mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-10-10 20:50:08 +02:00
codex/plugin-task-execution
6
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 DottaandPaperclip
|
b5342febe5 |
fix(runner): require current-turn completion after connection continuations (#15514)
## Thinking Path > - Paperclip manages agents, tasks, permissions, and execution budgets. > - Native tasks can resume after a connection decision in the same provider conversation. > - Each turn still needs an accepted completion report. > - Compact continuation messages did not explain that reports from earlier turns cannot finish the new turn. > - The connection evaluator could also grade before the final reply was stored or reject valid unavailable-access wording. > - This PR clarifies the current-turn report requirement and fixes those observation boundaries. > - The original connection instructions and strict native completion gate stay in place. ## Linked Issues or Issue Description Refs #15489. The reduction remains draft while this separate repair is qualified. Refs #15471 for the earlier connection continuation work. ## What Changed - Add a current-turn completion reminder to compact continuation inputs. - Keep final prose insufficient for completion. Preserve permissions and retry policy. - Wait for the final successful task run's saved, attributed decline reply within the existing deadline. - Use one bounded explanation matcher for both decline checks. - Wait for a recorded tool-action rejection to dispatch its bound continuation, with strict company, task, agent and source-run checks. - Retain the exact grading input before later API refreshes. - Add failure and delay regressions and update the Runner and evaluator docs. ## Verification The fresh comparison has **15/15 original passes on each variant**: 15 unchanged pass pairs, zero new failures, and no pending pair. There are 30 case attempts and **65 actual agent runs** (baseline 33; candidate 32). All runs succeeded. All 30 cleanups passed. No model attempt was retried. | Profile | Baseline | Candidate | | --- | --- | --- | | Native Codex `gpt-5.6-sol` | 5/5 | 5/5 | | ACPX Claude `claude-sonnet-5` | 5/5 | 5/5 | | OpenCode `openrouter/deepseek/deepseek-v4-flash-0731` | 5/5 | 5/5 | Each profile covers service approval, service decline, connection decline, provider decline, and selection of the second provider. The saved replies, approved briefings, decisions, fixture observations, final task states, and native completion records were inspected. All 18 saved decline-grade snapshots match their original captured inputs and checks. Result, API snapshot, and final ledger run sets agree. - [Candidate campaign](https://github.com/paperclipai/paperclip/actions/runs/37711658378) · [public candidate report](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-37711658378-1/index.html) - [Baseline campaign](https://github.com/paperclipai/paperclip/actions/runs/37711675579) · [public baseline report](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-37711675579-1/index.html) - Candidate source: `79905343bba280d462765faad19a26e7f179259e`. Baseline source: `7c5e120158f1385a1fc5f20be41f66c58a605534`. Both use master context `fc6304dfe5f2e446e09bd052a7b45f51e930f250`. The trusted workflow source is separately frozen at `dd777f4b7343305c4e6f44c422f44a1d78e12e4f`. - Both variants use the same evaluator, fixtures, models, permissions, 720-second cell deadline, and 1,000-cent company and agent hard stops. The only production difference is the compact continuation reminder. - Suite hash: `aee30b74b4d38ada08777798db0932fbc64e368bb427d29caa8cfd86c7f59747`. Definition hash: `ea9e17f54fe0af1acbb2337ddfab8a7e92db8488bd0f59510a63095ca0229b60`. - Provider-free transport capture: startup/resume input stays at 55,726 bytes. Compact continuation input grows from 53,334 to 53,535 bytes. The 42-tool catalog stays unchanged. These are Paperclip input bytes, not complete vendor prompt tokens. - Focused evaluator tests: 31 pass. Native contract, transport delivery, and session tests: 194 pass. Evaluator support: 1,819 TypeScript tests and 128 Node tests pass, with one intentional skip. - Full build, workspace typecheck, and evaluator typecheck pass. Current-head CI passes all required gates. The current rollup has 51 successful check runs, two intentional Storybook skips, and a successful Snyk status. Review is 5/5 with zero unresolved threads. - CI attempt 1 had one initial runtime-fixture health timeout. The exact test and its full 164-test file pass locally. One CI shard retry passed. The original CI failure, its dependent verify failure, and the retry remain visible in [CI history](https://github.com/paperclipai/paperclip/actions/runs/37711235060). - The broad local `pnpm test:run` attempt was interrupted after about 49 minutes (exit 130). It recorded one failure in the unchanged Zep memory-connector disabled-setting test. That test and the full 388-test tool-access file pass in separate local checks; current-head CI also passes. The local cause is not established, and this broad local attempt is **not** claimed as passing. Three earlier local failures also pass in their isolated checks; their original logs remain retained. - The first two setup admissions were cancelled before provider jobs to include the review correction. They made no provider calls. The completed campaigns above are the first and only model attempts for these corrected variants. Cost evidence stays separate from behavior. Original result summaries report only OpenCode amounts: baseline $0.039192096 and candidate $0.063221620. Final run ledgers also retain estimates for Claude (baseline $1.232439000; candidate $1.333611200) and Codex (baseline $2.340324400; candidate $2.129335600). These estimates do not replace the original summaries. Local and GitHub runtime are unmetered here. Invoices are unknown. This is not a cheaper or faster claim. ## Risks - A single matched trial cannot prove general equivalence or causation. The reminder is an instruction change, not a new completion enforcement rule. - Candidate OpenCode service-decline finished within one continuous run; its baseline used two. That pair passed the task outcome, but it does not qualify the reminder on a resumed decline turn. No extra paid run was used to replace it. - The text matcher is bounded evidence of an explanation. It does not prove reasoning or consumption of feedback. Bounded stdout excerpts do not prove that every extra attempted tool call is absent. - Missing saved replies or continuations still fail at the original deadline. Failed native completion remains a failure even when final prose is correct. - The unresolved local-suite discrepancy above remains a validation limit. Full remote CI and both focused local reproductions pass. - The original connection instructions stay in place. These results do not qualify the reduction in #15489. Its original 11/15 versus 12/15 grades and two new failing pairs remain unchanged. ## Model Used OpenAI Codex, based on GPT-6. The exact deployment ID and context window are not exposed in this session. Capabilities used: reasoning, repository editing, code execution, test inspection and eval 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 linked existing issues or described the issue in-PR - [x] I have not referenced internal/instance-local Paperclip issues or links - [x] My branch name describes the change and contains no internal Paperclip ticket id or instance-derived details - [x] I have run the focused local tests listed above and they pass; the interrupted broad local run is disclosed above - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing> |
||
|
DottaandPaperclip
|
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> |
||
|
DottaandPaperclip
|
caf120105c |
test: prepare neutral native connection guidance evals (#15407)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Agents need to discover connections, obtain consent, and continue from saved decisions. > - We want to reduce repeated instructions only when measured behavior supports the change. > - The existing decline tasks tell the model not to retry. One provider-decline check can pass without an explanation or an observed service counter. > - This PR adds neutral tasks and stricter saved-evidence checks before any connection instruction reduction. > - Production instructions remain unchanged. The new cells are configured, not live-qualified. ## Linked Issues or Issue Description Refs #15218. Refs #15389. **What existing behavior does this improve?** The Product E2E connection workflow evaluation and its instruction measurement provenance. **Current behavior** Some decline prompts supply the policy they intend to test. The provider-decline workflow does not require a saved post-decision explanation. Its old no-call check can use a missing fixture counter as zero. OpenCode has no connection cases in the original Everyday matrix. **Proposed behavior** Add an explicit-only suite with five connection stories on native Codex, ACPX Claude, and OpenCode. Require an explanation attributed by exact run ID after a saved decline. Observe the provider fixture counter. Preserve the original cases and grades. ## What Changed - Add fifteen configured cells with one attempt, twelve-minute deadlines, and verified 1,000-cent company and agent budget stops. - Remove procedure hints from the three new decline prompts. Keep a user-permitted explanation fallback and the existing positive controls. - Require saved decline state, one decision, unchanged connections, observed zero service calls where applicable, and a post-decision explanation from a successful run on the same task. - Add negative grader calibration and test the actual fixture budget payloads. Exclude the suite from default and generic selection. - Extend the existing full-catalog measurement source manifest with connection descriptions and schemas. Add an audit of fixed text, tool descriptions, returned instructions, and unqualified behavior. - Rebase on master `a6306ba606eb87c89b9ef0344e9fe8e0025580f9` and preserve its new Cursor suites. No production, credential, workflow, or lockfile change. ## Verification - Before rebase: Product E2E support passed 1,424 TypeScript tests and 128 Node checks. Six catalog measurement tests, repository typecheck/build, Product E2E typecheck, and exact fifteen-cell discovery passed. - The full pre-rebase repository test run was stopped when master advanced. Its partial result is not a pass. - After rebase and the review correction: repository build/typecheck, Product E2E typecheck, 1,799 TypeScript support tests (one skipped), 128 Node checks, six measurement tests, and exact fifteen-cell discovery pass. The duplicate local full-suite run was stopped incomplete after about 20 minutes once complete CI passed; no local full-suite pass is claimed. - Review found that the initial grader read `runId` instead of public `createdByRunId`. A regression calibration reproduced both rejection of valid public comments and acceptance of the wrong alias. The fix uses the actual field and binds the evidence type to the shared `IssueComment` contract. A subsequent type-only import path correction passes Product E2E typecheck. - Final source `0de306b9664bfbdebb6709ddb54c95152740d1ad` passes [complete CI](https://github.com/paperclipai/paperclip/actions/runs/37560250545): 51 successful checks and two intentional Storybook skips, plus separate Snyk success. Fresh Greptile review is 5/5 with the single review thread resolved and no new findings. The PR is clean and mergeable. - Local commands: `pnpm build`, `pnpm -r typecheck`, `pnpm test:e2e:runner:unit`, `pnpm test:e2e:runner:typecheck`, and `pnpm test:e2e:runner -- --list --suite native-connection-guidance`. The measurement uses `PAPERCLIP_NATIVE_PROCEDURE_MEASUREMENT=/tmp/connection-measurement.json pnpm exec vitest run --project @paperclipai/server server/src/__tests__/native-procedure-measurement.test.ts`. Validation used pinned pnpm 9.15.4. - No paid provider campaign was started. There is no baseline/candidate behavior result for these new cells. - The audit records 654 UTF-8 bytes of fixed connection guidance. A clean capture at `a04b8c6a452315625014888335d45670a2094fb6` confirms 41 supplied tools, 53,341 normalized bytes at start/resume, 50,949 at compact continuation, and a 48,195-byte authenticated OpenCode MCP catalog. These are byte counts, not tokens, bills, vendor-private prompt sizes, or savings from this PR. ## Risks - This is eval preparation. Passing support tests do not establish live model behavior or qualify an instruction reduction. - The explanation oracle checks attributed saved output. It does not prove cognition or arbitrary prose truthfulness. One saved interaction also does not prove the absence of repeated idempotent tool calls. - Successful new authentication and tool refresh, existing-connection agent grants, independent work while waiting, explicit retry after decline, and blocking when mandatory work remains still need separate coverage. - Notion setup decline does not execute a real Notion service. Positive service approval uses an already installed deterministic service; it does not qualify new connection creation. - The original historical failures remain unchanged. Future comparisons must freeze source, fixture, model, input, and grading controls and retain every actual attempt. ## Model Used OpenAI Codex, GPT-6 family, with reasoning, repository tools, and code execution. The exact serving model ID and context-window size were not exposed in this session; they are not inferred. No model provider was invoked by the eval suite in this PR preparation. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing> |
||
|
DottaandPaperclip
|
64895f187b |
fix(runner): clarify completion errors and restart test failures (#13682)
## Thinking Path > - Paperclip manages work across persistent agent sessions. > - The runner validates completion calls before accepting their results. > - Generic validation errors can leave the agent unable to repair a rejected call. > - Restart tests also exempted every later failure on an intentionally interrupted run. > - This change gives bounded schema feedback and limits the test exemption to expected interruption outcomes. > - Failures become easier to repair and diagnose without changing authorization or task prompts. ## Linked Issues or Issue Description Refs #13674 and #13676. Related environment and Agent Chat fixes landed in #13677 and #13678. Those changes do not cover these diagnostics. **What happened?** A malformed completion call received a general field list without the failed schema location. The everyday restart test hid later adapter errors on an intentionally interrupted run until its deadline. A clean pnpm install also broke the shutdown test because it resolved an undeclared Playwright package. **Expected behavior** Return enough schema information to repair completion calls without returning submitted values. Fail promptly on an unexpected recovery error. Resolve the declared test package's CLI. **Steps to reproduce** Run the new completion-validation and everyday lifecycle regressions against the parent commit. The new assertions fail there. Run the shutdown test in a clean workspace installation. **Paperclip version or commit** Based on master |
||
|
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> |
||
|
|
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> |