Jannik/PaperClipAI
1
0 Fork 0
mirror of https://github.com/paperclipai/paperclip.git synced 2026-11-07 07:55:47 +01:00
Code Issues Packages Projects Releases Wiki Activity
Files
0195fcb0168d32ee39442e1ff64d33c2bbc775fa
PaperClipAI/maps/agent-access-map/onboarding.md
T
DottaandPaperclip d40f9ac377 fix: enforce first-task completion decisions and retain E2E evidence (#17940) 
## Thinking Path

> - Paperclip lets people delegate work to agents and approve proposed
work.
> - The onboarding first task asks for scope, proposes a task, and waits
for a human decision.
> - An answer to its opening question supplies scope. It does not
approve a proposal.
> - Task creation already checks the saved proposal decision.
> - Native completion used the general completion policy and could mark
the onboarding parent Done without that decision.
> - This PR checks the trusted decision before completion feedback and
again when the native status is committed.
> - The first task stays in review until a saved human decision permits
closure. Ordinary completion and acknowledged refusal keep their current
behavior.
> - The Product E2E guard also retains closed scalar evidence so future
failures show which boundary condition was observed.

## Linked Issues or Issue Description

Refs: #17914. Profile compatibility follow-up to #17922.

**What happened?**

A native onboarding run can submit a valid low-risk Done result after
only the opening answer. The native finalizer then marks the first task
Done even though no human has accepted or rejected a proposal.

**Expected behavior**

The opening answer must not permit completion. A trusted saved proposal
decision must permit it. A saved rejection permits acknowledgment and
closure, but does not authorize new work. A later pending proposal must
keep the task in review.

**Steps to reproduce**

Create a server-owned onboarding first task with an answered opening
question, no proposal decision, and a valid low-risk completion
contract. Pass a Done result through native completion feedback, the
control-plane port, and the finalizer. Before this fix, the persisted
status is Done. The regression expects In review. Ordinary completion
and acknowledged rejection pass as controls.

## What Changed

- Share the trusted latest-proposal and human-response checks with
completion admission. Keep task creation acceptance-only.
- Refuse premature native completion feedback. Keep an already saved
premature result in review during finalization.
- Check the decision again under the existing task and run locks before
committing Done.
- Cover accepted decisions, saved refusals, forged context, pending or
changed proposals, and a real database race.
- Retain a closed scalar receipt when the existing E2E pre-acceptance
guard fails. Validate and display it without task content, IDs,
filenames, or raw rows. Preserve the original failure, blocked
dependents, and historical reports.
- Include the evidence module in the journey definition hash. Bind the
receipt to its exact failure code and check its closed keys against the
full type.
- Repair base-branch profile drift found by the full harness check:
include the active Copilot v66 fixture in image hashing and update stale
Pi version/hash expectations from #17922. Keep all older image inputs
and strict hash checks.
- Update the onboarding feature and agent access maps and E2E evidence
documentation.

## Verification

- Semantic regression before implementation: one failure and two passing
controls on PostgreSQL 18. The failed assertion observed Done instead of
In review.
- The local database uses an owned disposable container with an
immutable image digest. Actual migrations, feedback, control-plane port,
finalizer, and status commit run against PostgreSQL. A temporary test
adapter replaces only the embedded database transport because this host
has exhausted its PostgreSQL semaphores.
- Native control-plane suite: 55 tests passed, including 17 new
controls. Existing task-creation admission: 25 passed. Existing
completion feedback: 19 passed.
- Credential-free E2E support: 206 Vitest suites passed, 4,407 tests
passed, and two skipped. All 137 Node support checks passed. Harness
typecheck passed.
- The failure-receipt regression had 11 failed assertions before capture
was implemented. Two failure-code binding assertions fail without their
gate. Eight placement/binding cases first validate the receipt-free
control, then reject the misplaced receipt.
- The untouched base reproduced the three profile compatibility
failures. The narrow repair passed all 83 affected tests before the full
harness run.
- Private workflow preparation and credential-free onboarding preview:
nine compatibility checks passed. Ownership, recovery, evidence,
shared-contract and workflow compatibility: 77 passed. The actual
provider preview also confirms immediate success deletion, earlier
declared failure eligibility, limits, and zero retries without
credential access. Map checks and git diff checks passed.
- Required repository typecheck passed for the product fix. The combined
branch build passed. The local full repository suite was stopped after
repeated PostgreSQL startup failures; a separate initdb probe confirmed
host SysV semaphore exhaustion. No shared IPC resources were changed.
[Hosted
CI](https://github.com/paperclipai/paperclip/actions/runs/40591020873)
passed the full database suites, typecheck, build, runner checks,
serialized suites, and browser shards on final head
`1ac4c23605a03bfd1f1f8a017b14ce29fda85f6b` (55 success, two expected
skips, one advisory neutral).
- Independent source review approved the product guard, atomic race
regression, evidence contract, and maps with no actionable findings.
Both automated reviews are 5/5 on final head
`1ac4c23605a03bfd1f1f8a017b14ce29fda85f6b`; prior findings are fixed and
resolved. Final CI is green and the PR is conflict-free.
- No Cloud workspace, provider call, release publication, or deployment
is part of this verification. These tests do not identify a historical
Cloud failure or qualify live onboarding.
- Local dependency installation uses the existing CI-generated lockfile
from #17811. No lockfile change is included.

## Risks

- Existing onboarding runs without a trusted saved proposal decision
remain in review even when the agent reports success. This is the
intended approval boundary.
- Decision changes can race completion. The status commit checks the
decision under its existing locks and uses the existing status-race
recovery path.
- A saved refusal permits closure only. Creation admission still rejects
it.
- Evidence readers reject malformed receipts and unrelated failure
codes. The version-1 key registry is checked against every receipt field
at compile time. Existing attempts do not gain evidence after the fact.

## Model Used

OpenAI GPT-6.1 Sol (`gpt-6.1-sol`), ultra reasoning, through Codex. Used
repository inspection, code execution, and collaborating coding agents.
The runtime did not report a context-window size.

## 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 references)
- [x] My branch name describes the change and contains no internal
ticket 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>
2026-10-27 17:07:50 -05:00

274 lines
13 KiB
Markdown
Raw Blame History

# Onboarding and first work — agent access
Product map: [Onboarding and first work](../feature-map/onboarding.md).
Feature ID: `onboarding`.
Review date: 2026-10-12. Source commit: `f981fa3cc10cb8663a87dec60345fbff46d54d0a`.
This is a source-reviewed baseline of representative operations and known gaps.
Each capability needs operation-level review before its entire scope can be
qualified. No live agent execution is claimed. Follow the [map contract](../README.md)
for format, permission checks, evidence and maintenance.
Scoped runner-default source review: 2026-10-12 at
`eee0534154eaf5d0d3f2bbc97c1e24d86f34a5a5`, limited to first-agent selection,
selected-runtime validation and draft restoration. Unrelated baseline entries
retain the original source commit; no live agent verification is added.
## `instance`
Capability ID: `onboarding/instance`.
Review: `baseline`.
API: `not-applicable` — Bootstrapping an instance cannot depend solely on an API served
by that not-yet-running instance.
Agent access: `operator-only` — Existing CLI onboard/run/doctor / test-drive.
Policy: Instance setup is operator work; company creation is board; agent creation/task
creation retain their individual permissions.
Evidence: `source-only` —
[implementation](../../ui/src/components/OnboardingWizard.tsx#L279) at the reviewed
commit above.
Verification: `not-run` — exercise the listed local workflow in an authorized, owned
operator environment. Verify its isolation and result; do not count local machine
authority as company-agent API access.
Gaps: Bootstrapping an instance cannot depend solely on an API served by that
not-yet-running instance.
## `company`
Capability ID: `onboarding/company`.
Review: `baseline`.
API: `present` — representative operation IDs:
- `POST /api/companies`.
- `POST /api/companies/{companyId}/agents`.
Agent access: `partial` — Board company creation; authorized in-company agent hiring
API.
Policy: Instance setup is operator work; company creation is board; agent creation/task
creation retain their individual permissions.
Evidence: `source-only` —
[implementation](../../ui/src/components/OnboardingWizard.tsx#L279) at the reviewed
commit above.
Verification: `not-run` — exercise a listed permitted operation with actual agent
credentials/run context; inspect its result and applicable persistence/attribution.
Assert the relevant denied actor, owner, company or mode from Policy. Review the
remaining operations before qualifying the whole capability.
Gaps: API building blocks exist; an ordinary agent cannot create its parent company with
a company key.
## `adapter`
Capability ID: `onboarding/adapter`.
Review: `baseline`.
API: `present` — representative operation IDs:
- `GET /api/companies/{companyId}/adapters/{type}/models`.
- `POST /api/companies/{companyId}/adapters/{type}/test-environment`.
Agent access: `partial` — Permitted agent/model API; operator
provider-account/environment setup.
Policy: Instance setup is operator work; company creation is board; agent creation/task
creation retain their individual permissions.
The wizard selects the Codex harness and lets the server resolve an automatic
new-agent runner; explicit Legacy remains available. Supported-platform and
immutable sandbox evidence follow [environment probe policy](./execution-environments.md#probe).
Creation/discovery do not provision a target to determine this default. Adapter
setup validation requires `agents:create`, plus saved-agent update access when
testing an existing agent; interactive account login additionally requires a
board user and owner-bound session. An agent's right to hire is not login or
instance-environment administration authority.
Scoped source-only runtime preparation: the existing authorized adapter test
prepares the default Claude CLI in its already acquired sandbox when the image
version is too old for the selected model. It installs a pinned package into a
workspace-private versioned prefix and verifies the executable before the hello
test. This adds no installation API, account grant, environment authority or
engine fallback. Cloud UI omits manual shell debugging and legacy operator hints
while retaining check messages and details. Local, SSH and custom
commands remain operator-managed. Controls:
[runtime](../../packages/adapters/claude-local/src/server/sandbox-cli-version.test.ts),
[probe](../../packages/adapters/claude-local/src/server/test.remote.test.ts), and
[wizard](../../ui/src/components/OnboardingWizard.test.tsx). Live managed
authorization and subscription execution remain `not-run` for this change.
For fresh managed Codex Auto setup, the wizard's explicit Connect path can call
`POST /api/environments/{environmentId}/probe?companyId={companyId}` before
selected-runtime testing, then refresh scoped adapter discovery. This reuses the
existing board instance-admin/local-implicit probe gate; `agents:create` alone
is insufficient. A 403, absent proof, changed configuration, missing response
identity or unconfirmed cleanup remains visible. No probe is added to creation
or discovery, no agent/company grant is broadened, and provider authentication
errors never cause an automatic runner switch.
Native setup derives outer sandbox isolation from the server-resolved execution
target, as task execution does. This is an internal transport choice, not a
request/configuration permission. Local and SSH setup keep Codex isolation;
caller-supplied environment flags do not authorize an external sandbox. Existing
company, account, probe and registration-cleanup gates still apply.
The bounded hello probe retains read-only permissions and no dynamic tools. Its
trusted launch skips project-instruction discovery in the new, empty setup
workspace. This grants no filesystem or networking permission and does not
change instruction discovery for ordinary task execution.
Scoped source review: 2026-10-13, exact baseline
`1a0ca66242121e39d88455aa2b52a07acc4a07d9` plus the privately composed onboarding
correction. [Wizard controls](../../ui/src/components/OnboardingWizard.test.tsx)
and [existing Product E2E observer controls](../../tests/runner-e2e/first-task.test.ts)
exercise mocked allowed/denied setup and sticky unknown cost coverage. They do
not prove live actor authorization or provider execution. The explicit manual
`confirmation-replies.runner-codex.daytona.task-card-accept` case requires an
eligible immutable OCI target and the existing probe authority, two identified
setup leases and separately authorized paid/cleanup reservations. Its fixture
neither prequalifies the environment nor creates the agent. Actual Cloud named
snapshot binding, warm/cold signup and live allowed/denied agent checks remain
`not-run`.
Evidence: `source-only` —
[implementation](../../ui/src/components/OnboardingWizard.tsx#L279) at the reviewed
commit above.
Scoped Evidence: `source-only` — [wizard/default selection](../../ui/src/components/OnboardingWizard.tsx),
[creation resolver](../../server/src/services/agent-runner-selection.ts) and
[setup/login authorization](../../server/src/routes/agents.ts) at the scoped
commit. Existing agent/approval execution preservation follows
[hiring access](./agents.md#hire); no live onboarding proof is claimed here.
Verification: `not-run` — exercise a listed permitted operation with actual agent
credentials/run context; inspect its result and applicable persistence/attribution.
Assert the relevant denied actor, owner, company or mode from Policy. Review the
remaining operations before qualifying the whole capability.
Gaps: Account authorization, environment administration and model selection need
separate checks.
Verify automatic onboarding without a post-hire runner change, explicit Legacy,
saved configuration after reload and the actual selected runtime's useful task
plus follow-up. Assert denied agent login/probe and foreign-company account or
environment access separately. These agent-context checks remain `not-run`.
## `first-task`
Capability ID: `onboarding/first-task`.
Review: `baseline`.
API: `present` — representative operation IDs:
- `POST /api/companies/{companyId}/issues`.
- `POST /api/issues/{issueId}/children`.
Agent access: `available` — Native create_task / agent REST / CLI issue.
Policy: Instance setup is operator work; company creation is board; agent creation/task
creation retain their individual permissions.
An authenticated run bound to the server-created onboarding first task must
obtain persisted human acceptance of the latest ordinary proposal before creating
new tasks through native `create_task` or REST. Its authenticated run determines
this admission even for an explicit standalone task. A card decision or a saved
conversational resolution with a genuine later same-task user message supplies
acceptance; an agent-only resolution does not. A plan approval must name the
current same-task revision. Newer pending/rejected proposals stop new creation.
Already admitted task replay and ordinary delegation retain their existing rules.
Native `paperclip_finish` does not grant completion authority from an opening
answer. The onboarding parent requires a trusted saved human decision on its
latest proposal. Acceptance permits completion under the existing policy;
rejection permits acknowledgment and closure without authorizing new work.
The native status commit checks this decision again under its existing task/run
locks. This adds no new agent endpoint or cross-company authority. The
[native completion controls](../../server/src/services/native-runtime/paperclip-control-plane-port.test.ts)
check persisted outcomes on disposable PostgreSQL; they are not live Cloud
credential or onboarding qualification.
Source: [creation admission](../../server/src/services/onboarding-first-task-admission.ts).
Controls: [native/REST PostgreSQL regressions](../../server/src/__tests__/onboarding-first-task-admission.test.ts).
These controls do not qualify a live Cloud provider journey.
Evidence: `source-only` —
[implementation](../../ui/src/components/OnboardingWizard.tsx#L279) at the reviewed
commit above.
Verification: `not-run` — exercise a listed permitted operation with actual agent
credentials/run context; inspect its result and applicable persistence/attribution.
Assert the relevant denied actor, owner, company or mode from Policy. Review the
remaining operations before qualifying the whole capability.
Gaps: Task creation is agent-accessible where permitted; scheduling/readiness does not
follow from successful creation.
The Codex first-task fixture's operator cost guard uses the existing board
agent-configuration PATCH before admitting work. This is not evidence of agent
permission to update its runtime; the listed agent-context checks remain not-run.
Scoped source review: 2026-10-13, the first-task asset correction against
`ea6c8eb5e16d61111968f633a66748b397b64a3e`. The existing
[first-task instructions](../../server/src/onboarding-assets/first-task/skills/first-task/SKILL.md)
send file-producing work through the child's own execution and existing
dependency/block controls. Native `register_deliverable` retains its current-task
binding; this adds no cross-task file-registration authority or permission.
Document-only work may use the existing child-document API inline, and plan-only
approval does not authorize implementation. The existing asset tests check
wording only. The literal baseline live attempt failed child-file delivery and
completion reporting; revised live authorization and execution remain `not-run`.
## `resume`
Capability ID: `onboarding/resume`.
Review: `baseline`.
API: `not-applicable` — No server onboarding-draft API for this browser-local state;
classify explicitly or intentionally make it a cross-client product feature.
Agent access: `not-applicable` — Browser localStorage wizard draft; persisted resources
use their domain APIs.
Policy: Instance setup is operator work; company creation is board; agent creation/task
creation retain their individual permissions.
Evidence: `source-only` —
[implementation](../../ui/src/components/OnboardingWizard.tsx#L279) at the reviewed
commit above.
Verification: `not-run` — use the product recipe for the local/developer surface. Verify
listed shared-resource reads separately; local presentation alone is not agent API
evidence.
Gaps: No server onboarding-draft API for this browser-local state; classify explicitly
or intentionally make it a cross-client product feature.
Scoped source review of [draft restoration](../../ui/src/components/OnboardingWizard.tsx)
preserves harness/runner intent and invalidates obsolete setup-test results after
a selection change. Browser draft continuity is not API or live-agent evidence,
and opening a saved Legacy agent does not apply new-agent defaults.
The initial matching route opening preserves the authorized saved wizard step
on bare and company-prefixed reloads. Explicit new-company or changed-company
openings retain their navigation override and clear foreign company resource
IDs. [Existing component controls](../../ui/src/components/OnboardingWizard.test.tsx)
exercise these presentation and account boundaries. This scoped correction adds
no server draft API, agent grant or proof of live actor authorization. The
managed first-task eval still reloads before Get started and remains a separate
live acceptance gate. The existing mocked-login browser case also checks the
same company-scoped active session and saved selection through route reopening
and a real reload, with one login start and no pending-login hire. These fixture
assertions do not prove server authorization or live credential use.
Reference in new issue View Git Blame Copy Permalink