mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-04 19:16:16 +01:00
First PR: runtime. UI: #15728. Qualification: #15729.
## Thinking Path
> - Paperclip manages agent work through tasks and governed connections.
> - Chat connections already bind external conversations to those tasks.
> - Speko handles voice and telephony, while the selected Paperclip
agent does the work.
> - A call needs durable session authority, ordered follow-ups, and safe
result delivery.
> - This PR adds an explicit voice transport to the existing connection
runtime.
> - The UI and qualification suites follow in linked PRs. Speko stays
experimental.
## Linked Issues or Issue Description
**Problem or motivation**
Phone and browser voice conversations cannot use the chat connection
task lifecycle. A separate voice runtime is needed to preserve task
authority, retries, and reply history.
**Proposed solution**
Add company-scoped voice sessions, signed callbacks, durable replies,
inbound intake, and an agent-facing outbound-call tool. Reuse existing
tasks, queues, secrets, and publications.
**Roadmap alignment**
This extends the experimental chat connector entry points under Agent
Chat and Connected Apps. The project owner requested this feature.
Refs #11418 for the original provider catalog proposal. This
implementation uses the newer chat connection infrastructure rather than
an MCP catalog-only integration. Refs #15721 for remote OpenCode
startup.
## What Changed
- Add additive voice schema, shared contracts, session APIs, and
provider callbacks.
- Bind browser, inbound, and outbound sessions to an endpoint, task, and
selected agent.
- Add low-trust guest intake in an explicitly selected sandbox and keep
ordinary approval rules.
- Submit task work through session-scoped tools and push approved
replies through Speko POST /v1/calls/{id}/messages.
- Distinguish provider acceptance from confirmed spoken playback.
Reconcile reports without downloading recordings.
- Add protocol, migration, persistence, provider, and
delivery-diagnostic tests.
## Verification
- Master 3389bea708 is integrated. Database/shared builds, server
typecheck, migration upgrade/replay checks, and 46
communication-guidance/provider/protocol tests passed.
- The final persistence suite passed 85 real-database tests. Five
focused native continuation/authorization regressions passed. Five
callback ownership/rotation tests passed after the last runtime repair.
- Review repairs cover reconnect ownership, current caller authority,
duplicate delivery, multipart answers, task-page answers, guest question
handling, and saved sandbox recovery.
- A real OpenCode/OpenRouter DeepSeek task ran in Daytona and saved a
correct disk-space answer. This did not establish live-call playback.
- Full local typecheck/build passed before the final repairs; focused
typechecks passed after them. Latest-head CI runs the repository gates.
- The separate integrated browser qualification passed two journeys and
failed browser answer retrieval. The feature remains experimental. The
report in #15729 records this failure and outstanding real-provider
acceptance.
- No lockfiles are included. Speko migrations follow master as
0324–0330.
## Risks
- Voice sessions add migrations and provider-dependent lifecycle
behavior. Migrations preserve existing chat and AI transports.
- Callback origins must be reachable HTTPS. Provider keys and signing
secrets remain vaulted.
- Unverified callers receive task-scoped low-trust authority. Caller ID
does not grant private task access.
- Outbound telephony incurs provider charges. Provider acceptance is not
proof that the caller heard an answer.
- Keep the feature behind the existing experimental chat setting until
the real browser, inbound, outbound, and delayed-result acceptance
matrix passes.
## Model Used
OpenAI Codex, GPT-6, with tool use and code execution. The exact serving
model ID and context window are not exposed in this session.
## 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 searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [ ] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
76 lines
4.0 KiB
TypeScript
76 lines
4.0 KiB
TypeScript
import { afterEach, describe, expect, it, vi } from "vitest";
|
|
import { resolveClaudeExecutionEngineForRun } from "./acp.js";
|
|
import { execute } from "./execute.js";
|
|
import { testEnvironment } from "./test.js";
|
|
|
|
const originalVersion = process.version;
|
|
afterEach(() => Object.defineProperty(process, "version", { value: originalVersion }));
|
|
|
|
describe("claude engine availability", () => {
|
|
it.each([undefined, "auto", "acp"])("reports a setup failure for engine=%s without starting a process", async (engine) => {
|
|
Object.defineProperty(process, "version", { value: "v18.0.0" });
|
|
const config = { engine };
|
|
const onSpawn = vi.fn();
|
|
const result = await execute({ config, onSpawn } as never);
|
|
expect(result).toMatchObject({
|
|
exitCode: 1,
|
|
errorCode: "adapter_engine_unavailable",
|
|
errorMessage: expect.stringContaining("Node v18.0.0"),
|
|
resultJson: { executionRecovery: { kind: "bootstrap", providerWorkStarted: false } },
|
|
});
|
|
expect(result.errorMessage).toContain(process.execPath);
|
|
expect(onSpawn).not.toHaveBeenCalled();
|
|
const diagnostic = await testEnvironment({ config } as never);
|
|
expect(diagnostic.status).toBe("fail");
|
|
expect(diagnostic.checks).toContainEqual(expect.objectContaining({
|
|
code: "adapter_engine_unavailable", level: "error",
|
|
}));
|
|
});
|
|
|
|
it("does not apply ACP prerequisites to explicitly selected CLI", async () => {
|
|
Object.defineProperty(process, "version", { value: "v18.0.0" });
|
|
await expect(resolveClaudeExecutionEngineForRun({ config: { engine: "cli" } }))
|
|
.resolves.toEqual({ engine: "cli", explicit: true });
|
|
});
|
|
|
|
it("keeps an unavailable ACP command as a failure, not a CLI selection", async () => {
|
|
Object.defineProperty(process, "version", { value: "v24.11.0" });
|
|
const result = await resolveClaudeExecutionEngineForRun({
|
|
config: { agentCommand: "/nonexistent/paperclip-test/acp", command: "/nonexistent/paperclip-test/acp" },
|
|
});
|
|
expect(result.engine).toBe("acp");
|
|
expect(result.unavailableReason).toContain("not available");
|
|
});
|
|
});
|
|
|
|
|
|
describe("cold sandbox ACP setup", () => {
|
|
it("installs the default ACP server inside the selected sandbox without switching engines", async () => {
|
|
Object.defineProperty(process, "version", { value: "v24.11.0" });
|
|
let installed = false;
|
|
const commands: string[] = [];
|
|
const runner = { execute: async (input: { args: string[]; env?: Record<string, string> }) => {
|
|
const command = input.args.join(" ");
|
|
commands.push(command);
|
|
expect(input.env?.ANTHROPIC_API_KEY).toBeUndefined();
|
|
if (command.includes("npm install")) installed = true;
|
|
return { exitCode: installed ? 0 : 1, timedOut: false, signal: null, stdout: installed ? "/usr/local/bin/claude-agent-acp" : "", stderr: "", pid: null, startedAt: new Date().toISOString() };
|
|
}};
|
|
await expect(resolveClaudeExecutionEngineForRun({ config: {}, executionTarget: {
|
|
kind: "remote", transport: "sandbox", providerKey: "daytona", remoteCwd: "/work", runner,
|
|
} as never })).resolves.toEqual({ engine: "acp", explicit: false });
|
|
expect(commands.filter(command => command.includes("npm install"))).toHaveLength(1);
|
|
expect(commands.some(command => command.includes("@agentclientprotocol/claude-agent-acp@0.73.0"))).toBe(true);
|
|
});
|
|
|
|
it("does not install or substitute for an operator's unavailable custom ACP command", async () => {
|
|
Object.defineProperty(process, "version", { value: "v24.11.0" });
|
|
const runner = { execute: vi.fn(async () => ({ exitCode: 1, timedOut: false, stdout: "", stderr: "", signal: null, pid: null, startedAt: new Date().toISOString() })) };
|
|
const result = await resolveClaudeExecutionEngineForRun({ config: { agentCommand: "custom-acp" }, executionTarget: {
|
|
kind: "remote", transport: "sandbox", providerKey: "daytona", remoteCwd: "/work", runner,
|
|
} as never });
|
|
expect(result).toMatchObject({ engine: "acp", unavailableReason: expect.stringContaining("custom-acp") });
|
|
expect(runner.execute).toHaveBeenCalledTimes(1);
|
|
});
|
|
});
|