive parallel execution. Todo-driven workflow with extended thinking (32k budget). Fallback: `glm-5` → `big-pickle`.                                                                                                                               |
-| **Hephaestus**        | `gpt-5.3-codex`    | The Legitimate Craftsman. Autonomous deep worker inspired by AmpCode's deep mode. Goal-oriented execution with thorough research before action. Explores codebase patterns, completes tasks end-to-end without premature stopping. Named after the Greek god of forge and craftsmanship. Fallback: `gpt-5.4` on GitHub Copilot. Requires a GPT-capable provider. |
+| **Hephaestus**        | `gpt-5.4`          | The Legitimate Craftsman. Autonomous deep worker inspired by AmpCode's deep mode. Goal-oriented execution with thorough research before action. Explores codebase patterns, completes tasks end-to-end without premature stopping. Named after the Greek god of forge and craftsmanship. Requires a GPT-capable provider. |
 | **Oracle**            | `gpt-5.4`          | Architecture decisions, code review, debugging. Read-only consultation with stellar logical reasoning and deep analysis. Inspired by AmpCode. Fallback: `gemini-3.1-pro` → `claude-opus-4-6`.                                                                                                                                                                    |
 | **Librarian**         | `minimax-m2.7`     | Multi-repo analysis, documentation lookup, OSS implementation examples. Deep codebase understanding with evidence-based answers. Fallback: `minimax-m2.7-highspeed` → `claude-haiku-4-5` → `gpt-5-nano`.                                                                                                                                                         |
 | **Explore**           | `grok-code-fast-1` | Fast codebase exploration and contextual grep. Fallback: `minimax-m2.7-highspeed` → `minimax-m2.7` → `claude-haiku-4-5` → `gpt-5-nano`.                                                                                                                                                                                                                          |

src/agents/AGENTS.md

@@ -11,7 +11,7 @@ Agent factories following `createXXXAgent(model) → AgentConfig` pattern. Each
 | Agent | Model | Temp | Mode | Fallback Chain | Purpose |
 |-------|-------|------|------|----------------|---------|
 | **Sisyphus** | claude-opus-4-6 max | 0.1 | all | k2p5 → kimi-k2.5 → gpt-5.4 medium → glm-5 → big-pickle | Main orchestrator, plans + delegates |
-| **Hephaestus** | gpt-5.3-codex medium | 0.1 | all | gpt-5.4 medium (copilot) | Autonomous deep worker |
+| **Hephaestus** | gpt-5.4 medium | 0.1 | all | — | Autonomous deep worker |
 | **Oracle** | gpt-5.4 high | 0.1 | subagent | gemini-3.1-pro high → claude-opus-4-6 max | Read-only consultation |
 | **Librarian** | minimax-m2.7 | 0.1 | subagent | minimax-m2.7-highspeed → claude-haiku-4-5 → gpt-5-nano | External docs/code search |
 | **Explore** | grok-code-fast-1 | 0.1 | subagent | minimax-m2.7-highspeed → minimax-m2.7 → claude-haiku-4-5 → gpt-5-nano | Contextual grep |

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

@@ -202,7 +202,7 @@ exports[`generateModelConfig single native provider uses OpenAI models when only
       "variant": "medium",
     },
     "hephaestus": {
-      "model": "openai/gpt-5.3-codex",
+      "model": "openai/gpt-5.4",
       "variant": "medium",
     },
     "librarian": {
@@ -287,7 +287,7 @@ exports[`generateModelConfig single native provider uses OpenAI models with isMa
       "variant": "medium",
     },
     "hephaestus": {
-      "model": "openai/gpt-5.3-codex",
+      "model": "openai/gpt-5.4",
       "variant": "medium",
     },
     "librarian": {
@@ -490,7 +490,7 @@ exports[`generateModelConfig all native providers uses preferred models from fal
       "model": "anthropic/claude-haiku-4-5",
     },
     "hephaestus": {
-      "model": "openai/gpt-5.3-codex",
+      "model": "openai/gpt-5.4",
       "variant": "medium",
     },
     "metis": {
@@ -565,7 +565,7 @@ exports[`generateModelConfig all native providers uses preferred models with isM
       "model": "anthropic/claude-haiku-4-5",
     },
     "hephaestus": {
-      "model": "openai/gpt-5.3-codex",
+      "model": "openai/gpt-5.4",
       "variant": "medium",
     },
     "metis": {
@@ -641,7 +641,7 @@ exports[`generateModelConfig fallback providers uses OpenCode Zen models when on
       "model": "opencode/claude-haiku-4-5",
     },
     "hephaestus": {
-      "model": "opencode/gpt-5.3-codex",
+      "model": "opencode/gpt-5.4",
       "variant": "medium",
     },
     "metis": {
@@ -716,7 +716,7 @@ exports[`generateModelConfig fallback providers uses OpenCode Zen models with is
       "model": "opencode/claude-haiku-4-5",
     },
     "hephaestus": {
-      "model": "opencode/gpt-5.3-codex",
+      "model": "opencode/gpt-5.4",
       "variant": "medium",
     },
     "metis": {
@@ -1049,7 +1049,7 @@ exports[`generateModelConfig mixed provider scenarios uses Claude + OpenCode Zen
       "model": "anthropic/claude-haiku-4-5",
     },
     "hephaestus": {
-      "model": "opencode/gpt-5.3-codex",
+      "model": "opencode/gpt-5.4",
       "variant": "medium",
     },
     "metis": {
@@ -1124,7 +1124,7 @@ exports[`generateModelConfig mixed provider scenarios uses OpenAI + Copilot comb
       "model": "github-copilot/gpt-5-mini",
     },
     "hephaestus": {
-      "model": "openai/gpt-5.3-codex",
+      "model": "openai/gpt-5.4",
       "variant": "medium",
     },
     "metis": {
@@ -1329,7 +1329,7 @@ exports[`generateModelConfig mixed provider scenarios uses all fallback provider
       "model": "opencode/claude-haiku-4-5",
     },
     "hephaestus": {
-      "model": "opencode/gpt-5.3-codex",
+      "model": "github-copilot/gpt-5.4",
       "variant": "medium",
     },
     "librarian": {
@@ -1407,7 +1407,7 @@ exports[`generateModelConfig mixed provider scenarios uses all providers togethe
       "model": "anthropic/claude-haiku-4-5",
     },
     "hephaestus": {
-      "model": "openai/gpt-5.3-codex",
+      "model": "openai/gpt-5.4",
       "variant": "medium",
     },
     "librarian": {
@@ -1485,7 +1485,7 @@ exports[`generateModelConfig mixed provider scenarios uses all providers with is
       "model": "anthropic/claude-haiku-4-5",
     },
     "hephaestus": {
-      "model": "openai/gpt-5.3-codex",
+      "model": "openai/gpt-5.4",
       "variant": "medium",
     },
     "librarian": {

src/cli/model-fallback.test.ts

@@ -458,7 +458,7 @@ describe("generateModelConfig", () => {
       const result = generateModelConfig(config)
 
       // #then
-      expect(result.agents?.hephaestus?.model).toBe("openai/gpt-5.3-codex")
+      expect(result.agents?.hephaestus?.model).toBe("openai/gpt-5.4")
       expect(result.agents?.hephaestus?.variant).toBe("medium")
     })
 
@@ -484,7 +484,7 @@ describe("generateModelConfig", () => {
       const result = generateModelConfig(config)
 
       // #then
-      expect(result.agents?.hephaestus?.model).toBe("opencode/gpt-5.3-codex")
+      expect(result.agents?.hephaestus?.model).toBe("opencode/gpt-5.4")
       expect(result.agents?.hephaestus?.variant).toBe("medium")
     })
 

src/shared/agent-variant.test.ts

@@ -113,9 +113,9 @@ describe("resolveVariantForModel", () => {
   })
 
   test("returns correct variant for openai provider (hephaestus agent)", () => {
-    // #given hephaestus has openai/gpt-5.3-codex with variant "medium" in its chain
+    // #given hephaestus has openai/gpt-5.4 with variant "medium" in its chain
     const config = {} as OhMyOpenCodeConfig
-    const model = { providerID: "openai", modelID: "gpt-5.3-codex" }
+    const model = { providerID: "openai", modelID: "gpt-5.4" }
 
     // #when
     const variant = resolveVariantForModel(config, "hephaestus", model)