Files
PaperClipAI/cli/src/commands/client/prompt.ts
T
Aron PrinsandDevin Foley 70b1a9109d Improve CLI API parity coverage (#6626)
## Thinking Path

> - Paperclip is a control plane for AI-agent companies, with the CLI
acting as a scriptable operator and agent interface to that control
plane.
> - The REST API surface has grown across companies, agents, issues,
routines, plugins, auth, workspaces, secrets, and operational inspection
commands.
> - The CLI had drifted from that API surface: some commands were
missing, some command shapes differed from docs/reference material, and
several edge cases only failed during end-to-end local-source testing.
> - The local development runbook requires these tests to be disposable
and isolated from a real `~/.paperclip`, `~/.codex`, or `~/.claude`
installation.
> - This pull request adds broad CLI/API parity coverage, fixes the
actionable bugs found during that pass, and records the reproducible
test log under `doc/logs`.
> - The benefit is a more complete, scriptable CLI surface with
regression coverage for the command families exercised by the parity
run.

## What Changed

- Added or expanded CLI command coverage for access/auth, companies,
agents, projects, goals, issues and subresources, routines, plugins,
workspaces, activity/run/cost/dashboard inspection, assets, skills,
secrets, tokens, prompt/wake flows, and local setup helpers.
- Fixed CLI/API parity bugs found during the run, including context
profile patching, issue interaction optional payloads, malformed
tree-hold errors, environment duplicate handling, configure
invalid-section exit codes, worktree pnpm invocation, token agent ID
resolution, plugin tool worker lookup, and routine webhook secret
cleanup.
- Added missing CLI wrappers and route coverage for health/access,
invite resolution URL forwarding, join status normalization, secret
lifecycle commands, LLM docs routes, available-skill isolation, positive
board-claim coverage, and interactive `connect` prompt-flow tests.
- Added a schema-backed `/api/openapi.json` route sufficient for CLI
parity and `paperclipai openapi --json` smoke coverage.
- Added `doc/logs/2026-05-24-cli-api-parity-e2e-log.md` with the
detailed living test/bug log and renamed the log directory from
`doc/bugs` to `doc/logs`.
- Added `doc/plans/2026-05-23-cli-api-parity.md` and the OpenAPI parity
reference used during the pass.

OpenAPI note: this PR intentionally does not try to subsume
`feature/openapi-spec`. The OpenAPI implementation here is schema-backed
and better than the earlier route-inventory stub, but
`feature/openapi-spec` is the fuller/better OpenAPI branch because it
includes exact mounted-route coverage tests and additional current route
coverage. That branch should stay as its own PR and can supersede this
OpenAPI route implementation.

## Verification

Targeted automated checks run:

- `pnpm exec vitest run server/src/__tests__/openapi-routes.test.ts`
- `pnpm exec vitest run server/src/__tests__/board-claim.test.ts`
- `pnpm exec vitest run cli/src/__tests__/connect.test.ts`
- `pnpm exec vitest run cli/src/__tests__/agent-lifecycle.test.ts`
- `pnpm exec vitest run server/src/__tests__/plugin-database.test.ts`
- `pnpm exec vitest run server/src/__tests__/routines-service.test.ts`
- `pnpm --dir cli typecheck`
- `pnpm --dir server typecheck`

Manual/local E2E verification:

- Ran the full disposable local-source CLI/API parity pass with isolated
`PAPERCLIP_HOME`, `PAPERCLIP_CONFIG`, `PAPERCLIP_CONTEXT`,
`PAPERCLIP_AUTH_STORE`, `CODEX_HOME`, and `CLAUDE_HOME` under
`tmp/cli-api-parity`.
- Verified `DATABASE_URL` and `DATABASE_MIGRATION_URL` stayed unset for
the scratch server.
- Verified live health and schema-backed OpenAPI responses on
non-default port `3197`.
- Revoked created board/agent tokens and cleaned up temporary plugins,
secrets, non-default environments, and project workspaces.
- See `doc/logs/2026-05-24-cli-api-parity-e2e-log.md` for the full
command-by-command reproduction log.

Not run:

- Full `pnpm test`, `pnpm test:run`, or `pnpm build` were not run after
the entire branch because the branch is broad and the parity pass used
focused test/typecheck verification plus live isolated CLI reruns.

## Risks

- This is a broad PR and touches many CLI command modules, so review
surface is high. The changes are grouped around one theme, but a split
may be easier if maintainers prefer narrower PRs.
- The OpenAPI route in this PR is not the final/best OpenAPI
implementation. `feature/openapi-spec` has stronger exact-route coverage
and should remain the source for the dedicated OpenAPI PR.
- The living log is intentionally detailed and large. It is useful for
reproducibility but adds documentation weight.
- No UI changes are intended; screenshots are not applicable.

> For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and
discuss it in `#dev` before opening the PR. Feature PRs that overlap
with planned core work may need to be redirected — check the roadmap
first. See `CONTRIBUTING.md`.

## Model Used

- OpenAI Codex, GPT-5-based coding agent in Codex desktop. Exact served
model/context-window identifier was not exposed in the local app. Work
used shell/Git/GitHub CLI tooling, local source inspection, targeted
test execution, and live isolated Paperclip CLI/API smoke testing.

## Checklist

- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] If this change affects the UI, I have included before/after
screenshots
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] I will address all Greptile and reviewer comments before
requesting merge

---------

Co-authored-by: Devin Foley <devin@devinfoley.com>
2026-06-02 17:13:29 -07:00

277 lines
9.0 KiB
TypeScript

import { Command } from "commander";
import type { Agent, Issue, IssueComment } from "@paperclipai/shared";
import { addIssueCommentSchema, createIssueSchema } from "@paperclipai/shared";
import {
addCommonClientOptions,
apiPath,
handleCommandError,
printOutput,
resolveCommandContext,
type BaseClientOptions,
} from "./common.js";
interface PromptOptions extends BaseClientOptions {
agent?: string;
apiKeyEnv?: string;
issue?: string;
title?: string;
wake?: boolean;
companyId?: string;
}
interface PromptResult {
ok: true;
mode: "issue" | "comment";
actor: "agent" | "board";
apiBase: string;
companyId: string;
agent: {
id: string;
name: string;
urlKey?: string | null;
};
issue?: Issue | null;
comment?: IssueComment | null;
wakeup?: unknown;
}
export function registerPromptCommands(program: Command): void {
addCommonClientOptions(
program
.command("agent-prompt")
.description("Create/update Paperclip work for an agent using an agent API key")
.argument("<agent>", "Agent ID, shortname, or name")
.argument("<agentApiKey>", "Agent API key")
.argument("<prompt...>", "Prompt text")
.option("--issue <issueId>", "Append as a comment to an existing issue")
.option("--title <title>", "Issue title when creating a new issue")
.option("--no-wake", "Do not wake the agent after creating/updating work")
.action(async (agent: string, agentApiKey: string, promptParts: string[], opts: PromptOptions) => {
try {
const result = await runAgentPrompt(agent, promptParts.join(" "), {
...opts,
apiKey: agentApiKey,
wake: opts.wake,
});
printOutput(result, { json: opts.json });
} catch (err) {
handleCommandError(err);
}
}),
);
const agent = program.commands.find((cmd) => cmd.name() === "agent") ?? program.command("agent");
addCommonClientOptions(
agent
.command("prompt")
.description("Create/update Paperclip work using an agent persona")
.argument("<prompt...>", "Prompt text")
.option("--agent <agent>", "Agent ID, shortname, or name; defaults to profile/identity agent")
.option("--api-key-env <name>", "Read the agent API key from this environment variable")
.option("--issue <issueId>", "Append as a comment to an existing issue")
.option("--title <title>", "Issue title when creating a new issue")
.option("--no-wake", "Do not wake the agent after creating/updating work")
.action(async (promptParts: string[], opts: PromptOptions) => {
try {
const apiKey = readApiKeyEnvOption(opts);
const result = await runAgentPrompt(opts.agent, promptParts.join(" "), {
...opts,
apiKey: apiKey ?? opts.apiKey,
wake: opts.wake,
});
printOutput(result, { json: opts.json });
} catch (err) {
handleCommandError(err);
}
}),
);
const board = program.command("board").description("Board operator operations");
addCommonClientOptions(
board
.command("prompt")
.description("Create/update Paperclip work for an agent using board auth")
.requiredOption("--agent <agent>", "Target agent ID, shortname, or name")
.option("-C, --company-id <id>", "Company ID")
.option("--issue <issueId>", "Append as a comment to an existing issue")
.option("--title <title>", "Issue title when creating a new issue")
.option("--no-wake", "Do not wake the agent after creating/updating work")
.argument("<prompt...>", "Prompt text")
.action(async (promptParts: string[], opts: PromptOptions) => {
try {
const result = await runBoardPrompt(opts.agent ?? "", promptParts.join(" "), opts);
printOutput(result, { json: opts.json });
} catch (err) {
handleCommandError(err);
}
}),
{ includeCompany: false },
);
}
export async function runAgentPrompt(
agentRef: string | undefined,
prompt: string,
opts: PromptOptions,
): Promise<PromptResult> {
const ctx = resolveCommandContext(opts);
if (ctx.profile.persona && ctx.profile.persona !== "agent") {
throw new Error(`Profile '${ctx.profileName}' is persona=${ctx.profile.persona}; use an agent profile or board prompt.`);
}
const body = normalizePrompt(prompt);
const me = await ctx.api.get<Agent>("/api/agents/me");
if (!me) throw new Error("Agent authentication failed");
const expectedRef = agentRef?.trim() || ctx.profile.agentId || me.id;
assertAgentMatchesReference(me, expectedRef);
const result = await createOrCommentForAgent({
api: ctx.api,
actor: "agent",
agent: me,
companyId: me.companyId,
prompt: body,
issueId: opts.issue,
title: opts.title,
wake: opts.wake !== false,
});
return result;
}
export async function runBoardPrompt(
agentRef: string,
prompt: string,
opts: PromptOptions,
): Promise<PromptResult> {
const ctx = resolveCommandContext(opts, { requireCompany: true });
if (ctx.profile.persona && ctx.profile.persona !== "board") {
throw new Error(`Profile '${ctx.profileName}' is persona=${ctx.profile.persona}; use an agent prompt command or a board profile.`);
}
const body = normalizePrompt(prompt);
const query = new URLSearchParams({ companyId: ctx.companyId ?? "" });
const agent = await ctx.api.get<Agent>(`${apiPath`/api/agents/${agentRef}`}?${query.toString()}`);
if (!agent) throw new Error(`Agent not found: ${agentRef}`);
return createOrCommentForAgent({
api: ctx.api,
actor: "board",
agent,
companyId: ctx.companyId ?? agent.companyId,
prompt: body,
issueId: opts.issue,
title: opts.title,
wake: opts.wake !== false,
});
}
async function createOrCommentForAgent(input: {
api: {
apiBase: string;
post<T>(path: string, body?: unknown): Promise<T | null>;
};
actor: "agent" | "board";
agent: Agent;
companyId: string;
prompt: string;
issueId?: string;
title?: string;
wake: boolean;
}): Promise<PromptResult> {
if (input.issueId?.trim()) {
const payload = addIssueCommentSchema.parse({
body: input.prompt,
resume: input.wake,
});
const comment = await input.api.post<IssueComment>(apiPath`/api/issues/${input.issueId.trim()}/comments`, payload);
const wakeup = input.wake
? await wakeAgent(input.api, input.agent.id, input.issueId.trim(), "Prompt comment handoff")
: null;
return {
ok: true,
mode: "comment",
actor: input.actor,
apiBase: input.api.apiBase,
companyId: input.companyId,
agent: agentSummary(input.agent),
comment,
wakeup,
};
}
const payload = createIssueSchema.parse({
title: input.title?.trim() || defaultPromptTitle(input.prompt),
description: input.prompt,
status: "todo",
priority: "medium",
assigneeAgentId: input.agent.id,
});
const issue = await input.api.post<Issue>(apiPath`/api/companies/${input.companyId}/issues`, payload);
const wakeup = input.wake && issue?.id
? await wakeAgent(input.api, input.agent.id, issue.id, "Prompt issue handoff")
: null;
return {
ok: true,
mode: "issue",
actor: input.actor,
apiBase: input.api.apiBase,
companyId: input.companyId,
agent: agentSummary(input.agent),
issue,
wakeup,
};
}
function wakeAgent(
api: { post<T>(path: string, body?: unknown): Promise<T | null> },
agentId: string,
issueId: string,
reason: string,
): Promise<unknown> {
return api.post(apiPath`/api/agents/${agentId}/wakeup`, {
source: "on_demand",
triggerDetail: "manual",
reason,
payload: { issueId },
});
}
function normalizePrompt(prompt: string): string {
const normalized = prompt.trim();
if (!normalized) throw new Error("Prompt text is required");
return normalized;
}
function defaultPromptTitle(prompt: string): string {
const firstLine = prompt.split(/\r?\n/).map((line) => line.trim()).find(Boolean) ?? "Prompt handoff";
return firstLine.length > 100 ? `${firstLine.slice(0, 97)}...` : firstLine;
}
function assertAgentMatchesReference(agent: Agent, reference: string): void {
const normalized = reference.trim().toLowerCase();
if (!normalized) throw new Error("Agent reference is required");
const matches = [
agent.id,
agent.name,
typeof agent.urlKey === "string" ? agent.urlKey : null,
].some((value) => value?.toLowerCase() === normalized);
if (!matches) {
throw new Error(
`Agent key belongs to ${agent.name} (${agent.id}), not '${reference}'. Use the matching agent or a board prompt.`,
);
}
}
function agentSummary(agent: Agent): PromptResult["agent"] {
return {
id: agent.id,
name: agent.name,
urlKey: typeof agent.urlKey === "string" ? agent.urlKey : null,
};
}
function readApiKeyEnvOption(opts: PromptOptions): string | undefined {
if (!opts.apiKeyEnv?.trim()) return undefined;
const value = process.env[opts.apiKeyEnv.trim()]?.trim();
if (!value) throw new Error(`Environment variable ${opts.apiKeyEnv.trim()} is not set`);
return value;
}