Files
PaperClipAI/doc/plans/chat-adapters/setup-wireframe-data-v6.mjs
DottaandPaperclip 889947c238 feat: add experimental native chat connectors (#13038)
## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work.
> - People also ask agents for work in their existing chat tools.
> - Each external conversation needs one task and a current authorized
source.
> - Retries, Stop, and provider failures must not duplicate work or
expose private data.
> - The first chat PR establishes the opt-in provider and data
contracts.
> - This PR adds experimental channel integration and its durable
control plane.
> - Users can request work from connected channels and inspect delivery
in Paperclip.

## Linked Issues or Issue Description

Refs #13100 and #13092. This is the second of exactly two chat PRs.
Foundation #13100 is merged and changed 143 files. Runner prerequisite
#13092 is also merged. This PR changes 400 files against master, below
the 500-file review limit. It contains no wireframe images or HTML
galleries.

## What Changed

- Add native Slack, GitHub, Microsoft Teams, Telegram, and Discord chat
connections. Keep chat disabled unless the operator enables experimental
chat connectors. Preserve the production GitHub tool connection and its
normal setup path.
- Bind each provider bot identity to one immutable Paperclip agent. Bind
each admitted external conversation to one task. Paperclip owns tasks,
runs, permissions, and audit records.
- Add durable admission, per-conversation queues, questions, task
controls, progress, final replies, images, files, and delivery receipts.
Board comments remain internal unless explicitly sent to the channel.
- Check current identity, provider reach, resource access, credentials,
runtime generation, and exact source before provider effects. Keep
private responses private. Never send raw reasoning, private logs,
credentials, or tool arguments.
- Hold uncertain sends for explicit audited resolution. Make Board
Send-to-channel atomic and idempotent. Keep reconnect and setup
credentials in Paperclip secret storage.
- Preserve current native-runner authority across retries, lost
acknowledgements, and recovery. Keep immutable input and completion
contracts separate from newer user input. Receipt reconciliation cannot
launch a provider.
- Reconcile chat close/new ordering and provider-effect lock order.
Audit resource access changes in the same transaction. Submit only the
selected resource from each UI toggle so stale pages cannot undo
unrelated access changes.
- Drain Codex stdout before certifying process exit. Bound the drain
with the existing shutdown grace. Preserve observed terminal authority
without treating an undrained process as successful or reusable.
- Incorporate master `018ca5da` with its ACP Stop, mobile task layout,
runner packaging, and official lock changes. Preserve dedicated
chat-answer continuations in both directions when ordinary queued
comments are adopted after Stop.
- Fence late adapter readiness behind an earlier Stop for the same run.
Preserve verified cleanup for registered adapters. Handle single Stop,
agent pause, duplicate Stops, and failure release without creating a
false cancellation receipt.
- Incorporate master's `6dd48cad4` wake-queue extraction. Preserve exact
failed-chat retry authorization and lineage, retired question-source
suppression, and the block on generic recovery that would discard the
admitted source. Fresh deferred input retains its separate promotion
path.
- Incorporate master `2a05b5ed3` and its queue-admission extraction,
simplified transaction ports, and separate runner CI job. Preserve exact
durable receipts, actor separation, and dedicated-answer isolation
through the new module. A failed receipt insert rolls back the
accompanying deferred-wake merge.

## Verification

Current head: `afe19299d06253cb628eb398e91d1200ea9f412a`, incorporating
master `2a05b5ed3457ea33efd6895520447d1d97fe98d8`. The conflicts are
resolved. This successor fixes two test-harness boundaries exposed by
CI: per-case route-module preparation and actual durable-save completion
before intentional runner termination. Production code and all existing
test/turn deadlines are unchanged. [Exact-head Greptile
review](https://github.com/paperclipai/paperclip/pull/13038#issuecomment-5587250594)
is **5/5**, completed September 10 at 13:20:55 UTC, with no actionable
findings or open review threads. [Fresh exact-head
CI](https://github.com/paperclipai/paperclip/actions/runs/34481724341)
passes **all 24 jobs**, including Build and both required aggregates.
Normal exact-head guarded merge was attempted and rejected by the
remaining branch approval policy: CODEOWNER review is required and no
human approval is present. Normal **squash auto-merge is enabled** as of
September 10 at 13:36:26 UTC. Requested CODEOWNERS have been notified;
no approval bypass or self-approval was used. Earlier-head results below
remain historical evidence, not qualification of this successor.

- Final exact-head Linux evidence: 995/995 chat integration cases; 36/36
agent-skills routes; 35/35 runner live-session cases, including real
process kill/resume; 1948 runner Vitest cases with three existing
benchmark/platform guards; 870/870 API-authority cases; and 104 browser
cases with four existing optional skips. Rust, conformance/replay, full
repository build, typecheck, canary, all server/workspace shards, and
both required aggregates pass with normal CI concurrency. Earlier failed
attempts remain recorded below.

- Latest test-only qualification: 141/141
route/permissions/authentication cases pass in separate cold forks, with
plain server types and independent review clear. The real-runner suite
passes 35/35, with plain runner types and independent review clear. A
controlled premature-save acknowledgement fails as expected; matching
ownership/effect/process evidence, rejected saves, real turn outcome,
test abort, and pre-kill liveness are covered. No local reproduction of
the original CI scheduling failure is claimed. The preceding [CI
run](https://github.com/paperclipai/paperclip/actions/runs/34479680858)
passes 21/24 jobs, including all 995 Linux chat cases and browser
aggregate (104 passed, four existing optional skips); only Build, the
skills serialized shard, and the required verification aggregate fail.
Its exact-head Greptile review was 5/5. Both failed job logs are
retained.

- Final fixture qualification: all eight focused Discord cases and all
995 chat integration cases pass. The exact modal statement/PID is
observed before taking the real connection lock; the test then proves
its actual blocking relationship before mutation. Original SQL
execution, provider behavior, negative assertions, and 1s/15s timeouts
remain unchanged. Independent review is clear and test/production hashes
remain frozen. The preceding [CI
attempt](https://github.com/paperclipai/paperclip/actions/runs/34477184777)
passed 22 jobs, including Build/runner, typecheck, canary, all other
test shards, and browser aggregate (104 passed, four existing optional
skips); the two fixture failures and failed verification aggregate
remain recorded, not relabeled as a pass.

- Current queue-module composition: 308/308 recovery/batching/queue/Stop
tests; 995/995 full chat integration; 89/89 module tests, including real
PostgreSQL receipt-insert rollback; 24/24 workflow/module-boundary
tests; plain server and UI types. All four actual local process/ACP
browser paths pass in 1.4 minutes. Fresh databases, no skips or retries,
stable reviewed source hashes. The initial boundary failure is retained;
its no-op service wrapper was removed without changing recovery context
or weakening the check. An exploratory standalone test-directory
typecheck fails because its new upstream transformation config is not a
standalone typechecking project; standard CI/build does not invoke it,
and no configuration was weakened to suppress those diagnostics.

- The preceding head `e02a63d462ce5d47433b0aeb632bb6fd20aab1ba` passed
[all 24 CI
jobs](https://github.com/paperclipai/paperclip/actions/runs/34436462958)
and exact-head Greptile review at 5/5. Required CODEOWNER review
prevented its normal merge before master advanced again.

- Final extracted-module composition: 307/307 recovery, batching, queue
and Stop-control tests; 995/995 full chat integration; 49/49 module
tests including eight PostgreSQL adapter cases; and 19/19 issue-update
tests. Plain server types pass. All four actual local process/ACP
browser paths pass in 1.3 minutes. Fresh databases, no skips or retries
in these cohorts, frozen source hashes, and independent review clear.

- The preceding head `3e4e1c1c` passes [all PR CI
jobs](https://github.com/paperclipai/paperclip/actions/runs/34415826820),
including Build and required `ci / verify` and `ci / e2e`. Both the
original Rust failure and the previously load-sensitive lineage fixture
pass with unchanged Linux concurrency. Master advanced afterward and
required this reconciliation.
- Final master composition: 448/448 focused UI tests, 186/186 adapter
tests, 24/24 queue/control tests, and 11/11 packaging tests. Plain UI,
server, shared, and adapter types pass. Token gates and diff checks
pass. Independent server and UI reviews are clear.
- Stop-registration regression: both real-service cases fail against
exact `a95` source and pass with the fix. The full corrected
recovery/control suite passes 265/265. Duplicate-owner and failed-Stop
controls also pass. Plain server types pass. The readiness barrier
prevents provider startup without adding an acknowledgment to an already
terminal run.
- Final qualification strengthens terminal-field equality and repeats
both affected cases successfully on a fresh database. All four actual
local process/ACP browser paths pass again in 1.3 minutes, without skips
or retries. The final screenshot shows Cancelled, a paused subtree,
retained input, and no error toast.
- Two new actual-service regressions fail before the merge fix. They
prove that queued-comment adoption could consume a dedicated chat answer
or add unrelated input to that answer. The fixed four-case cohort
passes, including ordinary upstream continuation and adapter Stop
controls. Full recovery passes 257/257. All four actual local
process/ACP Stop browser flows pass in 1.4 minutes, without skips or
retries, on a fresh database.
- The unchanged runner artifact was qualified with 171/171 transport
tests, 870/870 API-authority tests, conformance 1/1, and replay 11/11.
Six controlled reader tests prove the exit/drain repair. Its local
serial Rust workspace passed 546 top-level cases plus two invoked
helpers; the later passing Linux CI supplies default-concurrency
evidence.
- Prior exact-source full chat integration passes 995/995. Settings
regressions cover concurrent stale pages, 501 destinations, pending
state, rejected updates, and explicit retry. These deterministic tests
do not prove live provider behavior.
- Retained failed attempts and their causes are in the [qualification
log](https://github.com/paperclipai/paperclip/blob/afe19299d06253cb628eb398e91d1200ea9f412a/doc/plans/chat-adapters/2026-09-08-chat-queue-and-webhook-repair.md).
The first merge adapter run timed out while macOS slept for 290 seconds.
Its unchanged repeat passed with a temporary sleep guard. No assertion,
deadline, or CI gate was weakened.

Review commands include `pnpm --filter @paperclipai/server exec vitest
run src/__tests__/heartbeat-process-recovery.test.ts
src/__tests__/issue-queued-comments-routes.test.ts` and `pnpm exec
playwright test --config tests/e2e/playwright.config.ts
tests/e2e/acp-stop-continuation.spec.ts`. Database suites require fresh
disposable databases. See the [browser
runbook](https://github.com/paperclipai/paperclip/blob/afe19299d06253cb628eb398e91d1200ea9f412a/doc/plans/chat-adapters/2026-09-04-chat-adapters-browser-e2e-runbook.md)
for provider setup and separate live acceptance steps.

## Risks

- This remains experimental. Deterministic tests and bounded live
evidence do not establish every provider feature, tenant, permission
layout, or media shape. Teams work-tenant qualification is still open.
- Failed and uncertain provider effects remain visible and can require
operator action. A transport receipt does not prove recipient
visibility.
- Native controller and runner artifacts must remain compatible.
Preserve lease ownership, terminal authority, source binding, and
quarantine during future changes.
- Access and audit rows commit together, but activity notifications
remain best-effort. This is not a new durable event outbox.
- The PR operation does not deploy a live server, replace its runner, or
change provider permissions. Remaining live qualification is documented
in the [temporary
handoff](https://github.com/paperclipai/paperclip/blob/afe19299d06253cb628eb398e91d1200ea9f412a/doc/plans/chat-adapters/2026-09-08-open-qualification-followups.md).

## Model Used

OpenAI Codex assisted with implementation, tool execution, testing, and
review. The work records `gpt-6-astra` assistance. The environment does
not report a context-window size. No private reasoning traces are
included.

## 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>
2026-09-10 10:06:45 -05:00

346 lines
17 KiB
JavaScript

export const setupFlows = [
{
provider: "Slack",
short: "Slack",
screens: [
{
id: "13",
slug: "slack-add",
title: "Connect a Slack app",
subtitle: "Bring your own Slack app using Paperclip's prepared manifest.",
rail: ["Agent selected", "Connect Slack app", "Try Maya"],
active: 1,
mode: "default",
instructions: [
["Copy the manifest", "Create a Slack app From an app manifest in the target workspace."],
["Install the app", "Open OAuth & Permissions, install it to the workspace, and copy the Bot User OAuth Token."],
["Copy the signing secret", "Open Basic Information and copy the App's Signing Secret."]
],
fields: [
["Bot User OAuth Token", "xoxb-••••••••••••"],
["Signing Secret", "••••••••••••"]
],
primary: "Connect Slack app",
secondary: "Open Slack app settings",
actions: [
["Connect Slack app", "Stores the two write-only credentials and verifies the Slack bot identity and required scopes."],
["Open Slack app settings", "Opens Slack's app-management page where the operator creates and installs the customer-owned App."]
],
annotations: [
"The prepared manifest and exact provider locations make the customer-owned App the complete required path.",
"Only the Bot User OAuth Token and Signing Secret are entered, and both remain write-only.",
"Managed Add to Slack is an optional later convenience and cannot gate this path or release."
],
rationale: "Bring-your-own credentials are sufficient to ship; managed installation remains optional."
},
{
id: "41",
slug: "slack-try",
title: "Try Maya in Slack",
subtitle: "Start one task and reply to it once.",
rail: ["Agent selected", "Connect Slack app", "Try Maya"],
active: 2,
mode: "default",
instructions: [
["Open a channel", "If Slack asks, add Maya with /invite @Maya."],
["Start a task", "Post “@Maya help me test this” as a new channel message."],
["Continue the task", "Reply once in the thread Maya creates; no second mention is needed."]
],
primary: "Open Slack",
actions: [
["Open Slack", "Opens the installed workspace while Paperclip waits for the root mention and thread reply to complete setup."]
],
annotations: [
"The body is only the three actions needed to test the real Slack interaction.",
"The instructions teach the root-mention-to-thread Paperclip task boundary.",
"There is one action: open Slack and perform the test."
],
rationale: "Installation health and automatic verification do not belong on an instruction screen."
}
]
},
{
provider: "GitHub",
short: "GitHub",
screens: [
{
id: "16",
slug: "github-create",
title: "Create Maya in GitHub",
subtitle: "Create a dedicated GitHub App from Paperclip's prepared manifest.",
rail: ["Agent selected", "Create GitHub App", "Choose repositories", "Try Maya"],
active: 1,
mode: "default",
instructions: [
["Choose the owner", "Select your personal account or the organization that should own the App."],
["Create the App", "Keep the suggested unique name, then click Create GitHub App."]
],
primary: "Create in GitHub",
secondary: "Use an existing GitHub App",
actions: [
["Create in GitHub", "Posts Paperclip's App Manifest to GitHub. GitHub returns to Paperclip after creation, and Paperclip stores the returned App credentials."],
["Use an existing GitHub App", "Opens the advanced path for an App the organization already owns."]
],
annotations: [
"Only the two choices GitHub presents during App creation are described.",
"The normal action uses the GitHub App Manifest handoff; credentials never pass through the operator.",
"The existing-App branch remains available without cluttering the default path."
],
rationale: "The manifest already fixes permissions, events, and webhook configuration."
},
{
id: "45",
slug: "github-install",
title: "Choose GitHub repositories",
subtitle: "Install Maya where people should be able to mention it.",
rail: ["Agent selected", "Create GitHub App", "Choose repositories", "Try Maya"],
active: 2,
mode: "default",
instructions: [
["Choose the account or organization", "GitHub may ask an organization owner to approve the installation."],
["Choose repository access", "Select all repositories or only the repositories where Maya should respond."],
["Install", "Review the requested chat permissions, then click Install."]
],
primary: "Install in GitHub",
actions: [
["Install in GitHub", "Opens GitHub's App installation page and returns the installation and selected repository IDs to Paperclip."]
],
annotations: [
"The screen contains only GitHub's installation decisions.",
"Repository scope stays in GitHub's native approval UI.",
"One button begins the complete provider-owned installation step."
],
rationale: "There is no Paperclip form to duplicate GitHub's repository picker."
},
{
id: "46",
slug: "github-try",
title: "Try Maya in GitHub",
subtitle: "Start one task in an installed repository.",
rail: ["Agent selected", "Create GitHub App", "Choose repositories", "Try Maya"],
active: 3,
mode: "default",
instructions: [
["Open an issue or pull request", "Use one of the repositories selected during installation."],
["Mention Maya", "Add a comment: “@paperclip-maya help me test this.”"],
["Continue", "Add another comment in the same issue or pull request to continue the same Paperclip task."]
],
primary: "Open GitHub",
actions: [
["Open GitHub", "Opens an installed repository while Paperclip waits for the first signed mention to complete setup."]
],
annotations: [
"The body is only the native GitHub test sequence.",
"The instructions explain that GitHub's existing issue or pull request is the task boundary.",
"There is one action: open GitHub and perform the test."
],
rationale: "A real mention proves the App installation without a separate verification screen."
},
{
id: "47",
slug: "github-existing",
title: "Connect an existing GitHub App",
subtitle: "Update the App in GitHub, then provide its identity credentials.",
rail: ["Agent selected", "Configure existing App", "Choose repositories", "Try Maya"],
active: 1,
mode: "advanced",
copyValue: ["Webhook URL and secret", "Copy Paperclip webhook settings"],
instructions: [
["Update the webhook", "In the GitHub App settings, paste Paperclip's URL and generated secret, then make the webhook active."],
["Set permissions and events", "Grant Issues: write, Pull requests: write, Metadata: read; subscribe to Issue comment and Pull request review comment."],
["Create a private key", "In the App settings, click Generate a private key and download the PEM file."]
],
fields: [
["GitHub App ID", "123456"],
["Private key", "Choose PEM file"]
],
primary: "Connect and verify",
secondary: "Back",
actions: [
["Copy Paperclip webhook settings", "Copies the endpoint URL and generated webhook secret needed in the existing GitHub App settings."],
["Connect and verify", "Stores the PEM file write-only, authenticates as the App, and verifies webhook, events, and least-privilege permissions."],
["Back", "Returns to the credential-free App Manifest path."]
],
annotations: [
"The copy control provides the exact values the operator must paste into GitHub.",
"The instructions list every provider change required for an existing App.",
"Only App ID and private key return to Paperclip; the generated webhook secret is already stored.",
"Verification happens as part of Connect rather than on another screen."
],
rationale: "Existing Apps lack the manifest callback, so this advanced page contains the complete minimum manual configuration."
}
]
},
{
provider: "Microsoft Teams",
short: "Teams",
screens: [
{
id: "19",
slug: "teams-register",
title: "Create Maya for Microsoft Teams",
subtitle: "Run one command to register Maya with Microsoft.",
rail: ["Agent selected", "Create Teams app", "Install Maya", "Try Maya"],
active: 1,
mode: "default",
code: "npx @paperclipai/teams-connect --setup PC-7K4M",
instructions: [
["Copy and run the command", "Run it in a terminal on a computer where you can sign in to Microsoft 365."],
["Sign in to Microsoft", "Approve the Microsoft login when the browser opens. The command creates the bot and returns here when it is ready."]
],
primary: "Copy setup command",
secondary: "Set up Microsoft manually",
actions: [
["Copy setup command", "Copies a one-time Paperclip command that invokes Microsoft's Teams Developer CLI, signs the operator in, creates the Teams App and bot registration, and sends the resulting identity to this setup draft."],
["Set up Microsoft manually", "Opens the Azure/Teams manual fallback for tenants that cannot run the guided command."]
],
annotations: [
"The generated command is the only normal-path configuration artifact.",
"Both instructions are actions the operator performs locally or in Microsoft's login.",
"The manual path is available without exposing Azure choices on the default screen."
],
rationale: "The helper collapses Microsoft registration into one attended command while Microsoft remains the authority for sign-in and tenant policy."
},
{
id: "49",
slug: "teams-install",
title: "Install Maya in Microsoft Teams",
subtitle: "Open the Microsoft install page and add the app.",
rail: ["Agent selected", "Create Teams app", "Install Maya", "Try Maya"],
active: 2,
mode: "default",
instructions: [
["Open the install page", "Sign in to the same Microsoft 365 tenant if prompted."],
["Add Maya", "Review the app, click Add, and choose the team or channel if Microsoft asks."]
],
primary: "Install Maya in Teams",
actions: [
["Install Maya in Teams", "Opens the install link returned by Microsoft. Tenant policy may route the same request to an administrator for approval."]
],
annotations: [
"The install link replaces package download and upload on the normal path.",
"The body contains only the two actions performed in Microsoft Teams.",
"Tenant approval is handled by Microsoft's install experience, not another Paperclip choice."
],
rationale: "Microsoft's CLI returns an install link, so normal setup should use it directly."
},
{
id: "50",
slug: "teams-try",
title: "Try Maya in Microsoft Teams",
subtitle: "Start one task in a channel post.",
rail: ["Agent selected", "Create Teams app", "Install Maya", "Try Maya"],
active: 3,
mode: "default",
instructions: [
["Open an installed channel", "Start a new post rather than replying to an unrelated post."],
["Mention Maya", "Post “@Maya help me test this.”"],
["Continue in replies", "Reply once beneath that post; the post and its replies are one Paperclip task."]
],
primary: "Open Microsoft Teams",
actions: [
["Open Microsoft Teams", "Opens Teams while Paperclip waits for the first authenticated mention and reply to complete setup."]
],
annotations: [
"The body is only the Teams channel test sequence.",
"The instructions teach the channel-post-and-replies task boundary.",
"There is one action: open Teams and perform the test."
],
rationale: "The final provider event is the verification; no installation report is shown first."
},
{
id: "48",
slug: "teams-manual",
title: "Set up Microsoft manually",
subtitle: "Create the bot in Microsoft, then paste the three identity values.",
rail: ["Agent selected", "Configure Microsoft", "Install Maya", "Try Maya"],
active: 1,
mode: "advanced",
copyValue: ["Messaging endpoint", "Copy Paperclip endpoint"],
instructions: [
["Create the Microsoft identity", "Create a single-tenant Entra App registration and a client secret."],
["Create the bot", "Create an Azure Bot with that App ID, enable the Microsoft Teams channel, and paste Paperclip's messaging endpoint."],
["Enter the identity below", "Copy Application ID and Directory ID from Entra; paste the client secret value before leaving Microsoft."]
],
fields: [
["Application (client) ID", "00000000-0000-0000-0000-000000000000"],
["Directory (tenant) ID", "00000000-0000-0000-0000-000000000000"],
["Client secret", "••••••••••••"]
],
primary: "Connect and create Teams app",
secondary: "Back",
actions: [
["Copy Paperclip endpoint", "Copies the public messaging endpoint that must be entered on the Azure Bot resource."],
["Connect and create Teams app", "Stores the client secret write-only, verifies Microsoft bot authentication, and creates the installable Teams app and install link."],
["Back", "Returns to the guided one-command setup."]
],
annotations: [
"The copy control provides the one Paperclip value required by Microsoft.",
"Every instruction is a portal operation the tenant administrator must perform.",
"The three fields are the minimum identity values Paperclip needs to send as the bot.",
"Connect verifies the identity and produces the same install step as the default flow."
],
rationale: "The manual fallback is longer because Microsoft has no manifest callback equivalent; no optional Azure choices are exposed."
}
]
},
{
provider: "Telegram",
short: "Telegram",
screens: [
{
id: "22",
slug: "telegram-create",
title: "Create Maya in Telegram",
subtitle: "Create the bot with BotFather and paste its token.",
rail: ["Agent selected", "Create Telegram bot", "Try Maya"],
active: 1,
mode: "default",
instructions: [
["Open BotFather", "Send /newbot."],
["Name the bot", "Enter Maya, then choose an available username ending in bot."],
["Copy the token", "BotFather sends a token after creating the bot. Paste it below."]
],
fields: [
["Bot token", "123456:••••••••••••"]
],
primary: "Connect bot",
secondary: "Open BotFather",
actions: [
["Open BotFather", "Opens Telegram's verified BotFather conversation so the operator can run /newbot."],
["Connect bot", "Stores the token write-only, verifies the bot with getMe, and continues to the test step."]
],
annotations: [
"The page contains the exact three BotFather actions.",
"The bot token is Telegram's only unavoidable setup input.",
"The two buttons let the operator leave for BotFather and connect after returning."
],
rationale: "Webhook, polling, commands, and identity checks are automatic and therefore absent."
},
{
id: "51",
slug: "telegram-try",
title: "Try Maya in Telegram",
subtitle: "Send the bot its first message.",
rail: ["Agent selected", "Create Telegram bot", "Try Maya"],
active: 2,
mode: "default",
instructions: [
["Open Maya", "Telegram opens the new bot's private chat."],
["Start the chat", "Tap Start, then send “Help me test this.”"]
],
primary: "Open Maya in Telegram",
actions: [
["Open Maya in Telegram", "Opens the bot's t.me link while Paperclip waits for the first verified private message to complete setup."]
],
annotations: [
"The minimum proof is one private message; group and forum reach can be added after connection.",
"The body contains only the two Telegram actions required for the test.",
"There is one action: open the bot and send the message."
],
rationale: "A private chat is Telegram's shortest path from BotFather token to a working Paperclip conversation."
}
]
}
];