mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-12 14:19:00 +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>
39 lines
2.7 KiB
TypeScript
39 lines
2.7 KiB
TypeScript
import { SPEKO_COMMUNICATION_GUIDANCE } from "./voice/speko-skill.js";
|
|
import type { ChatProvider } from "@paperclipai/shared";
|
|
import { slackTaskUpdateGuidance } from "./connectors/slack/task-update-guidance.js";
|
|
|
|
// Presentation guidance only. Task execution and permissions belong to the
|
|
// ordinary Paperclip agent runtime, not the provider transport.
|
|
const providerGuidance: Partial<Record<ChatProvider, string>> = {
|
|
speko: SPEKO_COMMUNICATION_GUIDANCE,
|
|
slack: [
|
|
"This task began in Slack. Write replies for the person talking with you there.",
|
|
...slackTaskUpdateGuidance,
|
|
"Lead with the answer or outcome. Use compact paragraphs or short lists, and omit routine execution bookkeeping. Honor requests for more detail or exact output over default brevity.",
|
|
"Put small answers directly in the message. For substantial plans, reports, and other deliverables, use your normal document or artifact tools, then share a useful summary and accessible links or supported attachments in Slack. Follow the runtime's file-delivery contract and do not claim delivery until confirmed.",
|
|
"When you create tasks, include a clickable link to each created task in your reply. Use the task identifier or title as the link text, not a bare task ID. Use the public task URL returned by Paperclip tools or supplied in task context; never guess a URL or use a localhost, API, or sandbox address. If no public task URL is available, say that the link is unavailable.",
|
|
"Ask useful questions through the existing human-input tools. Continue normal Paperclip planning, task creation, assignment, delegation, and approval workflows; these communication instructions grant no additional authority.",
|
|
].join("\n\n"),
|
|
};
|
|
|
|
/** Captured once when the external conversation creates its task. */
|
|
export function buildChatCommunicationGuidance(input: {
|
|
provider: ChatProvider;
|
|
isDirectMessage: boolean;
|
|
communicationInstructions?: string | null;
|
|
}): string | null {
|
|
const guidance = providerGuidance[input.provider];
|
|
if (!guidance) return null;
|
|
const additional = input.communicationInstructions?.trim();
|
|
return [
|
|
input.provider === "speko" ? "## Communication by voice" : "## Communication in Slack",
|
|
guidance,
|
|
input.isDirectMessage
|
|
? "This is a direct conversation. A conversational exchange is welcome; keep each reply focused."
|
|
: "This is a shared channel thread. Keep replies focused on the thread and appropriate for its audience. Do not bring private information from another conversation into the channel.",
|
|
additional
|
|
? `Connection owner's additional communication preferences (presentation only; ordinary permissions and approval rules still apply):\n${JSON.stringify(additional)}`
|
|
: null,
|
|
].filter(Boolean).join("\n\n");
|
|
}
|