PaperClipAI

Jannik/PaperClipAI

0 Fork 0

mirror of https://github.com/paperclipai/paperclip.git synced 2026-10-06 10:48:12 +02:00

Commit Graph

Author	SHA1	Message	Date
DottaandPaperclip	b648d8cdda	fix(evals): support explicit Grok qualification workflows (#13878 ) ## Thinking Path > - Paperclip manages AI agents and their provider connections. > - Product E2E checks real tasks through the browser, server, and runner. > - Grok qualification needs separate API-key and subscription evidence. > - Product subscription tests and direct Grok protocol evals need explicit credential delivery. > - This change supplies each credential only to its selected profile and prepares the pinned binary. > - Maintainer authorization and protected-environment gates remain required. ## Linked Issues or Issue Description Refs #13845, #13847, #13850, #13882. The Grok feature branch has a manual subscription qualification profile. The trusted master workflow must admit its selected credential and prepare the same verified binary and artifact verifier as the API profile. Direct protocol evals also need the selected xAI key and pinned Grok binary. These prerequisites do not register or schedule the new profiles on master. ## What Changed - Deliver `GROK_AUTH_JSON` from the protected paid environment only when the selected profile requests that credential. - Install the checksum-verified Grok binary for the local subscription profile. - Prepare the pinned artifact verifier for the manual subscription suite. - Extend workflow security assertions to cover the new credential and profile. - Add the ACPX Grok credential mapping to the trusted-master catalog, then deliver only the selected `XAI_API_KEY` to direct protocol cells and install the target’s checksum-verified Grok binary before packaging. - Allow a direct-protocol concurrency override from two cases up to the existing configured ceiling; it can only lower concurrency. - Document the Grok protocol workflow and its API-only credential boundary. - Render missing LLM usage and cost as Unavailable, and label partial observations with coverage. Preserve raw records, grades, and actual zero costs. - Preserve measured campaign source metadata during report regeneration instead of inheriting the renderer checkout or CI event; skip empty legacy source records when recovering older provenance. ## Verification - Latest commit `05d05801477104c8155977bbbe3e119a5241f960`: all 54 reported checks successful, two intentional skips, Greptile 5/5, and zero unresolved review threads. [CI run](https://github.com/paperclipai/paperclip/actions/runs/35890978288). - After merging current master, all 17 workflow security/image tests and 23 catalog/workflow policy tests passed. The trusted catalog also generated all 39 pinned Grok cells with `XAI_API_KEY` and one case per shard. The new policy tests execute the concurrency guard against valid, out-of-range, and malformed values. - The Grok branch separately passed 450 Product harness unit tests, including private company credential staging, cleanup, and token-fragment redaction. - The fresh-login native subscription smoke passed three repetitions of tool execution, session resume, restrictive permissions, and cleanup. These are setup evidence; full subscription Product qualification remains pending. - All 72 focused report/billing/history/catalog tests and the Product harness typecheck passed for the report-display change. The initial sandbox run could not open the tsx IPC socket; the permitted rerun passed. A zero-provider-call replay of the actual 16-cell Grok campaign preserved all result records, grades, timing, and source provenance while correcting missing usage labels. - Review the thirteen-file diff. Provider credentials still enter only the selected paid-test step; default-branch, numeric-actor, and environment restrictions are unchanged. ## Risks This admits a refreshable subscription credential to explicitly selected trusted tests. Store it only in `runner-e2e-paid`, use a test login, and remove it after qualification. Unselected profiles receive an empty value. Pull requests cannot trigger the paid workflow. This PR changes no fleet admission or actor allowlist. ## Model Used OpenAI GPT-6 through Codex, with tool use and code execution. The exact serving model identifier and context-window size 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>	2026-09-23 17:05:52 -05:00
DottaandPaperclip	11921075a4	Add first-task onboarding skill and Runner E2E coverage (#13517 ) ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - The first task helps a new user define and approve useful work. > - That workflow needs reusable instructions and tests against the production experience. > - Native Codex and Claude must load the assigned skill, including after resume. > - Maintainers need recorded conversations and precise failed checks to judge regressions. > - This pull request adds the first-task skill and a suite in the shared Runner E2E harness. > - It keeps behavior results separate from informational quality scores and incomplete recordings. ## Linked Issues or Issue Description What existing behavior does this improve? The first onboarding task and the Runner E2E report used to review it. Current behavior Onboarding embeds its policy in a hidden brief. Native Codex drops the skill-instructions setting at the Rust boundary. The shared E2E harness has no onboarding suite or full conversation view. Proposed behavior Assign and invoke `/first-task` for the onboarding task. Send selected Codex skills as structured protocol inputs. Run twelve scenarios across legacy Codex, legacy Claude, native Codex, and native ACPX Claude. Include all 48 cells in full campaigns. Show recorded chat, question and approval cards, exact checks, instructions, and billing in the shared dashboard. Reason and benefit Measure the real onboarding experience before changing prompts. Distinguish infrastructure failures, behavior failures, and unexercised journey steps. Breaking changes No database migration or production API change. First-task instructions now live in an assigned skill. The user-edited persona is preserved; the skill includes the maintainer-approved proposal-mode mapping and saved-plan requirement. Related: #11043 is earlier onboarding work. #13422 already fixes native Claude model pinning, context delivery, and read permissions on master; this branch includes those fixes through its base. The new Claude recovery test supplements them. ## What Changed - Extract and assign the first-task skill while retaining the production greeting and opening question. - Carry the Codex skill-instructions flag through thread start and resume. Resolve explicit task skill references only against assigned skills and send native skill inputs. - Invoke an unambiguously selected assigned skill through Claude ACPX’s native slash-command parser on initial and resumed turns, retaining the entire task/wake envelope as its argument. Do not carry that invocation into ordinary tasks. - Restore the saved single-task proposal modes: confirmation card, or saved plan with revision-targeted checkbox approval. Explicit plan requests also require a saved plan. - Add first-response and complete-journey cases with fixed user facts, acceptance checkpoints, durable outcome checks, and accounting for child runs. - Fail the eval when choice questions have fewer than two real options. Recognize planning documents without treating them as completed work. - Add optional, bounded quality judging as explicit post-processing. - Render full conversations and static interaction cards in the shared report. Conversations start folded. Show original and regraded results and incomplete journeys distinctly. - Keep credential-persistence scanning outside the first-task behavioral suite; retain public evidence redaction. - Refresh generated capability references after the API-reference edits. - Correct shared native question guidance and tool schemas: choices need at least two meaningful options; open-ended questions use canonical text fields with the required compatibility payload. Verify both formats through real tool-authority persistence. - Disable announcements automatically for every isolated Runner E2E process and label the gallery environment/provider/target explicitly. - Remove CI races in the GitHub connection browser test and native session recovery test by waiting for the actual async work before asserting its results. ## Verification - `pnpm exec vitest run server/src/services/onboarding-first-task-assets.test.ts server/src/__tests__/issue-onboarding-first-task-routes.test.ts`: 19 passed. - `pnpm --dir packages/paperclip-runner exec vitest run src/drivers/acpx/runtime-host.test.ts src/drivers/acpx/native-skill-prompt.test.ts src/cli/acpx-runtime-sidecar.test.ts`: 70 passed. Native command forwarding and the 1 MiB input boundary both failed before their fixes and passed afterward. Coverage includes changed skills on reopen, approval context, and an ordinary subsequent task. - Runner E2E unit suite: 306 passed. Harness typecheck passed. The 64 first-task fixture and grader tests also pass. - Full repository typecheck and build passed locally. Server typecheck and Runner build passed again after the native-command change. - Full GitHub Actions CI passed on `23e56447b`: all server/workspace/browser shards, Runner verification, typecheck/release registry, build, canary, policy, and Docker checks. Greptile reviewed this exact head at 5/5 with no unresolved threads. The earlier broad local run had database startup/timing failures that passed isolated retries; the complete remote suite is green. - Merge verification against current master: 312 harness tests and 13 native recovery tests passed. Regenerated semantic contracts and fixture hashes pass their consistency check. Full local typecheck and build also passed on the stacked queue branch. After merging the latest master and preserving the GitHub setup timing regression in the split browser suite, both focused GitHub browser tests passed. Three CI timing/startup flakes passed local verification and one remote retry; all latest-head checks are green. - Real pinned Claude SDK and Claude ACP JSON-RPC probes against a local mock API confirmed that `/skill-name` expands the assigned skill body before the model request and retains the task arguments. A prose mention does not. The probes made no paid model calls. The ACP probe used the current first-task skill body and retained the wake arguments. - [Full 48-case campaign and report](https://pages.paperclip.ing/runner-e2e-first-task-35053063880/): 44 passed after three interrupted Codex cases completed in targeted reruns. Original results, regrades, and all 51 executions remain in the report provenance. - [Claude campaign after the shared-question fix](https://pages.paperclip.ing/runner-e2e-first-task-claude-35099525201/): 10/12 passed with zero single-option failures. All 12 recorded the current assigned skill and corrected guidance. The failures exposed skipped skill invocation and a missing saved plan. This PR adds native command invocation and explicit saved-plan instructions; the subsequent report below still shows behavior failures. - [Fresh 12-case Claude report](https://pages.paperclip.ing/runner-e2e-first-task-claude-35102737804/) at `78452129e`: 10/12 pass after correcting two false proposal-matcher failures. The recordings said “Here is the task I will create and run/complete” in approval cards; the old matcher missed that word order. Regression tests failed before the fix and pass after it. Original results and offline regrade provenance remain linked. No agent rerun was needed. Zero single-option-question failures; two behavior failures remain: direct work before acceptance on a plain first message, and an explicit plan request without a saved plan. Neither check was relaxed. The follow-up `82087ac7e` fixes command-prefix size accounting; `94aefb1f3` fixes only that proposal matcher. - Report browser checks confirm folded conversations, rendered cards, explicit Local/Daytona labels, and no page errors. The published-object audit scanned 1,306 text files across 2,154 objects with no credential-format findings or prohibited files. Image pixels and unknown token formats are outside that scan. ## Risks - Model behavior is nondeterministic. One campaign is evidence, not a guarantee. The two remaining Claude behavior failures are visible in the report and require further product work; this PR does not claim all onboarding scenarios pass. - The suite checks persisted Paperclip effects. It cannot prove the absence of arbitrary external effects. - Historical recordings can miss later journey steps. These remain incomplete, never passes. - Native profiles switch runtime after the production onboarding wizard because it does not yet expose a native option. - Quality scores are informational and cannot override behavioral failures. ## Model Used OpenAI Codex, GPT-6, with reasoning, repository tools, and code execution. The exact deployed model identifier and context-window size 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>	2026-09-16 14:24:32 -05:00
Dotta	5716fe907e	test(runner): add full-stack acceptance and eval gates (#12700 ) ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - The runner subsystem executes agent work across local and managed provider backends. > - The lower pull requests restore the task runtime, provider backends, and managed-provider control plane. > - The restored system needs repeatable full-stack checks before it can ship safely. > - Paid live checks also need clear access, cost, and secret controls. > - This pull request adds acceptance, live evaluation, chaos, and release gates for the restored runner stack. > - The benefit is measurable runner parity with safer release decisions. ## Linked Issues or Issue Description Subsystem affected Cross-cutting. This change covers runner tests, release workflows, server contracts, and evaluation tools. Problem or motivation The runner stack did not have one complete acceptance surface for native Codex, ACPX, Claude Managed, and AWS AgentCore. Release checks could miss provider drift, task-view regressions, cost-policy errors, and destructive cleanup errors. Proposed solution Add a 57-cell full-stack catalog, a Daytona image, and opt-in paid workflows. Add live evaluation, chaos, cost-limit, redaction, and release contract checks. Add AWS AgentCore infrastructure and guarded provisioning tools. Keep the native runner experimental flag off by default. Alternatives considered We considered manual smoke tests only. They do not give repeatable evidence and they do not protect release branches. We also considered one large pull request. The stacked pull requests keep each review below the Greptile file limit. Roadmap alignment This work supports the shipped Cloud / Sandbox agents milestone and the shipped Agent evals & feedback milestone in `ROADMAP.md`. Related stack: - #12699 adds managed provider backends and lifecycle support. - #12691 adds qualified OpenCode and ACPX provider backends. - #12685 restores task runtime rendering and steering. ## What Changed - Add the runner full-stack harness with 57 catalog cells and 60 unit tests. - Add a Daytona runner image with digest-pinned base images and base-aware image-content checks. - Add guarded live evaluation and chaos workflows with a fixed 40-execution matrix; live and full-stack paid schedules now run only on Sundays or by manual dispatch. - Add in-flight reported-usage cost stops, post-turn cost caps, exact-threshold failure classification, secret redaction, retry classification, and actor authorization. - Reattach stream and hard-budget listeners before restart-recovery continuations so restored paid sessions cannot bypass in-flight interruption. - Preserve OpenCode usage and cost across tool-loop messages and turns while exposing an explicit current-run delta to durable accounting. - Keep PNG/WebM evidence in access-controlled artifacts only, reject SVG, and publish only pruned inert structured per-attempt evidence. - Add AWS AgentCore infrastructure, provisioning checks, and smoke tools; reject unsafe model identifiers, require exact stack ownership markers, and make failed-stack replacement explicit. - Add evaluation-session contracts and capability reports. - Add release workflow checks for immutable action pins, frozen dependency installs, exact weekly cron shape, paid-run guards, provider-secret isolation, and chaos test paths. - Reauthorize the original and triggering numeric actor IDs as the first step of every provider-secret job, including partial reruns, before checkout or provider access. - Give each full-stack matrix cell only its matching provider credential, expose Daytona only to Daytona cells, and disable shared dependency caches anywhere paid credentials or OIDC write access are present. - Protect the legacy manual E2E workflow with the same default-branch, allowlist, environment, and per-job authorization boundary. - Rotate live-eval candidates by week and retain 120 days of compatible history so the seven-week trend window remains viable. - Restore the root runner-acceptance commands and reconcile reported snapshots, raw receipts, and terminal usage without double counting or losing late usage. - Mark ACPX token deltas exact only when every budget field is present, keep cumulative cost/request authority separate, reject non-USD cost labeling, and include thought tokens in output-token budgets. - Keep `enableNativeRunner` off by default. The acceptance harness enables it only in its isolated test instance. ## Verification Passed locally: - `pnpm --filter @paperclipai/paperclip-runner typecheck` - `pnpm test:runner-acceptance:typecheck` - `pnpm test:runner-acceptance` (19 tests) - focused OpenCode proxy, driver, runnerd transport, live-session, and turn-stream tests (106 tests) - `pnpm --filter @paperclipai/paperclip-runner exec vitest run src/live/clean-room-server.test.ts` (22 tests) - `pnpm test:e2e:runner:typecheck` - `pnpm test:e2e:runner:unit` (62 tests) - `node --test scripts/__tests__/release-verify-workflow.test.mjs` - `pnpm --filter @paperclipai/paperclip-runner test:runner-workflow-evals` (22 tests) - `pnpm -r typecheck` - `pnpm build` - `node --test packages/paperclip-runner/scripts/aws-agentcore-provisioning.test.mjs` (6 tests) - `git diff --check` - `cargo test --manifest-path packages/paperclip-runner/runner/Cargo.toml -p paperclip-runner-core --lib --locked` (161 tests) - focused ACPX provider-event tests (10 tests) - The rebased PR changes 92 files. `pnpm-lock.yaml` is unchanged. I did not run paid live provider jobs or provision AWS resources. Those checks need credentials and can create cost. ## Risks The paid workflows can create provider cost. They require an allowlisted original and triggering actor, the protected `runner-e2e-paid` environment, explicit opt-in variables, and cost limits. The four provider credentials exist only in that master-only environment, which requires allowlisted reviewer approval and disables administrator bypass; repository and organization Actions scopes contain no copies. Provider usage arrives after a billable request, so the live guard cannot prevent one request from crossing a threshold. It interrupts immediately on the first reported threshold hit and permits no continuation. Visual evidence can contain secrets rendered as pixels. PNG/WebM remain only in access-controlled workflow artifacts; SVG and per-attempt XML are excluded, and S3/Pages receive a pruned structured dashboard. The AWS scripts can create cloud resources. They use explicit commands, least-privilege roles, KMS encryption, saved nonsecret metadata, and explicit teardown. This pull request does not enable the experimental native runner for existing instances. > For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and discuss it in `#dev` before opening the PR. Feature PRs that overlap with planned core work may need to be redirected — check the roadmap first. See `CONTRIBUTING.md`. ## Model Used OpenAI Codex with GPT-5. The model used extended reasoning, tool use, code execution, and parallel subagents. ## 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	2026-09-02 08:55:08 -05:00

Author

SHA1

Message

Date

DottaandPaperclip

b648d8cdda

fix(evals): support explicit Grok qualification workflows (#13878 )

## Thinking Path

> - Paperclip manages AI agents and their provider connections.
> - Product E2E checks real tasks through the browser, server, and
runner.
> - Grok qualification needs separate API-key and subscription evidence.
> - Product subscription tests and direct Grok protocol evals need
explicit credential delivery.
> - This change supplies each credential only to its selected profile
and prepares the pinned binary.
> - Maintainer authorization and protected-environment gates remain
required.

## Linked Issues or Issue Description

Refs #13845, #13847, #13850, #13882.

The Grok feature branch has a manual subscription qualification profile.
The trusted master workflow must admit its selected credential and
prepare the same verified binary and artifact verifier as the API
profile. Direct protocol evals also need the selected xAI key and pinned
Grok binary. These prerequisites do not register or schedule the new
profiles on master.

## What Changed

- Deliver `GROK_AUTH_JSON` from the protected paid environment only when
the selected profile requests that credential.
- Install the checksum-verified Grok binary for the local subscription
profile.
- Prepare the pinned artifact verifier for the manual subscription
suite.
- Extend workflow security assertions to cover the new credential and
profile.
- Add the ACPX Grok credential mapping to the trusted-master catalog,
then deliver only the selected `XAI_API_KEY` to direct protocol cells
and install the target’s checksum-verified Grok binary before packaging.
- Allow a direct-protocol concurrency override from two cases up to the
existing configured ceiling; it can only lower concurrency.
- Document the Grok protocol workflow and its API-only credential
boundary.
- Render missing LLM usage and cost as Unavailable, and label partial
observations with coverage. Preserve raw records, grades, and actual
zero costs.
- Preserve measured campaign source metadata during report regeneration
instead of inheriting the renderer checkout or CI event; skip empty
legacy source records when recovering older provenance.

## Verification

- Latest commit `05d05801477104c8155977bbbe3e119a5241f960`: all 54
reported checks successful, two intentional skips, Greptile 5/5, and
zero unresolved review threads. [CI
run](https://github.com/paperclipai/paperclip/actions/runs/35890978288).

- After merging current master, all 17 workflow security/image tests and
23 catalog/workflow policy tests passed. The trusted catalog also
generated all 39 pinned Grok cells with `XAI_API_KEY` and one case per
shard. The new policy tests execute the concurrency guard against valid,
out-of-range, and malformed values.
- The Grok branch separately passed 450 Product harness unit tests,
including private company credential staging, cleanup, and
token-fragment redaction.
- The fresh-login native subscription smoke passed three repetitions of
tool execution, session resume, restrictive permissions, and cleanup.
These are setup evidence; full subscription Product qualification
remains pending.
- All 72 focused report/billing/history/catalog tests and the Product
harness typecheck passed for the report-display change. The initial
sandbox run could not open the tsx IPC socket; the permitted rerun
passed. A zero-provider-call replay of the actual 16-cell Grok campaign
preserved all result records, grades, timing, and source provenance
while correcting missing usage labels.
- Review the thirteen-file diff. Provider credentials still enter only
the selected paid-test step; default-branch, numeric-actor, and
environment restrictions are unchanged.

## Risks

This admits a refreshable subscription credential to explicitly selected
trusted tests. Store it only in `runner-e2e-paid`, use a test login, and
remove it after qualification. Unselected profiles receive an empty
value. Pull requests cannot trigger the paid workflow. This PR changes
no fleet admission or actor allowlist.

## Model Used

OpenAI GPT-6 through Codex, with tool use and code execution. The exact
serving model identifier and context-window size 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>

2026-09-23 17:05:52 -05:00

DottaandPaperclip

11921075a4

Add first-task onboarding skill and Runner E2E coverage (#13517 )

## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work.
> - The first task helps a new user define and approve useful work.
> - That workflow needs reusable instructions and tests against the
production experience.
> - Native Codex and Claude must load the assigned skill, including
after resume.
> - Maintainers need recorded conversations and precise failed checks to
judge regressions.
> - This pull request adds the first-task skill and a suite in the
shared Runner E2E harness.
> - It keeps behavior results separate from informational quality scores
and incomplete recordings.

## Linked Issues or Issue Description

**What existing behavior does this improve?**

The first onboarding task and the Runner E2E report used to review it.

**Current behavior**

Onboarding embeds its policy in a hidden brief. Native Codex drops the
skill-instructions setting at the Rust boundary. The shared E2E harness
has no onboarding suite or full conversation view.

**Proposed behavior**

Assign and invoke `/first-task` for the onboarding task. Send selected
Codex skills as structured protocol inputs. Run twelve scenarios across
legacy Codex, legacy Claude, native Codex, and native ACPX Claude.
Include all 48 cells in full campaigns. Show recorded chat, question and
approval cards, exact checks, instructions, and billing in the shared
dashboard.

**Reason and benefit**

Measure the real onboarding experience before changing prompts.
Distinguish infrastructure failures, behavior failures, and unexercised
journey steps.

**Breaking changes**

No database migration or production API change. First-task instructions
now live in an assigned skill. The user-edited persona is preserved; the
skill includes the maintainer-approved proposal-mode mapping and
saved-plan requirement.

Related: #11043 is earlier onboarding work. #13422 already fixes native
Claude model pinning, context delivery, and read permissions on master;
this branch includes those fixes through its base. The new Claude
recovery test supplements them.

## What Changed

- Extract and assign the first-task skill while retaining the production
greeting and opening question.
- Carry the Codex skill-instructions flag through thread start and
resume. Resolve explicit task skill references only against assigned
skills and send native skill inputs.
- Invoke an unambiguously selected assigned skill through Claude ACPX’s
native slash-command parser on initial and resumed turns, retaining the
entire task/wake envelope as its argument. Do not carry that invocation
into ordinary tasks.
- Restore the saved single-task proposal modes: confirmation card, or
saved plan with revision-targeted checkbox approval. Explicit plan
requests also require a saved plan.
- Add first-response and complete-journey cases with fixed user facts,
acceptance checkpoints, durable outcome checks, and accounting for child
runs.
- Fail the eval when choice questions have fewer than two real options.
Recognize planning documents without treating them as completed work.
- Add optional, bounded quality judging as explicit post-processing.
- Render full conversations and static interaction cards in the shared
report. Conversations start folded. Show original and regraded results
and incomplete journeys distinctly.
- Keep credential-persistence scanning outside the first-task behavioral
suite; retain public evidence redaction.
- Refresh generated capability references after the API-reference edits.
- Correct shared native question guidance and tool schemas: choices need
at least two meaningful options; open-ended questions use canonical text
fields with the required compatibility payload. Verify both formats
through real tool-authority persistence.
- Disable announcements automatically for every isolated Runner E2E
process and label the gallery environment/provider/target explicitly.
- Remove CI races in the GitHub connection browser test and native
session recovery test by waiting for the actual async work before
asserting its results.

## Verification

- `pnpm exec vitest run
server/src/services/onboarding-first-task-assets.test.ts
server/src/__tests__/issue-onboarding-first-task-routes.test.ts`: 19
passed.
- `pnpm --dir packages/paperclip-runner exec vitest run
src/drivers/acpx/runtime-host.test.ts
src/drivers/acpx/native-skill-prompt.test.ts
src/cli/acpx-runtime-sidecar.test.ts`: 70 passed. Native command
forwarding and the 1 MiB input boundary both failed before their fixes
and passed afterward. Coverage includes changed skills on reopen,
approval context, and an ordinary subsequent task.
- Runner E2E unit suite: 306 passed. Harness typecheck passed. The 64
first-task fixture and grader tests also pass.
- Full repository typecheck and build passed locally. Server typecheck
and Runner build passed again after the native-command change.
- Full GitHub Actions CI passed on `23e56447b`: all
server/workspace/browser shards, Runner verification, typecheck/release
registry, build, canary, policy, and Docker checks. Greptile reviewed
this exact head at 5/5 with no unresolved threads. The earlier broad
local run had database startup/timing failures that passed isolated
retries; the complete remote suite is green.
- Merge verification against current master: 312 harness tests and 13
native recovery tests passed. Regenerated semantic contracts and fixture
hashes pass their consistency check. Full local typecheck and build also
passed on the stacked queue branch. After merging the latest master and
preserving the GitHub setup timing regression in the split browser
suite, both focused GitHub browser tests passed. Three CI timing/startup
flakes passed local verification and one remote retry; all latest-head
checks are green.
- Real pinned Claude SDK and Claude ACP JSON-RPC probes against a local
mock API confirmed that `/skill-name` expands the assigned skill body
before the model request and retains the task arguments. A prose mention
does not. The probes made no paid model calls. The ACP probe used the
current first-task skill body and retained the wake arguments.
- [Full 48-case campaign and
report](https://pages.paperclip.ing/runner-e2e-first-task-35053063880/):
44 passed after three interrupted Codex cases completed in targeted
reruns. Original results, regrades, and all 51 executions remain in the
report provenance.
- [Claude campaign after the shared-question
fix](https://pages.paperclip.ing/runner-e2e-first-task-claude-35099525201/):
10/12 passed with zero single-option failures. All 12 recorded the
current assigned skill and corrected guidance. The failures exposed
skipped skill invocation and a missing saved plan. This PR adds native
command invocation and explicit saved-plan instructions; the subsequent
report below still shows behavior failures.
- [Fresh 12-case Claude
report](https://pages.paperclip.ing/runner-e2e-first-task-claude-35102737804/)
at `78452129e`: 10/12 pass after correcting two false proposal-matcher
failures. The recordings said “Here is the task I will create and
run/complete” in approval cards; the old matcher missed that word order.
Regression tests failed before the fix and pass after it. Original
results and offline regrade provenance remain linked. No agent rerun was
needed. Zero single-option-question failures; two behavior failures
remain: direct work before acceptance on a plain first message, and an
explicit plan request without a saved plan. Neither check was relaxed.
The follow-up `82087ac7e` fixes command-prefix size accounting;
`94aefb1f3` fixes only that proposal matcher.
- Report browser checks confirm folded conversations, rendered cards,
explicit Local/Daytona labels, and no page errors. The published-object
audit scanned 1,306 text files across 2,154 objects with no
credential-format findings or prohibited files. Image pixels and unknown
token formats are outside that scan.

## Risks

- Model behavior is nondeterministic. One campaign is evidence, not a
guarantee. The two remaining Claude behavior failures are visible in the
report and require further product work; this PR does not claim all
onboarding scenarios pass.
- The suite checks persisted Paperclip effects. It cannot prove the
absence of arbitrary external effects.
- Historical recordings can miss later journey steps. These remain
incomplete, never passes.
- Native profiles switch runtime after the production onboarding wizard
because it does not yet expose a native option.
- Quality scores are informational and cannot override behavioral
failures.

## Model Used

OpenAI Codex, GPT-6, with reasoning, repository tools, and code
execution. The exact deployed model identifier and context-window size
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>

2026-09-16 14:24:32 -05:00

Dotta

5716fe907e

test(runner): add full-stack acceptance and eval gates (#12700 )

## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work.
> - The runner subsystem executes agent work across local and managed
provider backends.
> - The lower pull requests restore the task runtime, provider backends,
and managed-provider control plane.
> - The restored system needs repeatable full-stack checks before it can
ship safely.
> - Paid live checks also need clear access, cost, and secret controls.
> - This pull request adds acceptance, live evaluation, chaos, and
release gates for the restored runner stack.
> - The benefit is measurable runner parity with safer release
decisions.

## Linked Issues or Issue Description

**Subsystem affected**

Cross-cutting. This change covers runner tests, release workflows,
server contracts, and evaluation tools.

**Problem or motivation**

The runner stack did not have one complete acceptance surface for native
Codex, ACPX, Claude Managed, and AWS AgentCore. Release checks could
miss provider drift, task-view regressions, cost-policy errors, and
destructive cleanup errors.

**Proposed solution**

Add a 57-cell full-stack catalog, a Daytona image, and opt-in paid
workflows. Add live evaluation, chaos, cost-limit, redaction, and
release contract checks. Add AWS AgentCore infrastructure and guarded
provisioning tools. Keep the native runner experimental flag off by
default.

**Alternatives considered**

We considered manual smoke tests only. They do not give repeatable
evidence and they do not protect release branches. We also considered
one large pull request. The stacked pull requests keep each review below
the Greptile file limit.

**Roadmap alignment**

This work supports the shipped Cloud / Sandbox agents milestone and the
shipped Agent evals & feedback milestone in `ROADMAP.md`.

Related stack:

- #12699 adds managed provider backends and lifecycle support.
- #12691 adds qualified OpenCode and ACPX provider backends.
- #12685 restores task runtime rendering and steering.

## What Changed

- Add the runner full-stack harness with 57 catalog cells and 60 unit
tests.
- Add a Daytona runner image with digest-pinned base images and
base-aware image-content checks.
- Add guarded live evaluation and chaos workflows with a fixed
40-execution matrix; live and full-stack paid schedules now run only on
Sundays or by manual dispatch.
- Add in-flight reported-usage cost stops, post-turn cost caps,
exact-threshold failure classification, secret redaction, retry
classification, and actor authorization.
- Reattach stream and hard-budget listeners before restart-recovery
continuations so restored paid sessions cannot bypass in-flight
interruption.
- Preserve OpenCode usage and cost across tool-loop messages and turns
while exposing an explicit current-run delta to durable accounting.
- Keep PNG/WebM evidence in access-controlled artifacts only, reject
SVG, and publish only pruned inert structured per-attempt evidence.
- Add AWS AgentCore infrastructure, provisioning checks, and smoke
tools; reject unsafe model identifiers, require exact stack ownership
markers, and make failed-stack replacement explicit.
- Add evaluation-session contracts and capability reports.
- Add release workflow checks for immutable action pins, frozen
dependency installs, exact weekly cron shape, paid-run guards,
provider-secret isolation, and chaos test paths.
- Reauthorize the original and triggering numeric actor IDs as the first
step of every provider-secret job, including partial reruns, before
checkout or provider access.
- Give each full-stack matrix cell only its matching provider
credential, expose Daytona only to Daytona cells, and disable shared
dependency caches anywhere paid credentials or OIDC write access are
present.
- Protect the legacy manual E2E workflow with the same default-branch,
allowlist, environment, and per-job authorization boundary.
- Rotate live-eval candidates by week and retain 120 days of compatible
history so the seven-week trend window remains viable.
- Restore the root runner-acceptance commands and reconcile reported
snapshots,
raw receipts, and terminal usage without double counting or losing late
usage.
- Mark ACPX token deltas exact only when every budget field is present,
keep
cumulative cost/request authority separate, reject non-USD cost
labeling,
  and include thought tokens in output-token budgets.
- Keep `enableNativeRunner` off by default. The acceptance harness
enables it only in its isolated test instance.

## Verification

Passed locally:

- `pnpm --filter @paperclipai/paperclip-runner typecheck`
- `pnpm test:runner-acceptance:typecheck`
- `pnpm test:runner-acceptance` (19 tests)
- focused OpenCode proxy, driver, runnerd transport, live-session, and
turn-stream tests (106 tests)
- `pnpm --filter @paperclipai/paperclip-runner exec vitest run
src/live/clean-room-server.test.ts` (22 tests)
- `pnpm test:e2e:runner:typecheck`
- `pnpm test:e2e:runner:unit` (62 tests)
- `node --test scripts/__tests__/release-verify-workflow.test.mjs`
- `pnpm --filter @paperclipai/paperclip-runner
test:runner-workflow-evals` (22 tests)
- `pnpm -r typecheck`
- `pnpm build`
- `node --test
packages/paperclip-runner/scripts/aws-agentcore-provisioning.test.mjs`
(6 tests)
- `git diff --check`
- `cargo test --manifest-path
packages/paperclip-runner/runner/Cargo.toml -p paperclip-runner-core
--lib --locked` (161 tests)
- focused ACPX provider-event tests (10 tests)
- The rebased PR changes 92 files. `pnpm-lock.yaml` is unchanged.

I did not run paid live provider jobs or provision AWS resources. Those
checks need credentials and can create cost.

## Risks

The paid workflows can create provider cost. They require an allowlisted
original and triggering actor, the protected `runner-e2e-paid`
environment, explicit opt-in variables, and cost limits. The four
provider credentials exist only in that master-only environment, which
requires allowlisted reviewer approval and disables administrator
bypass; repository and organization Actions scopes contain no copies.

Provider usage arrives after a billable request, so the live guard
cannot prevent one request from crossing a threshold. It interrupts
immediately on the first reported threshold hit and permits no
continuation.

Visual evidence can contain secrets rendered as pixels. PNG/WebM remain
only in access-controlled workflow artifacts; SVG and per-attempt XML
are excluded, and S3/Pages receive a pruned structured dashboard.

The AWS scripts can create cloud resources. They use explicit commands,
least-privilege roles, KMS encryption, saved nonsecret metadata, and
explicit teardown.

This pull request does not enable the experimental native runner for
existing instances.

> For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and
discuss it in `#dev` before opening the PR. Feature PRs that overlap
with planned core work may need to be redirected — check the roadmap
first. See `CONTRIBUTING.md`.

## Model Used

OpenAI Codex with GPT-5. The model used extended reasoning, tool use,
code execution, and parallel subagents.

## 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

2026-09-02 08:55:08 -05:00