6d25adfd1a
* agent & model refactor with ASKPASS git auth, UI restructure, clerk v7 Made-with: Cursor * fix stale agent/effort refs, add tests for askpass + model resolution - reviewCleanup.ts: payload.agent -> payload.model, remove effort - selectMode.ts PlanEdit: remove delegation/subagent/effort references - pullfrog.yml.ts: update env vars (drop GOOGLE_API_KEY/CURSOR_API_KEY, add GOOGLE_GENERATIVE_AI_API_KEY/XAI_API_KEY/MOONSHOT_API_KEY/OPENCODE_API_KEY) - FlagsSettings/RepoInstructionsSection: remove stale effort/timeout copy - new: gitAuthServer.test.ts (10 tests — lifecycle, token delivery, tamper detection, script gen) - new: agent.test.ts (4 tests — default opentoad, AGENT_OVERRIDE, invalid override) - new: models.test.ts (19 tests — parseModel, resolution, registry invariants) - update models.dev snapshot Made-with: Cursor * fix changed-agents.sh to filter legacy agent files from CI matrix legacy agent files (claude.ts, codex.ts, etc.) are @ts-nocheck and not exported from index.ts. changed-agents.sh now reads index.ts imports to build the active agent set and treats changes to inactive files as non-agent changes (opentoad canary only). Made-with: Cursor * remove MCP file tools, old agent harnesses, and obsolete security tests ASKPASS-based git auth makes the old MCP file tool security layer unnecessary: - token never in subprocess env, so symlink/gitattributes/hook attacks can't exfiltrate it - agents now use native file tools (OpenCode builtin read/edit) deleted: - action/mcp/file.ts (file_read, file_write, file_edit, file_delete, list_directory) - action/mcp/index.ts (dead re-export) - agent harnesses: claude.ts, codex.ts, cursor.ts, gemini.ts, opencode.ts - opencode-runner.ts (inlined into opentoad.ts) - security tests that validated MCP file tool restrictions - commented-out three-step review flow (~300 lines) - sanitizeSchema/wrapSchema dead code from mcp/shared.ts - OPENCODE_MODEL_MINI/MAX env vars (effort-level model overrides removed) updated test prompts to use generic file ops instead of MCP tool names. restored pkg-json-scripts + requirements-txt-attack (test --ignore-scripts defense). Made-with: Cursor * bump actions/checkout v4 → v6 (node 24) node 20 actions deprecated june 2, 2026. Made-with: Cursor * temporarily disable fail-fast on agnostic tests to debug checkout@v6 Made-with: Cursor * re-enable fail-fast on agnostic tests Made-with: Cursor * fix test token mismatch: mint OIDC tokens scoped to target repo CI tests override GITHUB_REPOSITORY to pullfrog/test-repo but inherit the runner's GITHUB_TOKEN (scoped to pullfrog/app), causing 401s on every run-context fetch. Clear GITHUB_TOKEN in the test subprocess so ensureGitHubToken() mints a properly scoped token via OIDC. Also centralizes the default GITHUB_REPOSITORY in runAgentStreaming instead of repeating it in every test file, and fixes preview-cleanup to remove workers from all queues (not just name-matching ones). Made-with: Cursor * fix ensureGitHubToken to try OIDC when app credentials are absent ensureGitHubToken only attempted token minting when GITHUB_APP_ID and GITHUB_PRIVATE_KEY were set. In CI, OIDC is available but app creds aren't exposed — so the guard prevented minting entirely. Made-with: Cursor * dead code cleanup: remove remnants of deleted agents, file tools, effort system remove unused @anthropic-ai/claude-agent-sdk and @openai/codex-sdk deps, orphaned file-tool security tests, dead GEMINI_MODEL passthrough, stale opencode-runner wiki refs, deleted test file references, and MCP file tool docs. rename docs/effort → docs/models. fix vitest setup: move dotenv to globalSetup (runs once before forks instead of per-file, 19s → 200ms). Made-with: Cursor * address review feedback: remove dead code, update stale references - remove AGENT_OVERRIDE (only opentoad exists) - remove shellToolName plumbing (always restricted shell) - bump action version to 0.0.179 - remove CURSOR_API_KEY from all workflows/configs - remove OPENCODE_MODEL_MINI/MAX from workflows/docs - delete wiki/effort.md, rewrite docs/effort.mdx as "Models" - rewrite wiki/modes.md: orchestrator/subagent → single agent - simplify flag system: drop builtin flag extraction (debug, effort, timeout, agent), keep custom flag replacement only - reserve all legacy flag names to prevent custom flag conflicts Made-with: Cursor * regenerate lockfile after removing claude-agent-sdk and codex-sdk Made-with: Cursor * fix import ordering, add lockfile check to pre-push hook Made-with: Cursor * remove dead debug payload field, stale packageExtensions Made-with: Cursor * merge proc-sandbox and token-exfil into a single test proc-sandbox and token-exfil were duplicative — both tested that SANDBOX_TEST_TOKEN couldn't be exfiltrated. consolidated into token-exfil with shell:restricted (which actually exercises filterEnv) and the /proc attack vector hints from proc-sandbox. Made-with: Cursor * fix wiki adversarial.md to match actual tokenExfil validator Made-with: Cursor
214 lines
8.0 KiB
TypeScript
214 lines
8.0 KiB
TypeScript
/**
|
|
* model alias registry.
|
|
*
|
|
* slugs use the format `provider/model-id` (e.g. "anthropic/claude-opus").
|
|
* bump `resolve` when a new model generation ships — the alias (slug) stays stable.
|
|
*/
|
|
|
|
// ── types ──────────────────────────────────────────────────────────────────────
|
|
|
|
export interface ModelAlias {
|
|
/** stable alias stored in DB, e.g. "anthropic/claude-opus" */
|
|
slug: string;
|
|
/** provider key (matches providers keys) */
|
|
provider: string;
|
|
/** human-readable name shown in dropdowns */
|
|
displayName: string;
|
|
/** concrete models.dev specifier, e.g. "anthropic/claude-opus-4-6" */
|
|
resolve: string;
|
|
/** top-tier pick for this provider — preferred during auto-select */
|
|
recommended: boolean;
|
|
}
|
|
|
|
interface ModelDef {
|
|
displayName: string;
|
|
/** concrete models.dev specifier, e.g. "anthropic/claude-opus-4-6" */
|
|
resolve: string;
|
|
recommended?: boolean;
|
|
}
|
|
|
|
export interface ProviderConfig {
|
|
displayName: string;
|
|
envVars: readonly string[];
|
|
models: Record<string, ModelDef>;
|
|
}
|
|
|
|
// ── provider + model definitions ────────────────────────────────────────────────
|
|
|
|
function provider(config: ProviderConfig): ProviderConfig {
|
|
return config;
|
|
}
|
|
|
|
export const providers = {
|
|
anthropic: provider({
|
|
displayName: "Anthropic",
|
|
envVars: ["ANTHROPIC_API_KEY"],
|
|
models: {
|
|
"claude-opus": {
|
|
displayName: "Claude Opus",
|
|
resolve: "anthropic/claude-opus-4-6",
|
|
recommended: true,
|
|
},
|
|
"claude-sonnet": { displayName: "Claude Sonnet", resolve: "anthropic/claude-sonnet-4-6" },
|
|
"claude-haiku": { displayName: "Claude Haiku", resolve: "anthropic/claude-haiku-4-5" },
|
|
},
|
|
}),
|
|
openai: provider({
|
|
displayName: "OpenAI",
|
|
envVars: ["OPENAI_API_KEY"],
|
|
models: {
|
|
"gpt-codex": { displayName: "GPT Codex", resolve: "openai/gpt-5.3-codex", recommended: true },
|
|
"gpt-codex-mini": { displayName: "GPT Codex Mini", resolve: "openai/codex-mini-latest" },
|
|
o3: { displayName: "O3", resolve: "openai/o3" },
|
|
},
|
|
}),
|
|
google: provider({
|
|
displayName: "Google",
|
|
envVars: ["GOOGLE_GENERATIVE_AI_API_KEY", "GEMINI_API_KEY"],
|
|
models: {
|
|
"gemini-pro": {
|
|
displayName: "Gemini Pro",
|
|
resolve: "google/gemini-3.1-pro-preview",
|
|
recommended: true,
|
|
},
|
|
"gemini-flash": { displayName: "Gemini Flash", resolve: "google/gemini-3-flash-preview" },
|
|
},
|
|
}),
|
|
xai: provider({
|
|
displayName: "xAI",
|
|
envVars: ["XAI_API_KEY"],
|
|
models: {
|
|
grok: { displayName: "Grok", resolve: "xai/grok-4", recommended: true },
|
|
"grok-fast": { displayName: "Grok Fast", resolve: "xai/grok-4-fast" },
|
|
"grok-code-fast": { displayName: "Grok Code Fast", resolve: "xai/grok-code-fast-1" },
|
|
},
|
|
}),
|
|
deepseek: provider({
|
|
displayName: "DeepSeek",
|
|
envVars: ["DEEPSEEK_API_KEY"],
|
|
models: {
|
|
"deepseek-reasoner": {
|
|
displayName: "DeepSeek Reasoner",
|
|
resolve: "deepseek/deepseek-reasoner",
|
|
recommended: true,
|
|
},
|
|
"deepseek-chat": { displayName: "DeepSeek Chat", resolve: "deepseek/deepseek-chat" },
|
|
},
|
|
}),
|
|
moonshotai: provider({
|
|
displayName: "Moonshot AI",
|
|
envVars: ["MOONSHOT_API_KEY"],
|
|
models: {
|
|
"kimi-k2": { displayName: "Kimi K2", resolve: "moonshotai/kimi-k2.5", recommended: true },
|
|
},
|
|
}),
|
|
opencode: provider({
|
|
displayName: "OpenCode",
|
|
envVars: ["OPENCODE_API_KEY"],
|
|
models: {
|
|
"big-pickle": {
|
|
displayName: "Big Pickle",
|
|
resolve: "opencode/big-pickle",
|
|
recommended: true,
|
|
},
|
|
"claude-opus": { displayName: "Claude Opus", resolve: "opencode/claude-opus-4-6" },
|
|
"claude-sonnet": { displayName: "Claude Sonnet", resolve: "opencode/claude-sonnet-4-6" },
|
|
"claude-haiku": { displayName: "Claude Haiku", resolve: "opencode/claude-haiku-4-5" },
|
|
"gpt-codex": { displayName: "GPT Codex", resolve: "opencode/gpt-5.3-codex" },
|
|
"gemini-pro": { displayName: "Gemini Pro", resolve: "opencode/gemini-3.1-pro" },
|
|
"gemini-flash": { displayName: "Gemini Flash", resolve: "opencode/gemini-3-flash" },
|
|
"kimi-k2": { displayName: "Kimi K2", resolve: "opencode/kimi-k2.5" },
|
|
"gpt-5-nano": { displayName: "GPT-5 Nano", resolve: "opencode/gpt-5-nano" },
|
|
"mimo-v2-flash-free": {
|
|
displayName: "MiMo V2 Flash",
|
|
resolve: "opencode/mimo-v2-flash-free",
|
|
},
|
|
"minimax-m2.5-free": { displayName: "MiniMax M2.5", resolve: "opencode/minimax-m2.5-free" },
|
|
},
|
|
}),
|
|
openrouter: provider({
|
|
displayName: "OpenRouter",
|
|
envVars: ["OPENROUTER_API_KEY"],
|
|
models: {
|
|
"claude-opus": {
|
|
displayName: "Claude Opus",
|
|
resolve: "openrouter/anthropic/claude-opus-4.6",
|
|
recommended: true,
|
|
},
|
|
"claude-sonnet": {
|
|
displayName: "Claude Sonnet",
|
|
resolve: "openrouter/anthropic/claude-sonnet-4.6",
|
|
},
|
|
"claude-haiku": {
|
|
displayName: "Claude Haiku",
|
|
resolve: "openrouter/anthropic/claude-haiku-4.5",
|
|
},
|
|
"gpt-codex": { displayName: "GPT Codex", resolve: "openrouter/openai/gpt-5.3-codex" },
|
|
"gpt-codex-mini": {
|
|
displayName: "GPT Codex Mini",
|
|
resolve: "openrouter/openai/gpt-5.1-codex-mini",
|
|
},
|
|
"gemini-pro": {
|
|
displayName: "Gemini Pro",
|
|
resolve: "openrouter/google/gemini-3.1-pro-preview",
|
|
},
|
|
"gemini-flash": {
|
|
displayName: "Gemini Flash",
|
|
resolve: "openrouter/google/gemini-3-flash-preview",
|
|
},
|
|
grok: { displayName: "Grok", resolve: "openrouter/x-ai/grok-4" },
|
|
"deepseek-chat": {
|
|
displayName: "DeepSeek Chat",
|
|
resolve: "openrouter/deepseek/deepseek-chat-v3.1",
|
|
},
|
|
"kimi-k2": { displayName: "Kimi K2", resolve: "openrouter/moonshotai/kimi-k2.5" },
|
|
},
|
|
}),
|
|
} satisfies Record<string, ProviderConfig>;
|
|
|
|
export type ModelProvider = keyof typeof providers;
|
|
|
|
// ── slug parsing ───────────────────────────────────────────────────────────────
|
|
|
|
export function parseModel(slug: string): { provider: string; model: string } {
|
|
const slashIdx = slug.indexOf("/");
|
|
if (slashIdx === -1) {
|
|
throw new Error(`invalid model slug "${slug}" — expected "provider/model"`);
|
|
}
|
|
return { provider: slug.slice(0, slashIdx), model: slug.slice(slashIdx + 1) };
|
|
}
|
|
|
|
export function getModelProvider(slug: string): string {
|
|
return parseModel(slug).provider;
|
|
}
|
|
|
|
export function getModelEnvVars(slug: string): string[] {
|
|
const p = getModelProvider(slug);
|
|
return (providers as Record<string, ProviderConfig>)[p]?.envVars.slice() ?? [];
|
|
}
|
|
|
|
// ── derived flat list ──────────────────────────────────────────────────────────
|
|
|
|
export const modelAliases: ModelAlias[] = Object.entries(providers).flatMap(
|
|
([providerKey, config]) =>
|
|
Object.entries(config.models).map(([modelId, def]) => ({
|
|
slug: `${providerKey}/${modelId}`,
|
|
provider: providerKey,
|
|
displayName: def.displayName,
|
|
resolve: def.resolve,
|
|
recommended: def.recommended ?? false,
|
|
}))
|
|
);
|
|
|
|
// ── resolution ─────────────────────────────────────────────────────────────────
|
|
|
|
/** resolve a model slug to its concrete models.dev specifier (e.g. "anthropic/claude-opus-4-6") */
|
|
export function resolveModelSlug(slug: string): string | undefined {
|
|
return modelAliases.find((a) => a.slug === slug)?.resolve;
|
|
}
|
|
|
|
/** resolve a model slug to the CLI-ready model string (full models.dev specifier) */
|
|
export function resolveCliModel(slug: string): string | undefined {
|
|
return resolveModelSlug(slug);
|
|
}
|