luna/oh-my-opencode
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

chore: update GPT-5.2 references to GPT-5.4

Browse Source 
Align runtime defaults, tests, docs, and generated artifacts with the newer GPT-5.4 baseline. Keep think-mode and prompt-routing expectations consistent after the model version bump.
This commit is contained in:
YeonGyu-Kim
2026-03-07 02:33:32 +09:00
parent d6d1f998d4
commit ea2585e01a
62 changed files with 478 additions and 479 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/agents/AGENTS.md
+3 -3
View File
@@ -11,12 +11,12 @@ Agent factories following `createXXXAgent(model) → AgentConfig` pattern. Each
| Agent | Model | Temp | Mode | Fallback Chain | Purpose |
|-------|-------|------|------|----------------|---------|
| **Sisyphus** | claude-opus-4-6 max | 0.1 | all | glm-5 → big-pickle | Main orchestrator, plans + delegates |
| **Hephaestus** | gpt-5.3-codex medium | 0.1 | all | gpt-5.2 medium (copilot) | Autonomous deep worker |
| **Oracle** | gpt-5.2 high | 0.1 | subagent | gemini-3.1-pro high → claude-opus-4-6 max | Read-only consultation |
| **Hephaestus** | gpt-5.3-codex medium | 0.1 | all | gpt-5.4 medium (copilot) | 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** | gemini-3-flash | 0.1 | subagent | minimax-m2.5-free → big-pickle | External docs/code search |
| **Explore** | grok-code-fast-1 | 0.1 | subagent | minimax-m2.5-free → claude-haiku-4-5 → gpt-5-nano | Contextual grep |
| **Multimodal-Looker** | gpt-5.3-codex medium | 0.1 | subagent | k2p5 → gemini-3-flash → glm-4.6v → gpt-5-nano | PDF/image analysis |
| **Metis** | claude-opus-4-6 max | **0.3** | subagent | gpt-5.2 high → gemini-3.1-pro high | Pre-planning consultant |
| **Metis** | claude-opus-4-6 max | **0.3** | subagent | gpt-5.4 high → gemini-3.1-pro high | Pre-planning consultant |
| **Momus** | gpt-5.4 xhigh | 0.1 | subagent | claude-opus-4-6 max → gemini-3.1-pro high | Plan reviewer |
| **Atlas** | claude-sonnet-4-6 | 0.1 | primary | gpt-5.4 medium | Todo-list orchestrator |
| **Prometheus** | claude-opus-4-6 max | 0.1 | — | gpt-5.4 high → gemini-3.1-pro | Strategic planner (internal) |
src/agents/atlas/agent.ts
+1 -1
View File
@@ -5,7 +5,7 @@
* You are the conductor of a symphony of specialized agents.
*
* Routing:
* 1. GPT models (openai/*, github-copilot/gpt-*) → gpt.ts (GPT-5.2 optimized)
* 1. GPT models (openai/*, github-copilot/gpt-*) → gpt.ts (GPT-5.4 optimized)
* 2. Gemini models (google/*, google-vertex/*) → gemini.ts (Gemini-optimized)
* 3. Default (Claude, etc.) → default.ts (Claude-optimized)
*/
src/agents/dynamic-agent-prompt-builder.test.ts
+3 -3
View File
@@ -197,7 +197,7 @@ describe("buildParallelDelegationSection", () => {
it("#given non-Claude model with unspecified-high category #when building #then returns aggressive delegation section", () => {
//#given
const model = "openai/gpt-5.2"
const model = "openai/gpt-5.4"
const categories = [unspecifiedHighCategory, otherCategory]
//#when
@@ -223,7 +223,7 @@ describe("buildParallelDelegationSection", () => {
it("#given non-Claude model without deep or unspecified-high category #when building #then returns empty", () => {
//#given
const model = "openai/gpt-5.2"
const model = "openai/gpt-5.4"
const categories = [otherCategory]
//#when
@@ -261,7 +261,7 @@ describe("buildNonClaudePlannerSection", () => {
it("#given GPT model #when building #then returns plan agent section", () => {
//#given
const model = "openai/gpt-5.2"
const model = "openai/gpt-5.4"
//#when
const result = buildNonClaudePlannerSection(model)
src/agents/hephaestus/agent.test.ts
+3 -3
View File
@@ -39,8 +39,8 @@ describe("getHephaestusPromptSource", () => {
test("returns 'gpt' for generic GPT models", () => {
// given
const model1 = "openai/gpt-5.2";
const model2 = "github-copilot/gpt-5.2";
const model1 = "openai/gpt-4o";
const model2 = "github-copilot/gpt-4o";
const model3 = "openai/gpt-4o";
// when
@@ -111,7 +111,7 @@ describe("getHephaestusPrompt", () => {
test("generic GPT model returns generic GPT prompt", () => {
// given
const model = "openai/gpt-5.2";
const model = "openai/gpt-4o";
// when
const prompt = getHephaestusPrompt(model);
src/agents/hephaestus/gpt-5-3-codex.ts
+1 -1
View File
@@ -522,7 +522,7 @@ export function createHephaestusAgent(
return {
description:
"Autonomous Deep Worker - goal-oriented execution with GPT 5.2 Codex. Explores thoroughly before acting, uses explore/librarian agents for comprehensive context, completes tasks end-to-end. Inspired by AmpCode deep mode. (Hephaestus - OhMyOpenCode)",
"Autonomous Deep Worker - goal-oriented execution with GPT 5.4 Codex. Explores thoroughly before acting, uses explore/librarian agents for comprehensive context, completes tasks end-to-end. Inspired by AmpCode deep mode. (Hephaestus - OhMyOpenCode)",
mode: MODE,
model,
maxTokens: 32000,
src/agents/prometheus/system-prompt.ts
+1 -1
View File
@@ -48,7 +48,7 @@ export function getPrometheusPromptSource(model?: string): PrometheusPromptSourc
/**
* Gets the appropriate Prometheus prompt based on model.
* GPT models → GPT-5.2 optimized prompt (XML-tagged, principle-driven)
* GPT models → GPT-5.4 optimized prompt (XML-tagged, principle-driven)
* Gemini models → Gemini-optimized prompt (aggressive tool-call enforcement, thinking checkpoints)
* Default (Claude, etc.) → Claude-optimized prompt (modular sections)
*/
src/agents/sisyphus-junior/agent.ts
+1 -1
View File
@@ -5,7 +5,7 @@
* Category-spawned executor with domain-specific configurations.
*
* Routing:
* 1. GPT models (openai/*, github-copilot/gpt-*) -> gpt.ts (GPT-5.2 optimized)
* 1. GPT models (openai/*, github-copilot/gpt-*) -> gpt.ts (GPT-5.4 optimized)
* 2. Gemini models (google/*, google-vertex/*) -> gemini.ts (Gemini-optimized)
* 3. Default (Claude, etc.) -> default.ts (Claude-optimized)
*/
src/agents/sisyphus-junior/index.test.ts
+8 -8
View File
@@ -10,13 +10,13 @@ describe("createSisyphusJuniorAgentWithOverrides", () => {
describe("honored fields", () => {
test("applies model override", () => {
// given
const override = { model: "openai/gpt-5.2" }
const override = { model: "openai/gpt-5.4" }
// when
const result = createSisyphusJuniorAgentWithOverrides(override)
// then
expect(result.model).toBe("openai/gpt-5.2")
expect(result.model).toBe("openai/gpt-5.4")
})
test("applies temperature override", () => {
@@ -105,7 +105,7 @@ describe("createSisyphusJuniorAgentWithOverrides", () => {
// given
const override = {
disable: true,
model: "openai/gpt-5.2",
model: "openai/gpt-5.4",
temperature: 0.9,
}
@@ -216,7 +216,7 @@ describe("createSisyphusJuniorAgentWithOverrides", () => {
test("useTaskSystem=true produces Task Discipline prompt for GPT", () => {
//#given
const override = { model: "openai/gpt-5.2" }
const override = { model: "openai/gpt-5.4" }
//#when
const result = createSisyphusJuniorAgentWithOverrides(override, undefined, true)
@@ -253,7 +253,7 @@ describe("createSisyphusJuniorAgentWithOverrides", () => {
test("useTaskSystem=true includes task_create/task_update in GPT prompt", () => {
//#given
const override = { model: "openai/gpt-5.2" }
const override = { model: "openai/gpt-5.4" }
//#when
const result = createSisyphusJuniorAgentWithOverrides(override, undefined, true)
@@ -303,7 +303,7 @@ describe("createSisyphusJuniorAgentWithOverrides", () => {
test("GPT model uses GPT-optimized prompt with Hephaestus-style sections", () => {
// given
const override = { model: "openai/gpt-5.2" }
const override = { model: "openai/gpt-5.4" }
// when
const result = createSisyphusJuniorAgentWithOverrides(override)
@@ -401,7 +401,7 @@ describe("getSisyphusJuniorPromptSource", () => {
test("returns 'gpt' for generic GPT models", () => {
// given
const model = "openai/gpt-5.2"
const model = "openai/gpt-4o"
// when
const source = getSisyphusJuniorPromptSource(model)
@@ -473,7 +473,7 @@ describe("buildSisyphusJuniorPrompt", () => {
test("generic GPT model uses generic GPT prompt", () => {
// given
const model = "openai/gpt-5.2"
const model = "openai/gpt-5.4"
// when
const prompt = buildSisyphusJuniorPrompt(model, false)
src/agents/types.test.ts
+8 -8
View File
@@ -12,9 +12,9 @@ describe("isGpt5_4Model", () => {
test("does not match other GPT models", () => {
expect(isGpt5_4Model("openai/gpt-5.3-codex")).toBe(false);
expect(isGpt5_4Model("openai/gpt-5.2")).toBe(false);
expect(isGpt5_4Model("openai/gpt-5.1")).toBe(false);
expect(isGpt5_4Model("openai/gpt-4o")).toBe(false);
expect(isGpt5_4Model("github-copilot/gpt-5.2")).toBe(false);
expect(isGpt5_4Model("github-copilot/gpt-4o")).toBe(false);
});
test("does not match non-GPT models", () => {
@@ -26,7 +26,7 @@ describe("isGpt5_4Model", () => {
describe("isGptModel", () => {
test("standard openai provider gpt models", () => {
expect(isGptModel("openai/gpt-5.2")).toBe(true);
expect(isGptModel("openai/gpt-5.4")).toBe(true);
expect(isGptModel("openai/gpt-4o")).toBe(true);
});
@@ -39,22 +39,22 @@ describe("isGptModel", () => {
});
test("github copilot gpt models", () => {
expect(isGptModel("github-copilot/gpt-5.2")).toBe(true);
expect(isGptModel("github-copilot/gpt-5.4")).toBe(true);
expect(isGptModel("github-copilot/gpt-4o")).toBe(true);
});
test("litellm proxied gpt models", () => {
expect(isGptModel("litellm/gpt-5.2")).toBe(true);
expect(isGptModel("litellm/gpt-5.4")).toBe(true);
expect(isGptModel("litellm/gpt-4o")).toBe(true);
});
test("other proxied gpt models", () => {
expect(isGptModel("ollama/gpt-4o")).toBe(true);
expect(isGptModel("custom-provider/gpt-5.2")).toBe(true);
expect(isGptModel("custom-provider/gpt-5.4")).toBe(true);
});
test("venice provider gpt models", () => {
expect(isGptModel("venice/gpt-5.2")).toBe(true);
expect(isGptModel("venice/gpt-5.4")).toBe(true);
expect(isGptModel("venice/gpt-4o")).toBe(true);
});
@@ -108,7 +108,7 @@ describe("isGeminiModel", () => {
});
test("#given gpt models #then returns false", () => {
expect(isGeminiModel("openai/gpt-5.2")).toBe(false);
expect(isGeminiModel("openai/gpt-5.4")).toBe(false);
expect(isGeminiModel("openai/o3-mini")).toBe(false);
expect(isGeminiModel("litellm/gpt-4o")).toBe(false);
});
src/agents/utils.test.ts
+30 -30
View File
@@ -39,14 +39,14 @@ describe("createBuiltinAgents with model overrides", () => {
test("Sisyphus with GPT model override has reasoningEffort, no thinking", async () => {
// #given
const overrides = {
sisyphus: { model: "github-copilot/gpt-5.2" },
sisyphus: { model: "github-copilot/gpt-5.4" },
}
// #when
const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL, undefined, undefined, [], undefined, undefined)
// #then
expect(agents.sisyphus.model).toBe("github-copilot/gpt-5.2")
expect(agents.sisyphus.model).toBe("github-copilot/gpt-5.4")
expect(agents.sisyphus.reasoningEffort).toBe("medium")
expect(agents.sisyphus.thinking).toBeUndefined()
})
@@ -54,9 +54,9 @@ describe("createBuiltinAgents with model overrides", () => {
test("Atlas uses uiSelectedModel", async () => {
// #given
const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
new Set(["openai/gpt-5.2", "anthropic/claude-sonnet-4-6"])
new Set(["openai/gpt-5.4", "anthropic/claude-sonnet-4-6"])
)
const uiSelectedModel = "openai/gpt-5.2"
const uiSelectedModel = "openai/gpt-5.4"
try {
// #when
@@ -75,7 +75,7 @@ describe("createBuiltinAgents with model overrides", () => {
// #then
expect(agents.atlas).toBeDefined()
expect(agents.atlas.model).toBe("openai/gpt-5.2")
expect(agents.atlas.model).toBe("openai/gpt-5.4")
} finally {
fetchSpy.mockRestore()
}
@@ -84,9 +84,9 @@ describe("createBuiltinAgents with model overrides", () => {
test("user config model takes priority over uiSelectedModel for sisyphus", async () => {
// #given
const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
new Set(["openai/gpt-5.2", "anthropic/claude-sonnet-4-6"])
new Set(["openai/gpt-5.4", "anthropic/claude-sonnet-4-6"])
)
const uiSelectedModel = "openai/gpt-5.2"
const uiSelectedModel = "openai/gpt-5.4"
const overrides = {
sisyphus: { model: "google/antigravity-claude-opus-4-5-thinking" },
}
@@ -117,9 +117,9 @@ describe("createBuiltinAgents with model overrides", () => {
test("user config model takes priority over uiSelectedModel for atlas", async () => {
// #given
const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
new Set(["openai/gpt-5.2", "anthropic/claude-sonnet-4-6"])
new Set(["openai/gpt-5.4", "anthropic/claude-sonnet-4-6"])
)
const uiSelectedModel = "openai/gpt-5.2"
const uiSelectedModel = "openai/gpt-5.4"
const overrides = {
atlas: { model: "google/antigravity-claude-opus-4-5-thinking" },
}
@@ -173,8 +173,8 @@ describe("createBuiltinAgents with model overrides", () => {
// #when
const agents = await createBuiltinAgents([], {}, undefined, TEST_DEFAULT_MODEL, undefined, undefined, [], undefined, undefined)
// #then - oracle resolves via connected cache fallback to openai/gpt-5.2 (not system default)
expect(agents.oracle.model).toBe("openai/gpt-5.2")
// #then - oracle resolves via connected cache fallback to openai/gpt-5.4 (not system default)
expect(agents.oracle.model).toBe("openai/gpt-5.4")
expect(agents.oracle.reasoningEffort).toBe("medium")
expect(agents.oracle.thinking).toBeUndefined()
cacheSpy.mockRestore?.()
@@ -196,14 +196,14 @@ describe("createBuiltinAgents with model overrides", () => {
test("Oracle with GPT model override has reasoningEffort, no thinking", async () => {
// #given
const overrides = {
oracle: { model: "openai/gpt-5.2" },
oracle: { model: "openai/gpt-5.4" },
}
// #when
const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL, undefined, undefined, [], undefined, undefined)
// #then
expect(agents.oracle.model).toBe("openai/gpt-5.2")
expect(agents.oracle.model).toBe("openai/gpt-5.4")
expect(agents.oracle.reasoningEffort).toBe("medium")
expect(agents.oracle.textVerbosity).toBe("high")
expect(agents.oracle.thinking).toBeUndefined()
@@ -228,14 +228,14 @@ describe("createBuiltinAgents with model overrides", () => {
test("non-model overrides are still applied after factory rebuild", async () => {
// #given
const overrides = {
sisyphus: { model: "github-copilot/gpt-5.2", temperature: 0.5 },
sisyphus: { model: "github-copilot/gpt-5.4", temperature: 0.5 },
}
// #when
const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL, undefined, undefined, [], undefined, undefined)
// #then
expect(agents.sisyphus.model).toBe("github-copilot/gpt-5.2")
expect(agents.sisyphus.model).toBe("github-copilot/gpt-5.4")
expect(agents.sisyphus.temperature).toBe(0.5)
})
@@ -261,7 +261,7 @@ describe("createBuiltinAgents with model overrides", () => {
"opencode/kimi-k2.5-free",
"zai-coding-plan/glm-5",
"opencode/big-pickle",
"openai/gpt-5.2",
"openai/gpt-5.4",
])
)
@@ -298,7 +298,7 @@ describe("createBuiltinAgents with model overrides", () => {
test("excludes hidden custom agents from orchestrator prompts", async () => {
// #given
const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
new Set(["anthropic/claude-opus-4-6", "openai/gpt-5.2"])
new Set(["anthropic/claude-opus-4-6", "openai/gpt-5.4"])
)
const customAgentSummaries = [
@@ -334,7 +334,7 @@ describe("createBuiltinAgents with model overrides", () => {
test("excludes disabled custom agents from orchestrator prompts", async () => {
// #given
const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
new Set(["anthropic/claude-opus-4-6", "openai/gpt-5.2"])
new Set(["anthropic/claude-opus-4-6", "openai/gpt-5.4"])
)
const customAgentSummaries = [
@@ -370,7 +370,7 @@ describe("createBuiltinAgents with model overrides", () => {
test("excludes custom agents when disabledAgents contains their name (case-insensitive)", async () => {
// #given
const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
new Set(["anthropic/claude-opus-4-6", "openai/gpt-5.2"])
new Set(["anthropic/claude-opus-4-6", "openai/gpt-5.4"])
)
const disabledAgents = ["ReSeArChEr"]
@@ -406,7 +406,7 @@ describe("createBuiltinAgents with model overrides", () => {
test("deduplicates custom agents case-insensitively", async () => {
// #given
const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
new Set(["anthropic/claude-opus-4-6", "openai/gpt-5.2"])
new Set(["anthropic/claude-opus-4-6", "openai/gpt-5.4"])
)
const customAgentSummaries = [
@@ -438,7 +438,7 @@ describe("createBuiltinAgents with model overrides", () => {
test("sanitizes custom agent strings for markdown tables", async () => {
// #given
const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
new Set(["anthropic/claude-opus-4-6", "openai/gpt-5.2"])
new Set(["anthropic/claude-opus-4-6", "openai/gpt-5.4"])
)
const customAgentSummaries = [
@@ -479,7 +479,7 @@ describe("createBuiltinAgents without systemDefaultModel", () => {
// #then - connected cache enables model resolution despite no systemDefaultModel
expect(agents.oracle).toBeDefined()
expect(agents.oracle.model).toBe("openai/gpt-5.2")
expect(agents.oracle.model).toBe("openai/gpt-5.4")
cacheSpy.mockRestore?.()
})
@@ -787,7 +787,7 @@ describe("Atlas is unaffected by environment context toggle", () => {
beforeEach(() => {
fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
new Set(["anthropic/claude-opus-4-6", "openai/gpt-5.2"])
new Set(["anthropic/claude-opus-4-6", "openai/gpt-5.4"])
)
})
@@ -891,9 +891,9 @@ describe("createBuiltinAgents with requiresAnyModel gating (sisyphus)", () => {
})
test("sisyphus is not created when no fallback model is available and provider not connected", async () => {
// #given - only openai/gpt-5.2 available, not in sisyphus fallback chain
// #given - only openai/gpt-5.4 available, not in sisyphus fallback chain
const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
new Set(["openai/gpt-5.2"])
new Set(["openai/gpt-5.4"])
)
const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue([])
@@ -913,7 +913,7 @@ describe("createBuiltinAgents with requiresAnyModel gating (sisyphus)", () => {
// #given - user configures a model from a plugin provider (like antigravity)
// that is NOT in the availableModels cache and NOT in the fallback chain
const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
new Set(["openai/gpt-5.2"])
new Set(["openai/gpt-5.4"])
)
const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(
["openai"]
@@ -1021,7 +1021,7 @@ describe("buildAgent with category and skills", () => {
const categories = {
"custom-category": {
model: "openai/gpt-5.2",
model: "openai/gpt-5.4",
variant: "xhigh",
},
}
@@ -1030,7 +1030,7 @@ describe("buildAgent with category and skills", () => {
const agent = buildAgent(source["test-agent"], TEST_MODEL, categories)
// #then
expect(agent.model).toBe("openai/gpt-5.2")
expect(agent.model).toBe("openai/gpt-5.4")
expect(agent.variant).toBe("xhigh")
})
@@ -1247,7 +1247,7 @@ describe("override.category expansion in createBuiltinAgents", () => {
// #given - custom category has reasoningEffort=xhigh, direct override says "low"
const categories = {
"test-cat": {
model: "openai/gpt-5.2",
model: "openai/gpt-5.4",
reasoningEffort: "xhigh" as const,
},
}
@@ -1267,7 +1267,7 @@ describe("override.category expansion in createBuiltinAgents", () => {
// #given - custom category has reasoningEffort, no direct reasoningEffort in override
const categories = {
"reasoning-cat": {
model: "openai/gpt-5.2",
model: "openai/gpt-5.4",
reasoningEffort: "high" as const,
},
}