## Thinking Path
> - Paperclip manages agent work through company-scoped tasks.
> - Speko voice connections bind a caller to that work.
> - Private voice routes must recognize an authenticated human caller.
> - Cloud sign-in uses a trusted Cloud actor, rather than a local
session actor.
> - The voice caller check rejected that existing authentication type.
> - This pull request accepts authenticated Cloud callers and retains
the current access checks.
> - Cloud users can load call history and start private voice sessions.
## Linked Issues or Issue Description
Refs #15727, #15728, #15729.
**What happened?**
A signed-in Cloud user sees “Sign in to start a private voice
conversation” when the Speko connection loads call activity. The same
check prevents the user from starting a private voice session.
**Expected behavior**
The trusted Cloud user identity should have the same voice caller access
as a local authenticated session. The current company and user identity
checks must still apply.
**Steps to reproduce**
1. Sign in to a Cloud workspace with experimental chat connectors
enabled.
2. Connect a Speko persona to an existing agent.
3. Open its call activity, or start a browser voice session.
4. Observe the sign-in rejection despite the authenticated workspace
session.
**Paperclip version or commit**
Reproduced on the voice route in master at b8ffeb973a.
**Deployment mode**
Paperclip Cloud with trusted tenant authentication.
## What Changed
- Accept `cloud_tenant` and `session` actors with a user ID as private
voice callers.
- Use current company membership for Cloud owners, including owners with
temporary administrator access. Retain local administrator authority,
company isolation, and credential-source restrictions.
- Add route regressions for call history, session creation,
administrator authority, missing identities, company boundaries, and
rejected caller types.
- Add Cloud authentication qualification steps to the Speko runbook.
## Verification
- Before the fix: 2 Cloud regressions failed; 9 boundary and local-user
tests passed.
- After the fix: all 100 voice caller and real-database persistence
regressions passed. The Cloud-owner route test covers history, session
creation, persisted caller authority, and membership revocation.
- Repository typecheck and build passed with the repository’s pinned
dependencies.
- All current-head CI gates passed. Greptile reviewed f84fee2605 at 5/5
with no remaining findings. The repaired local full repository test run
is still in progress. The first local full-suite attempt failed on
missing native database library aliases; those aliases were repaired
only in the isolated test dependency. No skipped run is counted as
database proof.
- On Cloud, verify that signed-in call activity loads and private
session creation reaches media setup. Real conversation and spoken
playback acceptance remain separate.
## Risks
The change accepts an existing trusted Cloud actor type. Authentication
still runs in the current middleware. Raw Cloud headers, board API keys,
MCP OAuth, Cloud control credentials, and agent callers cannot establish
private voice caller authority. No migration, UI change, credential,
transcript, or lockfile is included.
## Model Used
OpenAI Codex, GPT-6 family, with tool use and code execution. The exact
serving variant 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
- [x] 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>
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>
