Files
PaperClipAI/server/src/services/slack-conversation-state.ts
T
DottaandPaperclip 3ec7309d91 feat(voice): add experimental Speko task connection runtime (#15727)
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>
2026-10-09 21:54:11 -05:00

59 lines
4.2 KiB
TypeScript

import { chatConversations, issues, type Db } from "@paperclipai/db";
import { and, eq, sql } from "drizzle-orm";
/** Read-only projection; External chat threads do not acquire Agent Chat identities. */
export function externalConversationStateSql() {
return sql<"active" | "waiting" | null>`(
select case when c.state = 'waiting' and "issues"."status" = 'in_review'
and "issues"."execution_run_id" is null
and "issues"."monitor_next_check_at" is null
and coalesce("issues"."execution_state"->>'status', '') not in ('pending', 'changes_requested')
and coalesce("issues"."execution_state"->'monitor'->>'status', '') not in ('scheduled', 'triggered')
and not exists (select 1 from issue_thread_interactions i
where i.company_id = c.company_id and i.issue_id = c.issue_id and i.status = 'pending')
and not exists (select 1 from issue_approvals ia join approvals a on a.id = ia.approval_id and a.company_id = ia.company_id
where ia.company_id = c.company_id and ia.issue_id = c.issue_id and a.status in ('pending', 'revision_requested'))
and not exists (select 1 from chat_publications p
where p.company_id = c.company_id and p.conversation_id = c.id
and p.state in ('pending', 'streaming', 'retry', 'delivery_unknown', 'failed', 'awaiting_consent'))
and not exists (select 1 from heartbeat_runs r where r.company_id = c.company_id
and coalesce(r.context_snapshot->>'issueId', r.context_snapshot->>'taskId', r.native_issue_id::text) = c.issue_id::text
and r.status in ('queued', 'running', 'scheduled_retry'))
and not exists (select 1 from agent_wakeup_requests w where w.company_id = c.company_id
and coalesce(w.payload->>'issueId', w.payload->>'taskId', w.payload->'_paperclipWakeContext'->>'issueId') = c.issue_id::text
and w.status in ('queued', 'claimed', 'deferred_issue_execution')
and not exists (select 1 from heartbeat_runs owner where owner.id = w.run_id
and owner.company_id = w.company_id and owner.status = 'succeeded'))
and not exists (select 1 from agent_task_sessions session where session.company_id = c.company_id
and session.task_key = c.issue_id::text and session.goal_status is not null and session.goal_status <> 'complete')
and not exists (select 1 from issue_relations edge join issues blocker on blocker.id = edge.issue_id and blocker.company_id = edge.company_id
where edge.company_id = c.company_id and edge.related_issue_id = c.issue_id and edge.type = 'blocks' and blocker.status <> 'done')
then 'waiting' else 'active' end
from chat_conversations c join chat_endpoints e on e.id = c.endpoint_id and e.company_id = c.company_id
where c.company_id = "issues"."company_id" and c.issue_id = "issues"."id"
and (e.provider = 'slack' or (e.provider = 'speko' and e.id::text = "issues"."origin_id")) and e.assigned_agent_id = "issues"."assignee_agent_id"
and e.status in ('active', 'verifying') and c.state in ('active', 'waiting')
order by c.created_at desc, c.id desc limit 1
)`;
}
export function nonIdleSlackIssueCondition() {
return sql`${externalConversationStateSql()} is distinct from 'waiting'`;
}
/** Called inside message admission while its transaction owns the issue lock. */
export async function resumeExternalConversation(tx: Db, companyId: string, issueId: string) {
// Only the verified idle convention may leave In Review automatically.
// A real decision or delivery problem keeps the existing review semantics.
await tx.update(issues).set({ status: "todo", updatedAt: new Date() })
.where(and(eq(issues.companyId, companyId), eq(issues.id, issueId),
sql`${externalConversationStateSql()} = 'waiting'`));
await tx.update(chatConversations).set({ state: "active", updatedAt: new Date() })
.where(and(eq(chatConversations.companyId, companyId), eq(chatConversations.issueId, issueId),
eq(chatConversations.state, "waiting"), sql`exists (select 1 from chat_endpoints e
where e.id = ${chatConversations.endpointId} and e.company_id = ${chatConversations.companyId} and e.provider in ('slack', 'speko'))`));
}
/** Compatibility name for existing Slack callers. */
export const resumeSlackConversation = resumeExternalConversation;