PaperClipAI

Jannik/PaperClipAI

0 Fork 0

mirror of https://github.com/paperclipai/paperclip.git synced 2026-10-08 11:13:44 +02:00

Commit Graph

Author	SHA1	Message	Date
DottaandPaperclip	d0db8820db	fix(connections): repair native baseline and approval continuations (#15420 ) ## Thinking Path > - Paperclip manages AI agents and the tools they may use. > - Connection setup separates provider preference from permission to use a tool. > - The first native connection baseline could not exercise its intended decisions. > - The browser used mutable task titles, and the provider fixture already granted access. > - Native provider-choice instructions also disagreed with the preferred question format. Schema rejection gave no field guidance. > - This pull request repairs those test preconditions and native guidance, then fixes restart/approval defects exposed by the corrected baseline. It also restores missing OpenCode tool-error evidence. > - The benefit is an inspectable baseline before any further instruction reduction. ## Linked Issues or Issue Description Refs #15407. The original 15-cell baseline remains 0 PASS / 15 FAIL. Ten cells stopped on stale titles, two Codex cells had schema denials, two OpenCode cells used already-granted tools, and one Claude cell returned no native result. No intended user decisions were submitted. The exact invalid Codex field and underlying Claude failure cause remain unknown. [Original campaign](https://github.com/paperclipai/paperclip/actions/runs/37562577199) · [Original report](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-37562577199-1/index.html) ## What Changed - Match the browser's task route and visible identifier instead of a title the agent can change. - Start native provider-choice fixtures with no agent tool access. Verify the public effective-access records. - In the positive case, select Arcade, then grant its exact HubSpot tool through the real access card. Require both saved decisions and exactly one observed call. - Return a canonical `providerQuestionSet` for native input and retain the equivalent legacy `providerQuestion`. - Keep invalid input rejected. Return bounded schema locations and required field names without submitted values. - Preserve Claude's exact session/content identity while allowing authenticated registered instruction-copy paths to rotate on a new run. - Reject duplicate approval reports for an existing exact tool-action card before they create another human review. - Wait for a recorded service-approval continuation within the existing deadline; retain missing or failed continuation grades. - Forward OpenCode tool activity through the runner facade, preserving bounded errors and execution-part identity without inventing host-call joins or exposing arguments. - Preserve original grades, costs, scope limits and diagnoses in the dated repair report. ## Verification - Eval typecheck passes. Support suite: 1,801 PASS, one intentional skip; Node checks: 128 PASS. - Connection/schema tests: 51 PASS. Real-server public fixture setup: one PASS with zero providers. - Browser support regression: five PASS, including renamed and wrong tasks. - Focused Rust safe-feedback test: one PASS. - Repository typecheck and build pass before the latest master replay. Post-replay connection/shared/real-server fixture checks: 52 PASS; eval typecheck passes. The browser review fix additionally passes all five browser checks and seven suite checks. - The full local repository run was interrupted incomplete after about 45 minutes, with five integration failures retained. All five pass in a separate targeted invocation (1,250 unrelated tests skipped). No full local-suite pass or root cause for the initial local failures is claimed. - Corrected frozen source `162cc90fdabe7f505b88ae095044531b82784c92`: 10 PASS / 5 FAIL across the [passing Codex canary](https://github.com/paperclipai/paperclip/actions/runs/37575158761) and [remaining 14 cells](https://github.com/paperclipai/paperclip/actions/runs/37576261807). The canary passes all 17 checks. Claude's two provider-choice continuations fail on restart, Claude service approval exposes an early evaluator rejection, Codex service approval creates a duplicate approval, and OpenCode provider-second times out after both decisions with no HubSpot call. No original result is regraded. - Final ledgers count 31 actual runs: 27 succeeded, two failed, two cancelled during cleanup. All 15 cleanup/budget checks pass. The late Claude continuation is absent from its earlier workflow snapshot; it remains in the result/API/final ledger. Original evidence retains 279 hashes. Recorded LLM subtotal $0.04553787 is incomplete billing, not actual total cost; local runtime is unmetered. - New repair regressions reproduce the Claude attach failure, duplicate approval acceptance and dropped OpenCode tool events before their respective fixes. Nine Rust attachment checks, 127 ACPX host/adapter tests, 33 completion/control-plane checks, nine eval deadline tests, 59 OpenCode proxy/driver tests, one Rust tool-error/redaction check, and TypeScript/Rust composer parity pass. Eval typecheck, repository typecheck and build pass. Existing support coverage is 1,802 PASS plus 128 Node PASS, one intentional support skip; two additional deadline tests also pass. - New-source full CI/review and live canaries are pending. The next bounded selection is Claude provider-decline, Codex service-approve and one OpenCode provider-second diagnostic with repaired event evidence. No broader campaign or instruction-reduction qualification is claimed. - Initial corrected campaign [37574251834](https://github.com/paperclipai/paperclip/actions/runs/37574251834) was cancelled during shared build after review found the breadcrumb whitespace assumption. Its matrix job has zero steps and no provider execution. The real adjacent-span browser regression now reproduces the old failure and passes after the fix. ## Risks - The corrected baseline remains 10/15. The new restart/approval fixes require live qualification; OpenCode evidence forwarding does not itself establish or fix its prior behavioral failure. - The positive provider case now expects three runs, including separate access approval. Its new results are distinct from the original invalid fixture. - The old Claude missing-result cause and rejected Codex field are unknown. These repairs do not retroactively explain or erase either failure. - Path rotation must preserve prompt, custom instruction, skill/content identity and protected provider settings; regression checks reject stale or changed content. No connection authorization, JSON schema, budget, cleanup, or final-result requirement is relaxed. Historical Everyday prompts and gateway setup remain unchanged. ## Model Used OpenAI Codex, GPT-6. The exact deployment variant and context window are not exposed in this session. Used repository inspection, code editing, test execution and retained-evidence analysis. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [ ] 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>	2026-10-07 06:18:51 -05:00
DottaandPaperclip	84fe89906d	fix: complete native agent review handoffs (#13581 ) ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work > - Native execution uses durable runs, issue locks, wake requests, and typed tool authority > - A child can finish with a native agent review request while its original assignee stays responsible for the work > - The reviewer then needs a bounded execution path that can inspect the child, record one decision, and finish safely > - Before this change, assignee-only gates rejected the reviewer or left the parent waiting after the child review ended > - This pull request adds typed reviewer admission, scoped reviewer tools, durable wake and recovery handling, and parent continuation evidence > - The benefit is that native review handoffs complete without changing child ownership or granting broad mutation access ## Linked Issues or Issue Description Refs: #13314 Refs: #13574 What happened? A native child run could report `needs_review` for an agent reviewer. The reviewer wake then failed assignee and execution-lock checks. The child remained in review and the parent remained waiting. Expected behavior The named reviewer should receive one durable wake. The reviewer should inspect the child and resolve the exact review card. The child assignee should stay unchanged. The parent should receive the recorded review outcome after the child reaches its terminal state. Steps to reproduce 1. Run a native task with a different named agent reviewer. 2. Keep the child assigned to its original worker. 3. Let the worker finish with a native completion review request. 4. Start the durable reviewer wake. 5. Resolve the review and finish the reviewer run. 6. Observe the child and parent state. Paperclip version or commit Base: `e926b1301`. PR head: `b31ad9ab8`. Live reviewer verification source: `eea171aae`. Deployment mode Built from source. Installation method Built from source (pnpm build). Agent adapter(s) involved Not adapter-specific (core bug). Access context Both. Database mode Embedded PostgreSQL in the isolated live test fixtures. ## What Changed - Add server-validated native review assignment facts. - Admit only the exact company, issue, source run, decision, revision, addressee, and resolver policy. - Give reviewer runs a narrow set of Paperclip read and resolve tools. File and shell access follow the configured agent and environment policy, so reviewers can run tests. - Separate server-owned reviewer instructions from untrusted persisted review data. Escape the data boundary; retain server-enforced authorization. - Keep the child assignee unchanged. Atomically claim the reviewer run, wake request, and issue execution lock. A competing lock prevents provider startup. - Require the exact running reviewer session and current issue lock to resolve its assigned card. Reject missing, unrelated, or terminal reviewer runs. - Add durable reviewer wake, lock, stale-card, and abandoned-run recovery handling. - Prevent duplicate native wake dispatches during deferred admission and recovery. - Carry accepted or rejected child review outcomes into parent task context and continuation evidence. - Add focused server, runner, and native protocol coverage. - Preserve upstream continuation rules. Add child review decisions as separate evidence, while keeping real human answers in their own field. - Return actionable completion validation feedback to both providers. Permit a corrected completion after rejection. Keep strict terminal acknowledgment validation. - Apply exclusive shared-workspace locks to sandbox environments. Local and SSH folders can run concurrently, including when old settings request serialization. - Repair test timing, native event parsing, and the review artifact assertion. Allow a valid reject, correct, and accept review sequence. Check the accepted card against its reviewer run and decision. Keep polling within the existing deadline when review acceptance precedes the parent wake projection; report a specific missing-continuation error at timeout. - Apply the ACPX pending-call limit to reserved finish/block calls, with capacity-release and cancellation tests. ## Verification - `pnpm build`: passed on `eea171aae`. - `pnpm -r typecheck`: passed on `eea171aae`. - `pnpm test:e2e:runner:unit`: 359 tests passed in 30 files on `b31ad9ab8`; runner E2E typecheck also passed. - `pnpm check:token-gates`: passed. - Focused DB review, reviewer authority, and prompt-boundary checks: 31 tests passed. They cover invalid reviewer runs, competing locks, atomic admission, duplicate claims, and valid resolution. - Heartbeat, workspace, and recovery checks: 30 tests passed. - ACPX sidecar suite: 27 tests passed. Moving the capacity guard back below reserved handling makes both new regression cases fail. - Four focused live continuation checks passed on their first attempt at `f15f55e0a`: answer updates scope (6/6 each on Codex and Claude) and question tool guidance (12/12 each). These cases do not use the reviewer prompt path changed afterward. - Fresh Codex and Claude review-handoff checks passed all 29 native checks each on their first attempt at `eea171aae`. Both runs received the expected fixed prompt and completed cleanup. Only the six selected live flows were tested; no full paid provider catalog run. - The final commit only extracts the existing test-harness timeout diagnostic into a shared helper and adds positive and negative coverage. Removing the accepted-review guard makes two regression assertions fail; restoring it passes all six timeout tests. Production runtime code, prompts, deadlines, and grading criteria are unchanged by this final commit. - Deadline regressions: a valid continuation delayed 20 seconds succeeds within its 30-second unit-test deadline; an absent wake returns a specific candidate-failure diagnostic at that same deadline. Both assertions failed before the fix. Production E2E deadlines remain unchanged. - Historical native failures remain recorded: Docker availability failures; a valid reject/correct/accept sequence that the first-card grader misread; and a test that rejected the gap between accepted child review and parent wake projection. No failed result was regraded. The latest tests use a protected reference to the pinned Docker image and the unchanged artifact oracle and time limits. - Full repository verification runs in GitHub CI. Local verification uses the focused suites above, full build, and full typecheck. An unchanged Codex shutdown timing test failed once in CI, passed in isolation, and its full shard passed on the final commit without changes to that test or its causal code path. The original failure is retained in the verification record. Greptile reviewed `b31ad9ab8` at 5/5 with no outstanding actionable findings. All review threads are resolved. All current-head CI gates passed, including the isolated native runner Docker build (55 successful checks; two skipped by the workflow). ## Risks - Reviewer admission depends on exact persisted decision and interaction bindings. A stale or changed card is rejected. - Paperclip control-plane tools are limited to inspection and review resolution. This is not a filesystem permission boundary; provider file and shell access retain the configured policy. - Deferred wake recovery changes dispatch receipt coalescing. A scheduler regression could delay a continuation if the receipt state is wrong. - Parent review outcomes are evidence for the model. They do not grant tool authority or change issue ownership. - This change does not address legacy lease-hold handoff behavior. > Roadmap review: native execution, review gates, and durable recovery are existing roadmap capabilities. This PR completes a narrow reliability path for those capabilities. ## Model Used OpenAI `gpt-6-astra` with reasoning, tool use, and code execution. OpenAI `gpt-5.6-luna` assisted with bounded implementation, review, and journal work. Context window size is not exposed by this session. Live test subjects use `gpt-5.6-sol` and `claude-sonnet-5`; they are not the PR authors. ## 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>	2026-09-17 15:52:19 -05:00
Dotta OpenAI GPT-5.6 Luna Paperclip	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

Author

SHA1

Message

Date

DottaandPaperclip

d0db8820db

fix(connections): repair native baseline and approval continuations (#15420 )

## Thinking Path

> - Paperclip manages AI agents and the tools they may use.
> - Connection setup separates provider preference from permission to
use a tool.
> - The first native connection baseline could not exercise its intended
decisions.
> - The browser used mutable task titles, and the provider fixture
already granted access.
> - Native provider-choice instructions also disagreed with the
preferred question format. Schema rejection gave no field guidance.
> - This pull request repairs those test preconditions and native
guidance, then fixes restart/approval defects exposed by the corrected
baseline. It also restores missing OpenCode tool-error evidence.
> - The benefit is an inspectable baseline before any further
instruction reduction.

## Linked Issues or Issue Description

Refs #15407.

The original 15-cell baseline remains 0 PASS / 15 FAIL. Ten cells
stopped on stale titles, two Codex cells had schema denials, two
OpenCode cells used already-granted tools, and one Claude cell returned
no native result. No intended user decisions were submitted. The exact
invalid Codex field and underlying Claude failure cause remain unknown.

[Original
campaign](https://github.com/paperclipai/paperclip/actions/runs/37562577199)
· [Original
report](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-37562577199-1/index.html)

## What Changed

- Match the browser's task route and visible identifier instead of a
title the agent can change.
- Start native provider-choice fixtures with no agent tool access.
Verify the public effective-access records.
- In the positive case, select Arcade, then grant its exact HubSpot tool
through the real access card. Require both saved decisions and exactly
one observed call.
- Return a canonical `providerQuestionSet` for native input and retain
the equivalent legacy `providerQuestion`.
- Keep invalid input rejected. Return bounded schema locations and
required field names without submitted values.
- Preserve Claude's exact session/content identity while allowing
authenticated registered instruction-copy paths to rotate on a new run.
- Reject duplicate approval reports for an existing exact tool-action
card before they create another human review.
- Wait for a recorded service-approval continuation within the existing
deadline; retain missing or failed continuation grades.
- Forward OpenCode tool activity through the runner facade, preserving
bounded errors and execution-part identity without inventing host-call
joins or exposing arguments.
- Preserve original grades, costs, scope limits and diagnoses in the
dated repair report.

## Verification

- Eval typecheck passes. Support suite: 1,801 PASS, one intentional
skip; Node checks: 128 PASS.
- Connection/schema tests: 51 PASS. Real-server public fixture setup:
one PASS with zero providers.
- Browser support regression: five PASS, including renamed and wrong
tasks.
- Focused Rust safe-feedback test: one PASS.
- Repository typecheck and build pass before the latest master replay.
Post-replay connection/shared/real-server fixture checks: 52 PASS; eval
typecheck passes. The browser review fix additionally passes all five
browser checks and seven suite checks.
- The full local repository run was interrupted incomplete after about
45 minutes, with five integration failures retained. All five pass in a
separate targeted invocation (1,250 unrelated tests skipped). No full
local-suite pass or root cause for the initial local failures is
claimed.
- Corrected frozen source `162cc90fdabe7f505b88ae095044531b82784c92`:
**10 PASS / 5 FAIL** across the [passing Codex
canary](https://github.com/paperclipai/paperclip/actions/runs/37575158761)
and [remaining 14
cells](https://github.com/paperclipai/paperclip/actions/runs/37576261807).
The canary passes all 17 checks. Claude's two provider-choice
continuations fail on restart, Claude service approval exposes an early
evaluator rejection, Codex service approval creates a duplicate
approval, and OpenCode provider-second times out after both decisions
with no HubSpot call. No original result is regraded.
- Final ledgers count 31 actual runs: 27 succeeded, two failed, two
cancelled during cleanup. All 15 cleanup/budget checks pass. The late
Claude continuation is absent from its earlier workflow snapshot; it
remains in the result/API/final ledger. Original evidence retains 279
hashes. Recorded LLM subtotal $0.04553787 is incomplete billing, not
actual total cost; local runtime is unmetered.
- New repair regressions reproduce the Claude attach failure, duplicate
approval acceptance and dropped OpenCode tool events before their
respective fixes. Nine Rust attachment checks, 127 ACPX host/adapter
tests, 33 completion/control-plane checks, nine eval deadline tests, 59
OpenCode proxy/driver tests, one Rust tool-error/redaction check, and
TypeScript/Rust composer parity pass. Eval typecheck, repository
typecheck and build pass. Existing support coverage is 1,802 PASS plus
128 Node PASS, one intentional support skip; two additional deadline
tests also pass.
- New-source full CI/review and live canaries are pending. The next
bounded selection is Claude provider-decline, Codex service-approve and
one OpenCode provider-second diagnostic with repaired event evidence. No
broader campaign or instruction-reduction qualification is claimed.
- Initial corrected campaign
[37574251834](https://github.com/paperclipai/paperclip/actions/runs/37574251834)
was cancelled during shared build after review found the breadcrumb
whitespace assumption. Its matrix job has zero steps and no provider
execution. The real adjacent-span browser regression now reproduces the
old failure and passes after the fix.

## Risks

- The corrected baseline remains 10/15. The new restart/approval fixes
require live qualification; OpenCode evidence forwarding does not itself
establish or fix its prior behavioral failure.
- The positive provider case now expects three runs, including separate
access approval. Its new results are distinct from the original invalid
fixture.
- The old Claude missing-result cause and rejected Codex field are
unknown. These repairs do not retroactively explain or erase either
failure.
- Path rotation must preserve prompt, custom instruction, skill/content
identity and protected provider settings; regression checks reject stale
or changed content. No connection authorization, JSON schema, budget,
cleanup, or final-result requirement is relaxed. Historical Everyday
prompts and gateway setup remain unchanged.

## Model Used

OpenAI Codex, GPT-6. The exact deployment variant and context window are
not exposed in this session. Used repository inspection, code editing,
test execution and retained-evidence analysis.

## Checklist

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

2026-10-07 06:18:51 -05:00

DottaandPaperclip

84fe89906d

fix: complete native agent review handoffs (#13581 )

## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work
> - Native execution uses durable runs, issue locks, wake requests, and
typed tool authority
> - A child can finish with a native agent review request while its
original assignee stays responsible for the work
> - The reviewer then needs a bounded execution path that can inspect
the child, record one decision, and finish safely
> - Before this change, assignee-only gates rejected the reviewer or
left the parent waiting after the child review ended
> - This pull request adds typed reviewer admission, scoped reviewer
tools, durable wake and recovery handling, and parent continuation
evidence
> - The benefit is that native review handoffs complete without changing
child ownership or granting broad mutation access

## Linked Issues or Issue Description

Refs: #13314
Refs: #13574

**What happened?**

A native child run could report `needs_review` for an agent reviewer.
The reviewer wake then failed assignee and execution-lock checks. The
child remained in review and the parent remained waiting.

**Expected behavior**

The named reviewer should receive one durable wake. The reviewer should
inspect the child and resolve the exact review card. The child assignee
should stay unchanged. The parent should receive the recorded review
outcome after the child reaches its terminal state.

**Steps to reproduce**

1. Run a native task with a different named agent reviewer.
2. Keep the child assigned to its original worker.
3. Let the worker finish with a native completion review request.
4. Start the durable reviewer wake.
5. Resolve the review and finish the reviewer run.
6. Observe the child and parent state.

**Paperclip version or commit**

Base: `e926b1301`. PR head: `b31ad9ab8`. Live reviewer verification
source: `eea171aae`.

**Deployment mode**

Built from source.

**Installation method**

Built from source (pnpm build).

**Agent adapter(s) involved**

Not adapter-specific (core bug).

**Access context**

Both.

**Database mode**

Embedded PostgreSQL in the isolated live test fixtures.

## What Changed

- Add server-validated native review assignment facts.
- Admit only the exact company, issue, source run, decision, revision,
addressee, and resolver policy.
- Give reviewer runs a narrow set of Paperclip read and resolve tools.
File and shell access follow the configured agent and environment
policy, so reviewers can run tests.
- Separate server-owned reviewer instructions from untrusted persisted
review data. Escape the data boundary; retain server-enforced
authorization.
- Keep the child assignee unchanged. Atomically claim the reviewer run,
wake request, and issue execution lock. A competing lock prevents
provider startup.
- Require the exact running reviewer session and current issue lock to
resolve its assigned card. Reject missing, unrelated, or terminal
reviewer runs.
- Add durable reviewer wake, lock, stale-card, and abandoned-run
recovery handling.
- Prevent duplicate native wake dispatches during deferred admission and
recovery.
- Carry accepted or rejected child review outcomes into parent task
context and continuation evidence.
- Add focused server, runner, and native protocol coverage.
- Preserve upstream continuation rules. Add child review decisions as
separate evidence, while keeping real human answers in their own field.
- Return actionable completion validation feedback to both providers.
Permit a corrected completion after rejection. Keep strict terminal
acknowledgment validation.
- Apply exclusive shared-workspace locks to sandbox environments. Local
and SSH folders can run concurrently, including when old settings
request serialization.
- Repair test timing, native event parsing, and the review artifact
assertion. Allow a valid reject, correct, and accept review sequence.
Check the accepted card against its reviewer run and decision. Keep
polling within the existing deadline when review acceptance precedes the
parent wake projection; report a specific missing-continuation error at
timeout.
- Apply the ACPX pending-call limit to reserved finish/block calls, with
capacity-release and cancellation tests.

## Verification

- `pnpm build`: passed on `eea171aae`.
- `pnpm -r typecheck`: passed on `eea171aae`.
- `pnpm test:e2e:runner:unit`: 359 tests passed in 30 files on
`b31ad9ab8`; runner E2E typecheck also passed.
- `pnpm check:token-gates`: passed.
- Focused DB review, reviewer authority, and prompt-boundary checks: 31
tests passed. They cover invalid reviewer runs, competing locks, atomic
admission, duplicate claims, and valid resolution.
- Heartbeat, workspace, and recovery checks: 30 tests passed.
- ACPX sidecar suite: 27 tests passed. Moving the capacity guard back
below reserved handling makes both new regression cases fail.
- Four focused live continuation checks passed on their first attempt at
`f15f55e0a`: answer updates scope (6/6 each on Codex and Claude) and
question tool guidance (12/12 each). These cases do not use the reviewer
prompt path changed afterward.
- Fresh Codex and Claude review-handoff checks passed all 29 native
checks each on their first attempt at `eea171aae`. Both runs received
the expected fixed prompt and completed cleanup. Only the six selected
live flows were tested; no full paid provider catalog run.
- The final commit only extracts the existing test-harness timeout
diagnostic into a shared helper and adds positive and negative coverage.
Removing the accepted-review guard makes two regression assertions fail;
restoring it passes all six timeout tests. Production runtime code,
prompts, deadlines, and grading criteria are unchanged by this final
commit.
- Deadline regressions: a valid continuation delayed 20 seconds succeeds
within its 30-second unit-test deadline; an absent wake returns a
specific candidate-failure diagnostic at that same deadline. Both
assertions failed before the fix. Production E2E deadlines remain
unchanged.
- Historical native failures remain recorded: Docker availability
failures; a valid reject/correct/accept sequence that the first-card
grader misread; and a test that rejected the gap between accepted child
review and parent wake projection. No failed result was regraded. The
latest tests use a protected reference to the pinned Docker image and
the unchanged artifact oracle and time limits.
- Full repository verification runs in GitHub CI. Local verification
uses the focused suites above, full build, and full typecheck. An
unchanged Codex shutdown timing test failed once in CI, passed in
isolation, and its full shard passed on the final commit without changes
to that test or its causal code path. The original failure is retained
in the verification record. Greptile reviewed `b31ad9ab8` at 5/5 with no
outstanding actionable findings. All review threads are resolved. All
current-head CI gates passed, including the isolated native runner
Docker build (55 successful checks; two skipped by the workflow).

## Risks

- Reviewer admission depends on exact persisted decision and interaction
bindings. A stale or changed card is rejected.
- Paperclip control-plane tools are limited to inspection and review
resolution. This is not a filesystem permission boundary; provider file
and shell access retain the configured policy.
- Deferred wake recovery changes dispatch receipt coalescing. A
scheduler regression could delay a continuation if the receipt state is
wrong.
- Parent review outcomes are evidence for the model. They do not grant
tool authority or change issue ownership.
- This change does not address legacy lease-hold handoff behavior.

> Roadmap review: native execution, review gates, and durable recovery
are existing roadmap capabilities. This PR completes a narrow
reliability path for those capabilities.

## Model Used

OpenAI `gpt-6-astra` with reasoning, tool use, and code execution.
OpenAI `gpt-5.6-luna` assisted with bounded implementation, review, and
journal work. Context window size is not exposed by this session. Live
test subjects use `gpt-5.6-sol` and `claude-sonnet-5`; they are not the
PR authors.

## 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>

2026-09-17 15:52:19 -05:00

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