5 Commits

Include renames

Author	SHA1	Message	Date
DottaandPaperclip	9d19f98b50	fix: harden native chat recovery and add coordination evals (#13741) ... ## Thinking Path > - Paperclip helps people manage AI agents and their work. > - Agent chat uses native runner sessions to plan, delegate, and track that work. > - A user can press Stop while the native session is still starting. > - The server can acknowledge that Stop without dispatching it, then let the session submit a turn. > - This leaves chat recovery waiting for an execution that the user expected to stop. > - This PR waits for the startup handle, dispatches cancellation, and prevents a late startup from submitting a turn. > - New full-stack evals check the resulting records and outputs across Claude and Codex. > - Those evals also exposed missing ACPX readiness fields, unbounded polling, and an old-run identity check that rejected valid warm handoffs. ## Linked Issues or Issue Description **What happened?** Stop during native startup could record an acknowledged cancellation with `dispatched: false`. The provider could then begin work. A subsequent `/new` stayed queued. A remote Claude follow-up also exhausted the command journal while probing warm-session readiness: ACPX never returned the readiness fields required by the shared transport. Once readiness worked, attachment incorrectly compared the next run descriptor against the old run ID. The 25 ms polling loop could issue 4,800 commands during its two-minute wait, beyond the 500-command bound. The existing chat eval treated lifecycle logs as proof of an active provider turn, so it did not distinguish startup cancellation from active-turn cancellation. **Expected behavior** A Stop during startup must reach the pending session. A late session must not submit a prompt after Stop. Recovery must retain control when startup exceeds the bounded wait. Chat evals must check saved task state, document contents, worker identity, account binding, and duplicate effects. **Steps to reproduce** 1. Start a native Claude or Codex chat turn. 2. Press Stop after process startup is requested but before the provider turn starts. 3. Send `/new`, then send a fresh message. 4. On the affected base, cancellation can be acknowledged without dispatch and the reset stays queued. **Paperclip version or commit** The live Claude baseline reproduced this on `29d6b3509`. The branch also includes master commit `0f5fafe16`. Related work: #13678, #13686, #13693, #13291, #13738. A separate runner reliability branch also contains a startup-wait fix. Its overlap must be reconciled before merging; this branch additionally prevents prompt submission after a late startup. ## What Changed - Wait for a pending native startup before acknowledging a run-scoped Stop. Preserve the existing recovery error when that wait expires. - Keep a Stop guard on startup. Cancel a late handle before it can submit a provider turn. - Add regression tests for normal handle publication and publication after the Stop deadline. - Back off blocked warm-attachment probes. Keep the fast two-snapshot barrier, fail closed, and record changed blockers. - Add red/green tests for delayed readiness, persistent blockers, alternating readiness, and readiness near the deadline. - Publish ACPX readiness and blockers. Preserve the old authority’s event acknowledgement barrier; only settled sessions can proceed to attachment. - Bind warm ACPX descriptors to the validated next authority while retaining old-run event correlation until activation. Preserve session identity and provider profile checks. - Exercise two consecutive run rotations through a qualified fake sidecar, verifying checkpointing, provider identity, pre-activation rejection, and new-run work admission. - Separate startup and active-turn cancellation checkpoints in the browser eval. - Add 18 explicit native chat eval cells: 12 local and 6 Daytona cells across Claude and Codex. - Cover hiring and reuse through managed AI accounts, source-based review, current blocked-task status, request replay after a lost HTTP acknowledgement, server restart continuity, and Stop/reset continuity. - Use ordinary production agent instructions. Enable API tools only for the two coordination cases that need them. - Calibrate the matchers with invalid records and outputs. Require remembered context after restart and a structured status snapshot that distinguishes the current blocker from history and task status from active execution. Compare the public issue mutation contract and relationships during read-only reporting. Preserve before/after source records in failed eval evidence. - Fix the lost-ack browser harness and verify it against a real HTTP server. Check the chat composer after restart instead of waiting for an unrelated document lifecycle event. - Document the scope and limits of each case. ## Verification - The startup regression failed on the unfixed executor and passed after the fix. - `pnpm test:e2e:runner:typecheck` passed. - `pnpm test:e2e:runner:unit` passed: 424 tests in 37 files. - `pnpm exec vitest run server/src/services/native-runtime/native-session-executor.test.ts` passed: 385 tests. - [Baseline live campaign](https://github.com/paperclipai/paperclip/actions/runs/35608208868): Claude Stop reproduced the bug. Codex Stop and Claude hire/reuse passed. Codex delegation was blocked by provider capacity. - [Eval-only startup campaign](https://github.com/paperclipai/paperclip/actions/runs/35609479786): both providers failed as expected. Both persisted `dispatched: false` and left `/new` queued. - [First fixed campaign](https://github.com/paperclipai/paperclip/actions/runs/35610533706) on `c9e95797d`: 10/18 cells passed. Startup Stop passed for both providers. Failed cases exposed eval harness defects and remote continuity failures. All attempts remain available. - [Original workflows and stronger memory checks](https://github.com/paperclipai/paperclip/actions/runs/35611896649) on `c04324fab`: 9/12 passed. Reassignment, local restart memory, and startup Stop passed for both providers; Codex remote restart passed. Claude remote restart exposed the missing readiness contract. Two Codex planning cells hit provider capacity. - [Unchanged-model retry](https://github.com/paperclipai/paperclip/actions/runs/35613854548): Codex planning and backlog creation both passed. - [18-cell campaign with ACPX readiness](https://github.com/paperclipai/paperclip/actions/runs/35614586963) on `6a98ef743`: 16/18 passed, including all local/remote Stop and committed-send cases. Claude remote continuity exposed the next-authority check, now fixed. Codex hiring produced its checklist, but the runner redacted the requested marker after it appeared as “Tracking token: …”. That content-redaction policy is unchanged and remains an explicit limitation. - [Structured status grading](https://github.com/paperclipai/paperclip/actions/runs/35614954725) on `50448c228`: both providers passed on their first attempt, including cleanup. - [Complete read-only state grading](https://github.com/paperclipai/paperclip/actions/runs/35616089011) on `551e13892`: both providers passed. - [Final ACPX handoff and hiring retry](https://github.com/paperclipai/paperclip/actions/runs/35617045456) on `cbd637587`: all three Claude Daytona cases passed (restart continuity, active Stop/reset, and lost-ack replay). Codex hiring reproduced the content-redaction failure: the saved checklist contained `Tracking token: [REDACTED]` instead of the required business marker. All four cases completed cleanup successfully. [Published report](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-35617045456-1/). The only subsequent commit adds the qualified-sidecar integration test; production code is identical to this live proof. - `pnpm test:e2e:runner:browser-support` passed: 5 browser tests without paid models. - Runner TypeScript typecheck passed. All 5 warm-readiness tests pass; two failed with the prior fixed-rate loop, and the late-readiness test failed before the pacing correction. - ACPX readiness and warm-identity regressions each failed before their fixes. All 292 runner-core Rust library tests passed. The qualified-sidecar integration test passes. Rust formatting is checked. - Status-grader regressions for misleading historical mentions and previously unchecked mutations each failed before tightening the oracle and pass now. - [Latest-head CI](https://github.com/paperclipai/paperclip/actions/runs/35617522307) passed on `a4093c8f1`: full build, type checks, test partitions, browser E2E, and native runner checks. Two unrelated tests initially failed (Sentry fixture release attribution and local-service fixture readiness); both passed locally together (35 passed, 5 optional SDK tests skipped) and on the failed-job retry. No changes were made to those tests. - Greptile reviewed `a4093c8f1` at 5/5; both earlier findings are fixed and all review threads are resolved. - The paid live suite is not fully green: the reproducible content-redaction case remains red. This is separate from the passing PR merge checks. No production content-redaction, prompt, model, or completion-policy change is included. - Managed-account hiring and review cases explicitly enable API tools; these do not qualify default new-user onboarding. ## Risks - Stop can wait up to 30 seconds for startup, then use the existing pending-recovery path. This does not prove that remote cleanup has finished. - Blocked warm readiness adds up to 750 ms between later probes with the two-minute remote budget, or about 32 ms with the default five-second budget. Ready sessions retain the short second barrier. - Paid evals can fail because of provider capacity or agent decisions. Each failure needs evidence-based classification. - The HTTP request replay case checks comment idempotency and duplicate effects. It does not prove replay safety for an ambiguous provider tool call. - The new suite is opt-in. It does not increase the default paid campaign. - No production prompts or model selection change. Review-handoff behavior and content-redaction policy remain separate product decisions. The latter can remove harmless business content that looks like credential syntax; the failing attempt is retained. ## Model Used OpenAI Codex, GPT-6, with repository tools and code execution. The exact deployment model ID and context window are not exposed in this task. ## 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>	2026-09-21 10:35:38 -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
3 people	cceeb0aa66	test(runner): add everyday workflow evaluation harness (#13474) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - The native runner must support project work, delegation, hiring, and service access. > - Browser tests exposed lost connection access, rejected helper events, and stalled recovery. > - Some eval failures also came from incorrect fixtures and decision controls. > - This pull request fixes those paths and adds eight everyday workflow stories. > - The tests retain observed failures and verify delivered files independently. > - The benefit is repeatable evidence for common user tasks and their remaining gaps. ## Linked Issues or Issue Description Related work: #13404 contains earlier workflow fixes. #13300 and #13470 changed the CI contracts used by the harness security tests. Merged companion: [paperclip-evals#22](https://github.com/paperclipai/paperclip-evals/pull/22). **What happened?** Native ACPX sessions did not receive the assigned connection gateway. Codex helper events could arrive before their spawn receipt and fail thread validation. A parent continuation could take a shared workspace before its child retried. A failed native continuation could leave the task status without a clear recovery blocker. The eval harness also confused tool approvals with new connection requests and could reject a valid delegated download. **Expected behavior** Keep assigned gateway access and its approval checks. Verify helper lineage before accepting helper progress. Let a waiting child proceed before automatic parent recovery. Preserve a failed task's recovery ownership. Grade the actual requested workflow and its delivered files. **Steps to reproduce** Run the everyday workflow suite with the native Codex and Claude profiles. Exercise service approval, connection refusal, delegated project work, and teammate reuse. The commands and case requirements are in `tests/runner-e2e/EVERYDAY-WORKFLOWS.md`. Use `pnpm test:runner-recovery` for controlled crash and replacement cases. ## What Changed - Pass the scoped connection gateway binding through the native ACPX host and sidecar. - Recognize Codex helper lineage from parent metadata and spawn receipts. Verify early helper events with `thread/read`. Keep helper events separate from root completion authority. - Guide agents to use persistent hiring, child tasks, dependency records, and a blocked handoff while waiting for a child. - Defer automatic parent recovery while a child has an active execution path in the same shared workspace. Allow parent recovery when the child needs review. - Record Blocked status and recovery evidence when a failed native continuation needs reconciliation, including existing active or escalated incidents. Preserve their owner and retry budget. - Add eight browser-driven workflow cases. Use real decision controls, explicit child feedback delivery, managed hiring credentials, and independent ZIP checks inside a bounded Docker sandbox. Verify sandbox availability before task creation. Record screenshot SHA-256 at capture. - Keep runner crash probes in controlled recovery tests. Preserve the original failure when cleanup also fails. - Display missing accounting and replay revisions as unavailable. Align harness security assertions with the approved CI changes. - Make the channel-rejection browser fixture bind its file after the send captures its payload. This prevents live refresh from removing the file before the simulated race. ## Verification - Full workspace `pnpm -r typecheck` passed after merging current master. - Runner E2E typecheck passed. Harness unit tests passed: 216/216. - Wake-queue database tests passed: 55/55. The two added existing-incident tests failed before the fix and pass after it. - Docker artifact calibration passed: 12/12. Host-file and host-loopback isolation tests failed before the fix and pass after it. Read-only delivery and output limits are also verified. - Full `pnpm build` passed. Targeted recovery tests passed: 83/83. - The channel-rejection browser test passed five consecutive runs after fixing the fixture race found in CI. - Local general-server (12,351 tests), UI (6,250), CLI (485), and workspace package groups passed. The monolithic run stopped at an unchanged lock-heartbeat fixture race; the isolated workspace group passed on rerun (shared: 747/747). A separate local serialized run passed 97 files before two socket errors in the unchanged issue-list route suite; that suite passed 15/15 on isolated rerun. These local full commands did not finish uninterrupted; the complete CI matrix below covers the remaining suites. - Final head `0fb293733fe307be7e6667ae8f1364077d0c6455`: **34 successful checks, 2 expected skips**, including every server/workspace shard, browser shard, native runner verification, build, and typecheck. [Final CI run](https://github.com/paperclipai/paperclip/actions/runs/34989136700). - Greptile reviewed this exact head at **5/5**; all review threads are resolved. Both Superagent security checks are successful. - ACPX credential-boundary tests passed: 118/118. Superagent accepted the runner/sidecar versus provider-environment trace and cleared its finding. - The latest paid local campaign on source `f6a2fdf7ac2af859826a2ae627ff4125a5478529` passed 22/24 cases: Sol 8/8, Claude 7/8, Mini 7/8. These results predate the merge with current master. - The two remaining failures are in `hire-reuse`: Claude exceeded the attempt deadline during final review; Mini made invalid deliverable tool calls and remained Blocked. - Six Daytona cases were not run because the matching immutable runner image was unavailable. This PR does not claim new remote model results. ## Risks The changes affect connection admission, helper identity, and recovery scheduling. Assigned gateway grants and user approval still govern service calls. The workspace admission gate still exists; the broader folder-sync design is separate work. Provider behavior can still cause the two recorded hiring failures. No database migration is required. Paid cases are opt-in and have bounded attempt deadlines. Project stories now require Docker and the documented pinned Python image on the harness host. ## Model Used OpenAI `gpt-6-astra` performed implementation, diagnosis, and substantive review. OpenAI `gpt-5.6-luna` assisted with verification, PR preparation, and review tracking. Both used repository tools and code execution. Context-window sizes were not recorded. ## 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 checks and isolated reruns; full-run limitations are documented above) - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: OpenAI GPT-5.6 Luna <noreply@openai.com> Co-authored-by: Paperclip <noreply@paperclip.ing>	2026-09-15 11:04:16 -05:00
Dotta	1dceee9a4e	fix(runner): persist warm Daytona workspaces (#12901) ... ## Thinking Path > - Paperclip manages AI agent work and the execution state for each task. > - Remote agents run in sandbox environments such as Daytona. > - Daytona keeps files while a sandbox is stopped, but deletion removes those files. > - Runner Codex did not copy successful remote workspace changes back to the host workspace. > - A warm sandbox could therefore hide data loss until Daytona replaced or deleted the sandbox. > - This pull request makes the host workspace durable after every successful turn and keeps verified reusable sandboxes warm. > - The benefit is reliable multi-turn work across warm reuse, restart, stop, and sandbox replacement. ## Linked Issues or Issue Description **What happened?** A successful native Codex turn in Daytona could leave workspace changes only in the remote sandbox. A later warm turn appeared to work because it reused that filesystem. A replacement sandbox could start from stale host data and lose the successful changes. **Expected behavior** Paperclip must merge each successful remote turn into the authoritative host workspace before it completes the run. A verified warm lease may reuse its remote files. A replacement lease must reconstruct the exact durable workspace seed. **Steps to reproduce** 1. Run Codex in a reusable Daytona environment. 2. Write a file during one successful turn. 3. Replace the Daytona sandbox before the next turn. 4. Observe that the next turn can start without the prior file on the unpatched code. Related remote workspace foundation: #10070. ## What Changed - Added explicit `host_current`, `durable_seed`, and `adopt_remote` workspace preparation modes. - Added atomic, versioned native workspace descriptors and seed archives under `PAPERCLIP_HOME`. - Added real native sandbox export and three-way host merge before terminal result completion. - Added workspace-only recovery after a proposed result. Recovery does not submit another provider turn or consume the provider retry budget. - Added fail-closed handling when a sandbox with unexported changes is gone. - Kept healthy reusable Daytona sandboxes started for legacy Codex and Runner Codex. - Kept the Runner Codex process and provider session across verified warm turns. - Added the paid `daytona-warm-continuity` browser suite. It contains exactly the legacy Codex and Runner Codex cells. Each cell performs three measured turns. - Documented `pnpm test:e2e:runner -- --suite daytona-warm-continuity`. No package script was added. - Added no database migration. The metadata format is backward compatible and idempotent. ## Verification - `pnpm typecheck` - `pnpm test:e2e:runner:unit` — 114 passed - Native workspace, finalizer, session, and environment tests — 232 passed - Daytona provider tests — 150 passed - Workspace staging and merge tests — 98 passed - Runner transport tests — 63 passed - Legacy Codex restore tests — 5 passed - Rust format and compile checks pass through root typecheck - The paid Daytona suite was not run locally because the required Daytona, OpenAI, and immutable image credentials are not present. ## Risks - The main risk is an incorrect workspace identity or merge after a crash. Durable descriptors bind the run, workspace, lease, provider lease, local root, remote root, and baseline digest. Ambiguous evidence fails closed. - The host merge may conflict with concurrent host edits. The existing three-way merge and exclusion rules handle this case and surface failures. - A deleted sandbox cannot recover unexported bytes. Paperclip now blocks with `workspace_sync_out_unrecoverable` instead of reporting success or rerunning the provider. - There is no database migration. Descriptor writes and recovery are atomic and idempotent. ## Model Used OpenAI Codex with GPT-5. The run used agentic reasoning, repository inspection, code execution, test execution, Git, and GitHub CLI tools. ## 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	2026-09-05 13:00:57 -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