## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - Agent Chat lets a person assign work through a conversation.
> - Feature and API maps do not prove that a natural request produces
the right saved result.
> - Product E2E already owns isolated fixtures, browser runs, evidence
and cleanup.
> - This pull request adds a chat scenario catalog and two real task
workflows in that framework.
> - Independent checks verify the task, its author, the saved output and
the reply in chat.
> - The benefit is a small executable foundation for broader chat
coverage.
## Linked Issues or Issue Description
**What existing behavior does this improve?**
It adds real task creation and delegation coverage for Agent Chat.
**Current behavior**
Existing maps describe features and agent access. Existing chat evals
cover specific protocols and handoffs. They do not connect a broad
human-request catalog to independent saved-state checks.
**Proposed behavior**
Keep 244 planned scenarios across 35 feature areas. Promote two requests
into the explicit-only `chat-features` suite. One saves a backlog task
without starting work. The other delegates an announcement and returns
the saved result to the original chat.
**Reason and benefit**
A successful tool call or confident reply does not prove the requested
result exists. These evals check public API state, attribution and
browser access after a real model run.
**Breaking changes**
No API or data schema changes. Chat instructions now require actual
relative task links. The local E2E private-state scanner recognizes
Codex account ownership metadata while continuing to reject credentials
and model-visible identity leaks.
**Additional context**
Related prior work: #13969 and #13762. This improves verification of the
existing Agent Chat roadmap item. It does not add a new core product
feature.
## What Changed
- Add YAML scenarios with capability IDs, starting context, user
requests and expected outcomes. Validate all area files against their
schema, global ID uniqueness and exact feature-map capability coverage.
- Add two local native Codex subscription cells. Send the exact catalog
request once through Chromium.
- Seed only prerequisites through public APIs. Use shipped agent
instructions and explicit disposable budget policies for unpriced
subscription usage.
- Check task ownership, creation audit, no premature execution, current
worker-authored output, automatic completion delivery and usable links
after reload.
- Keep private Codex account ownership metadata distinct from bearer
credentials. Scan rollout message content, all tokens and published
evidence as before.
- Teach normal chat instructions to use relative task links instead of
invented hosts. Update tests, maps and the runbook.
- Repair existing E2E contract drift: include the active Copilot
identity in the image digest and update Pi profile expectations. Keep
global catalog cardinality in its owning catalog test.
Product E2E owns the new flow and grader. Its existing launch and report
paths remain in use. The shared scanner change is limited to
owner-private temporary Codex runtime metadata. Other callers retain the
full secret scan. No UI, endpoint, schema or permission behavior
changes.
## Verification
- `node scripts/check-maps.mjs` passed: 35 areas and 191 capability IDs.
- Product E2E typecheck and focused tests passed before rebase: 225
Vitest tests and 137 Node tests. Conversation service tests passed
40/40. Five existing runner turn-binding regressions passed.
- Historical live measurement used real Chromium, server, database and
native Codex with no automatic retries. The initial same-definition
batch passed 5/6 cells. Backlog passed 3/3; delegation passed 2/3. One
CEO startup failed because the runner did not receive a provider turn
identity. The cause is unresolved.
- An unchanged follow-up passed delegation three times and backlog
twice. Combined evidence is backlog 5/5 and delegation 5/6. Each attempt
passed cleanup. Later passes do not erase the earlier failure or prove a
runner repair.
- Earlier failed revisions exposed an invented task hostname, private
account metadata false positives and missing funding for unpriced
subscription usage. Those led to the specific changes above; the failed
records remain retained locally.
- The runbook records campaign identifiers and definition provenance.
Generated result artifacts are not committed. Historical live results
predate this branch rebase; fresh PR-source live evidence and final
validation are recorded below.
- Full workspace typecheck and production build passed on the rebased
branch. Product E2E typecheck passed.
- The full Product E2E support suite first reproduced four baseline
failures: two missing active Copilot image-identity inputs and two stale
Pi/catalog expectations. The narrow contract fixes above resolved them.
The full rerun passed 4,282 Vitest tests plus 137 Node tests, with two
skipped. Image checks verify mutation changes the hash, unchanged input
stays stable, and an input closure without Copilot is unaffected.
Original failed logs remain retained.
- The repo-wide local Vitest run has reported two failures in unchanged
service files. The Workspace connection test passed an isolated recheck
and its full file passed 469/469 unchanged. The recovery test hit a
15-second timeout; its full file passed 89/89 unchanged. The run later
hit explicit PostgreSQL `semget` resource exhaustion and was interrupted
after those observed failures; no final aggregate counts or full local
pass are claimed. Its complete available log is retained. No assertion
or timeout was weakened. Matching remote server CI passed on the same
source.
- On clean PR head `39ad80b523ce194c90aafafd077d48dd9a36b4c5`, backlog
passed in `local-2026-10-26T19-24-13-014Z`. The parallel delegation
fixture failed during PostgreSQL initdb, before browser or model
execution; its failed cleanup grade is retained. A disposable standalone
initdb probe then passed. No semaphore sets or kernel settings were
changed before that probe/recheck. After confirming no remaining fixture
process, its private temporary files were removed.
- One separate delegation recheck passed in
`local-2026-10-26T19-29-24-800Z`, with one attempt, zero automatic
retries and successful cleanup. Both passing current-source cells use
definition
`3f2c9ba2d03e3dcddde47ddab3b43bc52de977f25e256fceae0a24c9128e204b`. The
earlier bootstrap failure and the historical provider startup failure
remain distinct. These local results omit automatic source-SHA metadata;
the clean checkout SHA is recorded here from the execution session.
- The later broad local run reported `could not create semaphores: No
space left on device`. A bounded cleanup removed 32 current-user
PostgreSQL sets with 17 members, marker 537, a dead recorded creator and
zero waiters. No live process or kernel limit was changed by that
cleanup. The test process group was subsequently stopped; no broad rerun
is planned. This direct later resource failure does not prove the
precise cause of the earlier live initdb failure.
- Review follow-up adds only static catalog validation and documentation
of the existing five-minute journey bound. The executable definition is
unchanged. Focused catalog/oracle tests passed 28/28; no redundant live
run is claimed.
- Final head `30fcb36ac9ae1f0270a589dbfafcec91ca6a03f3` passed all
required and underlying CI checks in [run
40391402347](https://github.com/paperclipai/paperclip/actions/runs/40391402347),
including `ci / verify` and `ci / e2e`. Greptile and Paperclip Review
both scored this head 5/5, with all review threads resolved. The static
follow-up leaves every executable definition input byte-identical to the
live-tested source at `39ad80b`.
Normal squash auto-merge is enabled. Actual merge is pending eligible
code-owner approval for the owned dependency manifest; no protection is
bypassed.
## Risks
- Live model behavior can vary. One missing turn-start event remains
unexplained; this PR does not claim provider reliability or broad
catalog qualification.
- Subscription costs are unpriced. Explicit fixture funding admits that
usage. Run counts and deadlines remain bounded, but the dollar limit
cannot cap unknown cost.
- Account identity exceptions apply only to known private Codex runtime
files. Token reuse, unknown files and model-visible rollout content
remain blocking findings.
- Deterministic checks establish saved state, output structure, required
brief facts and access. They do not score all prose quality. Initial
samples also require human inspection.
## Model Used
OpenAI Codex, GPT-6 family, with reasoning, code execution, browser and
repository tools. The precise model revision and context window are not
exposed to this session. Live eval agents used `gpt-5.6-sol`; that is
the evaluated model, not a claim about the authoring model.
## 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 local tests; focused suites pass and the interrupted
full-run failures are documented above
- [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>
## Thinking Path
> - Paperclip manages agents and their work.
> - Product E2E evaluations send model work through a gateway with cost
limits.
> - The gateway checks the request body before it reserves money or
contacts a provider.
> - A qualification probe needs that same check before it records a
spending-cap denial.
> - Namespace support already exists. Qualification must share that
policy without sending a paid request.
> - This pull request exposes the pure request validator and bounds the
supported local tool definitions.
> - The benefit is one request policy for qualification and forwarding.
## Linked Issues or Issue Description
Refs: #17452, #17469.
**What happened?**
The request validator was private to `forwardEvalRequest`. A
qualification caller could not reuse the request policy before
admission. A separate check could accept a request body that forwarding
rejects before a reservation.
**Expected behavior**
Qualification and forwarding use the same pure validator. One-level
OpenAI namespaces with local function or custom tools remain supported.
Invalid tool definitions fail before accounting or transport work.
**Steps to reproduce**
Use the synthetic native-daemon request fixture in
`eval-gateway.test.ts`. It has seven local function tools and one
namespace with five local function tools. Call the shared validator,
then forward through the fake provider. Run the malformed namespace and
tool-count cases to check rejection before side effects.
The namespace behavior follows the [OpenAI function-calling
guide](https://developers.openai.com/api/docs/guides/function-calling).
This change preserves the one-level contract introduced in #17452 and
hardened in #17469.
## What Changed
- Export `boundedEvalPayload` with credential-free route fields.
`forwardEvalRequest` calls that function.
- Keep one namespace level with function or custom leaves. Require exact
leaf types, nonblank string leaf names, and a closed namespace wrapper.
- Limit OpenAI tool definitions to 1,024 per request. Count namespace
wrappers and their children.
- Add native-daemon-shaped forwarding coverage, malformed and hosted
tool rejection, count and depth boundaries, and Anthropic compatibility
checks.
- Document the shared qualification policy in the Product E2E security
guide.
- Compile the real observability validator in the test parent. The owned
CLI fixture imports JavaScript, so its process group does not include a
test-only TypeScript compiler service. The parent resolves the compiler
from the root package, which declares that dependency. Production
cleanup checks and attempt deadlines stay intact.
## Verification
- `pnpm exec vitest run --config tests/runner-e2e/vitest.config.ts
eval-gateway.test.ts cost-ledger.test.ts provider-usage.test.ts
operating-overhead.test.ts operations.test.ts`: 173 passed.
- `pnpm test:e2e:runner:typecheck`: passed.
- `pnpm -r typecheck`: passed.
- `pnpm build`: passed.
- Separate Node support checks: 137 passed.
- `pnpm test:e2e:runner:unit`: 4,271 passed, two skipped, four failed in
unchanged Daytona image and Pi catalog contracts. The same four failures
reproduce on untouched base commit
`a67a18c171816b097f46eae78fc58c7e55c9c565` (79 passed, four failed in
those files).
- `pnpm test:run`: interrupted and incomplete after required CI
completed. Initial database startup failed because this checkout omitted
the embedded PostgreSQL package postinstall aliases. The package
hydrator restored them, and 14 real database checks passed. Earlier
failures and the full output remain preserved; this local full run is
not counted as passing verification. Its owned process group exited
after SIGINT, with no owned survivors.
- An offline full native authentication probe used the real Rust daemon
and pinned Codex 0.160.0 Darwin SDK. The same captured request failed
the older operations policy before reservation and reached a mock
reservation with this policy. The OS sandbox allowed loopback only. It
used synthetic credentials, retained no raw model payload, and made no
provider calls.
- Controller fixture suite: 70 passed. Three cold comparisons each
confirmed that the old child started an owned compiler service and the
corrected child did not. On Darwin the old compiler also exited cleanly,
so this does not prove the exact historical Linux process race. Fresh
Linux CI is required.
- Independent review passed. The private qualification integration
passed 14 exact-source compatibility checks and 67 shared-source tests
without provider calls.
- Required GitHub CI checks passed on the current head. The separate
Entire approval gate still awaits an eligible reviewer; the delegated
author account's explicitly AI-assisted approval does not satisfy it.
## Risks
Requests with more than 1,024 OpenAI tool definitions or extra namespace
wrapper fields now fail closed. New provider schema fields will need
review. Anthropic tool handling, model prices, billing restrictions,
output caps, and reservation ordering remain unchanged. This offline
request-policy proof does not establish a completed model turn or Linux
or Cloud onboarding acceptance.
## Model Used
OpenAI Codex, GPT-6 family. The exact serving model identifier and
context window are not exposed in this session. The model used
reasoning, tools, and code execution.
## 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
- [ ] 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>
Retain bounded native tracing in the Runner controller with attempt-bound relays, private export receipts, offline cost replay, conservative holds and bounded failure diagnostics.
Verified exact head 5cb991421e: full hosted CI, fresh Greptile 5/5, zero unresolved threads, 70 local controller tests including actual Codex/Claude CLI observability validators. Secondary review has no must-fix or should-fix findings and records optional coverage follow-ups. No paid evals or schedule changes.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip manages AI agents and their work.
> - Paid runner evals test real provider integrations.
> - Copilot cells use the saved-token connection path.
> - The two trusted workflows did not pass the Copilot credential to
those cells.
> - This PR supplies it only when the selected cell needs it.
> - Existing environment and actor gates protect access in this public
repository.
## Linked Issues or Issue Description
Related: #15705 and #15706. A search found no open PR that adds this
workflow credential binding.
**Describe the bug**
Copilot Product and direct-protocol eval cells require
`COPILOT_GITHUB_TOKEN`. The protected paid workflows do not currently
pass that environment secret to the selected execution step.
**Expected behavior**
Only a selected Copilot cell receives this credential. Ordinary PR,
build, catalog, image and reporting jobs receive none.
**Steps to reproduce**
Dispatch the trusted full-stack workflow for one Copilot cell.
Credential validation fails before the task starts, although the
protected environment can hold a valid token.
**Environment**
GitHub Actions in the public `paperclipai/paperclip` repository, with
the reviewed workflow on `master` and the `runner-e2e-paid` environment.
## What Changed
- Pass `COPILOT_GITHUB_TOKEN` in the paid Product and direct-protocol
execution steps, only when `matrix.credentialName` selects it.
- Add the missing Copilot protocol-catalog credential mapping and verify
it reaches the selected execution matrix.
- Add security checks for the selected-cell binding and bounded
protected-job scope. Extend the scan that rejects provider credentials
in unrelated workflows.
- Document the Copilot credential scope. No secret values, account data
or private test evidence are in this PR.
## Verification
- Product workflow security: 16 tests passed on this head.
- Protocol catalog and workflow security: 21 tests passed, including the
Copilot matrix regression reproduced red before its fix.
- Current-head required `ci / verify` and `ci / e2e` are green. Greptile
is 5/5 with zero unresolved review threads.
- The first CI attempt retained runner-shutdown failures; one failed-job
retry passed on the unchanged head. Both attempts remain in [the CI
run](https://github.com/paperclipai/paperclip/actions/runs/40342429106).
- `git diff --check` passed.
- A selected-credential scan found zero matching secret values in the
seven changed files.
- The environment setting was separately checked: `master` only,
required approval from existing allowlisted code owners, and
administrator bypass disabled. The new secret exists only at environment
scope; no repository-wide duplicate was created.
- The packaged Copilot runtime verified the selected token and the
explicit model without a model prompt. A fresh local UI journey then
created an agent, completed its first task and verified the downloaded
artifact and cleanup.
## Risks
The selected paid cells gain access to one additional environment
credential. Missing credentials still fail closed. Default-branch
checks, initiating/rerunning actor checks, protected environment access
and per-cell credential selection remain in place. This PR adds no
trigger and gives no credential to builds or ordinary PR checks.
## Model Used
OpenAI Codex, based on GPT-6, with repository tools and browser
regression tests. The exact runtime model identifier is 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 linked existing issues or described the issue in-PR
following the relevant issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links
- [x] My branch name describes the change and contains no internal
ticket id
- [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>
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work.
> - Runner evals execute real provider harnesses against maintained
fixtures.
> - Turn-level usage arrives after requests have already spent money.
> - Parallel cells need distinct allowances before requests start.
> - Missing output must preserve the remaining allowance and any known
charges.
> - This pull request adds a controller that reuses the existing request
ledger and gateway.
> - It makes a bounded local Runner attempt reviewable before hosted
scheduling is enabled.
## Linked Issues or Issue Description
Refs #17440. That PR added the explicit Runner gateway route. This PR
owns request admission and retained campaign accounting for that route.
The existing hosted matrix is not enabled or changed here. Its global
allocation, rerun rejection, and private evidence archive remain
separate integration work.
## What Changed
- Validate a trusted manifest with exact request, CLI, package, daemon,
model, and source identities. Assign each selected cell a distinct
allowance. Count operating overhead once. Reject allocations above the
campaign limit before launch.
- Run native Codex or ACPX Claude through the shared request proxy and
append-only ledger. Pass only the proxy credential to the child. Refuse
local attempt reuse and preserve existing output files.
- Close gateway admission on cancellation. Retain the ledger, receipts,
route descriptor, child result, and cleanup evidence outside the
disposable workspace.
- Recompute campaign accounting from retained ledgers. Missing or
invalid final evidence holds the full cell allowance while preserving
known charges. Reports distinguish provisional and incomplete costs.
- Accept namespaces containing only local function/custom tools. Disable
web search in the controlled Codex profile. Continue to reject hosted
tools, including tools hidden inside a namespace.
- Add controller tests to the existing Runner static test path and
document this source-checkout entry point.
## Verification
- 20 controller tests pass. They use real child processes, local HTTP,
and the actual ledger. Cases cover reservations before dispatch,
concurrent cell isolation, caps, cancellation, replay rejection, lost
artifacts, changed receipts, and Braintrust Claude routing. Upstream
responses are synthetic.
- 52 shared gateway tests and 55 Runner CLI tests pass. The namespace
acceptance and web-search configuration regressions failed before the
repair and pass afterward.
- Runner TypeScript/Rust checks, Runner build, shared E2E typecheck, and
`git diff --check` pass.
- The first actual-harness probe found that Codex advertised both a
local tool namespace and web search. It reached no upstream transport.
That failure is retained; the compatibility repair does not allow paid
hosted tools.
- An earlier test failure showed that separate dynamic imports created
different admission-error classes. The shared runtime bridge now loads
one module graph. Another regression showed that a missing final report
hid known ledger charges; the collector now preserves those charges.
- The repaired actual-harness probe passed its control checks for native
Codex and ACPX Claude: each reached exactly one synthetic upstream
request after the ledger reservation; both retained the unresolved hold
and route evidence; both recorded clean process exit. A scan of 41
retained files found no synthetic upstream credential. Deliberate
provider rejection preserved the failed Codex turn and Claude timeout;
these are not semantic passes. Prices, operating bounds, and the package
archive identity in this probe were synthetic.
- Review regressions reproduced lost request/receipt evidence, lost
admission metadata, executable replacement after verification, and a
SIGTERM-resistant descendant surviving the CLI. The repairs now pass.
Executable bytes are staged before launch; a trusted Node resolution
hook preserves relative imports. A symlink-path regression also failed
before its repair and now passes. The final staged native probe repeated
both one-request checks successfully.
- Full current-head
[CI](https://github.com/paperclipai/paperclip/actions/runs/40115932485)
passed on `4781487215116afd10a415d4db53b1ec8e004dd5`: all 58 check runs
and the legacy status are successful, neutral, or skipped. Greptile and
Paperclip both reviewed this commit at 5/5. All five finding threads are
fixed and resolved. No paid provider request ran during this change.
## Risks
- This is a trusted source-checkout controller, not a published package
command. It needs the repository's installed shared cost dependencies.
- The manifest declares reviewed prices and full-lifecycle bounds.
Synthetic tests do not qualify real prices, invoices, storage, or
Braintrust metering.
- The attempt-directory guard is local. Hosted fanout still needs unique
global allocations, rerun rejection, and durable private retention. Do
not enable the existing matrix on this change alone.
- Forced child termination can leave cleanup unverified. That attempt
remains incomplete and holds its full allocation. These checks do not
claim a host security boundary against an adversarial target.
- The current private publisher does not archive the separate controller
directory. Native trace relay, private report integration, and live
qualification remain open.
## Model Used
OpenAI Codex, GPT-6 family, with reasoning, tool use, and code
execution. This runtime does not expose the exact model ID or
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 `#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>
Keep remote native work under its authenticated connection lease through controller outages. Hold durable ACPX tools through reconnection, align the native Claude HTTP MCP client budget, and wait for the recovered handler before dispatch. Preserve Stop, cancellation, exact identity and artifact checks.
Verified with real-process regressions and a real Claude Opus 5.5 Daytona workflow: 125 seconds offline during useful work, original process and lease retained, no failed native tool calls, queued follow-up completed, independently verified ZIP and committed workspace receipts. All current-head CI gates pass and Greptile is 5/5 with all findings resolved.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
## Thinking Path
> - Paperclip's Product E2E journeys verify user outcomes in the real
app and GitHub.
> - The review journey must show the score and failed check for its
exact reviewed commit, then the visible task status before and after
reload.
> - GitHub includes a hidden “Re-run failed checks” menu item before the
visible check result.
> - The journey selected that hidden item and failed even after native
work and publication completed. A subsequent attempt exposed the same
first-text-match problem with Done in the task UI.
> - This change reads the selected check's status header and binds its
URL, score, and commit.
> - Browser fixtures retain this failure and reject plausible wrong
projections.
## Linked Issues or Issue Description
Refs: #17457, #17513, #17551.
**What happened?**
The bot completed its native run and task, then published its summary,
inline precision finding, and failed 2/5 check. The browser assertion
selected a hidden “Re-run failed checks” menu item before the visible
result, so the journey still failed. After that was corrected, the next
live attempt passed the check projection but selected hidden Done text
before the visible task status.
**Expected behavior**
Verify the actual selected GitHub check. A hidden menu item or a word in
the model's narrative cannot prove its conclusion.
**Steps to reproduce**
1. Render a hidden “Re-run failed checks” item before a visible failed
check.
2. Use the old first text match for “failed”.
3. Observe the false visibility failure.
**Paperclip version or commit**
The base includes the journey changes from #17457 and #17513.
## What Changed
- Validate the check URL against the configured repository and select
its exact check-run ID.
- Require the expected score and full reviewed commit inside that check.
- Read failure status only from that check's header.
- Give each projection step its own phase so failures identify the
correct boundary.
- Stage the verified persisted screenshot as the standard report
final-state artifact, rejecting a passing report if it is absent.
- Preserve measured billing summaries during regeneration when raw run
usage is absent; newer raw usage takes precedence.
- Extend the catalog-wide history fixture to include the new journey
evidence contract.
- Read task completion from the visible Status property picker before
and after reload, with separate phase labels.
- Add eighteen isolated browser fixtures to the existing browser-support
suite and document both boundaries.
## Verification
- Reproduced the old selector failure in the live GitHub page and a
credential-free browser fixture before fixing it.
- All 60 browser-support cases pass, including eighteen focused
projection cases. They reject the wrong check status, score, commit,
page, and repository reference, plus hidden or unrelated Done text.
- All 163 focused billing, history, accounting, report, and journey
tests pass, as does runner E2E typechecking.
- A regression reproduced discarded saved token totals. Retained totals
now survive per-cell and campaign aggregation while missing dollar
prices stay unknown; fresh raw usage still overrides stale summaries.
- Diff and credential-value checks pass.
- The earlier failed attempts remain failed. A fresh complete QA journey
passed all 18 checkpoints and cleanup with a successful native run, a
below-threshold review and inline precision finding, the correctly
failed check, visible Done status, and reload persistence. The later
reference-validation commit changes only browser fixtures; the live
driver bytes are unchanged.
- A report regression reproduced the missing standard final-state
artifact. The packager now aliases only the hash-verified persisted
screenshot for passing results; missing final-state proof is rejected.
Presentation regeneration preserves the original live grade and
dispatches no provider work.
## Risks
This depends on GitHub's check-run header structure. A markup change
fails the journey instead of accepting narrative text as a result. The
product runtime and behavioral oracle stay unchanged. Usage-price
coverage remains a separate evidence dimension. A saved billing summary
is reused only when raw usage is absent, preserving the recorded
coverage and unknown prices.
The separate advisory Paperclip Review remains queued after its prior
assigned attempt timed out. Its normal Retry control rejected the
obsolete failed chat request as unsafe to retry. Required repository
gates `ci / verify` and `ci / e2e` pass, all 55 completed CI checks are
green, and final-head Greptile is 5/5 with no unresolved findings. The
advisory queue is not represented as a completed assessment.
## Model Used
OpenAI Codex, based on GPT-6. The exact runtime model ID and
context-window size are not exposed in this session. Used for code,
browser fixtures, and live evidence analysis.
## 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 <paperclip@paperclip.ing>
Co-authored-by: Paperclip <bot@paperclip.ing>
## Thinking Path
> - Paperclip manages work performed by AI agents.
> - The Product E2E harness verifies a GitHub review-bot journey.
> - GitHub can return a registration page without the expected creation
control.
> - The journey could then wait for the full login allowance without
useful evidence.
> - A failed native run can also retain a retry after its terminal
status is visible.
> - This change records a safe registration boundary and uses the normal
Stop route for owned retries.
> - Operators can diagnose the setup failure and confirm cleanup without
changing the behavioral oracle.
## Linked Issues or Issue Description
Refs: #17457.
**What happened?**
The GitHub review journey waited at App registration with no useful
handoff evidence. Its cleanup also skipped failed native runs that still
owned a durable retry.
**Expected behavior**
The journey should report a bounded registration failure or
reauthentication boundary. Cleanup should Stop an owned native retry and
require its audited acknowledgement.
**Steps to reproduce**
1. Run the configured GitHub review journey.
2. Return a GitHub registration page without the expected creation
button, or fail a native review run while its coordinator can retry.
3. Inspect the result and cleanup evidence.
**Paperclip version or commit**
Source built from current master. This extends the driver merged in
#17457.
## What Changed
- Bound the registration render wait to 30 seconds. Keep the separate
attended confirmation allowance.
- Retain GitHub origin, path, and control-presence flags. Retain
headings, button labels, and alerts only on known registration error
pages without authentication fields.
- Exclude query parameters, entered values, page bodies, grant payloads,
and authentication content from that diagnostic.
- Add an optional private authentication hook for ordinary GitHub access
reconfirmation. Detect passkey-first sudo at the manifest URL without
retaining its authentication content.
- Stop owned failed native retries through the existing run-only
cancellation route. Verify company, agent, task, and audit
acknowledgement.
- Use native Stop correlation only for native runs. Queued legacy or
unresolved runs use the ordinary cancel request. Stop scheduled retries
and wait for them to leave the live state set.
- Keep pending accounting debt intact. Add regression coverage and
journey documentation.
## Verification
- Focused journey and report suite: 58 tests passed.
- Runner E2E TypeScript check passed.
- `git diff --check` passed. Credential-value scan passed.
- Live fixture reproduced the missing creation control at the manifest
handoff. The new diagnostic retained its path and control-presence
flags. No model work started. Draft cleanup passed.
- All 58 current-head checks are terminal and green. Greptile scored the
exact head 5/5, with no unresolved review threads.
## Risks
GitHub pages that take more than 30 seconds to render the creation
control now fail early. Native cleanup fails closed if the server does
not provide the expected Stop acknowledgement. The live setup-to-Done
behavioral journey is still unqualified. These changes do not repair a
missing provider usage receipt or weaken its accounting gate.
## Model Used
OpenAI Codex, based on GPT-6. Exact runtime model identifier and
context-window size are not exposed in this session. Used for code
execution, browser tooling, and regression analysis.
## 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>
Co-authored-by: Paperclip <paperclip@paperclip.ing>
Dotta