Skip to content

chore: update known-models and E2E tests to latest cheapest models #529

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
FL4TLiN3 merged 3 commits into from
Feb 15, 2026
Merged

chore: update known-models and E2E tests to latest cheapest models #529

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
a6caf6e
chore: update known-models and E2E tests to latest model IDs
FL4TLiN3 Feb 15, 2026
0939649
chore: switch all E2E tests to cheapest models per provider
FL4TLiN3 Feb 15, 2026
d7edf6f
chore: add changeset for known-models update
FL4TLiN3 Feb 15, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions .changeset/update-known-models.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
---
"@perstack/core": patch
---

Add latest models to known-models: claude-opus-4-6, gpt-5.1, gpt-5.2, gpt-5.2-pro, gemini-3-flash-preview
2 changes: 1 addition & 1 deletion e2e/experts/bundled-base.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
# E2E test configuration for bundled base skill with InMemoryTransport
# Tests that the bundled @perstack/base uses in-memory transport (no process spawn)

model = "claude-sonnet-4-5"
model = "claude-haiku-4-5"

[provider]
providerName = "anthropic"
Expand Down
2 changes: 1 addition & 1 deletion e2e/experts/cli-commands.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
model = "claude-sonnet-4-5"
model = "claude-haiku-4-5"

[provider]
providerName = "anthropic"
Expand Down
2 changes: 1 addition & 1 deletion e2e/experts/continue-resume.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
model = "claude-sonnet-4-5"
model = "claude-haiku-4-5"

[provider]
providerName = "anthropic"
Expand Down
2 changes: 1 addition & 1 deletion e2e/experts/delegate-chain.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
model = "claude-sonnet-4-5"
model = "claude-haiku-4-5"

[provider]
providerName = "anthropic"
Expand Down
2 changes: 1 addition & 1 deletion e2e/experts/error-handling.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
model = "claude-sonnet-4-5"
model = "claude-haiku-4-5"

[provider]
providerName = "anthropic"
Expand Down
2 changes: 1 addition & 1 deletion e2e/experts/errors.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
model = "claude-sonnet-4-5"
model = "claude-haiku-4-5"

[provider]
providerName = "anthropic"
Expand Down
2 changes: 1 addition & 1 deletion e2e/experts/global-runtime.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
model = "claude-sonnet-4-5"
model = "claude-haiku-4-5"

[provider]
providerName = "anthropic"
Expand Down
2 changes: 1 addition & 1 deletion e2e/experts/lazy-init.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
model = "claude-sonnet-4-5"
model = "claude-haiku-4-5"

[provider]
providerName = "anthropic"
Expand Down
2 changes: 1 addition & 1 deletion e2e/experts/lockfile.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
# E2E test configuration for lockfile functionality
# Tests perstack install and lockfile-based execution

model = "claude-sonnet-4-5"
model = "claude-haiku-4-5"

[provider]
providerName = "anthropic"
Expand Down
2 changes: 1 addition & 1 deletion e2e/experts/mixed-tools.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
model = "claude-sonnet-4-5"
model = "claude-haiku-4-5"

[provider]
providerName = "anthropic"
Expand Down
2 changes: 1 addition & 1 deletion e2e/experts/multi-modal.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
model = "claude-sonnet-4-5"
model = "claude-haiku-4-5"

[provider]
providerName = "anthropic"
Expand Down
2 changes: 1 addition & 1 deletion e2e/experts/parallel-delegate.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
model = "claude-sonnet-4-5"
model = "claude-haiku-4-5"

[provider]
providerName = "anthropic"
Expand Down
2 changes: 1 addition & 1 deletion e2e/experts/parallel-mcp.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
model = "claude-sonnet-4-5"
model = "claude-haiku-4-5"

[provider]
providerName = "anthropic"
Expand Down
2 changes: 1 addition & 1 deletion e2e/experts/runtime-version-future.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
model = "claude-sonnet-4-5"
model = "claude-haiku-4-5"

[provider]
providerName = "anthropic"
Expand Down
2 changes: 1 addition & 1 deletion e2e/experts/runtime-version.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
model = "claude-sonnet-4-5"
model = "claude-haiku-4-5"

[provider]
providerName = "anthropic"
Expand Down
2 changes: 1 addition & 1 deletion e2e/experts/skills.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
model = "claude-sonnet-4-5"
model = "claude-haiku-4-5"

[provider]
providerName = "anthropic"
Expand Down
2 changes: 1 addition & 1 deletion e2e/experts/special-tools.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
model = "claude-sonnet-4-5"
model = "claude-haiku-4-5"

[provider]
providerName = "anthropic"
Expand Down
2 changes: 1 addition & 1 deletion e2e/experts/versioned-base.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
# E2E test configuration for versioned base skill with StdioTransport
# Tests that pinning a version falls back to npx (StdioTransport)

model = "claude-sonnet-4-5"
model = "claude-haiku-4-5"

[provider]
providerName = "anthropic"
Expand Down
2 changes: 1 addition & 1 deletion e2e/perstack-cli/options.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,7 +48,7 @@ describe.concurrent("CLI Options", () => {
"--config",
GLOBAL_RUNTIME_CONFIG,
"--model",
"claude-sonnet-4-5",
"claude-haiku-4-5",
"e2e-global-runtime",
"Say hello",
],
Expand Down
2 changes: 1 addition & 1 deletion e2e/perstack-cli/providers.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@ const CONFIG = "./e2e/experts/providers.toml"
const LLM_TIMEOUT = 120000

const providers = [
{ provider: "openai", model: "gpt-4.1", hasKey: hasOpenAIKey },
{ provider: "openai", model: "gpt-5-nano", hasKey: hasOpenAIKey },
{ provider: "anthropic", model: "claude-haiku-4-5", hasKey: hasAnthropicKey },
{ provider: "google", model: "gemini-2.5-flash", hasKey: hasGoogleKey },
]
Expand Down
8 changes: 4 additions & 4 deletions e2e/perstack-cli/reasoning-budget.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -97,8 +97,8 @@ async function runReasoningTest(

describe("Reasoning Budget", () => {
describe("Anthropic Extended Thinking", () => {
// Note: Claude claude-sonnet-4-5 supports extended thinking
const ANTHROPIC_MODEL = "claude-sonnet-4-5"
// Note: Claude claude-haiku-4-5 supports extended thinking
const ANTHROPIC_MODEL = "claude-haiku-4-5"

it(
"should produce reasoning tokens when budget is set",
Expand Down Expand Up @@ -152,8 +152,8 @@ describe("Reasoning Budget", () => {
})

describe("OpenAI Reasoning Effort", () => {
// Note: o3-mini supports reasoning effort
const OPENAI_MODEL = "o3-mini"
// Note: gpt-5-nano supports reasoning effort
const OPENAI_MODEL = "gpt-5-nano"

it(
"should produce reasoning tokens when budget is set",
Expand Down
6 changes: 3 additions & 3 deletions e2e/perstack-cli/streaming.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,7 +32,7 @@ function filterStreamingEvents(events: ParsedEvent[]): ParsedEvent[] {

describe("Streaming Events", () => {
describe("Event Sequence with Reasoning", () => {
const ANTHROPIC_MODEL = "claude-sonnet-4-5"
const ANTHROPIC_MODEL = "claude-haiku-4-5"

it(
"emits reasoning events in correct order (start → stream... → complete)",
Expand Down Expand Up @@ -180,7 +180,7 @@ describe("Streaming Events", () => {

describe("Without Reasoning", () => {
// Use a model/provider without reasoning or with reasoning disabled
const ANTHROPIC_MODEL = "claude-sonnet-4-20250514"
const ANTHROPIC_MODEL = "claude-haiku-4-5"

it(
"skips reasoning events when budget is none",
Expand Down Expand Up @@ -220,7 +220,7 @@ describe("Streaming Events", () => {
})

describe("Streaming Delta Content", () => {
const ANTHROPIC_MODEL = "claude-sonnet-4-5"
const ANTHROPIC_MODEL = "claude-haiku-4-5"

it(
"streamReasoning events contain non-empty deltas",
Expand Down
29 changes: 29 additions & 0 deletions packages/core/src/known-models/index.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,11 @@ export const knownModels = [
provider: "anthropic",
models: [
// https://docs.claude.com/en/docs/about-claude/models/overview#model-comparison-table
{
name: "claude-opus-4-6",
contextWindow: 200_000,
maxOutputTokens: 128_000,
},
{
name: "claude-opus-4-5",
contextWindow: 200_000,
Expand Down Expand Up @@ -48,6 +53,12 @@ export const knownModels = [
{
provider: "google",
models: [
// https://ai.google.dev/gemini-api/docs/models#gemini-3-flash
{
name: "gemini-3-flash-preview",
contextWindow: 1_048_576,
maxOutputTokens: 65_536,
},
// https://ai.google.dev/gemini-api/docs/models#gemini-3-pro
{
name: "gemini-3-pro-preview",
Expand Down Expand Up @@ -95,6 +106,24 @@ export const knownModels = [
contextWindow: 400_000,
maxOutputTokens: 128_000,
},
// https://platform.openai.com/docs/models/gpt-5.2
{
name: "gpt-5.2",
contextWindow: 400_000,
maxOutputTokens: 128_000,
},
// https://platform.openai.com/docs/models/gpt-5.2-pro
{
name: "gpt-5.2-pro",
contextWindow: 400_000,
maxOutputTokens: 128_000,
},
// https://platform.openai.com/docs/models/gpt-5.1
{
name: "gpt-5.1",
contextWindow: 400_000,
maxOutputTokens: 128_000,
},
// https://platform.openai.com/docs/models/gpt-5-chat-latest
{
name: "gpt-5-chat-latest",
Expand Down