mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-08 22:13:59 +01:00
5d9f6c56c2b325297c467005bf619da16dfd7a75
6
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 DottaandPaperclip
|
7c66b6b1f6 |
test(onboarding): cover plan, hiring, and execution approval history (#19069)
## Thinking Path > - Paperclip manages agent work and human decisions. > - Onboarding can approve a plan, a hire, and an execution step in separate turns. > - Tests covered single approvals more closely than that full history. > - The repaired gate must retain valid plan approval through later decisions. > - Every consumer must recognize the saved confirmation kind and selected scope. > - This change tests that contract and registers a complete interview-to-execution journey. ## Linked Issues or Issue Description Refs #19043, #17914, #18283. The earlier tests admitted one accepted proposal at a time. Decomposition fixtures used standard confirmations. The direct-task E2E path forbids hiring. Those cases did not cover an accepted checkbox plan followed by hiring and a separate untargeted execution approval. ## What Changed - Add eight PostgreSQL contract cases for standard and checkbox plan approvals. Native tools create the cards. An authenticated human accepts them through HTTP. A later native run reads the approved revision and actual selected scope. - Exercise native task creation, generic REST creation, child REST creation, and accepted-plan decomposition. Check the assigned child and one creation audit event. Check durable replay on the three entry points that support it. A pending execution confirmation still prevents creation. - Register the explicit-only `onboarding-approval-history` suite for local native Codex and ACPX Claude. The browser chooses the interview, selects only drafting in the saved plan, approves one writer hire, and approves a separate Start drafting confirmation. The model must hire the writer and use that writer's own child execution to save the welcome document. - Grade each human decision, the unchanged plan revision and selection, approval timing, one assigned child and worker execution, the exact writer-authored saved revision, no pending requests, and persistence after reload. Calibrate the oracle against missing, forged, premature, duplicate, and changed outcomes. - Preserve synthetic option choices, document/run bindings, and saved revision authorship in the existing public first-task evidence projection. Keep private provider/account data excluded. Document the workflow, evidence, billing, and cleanup bounds. - Align the approval-history fixture with its completion oracle: the onboarding parent must be Done. Test both native profiles against graded completion evidence and reject a completed child whose parent remains In review. Count parent heartbeats separately from the writer: accept one to seven parent records while retaining the twelve-company-run cap and the independent three-approval/one-writer oracle. - Retain the existing 52-cell first-task suite. The new suite has one attempt, seven expected work turns, a twelve-run maximum, a fifteen-minute deadline, and the existing $5 company task budget. It is excluded from `--all`. - Update two stale cleanup assertions to include the existing thirty-second deletion timeout. ## Verification - Red control: temporarily restore the pre-fix admission module and run the new checkbox/native history case. It fails with the expected `First-task proposal requires human acceptance` error after plan, hiring, and execution acceptance. Restore the repaired module after the probe. - The final post-rebase history matrix and existing onboarding safety suite passed together: 74 tests, no skips. - Final focused Runner E2E support passed: 413 Vitest tests and all 370 Node support checks. This covers catalog discovery, journey controls, wrong-outcome calibration, public evidence, and existing first-task behavior. - Review controls: four authorship cases fail before the revision check. A delayed browser-response control fails before the approval-time fix. Both pass after repair. The final oracle requires the exact current document revision, writer ID, native child run ID, matching body, and readback after reload. - Credential-free discovery lists both new native cells. No provider call was made. `OPENAI_API_KEY` and `ANTHROPIC_API_KEY` are absent, so the real provider journey remains unqualified. - The earlier broad credential-free E2E support run reported 6,728 passing cases, three skipped cases, and nine failures in three unrelated files. All nine reproduce with the changed E2E source restored to the unchanged baseline: three expired overhead-fixture cases, one stale Pi profile-version assertion, and five workflow security assertions. This change does not alter those files, paid workflow policy, or provider pins. - Previous full workspace typecheck/build and [Linux CI](https://github.com/paperclipai/paperclip/actions/runs/41921754638) passed on `4f431f5aae99d072cc75027e90d7b847b4c342ca`, including the new eight-case PostgreSQL file. Ponytail subsequently found a fixture/oracle terminal-status mismatch. Both native-cell controls fail on that fixture (`done` observed versus `in_review` expected), while the parent-in-review negative control passes. A second comparison uses the actual `matchesRunCount` predicate: graded evidence with six parent runs and one writer run fails the old exact-seven-parent requirement. Both fixes pass these controls, all 413 focused support tests, all 370 Node checks, and the owning E2E project typecheck. [Fresh CI](https://github.com/paperclipai/paperclip/actions/runs/41936699686) passed on `91c980b110252da451b92eda597c168517de1276`: 48 successful jobs and one expected skip. Greptile reviewed this head at 5/5 with no unresolved findings. Ponytail's terminal-status finding is fixed and its thread is resolved; its current-head re-review remains queued. Live provider cells remain unqualified. ## Risks The production API and approval gate are unchanged. The new paid journey can expose model or product failures at an intermediate approval boundary. It retains those failures and uses the existing diagnostics and cleanup. Registration and deterministic tests do not establish a live provider pass. The unrelated baseline support failures remain explicit. ## Model Used OpenAI GPT-6 through Codex, with reasoning, repository tools, and code execution. The exact serving model ID 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 (focused tests; unrelated baseline failures are recorded 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> |
||
|
DottaandPaperclip
|
3f4f8b37ba |
fix: grade Codex clarification and refusal outcomes from evidence (#14570)
Grade clarification lists, obsolete unstarted wakes, and refusal cancellation from persisted evidence. Preserve execution and ownership assertions, add boundary regressions, and version the affected eval definitions. Co-Authored-By: Paperclip <noreply@paperclip.ing> |
||
|
DottaandPaperclip
|
cea8dda472 |
test: evaluate completion updates after native task handoffs (#13969)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Users can delegate work through onboarding and Agent Chat. > - A completed task does not prove that its result reached the original conversation. > - Existing tests do not isolate completion after the source chat becomes idle. > - This pull request adds four explicit native-runner probes across Claude and Codex. > - The probes preserve the result and reply so we can separate delivery failures from inaccurate answers. ## Linked Issues or Issue Description Refs #13775. Refs #13813. These evals extend native-runner qualification. They measure completion updates before we choose a product change. ## What Changed - Add the opt-in `completion-updates` suite with two stories for each native provider. - Test completion in the existing onboarding task flow and after an Agent Chat handoff becomes idle. - Gate the chat worker on a brief inside its managed project workspace. Prove the source is idle before releasing the worker. - Check durable task completion, saved output, a subsequent source reply, and rendered access to the result. - Preserve replies, task state, screenshots, run events, and a separate semantic review rubric. - Add grader regression tests and update the documented eval contract. - Preserve the suites added on master and include four completion cases in the 306-cell catalog. Production behavior and prompts are unchanged. ## Verification - Passed all 565 eval support tests across 45 files after merging current master: `node node_modules/vitest/vitest.mjs run --config tests/runner-e2e/vitest.config.ts`. - Passed eval TypeScript: `node node_modules/typescript/bin/tsc -p tests/runner-e2e/tsconfig.json`. - Confirmed four selected cells: `node cli/node_modules/tsx/dist/cli.mjs tests/runner-e2e/launch.ts --list --suite completion-updates`. - Four-cell behavior campaign on source `ad47cf1da2b1e36f19f4227cfeb53998720b0b5b`: https://github.com/paperclipai/paperclip/actions/runs/36072337485. - A screenshot-only follow-up waits for the restored source reply to render after result-link navigation. Its one-cell Claude onboarding verification passed on final head: https://github.com/paperclipai/paperclip/actions/runs/36075716141. Corrected report: https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-36075716141-1/. The original four-cell onboarding screenshots caught navigation loading; its saved reply evidence remains valid. The follow-up again found stale wording: "That work will run next" was posted 38 seconds after the child was Done. The four-cell campaign keeps its original source and measurements. - Published evidence: https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-36072337485-1/. - Suite definition: `afba4d85d6c53d9f64c08b37a2e9cc20481b78f5bd7e2fa012045e2c69444d9d`, version 6. Models: native `gpt-5.6-sol` and `claude-sonnet-5`, local execution, one attempt per cell. All four cleanup checks passed. Onboarding billing coverage is partial; reported zero cost must not be read as a free run. | Story | Automated delivery/access | Separate semantic review | | --- | --- | --- | | Codex onboarding | Pass | Pass: accurate completion reply with an accessible result | | Claude onboarding | Pass | Fail: reply says it will save the note once the task runs, after the note is already saved and the task is Done | | Codex idle chat handoff | Fail | Worker completed and saved the note; no completion reply during the full observation window | | Claude idle chat handoff | Fail | Worker completed and saved the note; no completion reply during the full observation window | Both chat cases positively recorded the source waiting and the worker at the brief gate before release. Both saved outputs include the brief-only start time. The opt-in campaign is red because it exposes current behavior. It is not a required merge gate. The PR does not fix that product behavior. Semantic review is a recorded human/agent assessment of retained evidence; it is not an automated prose-quality judge. - Second campaign: https://github.com/paperclipai/paperclip/actions/runs/36071065098. Codex chat reached the idle boundary and completed its task, then received no completion reply during the full window. Claude onboarding again returned a stale handoff answer. Claude chat exceeded the prior 110-second handoff setup budget; this revision raises that bounded setup window to 180 seconds. - Retained baseline: https://github.com/paperclipai/paperclip/actions/runs/36069427676. Onboarding passed delivery/access for both providers, but Claude gave a stale handoff answer. Chat cases stopped at fixture problems; they do not establish a completion-delivery failure. This revision fixes the workspace path and competing reference requirements. - On the previous head `4023a2a3c28d45c9eb2c42d452ce99ffba5c7b73`, 54 PR checks passed and two were skipped, including typecheck, tests, and build. Broad checks ran in CI, not locally. That head received Greptile 5/5 with no unresolved findings. The unchanged mobile repository-settings browser test passed on one targeted retry after a detached/disabled Save-button timeout. - Merged current master in `9b4491e1f` and resolved the catalog-count conflict. Eval support tests and eval TypeScript pass locally. All individual CI jobs passed on this merge commit, including build, typecheck, server tests, runner checks, and browser shards. The final aggregate check also passed: 54 checks passed and two were skipped. Greptile reviewed this exact commit at 5/5 with no unresolved findings. ## Risks - These explicit probes can expose current product failures. They do not change the default paid test selection. - Mechanical delivery and result access do not establish answer accuracy. The preserved reply still requires semantic review. - A fixture failure before the idle boundary or worker completion cannot establish a completion-update failure. - The handoff setup window lasts three minutes. The worker brief wait is bounded at four minutes. The observation window lasts two minutes after worker completion. It retains later replies without erasing earlier accessible delivery. ## Model Used OpenAI Codex, GPT-6 (`gpt-6-astra`), with reasoning, repository inspection, code execution, and GitHub tool use. The runtime does not expose the 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> |
||
|
DottaandPaperclip
|
43acbcc398 |
fix(runner): preserve sessions and complete question and approval continuations (#13655)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - The native runner connects task state to provider sessions. > - Follow-up turns must retain provider memory and carry new user direction. > - Lost session IDs caused repeated context and extra input tokens. > - Native question answers and approval races could leave valid work blocked. > - This pull request repairs those paths and adds regression coverage. > - Agents can continue accepted work without repeating the conversation or losing the user's answer. ## Linked Issues or Issue Description Refs #13574. That merged PR shortened continuation prompts and moved question instructions into tool documentation. This change preserves sessions and fixes failures exposed by broader testing. Related runtime work: #13408 and #13410. **What happened?** Native follow-up turns could lose the provider session ID. Completion guidance could replace the original task with its latest comment. Claude native questions could remain pending after the user answered. Approval during a running tool call could suspend the run before the tool response arrived. Onboarding and chat handoff instructions also caused repeated planning or missing plan documents. **Expected behavior** Reuse a valid provider session. Send only new events when that session already has the history. Preserve the task requirements and apply later user direction. Store the question answer and deliver it to the waiting run. Finish governed tool responses before suspending. Execute the accepted plan without asking for the same approval again. **Steps to reproduce** Run the continuation, local-session-integrity, first-task, and agent-chat suites with native Codex and Claude. Include provider-question-bridge, accept-while-running, and plan-handoff. **Paperclip version or commit** This branch is based on master |
||
|
DottaandPaperclip
|
d0b67bfe71 |
feat: queue approvals and answers during active runs (#13539)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Users guide running agents through messages, questions, and approval cards. > - Messages already wait in a queue when an agent is running. > - Card responses did not appear in that queue. Some question answers also steered a later run without a user click. > - A fast approval could invalidate the agent's review handoff and cause it to stop its own run. > - This pull request gives card responses the same queue controls and preserves the exact response during delivery. > - Users can wait for completion or explicitly send the response with Interrupt or Steer. ## Linked Issues or Issue Description Refs #13517, which is merged. This PR targets master and adds queued interaction responses on top of the onboarding changes. Related continuation work: #10519 and #12866. **What happened?** Accepting a proposal while its source run was active left a saved response outside the message queue. The agent could then lose its review path, reassign the task, and cancel itself. Answers to older questions could also steer another active turn without a click. **Expected behavior** Save the response immediately. Queue its continuation behind the active run. Deliver it after completion, or when the user explicitly chooses Interrupt or Steer. Preserve approval revisions and answer choices. **Steps to reproduce** 1. Let an agent publish a confirmation card while its run is still active. 2. Accept the card before the agent finishes its review handoff. 3. Inspect the message queue and the task's next run. **Paperclip version or commit** Reproduced on da8a3876c with the onboarding changes from #13517. **Deployment mode** Local development from source. The fix covers legacy adapters and native Runner turns. ## What Changed - Project resolved cards into the existing queue as immutable responses. Keep answers and exact approval revisions. - Require an explicit click to steer a response into a compatible native turn. Use Interrupt when a fresh session is required. - Preserve typed response context through interruption, cleanup waits, and normal queue promotion. Keep the direct answer channel for a provider blocked on its original question request. - Accept the source run's review handoff after its card resolves. Reject stale agent reassignment that would orphan a queued response. - Add deterministic regression tests and an `accept-while-running` case to the first-task suite. Require recorded timestamp overlap before that case can pass. - Keep the first-task skill name out of user-facing messages. ## Verification - Red-green: the original route failed the queue regression; the changed route passes it. - Focused server/UI tests: 139 passed, including 64 queue-route tests. - Runner harness unit tests: 314 passed. - Server, UI, and Runner E2E typechecks passed. UI token gates passed. - Full repository typecheck and build passed. Server typecheck passed again after review fixes. - Review regressions: 165 queue/reopen route tests, 53 wake admission tests, and 18 run identity tests passed. Approval acknowledgement recovery and both message/approval arrival orders are covered. - Full local test run: 12,401 passed; three new admission regressions ran against a cached pre-fix module. A fresh run of that entire suite passed (53 tests). The complete CI suite passed on the final commit. - Previous-head CI at `c28e2ef12`: 32 checks passed and 2 optional Storybook checks skipped. Every server/workspace/browser shard, Runner verification, build, typecheck/release registry, canary, policy, and security check passed. Greptile: 5/5, no unresolved threads. Earlier interrupted CI workers were replaced by this fresh complete run. - After integrating the updated parent: 314 harness tests, 119 queue/admission tests, 44 onboarding/question-delivery tests, and 13 native recovery tests passed locally. Full repository typecheck and build passed. - Clarified the skill wording preference: routine replies describe the action without announcing the internal skill; direct questions and permission/security/execution disclosures remain truthful. - The paid `accept-while-running` scenario is registered for all four local first-task profiles. It has not been run against a model in this change. - Rebased onto the merged parent at `11921075a`; the resulting tree exactly matches the locally verified integration tree. Final-head CI on `b53054807` passed: 54 successful checks, 2 optional Storybook checks skipped, no failed checks. Every new server/browser shard, aggregate verify/e2e gate, Runner, typecheck, build, canary, and security check passed on the first attempt. Greptile reviewed this exact head at 5/5 with no unresolved threads. ## Risks - Responses now wait instead of implicitly steering another active turn. A provider blocked on the original question still receives its answer directly. - Approval receipts cannot be edited, discarded, or reordered as comments. This preserves the recorded decision. - Interruption must still prove that the prior execution stopped. The tests cover cleanup waits and duplicate delivery. - The new paid overlap case can be unexercised if the model finishes before the click lands. It cannot pass without evidence of overlap. - No database migration is required. This repairs the existing approvals and execution controls; it does not implement the roadmap's work-stream queues. ## Model Used OpenAI GPT-6 through Codex. The exact deployed model ID and context-window size were not exposed in this session. Capabilities used: agentic reasoning, repository inspection, code editing, terminal commands, and test 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 - [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> |
||
|
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> |