Files
shockbot/external.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

266 lines
7.9 KiB
TypeScript

/**
* ⚠️ LIMITED IMPORTS - this file is imported by Next.js and must avoid pulling in backend code.
* All shared constants, types, and data used by both the Next.js app and the action runtime live here.
* Other files in action/ re-export from this file for backward compatibility.
*/
// mcp name constant
export const ghPullfrogMcpName = "gh_pullfrog";
// model alias registry lives in models.ts — re-exported here for shared access
export type { ModelAlias, ModelProvider, ProviderConfig } from "./models.ts";
export {
getModelEnvVars,
getModelProvider,
modelAliases,
parseModel,
providers,
resolveCliModel,
resolveModelSlug,
} from "./models.ts";
// tool permission types shared with server dispatch
export type ToolPermission = "disabled" | "enabled";
export type ShellPermission = "disabled" | "restricted" | "enabled";
export type PushPermission = "disabled" | "restricted" | "enabled";
// workflow yml permissions for GITHUB_TOKEN
export type WorkflowPermissionValue = "read" | "write" | "none";
export type WorkflowIdTokenPermissionValue = "write" | "none";
export interface WorkflowPermissions {
actions?: WorkflowPermissionValue;
attestations?: WorkflowPermissionValue;
checks?: WorkflowPermissionValue;
contents?: WorkflowPermissionValue;
deployments?: WorkflowPermissionValue;
discussions?: WorkflowPermissionValue;
"id-token"?: WorkflowIdTokenPermissionValue;
issues?: WorkflowPermissionValue;
models?: WorkflowPermissionValue;
packages?: WorkflowPermissionValue;
pages?: WorkflowPermissionValue;
"pull-requests"?: WorkflowPermissionValue;
"repository-projects"?: WorkflowPermissionValue;
"security-events"?: WorkflowPermissionValue;
statuses?: WorkflowPermissionValue;
}
// permission level for the author who triggered the event
// matches GitHub's permission levels: admin > write > maintain > triage > read > none
export type AuthorPermission = "admin" | "maintain" | "write" | "triage" | "read" | "none";
// base interface for common payload event fields
interface BasePayloadEvent {
issue_number?: number;
is_pr?: boolean;
branch?: string;
/** title of the issue/PR (or contextual title for comments) */
title?: string;
/** primary content for this trigger (issue body, PR body, comment body, review body, etc.) */
body?: string | null;
comment_id?: number;
review_id?: number;
review_state?: string;
thread?: any;
pull_request?: any;
check_suite?: {
id: number;
head_sha: string;
head_branch: string | null;
status: string | null;
conclusion: string | null;
url: string;
};
comment_ids?: number[] | "all";
/** permission level of the user who triggered this event */
authorPermission?: AuthorPermission;
/** when true, runs silently without progress comments (e.g., auto-labeling) */
silent?: boolean;
[key: string]: any;
}
interface PullRequestOpenedEvent extends BasePayloadEvent {
trigger: "pull_request_opened";
issue_number: number;
is_pr: true;
title: string;
body: string | null;
branch: string;
}
interface PullRequestReadyForReviewEvent extends BasePayloadEvent {
trigger: "pull_request_ready_for_review";
issue_number: number;
is_pr: true;
title: string;
body: string | null;
branch: string;
}
interface PullRequestReviewRequestedEvent extends BasePayloadEvent {
trigger: "pull_request_review_requested";
issue_number: number;
is_pr: true;
title: string;
body: string | null;
branch: string;
}
interface PullRequestReviewSubmittedEvent extends BasePayloadEvent {
trigger: "pull_request_review_submitted";
issue_number: number;
is_pr: true;
review_id: number;
/** review body is the primary content */
body: string | null;
review_state: string;
branch: string;
}
interface PullRequestReviewCommentCreatedEvent extends BasePayloadEvent {
trigger: "pull_request_review_comment_created";
issue_number: number;
is_pr: true;
title: string;
comment_id: number;
/** comment body is the primary content (null if already in prompt) */
body: string | null;
thread?: any;
branch: string;
}
interface IssuesOpenedEvent extends BasePayloadEvent {
trigger: "issues_opened";
issue_number: number;
title: string;
body: string | null;
}
interface IssuesAssignedEvent extends BasePayloadEvent {
trigger: "issues_assigned";
issue_number: number;
title: string;
body: string | null;
}
interface IssuesLabeledEvent extends BasePayloadEvent {
trigger: "issues_labeled";
issue_number: number;
title: string;
body: string | null;
}
interface IssueCommentCreatedEvent extends BasePayloadEvent {
trigger: "issue_comment_created";
comment_id: number;
/** distinguishes this from PR review comments (which use pull_request_review_comment_created) */
comment_type: "issue";
/** comment body is the primary content (null if already in prompt) */
body: string | null;
issue_number: number;
// PR-specific fields (only present when is_pr is true)
is_pr?: true;
branch?: string;
title?: string;
}
interface CheckSuiteCompletedEvent extends BasePayloadEvent {
trigger: "check_suite_completed";
issue_number: number;
is_pr: true;
title: string;
body: string | null;
pull_request: any;
branch: string;
check_suite: {
id: number;
head_sha: string;
head_branch: string | null;
status: string | null;
conclusion: string | null;
url: string;
};
}
interface WorkflowDispatchEvent extends BasePayloadEvent {
trigger: "workflow_dispatch";
}
interface FixReviewEvent extends BasePayloadEvent {
trigger: "fix_review";
issue_number: number;
is_pr: true;
review_id: number;
/** when true, only address comments the triggerer approved with 👍 (vs all comments) */
approved_only?: boolean | undefined;
}
interface ImplementPlanEvent extends BasePayloadEvent {
trigger: "implement_plan";
issue_number: number;
plan_comment_id: number;
/** plan content is the primary content (null if already in prompt) */
body: string | null;
}
interface PullRequestSynchronizeEvent extends BasePayloadEvent {
trigger: "pull_request_synchronize";
issue_number: number;
is_pr: true;
title: string;
body: string | null;
branch: string;
/** SHA before the push -- used to compute incremental diff via `git diff before_sha...HEAD` */
before_sha: string;
}
interface UnknownEvent extends BasePayloadEvent {
trigger: "unknown";
}
// discriminated union for payload event based on trigger
// note: all events use issue_number for consistency (PRs are issues in GitHub's API)
export type PayloadEvent =
| PullRequestOpenedEvent
| PullRequestReadyForReviewEvent
| PullRequestSynchronizeEvent
| PullRequestReviewRequestedEvent
| PullRequestReviewSubmittedEvent
| PullRequestReviewCommentCreatedEvent
| IssuesOpenedEvent
| IssuesAssignedEvent
| IssuesLabeledEvent
| IssueCommentCreatedEvent
| CheckSuiteCompletedEvent
| WorkflowDispatchEvent
| FixReviewEvent
| ImplementPlanEvent
| UnknownEvent;
// writeable payload type for building payloads
export interface WriteablePayload {
"~pullfrog": true;
/** semantic version of the payload to ensure compatibility */
version: string;
/** provider/model slug (e.g. "anthropic/claude-opus") */
model?: string | undefined;
/** the user's actual request (body if @pullfrog tagged) */
prompt: string;
/** github username of the human who triggered this workflow run */
triggerer?: string | undefined;
/** event-level instructions for this trigger type (flag-expanded server-side) */
eventInstructions?: string | undefined;
/** event data from webhook payload - discriminated union based on trigger field */
event: PayloadEvent;
/** timeout for agent run (e.g., "10m", "1h30m") - defaults to "1h" */
timeout?: string | undefined;
/** working directory for the agent */
cwd?: string | undefined;
/** pre-created progress comment ID for updating status */
progressCommentId?: string | undefined;
}
// immutable payload type for agent execution
export type Payload = Readonly<WriteablePayload>;