test: align model expectations with GPT-5.5 defaults

This commit is contained in:
auyua9
2026-04-26 02:00:41 +08:00
parent 6cd145ef28
commit 5bbac51e6d
6 changed files with 52 additions and 52 deletions
+33 -33
View File
@@ -58,14 +58,14 @@ describe("createBuiltinAgents with model overrides", () => {
const providerModelsSpy = spyOn(connectedProvidersCache, "readProviderModelsCache").mockReturnValue(null)
const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(new Set())
const overrides = {
sisyphus: { model: "github-copilot/gpt-5.4" },
sisyphus: { model: "github-copilot/gpt-5.5" },
}
// #when
const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL, undefined, undefined, [], undefined, undefined)
// #then
expect(agents.sisyphus.model).toBe("github-copilot/gpt-5.4")
expect(agents.sisyphus.model).toBe("github-copilot/gpt-5.5")
expect(agents.sisyphus.reasoningEffort).toBe("medium")
expect(agents.sisyphus.thinking).toBeUndefined()
providerModelsSpy.mockRestore()
@@ -75,9 +75,9 @@ describe("createBuiltinAgents with model overrides", () => {
test("Atlas uses uiSelectedModel", async () => {
// #given
const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
new Set(["openai/gpt-5.4", "anthropic/claude-sonnet-4-6"])
new Set(["openai/gpt-5.5", "anthropic/claude-sonnet-4-6"])
)
const uiSelectedModel = "openai/gpt-5.4"
const uiSelectedModel = "openai/gpt-5.5"
try {
// #when
@@ -96,7 +96,7 @@ describe("createBuiltinAgents with model overrides", () => {
// #then
expect(agents.atlas).toBeDefined()
expect(agents.atlas.model).toBe("openai/gpt-5.4")
expect(agents.atlas.model).toBe("openai/gpt-5.5")
} finally {
fetchSpy.mockRestore()
}
@@ -105,9 +105,9 @@ 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-5.4", "anthropic/claude-sonnet-4-6"])
new Set(["openai/gpt-5.5", "anthropic/claude-sonnet-4-6"])
)
const uiSelectedModel = "openai/gpt-5.4"
const uiSelectedModel = "openai/gpt-5.5"
const overrides = {
sisyphus: { model: "google/antigravity-claude-opus-4-5-thinking" },
}
@@ -138,9 +138,9 @@ 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-5.4", "anthropic/claude-sonnet-4-6"])
new Set(["openai/gpt-5.5", "anthropic/claude-sonnet-4-6"])
)
const uiSelectedModel = "openai/gpt-5.4"
const uiSelectedModel = "openai/gpt-5.5"
const overrides = {
atlas: { model: "google/antigravity-claude-opus-4-5-thinking" },
}
@@ -263,14 +263,14 @@ describe("createBuiltinAgents with model overrides", () => {
const providerModelsSpy = spyOn(connectedProvidersCache, "readProviderModelsCache").mockReturnValue(null)
const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(new Set())
const overrides = {
sisyphus: { model: "github-copilot/gpt-5.4", temperature: 0.5 },
sisyphus: { model: "github-copilot/gpt-5.5", 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-5.4")
expect(agents.sisyphus.model).toBe("github-copilot/gpt-5.5")
expect(agents.sisyphus.temperature).toBe(0.5)
providerModelsSpy.mockRestore()
fetchSpy.mockRestore()
@@ -304,7 +304,7 @@ describe("createBuiltinAgents with model overrides", () => {
"opencode/kimi-k2.5-free",
"zai-coding-plan/glm-5",
"opencode/big-pickle",
"openai/gpt-5.4",
"openai/gpt-5.5",
])
)
@@ -341,7 +341,7 @@ 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-4-7", "openai/gpt-5.4"])
new Set(["anthropic/claude-opus-4-7", "openai/gpt-5.5"])
)
const customAgentSummaries = [
@@ -377,7 +377,7 @@ 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-4-7", "openai/gpt-5.4"])
new Set(["anthropic/claude-opus-4-7", "openai/gpt-5.5"])
)
const customAgentSummaries = [
@@ -413,7 +413,7 @@ 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-4-7", "openai/gpt-5.4"])
new Set(["anthropic/claude-opus-4-7", "openai/gpt-5.5"])
)
const disabledAgents = ["ReSeArChEr"]
@@ -449,7 +449,7 @@ describe("createBuiltinAgents with model overrides", () => {
test("does not advertise duplicate custom agents case-insensitively", async () => {
// #given
const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
new Set(["anthropic/claude-opus-4-7", "openai/gpt-5.4"])
new Set(["anthropic/claude-opus-4-7", "openai/gpt-5.5"])
)
const customAgentSummaries = [
@@ -481,7 +481,7 @@ describe("createBuiltinAgents with model overrides", () => {
test("does not surface custom agent strings in orchestrator prompts", async () => {
// #given
const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
new Set(["anthropic/claude-opus-4-7", "openai/gpt-5.4"])
new Set(["anthropic/claude-opus-4-7", "openai/gpt-5.5"])
)
const customAgentSummaries = [
@@ -840,7 +840,7 @@ describe("Atlas is unaffected by environment context toggle", () => {
beforeEach(() => {
fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(
new Set(["anthropic/claude-opus-4-7", "openai/gpt-5.4"])
new Set(["anthropic/claude-opus-4-7", "openai/gpt-5.5"])
)
})
@@ -966,7 +966,7 @@ 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-5.4"])
new Set(["openai/gpt-5.5"])
)
const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(
["openai"]
@@ -1016,7 +1016,7 @@ describe("createBuiltinAgents with requiresAnyModel gating (sisyphus)", () => {
test("atlas and metis resolve to OpenAI in an OpenAI-only environment without a system default", async () => {
// #given
const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(new Set(["openai/gpt-5.4"]))
const fetchSpy = spyOn(shared, "fetchAvailableModels").mockResolvedValue(new Set(["openai/gpt-5.5"]))
const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(["openai"])
try {
@@ -1025,10 +1025,10 @@ describe("createBuiltinAgents with requiresAnyModel gating (sisyphus)", () => {
// #then
expect(agents.atlas).toBeDefined()
expect(agents.atlas.model).toBe("openai/gpt-5.4")
expect(agents.atlas.model).toBe("openai/gpt-5.5")
expect(agents.atlas.variant).toBe("medium")
expect(agents.metis).toBeDefined()
expect(agents.metis.model).toBe("openai/gpt-5.4")
expect(agents.metis.model).toBe("openai/gpt-5.5")
expect(agents.metis.variant).toBe("high")
} finally {
fetchSpy.mockRestore()
@@ -1096,7 +1096,7 @@ describe("buildAgent with category and skills", () => {
const categories = {
"custom-category": {
model: "openai/gpt-5.4",
model: "openai/gpt-5.5",
variant: "xhigh",
},
}
@@ -1105,7 +1105,7 @@ describe("buildAgent with category and skills", () => {
const agent = buildAgent(source["test-agent"], TEST_MODEL, categories)
// #then
expect(agent.model).toBe("openai/gpt-5.4")
expect(agent.model).toBe("openai/gpt-5.5")
expect(agent.variant).toBe("xhigh")
})
@@ -1185,7 +1185,7 @@ describe("buildAgent with category and skills", () => {
const agent = buildAgent(source["test-agent"], TEST_MODEL)
// #then - category's built-in model and skills are applied
expect(agent.model).toBe("openai/gpt-5.4")
expect(agent.model).toBe("openai/gpt-5.5")
expect(agent.variant).toBe("xhigh")
expect(agent.prompt).toContain("Role: Designer-Turned-Developer")
expect(agent.prompt).toContain("Task description")
@@ -1309,9 +1309,9 @@ describe("override.category expansion in createBuiltinAgents", () => {
// #when
const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL)
// #then - ultrabrain category: model=openai/gpt-5.4, variant=xhigh
// #then - ultrabrain category: model=openai/gpt-5.5, variant=xhigh
expect(agents.oracle).toBeDefined()
expect(agents.oracle.model).toBe("openai/gpt-5.4")
expect(agents.oracle.model).toBe("openai/gpt-5.5")
expect(agents.oracle.variant).toBe("xhigh")
})
@@ -1333,7 +1333,7 @@ describe("override.category expansion in createBuiltinAgents", () => {
// #given - custom category has reasoningEffort=xhigh, direct override says "low"
const categories = {
"test-cat": {
model: "openai/gpt-5.4",
model: "openai/gpt-5.5",
reasoningEffort: "xhigh" as const,
},
}
@@ -1353,7 +1353,7 @@ describe("override.category expansion in createBuiltinAgents", () => {
// #given - custom category has reasoningEffort, no direct reasoningEffort in override
const categories = {
"reasoning-cat": {
model: "openai/gpt-5.4",
model: "openai/gpt-5.5",
reasoningEffort: "high" as const,
},
}
@@ -1378,9 +1378,9 @@ describe("override.category expansion in createBuiltinAgents", () => {
// #when
const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL)
// #then - ultrabrain category: model=openai/gpt-5.4, variant=xhigh
// #then - ultrabrain category: model=openai/gpt-5.5, variant=xhigh
expect(agents.sisyphus).toBeDefined()
expect(agents.sisyphus.model).toBe("openai/gpt-5.4")
expect(agents.sisyphus.model).toBe("openai/gpt-5.5")
expect(agents.sisyphus.variant).toBe("xhigh")
})
@@ -1393,9 +1393,9 @@ describe("override.category expansion in createBuiltinAgents", () => {
// #when
const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL)
// #then - ultrabrain category: model=openai/gpt-5.4, variant=xhigh
// #then - ultrabrain category: model=openai/gpt-5.5, variant=xhigh
expect(agents.atlas).toBeDefined()
expect(agents.atlas.model).toBe("openai/gpt-5.4")
expect(agents.atlas.model).toBe("openai/gpt-5.5")
expect(agents.atlas.variant).toBe("xhigh")
})