PaperClipAI

Jannik/PaperClipAI

0 Fork 0

mirror of https://github.com/paperclipai/paperclip.git synced 2026-10-23 09:07:46 +02:00

Commit Graph

Author	SHA1	Message	Date
DottaandPaperclip	2b16262280	Improve runner E2E report navigation and local previews (#16996 ) ## Thinking Path > - Paperclip is the open source app that people use to manage AI agents for work. > - Product E2E campaigns check user journeys across agent profiles and environments. > - Readers use the campaign history and reports to inspect results and retained evidence. > - The reports showed image summaries, many unselected suites, and a long sticky index. > - Individual case cards also showed routine diagnostics before the visual evidence. > - This pull request adds text summaries, feature filters, folding case indexes, and simpler cards. > - A local preview uses retained public data so designers can change reports without another paid campaign. ## Linked Issues or Issue Description Current behavior The report is hard to scan as the journey catalog grows. Suite links can point into hidden results. Case indexes do not show whether a case passed across its configurations. Design changes also need a realistic local preview. Proposed behavior Show the selected campaign as text. Link journeys to current feature-map capabilities. Add folding case indexes with status indicators, reliable section links, and a back-to-top control. Keep failed outcomes visible and put routine diagnostics under Test details. Render retained public campaign data with local templates. Reason and benefit Readers can find a feature or failed case faster. Designers can iterate against real retained data without starting an application instance or using provider credentials. Breaking changes No result schema or grading change. The report stops embedding the generated summary PNG. The publisher still produces that artifact for existing consumers. Related work: #12889 added the existing matrix browser. #12846 concerns the public image publication boundary. This PR changes report presentation and local preview behavior. ## What Changed - Replace image summaries with shared HTML suite summaries on the history and campaign pages. - Show selected executions and preserve missing results for selected cells. - Add explicit journey-to-capability associations, feature filters, and a coverage view with unmapped journeys. - Add folding case indexes, section case lists, and red, green, or amber status indicators across matching configurations. - Fix anchor navigation through filters and add a floating back-to-top control. - Simplify case cards. Keep failure reasons visible. Fold routine checks, billing, and context into Test details. - Add an original-image link to the gallery. - Add a local preview utility with public data caching and offline mode. Document the direct Node command. - Test manifest-listed evidence, rejection of unlisted files and encoded traversal, cache reuse, and offline misses with a real loopback server and a stub downloader. ## Verification - Focused report, history, and preview tests: 75 passed in 6 files. - Report Playwright spec: 4 passed in Chrome with a standalone config that does not start the application server. - `node scripts/check-maps.mjs`: passed. - `git diff --check`: passed. - Manually checked retained campaign reports, feature filters, folding indexes, failure links, card details, gallery links, mobile layout, and keyboard navigation. - `pnpm build`: passed. - `pnpm -r typecheck`: passed. - `pnpm test:e2e:runner:typecheck`: passed. - `pnpm test:run`: stopped after 15 native session database cases failed. The local Postgres package first lacked dynamic-library links. After link hydration, the same cases still failed. A direct `initdb` check then reported `could not create semaphores: No space left on device` and identified the macOS semaphore limit. The complete local suite has not passed. - `pnpm test:e2e:runner:unit`: 3,250 passed, 6 failed, 2 skipped. All six failures reproduced against unchanged `origin/master` report sources with the same installed dependencies. They concern Copilot admission and its Daytona image input, plus the launcher test that runs those assertions. No report or history test failed. - No live provider evaluation was run for this presentation change. - CI on `b1a9c06823` first failed browser shard 3/8. The agent-chat split-handoff test reached cleanup, where cancelling a run returned HTTP 500 from a Postgres deadlock. Cleanup did not restore the experiment setting, and a later test failed its initial setting check. This shard does not contain the report spec. One targeted rerun passed, and that full workflow then passed. This shows recovery; no production fix was made for the deadlock. The later preview-test commit requires its own fresh checks. To review the design, run `node --watch --import ./cli/node_modules/tsx/dist/loader.mjs tests/runner-e2e/preview.ts`. Open the history address printed by the command, then open a campaign. The README covers offline mode and cache refresh. ## Risks - Feature associations use the current map. They describe linked scenarios, not proof that a whole capability is covered. Historical grades remain unchanged. - New or unfamiliar cases remain unmapped until their assertions are inspected. - The preview needs the public history host on first access. Offline mode requires cached files. It binds to the loopback interface and serves manifest-listed public evidence. - Hiding routine diagnostics adds one disclosure step. Failed or incomplete outcomes remain visible. This is report polish. It does not duplicate planned core work in `ROADMAP.md`. ## Model Used OpenAI Codex, GPT-6 family, with reasoning, tool use, code execution, and browser automation. The exact serving model ID and context window are not exposed in this session. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [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 - [ ] 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>	2026-10-20 14:02:19 -05:00
DottaandPaperclip	83076d7e7c	feat: return completed handoffs to Agent Chat (#14408 ) Return completed Agent Chat handoffs through a durable outbox and scope each generated update to its supplied tasks. Add recovery, browser delivery, result access, and calibrated quality coverage. Validated with two consecutive ten-case Claude/Codex campaigns, all CI checks, and a 5/5 review. Co-Authored-By: Paperclip <noreply@paperclip.ing>	2026-09-29 10:25:52 -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

Author

SHA1

Message

Date

DottaandPaperclip

2b16262280

Improve runner E2E report navigation and local previews (#16996 )

## Thinking Path

> - Paperclip is the open source app that people use to manage AI agents
for work.
> - Product E2E campaigns check user journeys across agent profiles and
environments.
> - Readers use the campaign history and reports to inspect results and
retained evidence.
> - The reports showed image summaries, many unselected suites, and a
long sticky index.
> - Individual case cards also showed routine diagnostics before the
visual evidence.
> - This pull request adds text summaries, feature filters, folding case
indexes, and simpler cards.
> - A local preview uses retained public data so designers can change
reports without another paid campaign.

## Linked Issues or Issue Description

**Current behavior**

The report is hard to scan as the journey catalog grows. Suite links can
point into hidden results. Case indexes do not show whether a case
passed across its configurations. Design changes also need a realistic
local preview.

**Proposed behavior**

Show the selected campaign as text. Link journeys to current feature-map
capabilities. Add folding case indexes with status indicators, reliable
section links, and a back-to-top control. Keep failed outcomes visible
and put routine diagnostics under Test details. Render retained public
campaign data with local templates.

**Reason and benefit**

Readers can find a feature or failed case faster. Designers can iterate
against real retained data without starting an application instance or
using provider credentials.

**Breaking changes**

No result schema or grading change. The report stops embedding the
generated summary PNG. The publisher still produces that artifact for
existing consumers.

Related work: #12889 added the existing matrix browser. #12846 concerns
the public image publication boundary. This PR changes report
presentation and local preview behavior.

## What Changed

- Replace image summaries with shared HTML suite summaries on the
history and campaign pages.
- Show selected executions and preserve missing results for selected
cells.
- Add explicit journey-to-capability associations, feature filters, and
a coverage view with unmapped journeys.
- Add folding case indexes, section case lists, and red, green, or amber
status indicators across matching configurations.
- Fix anchor navigation through filters and add a floating back-to-top
control.
- Simplify case cards. Keep failure reasons visible. Fold routine
checks, billing, and context into Test details.
- Add an original-image link to the gallery.
- Add a local preview utility with public data caching and offline mode.
Document the direct Node command.
- Test manifest-listed evidence, rejection of unlisted files and encoded
traversal, cache reuse, and offline misses with a real loopback server
and a stub downloader.

## Verification

- Focused report, history, and preview tests: 75 passed in 6 files.
- Report Playwright spec: 4 passed in Chrome with a standalone config
that does not start the application server.
- `node scripts/check-maps.mjs`: passed.
- `git diff --check`: passed.
- Manually checked retained campaign reports, feature filters, folding
indexes, failure links, card details, gallery links, mobile layout, and
keyboard navigation.
- `pnpm build`: passed.
- `pnpm -r typecheck`: passed.
- `pnpm test:e2e:runner:typecheck`: passed.
- `pnpm test:run`: stopped after 15 native session database cases
failed. The local Postgres package first lacked dynamic-library links.
After link hydration, the same cases still failed. A direct `initdb`
check then reported `could not create semaphores: No space left on
device` and identified the macOS semaphore limit. The complete local
suite has not passed.
- `pnpm test:e2e:runner:unit`: 3,250 passed, 6 failed, 2 skipped. All
six failures reproduced against unchanged `origin/master` report sources
with the same installed dependencies. They concern Copilot admission and
its Daytona image input, plus the launcher test that runs those
assertions. No report or history test failed.
- No live provider evaluation was run for this presentation change.
- CI on `b1a9c06823` first failed browser shard 3/8. The agent-chat
split-handoff test reached cleanup, where cancelling a run returned HTTP
500 from a Postgres deadlock. Cleanup did not restore the experiment
setting, and a later test failed its initial setting check. This shard
does not contain the report spec. One targeted rerun passed, and that
full workflow then passed. This shows recovery; no production fix was
made for the deadlock. The later preview-test commit requires its own
fresh checks.

To review the design, run `node --watch --import
./cli/node_modules/tsx/dist/loader.mjs tests/runner-e2e/preview.ts`.
Open the history address printed by the command, then open a campaign.
The README covers offline mode and cache refresh.

## Risks

- Feature associations use the current map. They describe linked
scenarios, not proof that a whole capability is covered. Historical
grades remain unchanged.
- New or unfamiliar cases remain unmapped until their assertions are
inspected.
- The preview needs the public history host on first access. Offline
mode requires cached files. It binds to the loopback interface and
serves manifest-listed public evidence.
- Hiding routine diagnostics adds one disclosure step. Failed or
incomplete outcomes remain visible.

This is report polish. It does not duplicate planned core work in
`ROADMAP.md`.

## Model Used

OpenAI Codex, GPT-6 family, with reasoning, tool use, code execution,
and browser automation. The exact serving model ID and context window
are not exposed in this session.

## Checklist

- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [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
- [ ] 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>

2026-10-20 14:02:19 -05:00

DottaandPaperclip

83076d7e7c

feat: return completed handoffs to Agent Chat (#14408 )

Return completed Agent Chat handoffs through a durable outbox and scope each generated update to its supplied tasks. Add recovery, browser delivery, result access, and calibrated quality coverage.

Validated with two consecutive ten-case Claude/Codex campaigns, all CI checks, and a 5/5 review.

Co-Authored-By: Paperclip <noreply@paperclip.ing>

2026-09-29 10:25:52 -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