Files
shockbot/main.ts
T
Colin McDonnell 6d25adfd1a Agent & model refactor (#478)
* 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
2026-03-12 05:22:51 +00:00

329 lines
12 KiB
TypeScript

// changes to tool permissions should be reflected in wiki/granular-tools.md
import * as core from "@actions/core";
import {
initToolState,
startMcpHttpServer,
type ToolContext,
type ToolState,
} from "./mcp/server.ts";
import { computeModes } from "./modes.ts";
import {
type ActivityTimeout,
createProcessOutputActivityTimeout,
DEFAULT_ACTIVITY_CHECK_INTERVAL_MS,
DEFAULT_ACTIVITY_TIMEOUT_MS,
} from "./utils/activity.ts";
import { resolveAgent } from "./utils/agent.ts";
import { validateAgentApiKey } from "./utils/apiKeys.ts";
import { resolveBody } from "./utils/body.ts";
import { formatUsageSummary, log, writeSummary } from "./utils/cli.ts";
import { reportErrorToComment } from "./utils/errorReport.ts";
import { onExitSignal } from "./utils/exitHandler.ts";
import { resolveGit, setGitAuthServer } from "./utils/gitAuth.ts";
import { startGitAuthServer } from "./utils/gitAuthServer.ts";
import { createOctokit, writeGitHubUsageSummaryToFile } from "./utils/github.ts";
import { resolveInstructions } from "./utils/instructions.ts";
import { executeLifecycleHook } from "./utils/lifecycle.ts";
import { normalizeEnv } from "./utils/normalizeEnv.ts";
import { resolvePayload, resolvePromptInput } from "./utils/payload.ts";
import { postReviewCleanup } from "./utils/reviewCleanup.ts";
import { handleAgentResult } from "./utils/run.ts";
import { resolveRunContextData } from "./utils/runContextData.ts";
import { createTempDirectory, setupGit } from "./utils/setup.ts";
import { killTrackedChildren } from "./utils/subprocess.ts";
import { parseTimeString, TIMEOUT_DISABLED } from "./utils/time.ts";
import { Timer } from "./utils/timer.ts";
import { getJobToken, resolveTokens } from "./utils/token.ts";
import { resolveRun } from "./utils/workflow.ts";
export { Inputs } from "./utils/payload.ts";
export interface MainResult {
success: boolean;
output?: string | undefined;
error?: string | undefined;
result?: string | undefined;
}
function resolveOutputSchema(): Record<string, unknown> | undefined {
const raw = core.getInput("output_schema");
if (!raw) return undefined;
let parsed: unknown;
try {
parsed = JSON.parse(raw);
} catch {
throw new Error(`invalid output_schema: not valid JSON`);
}
if (!parsed || typeof parsed !== "object" || Array.isArray(parsed)) {
throw new Error(`invalid output_schema: must be a JSON object`);
}
log.info("» structured output schema provided — output will be required");
return parsed as Record<string, unknown>;
}
async function writeJobSummary(toolState: ToolState): Promise<void> {
const usageSummary = formatUsageSummary(toolState.usageEntries);
const summaryParts = [toolState.lastProgressBody, usageSummary].filter(Boolean);
if (summaryParts.length > 0) {
await writeSummary(summaryParts.join("\n\n"));
}
}
export async function main(): Promise<MainResult> {
// normalize env var names to uppercase (handles case-insensitive workflow files)
normalizeEnv();
// write usage summary on SIGINT/SIGTERM so the worker can read it after sandbox.exec
const usageSummaryPath = process.env.PULLFROG_USAGE_SUMMARY_PATH;
if (usageSummaryPath) {
onExitSignal(() => writeGitHubUsageSummaryToFile(usageSummaryPath));
}
const timer = new Timer();
let activityTimeout: ActivityTimeout | null = null;
// parse prompt early to extract progressCommentId for toolState
const resolvedPromptInput = resolvePromptInput();
const toolState = initToolState({
progressCommentId:
typeof resolvedPromptInput !== "string" ? resolvedPromptInput.progressCommentId : undefined,
});
// resolve and fingerprint git binary before any agent code runs
resolveGit();
// get job token for initial API calls
const jobToken = getJobToken();
const initialOctokit = createOctokit(jobToken);
const runContext = await resolveRunContextData({ octokit: initialOctokit, token: jobToken });
timer.checkpoint("runContextData");
// resolve payload to determine shell permission
const payload = resolvePayload(resolvedPromptInput, runContext.repoSettings);
// resolve tokens:
// - gitToken: contents permission based on push setting (assumed exfiltratable)
// - mcpToken: full installation token (not exfiltratable via MCP tools)
await using tokenRef = await resolveTokens({ push: payload.push });
// clear OIDC env vars in restricted mode to prevent agent from minting tokens
if (payload.shell !== "enabled") {
delete process.env.ACTIONS_ID_TOKEN_REQUEST_URL;
delete process.env.ACTIONS_ID_TOKEN_REQUEST_TOKEN;
}
// create octokit with MCP token for GitHub API calls
const octokit = createOctokit(tokenRef.mcpToken);
const runInfo = await resolveRun({ octokit });
let toolContext: ToolContext | undefined;
try {
if (payload.cwd && process.cwd() !== payload.cwd) {
process.chdir(payload.cwd);
}
// resolve body - fetches body_html and converts to markdown if images present
// this ensures agents receive markdown with working signed image URLs
const originalBody = payload.event.body;
const resolvedBody = await resolveBody({
event: payload.event,
octokit,
repo: runContext.repo,
});
if (resolvedBody !== originalBody) {
payload.event.body = resolvedBody;
// also update prompt if original body was included there
if (originalBody && payload.prompt.includes(originalBody)) {
payload.prompt = payload.prompt.replace(originalBody, resolvedBody ?? "");
}
}
const tmpdir = createTempDirectory();
await using gitAuthServer = await startGitAuthServer(tmpdir);
setGitAuthServer(gitAuthServer);
const agent = resolveAgent();
validateAgentApiKey({
agent,
owner: runContext.repo.owner,
name: runContext.repo.name,
});
await setupGit({
gitToken: tokenRef.gitToken,
owner: runContext.repo.owner,
name: runContext.repo.name,
octokit,
toolState,
shell: payload.shell,
postCheckoutScript: runContext.repoSettings.postCheckoutScript,
});
timer.checkpoint("git");
// execute setup lifecycle hook (runs once at initialization)
await executeLifecycleHook({
event: "setup",
script: runContext.repoSettings.setupScript,
});
timer.checkpoint("lifecycleHooks::setup");
const modes = [...computeModes(), ...runContext.repoSettings.modes];
const outputSchema = resolveOutputSchema();
// mcpServerUrl and tmpdir are set after server starts
toolContext = {
repo: runContext.repo,
payload,
octokit,
githubInstallationToken: tokenRef.mcpToken,
gitToken: tokenRef.gitToken,
apiToken: runContext.apiToken,
modes,
postCheckoutScript: runContext.repoSettings.postCheckoutScript,
prApproveEnabled: runContext.repoSettings.prApproveEnabled,
modeInstructions: runContext.repoSettings.modeInstructions,
toolState,
runId: runInfo.runId,
jobId: runInfo.jobId,
mcpServerUrl: "",
tmpdir,
};
await using mcpHttpServer = await startMcpHttpServer(toolContext, { outputSchema });
toolContext.mcpServerUrl = mcpHttpServer.url;
log.info(`» MCP server started at ${mcpHttpServer.url}`);
timer.checkpoint("mcpServer");
const instructions = resolveInstructions({
payload,
repo: runContext.repo,
modes,
outputSchema,
});
// log instructions as soon as they are fully resolved
const logParts = [
instructions.eventInstructions
? `EVENT-LEVEL INSTRUCTIONS:\n${instructions.eventInstructions}`
: null,
instructions.user ? `USER REQUEST:\n${instructions.user}` : null,
instructions.event,
].filter(Boolean);
log.box(logParts.join("\n\n---\n\n"), {
title: "Instructions",
});
// run agent, optionally with timeout enforcement
activityTimeout = createProcessOutputActivityTimeout({
timeoutMs: DEFAULT_ACTIVITY_TIMEOUT_MS,
checkIntervalMs: DEFAULT_ACTIVITY_CHECK_INTERVAL_MS,
});
activityTimeout.promise.catch(() => {}); // prevent unhandled rejection if agent wins race
const agentPromise = agent.run({
payload,
mcpServerUrl: mcpHttpServer.url,
tmpdir,
instructions,
});
// timeout enforcement: default is 1 hour, but can be overridden via flags in the prompt:
// - --timeout=2h (or any duration like "--timeout=30m", "--timeout=1h30m") to set a custom timeout
// - --notimeout to disable timeout entirely
let result: Awaited<typeof agentPromise>;
if (payload.timeout === TIMEOUT_DISABLED) {
result = await Promise.race([agentPromise, activityTimeout.promise]);
} else {
const parsed = payload.timeout ? parseTimeString(payload.timeout) : null;
if (payload.timeout && parsed === null) {
log.warning(`invalid timeout format "${payload.timeout}", using default 1h`);
}
const timeoutMs = parsed ?? 3600000;
const actualTimeout = parsed !== null ? payload.timeout : "1h";
let timeoutId: NodeJS.Timeout | undefined;
const timeoutPromise = new Promise<never>((_, reject) => {
timeoutId = setTimeout(() => {
reject(new Error(`agent run timed out after ${actualTimeout}`));
}, timeoutMs);
});
timeoutPromise.catch(() => {}); // prevent unhandled rejection if agent wins race
try {
result = await Promise.race([agentPromise, timeoutPromise, activityTimeout.promise]);
} finally {
clearTimeout(timeoutId);
}
}
// accumulate top-level agent usage
if (result.usage) {
toolState.usageEntries.push(result.usage);
}
// validate this before writing job summary to avoid masking the error
if (outputSchema && !toolState.output) {
throw new Error(
"output_schema was provided but agent did not call set_output — structured output is required"
);
}
// post-agent review cleanup: reportReviewNodeId → follow-up dispatch → delete progress comment.
// runs after the agent exits so ordering is architecturally guaranteed (no LLM involvement).
// best-effort: cleanup failures must not turn a successful agent run into a failure.
if (toolContext) {
await postReviewCleanup(toolContext).catch((error) => {
log.debug(`post-review cleanup failed: ${error}`);
});
}
await writeJobSummary(toolState);
// emit structured output marker for test validation
if (toolState.output) {
log.info(`::pullfrog-output::${Buffer.from(toolState.output).toString("base64")}`);
core.setOutput("result", toolState.output);
}
return await handleAgentResult({
result,
toolState,
silent: payload.event.silent ?? false,
});
} catch (error) {
const errorMessage = error instanceof Error ? error.message : "unknown error occurred";
killTrackedChildren();
log.error(errorMessage);
// best-effort summary — don't mask the original error
try {
await writeJobSummary(toolState);
} catch {}
try {
await reportErrorToComment({ toolState, error: errorMessage });
} catch {
// error reporting failed, but don't let it mask the original error
}
// best-effort review cleanup (e.g., agent timed out after submitting a review)
if (toolContext) {
await postReviewCleanup(toolContext).catch((error) => {
log.debug(`post-review cleanup failed: ${error}`);
});
}
return {
success: false,
error: errorMessage,
};
} finally {
activityTimeout?.stop();
if (usageSummaryPath) {
await writeGitHubUsageSummaryToFile(usageSummaryPath);
}
}
}