Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
2 changes: 1 addition & 1 deletion .agents/claude-code-cli.ts
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ const baseDefinition = createCliAgent({
startCommand: 'claude --dangerously-skip-permissions',
permissionNote:
'Always use `--dangerously-skip-permissions` when testing to avoid permission prompts that would block automated tests.',
model: 'anthropic/claude-opus-4.5',
model: 'anthropic/claude-opus-4.6',
})

// Constants must be inside handleSteps since it gets serialized via .toString()
Expand Down
2 changes: 1 addition & 1 deletion .agents/codebuff-local-cli.ts
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ const baseDefinition = createCliAgent({
startCommand: 'bun --cwd=cli run dev',
permissionNote:
'No permission flags needed for Codebuff local dev server.',
model: 'anthropic/claude-opus-4.5',
model: 'anthropic/claude-opus-4.6',
skipPrepPhase: true,
spawnerPromptExtras: `**Purpose:** E2E visual testing of the Codebuff CLI itself. This agent starts a local dev Codebuff CLI instance and interacts with it to verify UI behavior.

Expand Down
2 changes: 1 addition & 1 deletion .agents/codex-cli.ts
Original file line number Diff line number Diff line change
Expand Up @@ -81,7 +81,7 @@ const baseDefinition = createCliAgent({
startCommand: 'codex -a never -s danger-full-access',
permissionNote:
'Always use `-a never -s danger-full-access` when testing to avoid approval prompts that would block automated tests.',
model: 'anthropic/claude-opus-4.5',
model: 'anthropic/claude-opus-4.6',
extraInputParams: {
reviewType: {
type: 'string',
Expand Down
2 changes: 1 addition & 1 deletion .agents/gemini-cli.ts
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ const baseDefinition = createCliAgent({
startCommand: 'gemini --yolo',
permissionNote:
'Always use `--yolo` (or `--approval-mode yolo`) when testing to auto-approve all tool actions and avoid prompts that would block automated tests.',
model: 'anthropic/claude-opus-4.5',
model: 'anthropic/claude-opus-4.6',
cliSpecificDocs: `## Gemini CLI Commands

Gemini CLI uses slash commands for navigation:
Expand Down
11 changes: 5 additions & 6 deletions agents-graveyard/editor/best-of-n/best-of-n-selector.ts
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@ export const createBestOfNSelector = (options: {
model: isSonnet
? 'anthropic/claude-sonnet-4.5'
: isOpus
? 'anthropic/claude-opus-4.5'
? 'anthropic/claude-opus-4.6'
: isGemini
? 'google/gemini-3-pro-preview'
: 'openai/gpt-5.1',
Expand Down Expand Up @@ -108,13 +108,12 @@ Try to select an implementation that fulfills all the requirements in the user's

## Response Format

${
isSonnet || isOpus
? `Use <think> tags to write out your thoughts about the implementations as needed to pick the best implementation. IMPORTANT: You should think really really hard to make sure you pick the absolute best implementation! As soon as you know for sure which implementation is the best, you should output your choice.
${isSonnet || isOpus
? `Use <think> tags to write out your thoughts about the implementations as needed to pick the best implementation. IMPORTANT: You should think really really hard to make sure you pick the absolute best implementation! As soon as you know for sure which implementation is the best, you should output your choice.

Then, do not write any other explanations AT ALL. You should directly output a single tool call to set_output with the selected implementationId and short reason.`
: `Output a single tool call to set_output with the selected implementationId. Do not write anything else.`
}`,
: `Output a single tool call to set_output with the selected implementationId. Do not write anything else.`
}`,
}
}

Expand Down
2 changes: 1 addition & 1 deletion agents-graveyard/editor/best-of-n/editor-implementor2.ts
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@ export const createBestOfNImplementor2 = (options: {
model: isGpt5
? 'openai/gpt-5.2'
: isOpus
? 'anthropic/claude-opus-4.5'
? 'anthropic/claude-opus-4.6'
: 'anthropic/claude-sonnet-4.5',
displayName: isGpt5
? 'GPT-5 Implementation Generator v2'
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ import type { SecretAgentDefinition } from '../../types/secret-agent-definition'
export function createMultiPromptEditor(): Omit<SecretAgentDefinition, 'id'> {
return {
publisher,
model: 'anthropic/claude-opus-4.5',
model: 'anthropic/claude-opus-4.6',
displayName: 'Multi-Prompt Editor',
spawnerPrompt:
'Edits code by spawning multiple implementor agents with different strategy prompts, selects the best implementation, and applies the changes. It also returns further suggested improvements which you should take seriously and act on. Pass as input an array of short prompts specifying different implementation approaches or strategies. Make sure to read any files intended to be edited before spawning this agent.',
Expand Down
11 changes: 5 additions & 6 deletions agents-graveyard/editor/reviewer-editor.ts
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@ export const createCodeEditor = (options: {
model:
options.model === 'gpt-5'
? 'openai/gpt-5.1'
: 'anthropic/claude-opus-4.5',
: 'anthropic/claude-opus-4.6',
displayName: 'Code Editor',
spawnerPrompt:
'Expert code reviewer that reviews recent code changes and makes improvements.',
Expand Down Expand Up @@ -58,10 +58,9 @@ OR for new files or major rewrites:
}
</codebuff_tool_call>

${
model === 'gpt-5'
? ''
: `Before you start writing your implementation, you should use <think> tags to think about the best way to implement the changes.
${model === 'gpt-5'
? ''
: `Before you start writing your implementation, you should use <think> tags to think about the best way to implement the changes.

You can also use <think> tags interspersed between tool calls to think about the best way to implement the changes.

Expand All @@ -88,7 +87,7 @@ You can also use <think> tags interspersed between tool calls to think about the
</codebuff_tool_call>

</example>`
}
}

### Simplify the code.

Expand Down
44 changes: 22 additions & 22 deletions agents/__tests__/editor.test.ts
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,7 @@ describe('editor agent', () => {
})

test('uses opus model by default', () => {
expect(editor.model).toBe('anthropic/claude-opus-4.5')
expect(editor.model).toBe('anthropic/claude-opus-4.6')
})

test('has output mode set to structured_output', () => {
Expand All @@ -54,7 +54,7 @@ describe('editor agent', () => {
describe('createCodeEditor', () => {
test('creates opus editor by default', () => {
const opusEditor = createCodeEditor({ model: 'opus' })
expect(opusEditor.model).toBe('anthropic/claude-opus-4.5')
expect(opusEditor.model).toBe('anthropic/claude-opus-4.6')
})

test('creates gpt-5 editor', () => {
Expand Down Expand Up @@ -160,10 +160,10 @@ describe('editor agent', () => {
]
const mockAgentState = createMockAgentState(initialMessages)
const mockLogger = {
debug: () => {},
info: () => {},
warn: () => {},
error: () => {},
debug: () => { },
info: () => { },
warn: () => { },
error: () => { },
}

const generator = editor.handleSteps!({
Expand All @@ -183,10 +183,10 @@ describe('editor agent', () => {
]
const mockAgentState = createMockAgentState(initialMessages)
const mockLogger = {
debug: () => {},
info: () => {},
warn: () => {},
error: () => {},
debug: () => { },
info: () => { },
warn: () => { },
error: () => { },
}

const generator = editor.handleSteps!({
Expand Down Expand Up @@ -227,10 +227,10 @@ describe('editor agent', () => {
]
const mockAgentState = createMockAgentState(initialMessages)
const mockLogger = {
debug: () => {},
info: () => {},
warn: () => {},
error: () => {},
debug: () => { },
info: () => { },
warn: () => { },
error: () => { },
}

const generator = editor.handleSteps!({
Expand Down Expand Up @@ -278,10 +278,10 @@ describe('editor agent', () => {
const initialMessages: any[] = []
const mockAgentState = createMockAgentState(initialMessages)
const mockLogger = {
debug: () => {},
info: () => {},
warn: () => {},
error: () => {},
debug: () => { },
info: () => { },
warn: () => { },
error: () => { },
}

const generator = editor.handleSteps!({
Expand Down Expand Up @@ -315,10 +315,10 @@ describe('editor agent', () => {
test('works with empty initial message history', () => {
const mockAgentState = createMockAgentState([])
const mockLogger = {
debug: () => {},
info: () => {},
warn: () => {},
error: () => {},
debug: () => { },
info: () => { },
warn: () => { },
error: () => { },
}

const generator = editor.handleSteps!({
Expand Down
82 changes: 41 additions & 41 deletions agents/__tests__/thinker.test.ts
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@ describe('thinker agent', () => {
})

test('uses opus model', () => {
expect(thinker.model).toBe('anthropic/claude-opus-4.5')
expect(thinker.model).toBe('anthropic/claude-opus-4.6')
})

test('has output mode set to structured_output', () => {
Expand Down Expand Up @@ -94,10 +94,10 @@ describe('thinker agent', () => {
test('yields STEP to get agent state', () => {
const mockAgentState = createMockAgentState()
const mockLogger = {
debug: () => {},
info: () => {},
warn: () => {},
error: () => {},
debug: () => { },
info: () => { },
warn: () => { },
error: () => { },
}

const generator = thinker.handleSteps!({
Expand Down Expand Up @@ -125,10 +125,10 @@ describe('thinker agent', () => {

const mockAgentState = createMockAgentState(messages)
const mockLogger = {
debug: () => {},
info: () => {},
warn: () => {},
error: () => {},
debug: () => { },
info: () => { },
warn: () => { },
error: () => { },
}

const generator = thinker.handleSteps!({
Expand Down Expand Up @@ -170,10 +170,10 @@ describe('thinker agent', () => {

const mockAgentState = createMockAgentState(messages)
const mockLogger = {
debug: () => {},
info: () => {},
warn: () => {},
error: () => {},
debug: () => { },
info: () => { },
warn: () => { },
error: () => { },
}

const generator = thinker.handleSteps!({
Expand Down Expand Up @@ -220,10 +220,10 @@ Actual response here`,

const mockAgentState = createMockAgentState(messages)
const mockLogger = {
debug: () => {},
info: () => {},
warn: () => {},
error: () => {},
debug: () => { },
info: () => { },
warn: () => { },
error: () => { },
}

const generator = thinker.handleSteps!({
Expand Down Expand Up @@ -255,10 +255,10 @@ Actual response here`,

const mockAgentState = createMockAgentState(messages)
const mockLogger = {
debug: () => {},
info: () => {},
warn: () => {},
error: () => {},
debug: () => { },
info: () => { },
warn: () => { },
error: () => { },
}

const generator = thinker.handleSteps!({
Expand Down Expand Up @@ -298,10 +298,10 @@ Actual response here`,

const mockAgentState = createMockAgentState(messages)
const mockLogger = {
debug: () => {},
info: () => {},
warn: () => {},
error: () => {},
debug: () => { },
info: () => { },
warn: () => { },
error: () => { },
}

const generator = thinker.handleSteps!({
Expand Down Expand Up @@ -337,10 +337,10 @@ Actual response here`,

const mockAgentState = createMockAgentState(messages)
const mockLogger = {
debug: () => {},
info: () => {},
warn: () => {},
error: () => {},
debug: () => { },
info: () => { },
warn: () => { },
error: () => { },
}

const generator = thinker.handleSteps!({
Expand Down Expand Up @@ -389,10 +389,10 @@ Actual response here`,

const mockAgentState = createMockAgentState(messages)
const mockLogger = {
debug: () => {},
info: () => {},
warn: () => {},
error: () => {},
debug: () => { },
info: () => { },
warn: () => { },
error: () => { },
}

const generator = thinker.handleSteps!({
Expand Down Expand Up @@ -442,10 +442,10 @@ Actual response here`,

const mockAgentState = createMockAgentState(messages)
const mockLogger = {
debug: () => {},
info: () => {},
warn: () => {},
error: () => {},
debug: () => { },
info: () => { },
warn: () => { },
error: () => { },
}

const generator = thinker.handleSteps!({
Expand Down Expand Up @@ -477,10 +477,10 @@ Actual response here`,

const mockAgentState = createMockAgentState(messages)
const mockLogger = {
debug: () => {},
info: () => {},
warn: () => {},
error: () => {},
debug: () => { },
info: () => { },
warn: () => { },
error: () => { },
}

const generator = thinker.handleSteps!({
Expand Down
2 changes: 1 addition & 1 deletion agents/base2/base2.ts
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,7 @@ export function createBase2(

return {
publisher,
model: isFree ? 'x-ai/grok-4.1-fast' : 'anthropic/claude-opus-4.5',
model: isFree ? 'x-ai/grok-4.1-fast' : 'anthropic/claude-opus-4.6',
displayName: 'Buffy the Orchestrator',
spawnerPrompt:
'Advanced base agent that orchestrates planning, editing, and reviewing for complex coding tasks',
Expand Down
Loading