86 Commits

Include renames

Author	SHA1	Message	Date
DottaandPaperclip	b17019e14d	fix(agents): reduce default instructions and qualify stock harnesses (#14948) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Its adapters supply task context and access to Paperclip skills and tools. > - The default hire manual and shared prompts also repeat general work procedures. > - Those procedures overlap with stock provider instructions and the Paperclip skill. > - Existing E2E fixtures supply a QA manual, so they do not qualify the production default. > - This pull request reduces the generic instructions and adds real default-hire coverage. > - The benefit is less competing guidance, with inspectable evidence for preserved skills and task context. ## Linked Issues or Issue Description Refs: #14920. That merged change preserves native Codex base instructions. This PR covers the default manual, shared legacy prompts, operational skill guidance, and the narrowly approved ACP skill-discovery/session-environment repair for measured delivery and credential-persistence failures. **What existing behavior does this improve?** New non-CEO hires without a custom bundle and legacy task/chat startup and continuation prompts. **Current behavior** The shipped default manual contains 602 words. Generic task/chat prompts and ordinary resume deltas repeat work procedures already available through the harness and Paperclip skill. **Proposed behavior** The default manual contains only the eight-word company identity. Shared startup prompts retain identity and connection guidance. Ordinary resume deltas retain current work context without the generic execution contract. **Reason and benefit** Let the stock harness guide general work. Keep Paperclip-specific capabilities and independently test default hires, skills, ordered comments, and chat restart. **Breaking changes** New default hires receive less guidance. Existing saved manuals, explicit custom bundles, CEO templates, and specialized wake contracts retain their behavior. The obsolete includeExecutionContract option remains accepted for source compatibility. ## What Changed - Reduce the default hire manual to one sentence. - Reduce shared task/chat defaults and remove the generic ordinary-resume contract. - Keep connection guidance, auth, skills, custom prompts, and specialized wake context. - Add credential-free instruction-boundary gates and 26 explicit Product E2E cells across eight legacy/native profiles, including two focused Paperclip-storage cases. - Capture public hire receipts before providers run, then grade delivered prompts and independent task/chat outcomes. - Add an early legacy skill API recipe for saving a task document, checking the saved revision receipt and linking the document. Improve stock task/heartbeat skill-selection metadata and show a clickable Markdown UI-link example. Keep native tool completion separate. - Advertise bounded routing descriptions and exact successfully staged SKILL.md paths in legacy ACP Claude; keep full bodies on demand and preserve remote path rebasing. - Remove only the provider environment from copied persisted ACP session records, while loading current run credentials and preserving all other options/conversation state. - Regenerate both capability metadata inventories and reject stale manifests/inventories before provider admission. - Publish the original reduction and focused skill-repair comparisons, preserving all failures, automatic recovery, cost coverage and limitations. ## Verification **Behavioral qualification remains pending.** Original legacy ACP Claude loses the issue document only in the reduced cohort beneath an unchanged credential failure. A source-backed diagnosis finds that neither ordinary assignment reads the staged operational skill, while the runtime persists provider environment in session state. The new common repairs expose skill metadata/path and omit persisted env; strict document and credential guards stay intact. [Inspectable diagnosis and retained hashes](https://github.com/paperclipai/paperclip/blob/9f654db4541d3d002769c988f6e51fc0b08dadbd/doc/plans/2026-10-03-legacy-acp-claude-readiness.md). Current repair head `de0965984ff3edf611ae6d0e7ca5c7d5ae3947bb` incorporates master `569c7203aa24b95440682983ce7940ba1d4247bd` (merged #14961/#15007). All 222 affected adapter tests, adapter-utils/E2E typechecks, and final 96 variant/grader/retry calibrations pass. The frozen historical comparator is `c25697f4260b6f3adfea143c3ae9932e2f42986d`: 8,280 of 8,291 paths identical, exactly two production instruction paths plus nine declared unit expectations differ. The operational skill/discovery/environment repairs, selected model/profile/task/core grader/auth/permissions/retry policy are identical. Both actual launcher prepare→verify admissions pass with zero providers. [Immutable manifest and exact receipts](https://github.com/paperclipai/paperclip/blob/9f654db4541d3d002769c988f6e51fc0b08dadbd/doc/plans/2026-10-03-legacy-acp-claude-evidence/manifest.json). One original legacy ACP Claude cell per variant is authorized, with enforced single campaign attempts, 12-minute deadlines and company/agent 1,000-cent hard stops; every product recovery run/cost is counted. Actual live outcomes are pending. Current normal CI has one failed server shard and failed aggregate verify under diagnosis; other normal gates including typecheck/build/Rust/all eight browser shards pass. Fresh review completed successfully; the valid historical startup/resume masking finding was fixed with per-invocation task/chat checks and strict complete-snapshot capture, calibrated and resolved. Prior heads, failures and campaigns below remain historical evidence, not checks on this repair head. - Prior head `36aa4d81c49a1a8f6f04b1a068fae19aa901955f` is replayed on merged hiring master `862a5758ba0e88a33232c1f1fa645e85c38a3113`. All 52 current-head checks pass with two intentional Storybook skips, including repository typecheck/test/build and the browser shard. Fresh Greptile is 5/5 with zero unresolved review threads. Exact-head stock prerequisites pass 599 assertions (598 TypeScript + 1 Rust), all six gates and retained receipt verification, zero providers/source errors. Fingerprint `a7f5a22d860a88fe20cce213c6d5e0004788f32c8363930729aea4fd740ad16d`. Combined catalog/hiring calibrations pass 67 assertions, E2E typecheck and 26-cell stock discovery pass. Canonical contract/inventory checks and the later issue-derived reference calibration are retained; that reference-only follow-up is not live-qualified by earlier frozen runs. - Prior full repository typecheck/build passed. The complete local Vitest run executed 14,956 tests: 14,870 passed, 83 skipped, three timing failures. All three affected files passed unchanged narrow reruns; original failures remain retained. Current-head CI now passes the full general checks; the original local failures remain retained. - The original 24-pair default-manual/shared-prompt comparison has two new overall classic Claude/OpenCode document-delivery failures plus an additional legacy ACP Claude document loss beneath an unchanged credential-guard failure (not closed by later runs), two newly passing OpenCode ordered cases, seven unchanged failures and 13 unchanged passes. Equal 15/24 totals do not establish behavioral equivalence. [Complete original report](https://github.com/paperclipai/paperclip/blob/875f4c397d9e8c3f12f39dedd59abaf1eaf5236e/doc/plans/2026-10-02-stock-harness-live-comparison.md). - The skill-only repair holds the eight-word manual/shared prompts and merged #14920 fixed. All four matched profile configurations and 203 fixture/behavior files match. Candidate `abd0b628ca642c09a54a4edc56a5227402f6686e` varies only the two skill sources against baseline `bc83fe030234439ac51279502a28803958963e2e`. [Candidate workflow](https://github.com/paperclipai/paperclip/actions/runs/37060885547) and [baseline workflow](https://github.com/paperclipai/paperclip/actions/runs/37060888047) each pass 571 exact-source prerequisites before providers; all eight cells clean up successfully. Failed campaigns publish successfully and remain failed. - Repair pairs: Claude original Fail → Pass; Claude explicit Pass → Pass; both OpenCode cases Fail → Fail. Explicit OpenCode's handoff worsens beneath the unchanged failing UI-link grade: baseline gives a clickable API URL, candidate gives a code-formatted path without an anchor. The request's usable-link wording is narrower in the UI-only oracle. [Complete repair report and safe projection](https://github.com/paperclipai/paperclip/blob/875f4c397d9e8c3f12f39dedd59abaf1eaf5236e/doc/plans/2026-10-02-legacy-document-skill-repair.md). - The subsequent narrow stock metadata/link correction has two matched Pass → Pass cases, zero new machine failures/passes and no pending pairs. Both original-case handoff links remain deficient: candidate uses a wrong PAP prefix, baseline supplies a bare prefix-less slug path; the preserved original oracle only requires a durable document. Both explicit clickable UI-link cases pass revision/content/link grading. All four exact-source 587-check gates, single assignment runs and cleanup pass. This does not establish fix causality because baseline also succeeds. [Candidate workflow](https://github.com/paperclipai/paperclip/actions/runs/37069547401) freezes `fe9dc1e3c518825242ed889ab9c8352986f8c2ed`; [matched baseline](https://github.com/paperclipai/paperclip/actions/runs/37069552374) freezes `0d7ecfa96d72fba79b7f0a25052b42c0686c0488`. This is a skill-only comparison with reduced manuals/shared prompts held constant, not a repeat of the historical-manual comparison. Only original and clarified explicit classic OpenCode cases are selected, two per variant/four expected turns. 8,242 other tracked files and both profile hashes match; protected workflows admit each exact source before credentials. [Complete qualification report](https://github.com/paperclipai/paperclip/blob/74d0d3d945f4c52d0814b5a845ab5bd09f33cd6b/doc/plans/2026-10-02-opencode-skill-routing-link-qualification.md). Candidate original loads Paperclip/reference before saving publicly; baseline original loads it after writing locally, then saves publicly within the same assignment. Reported cost totals are $0.0107824490 candidate / $0.0107909015 baseline, with unmetered runtime. The later reference-only issue-derived link correction is provider-free calibrated and **not live-qualified** by these frozen runs; no further paid runs. - Retained tool calls show the repaired original OpenCode assignment loads only its assigned output skill before writing locally. Operational Paperclip is first loaded during automatic disposition recovery; its early recipe is visible then, but it never saves the missing document. Explicit candidate loads Paperclip and reads the new reference before saving successfully. All nine actual runs are counted. Reported LLM totals are $0.3802537209 baseline and $0.4918990161 candidate; local runtime is unmetered. - Initial setup, packaging, cancelled/missing-cell recovery, callback test and relative-output attempts remain retained. No completed provider failure was rerun. Frozen measurement branches are unchanged by later canonical metadata maintenance. - Run `pnpm test:e2e:runner:stock-harness`, `pnpm test:e2e:runner:unit`, and `pnpm test:e2e:runner:typecheck`. Select `stock-harness` explicitly for paid execution; it is excluded from `--all`. Prior-head integration: `36aa4d81c49a1a8f6f04b1a068fae19aa901955f` replays this PR on merged hiring #14985 (`862a5758ba0e88a33232c1f1fa645e85c38a3113`), preserving the four explicit custom-CEO-bundle checks, minimal generic manual boundary, and both suites. The combined fixture catalog and hiring calibrations pass 67 assertions; exact-head stock prerequisites pass 599 assertions (598 TypeScript + 1 Rust), all six gates and retained-receipt verification, zero providers/source errors, fingerprint `a7f5a22d860a88fe20cce213c6d5e0004788f32c8363930729aea4fd740ad16d`. E2E typecheck and 26-cell stock discovery pass. Fresh current-head CI passes all 52 checks with two intentional skips, and fresh Greptile is 5/5 with zero unresolved review threads. The prior source-plan browser failure is retained: a deterministic process fixture replayed its last `fixture:plan` command on `chat_task_completed`, writing revision 2 with identical body after the approval handoff. This was not paid provider execution. Rebased current-head CI passes the same assertion without an old-head retry or a change to that browser fixture. The merged hiring change was measured separately on immutable matched unions, with this reduced/shared/operational context and native completion guidance held constant. [Complete original two-profile report](https://github.com/paperclipai/paperclip/blob/f0512647656be78e48abd8c22a3078db8bf6bcd2/doc/plans/2026-10-02-hiring-template-live-comparison.md): [candidate](https://github.com/paperclipai/paperclip/actions/runs/37075466208) / [historical baseline](https://github.com/paperclipai/paperclip/actions/runs/37075469463), 705 provider-free prerequisites each. Both pairs are unchanged Fail → Fail on the exact-five count, with six core delivery checks passing all four cells; 28 actual successful runs include eight automatic completion wakes, zero retries, four successful cleanups. Source-read coverage is uncomparable, actual model charges unknown. Separately versioned provider-free accounting remains analytical work; original verdicts are preserved. This does not rerun or qualify the completed default-manual or native campaigns. ## Risks - Legacy ACP Claude's additional delivery loss is not closed by any later matched run and blocks the no-extra-failing-behavior merge criterion. Legacy document delivery may have relied on the prior manual/shared prompts. The early skill repair improves Claude in one trial; the later OpenCode pairs pass in both variants and cannot establish causality or robust recovery. Both original-case links remain deficient beneath the storage-only grade. The later issue-derived reference correction has only provider-free validation. Native finish/block descriptions must not be supplied to legacy agents. - The comparison holds merged native Codex fix #14920 constant; it cannot measure that fix's before/after task performance. - These bounded skill/context/chat workflows do not measure general coding quality. Unrepresented providers remain unqualified. - Saved manuals and old Codex sessions are not automatically migrated. Codex through ACP still has a separate base-instruction follow-up. ## Model Used OpenAI Codex, GPT-6 family as identified by this session. The exact deployment ID and context-window size are not exposed. The assistant used reasoning, repository tools, code execution, and delegated PR/eval work. ## 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 (relevant suites and all three unchanged narrow reruns pass; complete-run timing failures retained in Verification) - [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 on the new repair head (prior-head checks retained above) - [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups on the new repair head - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>	2026-10-03 12:32:42 -05:00
DottaandPaperclip	78e0034498	fix(evals): account for hiring completion notifications (#15007) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Product E2E evals check real hiring and delegated task completion. > - The hiring fixture requires three requested CEO turns and two coder executions. > - The server can also wake the CEO when each delegated task completes. > - Two exact-five-run guards rejected these valid completion turns in all four retained cells. > - This pull request validates bounded completion turns in both guards. > - The benefit is accurate workflow grading while all actual runs and coverage failures remain visible. ## Linked Issues or Issue Description Refs: #14985, #14948, #14961. **What happened?** The original hiring comparison reports Codex Fail → Fail and Claude Fail → Fail. Each cell has seven successful runs. The five requested work turns are accompanied by two server task-completion notifications. All six other delivery checks pass. **Expected behavior** Require exactly three distinct user-requested CEO turns and one coder execution for each of two known tasks. Admit at most two strictly attributed server completion turns, including one turn that batches both tasks. Reject unknown, duplicate, failed, retried or extra-work runs. **Steps to reproduce** Inspect the retained four-cell report linked below. Each original result fails `five-successful-turns`. The same exact count was also enforced by the final chat-flow guard. ## What Changed - Add one typed lifecycle helper shared by the hiring scorer and the hiring-only final chat guard. - Validate public run ledgers, company/user/account identity, request attribution, task origins, completion deliveries, timing and replies. - Keep exactly five required work turns; declare seven maximum total turns for cost and timeout planning. - Count all actual runs, including notification runs and unexpected resets. Keep other chat count guards unchanged. - Version the hiring grader as v3 (turn accounting v2) and include the helper and chat guard in its definition digest. - Keep source-read, exact coder-body and all six other delivery checks unchanged. - Add 144 focused helper/scorer/settlement calibrations and separately versioned exact retained-input replay reports. - Retry complete bracketed observations, await both owed callbacks and attributed replies, and refresh the final guard consistently. - Reject unrelated completion writes and failed mutation attempts using exact canonical/native action IDs. Missing identity mapping is uncomparable action coverage. ## Verification - All 977 credential-free E2E support tests pass across 64 files, including 144 focused lifecycle/action/scorer/settlement calibrations. - E2E typecheck, ordinary plugin SDK and Runner TypeScript dependency builds, capability contract/inventory checks and the existing two-cell hiring discovery pass. - [Executable replay report](https://github.com/paperclipai/paperclip/blob/fed1729018cc100f5f4bbfb692777e49009c423b/doc/plans/2026-10-02-hiring-executable-accounting-replay.md) pins current code revision `e4077ade1818d98b9862ae79ee1d49a007dcf9c1`, v3 definition digest, exact source/input hashes and each original/new check. - The stricter replay verifies both Codex variants through both executable guards. ACPX Claude action attribution remains unresolved/uncomparable because provider execution IDs cannot be exactly joined to native request IDs; guards fail closed. No notification writes are observed. All six other outcomes and every original source/template coverage check stay unchanged. Original files and Fail → Fail machine verdicts remain preserved; zero providers are called. - Full attempts remain uncomparable in both profiles. Historical Claude also keeps its six-backtick exact-template mismatch. This grading repair does not prove model-performance equivalence. - The limited sidecar-v1 and initial executable-v2 passes checked notification-created tasks but could miss unrelated document writes. Those assessments remain preserved and do not prove harmless notifications. The stricter v3 replay is separate. - [Original measurement and separate sidecar](https://github.com/paperclipai/paperclip/blob/8eb517ca1497687237163bdef4dfc4d3332ea916/doc/plans/2026-10-02-hiring-template-live-comparison.md) retain 28 actual runs, eight automatic notifications, four successful cleanups and unknown actual model charges. No models are rerun. - The branch is replayed on master `59c07ede7`. Intervening master changes are UI-only; eval source bytes and replay verdicts match. The four-cell provider-free replay was repeated against the reachable code revision. - Initial-head normal CI retained browser failures in agent-run denial feedback and touch-picker scroll position. Those browser paths and imports were unchanged, but their cause was not established. The necessary review-fix head passes both browser checks; no blind rerun was requested. - Local full repository typecheck/test/build were not repeated. Exact-head normal CI passes the required repository gates, including typecheck, tests, build and browser shards. Fresh Greptile review completed on `fed1729018cc100f5f4bbfb692777e49009c423b` with 5/5 and zero unresolved threads. An independent rerun of the 144 focused helper/scorer/settlement tests passes on the unchanged head. **Merge readiness:** This PR repairs the evaluator. Its positive and negative calibrations pass, both guards reject missing action attribution, current-head CI and review pass, and there are no merge conflicts. The retained ACPX cells remain uncomparable because their action IDs cannot be joined. That coverage limit remains a separate follow-up; it does not require relaxing this grader or changing the old results. No model calls, production instructions, carrier changes, or historical regrades are part of this readiness update. ## Risks - Missing or inconsistent public lifecycle evidence fails the bounded helper. The focused calibrations reject plausible false positives and malformed observations. Unmatched action IDs fail closed and are reported as uncomparable rather than a model task regression. - Source-read evidence remains incomplete. This PR does not change provider event carriers or relax the coverage oracle. - The versioned count check differs from original v1 results. Reports retain both versions and exact input hashes. ## Model Used OpenAI Codex, GPT-6 family as identified by this session. The exact deployment ID and context-window size are not exposed. The assistant used reasoning, repository tools, code execution and delegated calibration work. ## 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 normal CI gates are green (exact head `fed1729018cc100f5f4bbfb692777e49009c423b`; fresh review tracked separately below) - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups (completed exact-head review; zero unresolved threads) - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>	2026-10-03 06:42:51 -05:00
DottaandPaperclip	dd868ed125	fix(runner): share native completion tool guidance (#14961) ... ## Thinking Path > - Paperclip manages AI agents and their work. > - Native Runner agents report completion through finish and block tools. > - The providers receive different descriptions for those tools. > - Completion guidance belongs with the tools that enforce the result. > - This pull request shares the descriptions and refreshes retained catalogs. > - A separate native suite checks completion and blocking on production defaults. > - Legacy agents retain their separate skill and API paths. ## Linked Issues or Issue Description Refs: #14920, #14948, #14985. **Current behavior** Native Codex and MCP bridges describe finish and block differently. Retained provider sessions can keep old descriptions. **Proposed behavior** Native providers receive the same finish and block descriptions. The descriptions cover report selection, validation feedback, returned outcomes, approval gates and final-answer timing. Retained native sessions refresh from v13 to v14. **Reason and benefit** Put the completion procedure next to its native tool. Preserve stock base instructions, schemas, permissions and terminal semantics. This PR now stands alone on master. It contains no reduced manual, shared prompt or operational-skill changes from #14948. ## What Changed - Add canonical native finish and block descriptions. Use them in direct Codex and both native MCP bridges. - Advance the native tool contract to v14. Cover old-v13 refresh without replacing task identity or prior history. - Check authenticated tool catalogs, provider start/resume frames and serialized daemon catalogs. - Add an independent, explicit-only native completion suite. Preserve the original assigned-skill durable-document journey. Pair it with a concrete whole-task blocker across Codex, ACPX Claude and OpenCode. - Verify the actual public production default bundle and budgets before execution. Require independent durable disposition, native result/terminal receipts and observable provider-final ordering. - Correct the blocker browser oracle to accept the requested explanation. Keep exact owner/action/scope checks. Calibrate positive, missing and contradictory replies. - Preserve only actual `tool_call` terminal names (`paperclip_finish` / `paperclip_block`) in the native compatibility run-log projection. Require the same named call ID through its finishing result; retain all other redaction boundaries. - Admit verified hosted shallow checkout/build hydration and bind the selected runnerd to exact source/archive/binary provenance. Hosted cells truthfully reuse the existing trusted build; local admission executes Rust calibration. Forward only public source/run identifiers through both launcher preflight subprocess paths. - Enforce single attempts in the launcher for opted-in fixtures. Keep ordinary retry policy unchanged. Run exact-source, credential-free admission before credential loading. ## Verification - Frozen candidate: `d6e59e4712a3158ab4cd7d58deff1389b4578c21`, based on master `59c07ede72dc08b8aba149a01cc11e0b7a204621`; historical descriptions: `e74ed61a69fbdd8b3a8f15dd6456bc3140246e33`. Exactly the five original native production files and six unit tests differ. Both carry identical corrected fixtures, strict named finishing-call grader, closed compatibility carrier and admission. Defaults, profiles/models/auth/permissions and manifest bytes match. - Actual launcher `prepareNativeCompletionPreflight` → `verifyNativeCompletionPreflight` admission passes on both exact refs with zero providers: candidate 132 / historical 127 selected TypeScript assertions, 128 Node calibrations and one Rust normalization calibration each; E2E typecheck, manifest checks, selected binary provenance and six-cell discovery pass. Each has 257 explicitly skipped unrelated assertions, not coverage. The credential-free environment calibration exercises both real prepare/verify subprocess options with public hosted identifiers and rejects credential/ambient overrides. Complete actual launcher prepare→verify also passes on both frozen refs with explicitly synthetic hosted metadata/verified archives, separately labeled as calibration rather than a trusted GitHub run. Exact framed provenance parsing and mock source identity are calibrated without relaxing the real verifier. - [Complete matched qualification report](https://github.com/paperclipai/paperclip/blob/532066620b88e8731a5211fbe1cbc48ce8c7dd1a/doc/plans/2026-10-02-native-completion-master-qualification.md), [immutable manifest](https://github.com/paperclipai/paperclip/blob/532066620b88e8731a5211fbe1cbc48ce8c7dd1a/doc/plans/2026-10-02-native-completion-calibrated-manifest.json) and [closed retained audit/hashes](https://github.com/paperclipai/paperclip/blob/532066620b88e8731a5211fbe1cbc48ce8c7dd1a/doc/plans/2026-10-02-native-completion-calibrated-results/comparison.json) are inspectable. All six candidate cells pass; historical descriptions pass five. Paired outcomes: **zero new failures, one new pass (Codex blocker), five unchanged passes, zero pending pairs**. [Candidate campaign](https://github.com/paperclipai/paperclip/actions/runs/37098728980) and [historical campaign](https://github.com/paperclipai/paperclip/actions/runs/37098815696) each execute six original attempt-1 native runs, with no campaign retry and successful cleanup. Their trusted workflow revision is `215586d127e97c9301d86e769a39a15c13298ca2`, separate from measured source. [Candidate public HTML](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-37098728980-1/index.html) and [historical public HTML](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-37098815696-1/index.html) retain declared screenshots. - Independent candidate evidence agrees with all original grades: 51 strict native checks, 12 served-default/budget checks and 21 original skill/document checks pass. The historical Codex blocker saves the correct whole-task blocker but omits the required marker from its actual provider final and identical saved reply. This is not semantic-summary fallback. Its original browser/matcher failure stays retained; the additional native snapshot/grade and workspace before/after digest were never written and are not fabricated by the separate API/PRP audit. Historical Codex completion has one failed finish followed by success within the same native run; the public receipt records no failure reason. All twelve runs and their usage remain counted. Reported model-cost subtotals are $0.00421482 historical/$0.00437391 candidate; Codex/Claude zero entries have unknown billing type, actual invoices are unverified and hosted execution cost is unmetered. One matched trial supports no extra failure within these six cases, not broad statistical or coding-quality equivalence. - Initial hosted `e18c2cf9` / `459455ac` and subsequent `0a9c5a7` / `00a761b` cohorts each stopped before providers in all twelve cells. The latter failed a mocked-receipt unit test under ambient hosted metadata; all source/build proofs passed. [All twelve later setup receipts](https://github.com/paperclipai/paperclip/blob/402ee94c52273ad58de355ae9a7d562dd22f8101/doc/plans/2026-10-02-native-completion-qualified-hosted-setup.json) are retained. [Exact failed setup receipts](https://github.com/paperclipai/paperclip/blob/27653eb1a8f8ce839776d760f4563f672e5a706c/doc/plans/2026-10-02-native-completion-master-hosted-setup.json) and the original manifest remain intact. Local sandbox-denied loopback and stale anchor-expectation attempts are retained separately; unchanged appropriate assertions were corrected/admitted before paid dispatch. Old anonymous OpenCode streams are not assigned inferred tool names or retroactively passed. - Full provider-free E2E support previously passed 927 tests in 67 files. Exact-head d6 normal CI run `37098409915`, attempt 1 passes full repository typecheck/build/tests, Runner Rust/static checks, all browser shards/aggregate and canary: 52 check-runs pass, four intentional skips, Snyk passes. Fresh Greptile check `111132956342` is 5/5 with zero unresolved threads. Source-specific deterministic tests do not substitute for the bounded live comparison. - Earlier native source `9138f570c341c251a5727c32d6615ce238bc8e03` is archived. Its [complete reduced-manual-context report](https://github.com/paperclipai/paperclip/blob/9138f570c341c251a5727c32d6615ce238bc8e03/doc/plans/2026-10-02-native-completion-live-comparison.md) remains intact, including original failures, grader limits and provider-free replay. It is not current-master-context qualification. ## Risks Changed tool text can change model behavior. The completed six-pair qualification shows no extra failing outcomes in this bounded trial; other tasks and repeated-run variance remain unmeasured. Observable final ordering does not prove provider feedback consumption. Public evidence can fail closed if a provider does not expose the required result sequence. This slice does not remove native fixed prompts or measure general coding quality. No database, schema, permission or legacy completion changes occur. ## Model Used OpenAI Codex, GPT-6 family, with code inspection, execution and tool use. The exact deployment ID and context-window size are not exposed in this session. They are unavailable rather than inferred from the model menu. ## 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>	2026-10-03 06:20:38 -05:00
DottaandPaperclip	862a5758ba	fix(agents): reduce hiring templates to role descriptions (#14985) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - New agents receive role instructions from onboarding, the hiring skill, or a team package. > - These sources repeat harness procedures and impose generic work policies. > - They can crowd out the task and the harness instructions. > - This pull request reduces those sources to short role descriptions. > - It preserves configuration, skills, authentication, reporting lines, and approval controls. > - The benefit is less repeated instruction text with explicit coverage for the default hiring path. ## Linked Issues or Issue Description Refs #3307. The CEO template can impose a fixed delegation route instead of letting the agent choose how to fulfill the request. This change removes that route. It does not implement autonomous goal selection. Related work: #14920 preserves stock Codex base instructions. #14948 reduces the generic manual and shared runtime prompts. #14961 improves native completion-tool descriptions. This PR is separate from those changes. ## What Changed - Select only the short CEO `AGENTS.md` for new default CEO bundles. Keep the three former companion files as compatibility assets. - Reduce the first-agent chief-of-staff prompt and coder, QA, UX, and security role examples. - Reduce seven bundled team role bodies. Preserve their role, reporting, and skill metadata. Regenerate the catalog. - Make hiring examples optional. Replace the long generic role manual with short role drafting guidance. Preserve explicit requester instructions. - Add configuration and import coverage for native and legacy managed bundles, custom instructions, first-agent rendering, and catalog contents. - Add an explicit-only hiring eval that starts from the production CEO default and checks one coder hire, independently computed JSON output, saved instructions, and worker reuse. - Include the full prompt comparison and a separate three-request drafting simulation. Neither is a live provider comparison. Prompt differences: [before and after](doc/plans/2026-10-02-hiring-template-prompt-diff.md). The CEO default falls from 1,897 to 20 words. The coder example falls from 652 to 18 words. Word counts describe instruction size, not outcome quality or billing. ## Verification - PASS: 99 focused server tests and eight shipped-catalog tests. - PASS: catalog generation and validation for four shipped teams. - PASS: hiring skill validation. - PASS: `pnpm -r typecheck`. - PASS: `pnpm build`. - INCOMPLETE: the full local `pnpm test:run` was stopped before rebase. Its original log is retained. This is not a completed full-suite pass. The full current-head GitHub CI workflow passed: https://github.com/paperclipai/paperclip/actions/runs/37073372419. - PASS: `pnpm test:e2e:runner:typecheck` and `pnpm test:e2e:runner:unit` (63 files / 843 tests). - PASS: discovery for the two new hiring cells, 50 existing everyday cells, and the full 438-cell catalog. - PASS after rebase: 99 server tests, 11 catalog tests, 62 selected E2E support tests, and the E2E typecheck. - PASS: all current-head PR checks at `57dcee147ed0b2d2e3cc657cd9e50fb16bf9ec25`: 51 successful check runs, two intentional Storybook skips, and successful Snyk status. Fresh Greptile is 5/5 with zero unresolved threads. - PENDING follow-up: matched live hiring runs on frozen integration refs. No live outcome-quality or non-regression result is claimed from the configuration checks or this merge. The new suite has two local native cells: Codex and ACPX Claude. It expects five provider turns per cell. It compares source-derived bundles, so the historical long templates remain admissible. Missing successful source-read receipts make a pair uncomparable. They do not establish a behavior regression or equivalence. ## Risks - New default roles have fewer prescribed procedures. Live checks must determine whether a removed instruction was needed for an outcome. - Existing custom and saved bundles keep their contents. The retained companion assets avoid a source-file compatibility break. - Specialized Summarizer, Reflection Coach, and Wiki Maintainer prompts remain unchanged. Their product contracts need separate review. - The generic non-CEO fallback reduction is in #14948. This PR alone does not provide its eight-word fallback. - Configuration tests and drafting simulations do not establish live outcome quality. QA, UX, security, and chief-of-staff hiring behavior remain outside the new two-cell comparison. > For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and discuss it in `#dev` before opening the PR. Feature PRs that overlap with planned core work may need to be redirected — check the roadmap first. See `CONTRIBUTING.md`. ## Model Used OpenAI Codex, based on GPT-6, with reasoning, code editing, shell tools, and delegated verification. The runtime does not expose the exact deployment model ID or context-window size. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge Co-Authored-By: Paperclip <noreply@paperclip.ing>	2026-10-02 17:56:42 -05:00
DottaandPaperclip	6c1a75da49	feat(connections): make AgentMail a default connection with inline setup (#14772) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Connections give agents access to external services. > - AgentMail needs both a saved key and an inbox assigned to the agent. > - Chat requests offered a setup link instead of an inline card and could treat a saved key as complete. > - Inbox setup also hid address conflicts behind a generic server error and a separate review step. > - This pull request makes AgentMail a default connection, adds the inline card, reduces setup to two steps, and shows conflicts beside the address. > - Shared native dropdown styles also give every caret a consistent inset. ## Linked Issues or Issue Description **What happened?** AgentMail requests in chat did not show a usable inline connection card. Manual setup required extra screens, ignored saved account keys, and could trap new-address setup in a locked inbox dropdown. Agent selectors omitted the avatar from the selected value. A taken address could produce an HTTP 403 from AgentMail and appear as an internal server error. Native dropdown arrows also touched the right edge of their fields. **Expected behavior** Make AgentMail available as a default connection. Ask for the API key inline, with a direct link to its provider page. Default human access to the company and agent access to the requesting agent. Resume the agent only after an assigned inbox is active. Manual setup should ask for an agent and email address, then finish. Address checks should run as the user types. Taken addresses should show clickable alternatives. A domain dropdown beside the name should prefer a verified custom domain. Setup should suggest authorized saved AgentMail keys and show agent avatars in the picker and selected value. **Steps to reproduce** 1. Ask an agent to connect AgentMail when it has no assigned inbox. 2. Check that an inline API-key card appears and links to the provider's API-key page. 3. Open AgentMail setup, choose an agent, and request an address that is already taken. 4. Correct the inline error, refresh, and finish setup with the same request ID. 5. Inspect native dropdown carets in light, dark, disabled, and right-to-left states. Uses the bounded provider-error parser merged in #14768. Related work: #13256 introduced AgentMail; #14725 expanded connection search. ## What Changed - Stop recurring email queries for tasks that have no email thread. Share the query between the thread provider and activity view. Keep email-task updates and invalidation-based discovery. - Make AgentMail available without the experimental chat setting. Keep the catalog, setup and management routes, agent Channels tab, task email feed, receiving worker, and agent tools available by default. Other experimental chat providers stay gated. - Make the email address and copy icon a single clickable action with the shared Copied! confirmation. Add View inbox linking directly to the matching AgentMail console inbox, with the address encoded as one URL path segment. - Reorganize inbox Settings around the copyable email address, usage instructions, and receiving status. Move reconnect credentials into a disclosure and separate the Disconnect action. Add production Settings stories for active, paused, unassigned-address, revoked, webhook, long-address, mobile, and reconnect states. Show repair controls when the inbox has an error. Keep usage instructions tied to an active inbox with an address. - Add AgentMail channel intents and an inline key field with the direct API-key URL. - Keep setup and retry state tied to the interaction. Require an active inbox for completion. Preserve company and agent access checks. - Reduce manual setup to agent selection and email selection. Put the domain dropdown beside the address and default to a verified custom domain. Preserve explicit choices across reloads. Keep receiving settings under Advanced options. - Check the initial address and edits after a 350 ms pause. Abort superseded requests and ignore stale responses. Show clickable suggestions and retain known creation conflicts across reloads. - Add a company-scoped, manager-only address check using the saved credential. Search the visible inbox list instead of fetching an uncreated inbox: live AgentMail retains negative lookups that can break subsequent access-key creation. Unlisted addresses remain unknown; creation is authoritative. - Suggest labeled saved AgentMail keys in both manual setup and the inline card. Filter by company, provider, active credential, and current-user grants on the server. Prefer an account key and preserve the selected key or an explicit new-key choice across refresh. Use verified scope metadata and bounded concurrent checks for legacy keys. Never return secret values. - Catch an inbox-only key before the email step. Allow its existing inbox only after an explicit choice. Recover old locked drafts at the key picker. Save the replacement key before retiring an empty draft, then use a new setup URL so refresh preserves the switched account; stop if cleanup fails. Preserve already allocated addresses and their original accounts. - Use the shared AgentSelect in email setup. Show the canonical agent avatar in each option and the selected value, including other consumers of the shared component. Add regression coverage for legacy and current Lucide agent-mention icon formats. - Start each catalog Add connection with a fresh setup identity. Honor Finish setup's exact draft/account/address instead of resuming an unrelated browser draft. Return Cancel and Done to Connectors and Email settings to the inbox. Group the task/thread explanation in a How it Works card. - Route AgentMail catalog removal through the email inbox control API, including unfinished drafts. Refresh both the catalog and inbox views. - Render each inbox management tab separately. Access uses the saved account grants and agent controls; Conversations and Activity use the shared persisted email feed. Activity lifecycle actions use the email API. Reconnect returns to inbox Settings. Conversation failures show a retry instead of a false empty state. Email delivery recovery stays in the task. - Map documented provider address conflicts to a field error. Preserve actionable messages for other failures. - Preserve non-secret draft fields across refresh, scoped to the requested agent. Never save API keys in browser storage. Resume partial inbox creation with the original agent, address, and request ID. - Show an already-created address with explicit retry and new-address recovery instead of locked inputs. Preserve the original inbox and resumable draft when choosing another address. Distinguish runtime-key 404 errors and log safe provider status/operation/code. - Apply final agent access once within email setup authorization for a new account whose original installs are unchanged. Preserve later permission edits and reused account installs. Support in-place retry of progress loading. - Let a failed inline setup change keys after retiring an empty draft. Persist its replacement setup identity without storing secrets. Recover a server-saved account when refresh interrupts the save response, while preserving intentional account changes. - Render the production setup in Storybook and add error, recovery, and mobile states. - Inset native select carets in shared CSS. Preserve custom icons, listboxes, keyboard behavior, and forced-color controls. - Add browser regression coverage and an AgentMail Product E2E case with persisted-state and rendered-card evidence. ## Verification - Full `pnpm -r typecheck`, `pnpm build`, `pnpm check:token-gates`, and `git diff --check` passed after the default-availability change. - All 485 focused tests passed. These cover setup, management, catalog and route gates, connection intents, email authorization, Cursor execution, and the OpenAPI contract. All 39 email integration tests run with the experimental chat setting off. - The shared polling change passed four behavioral tests, UI typecheck and build, and token gates. - `tests/e2e/agentmail.spec.ts` passed with the actual server setting off. This full-stack browser test uses simulated provider responses. It covers catalog entry, saved keys, editable address and domain controls, creation, conflicts, retry, all management tabs, clipboard feedback, the provider link, and task email rendering. - In the live local browser, Add connection reached the editable email step with the saved account key. The verified custom domain was selected by default. Both domain choices worked. The existing inbox Settings page remained available. Both active inboxes completed new mail checks with the setting off. No new provider inbox or email message was created for this pass. - Earlier live provider acceptance covered creation on a verified custom domain, Finish connecting on the reported draft, successful mail checks after refresh, and catalog removal of disposable draft and active connections. Clicking the email address copied the exact address and showed Copied!. View inbox opened the same inbox in AgentMail’s console. No email messages were sent. - Production setup and Settings Storybook builds and interactions passed. Settings states include active, paused, unassigned, revoked, webhook, long-address, mobile, and reconnect. Receiving and revoked-access stories had zero accessibility violations. - Full local `pnpm test:run` on an earlier revision completed with 14,709 passing, 87 skipped, and four transient failures. All four failed cases passed in focused reruns without product changes. That serial full local command was not repeated after each follow-up. The latest-head full CI suite is the final test gate. - CI found an obsolete browser assertion that hid every channel when the flag was off. Updated it to keep AgentMail and the Channels surface visible while preserving the GitHub chat route gates. All 11 provider browser tests passed locally after scoping the Channels selector to the agent sidebar. Two initial local attempts stopped at temporary Postgres initialization. The passing run used a separate disposable database on the existing local Postgres server; it was removed after the test. - Updated the remaining sidebar and aggregator discovery assertions for default AgentMail availability. Ordinary task fixtures now return no email thread. All 128 sidebar/task-page tests and all 42 aggregator tests passed locally. - Latest head `b42bb4cd5cc9f2d01a99ab8026832d5a956ea85f`: full CI passed, with 54 successful checks including Snyk and two intentional Storybook skips. The CI run is https://github.com/paperclipai/paperclip/actions/runs/37020833647. A fresh Greptile review scored 5/5 with no unresolved threads. Live model evaluations and inbound/outbound email delivery were not run. ## Risks - AgentMail no longer needs experimental opt-in. Setup still requires a human to connect an account and assign an inbox. Inline setup creates an inbox after a human submits a new or saved key. Company access, agent access, inbox assignment, and completion checks remain enforced. - AgentMail read APIs cannot prove global address availability. The visible-list check is bounded to 100 entries and cannot see inboxes outside the key’s scope. The UI reports this limitation, suggests alternatives without claiming they are free, and keeps final creation conflicts inline. Lookup outages show an error without preventing the authoritative creation attempt. - Native select CSS affects the whole app. Custom-icon selects and multi-row lists are excluded. Forced-color mode keeps the browser caret. - Saved-key discovery uses stored verified scope metadata and checks authorized legacy credentials concurrently within a shared three-second deadline. Provider outages mark legacy choices unavailable; users can still enter another key. Final use rechecks authorization and provider access. - No database migration or transport default change. Live connection remains the default. ## Model Used OpenAI Codex, GPT-6, with reasoning, tool use, and code execution. The exact served model ID and context-window size are not exposed in this session. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass (focused suites; full-suite limitation 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 (latest head `b42bb4cd5cc9f2d01a99ab8026832d5a956ea85f`) - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups (latest head `b42bb4cd5cc9f2d01a99ab8026832d5a956ea85f`) - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>	2026-10-02 10:01:15 -05:00
DottaandPaperclip	018993140f	feat: let agents name prompt-only tasks (#14761) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Users create tasks with a title and a description. > - A required title adds work when the prompt already explains the request. > - An agent can name the task once it reads that request. > - This pull request accepts prompt-only tasks and starts them with a short prompt slice. > - A scoped title tool lets the assigned agent replace that slice early without changing execution state. > - A live browser eval checks the real agent call, saved title, audit entry, and preservation of user titles. ## Linked Issues or Issue Description **Subsystem affected** Cross-cutting: task creation, shared contracts, database, server, runner tools, and board UI. **Problem or motivation** Users must currently write a title before they can submit a detailed task prompt. The agent has enough context to write a useful title itself. **Proposed solution** Make the title optional when a description is present. Save the first 120 characters of the normalized prompt as a provisional title. Ask the assigned agent to call `set_task_title` early. Use an atomic provisional-title guard to preserve titles supplied or edited by users. Keep explicit titles supported. Related: #14543 and #14556 concern empty-title submission. This change intentionally enables that submission when a prompt is present, instead of requiring a title. ## What Changed - Add the `titleNeedsGeneration` field with an idempotent migration. Keep existing titles unchanged. - Add `PUT /api/issues/:id/title` and the native and legacy `set_task_title` tool. Enforce company access, active-run ownership, shared, bounded retry receipts across native/HTTP calls, and transactional audit logging. Refresh external-object links after commit, with the same feature gate and plugin detectors as ordinary title edits. - Add early naming guidance in Standard, Ask, and Plan task context. Preserve the description, status, and assignment. - Allow prompt-only root and child task creation, plus draft restoration in the New Task dialog. Keep user titles supported. - Add an opt-in Product E2E suite for prompt-only Standard and Ask tasks, plus an explicit-title control. It checks actual provider calls within the first five tools, persisted state, audit attribution, and the reloaded UI. - Preserve a closed vocabulary of API key maintenance phrases in declared prose while rejecting opaque credential suffixes. Add one bounded naming retry after wording is rejected, without treating the rejected call as a saved title. - Repair the native cleanup receipt check exposed during full verification: accept matching input digests, retain legacy input checks, and reject conflicting receipts. ## Verification - Live Product E2E on `f43478473800e3a46b85c5ee79677efdb15108e7`: **3/3 passed** with native Codex `gpt-5.4-mini`, first attempts only, automatic retries disabled. Standard and Ask each saved “Rotate expired API key” on their first tool call, with matching persisted state and a single same-run audit entry. The explicit-title control retained its user title with zero title writes. All three verified the reloaded browser UI. - Campaign: `local-2026-09-30T21-30-11-021Z`. Earlier failed campaigns are retained separately; they exposed credential-prose handling and prompted the naming recovery fix. No failed result was regraded or deleted. - Reproduce with `pnpm test:e2e:runner -- --id task-titles.runner-codex-mini.local.prompt-title-standard --id task-titles.runner-codex-mini.local.prompt-title-ask --id task-titles.runner-codex-mini.local.preserve-explicit-title --max-automatic-retries 0` and an authorized provider key. - Full `pnpm -r typecheck` and `pnpm build` passed on the latest commit. The runner build used the configured external eval source tree. - Product E2E unit suite: **61 files, 818 tests passed**; E2E typecheck and UI token gates passed. - Title API/native regressions cover prompt-only and explicit child creation, user edits, ownership/company isolation, external reference refresh, cross-surface retry replay, and the 64-key limit without receipt eviction. All passed. Prompt-context coverage: **44 tests passed**. - Rust credential regressions: **35 tests passed**, including benign maintenance qualifiers and opaque credential rejection in every declared prose field. Catalog/report reconciliation: **28 tests passed**. Native recovery: **560 tests passed**. - Broad local `pnpm test:run`: **14,555 tests passed** in the general server group; two suites failed to initialize embedded PostgreSQL and the existing 40,000-file Git streaming stress test exceeded its 300-second macOS timeout. All three suites then passed in isolation (**5 tests passed**) without code or timeout changes. The original full local command exited nonzero and is not being represented as a clean full run. - Latest-head GitHub checks are green: **53 passed, 4 skipped, zero failed or pending**, including all test shards and the canary packaging dry run. Greptile reviewed the same commit at **5/5**, with zero unresolved review threads. ## Risks - The additive database field must reach the server and UI together. The migration uses `IF NOT EXISTS` and defaults existing tasks to a final title. - Title generation depends on the assigned agent running. Tasks without a run keep their provisional title. - Live qualification covers the native Codex path in Standard and Ask modes. API/legacy and Plan behavior have deterministic coverage. - The credential-prose exception validates the entire suffix against a closed maintenance vocabulary. Unknown suffixes, assignments, quoted values, credential prefixes, and diagnostics retain strict checks. ## Model Used OpenAI Codex, based on GPT-6, with reasoning, tool use, and code execution. The exact deployment ID and context window are not exposed in this session. The live eval uses the native Codex `gpt-5.4-mini` profile. ## 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>	2026-09-30 16:48:24 -05:00
DottaandPaperclip	cbd278dc03	fix(interactions): derive chat recipients and validate explicit users (#14742) ... ## Thinking Path > - Paperclip helps people manage AI agents and their work. > - Agents use saved questions to get human input and continue the same task. > - The standard question example recently told models to copy a user ID. > - A model can omit an identity prefix and create a question its intended recipient cannot answer. > - Agent Chat already knows the conversation owner, so the server can supply that identity. > - This pull request removes the blanket instruction and validates explicit recipients before saving. > - Ordinary questions stay simple, and explicit addressing remains available for decisions that need a particular person. ## Linked Issues or Issue Description Refs #14707, #14188. Related: #14238 handles legacy email recipients; this change prevents invalid recipients in new cards and retains exact ID matching. **What happened?** A model copied a Cloud user ID without its prefix into `addresseeUserId`. Creation succeeded. The intended user's answer then failed the exact recipient check. **Expected behavior** Ordinary chat questions use the saved conversation owner. A task may optionally name a specific recipient. The API rejects an unknown or unauthorized recipient before it creates a card. **Steps to reproduce** Create a chat question for a user whose ID is `paperclip-id:example`. Supply `example` as the addressee. Before this change, creation accepts the invalid recipient and the owner cannot answer. With this change, creation returns 422. Omitting the field saves the full owner ID and allows that owner to answer. ## What Changed - Remove `addresseeUserId` from standard question examples and remove the blanket requester-ID instruction. - Derive the recipient of ordinary chat questions from the persisted conversation owner. Reject conflicting explicit user IDs. - Keep explicit task recipients optional. Validate supplied user IDs with the existing board mutation policy, including company, viewer, and Cloud restrictions. - Preserve explicit agent routing, connector intents, confirmations, exact recipient checks, idempotent retries, and no-login local-board authority in local-trusted mode. - Update the blocker grader to accept an omitted recipient and verify the actual requester answered. - Add database and HTTP tests for prefixed identities, denied recipients, concurrent retries, saved answers, and response delivery. ## Verification - Database interaction service suite: 90 tests passed, including implicit local-board creation/answering and authenticated/Cloud denial. - Interaction HTTP route suite: 84 tests passed. - Affected interaction/native/connector/documentation suites: 231 tests passed across six files after valid-user fixtures were updated. - Resolver and interaction unit suites: 29 tests passed. - Product E2E unit/calibration suite: 793 tests passed; Product E2E typecheck and blocker catalog discovery passed. - Generated API-reference and capability contract checks passed. - `pnpm -r typecheck` and `pnpm build` passed. - Full local `pnpm test:run` did not finish green: its initial general-server pass had 14,416 passing assertions, one unrelated native-resume assertion failure on macOS, and three teardowns from an intermediate fixture cleanup fixed above. Separate broad local groups also encountered timeout/live-port failures under host load. Local UI (7,026), CLI (502), shared (817), and skills-catalog (20) tests passed; the complete final-head CI matrix is the broad verification gate. - After two CI cold-start readiness timeouts, a separate test-only commit gives the first exposure lifecycle fixture the existing normal 30-second readiness budget. Its real HTTP, ordering, and cleanup assertions remain intact; the targeted case and final Linux CI shard passed. Production deadlines are unchanged. - A separate OpenCode fixture failed twice on GitHub-hosted Ubuntu because its cached Node executable was group-writable; the same case passed on AWS runners. The fixture now qualifies its own Linux copy with mode `0500` and the actual copy digest. Host files and production security checks are unchanged. The focused macOS case passed; the new Linux-copy branch also passed on the final AWS-hosted Linux runner (1,125 passing Runner tests, 3 skipped). The final run was not on a GitHub-hosted runner. - Final-head [CI run 36762078176](https://github.com/paperclipai/paperclip/actions/runs/36762078176) passed for `116b968b24fa0a8c5724a7bf96e73a8dda5f0425`: 54 successful checks and two conditional Storybook skips, with no pending or failed checks. The 27 general/serialized test jobs reported 28,635 passing tests. Typecheck, build, Runner, browser E2E, and Canary gates passed. Greptile reviewed that exact head at 5/5; both review threads are resolved, with no open follow-ups. - No live provider replay is claimed by this PR. ## Risks - New explicitly addressed cards reject users who cannot mutate the issue, including viewers, inactive members, and invalid IDs. Callers that supplied invalid recipients must correct their request. - Existing addressed cards are not rewritten. Existing authorization checks remain strict. - Chat inference applies only to questions without an agent addressee. Connector intents and governed confirmations retain their own recipient paths. - No schema change or migration is required. ## Model Used OpenAI Codex, GPT-6 (exact serving variant and context window are not exposed in this environment). Used reasoning, tool use, code editing, and test execution. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>	2026-09-30 14:16:15 -05:00
DottaandPaperclip	b54b2dc35c	fix: preserve warm Codex turns with incremental managed file checkpoints (#14735) ... ## Thinking Path > - Paperclip manages AI agents and keeps their instructions and files durable. > - Native Codex runners can keep a process alive between compatible turns. > - Managed file collection stopped that process after each turn, which defeated warm reuse. > - Agent folders can contain large images and other files, so full copies on every turn are expensive. > - This change keeps one managed directory for the live session and saves only file changes after each turn. > - Ownership, authorization, instruction changes, and process retirement still control when reuse is safe. ## Linked Issues or Issue Description Related: #13710 introduced native warm session reuse. This fixes managed file collection that still forced those sessions to stop. No duplicate open PR or issue was found. **What happened?** With managed instructions and warm native Codex enabled, consecutive turns reused a Daytona sandbox but started a new runner process each time. The managed directory collector required process termination before saving files. **Expected behavior** Compatible turns keep the same process and managed `AGENT_HOME`. Each completed turn saves added, changed, and deleted files before the next turn starts. Unchanged large files do not transfer again. **Steps to reproduce** 1. Use a native Codex agent with managed instructions and a reusable Daytona environment. 2. Enable warm session reuse and run three turns on the same task. 3. Write a large binary on the first turn, edit a small note on each turn, and delete a file on the second turn. 4. Compare process identity across turns and read the canonical files through the public agent-files API. **Paperclip version or commit** Reproduced on `d30b03bd8c17604cdab1533eeeeb087aba30e8b1`. **Deployment mode** Local server with remote Daytona execution; cloud native runner uses the same path. ## What Changed - Retain the managed directory only for the verified owner of a live native Codex session. - Checkpoint each completed turn before releasing the session for reuse. Retry unstable captures, then stop and collect when a warm checkpoint cannot be validated. - Compare metadata and cached hashes, stream only changed file payloads, record deletions, and validate path, content, quota, and authorization before saving. - Rotate sessions when canonical files, loaded instructions, credentials, or launch policy change. Fence stale collection and cleanup callbacks from later owners. - Keep cleanup and recovery aware of the current session owner. Recheck canonical files under the writer lock at handoff, attach the successor collector before fallible bookkeeping, and emit one final save receipt on checkpoint fallback. Preserve storage warnings across unchanged checkpoints. - Add regression coverage and a three-turn Daytona test with independent public API file checks, an unchanged 8 MiB binary, deletion checks, and strict process identity checks. - Document checkpoint consistency, lifecycle behavior, and local run-log counters. - Replace a timing assumption in the Daytona teardown test with explicit transfer-arrival gates after CI exposed an unset release callback. ## Verification - Full local `pnpm -r typecheck` and `pnpm build` passed. Server checks were repeated after the final storage-warning fix. - Runner E2E typecheck and 749 runner E2E unit tests passed. - Focused file checkpoint, directory ownership, instruction collection, native session, and merge tests passed. After review fixes, the managed-directory and native-session suites passed 550 tests, including intervening canonical edits, same-run fresh restore, failed handoff collection, and one-call fallback collection. Server typecheck passed again. The Daytona plugin suite passed 218 tests. The quota-warning regression failed before the fix and passed afterward. - Three real Daytona campaigns passed before the final handoff review fixes. The latest kept PID 547 across all three turns. The first checkpoint copied 8,388,635 bytes; the next two copied 36 and 54 bytes. Public API reads verified the binary, note contents, and deletion after every turn. Test cleanup deleted the sandbox. - The final head was also deployed to an isolated cloud staging instance and passed three UI-triggered native Codex turns with managed instructions. All three retained the same process ID/start time, native session, provider session, runner instance, and Daytona sandbox. Checkpoints copied 8,388,643 bytes on turn 1, then only 52 and 78 bytes on turns 2 and 3; those warm captures also hashed only 52 and 78 bytes. Independent canonical API reads verified every byte of the unchanged 8 MiB binary and the exact note contents after every turn; the deleted file returned 404 after turns 2 and 3. After restoring the original lifecycle and agent-auth configuration, removing the temporary secret, pausing the test agent, and deleting both test sandboxes, independent canonical API reads still verified the entire binary, the final 78-byte three-line note, and the deletion. The native runner flag remained enabled and the final serving revision remained the PR head. - Two earlier staging attempts are preserved as failures and are excluded from the acceptance result: a saved ChatGPT login failed with a provider routing 401, and its subsequent stopped-sandbox retry failed before provider startup with a closed-lease admission error. The successful campaign used a fresh sandbox and a temporary encrypted API-key binding. The stopped-lease retry remains unexplained; this campaign does not establish recovery of that failed sandbox. - All [Paperclip CI gates](https://github.com/paperclipai/paperclip/actions/runs/36750397355) pass on `26ef2ef56a389259246809805c0b34a4747eb86b`, including full test partitions, build, typecheck, runner verification, E2E shards, and the Canary clean public-npm install. Greptile reviewed that exact head at 5/5 with no unresolved review threads or outstanding findings. - Full local repository coverage used the existing CI partitions, but the 40,000-file Git streaming stress test timed out and its local retry was interrupted by macOS thermal emergency sleep; this is not a green full local suite claim. The exact stress test passed on the final head in [CI server shard 2/12](https://github.com/paperclipai/paperclip/actions/runs/36750397355/job/110008294290), in 111.9 seconds. - Repeat the live test with configured credentials and a Linux runner artifact: `pnpm test:e2e:runner -- --id daytona-warm-continuity.runner-codex.daytona.warm-three-turn`. ## Risks - This is a file-level checkpoint, not an atomic snapshot of the whole folder. Background writes after a capture are saved by the next checkpoint or final stopped collection. - Metadata scans still visit all paths. Modified files transfer in full; unchanged files do not rehash or transfer. - Incorrect ownership or reuse could collect the wrong directory. Run ownership fences, current authorization, stable capture validation, and stopped collection fallbacks are covered by tests. - Warm reuse remains opt-in. No database migration or fleet default changes. ## Model Used OpenAI GPT-6 through Codex, with reasoning, code editing, tool use, and test execution. The exact serving model ID and context-window size are not exposed by this session. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>	2026-09-30 13:33:37 -05:00
DottaandPaperclip	3c561642b4	fix(chat): resolve approvals and preserve unanswered questions (#14613) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Agents ask for decisions and optional details through cards in chat. > - A clear approval in a message can leave the matching card pending. > - An unanswered question can also block an unrelated later reply. > - Decisions need a saved source message, while optional questions need to remain answerable in history. > - This pull request records conversational decisions and lets users move on from questions and answer them later. ## Linked Issues or Issue Description **What happened?** Native Claude and Codex could act on approval in chat while the original approval card stayed pending. Pending question forms stayed above the composer, were absent from history, and could suppress later chat replies. A late native question answer could wait for a finished run to reconnect. **Expected behavior** The active agent records a clear approval or refusal against the exact card and user message. Ambiguous replies do not grant consent. Users can send another message without answering a question. The question remains pending in history and can be reopened and answered later. The saved answer reaches the agent. **Steps to reproduce** 1. Ask an agent to propose work with a confirmation card, then approve it in chat. 2. Check that the original card records that approval before work starts. 3. Ask an interactive question, send an unrelated message, and reload. 4. Open the unanswered question from history and submit an answer. Related work: #14408 added completion delivery. #14607 tests completion reporting turns. Neither records conversational answers on approval cards. ## What Changed - Add a confirmation endpoint backed by a user comment, with schema validation, OpenAPI discovery, and native Plan-mode access. Ask mode remains read-only. - Check company, active run, actor, current session, message provenance, revision, and resolver policy. Save the decision and audit in one transaction. Retries do not repeat effects. Emit resolution telemetry after commit. - Give fresh and resumed chat turns the actual pending confirmation identities. Teach agents to save clear conversational decisions before acting and to clarify ambiguity. - Keep unanswered Agent Chat questions as compact history entries. A newer user message closes the old form. Question cards never contribute to composer pending counts or navigation, including after dismissing a fresh form. The history card is the sole reminder; clicking it restores that exact form and draft. - Preserve Agent Chat questions when later messages or questions arrive. Historical ordinary inputs no longer gate later chat replies. Current-run requests, task execution, and governed approvals keep their gates. Remove the special acknowledgement-publication proof helpers that this rule replaces. - Route answers to finished native runs through durable fresh-wake delivery, with existing idempotency and source-question context. Settle late replies against contiguous completed conversation turns and freeze their history replay; failed, unhandled, and newly arriving messages remain actionable. - Add real-component Storybook scenarios, database and UI regressions, and a three-turn native Claude/Codex E2E case. Capture distinct, UI-ready screenshots and report the individual assertions. ## Verification - Focused decision/publication/UI regressions after merging master: 288 passed; subsequent UI draft, failed-send, and conversation checks: 199 passed. - Native question and durable delivery regressions: 106 passed, including all four terminal run states and exactly-once late delivery. Seven targeted regressions fail against the original implementation and pass with the fix. - Latest conversation/decision/native-delivery regressions after the master merge: 121 passed. Covers completed progress, missing or failed intervening turns, new messages during a late reply, stale sessions, and frozen retry/replay boundaries. Four new assertions fail before the ordering fix. - E2E support suite after the master merge: 792 passed. Negative controls reject expired cards, wrong questions/answers, stale or missing replies, unrelated clarification forms, and unexpected tasks. - The embedded-browser walkthrough caught one additional defect: dismissing a fresh question still showed a composer badge. Both Cancel and close-button regressions failed before the fix. The fix at `65f2ade12` passes 170 chat-thread tests and 792 E2E support tests. After merging master, 232 chat-thread/confirmation tests, server/UI typechecks, and token gates pass. The preview and two-provider live E2E pass at `e5512a206`; Greptile is 5/5 with zero unresolved threads at that commit. All 55 checks are now successful at `e5512a206` (four conditional checks skipped), including the aggregate verification gate and clean-install canary test. The first attempt was interrupted by simultaneous CI worker shutdowns; one failed-job rerun passed without code changes. - [Published Storybook](https://d1p6rlowie26tp.cloudfront.net/storybook/branches/codex~2Fchat-approval-resolution/?path=/story/chat-comments-agent-chat-unanswered-questions--moved-on): nine real-component scenarios. Manually exercised move on, reopen, preserve draft, answer later, answer one of multiple questions, and a custom mobile answer in the embedded browser. Retested fresh Cancel and close-button dismissal in the updated build, then reopened and submitted the preserved Green selection and inspected its answered receipt. Static preview has no live model/backend; its callbacks are fixture responses. - [First live campaign](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-36714504406-1/) reproduced the late-answer completion-state defect on both providers despite correct saved answers and acknowledgements. It also exposed a valid imperative clarification rejected by the old oracle. Both issues are fixed with regression controls; this failing run is retained as evidence. - [Four-cell qualification](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-36717804064-1/) passed 4/4 at `2bf8a1009`: unanswered-question return and ambiguous confirmation, each on native Claude and Codex. Inspected saved state, source-message decisions, visible cards, and agent replies. Both late-answer chats settled to waiting; no unrequested tasks were created. [Final branch rerun](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-36719666238-1/) passed 2/2 at `142630720`: the same unanswered-question journey after merging master, plus an additional screenshot and browser assertion for the actual late-answer acknowledgement. - [Composer-reminder E2E](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-36727006818-1/) passed 2/2 at `5b62c52d9`: native Claude and Codex, three turns each, with explicit no-badge assertions before and after reload. Inspected saved pending/answered state, both screenshots with a clear composer, and actual Blue acknowledgements; all five behavioral matchers passed per provider and neither created tasks. Cost coverage is partial; this is bounded workflow qualification. - [Fresh-dismissal E2E](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-36742773318-1/) passed 2/2 at `e5512a206`: native Claude and Codex, including fresh Cancel, clear composer, reopen, unrelated message, reload, late Blue answer, and actual agent acknowledgement. All five behavioral matchers pass per provider. Inspected the fresh-dismissal screenshots and saved pending/answered identity; neither created tasks. Cost coverage is partial (4/6 runs). - Prior evidence remains available in [the earlier campaign](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-36642252725-1/). Its early loading screenshot and overwritten final capture prompted the UI-ready, distinct screenshot fixes. ## Risks - The model interprets intent. The server verifies permission and provenance; it does not infer consent from text. Ambiguous and unrelated replies are not approvals. - Historical questions can accumulate. They remain visible, pending, and answerable; no automatic answer or expiry is invented. - The change to completion gates is scoped to Agent Chat and ordinary historical inputs. Current-turn and governed approvals retain their existing controls. - Live qualification is limited to the selected stories. Broader native onboarding finalization remains separate work. - No database migration. Telemetry adds no fields or values; the contract and README document the commit boundary. Privacy review was requested on the PR. ## Model Used OpenAI Codex, GPT-6 family, with reasoning, repository tools, code execution, and browser-test orchestration. The exact model ID and context-window size are not exposed to this session. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>	2026-09-30 11:46:46 -05:00
DottaandPaperclip	d30b03bd8c	test: add persistent E2E coverage for human blocker decisions (#14707) ... ## Thinking Path > - Paperclip manages work for AI agents. > - Agents use the coordination skill when work needs human authority or a scope decision. > - PR #14188 replaced automatic manager escalation with direct blocker handling. > - This behavior needs real browser, server, database, and provider tests. > - The test must verify saved human input, task ownership, and resumed work. > - This pull request adds six reusable Product E2E cases and improves the skill examples that they exercise. ## Linked Issues or Issue Description Refs #14188. The merged change needs repeatable behavior coverage. The new suite tests missing administrator access, missing hiring permission, and requester scope questions. Searches found no duplicate blocker-guidance suite. This extends the existing eval system described in ROADMAP.md. ## What Changed - Add the explicit-only `blocker-guidance` Product E2E suite. It has three local scenarios on legacy Codex and legacy Claude. - Use the production UI and public APIs to create work, save a human-only question or confirmation, answer it after reload, and resume the same task. - Check requester identity, ownership history, manager activity, hiring, saved answers, and completion. Keep direct text input as a separate UX result. - Save pending and final screenshots, API checkpoints, skill hashes, provider evidence, and billing data through the existing report pipeline. - Isolate the Claude fixture home. Verify the served skill bytes before dispatch so an old installed skill cannot silently replace the evaluated skill. - Improve the coordination and hiring skill examples. Include the human-only policy, requester address, wake behavior, and handling of authorized scope changes. - Grader v5 requires the exact approved public welcome note as a new worker comment. Browser input checks reject unwritable scope cards before clicking, and confirmation direction must be saved in the resolution before the worker wakes. - Add grader calibration and browser-input tests. Update the fixture guide and generated capability inventories. ## Verification - `pnpm build`: passed after rebasing onto current master. - `pnpm -r typecheck`: passed. - `pnpm test:e2e:runner:typecheck`: passed. - `pnpm test:e2e:runner:unit`: 742 tests passed. - `pnpm test:e2e:runner:browser-support blocker-input.spec.ts`: 10 tests passed. - `pnpm test:e2e:runner -- --list --suite blocker-guidance`: six cells found. - Capability inventory and generated-contract checks: passed. - `pnpm exec vitest run server/src/__tests__/hiring-operational-examples.test.ts`: four tests passed after synchronizing the generated API reference and section anchor. - Full general and serialized test suites: passed in CI on `6652cee74517039676bad6a720f213625d265acd`. The redundant local `pnpm test:run` was interrupted after complete CI coverage passed; it is not claimed as a completed local full-suite run. - Final GitHub checks: 54 passed, two optional Storybook checks skipped. The runtime-exposure startup test hit a 10-second readiness timeout once, passed a targeted local reproduction, and its CI shard passed the single retry without code changes. - Current-head Greptile: 5/5, clean check, zero unresolved threads. - Historical live measurement on September 29 at `4edc77ae2b95b10dd61426ce3f042bac00527ad9`: three independent six-cell runs scored 5/6, 6/6, and 6/6. Claude Sonnet 4.6 passed 9/9. Codex `gpt-5.6-sol` passed 8/9. These runs predate this rebase. - Version 5 changes the scope answer to an exact approved publication draft. The historical runs do not qualify that new requirement; the two-provider scope pilot at `49a1f4eab369948b9e3b34a6ce436489e875e4ec` passed Codex and failed Claude. Claude posted the correct salary-free sentence but omitted its required reference line from that comment, placing the reference in a separate completion message. The `public-welcome-note` check correctly failed. An earlier Claude database-startup failure was retained separately; its fresh-instance retry reached the model. This pilot is not a six-cell qualification. - The failed Codex scope case omitted `addresseeUserId`. The strict routing check remains. All 18 attempts had clean evidence manifests and passed cleanup. - To repeat with provider credentials: `pnpm test:e2e:runner -- --suite blocker-guidance --max-parallel 1`. This is a paid, opt-in suite and is excluded from `--all`. ## Risks - The live suite measures variable model behavior. The retained 17/18 historical result and the current 1/2 scope pilot are not all-pass qualifications. These paid cases are opt-in; their observed model failures remain visible independently of deterministic CI checks. - A separate generic task-replacement diagnostic still exposed a Claude refusal. The ordinary cases use specific business decisions. The diagnostic is not a standalone catalog case in this change. - Earlier measurements included an old installed Claude skill and test defects. Their grades remain retained and are not combined with the three final repetitions. - Skill examples can affect when agents ask for human input. Downstream permission checks still apply. - Native runners, Daytona, agent-requester routing, and real external connection authorization are outside this suite. - Raw provider traces and credentials remain private. No screenshots, raw reports, secrets, workflow changes, or lockfile changes are committed. ## Model Used OpenAI GPT-6 through Codex assisted with this change. The exact deployed variant and context window size are not exposed in this session. The assistant used reasoning, repository edits, tool use, and shell execution. The evaluated models were `gpt-5.6-sol` and `claude-sonnet-4-6`. ## 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>	2026-09-30 07:56:54 -05:00
DottaandPaperclip	f4f9a7c613	test(runner): guard continuation after journals exceed 2 MiB (#14312) ... Add an actual runner resume regression above the former 2 MiB journal boundary and an explicit-only three-turn Daytona workflow that grows real execution history. Verify journal size and distinct completed tool calls without exporting private payloads. Co-Authored-By: Paperclip <noreply@paperclip.ing>	2026-09-30 07:01:45 -05:00
DottaandPaperclip	fc36d1ccd3	test(e2e): qualify large Daytona Git workspace continuation (#14316) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - A task can keep one agent process and workspace across human review turns. > - Large workspaces must survive each transfer between Daytona and the host. > - Small fixtures do not cross the previous 32 MiB filename-output limit. > - Correct files alone do not prove that finalization and recovery have settled. > - This pull request adds an explicit three-turn test with 60,000 files and independent host checks. > - The test detects lost files, replaced processes, and stale finalization retries. ## Linked Issues or Issue Description Refs: #14253, #14314, #14315, #14402, #14420. This test covers the workspace Git streaming fix in #14253 and the Daytona archive validation and native finalization fixes consolidated from #14315 and #14314 into #14402. These runtime changes are merged into master. This PR adds regression coverage. ## What Changed - Add one explicit-only native Codex Daytona test. Broad matrix runs do not select it. - Create 60,000 small untracked files through ordinary provider execution. Independently check all host file contents and the 39,828,890-byte filename manifest after each turn. Each continuation changes all generated file contents, so stale host copies fail. - Check spaces, newlines, leading hyphens, Unicode, and glob characters in filenames. - Require committed native finalization, successful workspace receipts, no active transfer or runless cleanup, and no scheduled recovery before each continuation and after the final turn. - Use a fixed external instruction bundle so the same runner PID and process identity can continue across the three browser-driven turns. Managed agent folders intentionally stop the process for file collection after #14420. Set the 20-minute idle window on the environment, then verify the admitted policy on every run. Set a 25-minute Daytona auto-stop window for this large-file test. - Save public workspace-operation evidence when an E2E attempt fails. - Bound this large-file fixture to 15 minutes per turn and 50 minutes total, reserving five minutes outside the turns for setup, host verification, and cleanup. A measured CI continuation succeeded in 11 minutes 5 seconds, exceeding the ordinary warm fixture's 10-minute deadline. The ordinary fixture and all file, process, finalization, and cleanup assertions remain unchanged. ## Verification - Final PR head: `b7eed5517426507f5d7912edb8ae49163d1783b0`. - `pnpm test:e2e:runner:unit` — 56 files and 708 tests passed locally. The catalog retains all 407 existing cells and adds this one explicit-only cell. - `pnpm test:e2e:runner:typecheck` — passed locally. - [Final-head CI](https://github.com/paperclipai/paperclip/actions/runs/36640920233) — all gates passed, including repository typechecks, tests, build, browser suites, and canary dry run. The PR has 54 successful checks and two expected skips. Fresh Greptile reviewed all seven files at 5/5; all review threads are resolved. - [Live single-cell Daytona verification](https://github.com/paperclipai/paperclip/actions/runs/36637283902) — passed on the first attempt in 1,822,299 ms (30m 22s) on `227074b7b`, using native Codex `gpt-5.6-sol` and the verified Daytona image. All three turns independently verified every one of the 60,000 file contents, 39,828,890 filename bytes, and five unusual names. All runs committed with one stable runner PID/process fingerprint, native/provider sessions, runner instance, and sandbox. Final browser/download assertions, all nine matchers, explicit cleanup, and report publication passed. Results are published through the [Product E2E history](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/) and [eval hub](https://pages.paperclip.ing/evals/). - The final `b7eed5517` follow-up only extends the total allowance from 45 to 50 minutes, updates its catalog assertion/version, and documents the setup/cleanup margin. Per-turn limits and behavioral assertions are unchanged from the successful live run; that paid run was not repeated for this allowance-only follow-up. - The [first integrated-head live attempt](https://github.com/paperclipai/paperclip/actions/runs/36632127364) is retained: turn 1 passed, then turn 2 hit the old 10-minute deadline while finalizing. Its trace records successful completion after 11m 5s and successful cleanup. Process diagnostics also showed the intentional managed agent-folder stop boundary introduced in #14420. These observations motivated the larger turn budget and fixed external instructions. - The broad local `pnpm test:run` began alongside the build and encountered server setup and port-test failures. The affected setup suites and assertions passed on focused reruns after the build, using canonical macOS temporary paths where needed. The redundant broad local run was stopped; full-suite success is established by final-head CI, not by that local run. ## Risks - The live test makes provider calls and creates a billable Daytona sandbox. It runs only when explicitly selected and deletes its sandbox during cleanup. - The test creates 60,000 files and can take several minutes per transfer. Its longer retention window applies only to this fixture. - The test will fail on a runtime that does not include all three required fixes. ## Model Used OpenAI GPT-6 in Codex assisted with code, terminal tools, and test analysis. The exact serving model suffix and context-window size were not exposed to this task. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>	2026-09-29 17:49:36 -05:00
DottaandPaperclip	83076d7e7c	feat: return completed handoffs to Agent Chat (#14408) ... Return completed Agent Chat handoffs through a durable outbox and scope each generated update to its supplied tasks. Add recovery, browser delivery, result access, and calibrated quality coverage. Validated with two consecutive ten-case Claude/Codex campaigns, all CI checks, and a 5/5 review. Co-Authored-By: Paperclip <noreply@paperclip.ing>	2026-09-29 10:25:52 -05:00
DottaandPaperclip	3f4f8b37ba	fix: grade Codex clarification and refusal outcomes from evidence (#14570) ... Grade clarification lists, obsolete unstarted wakes, and refusal cancellation from persisted evidence. Preserve execution and ownership assertions, add boundary regressions, and version the affected eval definitions. Co-Authored-By: Paperclip <noreply@paperclip.ing>	2026-09-29 09:40:55 -05:00
DottaandPaperclip	24beb00575	feat(runner): add rich ACP transport and durable interaction foundation (#14430) ... Add shared rich ACP transport, durable questions and permissions, verified provider packaging, and bounded activity and plan presentation. Keep Cursor, Copilot, and Pi pending their separate provider qualification. Persist interaction settlement before publication, fence failed writes until fresh recovery, and preserve owned-process cleanup. Incorporate reviewed mainline integration with extended harness coverage. Co-Authored-By: Paperclip <noreply@paperclip.ing>	2026-09-29 08:56:21 -05:00
DottaandFry	3ca196b0a6	feat(agents): persist agent files across tasks without revision history (#14420) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - An agent needs personal files across tasks and sessions. > - AGENTS.md is one file in that directory. Supporting files need the same persistence. > - The Instructions Editor and agent runs must share one current directory. > - Concurrent runs should apply only the files they change. The last sync of the same file wins. > - This pull request uses existing file transport and removes temporary copies after sync. > - Old instruction-only sessions keep their restore contract. New saves do not create revision history. ## Linked Issues or Issue Description Refs #14325. This replaces its revision-oriented design with persistent agent files. Keep #14325 unmerged. Transport prerequisite #14416 merged first at `d172197117a14b80a1eb2d2835a0e7cce2679656`. This PR now targets master and remains below 100 changed files. Related work: #4513 and #8798 cover instruction tooling. This change handles run synchronization, cross-task personal files, browser editing, and old-session restoration. ## What Changed - Keep one current directory per company and agent. Point AGENT_HOME at a temporary working copy for each active run. Keep task files and provider HOME separate. - Restore text, binary files, and nested folders through workspace transport. Exclude remote agent files from task Git snapshots with a self-ignoring file inside the reserved runtime directory; never write through repository-controlled Git metadata. - Collect after the provider and child processes have stopped. Keep resumable conversation state. - Apply changed and deleted files under the agent lock. The last sync wins for the same file. Unrelated concurrent changes survive. - Remove temporary copies after successful sync, rejected sync, and staging failure. Register ownership before copying so restart recovery can remove interrupted preparation. Retry transient synchronization up to three times. Preserve the original remote lease reference until deletion succeeds; restart cleanup never acquires a replacement sandbox. Do not create captured directories or a conflict-review queue for new runs. - Keep browser editing, stale-draft protection, and streaming binary downloads. Keep the instruction entry and text editor limited to 1 MiB. - Keep historical agent-folder sync failures on their affected runs instead of repeating them above current saved instructions. Preserve legacy candidate review and current browser-save errors. Avoid duplicate quota warnings while retaining separate sync failures when they describe a different problem. - Require target-scoped caller grants for peer instruction access, while preserving self edits, responsible-user checks, and protected-change consent. - Treat full storage as a nonblocking run warning, never an agent pause or run-admission failure. Restore already-over-quota saved folders so ordinary agent cleanup can recover; warn on each run until cleanup. The run detail view shows the warning. - Allow 256 MiB per file, 2 GiB per directory, and 100,000 entries. Hash large files as streams. Check editor-save quotas with metadata instead of hashing unrelated files. - Preserve old native inputs, instruction-only copies, paths, digests, and pending legacy candidates. Adopt old revision heads once. New writes do not append history rows. - Add idempotent migration 0287 and verify upgrades from the preview tables and receipts. - Add nine interactive stories under **Agents / Persistent files**, including automatic incoming edits, stale browser drafts, and storage-limit diagnostics. ## Verification - Merge candidate: `4f5390107ec6ffd80a76d1d2e85530e66f21d079`, after merging current master and the landed transport prerequisite. Integration required no manual conflict resolution; the feature remains 99 changed files. Full workspace typecheck, production build, token gates, and 715 focused tests passed on this merge candidate. Fresh Greptile review is 5/5 with no unresolved findings. All 55 checks passed, with four conditional skips, including the build, typecheck, browser E2E, and canary dry run. A single retry recovered four jobs interrupted by runner shutdowns; no source changes were required. - Historical-warning UI fix: all 6,834 UI tests across 640 files passed, including regression coverage for three old failures, legacy preserved edits, and warnings scoped to the affected run. Full workspace typecheck, production build, Storybook build, and token gates passed. Browser-verified Storybook playtests passed for Historical Failures After Successful Save, Storage Limit, and Full Storage Run Warning. - Review follow-ups at `4e20c9fb2`: all 18 focused tests passed, including external Git directories, linked worktrees, symlinks, hardlinks, and distinct I/O failures alongside storage warnings. Server and UI typechecks, token gates, and the production build passed. - Storage warning regressions at `0724f3012`: all 33 directory tests and all five heartbeat-list tests passed, with no skips in their successful runs. They cover repeated runs while full, an already-over-quota saved folder, cleanup, warnings retained after unrelated save failures, and bounded warnings in large result JSON. Server typecheck passed after the final warning fixes. - Full workspace typecheck, production build, and token gates passed during this follow-up. Product E2E harness: 631 tests passed across 52 files; harness typecheck passed. Earlier native session/context and directory/legacy collection suites passed 537 tests; Runner unit/transport suites passed 329 tests. - **Real E2E at `0724f3012` (before this follow-up):** legacy local Codex and native Daytona Codex each passed six tasks, one server restart, seven independent assertions, and cleanup verification. Both prove browser-to-agent edits, agent-to-browser edits, nested/binary restoration, per-file last-sync-wins, a successful run after an oversized save rejection, and cleanup clearing the warning. - Native local Codex also passed the six-task quota flow before the final warning-retention fixes. That pass began at `918d1ed02` while the bounded-result warning fix was being edited, so it is not claimed as exact-final-head evidence. Its final-head rerun failed during embedded PostgreSQL bootstrap before any provider run: the macOS host had 87,365 of 87,381 SysV semaphores occupied. No unrelated services or kernel limits were changed. - The final-source report intentionally records **2/3 cells passed**, preserving the blocked native-local attempt: `tests/runner-e2e/results/agent-files-quota-final-20260928-report/`. Earlier failed attempts and provenance notes remain under `tests/runner-e2e/results/agent-files-quota-final-20260928-input/` and the original campaign directories. - Daytona used immutable image `ghcr.io/paperclipai/paperclip-daytona-runner@sha256:5643f0d801417cae3581833a1a3bc6715b325e028602738d2652c44cac5dc6bf` and its exact Linux runner binary. Controller source is `0724f3012`; image source is recorded separately. - Legacy-session compatibility and all three ACP Stop/resume browser regressions passed on the prior validated feature head `169fab46d5af21caa2269b4c1b29b69c933a6951`. They assert the same provider session is retained and interrupted writes are not replayed. Migration upgrade tests also passed earlier. - Nine interactive stories are under **Agents / Persistent files**, including **Full Storage Run Warning**. Its playtest and visual browser inspection passed; the warning states that runs continue and the editor remains available. - Prior-head checks on `4e20c9fb2`: 55 passed, two conditional jobs skipped, no failures or pending checks. All eight browser E2E shards and their aggregate passed. Fresh Greptile review is 5/5 with no findings; all review threads are resolved, the security scan passed, and GitHub reports no merge conflicts. - The broad local follow-up test run was interrupted after host semaphore exhaustion affected isolated PostgreSQL instances. It also encountered the existing macOS long-path fixture failure and two timeout failures. This is not a claim that the full local suite passed. Logs are retained; focused storage/warning tests passed. ## Risks - A later sync can overwrite an earlier edit to the same file, including a saved browser edit. There is no text merge or retained version. This is the intended last-sync-wins policy. - A save that exceeds a storage limit is rejected and its temporary copy is discarded. The run itself continues normally, and later runs restore the last saved files with a warning until cleanup. Transient sync failures get bounded retries. An I/O failure partway through a sync can leave some files updated; a failed receipt does not claim whole-folder success. - Larger folders increase copy time, network traffic, and temporary disk usage. Active runs still need working copies. Terminal runs do not accumulate archives. Operators must provision disk for agents and configured concurrency; these limits are not company-wide quotas. - A restored old native session remains instruction-only until a fresh session starts. Its original conflict fence and existing pending candidates remain compatible. - Provider processes close at the collection boundary. Conversation resume remains available, but warm process reuse is lost. - Backups must include the instance filesystem and database. External bundles keep their existing behavior until explicitly moved to managed storage. ## Model Used OpenAI Codex, GPT-6 family. The session does not expose a more specific model ID or context-window size. Reasoning, code execution, and browser tools assisted this change. Real provider E2E uses `gpt-5.6-sol`. ## 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: Fry (Paperclip) <noreply@paperclip.ing>	2026-09-29 08:25:56 -05:00
3 people	0be2afcca6	feat(ui): improve task composer controls and pending input (#14322) ... ## Thinking Path > - Paperclip lets operators assign tasks to AI agents and review their work. > - The task composer controls the next message and its assigned agent. > - Operators needed a way to choose that agent's model and effort without leaving the composer. > - The old mode selector, upload button, and input cards made the mobile composer crowded and hid normal messaging during a pending decision. > - Harnesses publish different model and effort capabilities, so the picker must follow the selected agent. > - This pull request adds one responsive composer flow, keeps pending cards visible above it, and protects Codex ACP authentication in the local test path. > - Operators can choose run settings, send a message, and answer a pending card as separate actions. ## Linked Issues or Issue Description **Subsystem affected** Task composer UI, issue thread interactions, Codex ACP credential handling, and Storybook. **Problem or motivation** The composer did not expose model or effort for the selected agent. Mobile actions wrapped poorly. Pending questions and confirmations replaced the composer. A local Codex ACP test could also reuse host authentication after the managed key was removed. **Proposed solution** Put assignee search, model search, exact model IDs, effort, and fast mode in one picker. Use a mobile dialog. Replace the direct-upload plus action and separate mode selector with an Add menu and removable Plan or Ask chips. Place pending interaction cards above the usable composer. Keep these cards pending after an ordinary message unless their creator asks for comment superseding. Replace managed ACP auth files atomically and isolate the test key from host credentials. **Roadmap alignment** ROADMAP.md does not list an overlapping composer milestone. This change improves the existing task and review flows. ## What Changed - Added the combined assignee, model, and effort picker to both task composers. Search matches agent name, role, and harness. The server uses a curated Codex list by default and honors instance-declared models. Manual IDs remain available. - Added an effort slider for known model capabilities, a conditional Codex fast control, and reset. The picker opens in a modal on mobile. - Added the Add menu for files, supported goals, Plan mode, and Ask mode. Plan and Ask are exclusive removable chips. Keyboard mode cycling remains available. - Adjusted mobile spacing, avatars, wrapping, and Send placement. Removed the composer divider. - Moved pending question, confirmation, review, and related cards above the composer. Ordinary comments now leave question and confirmation cards pending by default. The onboarding prompt retains explicit comment superseding. - Updated the Storybook composer group with responsive states and the production picker. Added UI, service, route, and browser regression coverage. - Isolated Codex ACP API-key authentication, skipped subscription auth merge and shared-home copy-back for remote API-key runs, and replaced the managed auth file atomically. ## Verification - `pnpm -r typecheck` — passed on the final local head. - `pnpm check:token-gates` — passed on the final local head. - `pnpm exec vitest run server/src/__tests__/adapter-models.test.ts ui/src/components/task-chat/ComposerRunSettingsPicker.test.tsx` — 31 tests passed, including role and harness search, declared Codex models, and filtering general OpenAI models. - `pnpm exec vitest run server/src/__tests__/issue-thread-interactions-service.test.ts` — 74 tests passed. - `pnpm exec vitest run packages/adapters/codex-local/src/server/acp.test.ts` — 42 tests passed, including remote API-key copy-back isolation. - `pnpm test:run` — attempted locally; the embedded PostgreSQL test database could not initialize on macOS. The isolated `heartbeat-run-event-sequencing` suite reproduced that environment failure. GitHub CI runs the full test matrix for this head. - `pnpm build` — passed on the final head. `pnpm build-storybook` passed after the last UI change; only server code, tests, and docs changed afterward. - Live local test drive — Codex ACP ran a task with a managed API key. The test agent was restored to its default ACP configuration afterward. - Review the interactive stories under the top-level Composer group with `pnpm storybook`. Check a narrow desktop width and mobile Plan, Ask, picker, and pending-question states. ## Risks - A pending card stays open when an ordinary comment changes the discussion. Its creator can set `supersedeOnUserComment: true` when a new comment should replace it. - Model and effort overrides persist on the task until reset or changed. An unlisted manual model ID may fail when the provider runs it. - Some harness catalogs do not report effort support. The picker hides effort for those models. - No database migration is required. > For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and discuss it in `#dev` before opening the PR. Feature PRs that overlap with planned core work may need to be redirected — check the roadmap first. See `CONTRIBUTING.md`. ## Model Used OpenAI GPT-6 via Codex. This runtime does not expose the exact model ID or context window to the task. The model used code execution and browser tools. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [ ] 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> Co-authored-by: OpenAI Codex <codex@openai.com>	2026-09-28 23:02:39 +00:00
DottaandPaperclip	18e8c121d9	fix(runner): include Grok support in public installs with sandbox prerequisites (#14024) ... ## Thinking Path > - Paperclip manages agents through a shared native runner. > - Built-in harness support should ship with Paperclip's public distribution. > - Grok already speaks ACP; it does not require a new public bridge package. > - Sandbox provisioning owns the native executable and its pinned version. > - The runner must verify that prerequisite without downloading it during npm installation. > - This change separates built-in launcher identity from external runtime identity. > - Clean npm installation and live staging checks verify the distribution boundary. ## Linked Issues or Issue Description Refs #13882, #13973, #13977, #13979. This follow-up now targets master after #13882 was squash-merged. It replaces the private `@paperclipai/grok-acp` workspace package with runner-owned assets. Current master is included so the branch also contains the merged scheduler, complete-event capture, and durable cleanup fixes. ## What Changed - Ship Grok launcher and qualification metadata inside the runner's compiled output and the public server's vendored runner tree. - Remove the separate Grok npm package and all package-manager install hooks for this runtime. - Require the checksum-verified Grok Build 1.0.13 binary at `/opt/paperclip/providers/grok/1.0.13/grok` in the selected execution environment. Provision it explicitly in the Daytona image and CI setup. - Keep native binaries outside the provider pack. Bind the built-in launcher into the pack manifest. - Preserve executable leases, descriptor-backed startup, credential fences, permissions, and exact ACP model admission. - Use `builtin:grok-acp` and `native:grok` as profile identities. Historical package-profile sessions fail closed on resume rather than being silently reinterpreted. - Resolve built-in assets from the authenticated sidecar location, including public server npm layouts. Keep the controller path out of provider environments. - Add clean npm tarball installation verification to the existing trusted canary CI job and the admitted manual EC2 verification path. It stages a unified release version and runs npm lifecycle scripts, then verifies missing-prerequisite rejection and admission after separate provisioning without credentials or inference. - Include the controller-owned provider pack in stamped Cloud images. Unstamped local images omit the pack and remain usable; remote ACPX requires full source provenance. - Correct CLI approval-page metadata for an already authenticated Cloud board user; approval authorization remains unchanged. - Honor explicit native-runner enablement in the Cloud agent picker and direct setup page, keeping the flag disabled by default. - Allow selecting the execution environment before connecting credentials. Include Grok in the existing authenticated hello-probe flow, targeting its pinned native prerequisite for runner setup. - Recover an existing subscription sign-in conflict through an explicit cancel-and-retry action, serialized after cancellation succeeds. - Preserve the selected ACPX harness before normalizing config fields, so new Grok agents use the Grok default model. - Keep the credential-free Cloud provider pack root-owned and readable after runtime UID remapping; verify manifest and referenced asset access under an unrelated unprivileged UID during image builds. - Archive prior failover backups alongside explicitly replaced harness state, preserving evidence while preventing stale backups from blocking a fresh replacement. - Update Daytona image content inputs and contract tests for the built-in assets and explicit provisioner. - Document and regression-test the shared `approve-all` default for Grok setup, saved configuration, and native execution. Explicitly saved restrictions remain unchanged. ## Verification Current merge-repair head `df09eb3e1a619430ad8419a0ee9aedd486689b05` incorporates master `f1a394bd30cb56fb9e479f98b9f50176fe921858` after the base PR was squash-merged. All 12 conflicts came from incoming files identical to the tested pre-squash base. The final tree exactly matches a three-way merge using that original base, preserving built-in Grok distribution and removal of the obsolete private package. All 252 focused runner/UI tests, six npm-isolation tests, and token gates pass. Fresh exact-head Greptile review is 5/5 with no outstanding findings; security scans and EC2 native compilation pass. All current-head CI is green: 56 successful checks/statuses and four intentional skips ([run 36468768035](https://github.com/paperclipai/paperclip/actions/runs/36468768035)). The repository owner explicitly authorized bypassing code-owner approval after all checks passed; no CI checks or repository protection settings are bypassed or changed. The only remaining PR was removed from the completed stack metadata to permit native auto-merge. Earlier integration head `78cb306ecc41b5c96577c26c1d89153b0ef865a1` includes master `3447609d2247e75e55d91493dda91a608364f672` (2026-09-28). Two master advances during verification overlapped the eval catalog; the final merge preserves Grok qualification, completion updates, and bounded API-response reading in all 348 cells. All 77 focused catalog/eval/workflow tests pass. Both native stack layers (#14397) are mergeable, and both exact-head Greptile reviews are 5/5 with successful security scans and no unresolved review threads. All current-head CI is green: 56 successful checks/statuses and four intentional skips ([CI attempts](https://github.com/paperclipai/paperclip/actions/runs/36447124691)). The initial attempt lost two EC2 runners to shutdown signals and stalled a third shard during dependency preparation; all three passed the same-commit failed-job-only retry. Trunk code-owner requirements remain enforced. The review summary’s non-blocking saved-asset offset classification note concerns code already merged in #14301; those runtime files are identical to master and outside this stack’s diff. Historical live evidence below retains its original source revisions. [Final public npm verification](https://github.com/paperclipai/paperclip/actions/runs/36445542764) passed on `76ea70cd4d13786a042af9df82f0fd7a8c85ae30`: 17 public packages, an executed offline lifecycle sentinel, unchanged consumer lock, built-in launcher, missing-prerequisite rejection, and verified separately provisioned binary/command lease. Provisioning and cleanup require no host privilege elevation; only the positive probe mounts the temporary native binary read-only. The verifier is unchanged by the final master merge. All six isolation tests and an offline npm smoke test pass. The prior head had 56 green CI checks and a 5/5 review after two unchanged tests timed out and passed a failed-job-only retry ([CI attempts](https://github.com/paperclipai/paperclip/actions/runs/36444597313)). All 56 recovery-display/lineage tests pass; re-review cleared the already-covered missed-retry concern. Earlier EC2 failures remain retained: [npm lockfile rejection](https://github.com/paperclipai/paperclip/actions/runs/36436311203), [missing compiler in the slim image](https://github.com/paperclipai/paperclip/actions/runs/36440210984), and the aggregate 15-minute test timeouts in those broad runs. Both broad attempts passed typecheck, token gates, Product E2E type/unit checks and build. The focused EC2 lane preserves the existing trusted-actor and immutable-source gates. Earlier documentation/test checkpoint `ff244c4fd78a7ede5a3e00efe09f475f133ef33e` leaves runtime behavior unchanged. 154 focused tests pass across configuration building, native provider resolution, permission policy, credentials, UI configuration, and new-agent setup (including both Grok auth modes); token gates pass. All fresh CI is green for this head: 56 successful checks/statuses and two intentional skips ([run 36367065119](https://github.com/paperclipai/paperclip/actions/runs/36367065119)). Greptile is 5/5 with no new findings. Grok already inherits the shared `approve-all` default, so unattended setup requires no manual permission change. Runtime head `bb5a9307991f1ac567b781970ef11b39d518e19b` fixes a final staging continuation failure before provider startup: explicit replacement archived the old harness but left its failover backups active, which caused `runner_harness_state_mismatch`. The regression fails before the fix and passes after it; all eight adjacent recovery-safety cases also pass. Old backups remain inspectable inside the continuity archive. All fresh CI is green at this head ([run 36360839248](https://github.com/paperclipai/paperclip/actions/runs/36360839248)), with a 5/5 review. One unrelated Cursor test timed out in the initial server shard; the same-commit failed-job rerun passed, and both attempts are retained. Staging deployment is confirmed healthy on this revision. The controller image is `ghcr.io/paperclipai/paperclip@sha256:6ad91c487910ccd2596ff7aed0a3a3ea5233d12b51b83cd6e1402237749b9673`. The final browser-created staging task passed on this exact revision with API authentication: context read → structured human question → controller restart → answer submission → same native provider session resumed → document saved → task Done. The two turns took approximately 119s and 77s. The actual write receipt was applied, and the saved document has exactly one revision containing the selected answer and requested marker. Usage and cost were not reported. [Controller image build](https://github.com/paperclipai/paperclip/actions/runs/36360889243). - Previous integration head `a44f7dbb6b6f77cd9ed893756ca453307f281e5f`: all CI green (53 successful checks/statuses, two intentional skips), including repository typecheck/build/tests, native Runner tests, browser shards, and canary installation checks. [CI run 36358672529](https://github.com/paperclipai/paperclip/actions/runs/36358672529). Greptile is 5/5 with no unresolved findings. - Focused checks cover Grok credentials, executable admission, launcher assets, provider-pack paths/permissions, workflow contracts, setup defaults, CLI authorization, and subscription conflict recovery. All 39 protocol definitions validate. Final integration checks pass 124 catalog/evidence/cache tests and nine project-form tests; token gates pass. Some local dependency checks could not load the stale installed dependency tree; the corresponding fresh EC2 checks pass. - Clean public npm installation passed on EC2 at `8b172ebcf8e02e30662d830c00f3961e3bd459ec` ([run 36164964900](https://github.com/paperclipai/paperclip/actions/runs/36164964900)): 17 unified-version packages, lifecycle scripts enabled, built-in launcher present, no separate Grok package or npm-downloaded binary, missing prerequisite rejected, separately provisioned native executable and command lease verified. No credentials or inference were used. Subsequent changes preserve this npm asset layout. - The immutable Daytona prerequisite image is `ghcr.io/paperclipai/paperclip-daytona-runner@sha256:98957d5be0ac774d086b6402b5849e8e6356fec70fb8c09fca6eb4ed6de918e0`, built from `5a2db471f3ddabe77f9f80e76ed27f996cb97fba`. The previous Cloud controller image was `ghcr.io/paperclipai/paperclip@sha256:fd914e1ab1e45f741e8e078ff452d16f082d7ac05f9b4b3506d3a3c64150d204`, built from `a44f7dbb6b6f77cd9ed893756ca453307f281e5f`; it is superseded by the latest image above. Its EC2 build verified provider-pack access under an unrelated unprivileged UID. - Browser staging at `40f898bc4cba73c1dff4e6344a3983ba0fb247ef` passed full Grok onboarding with the correct `grok-4.7` model, saved credential delivery, and pinned Daytona execution. A browser-created task read context and asked the structured human question. After a controller restart, answering the persisted question resumed the same native provider session, saved the requested document, and completed the task. Actual tool outcomes and durable state agree: one question and one document revision. The two successful turns took 42.7s and 63.1s; usage and cost were not reported. - Restricted policy returned the expected `approval_required` outcome. Functional staging tests explicitly selected `approve-all`; controller authorization and governed approvals remain enforced. Temporary board CLI access was revoked and verified rejected (HTTP 401), and the disposable onboarding agent was paused. Failures remain retained: the pre-fix continuation failure (its task remains blocked; the passing final task is fresh), the original Cloud provider-pack permission failure, the expected restricted-policy denial, the superseded npm staging failure, and an earlier monolithic CI infrastructure timeout. Browser CI exposed a project alias/form race; the final stack uses master's stronger draft-preservation fix and all browser shards pass. Historical full subscription/API protocol and Product rosters retain their original source revisions and do not qualify this packaging revision. No local Docker or Rust build was used. ## Risks The branch includes master’s draft-preservation fix for project URL aliases. It keeps the same project’s edit form mounted and clears prior data when the project or company changes. Custom sandboxes and local execution hosts must provision the pinned binary before Grok starts. Missing, changed, unsupported-platform, and symlinked executables fail admission. The new builtin profile cannot resume sessions created with the former private-package profile. Existing Claude/Codex npm bridge profiles retain their package pins. Grok restricted modes preserve the selected policy but cannot automatically admit Paperclip calls: ACP permission metadata does not independently bind tool authority, so those calls stop with `approval_required`. New Grok configurations default to `approve-all`, including API configurations that omit the mode. Existing explicitly restricted configurations remain restricted; controller authorization and governed approvals remain enforced. ## Model Used OpenAI GPT-6 through Codex, with tool use and code execution. The exact serving model identifier and context-window size are not exposed in this session. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>	2026-09-28 14:54:44 -05:00
DottaandPaperclip	992f720262	fix: make runner task context ownership explicit (#13753) ... <!-- Write all pull request text in Simplified Technical English (ASD-STE100). --> ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Task descriptions, comments, continuation data, skills, and execution rules enter several agent adapters. > - The same source can be rendered by more than one automatic input carrier. > - Failed resumes can also rebuild input from stale or compact context. > - This pull request gives each Paperclip-owned source one delivery owner and preserves the required transport boundaries. > - It adds deterministic adapter, interaction, runner, and browser tests for these boundaries. > - The benefit is more predictable context delivery with explicit evidence for later live qualification. ## Linked Issues or Issue Description Related: #13144 removes a duplicate environment payload and bounds wake lists. Related: #11360 addresses Hermes resume behavior. This pull request preserves compatible active-session formats while repairing context ownership and stale question creation. **What happened?** Task descriptions and comments could enter more than one automatic context block. Native transports could wrap a complete model input in a second task envelope. Some legacy and gateway adapters could omit the owned assignment on ordinary tasks or rebuild a failed resume with stale compact context. A continuation could also request a question after newer human comments had arrived. **Expected behavior** Each task or comment source has one automatic model-facing owner. Distinct comment IDs and repeated wording remain distinct. Fresh fallback attempts rebuild the required full context. A question request is rejected when newer queued human direction makes it stale. Harness access policy remains owned by execution configuration. **Steps to reproduce** 1. Build a task with a description and current comments. 2. Capture the actual adapter or runner input. 3. Compare source ownership and task-envelope nesting. 4. Queue a human comment before a continuation requests a question. 5. Trigger a failed resume and inspect the fresh retry input. 6. Run the focused adapter, interaction, runner, and browser checks. ## What Changed - Add shared prompt-section selection at the provider-attempt boundary. - Deliver owned assignment context through native, legacy CLI, ACP, gateway, cloud, Pi, Kimi, Grok, Gemini, OpenCode, Cursor, OpenClaw, and Hermes paths. - Rebuild full or compact context after resume recovery changes the attempt. Add native and Claude ACP tests of actual recovery requests. - Preserve custom templates, loaded instruction files, execution policies, and older active-session formats. - Record continuation source metadata and reject stale question creation under the issue-row lock. - Add explicit Product E2E context-integrity profiles, prerequisite gates, credential-isolation checks, and report fixtures. - Bypass service-worker forwarding for same-origin Vite development modules. A real Chromium test fails with resource exhaustion before the repair and passes after it. Production asset caching keeps its existing policy. - Add browser diagnostics and service-worker module-loading regressions. - Add an explicit zero-retry eval option. The default retry behavior remains unchanged. Each campaign records its effective policy. - Remove the model-facing working-directory sentence from four prompt builders. Existing workspace, sandbox, permission, and custom-template configuration remains unchanged. - Align the everyday workflow assertion with the current 47-entry catalog. Compared with current upstream master, the branch carries the context-ownership implementation and its tests, the explicit context-integrity catalog and evidence harness, and the focused browser regression checks. ## Verification **Merge assessment:** focused regression evidence supports merge. This is not full completion of the original broad qualification matrix. The maintainer has authorized merge after fresh verification of the master integration. - Current head: `bbd52f82114eabf09bc7b1a7e97d54a5b43bbc00`. This integrates current master `2f585ef26a1814fa209715242d1ca791b63e4c4e`. All 14 conflicts are resolved. Cancellation checks, workspace finalization, native Grok support, and both sets of tests are retained. - Current-head Greptile: **5/5**, with no blocking findings. The review names this exact commit. All **59 reported checks are terminal: 55 successful, 4 skipped, zero pending or failing**. This includes the full root general and serialized suites, separate runner checks, typecheck, build, canary, browser E2E, Docker, and security checks. The successful legacy security status is included in that total. - After integration: workspace typecheck and full build passed. Separate runner checks passed: **2,160 TypeScript tests (10 skipped), 582 Rust tests, and 39 preparation checks**. Other passing checks include 621 Product E2E harness units, 376 focused shared/adapter tests, 160 real-database/API tests, 86 Hermes tests, 18 browser-support checks, and Product E2E typechecking. The complete root suite passed in CI. The duplicate local monolithic root run was stopped after that CI result; it is not counted as a completed local pass. - New native recovery coverage retains full assignment, completion contract, and explicit skill selection after safe replacement, for old and prepared input formats. Full native session test file: **136/136 passed**. - New Claude ACP coverage captures actual fresh, resumed, and missing-session fallback requests. It verifies one assignment copy, comment order, identical text under distinct comment IDs, and full fallback context. Full file: **33/33 passed**. Both affected TypeScript checks passed. - Existing deterministic tests cover source revisions, approval and trust boundaries, completion validation, custom templates, compatible sessions, standalone driver wrapping, and maintained adapter transport requests. - Provider-free browser support: **17/17 passed** after the master merge. Service-worker unit tests: **33/33 passed**. The module-overload regression failed before the repair and passed after it in real Chromium. ### Fresh live comparisons The new batch ran exactly four Product E2E attempts. **All four passed on the first attempt; no retries.** Each has six terminal matchers plus the existing browser lifecycle and invariant checks. | Exact case ID | Control | Candidate | |---|---|---| | `core-compatibility.runner-codex.local.plan-revise-accept` | Passed | Passed | | `local-session-integrity.runner-acpx-claude.local.structured-question-restart-resume` | Passed | Passed | The plan case checks a revised canonical plan and revision-bound approval before completion. The question case restarts the server before submitting the answer, then verifies the continuation completes. Control source is `dfa4e1bda8d50a1a01746603251a9128dbe9d0d6`. Candidate source is `79fcdb5dece501d28064ea9da306603881b46f0c`. They use identical frozen definitions and provider versions: Codex `0.156.0` with `gpt-5.6-sol`; ACPX `0.13.1` / Claude ACP `0.73.0` with `claude-sonnet-5`. The September 24 head added master browser recovery and test-only changes. The September 28 head also integrates newer master changes, including cancellation, workspace finalization, and native Grok. These are frozen-source live results, not exact-head live runs. The candidate received one description copy where the control initially received three. The submitted initial plan envelopes were 7,969 versus 19,097 characters. Question envelopes were 7,592 versus 18,919. These are structural measurements, not whole-provider token or dollar savings. ### Earlier evidence and failed attempts - The preceding fresh batch has four effective passing pairs: OpenCode comment continuation and assigned skill, native Codex comment continuation, and native Claude comment continuation. It retains **11 attempts: eight passed and three failed**. - Original failures remain recorded: missing local PostgreSQL library links before task creation; host-sleep cleanup after task/page checks passed; and a Claude **control** session-open rejection before a model turn. Setup was repaired identically on both worktrees. The permitted unchanged infrastructure retries passed. The underlying Claude provider startup error was not retained and remains unknown. - Older R2 retains **17 passes and one failure** across 18 attempts, including eight both-pass native/legacy Codex/Claude pairs. Its OpenCode blank-page failure led to the service-worker repair. R2 is historical evidence: master changed the native fixed prompt and removed duplicate wake environment data afterward. - The September 24 CI run initially failed one unrelated preview readiness test (`ECONNREFUSED` on its local fixture). Its test and production code match master. Isolated local verification passed **28 tests, 3 skipped**. One unchanged CI retry passed the full shard: **831 passed, 1 skipped**, including all **31 preview-exposure tests**. The aggregate CI gate passed afterward. The precise startup cause remains unknown; a port race is a hypothesis, not a proved cause. ### Limits The original wider profile/workflow matrix, repeated trials, and remote Daytona qualification are incomplete. These results support a focused merge recommendation, not statistical equivalence or universal harness qualification. Some usage receipts are missing in both variants, so no token or dollar savings are claimed. The $500 ceiling was preserved using conservative allowances; failed attempts and unknown charges remain in the ledger. Reproduce the focused additions with `pnpm exec vitest run packages/adapters/claude-local/src/server/acp.test.ts` and `pnpm --filter @paperclipai/paperclip-runner exec vitest run src/native-session-runtime.test.ts`. Full checks use `pnpm -r typecheck`, `pnpm test:run`, `pnpm build`, and the separate runner checks. Paid evals require the frozen definitions, profiles, and credentials; do not use `--all` as a substitute for the selected cases. ## Risks - Context placement changes can affect model behavior. Deterministic checks cover the selected paths, but live qualification remains incomplete. - The stale-question guard can reject a request when queued human comments arrived during the run. This is intended. - New stored inputs and model envelopes retain compatibility readers for older active sessions. - Custom templates may intentionally repeat content. - Removing a model-facing working-directory sentence does not change filesystem, command, sandbox, or permission configuration. - The worker bypass applies only to same-origin development module paths. Cache-policy tests preserve private-response handling and production asset caching. Mounted HTTP fixture changes remain test-only. - This PR does not claim measured token savings or statistical equivalence across every harness. ## Model Used OpenAI Codex, exact model gpt-6-astra, with repository tools and code execution. Bounded supporting work used gpt-5.6-luna and gpt-6-luna. The serving context-window size is not exposed in this task. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have described the issue in-PR using the required issue fields - [x] I have not referenced internal/instance-local Paperclip issues or links - [x] My branch name describes the change and contains no internal ticket id - [x] I have run the focused local checks and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect these changes - [x] I have considered and documented risks above - [x] All current-head Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups for the current head - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>	2026-09-28 14:49:14 -05:00
DottaandPaperclip	f1a394bd30	feat(runner): add Grok Build through native ACP (#13882) ... ## Thinking Path > - Paperclip manages AI agents and governs their work. > - Its native runner uses structured provider protocols for sessions and tools. > - Grok Build supports ACP over stdio, but the runner did not expose it. > - Native execution requires company-scoped credentials, verified identities, and permission gates. > - This change adds Grok through ACPX for local and Daytona execution. > - Subscription login and explicit API-key execution have separate credential paths. > - Qualification grades real tool outcomes, durable state, and browser workflows. ## Linked Issues or Issue Description Refs #13845, #13847, #13850, #13878, #13901, #13973, #13977, #13979. Add **Grok Build** to `paperclip_runner` with `provider: "acpx"`, `acpxAgent: "grok"`, and model `grok-4.7`. Existing legacy Grok agents keep their adapter. Merge the three companion fixes (#13973, #13977, #13979) before treating the integrated Product qualification as deployed behavior. ## What Changed - Synchronize shared, TypeScript, Rust, server, validation, and UI provider contracts. - Run Grok native ACP stdio through ACPX and the authenticated Paperclip MCP bridge. Verify the pinned executable and exact ACP model identity. - Prefer company subscription login. Support an explicit company-secret API key without automatic paid fallback. Fence refresh and copyback to the same account and remove private runtime credentials after containment. - Preserve selected permissions, cancellation, durable session identity, resume, and restart recovery. Keep unsupported steering and goals unavailable. Preserve missing usage and cost as unknown. - Package checksum-verified Grok Build 1.0.13 for Daytona with an immutable, signed image built on EC2. - Add deterministic admission, protocol, permissions, identity, credential, failure, and cleanup checks. Add the maintained 39-case protocol roster and separate subscription/API Product profiles. - Fix live-test findings in reasoning events, reloads, idle-owner retirement, credential-home cleanup, expired-login model discovery, launcher pinning, and rerun evidence selection. - Align control-plane state readers with the transport's 64 MiB bound while retaining identity, ownership, lifecycle, and size rejection checks. - Stabilize two asynchronous CI assertions while retaining actual outcome and filesystem-evidence checks. ## Verification Current integration head `f114948376056fe0b6b34c1496ae8667b59daa63` includes master `3447609d2247e75e55d91493dda91a608364f672` (2026-09-28). Two master advances during verification overlapped the eval catalog; the final merge preserves Grok qualification, completion updates, and bounded API-response reading in all 348 cells. All 77 focused catalog/eval/workflow tests pass. Both native stack layers (#14397) are mergeable, and both exact-head Greptile reviews are 5/5 with successful security scans and no unresolved review threads. All current-head CI is green: 56 successful checks/statuses and four intentional skips ([CI run](https://github.com/paperclipai/paperclip/actions/runs/36447097232)). Trunk code-owner requirements remain enforced. The review summary’s non-blocking saved-asset offset classification note concerns code already merged in #14301; those runtime files are identical to master and outside this stack’s diff. Historical live evidence below retains its original source revisions. Earlier integration checkpoint: `24fc9b94ca0afb21ccdc8d26dbb2e4b258ad72cb`. Refreshed against master `0f14d2612`, preserving Grok qualification alongside the new accounting and lifecycle suites. All 124 focused catalog, evidence, and service-worker checks pass. The current base workflow includes the explicitly selected public-install verification lane; follow-up #14024 supplies its verifier script. CI at that earlier checkpoint was green (56 successful checks/statuses, four intentional skips), and the review is 5/5 with no unresolved findings. Prior feature CI at `fd73f0a9b1ecdf4094685054028df71739ddc3e1` passed ([run 36148259902](https://github.com/paperclipai/paperclip/actions/runs/36148259902)); that is historical evidence, not a current-head result. Paid Product measurements use frozen integrated source `2d939a92b21dcaf5c77c88b54d96784d2ddd0699`, which combines the feature with #13973, #13977, and #13979. That source passed all 52 CI checks and clean 5/5 review. Later master syncs incorporate upstream changes. Their checks remain separate from these pinned live measurements. | Check | Result and source-pinned report | | --- | --- | | Subscription protocol roster | [39/39 first attempts; 206 assertions](https://d1p6rlowie26tp.cloudfront.net/runner-protocol-evals/campaigns/gha-36046839612-1/index.html), runtime `bc6833f7`, evals `92bb4b8c` | | API protocol roster | [39/39 first attempts; 206 assertions](https://d1p6rlowie26tp.cloudfront.net/runner-protocol-evals/campaigns/gha-35926577007-1/index.html), runtime `4a1061c8`, evals `3213dbec` | | Subscription full Product matrix | [16/16 first attempts; 144 assertions; cleanup passed](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-36096908572-1/index.html), source `2d939a92` | | Subscription core repetitions | 18/18: tool use, planning approval, and Stop/resume each passed three times in local and Daytona profiles. The full matrix contains repetition one; [repeat two](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-36104551060-1/index.html) and [repeat three](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-36108100404-1/index.html) each passed 6/6. Total: 28 unique subscription attempts at `2d939a92`. | | API smoke and question continuation | [4/4 first attempts; cleanup passed](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-36147315401-1/index.html), both environments at `2d939a92` | | Historical API Product coverage | [16/16 full matrix](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-35875144860-1/index.html) and 18/18 core repetitions at `4a1061c8`; retained as measurements of that revision | | Native Daytona proof | Three subscription and three API MCP/permissions/resume runs passed at `bc6833f7`. Three expired-login admission and fenced refresh checks passed without inference. All test sandboxes were removed. | | Inspectable artifacts and UI | Current-source screenshots verify planning approval, direct Ask completion, question continuation after controller restart, and two downloadable project revisions. The project downloads pass 12 and 18 tests; all 40 independent artifact oracle checks pass. | | Provider-free checks | 116 eval-validator tests, 39 Grok definitions, and 359 enabled/external campaign cells pass. Continuation regressions above 2 MiB and 16 MiB failed before their fixes; 32 focused recovery/ownership/size checks pass. | The 32 unique current-source Product attempts have no failures, retries, or skipped cells, and all cleanup checks pass. Whole-workflow timing, model identity, image and provider-pack provenance, attempts, and accounting coverage are retained in the canonical reports. The report publisher's conservative `complete=false` flag is preserved; independent audits verify the exact selected source catalog and immutable result rows. Pins: Grok Build `1.0.13 (5e9a58528b76)`, ACPX `0.13.1`, ACP model `grok-4.7`. Linux binary SHA-256: `edf79521581bb5e6b95abef848491a6a742e860da3e237ebe86a280d30dce4c1`. Launcher SHA-256: `f0b698395a3704ed2ffaf84ea19bdb20c36c8a0a70b7c629c7b6ffe144e59e55`. Image: `ghcr.io/paperclipai/paperclip-daytona-runner@sha256:76b24edfd850219e949418b19e4ceba690e84d51d199ade426e484953329b5e9`. Image build source is `4196a4cd`, recorded separately from application source `2d939a92`; each campaign verifies the image signature and provider pack. Original failed campaigns remain available: [continuation bound](https://github.com/paperclipai/paperclip/actions/runs/36057718059), [scheduler/event capture](https://github.com/paperclipai/paperclip/actions/runs/36071063537), and [startup cleanup plus EC2 interruption](https://github.com/paperclipai/paperclip/actions/runs/36080870743). They retain their original grades. No Docker or Rust builds ran on the developer laptop for these follow-ups. ## Risks Merge packaging follow-up #14024 with this base before public release. The follow-up replaces the private Grok bridge package with a built-in launcher and makes the native binary an explicit sandbox prerequisite. Three separate, reviewed fixes are part of the tested integrated behavior: #13973 serializes task-run admission; #13977 captures complete event evidence; #13979 durably reconciles failed Daytona creation. Each has green CI and clean 5/5 review. Failed-create recovery has 277 plugin tests, 92 SDK tests, host-runtime recovery tests, and a real Daytona lost-deletion-receipt proof. The live proof uses a private file for journal persistence; database durability is covered by host tests. Worker death before delivery of a failure envelope remains outside that recovery mechanism. Subscription fixtures stage an authorized company login; interactive browser sign-in is not qualified. Local Product profiles ran on EC2 Linux. The temporary subscription credential was removed from the protected GitHub environment after all subscription audits, with absence verified. Runtime homes and refresh copyback remain ownership-fenced. Protocol results remain pinned to their original revisions; they are not relabeled as tests of the latest feature commit. New binary/model versions require qualification. Missing token usage and model cost remain unknown; runtime estimates do not establish a full bill. Automatic paid Grok scheduling remains disabled pending separate reviewed enablement. The 64 MiB bound can increase memory use for verbose sessions, and larger files still fail closed. No automatic legacy-agent migration occurs. ## Model Used OpenAI GPT-6 through Codex, with tool use and code execution. The exact serving model identifier and context-window size are not exposed in this session. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>	2026-09-28 13:54:36 -05:00
DottaandPaperclip	3447609d22	fix(runner): stream and page large API responses within capture budgets (#14301) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Agents use governed API tools to inspect task evidence. > - Large API results become saved assets with short previews. > - Reading an asset through the same tool used to create another asset, so the agent could not reach the rest of the evidence. > - The 10 MiB response cap also blocked useful large results. Removing all bounds allowed excessive disk use. > - This pull request streams responses up to 1 GiB and makes saved text readable in bounded pages. It adds durable run budgets and capture admission limits. > - Agents can inspect complete evidence while tool results, memory use, and capture work stay bounded. ## Linked Issues or Issue Description **What happened?** A large response became an asset. Reading that asset returned another asset and the same preview. Responses above 10 MiB failed before the agent could read any page. **Expected behavior** The agent can fetch a large response and read its saved text to EOF. Each page stays bounded. New snapshots have a generous finite limit and a durable run budget. Existing larger assets remain readable through byte ranges. **Steps to reproduce** 1. Call a GET operation that returns more than 10 MiB of text or JSON. 2. Before the fix, the tool returns `api_transport_failure`. 3. With this change, responses up to 1 GiB become streamed snapshots with artifact references. 4. Read `GET /api/assets/{assetId}/content` with `responseText: {offsetBytes: 0, limitBytes: 8192}`. Follow `nextOffsetBytes` until null. Related work: #14186 added the API fallback tools. #14218 bounded API discovery. ## What Changed - Add authenticated UTF-8 text windows to `call_api`, with byte offsets and total size. Keep each page at or below 24 KiB. - Stream new responses above 24 KiB through private temporary files into company-owned assets. Bound each capture to 1 GiB of decoded bytes. Reject oversized declared lengths before reading and count streamed bytes before writing. - Reserve capture budget in the run record before spilling. Allow 4 GiB per run. Settle successful captures to their actual size. Failed or interrupted captures retain their full 1 GiB reservation. Run restarts do not reset the budget. - Enforce a 20 GiB company snapshot quota with database reservations. Count legacy snapshots and unfinished storage work across runs and processes. Asset deletion frees quota. - Limit large captures to two per company and four per server process. Hold slots through storage upload and temporary-file cleanup. Use a 10-minute download deadline and 30-second connection/idle-read timeouts. - Return explicit size, budget, busy, and timeout errors. Preserve unknown outcomes for mutations whose response cannot be captured. - Read saved assets through authenticated storage ranges, with at most two extra bytes for UTF-8 and EOF handling. Unpaged reads return the existing asset and digest with a bounded preview. Reads create no copies and do not consume capture budget. - Keep existing assets above 1 GiB readable in pages. Use safe integer offsets and PostgreSQL `bigint` asset sizes. - Stream large S3 uploads through ordered multipart requests. Abort failed uploads and remove partial local files. - Revalidate run authority during downloads. Keep company authorization, GET-only text paging, redirect denial, and mutation replay receipts. - Document the separate 10 MiB upload limits. This PR does not raise memory-buffered attachment ingestion limits. Future large video uploads need streamed ingestion and storage quotas. ## Verification - Full workspace `pnpm -r typecheck` and `pnpm build` pass after rebasing on master. - Focused API and response tests: 1,761 pass. Cover declared and chunked oversize responses, incorrect Content-Length, exact-limit success, active-stream deadline, cancellation, cleanup, concurrency admission, and mutation outcome handling. - Real HTTP integration: 28 tests pass, including runnerd → PRP → authority → HTTP, a 12 MiB snapshot, final-page/EOF reads, cross-company denial, a persisted 3 GiB sparse asset, and large mutation receipt replay. - The HTTP suite verifies durable run-budget accounting, simultaneous runs competing for company quota, legacy snapshot accounting, deletion refunds, failed-storage reservations, cleaned-failure refunds, metadata-rollback cleanup refunds, preservation after a lost commit acknowledgement, and small/saved reads after capture-budget exhaustion. - A standalone proof streams exactly 1 GiB through the production capture helper, verifies the final bytes, and removes its temporary file. It uses repeated 256 KiB chunks and records a peak process RSS of 191 MiB. - Earlier storage verification covers exact S3 multipart boundaries, cleanup/abort failures, and a 17 MiB transfer through the real AWS SDK to a local HTTP S3 endpoint. No cloud S3 qualification was run for this follow-up. - The local full test run was interrupted for the company-quota changes. A later targeted run hit exhausted macOS shared-memory slots before tests started; two unattached PostgreSQL segments with dead owners were reclaimed before retrying. All 55 current-head checks pass at `aebb80ceeeee77d5a56b67bfffd835f2f846878c`, including the full CI test suite, typecheck, build, browser suites, security scan, and Greptile (5/5). There are no unresolved review threads. The combined rebased test catalog also passes (48 tests). - Earlier paging acceptance passed Daytona and separate staging at `7739879e9`. Those runs predate the streaming and budget changes. ## Risks - The 1 GiB response cap and 10-minute active-download deadline are intentional product limits. Larger live results must use endpoint pagination or a direct file workflow. Existing larger assets remain readable through bounded ranges. - A durable 20 GiB company snapshot quota counts stored runner-api assets and active/orphan reservations across runs and processes. The operator can set PAPERCLIP_RUNNER_API_COMPANY_CAPTURE_MAX_BYTES to a finite value of at least 1 GiB. Deleting snapshots frees capacity; possible orphan storage must be reconciled before releasing its reservation. - A failed capture uses its full reservation. A new large capture needs a full 1 GiB available, even if it later completes at a smaller size. Small reads and existing asset pages remain available. - Concurrency limits apply per server process. The run byte budget is shared through the database. - The `integer` to `bigint` migration rewrites asset metadata and takes an exclusive table lock. File bytes stay in storage. - A live endpoint is fetched once before returning its snapshot. Continue reading the saved artifact for stable pages. Mutations may commit before any size or transport error; inspect state before retrying. - Attachment uploads and native file handoffs still default to 10 MiB. Raising buffered ingestion paths to GiB sizes is separate work. ## Model Used OpenAI Codex, based on GPT-6, with code execution and repository tools. The runtime does not expose an exact serving model variant or context-window size. The earlier paging work also used browser testing and subagents. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>	2026-09-28 10:36:32 -05:00
DottaandPaperclip	cea8dda472	test: evaluate completion updates after native task handoffs (#13969) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Users can delegate work through onboarding and Agent Chat. > - A completed task does not prove that its result reached the original conversation. > - Existing tests do not isolate completion after the source chat becomes idle. > - This pull request adds four explicit native-runner probes across Claude and Codex. > - The probes preserve the result and reply so we can separate delivery failures from inaccurate answers. ## Linked Issues or Issue Description Refs #13775. Refs #13813. These evals extend native-runner qualification. They measure completion updates before we choose a product change. ## What Changed - Add the opt-in `completion-updates` suite with two stories for each native provider. - Test completion in the existing onboarding task flow and after an Agent Chat handoff becomes idle. - Gate the chat worker on a brief inside its managed project workspace. Prove the source is idle before releasing the worker. - Check durable task completion, saved output, a subsequent source reply, and rendered access to the result. - Preserve replies, task state, screenshots, run events, and a separate semantic review rubric. - Add grader regression tests and update the documented eval contract. - Preserve the suites added on master and include four completion cases in the 306-cell catalog. Production behavior and prompts are unchanged. ## Verification - Passed all 565 eval support tests across 45 files after merging current master: `node node_modules/vitest/vitest.mjs run --config tests/runner-e2e/vitest.config.ts`. - Passed eval TypeScript: `node node_modules/typescript/bin/tsc -p tests/runner-e2e/tsconfig.json`. - Confirmed four selected cells: `node cli/node_modules/tsx/dist/cli.mjs tests/runner-e2e/launch.ts --list --suite completion-updates`. - Four-cell behavior campaign on source `ad47cf1da2b1e36f19f4227cfeb53998720b0b5b`: https://github.com/paperclipai/paperclip/actions/runs/36072337485. - A screenshot-only follow-up waits for the restored source reply to render after result-link navigation. Its one-cell Claude onboarding verification passed on final head: https://github.com/paperclipai/paperclip/actions/runs/36075716141. Corrected report: https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-36075716141-1/. The original four-cell onboarding screenshots caught navigation loading; its saved reply evidence remains valid. The follow-up again found stale wording: "That work will run next" was posted 38 seconds after the child was Done. The four-cell campaign keeps its original source and measurements. - Published evidence: https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-36072337485-1/. - Suite definition: `afba4d85d6c53d9f64c08b37a2e9cc20481b78f5bd7e2fa012045e2c69444d9d`, version 6. Models: native `gpt-5.6-sol` and `claude-sonnet-5`, local execution, one attempt per cell. All four cleanup checks passed. Onboarding billing coverage is partial; reported zero cost must not be read as a free run. | Story | Automated delivery/access | Separate semantic review | | --- | --- | --- | | Codex onboarding | Pass | Pass: accurate completion reply with an accessible result | | Claude onboarding | Pass | Fail: reply says it will save the note once the task runs, after the note is already saved and the task is Done | | Codex idle chat handoff | Fail | Worker completed and saved the note; no completion reply during the full observation window | | Claude idle chat handoff | Fail | Worker completed and saved the note; no completion reply during the full observation window | Both chat cases positively recorded the source waiting and the worker at the brief gate before release. Both saved outputs include the brief-only start time. The opt-in campaign is red because it exposes current behavior. It is not a required merge gate. The PR does not fix that product behavior. Semantic review is a recorded human/agent assessment of retained evidence; it is not an automated prose-quality judge. - Second campaign: https://github.com/paperclipai/paperclip/actions/runs/36071065098. Codex chat reached the idle boundary and completed its task, then received no completion reply during the full window. Claude onboarding again returned a stale handoff answer. Claude chat exceeded the prior 110-second handoff setup budget; this revision raises that bounded setup window to 180 seconds. - Retained baseline: https://github.com/paperclipai/paperclip/actions/runs/36069427676. Onboarding passed delivery/access for both providers, but Claude gave a stale handoff answer. Chat cases stopped at fixture problems; they do not establish a completion-delivery failure. This revision fixes the workspace path and competing reference requirements. - On the previous head `4023a2a3c28d45c9eb2c42d452ce99ffba5c7b73`, 54 PR checks passed and two were skipped, including typecheck, tests, and build. Broad checks ran in CI, not locally. That head received Greptile 5/5 with no unresolved findings. The unchanged mobile repository-settings browser test passed on one targeted retry after a detached/disabled Save-button timeout. - Merged current master in `9b4491e1f` and resolved the catalog-count conflict. Eval support tests and eval TypeScript pass locally. All individual CI jobs passed on this merge commit, including build, typecheck, server tests, runner checks, and browser shards. The final aggregate check also passed: 54 checks passed and two were skipped. Greptile reviewed this exact commit at 5/5 with no unresolved findings. ## Risks - These explicit probes can expose current product failures. They do not change the default paid test selection. - Mechanical delivery and result access do not establish answer accuracy. The preserved reply still requires semantic review. - A fixture failure before the idle boundary or worker completion cannot establish a completion-update failure. - The handoff setup window lasts three minutes. The worker brief wait is bounded at four minutes. The observation window lasts two minutes after worker completion. It retains later replies without erasing earlier accessible delivery. ## Model Used OpenAI Codex, GPT-6 (`gpt-6-astra`), with reasoning, repository inspection, code execution, and GitHub tool use. The runtime does not expose the context window size. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>	2026-09-28 09:58:14 -05:00
DottaandPaperclip	f2ed0b65c4	fix(runner): enable API tools by default (#14186) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - The native runner exposes tools for company tasks. > - API search and call tools cover operations without a dedicated tool. > - The current default hides these tools unless an operator sets an environment variable. > - This pull request enables the tools when that variable is absent. > - Operators can still disable the tools or restrict them to selected companies. ## Linked Issues or Issue Description Refs #13003, which added the guarded API tools. **What happened?** The native runner does not advertise `search_api` or `call_api` with the default server configuration. **Expected behavior** The tools are available without a special environment variable. Existing authorization checks still apply. **Steps to reproduce** Remove `PAPERCLIP_RUNNER_API_TOOLS_ENABLED` and `PAPERCLIP_RUNNER_API_TOOLS_COMPANY_IDS`. Create a normal runner authority. Inspect its tool definitions. **Paperclip version or commit** a6c4e7a. ## What Changed - Enable API tools when the server flag is absent. - Keep explicit disable, invalid-value rejection, company restrictions, and binding restrictions. - Test default tool definitions and run HTTP integration tests without the enabling flag. - Update operator and hiring documentation. The existing shared gate also controls `hire_agent`. - Use the same policy in the E2E evidence summary so an unset flag is not reported as disabled. - Isolate default-availability tests from operator environment variables. ## Verification - Red test: two new rollout policy assertions failed before the fix. - Focused policy, authority, and HTTP tests: 3 files passed; 41 tests passed, 2 skipped. The two runnerd transport cases require a Rust-built binary absent from this workspace. - Command: `pnpm exec vitest run server/src/services/native-runtime/runner-api-rollout.test.ts server/src/services/native-runtime/paperclip-runner-tool-authority.test.ts server/src/services/native-runtime/runner-api.integration.test.ts`. - Attempted `pnpm -r typecheck`: blocked by missing `cargo` in this workspace. - Attempted `pnpm build`: terminated at the 4 GiB memory limit. - Attempted `pnpm test:run`: stopped after memory pressure to run focused tests alone. - Repeated the 41 passing focused tests with an inherited disabled flag and a foreign-company restriction; test isolation passed. - `pnpm test:e2e:runner:unit`: 44 files and 543 tests passed. - `pnpm test:e2e:runner:typecheck` exceeded the workspace memory limit, including a retry with bounded Go memory settings. - CI results will be recorded before handoff. ## Risks - More native runs can discover API tools and the existing `hire_agent` tool by default. - The change does not remove company, run, mode, credential, lifecycle, or approval checks. - Explicit operator restrictions still take precedence. No database migration is required. ## Model Used OpenAI Codex agent. The runtime does not expose the exact model ID or context-window size. Used reasoning, repository tools, shell execution, and tests. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [ ] All Paperclip CI gates are green - [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>	2026-09-26 21:16:33 -05:00
DottaandPaperclip	96bf004a79	fix: use persisted state for lifecycle continuation and retry budgets (#13888) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Its control plane decides when a task can continue, wait, stop, or complete. > - Legacy continuation could change when an agent changed its wording without changing task state. > - Shared attempt counts also let repair and infrastructure retries affect each other's limits. > - This pull request uses persisted state and separate, bounded allowances for these decisions. > - If automatic repair stops, the task explains what happened and offers a guarded retry. > - Paired tests and real-provider evaluations verify that Stop, approvals, ownership, and spending limits remain authoritative. ## Linked Issues or Issue Description Related work: Refs #13761, Refs #11126, Refs #13610. These cover obsolete continuation dispatch and retry storms. Open and closed issues and PRs were searched for related lifecycle, continuation, and retry work. **What happened?** Legacy continuation depended on English wording and progress heuristics. Repair, failure retry, and productive continuation could consume shared counts. When bounded repair stopped, the task showed a technical recovery message without a clear next action. **Expected behavior** Persisted disposition and owned execution paths determine the next action. Missing disposition prompts bounded agent repair. Explicit work mode determines planning mode. Narrative changes and raw activity counts cannot replenish allowances. An exhausted repair shows a readable notice. An explicit retry checks current controls and preserves the assigned agent. **Steps to reproduce** Run `pnpm test:lifecycle-baseline`. The paired probes keep structured state constant while varying completion, planning, blocker, and progress prose. Run the explicit `lifecycle-baseline` and `continuation-accounting` Product E2E suites for real-provider coverage. In Storybook, open **Design previews / Recovery notice** to inspect the production component's normal, pending, acknowledged, unavailable, failure, and mobile states. ## What Changed - Hide the image attachment button, icon, and drop/paste hint in answer composers. Image paste and drop support remains available. - Merge current master and retain both browser regression sets. Use a production-stamped service worker in the offline recovery browser fixture. - Share one state-based legacy continuation decision across immediate, delayed, and recovered dispatch. Bind bounded repairs to their source run and episode. - Remove title and description wording from work-mode authority. Agents can still write requested plans in execution mode. - Persist separate failure-retry and productive-continuation counters. Disposition repair and resource waits cannot consume or reset those allowances. - Validate delayed repair identity, then recheck current gates before provider dispatch. Fence native startup cancellation. - Show **Agent needs attention**, a plain-language explanation, **Retry agent**, and expandable details in both task interfaces. Report request progress, acknowledgement, and errors inline. - Store typed recovery notice metadata. Recognize older active notices only through exact stored action and run IDs. Notice text never grants retry authority. - Use the existing recovery-action endpoint for retry. Recheck current action, status, owner, agent availability, dependencies, active runs, pending questions and confirmations, approvals, pause controls, and budget. Duplicate requests do not wake twice. - Add component, page, route, database, contract, and Storybook coverage. Keep the scenario inventory and executable evals here. Historical reports and snapshots live in the [commit-pinned paperclip-evals archive](https://github.com/paperclipai/paperclip-evals/blob/ce3e5afcd4a1184650f586a2b5b8be5874c66c8b/experiments/2026-09-lifecycle-authority/README.md). - Preserve unsaved project fields while the same project URL changes to its canonical alias. Do not reuse data across projects or companies. This separate fix addresses the repeated repository-editor browser failure without changing the browser test. - Keep the development service worker from intercepting Vite module reloads. Update the connection-intent browser fixture to record progress and completion through the agent API. ## Verification Merge preparation on September 25, commit `c1e8e4b7ddd9fbc4913ed55ce21b8e12906c2f97`: - Merged master `bd2030932` and resolved the browser test-list conflict by keeping both sets of regressions. - Deterministic lifecycle baseline: 1,090/1,090 assertions passed; no failures, skips, or missing selected evidence. Unit 423, runner 184, database integration 397, grading 86. - Browser support: 17/17 passed. The offline recovery test first failed with an unstamped development worker, then passed with the production stamp. Its assertions are unchanged. - Focused interaction UI and offline fallback tests: 19/19 passed. Verified the custom-answer composer in Storybook: no attachment controls or hint; entering an answer enables Next. - Recursive typecheck, production build, token gates, and diff checks passed. The worktree is clean. No new real-provider campaign was run. - Current CI and review: [Current PR CI passed](https://github.com/paperclipai/paperclip/actions/runs/36166011243): 55 successful checks and two optional Storybook skips. Greptile scored this exact commit 5/5. Hiding the question attachment controls is an intentional UI change; paste/drop remains available. Earlier recovery UI verification, commit `21be0fec0e90e86b6d662b8ee4831847cd041cdb`: - Recursive typecheck, production build, token gates, and diff checks passed. - Focused UI coverage: 338 tests passed across six suites (336 before the interaction guard, with the two affected suites rerun at 149 passed after it). Covers both task interfaces, the real page mutation, pending/error acknowledgement, stale state, and unavailable controls. - Recovery database integration: 352 tests passed before the interaction guard. The complete recovery-action and mutation-route suites passed 181 tests after it. The two new pending question/confirmation regressions failed before the fix and passed afterward, including resolved-interaction controls. Shared validator suite: 31 passed. E2E catalog suites: 34 passed. - Browser inspection passed for light/dark themes, mobile layout, expandable details, pending retry, acknowledgement, failure, and disabled retry. Storybook renders the production component; its request is simulated. - The broad local run hit two chat callback-order wait failures and was stopped after all CI unit/database/runner shards passed. Both local failures passed when rerun without the competing full-suite process. - CI exposed a repeated project-repository draft-loss race during canonical redirects. A new unit regression failed before the fix; all nine project-page tests now pass, including controls for other projects and companies. Both unchanged repository browser tests passed against a fresh local server. UI typecheck, production UI build, and token gates passed after this fix. - [Earlier PR CI passed](https://github.com/paperclipai/paperclip/actions/runs/36072486798) on `21be0fec0e90e86b6d662b8ee4831847cd041cdb`: 55 successful checks, two optional Storybook skips, and no failed or pending checks. The repository browser shard passed with the production fix. Greptile is 5/5 on this exact commit with no unresolved review threads. The PR is mergeable. Historical, source-qualified lifecycle evidence: - Lifecycle baseline: 1,074 assertions. Native session coverage: 447 tests. Product E2E support: 515 tests. Browser support: 11 tests. Full earlier verification is retained in the archive. - [Real-provider campaign: 8/8 passed, zero retries](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-35881382080-1/index.html), source `e88d210417280140b44a36449027290adcb1aeaa`. Evidence and cleanup checks passed. This includes deliberately exhausted repair cases that correctly remain blocked; it does not mean every task finished Done. This campaign predates the recovery UI change. - Archive migration verified all 16 original JSON files byte-for-byte and all 24 checksum entries. App tests do not need private archive access. [Archive PR #27](https://github.com/paperclipai/paperclip-evals/pull/27) is merged. ## Risks - Agents that omit durable disposition receive at most two repair attempts by default. Prose-only completion exposes missing state rather than silently changing scheduling. - A retry is an explicit board action. The server rechecks current controls. A successful response confirms the task returned to To do; it does not claim that the provider has already started. - Existing notice metadata remains valid. Only older active notices with matching structured evidence receive the new UI. Historical notices without that evidence keep their existing rendering. No schema migration is required. - Old run records require conservative retry accounting. Tests cover old counters, alternating retry lanes, restarts, and exhausted repairs. - Historical snapshots require private `paperclip-evals` access. The app index retains public campaign links. Live campaigns qualify specific sources and scenarios; no new real-provider campaign has run for the recovery UI commit. > This fixes existing lifecycle and recovery behavior and does not duplicate planned core work. ## Model Used OpenAI GPT-6 through Codex assisted implementation, reasoning, code execution, and review. The exact serving model ID and context window are not exposed in this task. Historical real-provider evaluations used Codex model `gpt-5.6-sol`, separately from the implementation assistant. ## 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 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>	2026-09-25 15:28:11 -07:00
DottaandPaperclip	f56aee5423	fix(evals): capture complete durable run event streams (#13977) ... ## Thinking Path > - Paperclip manages AI agents and records their durable work outcomes. > - Product E2E checks those outcomes through the browser and public API. > - A successful long run can emit more than 1,000 durable events. > - The harness read one page and missed the later completion evidence. > - This pull request reads every page before it checks runtime invariants. > - Invalid or incomplete capture still fails. A missing page cannot produce a pass. ## Linked Issues or Issue Description Related: #13882 (Grok qualification). A duplicate search found no existing event-pagination fix. **What happened?** The local structured-question case in [campaign 36071063537](https://github.com/paperclipai/paperclip/actions/runs/36071063537) completed the task and passed its six outcome matchers. It failed native runtime invariants because the capture contained exactly 1,000 events. The last captured event preceded the run's completion by more than a minute. The API caps each response at 1,000 rows. The harness did not request the next page. **Expected behavior** Read the complete durable event stream through the public API before checking semantic-result and terminal-event counts. Reject incomplete or malformed evidence. **Steps to reproduce** 1. Complete a native task that emits more than 1,000 durable events. 2. Place the semantic-result and terminal events after row 1,000. 3. Capture the run with the Product E2E harness. 4. Before this fix, the invariant checker sees only the first page. **Paperclip version or commit** Observed at `4196a4cd76db434854b679035e4146c7f69689ce`. The same single-page capture exists on master. The original failed result remains unchanged; missing historical tail evidence is not reconstructed or graded as a pass. ## What Changed - Add a bounded event collector that advances through the public `afterSeq` cursor. - Use it for task success/failure evidence and shared chat run evidence. - Reject invalid pages, missing or non-increasing sequence numbers, repeated cursors, failed later requests, and an exhausted page limit. - Test completion events beyond the first page, exact page boundaries, and malformed evidence. - Correct the existing Everyday catalog test from 38 to the maintained 47 cells. The suite stays explicit-only. - Document the complete-capture requirement and its bound. ## Verification - Product harness typecheck passes. - The full credential-free harness suite passed 477 tests. After adding the chat integration regression, all 34 chat evidence tests pass. - Seventeen pagination tests cover the valid tail and malformed-evidence cases. - `git diff --check` passes. - [Full repository CI](https://github.com/paperclipai/paperclip/actions/runs/36080683422) passes at `aed6f79c089226be79e75dcf390969561ec4f787`: 52 successful checks and two intentional skips, including Rust, typecheck, build, server tests, and browser shards. Greptile gives this exact head 5/5 with no findings. No local Docker, Rust build, browser suite, or model invocation was used for this change. - [Live Grok requalification](https://github.com/paperclipai/paperclip/actions/runs/36080870743) is running on combined source `1b0551bb7c8de3c54f4bee64dbe2c88328b3645e`, with the runner, scheduler, and evidence fixes. Its full credential-free harness passes all 493 tests and typecheck. Live results are pending; the original campaign remains a failed measurement. ## Risks Long runs need more read-only API requests and larger private evidence files. Capture stops with an explicit error after 100 full pages. This changes neither production APIs nor provider behavior. It does not relax an invariant or change a historical grade. ## Model Used OpenAI GPT-6 through Codex, with repository tools and code execution. The exact serving identifier and context-window size are not exposed in this session. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` 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>	2026-09-25 10:06:33 -05:00
DottaandPaperclip	efce9356b5	fix(ui): offer recovery when the app fails before React starts (#13970) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - The browser must load its JavaScript before React can render a task. > - A failed import can stop that process before the React error boundary exists. > - The HTML entry then leaves an empty page with no recovery action. > - This PR adds a small recovery screen that works without React. > - The user can retry the same page and return to saved task content. ## Linked Issues or Issue Description Refs #13824 and #13895. This is a follow-up to their browser startup investigation. **What happened?** Interrupting the app bundle or a required import leaves an empty React root. A startup exception has the same effect. A React error boundary cannot handle these failures because React has not started. **Expected behavior** The page must explain the startup failure and offer a manual retry. A late successful load must dismiss the recovery message without a reload. **Steps to reproduce** 1. Open a saved task in the browser. 2. Abort the application bundle request, or make a required module return HTTP 503. 3. Observe the empty page before this change. With this change, use Reload page after the fault clears and verify the saved task and comment. **Paperclip version or commit** The failing regression baseline used master at `8781f06a8`. **Deployment mode** Local source build and compiled UI. Tests cover both initial navigation and a page controlled by the production service worker. The exact cause of the older intermittent Vite stall remains unconfirmed. Forty app loads and thirty replays of retained responses did not reproduce it. This PR fixes the missing recovery path; it does not claim to remove that historical cause. A normal HTTP 304 response is not a failure. ## What Changed - Add an inline startup guard and recovery screen in the HTML entry. It does not depend on the app module graph. - Show a manual reload action after a startup error or after 30 seconds without rendered root content. - Remove the notice, timer, observer, and error listeners when the app starts. Never reload automatically. - Keep the recovery screen outside the React root so it cannot satisfy app-readiness checks. - Add browser tests for interrupted imports, a stalled import, an evaluation error, service-worker-controlled retry, repeated offline retry, and cleanup after successful startup. - Return a static, uncached HTML retry screen when a service-worker-controlled navigation fails offline. It contains no task content. - Add a full-app test that retries an interrupted compiled bundle and checks the saved task, comment, composer, route, and absence of agent runs. - Document the coverage and the limits of the historical diagnosis. ## Verification - Red baseline: four recovery cases failed; the normal-startup case passed. After the change, all five recovery cases passed. The review found an offline retry gap; that additional case failed before the worker fix and passed afterward. - Full provider-free browser-support suite: 16 passed. - Compiled-app browser tests: four passed, including saved-task reload, interrupted-bundle recovery, slow-CPU service-worker reload, and sidebar navigation. - Expanded service-worker, offline response, PWA, and worker build-ID unit tests: 37 passed. The two old plain-text offline expectations were reproduced as failures and updated for the HTML retry contract. - UI production build, full local repository typecheck (`pnpm -r typecheck`), runner-E2E typecheck, and design token checks passed. - Manual browser check: a temporary server failed the compiled bundle once. The recovery screen appeared. Clicking Reload page restored the same saved task, comment, and composer. - Full local `pnpm build` passed. - Full local `pnpm test:run` was attempted with a bounded deadline and stopped after it timed out. Workspace runtime/cleanup tests reported timeouts on this host. The monolithic local run is not a pass. The focused tests above and the complete Linux CI run provide the successful verification. - Final-head [CI run](https://github.com/paperclipai/paperclip/actions/runs/36072201966) passed. All 53 check runs succeeded; the two Storybook jobs were intentionally skipped. The legacy security status also passed. - Greptile reviewed `f83e0f51fb760541d83353f2c1df4e182f3948f9`: 5/5. Both review findings are fixed and resolved. ## Risks - The guard only handles startup before React renders root content. Existing React boundaries handle later rendering errors. - A slow startup can show the message after 30 seconds. A later successful render removes it; the page does not reload by itself. - The fallback uses native HTML when the app stylesheet is unavailable. - The worker changes only its offline navigation response. It returns static HTML with a reload button and `Cache-Control: no-store`. Its cache allowlist, private-response protections, task state, provider prompts, and grading rules stay unchanged. - This does not establish or fix the unknown cause of the historical intermittent Vite stall. ## Model Used OpenAI GPT-6 through Codex. The session exposes the GPT-6 family but not an exact served model ID or context window size. Used reasoning, code editing, shell tools, and browser testing. No subagents were used. ## 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>	2026-09-24 19:36:45 -05:00
DottaandPaperclip	8781f06a87	feat(connections): enable MCP aggregators by default (#13964) ... ## Thinking Path > - Paperclip helps people manage AI agents for work. > - Connections let those agents use external services with explicit access rules. > - Zapier, Arcade, Composio Connect, and Executor already have setup and runtime support. > - Their experimental switch still blocks discovery and setup by default. > - This pull request removes those gates and the Settings toggle. > - Users can connect these providers without enabling an experiment. ## Linked Issues or Issue Description Refs #13755. Refs #13941. **What existing behavior does this improve?** Apps browsing, inline setup, and agent connection search for the four MCP aggregators. **Current behavior** An instance must enable the MCP aggregators experiment before users or agents can start setup. **Proposed behavior** All four providers are available by default on local and managed instances. Old stored and managed values still parse but cannot disable them. ## What Changed - Remove the aggregator gates from Apps, inline setup, server setup, and agent search. - Remove the Settings toggle and its UI hook. - Retain the old setting key only for upgrade compatibility. Normalize it to true and ignore managed overrides, as Apps already does. - Replace opt-in fixtures with default-on coverage. Test old false values, all four setup flows, provider choice, and the removed toggle. - Update current connector guidance and remove the opt-in from the runner acceptance fixture. ## Verification - 306 focused tests passed across eight files: shared remote MCP contracts; server remote MCP lifecycle, aggregator fallback, settings normalization, and managed overlay; UI Apps browsing, setup, and experimental settings. - Server and UI TypeScript checks passed. - UI token gates and `git diff --check` passed. - The full local suite was not run, per the maintainer's instruction. All 54 CI checks passed; two checks were skipped. One unrelated workspace-preview readiness timeout passed on one failed-shard retry. - The setup fixtures use simulated MCP responses. This change does not claim new live provider acceptance. ## Risks - Existing instances now show all four providers, even if the old flag was false. This is intentional. - External provider choice, credentials, company isolation, agent grants, and tool policies still apply. Showing a connector does not authorize an external account. - No data migration is required. The compatibility key keeps old managed configuration documents valid. - Historical Zapier live acceptance remains incomplete in the existing evidence report. The maintainer explicitly requested the default-on rollout for all four existing providers; the report records that scoped exception. ## Model Used OpenAI GPT-6 (`gpt-6-astra`) through Codex, with reasoning, repository tools, and test execution. The context window size is not exposed in this session. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>	2026-09-24 17:31:32 -05:00
DottaandPaperclip	aa8fc86331	feat(connections): prefer native apps and ask users to choose external providers (#13941) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Connections give agents governed access to external services. > - Native connections should remain the first choice for a supported app. > - Other apps may be available through an external MCP provider. > - The user must know which external provider handles the connection and choose it before setup. > - This pull request adds ranked alternatives and server-authored instructions to connection search. > - Agents can follow the returned instructions while Paperclip validates saved choices and access. ## Linked Issues or Issue Description Related: #13879, which fixed inline MCP provider setup. This PR adds discovery and provider selection on top of that work. **Subsystem affected** Cross-cutting: shared connection contracts, server search and intent services, native runtime, CLI, inline setup UI, and evals. **Problem or motivation** An agent cannot offer a clear external-provider choice when Paperclip has no native connection for an app. Adding provider-specific branches to the core prompt would make those instructions harder to maintain. **Proposed solution** Prefer a native connection. Otherwise return verified alternatives in Composio, Arcade, Executor, Zapier order. Include an external-service disclosure, a question with None, and the next instruction in the search result. Validate the saved human choice before creating a selected fallback setup card. Reuse existing provider accounts and verify underlying app access separately. **Alternatives considered** Do not silently choose a provider. Do not claim that broad execution tools prove support for every app. Reuse existing questions and connection intents rather than add another connection model. **Roadmap alignment** Extends the existing MCP Tool Gateway & Apps and Agent evals & feedback capabilities. The MCP aggregators experiment remains the gate. No duplicate provider-routing PR was found in the public search. ## What Changed - Add a dated support index and authorized cached-tool evidence for external routes. - Return provider questions and next-step instructions from `connections_search`. - Preserve pending choices and declines across continuation. Validate company, task, agent, human, app, and current route eligibility. - Carry the selected app into new setup and account reuse, validate explicit provider requests against persisted human messages, and distinguish provider readiness from app authorization. - Sync native, MCP, REST, and CLI contracts. Keep core agent instructions provider-neutral. - Add production-component Storybooks, focused database tests, and three real-agent browser eval cases. - Record the plan, observed failures, fixes, passing evidence, and acceptance limits. ## Verification - Latest head `586f0e6cd`: 54 checks passed, 2 skipped; Greptile 5/5 and all review threads resolved. - After rebasing on master `18dac1e1e`: 64 focused shared, validator, route-contract, and database tests passed; server typecheck passed. - Embedded-browser test drive on the rebased head: native Jira card, HubSpot external-provider question, Arcade account reuse, one actual MCP read against a local synthetic fixture, reload persistence, and None preventing further calls. A real OpenAI-backed agent performed discovery and continuation. - UX observation: the agent initially combined mutually exclusive request fields; the server rejected it and the agent recovered without changing access. This extra retry remains visible in the transcript. - After rebase: 23 focused eval grader/catalog tests, affected TypeScript checks, token gates, production UI build, and Storybook build passed. Full local tests are intentionally excluded at the maintainer's request. - Before rebase: four browser/real-agent attempts passed: native Jira, None, and reuse of the second provider on two Codex profiles. - Browser evals used an isolated deterministic MCP fixture through the real Paperclip gateway. They do not prove production compatibility with all four providers. - Review `Apps / Connections / Provider choice` in Storybook. Choose Arcade, continue through Access, and verify the app name, external-service disclosure, and URL configuration. - The detailed verification report is `doc/connections/2026-09-23-aggregator-routing-verification.md`. ## Risks - The public support index is finite and can age. Account capability and app authorization still require verification after selection. - Existing installed-tool permissions remain in effect. Provider choice is not a new execution permission boundary. An early Mini attempt skipped search; clearer provider-neutral instructions made the targeted rerun pass. This is not a measured reliability rate. - Explicit requests skip provider confirmation only when a clear persisted human message or saved provider choice supports them. Other phrasing falls back to confirmation; the agent query alone is not consent. These routes do not add tool permissions. - No database migration or legacy Composio broker is added. Real-provider acceptance remains separate from fixture proof. ## Model Used OpenAI GPT-6 through Codex, with reasoning, repository tools, code execution, and browser tools. The exact deployment variant and context-window size are not exposed in this session. Product evals separately used the repository's primary Codex and Codex Mini profiles; those agents supplied test behavior, not independent provider compatibility proof. ## 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>	2026-09-24 16:36:49 -05:00
DottaandPaperclip	b648d8cdda	fix(evals): support explicit Grok qualification workflows (#13878) ... ## Thinking Path > - Paperclip manages AI agents and their provider connections. > - Product E2E checks real tasks through the browser, server, and runner. > - Grok qualification needs separate API-key and subscription evidence. > - Product subscription tests and direct Grok protocol evals need explicit credential delivery. > - This change supplies each credential only to its selected profile and prepares the pinned binary. > - Maintainer authorization and protected-environment gates remain required. ## Linked Issues or Issue Description Refs #13845, #13847, #13850, #13882. The Grok feature branch has a manual subscription qualification profile. The trusted master workflow must admit its selected credential and prepare the same verified binary and artifact verifier as the API profile. Direct protocol evals also need the selected xAI key and pinned Grok binary. These prerequisites do not register or schedule the new profiles on master. ## What Changed - Deliver `GROK_AUTH_JSON` from the protected paid environment only when the selected profile requests that credential. - Install the checksum-verified Grok binary for the local subscription profile. - Prepare the pinned artifact verifier for the manual subscription suite. - Extend workflow security assertions to cover the new credential and profile. - Add the ACPX Grok credential mapping to the trusted-master catalog, then deliver only the selected `XAI_API_KEY` to direct protocol cells and install the target’s checksum-verified Grok binary before packaging. - Allow a direct-protocol concurrency override from two cases up to the existing configured ceiling; it can only lower concurrency. - Document the Grok protocol workflow and its API-only credential boundary. - Render missing LLM usage and cost as Unavailable, and label partial observations with coverage. Preserve raw records, grades, and actual zero costs. - Preserve measured campaign source metadata during report regeneration instead of inheriting the renderer checkout or CI event; skip empty legacy source records when recovering older provenance. ## Verification - Latest commit `05d05801477104c8155977bbbe3e119a5241f960`: all 54 reported checks successful, two intentional skips, Greptile 5/5, and zero unresolved review threads. [CI run](https://github.com/paperclipai/paperclip/actions/runs/35890978288). - After merging current master, all 17 workflow security/image tests and 23 catalog/workflow policy tests passed. The trusted catalog also generated all 39 pinned Grok cells with `XAI_API_KEY` and one case per shard. The new policy tests execute the concurrency guard against valid, out-of-range, and malformed values. - The Grok branch separately passed 450 Product harness unit tests, including private company credential staging, cleanup, and token-fragment redaction. - The fresh-login native subscription smoke passed three repetitions of tool execution, session resume, restrictive permissions, and cleanup. These are setup evidence; full subscription Product qualification remains pending. - All 72 focused report/billing/history/catalog tests and the Product harness typecheck passed for the report-display change. The initial sandbox run could not open the tsx IPC socket; the permitted rerun passed. A zero-provider-call replay of the actual 16-cell Grok campaign preserved all result records, grades, timing, and source provenance while correcting missing usage labels. - Review the thirteen-file diff. Provider credentials still enter only the selected paid-test step; default-branch, numeric-actor, and environment restrictions are unchanged. ## Risks This admits a refreshable subscription credential to explicitly selected trusted tests. Store it only in `runner-e2e-paid`, use a test login, and remove it after qualification. Unselected profiles receive an empty value. Pull requests cannot trigger the paid workflow. This PR changes no fleet admission or actor allowlist. ## Model Used OpenAI GPT-6 through Codex, with tool use and code execution. The exact serving model identifier and context-window size are not exposed in this session. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>	2026-09-23 17:05:52 -05:00
DottaandPaperclip	60c7c9cd1a	fix(runner-e2e): pass verified lock digest to Daytona image build (#13876) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Product E2E campaigns test the native runner in local and Daytona environments. > - Each campaign resolves one target lockfile and verifies its downloaded artifact. > - The Daytona image job did not pass that artifact digest to Docker. > - Docker used an older default digest and stopped before any selected task ran. > - This pull request passes and validates the campaign digest at the image build boundary. > - The image keeps its checksum check and frozen package installation. ## Linked Issues or Issue Description **What happened?** The merged-master [qualification campaign](https://github.com/paperclipai/paperclip/actions/runs/35863582409) stopped in the Daytona image build. The resolved target lock digest was `e0c928a494f90ddad3c00791e83f09315ee8c82df2a0418a809dcf93649a8ab3`. Docker used its default digest, `57b298aceebc48bb94ea0593347348256475da7b2fddb77025d9e57cc8759420`. The checksum check rejected the mismatch. All 12 selected model cells were skipped. This follows the image provenance work in #13814. **Expected behavior** The image build must check the same lockfile artifact that the campaign restored and verified. A changed lockfile must still fail the checksum check. **Steps to reproduce** 1. Start a Product E2E campaign with a Daytona cell on master `7944ed3d976d1a7cc26a2d0cee51f227f3542084`. 2. Resolve a target lockfile whose digest differs from the Dockerfile default. 3. Observe the provider-pack image stage reject the lockfile before model execution. **Paperclip version or commit** `7944ed3d976d1a7cc26a2d0cee51f227f3542084`. **Deployment mode** GitHub Actions Product E2E campaign with a Daytona image build. **Install method** Built from source with the campaign lockfile artifact. **Agent adapter(s) involved** Native Codex and ACPX Claude cells were selected. No model cell ran in this failed campaign. **Database mode** Not involved. The failure occurs during image creation. **Access context** The authorized default-branch paid workflow. The build receives no provider credentials. ## What Changed - Read the image checksum from the existing target-lock job output. - Require a 64-character lowercase hexadecimal digest before image inspection or build. - Pass the digest as the existing Docker build argument. - Add regression checks and document the campaign checksum handoff. ## Verification - The Daytona image regression fails with the original workflow and passes with the fix. - All six Daytona image contract tests pass. - All 450 Product E2E unit tests pass. - Product E2E typecheck passes. - Actionlint passes for the changed workflow. - A context-shaped resolution probe preserves the downloaded lockfile bytes and digest. - All latest-head CI checks passed on `67d41fd9439b2a9a809ddb05765f8617585072c5` ([run](https://github.com/paperclipai/paperclip/actions/runs/35865739359)). - Greptile gave 5/5 on this head; its test-scoping comment is addressed and resolved. - A hosted Daytona image rebuild and the three remote qualification cells remain pending after merge. ## Risks The campaign digest comes from the existing trusted target-lock job. The restored artifact checks, Docker checksum check, frozen install, content identity, image signing, and verification remain in place. The standalone Docker default remains available. This change does not alter task behavior, prompts, credentials, or dependency versions. ## Model Used OpenAI `gpt-6-astra` through Codex performed diagnosis and review with code execution tools. OpenAI `gpt-5.6-luna` assisted with investigation, implementation, and verification. Context window limits are not exposed in this session. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>	2026-09-23 08:45:52 -05:00
DottaandPaperclip	106d89314f	fix(evals): keep raw diagnostics out of public history (#13850) ... ## Thinking Path > - Paperclip manages AI agents and their work. > - Product E2E campaigns retain evidence from live provider runs. > - The public publisher copied per-attempt files based on their extension. > - Credential redaction does not remove hidden reasoning or provider session IDs. > - This pull request keeps those raw diagnostics out of public evidence bundles. > - Public reports retain normalized grades and declared fixture screenshots. ## Linked Issues or Issue Description **What happened?** The Product history publisher accepted all JSON, log, Markdown, and text files under an attempt directory. API snapshots and process logs can contain provider reasoning even after credential redaction. **Expected behavior** Keep raw attempt diagnostics in retained Actions artifacts. Publish normalized results and declared fixture screenshots. Preserve the original grades and attempt evidence. **Steps to reproduce** Place a credential-redacted API snapshot with a reasoning event under an attempt's snapshots directory. The previous public path check admitted it because it ended in .json. ## What Changed - Remove extension-based admission for per-attempt text files in both S3 and Pages staging. - Require PNG paths to appear in the existing screenshot declaration allowlist. - Preserve root normalized results, grading, billing, provenance, and reviewed screenshot behavior. - Add seven denial cases for raw diagnostics, renamed files, malformed JSON, and false screenshot declarations. - Update report copy and the publication security contract. ## Verification - Focused history and report tests: 47 passed. - Replayed the filter against a copy of retained Grok evidence: six diagnostic files removed, one declared screenshot retained, zero provider calls. Original artifacts remain unchanged. - git diff --check passed. - Product typecheck in the reused local dependency tree reports an unrelated plugin type mismatch for organizationSwitcher in server/src/services/plugin-capability-validator.ts. CI will verify a fresh install. - No local browser or Docker execution. ## Risks Public reports no longer link raw per-attempt logs or API snapshots. Those files remain in the original Actions artifact. This change affects future publication only; it does not withdraw or rewrite existing immutable public campaigns. Normalized result content and marked screenshot review retain their existing boundaries. No workflow authorization, provider credentials, application behavior, or database changes. ## Model Used OpenAI Codex, GPT-6 family, with reasoning, code editing, and tool execution. The exact deployment model ID and context-window size are not exposed in this session. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [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>	2026-09-22 21:31:39 -05:00
DottaandPaperclip	ac854a9b59	ci: build Daytona eval images on the authorized fleet (#13847) ... ## Thinking Path > - Paperclip manages AI agents and their work. > - Product E2E campaigns test the browser, server, and runner together. > - The trusted workflow selects an authorized execution fleet. > - Daytona image builds still use a fixed GitHub-hosted runner. > - This pull request applies the existing fleet selection to image builds. > - Campaign builds and tests then use the configured EC2 fleet. ## Linked Issues or Issue Description Refs: https://github.com/paperclipai/paperclip/pull/13845 **What existing behavior does this improve?** The location of Daytona Product E2E image builds. **Current behavior** The image job uses ubuntu-latest even when RUNNER_E2E_AWS_ENABLED selects EC2 for the rest of the campaign. **Proposed behavior** Use the existing authorized runner output for the image job. Preserve the GitHub-hosted fallback when the EC2 switch is off. ## What Changed - Route Daytona image builds through the existing authorized runner selection. - Assert that the image job depends on authorization and receives no provider credentials. - Document the build routing and credential boundary. ## Verification - Product E2E workflow security: 11 tests passed. - git diff --check passed. - Reviewed actor checks, workflow triggers, target commit selection, signing, and package permissions. They are unchanged. - Required CI checks pass on the latest head. The first CI attempt had failures in unchanged chat tests; one diagnostic rerun passed. Both attempts remain in Actions. - Greptile reviewed the latest head at 5/5 with no inline findings. - Live EC2 image verification follows after this trusted workflow change is merged. No local Docker execution. ## Risks EC2 image builds depend on the fleet having working Docker and sufficient disk space. Existing authorization, image digest checks, signing, and the GitHub-hosted fallback remain in place. No provider secrets are added to the image job. No application or database changes. ## Model Used OpenAI Codex, GPT-6 family, with reasoning, code editing, and tool execution. The exact deployment model ID and context-window size are not exposed in this session. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [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>	2026-09-22 21:30:09 -05:00
DottaandPaperclip	950ccb8eef	ci: enable Grok qualification in the trusted paid workflow (#13845) ... ## Thinking Path > - Paperclip manages AI agents and their work. > - Product E2E tests verify tasks through the browser, server, and runner. > - These paid tests use a trusted workflow from master and an isolated target commit. > - The Grok target branch selects XAI_API_KEY, but the trusted workflow does not deliver that credential. > - Its artifact test also needs the pinned Python verifier before execution. > - This pull request adds both bindings inside the existing paid boundary. > - The tests can then run on the configured EC2 fleet without laptop Docker. ## Linked Issues or Issue Description Related evaluation infrastructure: https://github.com/paperclipai/paperclip/pull/11297. No duplicate Grok paid-workflow change was found. **What existing behavior does this improve?** Branch-targeted Grok Product E2E qualification in the existing paid workflow. **Current behavior** Grok cells cannot receive their selected API credential. The Grok build-revise case also misses the artifact-verifier setup step. **Proposed behavior** Deliver XAI_API_KEY only when the selected matrix credential is XAI_API_KEY. Prepare the existing pinned verifier for the Grok qualification suite. **Reason and benefit** Run the controller, browser, runner and artifact checks on the EC2 fleet. Preserve default-branch workflow authorization and protected environment secret access. ## What Changed - Bind the selected XAI credential only in the paid test step. - Install the checksum-verified Grok binary for local cells before provider access. - Include Grok qualification in the existing pinned artifact-verifier preparation. - Add an optional max_parallel input that can only lower the configured campaign concurrency. Use 1 for the Grok test key. - Extend security assertions and document setup. ## Verification - Ran the Product E2E workflow-security tests: 11 passed. - Checked the diff for whitespace errors. - Reviewed credential selection, setup ordering, numeric actor gates, target commit pinning, and trusted report checkout. - Live Grok execution follows after this workflow is available on master. This PR does not claim completed Grok qualification. ## Risks The paid test step can use the selected XAI credential and incur provider charges. The credential remains in runner-e2e-paid and is absent from setup, build, and reporting jobs. The default-branch gate and existing environment restrictions remain in place. No database migration or product behavior changes. ## Model Used OpenAI Codex, GPT-6 family, with reasoning, code editing, and tool execution. The exact deployment model ID and context-window size are not exposed in this session. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [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>	2026-09-22 20:17:25 -05:00
DottaandPaperclip	9a76390cfa	test(runner): improve blank-page diagnostics and infrastructure coverage (#13824) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Runner E2E tests verify real tasks and retain evidence for failures. > - Some exposure tests assumed that port 42000 was free. > - A blank task page could also fail without enough browser startup evidence. > - This pull request tests occupied ports and task reloads, and records private startup diagnostics. > - These changes make test failures easier to reproduce and explain. ## Linked Issues or Issue Description Refs #13815. Report publication already received its production fix in #13750; this PR adds a regression check for that workflow. **What happened?** Three exposure tests assumed that the allocator would select port 42000. The synthetic failure disappeared when another process occupied that port. A prior Daytona run also retained an empty task page after navigation, but its evidence did not record pending modules or service-worker control. **Expected behavior** Exposure tests must exercise the intended failure on the actual assigned port. Browser failure evidence must distinguish an empty root from loaded content. A saved task must remain usable after navigation and reload. **Steps to reproduce** Run the exposure regression with the base port pair marked unavailable. Run the browser-support tests with an unresolved entry module. Open a saved task under the service worker, navigate to the same URL, and reload it. **Paperclip version or commit** Based on master at a68f3d8e3. ## What Changed - Make synthetic exposure failures use the assigned port. Test both free and occupied base pairs. - Record document readiness, root children, service-worker control, pending module paths, and recent module error or 304 statuses in private runner evidence. - Add browser tests for pending startup, failed module responses, and diagnostic reset after navigation. - Add a provider-free browser test for persisted task content and the composer across three navigation/reload cycles. - Guard trusted report-job lockfile resolution before frozen install and AWS credential setup. - Document the new evidence and test commands. ## Verification - `pnpm test:e2e:runner:unit`: 443 tests passed. - `pnpm test:e2e:runner:browser-support`: 10 tests passed. - Exposure tests: 28 passed; 3 platform-specific skips. - Harness typecheck, workspace typecheck, and full build passed. - Task-reload browser test passed against a throwaway local instance. It checks three navigation/reload cycles with a controlling service worker. - All PR verification suites passed, including server, chat, workspace, serialized server, Rust, runner, build, typecheck, and browser shards. The existing sidebar navigation case showed an empty page on the first CI attempt and passed on one retry. - The monolithic local `pnpm test:run` was started, then stopped after CI completed the equivalent suites. Additional local browser reproduction attempts also hit embedded-Postgres startup failures; the focused checks listed above completed successfully. - Greptile: 5/5 on the current head, with no findings. ## Risks This change affects tests and private test evidence. It does not change production prompts or runtime behavior. Module paths omit queries; the collector reads no response bodies or headers. The existing sanitizer and publication allowlist still apply. A 304 response does not cause a test failure. The blank-page cause remains unconfirmed. The first CI attempt reproduced it in an existing sidebar navigation case: the trace shows an empty page after a service-worker-mediated 304 response for the large editor module. The single retry passed. This PR adds coverage and diagnostics; it does not claim to fix that intermittent symptom. ## Model Used OpenAI Codex, GPT-6, with repository tools, code execution, and browser tests. The exact deployed model variant and context-window size are not exposed in this session. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge Co-authored-by: Paperclip <noreply@paperclip.ing>	2026-09-22 15:04:13 -05:00
DottaandPaperclip	a68f3d8e35	fix(runner-e2e): align Daytona image and provider pack provenance (#13814) ... ## Thinking Path > - Paperclip is an open source app people use to manage AI agents for work. > - The Daytona runner image provides the native runner and its provider package. > - The controller also sends a provider package to native Daytona cells when the image package does not match. > - A stale image and a package from another source revision caused a 1.8 GB upload before Claude could run. > - This pull request refreshes the reviewed lock checksum and documents how to reuse the exact package from an immutable image. > - The benefit is a reproducible setup path and clear evidence when image and package provenance do not match. ## Linked Issues or Issue Description **What happened?** A Daytona native Claude run used image source revision `45c99a0d06cbd5b04982b06b79de321149930ac5` with a controller provider package from revision `294853dc...`. Runtime verification rejected the image package and staged a large package upload before model execution. A hosted campaign also failed during image setup because the Dockerfile expected lock checksum `d7d96cf0...` while the resolved lockfile checksum was `4b796c312833ebf2be4c38228babc0292c76774fb40d43bd18b54bd6b205753d`. Related public work reviewed: [#12795](https://github.com/paperclipai/paperclip/pull/12795), [#12862](https://github.com/paperclipai/paperclip/pull/12862), and [#12887](https://github.com/paperclipai/paperclip/pull/12887). **Expected behavior** The Daytona image and controller provider package must come from the same verified build. A package extracted from the immutable image must pass the existing manifest, source revision, lockfile, binary, bridge, and artifact checks before a native Claude run starts. **Steps to reproduce** 1. Set `PAPERCLIP_E2E_DAYTONA_IMAGE` to the old immutable image digest. 2. Set `PAPERCLIP_RUNNER_REMOTE_PROVIDER_PACK_PATH` to a package built from a different source revision. 3. Run a native Claude Daytona cell. 4. Observe provider package verification failure followed by the large staging upload. 5. Build the image with the stale Dockerfile lock checksum and observe the checksum failure. **Paperclip version or commit** `3b8df3dcd6f99e99277faa45f3351989edb5c239`. **Deployment mode** Daytona native runner E2E. **Install method** Built from source. **Agent adapter(s) involved** Claude Code through the native ACPX runner. **Database mode** Not database-related. **Access context** Not applicable to the setup failure. ## What Changed - Refreshed `PAPERCLIP_RUNNER_LOCK_SHA256` in `docker/daytona-runner/Dockerfile` to the resolved lockfile checksum. - Added a local guide for extracting the provider package from an immutable verified image with Docker. - Documented the required provenance checks and the expected manifest-matched runtime log. - Documented that cold package upload coverage must remain separate from recovery coverage. - Pinned the preview-service test guest to the test runner’s Node executable and logged guest startup and bound ports for readiness diagnostics. ## Verification - 442 focused E2E tests passed. - Typecheck passed. - `pnpm build` passed. - Five provider-pack reuse tests passed. - Six Daytona image contract tests passed. - Fixed Daytona campaign [35740613581](https://github.com/paperclipai/paperclip/actions/runs/35740613581) passed. - The overall hiring campaign [35739993219](https://github.com/paperclipai/paperclip/actions/runs/35739993219) failed because of an unrelated Mini metadata failure; its Claude cell passed. - Full local `pnpm test:run` was attempted but did not complete. The isolated Postgres install was repaired and its 15-test probe passed. - After the fixture change, all seven preview reservation tests passed locally and CI server shard 6/12 passed on `20234f75f`. This removes login-shell Node resolution variance; the exact cause of the earlier CI-only timeout is not established. - CI run [35766034635](https://github.com/paperclipai/paperclip/actions/runs/35766034635) passed on `20234f75f`. All server, runner, browser, build, and typecheck gates passed. - The signoff browser case initially failed waiting for an approver run. All five signoff tests passed locally without changes; the one allowed CI retry passed all 19 shard tests. This is recorded as an intermittent failure, not a demonstrated product fix. - Greptile reviewed `20234f75f`: 5/5, no actionable findings. - [Follow-up report](https://pages.paperclip.ing/runner-daytona-hiring-20260922/) includes timings, evidence links, and the remaining hiring configuration failure. - Review the immutable image source revision and extracted `provider-pack.json` before another paid recovery run. ## Risks - The Dockerfile checksum gate intentionally fails when the resolved lockfile changes. A future dependency change must refresh the reviewed checksum with the image change. - The local extraction guide requires Docker and a pullable immutable image. - An image built from an older source revision can still fail runtime manifest verification. The guide does not bypass that check. - The change does not alter runner prompts, approval policy, or recovery behavior. ## Model Used OpenAI Codex using the primary GPT-6 backend; the exact backend deployment ID is not exposed. Repository analysis and code execution used tool access. Assistance also came from OpenAI gpt-5.6-luna. ## 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>	2026-09-22 13:49:00 -05:00
DottaandPaperclip	74a9730acb	fix: continue native agent chats after worker loss (#13813) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Agent Chat uses native workers to run Claude and Codex conversations. > - A worker crash leaves a cleanup hold because its provider did not acknowledge suspension. > - A new user message must not reuse that unverified session or repeat old tool calls. > - The existing continuation path can preserve history and start a fresh session, but local cleanup ownership remained held. > - This pull request verifies the stopped local owners and releases only their cleanup hold for a new user turn. ## Linked Issues or Issue Description Refs #13775. **What happened?** After a native worker crashed, both providers retained cleanup quarantine. A saved plan survived, but the conversation could not produce another answer. **Expected behavior** Once the old worker and provider process groups have stopped, a new user message can continue in a fresh session with the saved work and prior action history. **Steps to reproduce** Run the opt-in `agent-chat-qualification` suite with case `worker-crash-retry` on native Codex and native Claude. The fixture saves a plan, kills the exact worker through a Linux pidfd, releases a local read-only brief, and sends a new message. ## What Changed - Verify the exact local worker stop receipt, provider identity receipts, released leases, and retained state before retiring a native cleanup hold. - Recheck process liveness and state before admission. Keep the old run and durable session files intact. - Use the existing explicit conversation continuation path. Generic Retry remains blocked for cleanup quarantine, including on the old failed-run marker after a successful continuation. - Extend the live oracle to require a successful fresh session, correct predecessor context, unchanged plan, one original message, and one answer containing a reference introduced after the crash. - Add physical-proof and database-backed admission tests. Document the precise qualification scope. ## Verification - Live Product E2E: **2/2 passed**, **2/2 cleanup passed**, with real native `gpt-5.6-sol` and `claude-sonnet-5`, Chromium, server, database, and public APIs. - Core recovery proof source: `3592b04c2bc76e23795fcdf964720e38a409dc4d`. Suite definition version 8: `9867367994d81a0c726956d91f2c7fddab6417a12f41b5cef3f7e62f3be417da`. - [Core recovery campaign](https://github.com/paperclipai/paperclip/actions/runs/35741746990) · [Public evidence report](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-35741746990-1/). - Both cells verify the real crash boundary, blocked generic Retry, unchanged saved plan, one original prompt, one fresh successor with predecessor context, and one run-attributed answer containing the post-crash reference. Billing coverage is partial because the crashed runs did not report complete usage; missing cost is not zero cost. - [Master baseline](https://github.com/paperclipai/paperclip/actions/runs/35737364443): both providers stopped at quarantine, with cleanup passing. - [Follow-up baseline without the fix](https://github.com/paperclipai/paperclip/actions/runs/35738638866): Codex produced a complete red result. Claude reached the same error, but its artifact upload was canceled. - [Complete Claude baseline with the same version-8 definition](https://github.com/paperclipai/paperclip/actions/runs/35740555177): red at cleanup quarantine, cleanup passed, source `6479a90c5754044356b39a9278b9a3e92ce8e55e`. - Earlier candidate attempts remain retained: [first](https://github.com/paperclipai/paperclip/actions/runs/35738449214) passed Codex and found a Claude fixture wait race; [second](https://github.com/paperclipai/paperclip/actions/runs/35740408065) exposed the normalized session-open receipt mismatch. Both corrections are in the final source. - Targeted server suites: 570 passed before the final two additional receipt regression cases. The physical-proof suite, including those cases, passed 46/46. Eval oracle and catalog: 40 passed. Server and Product E2E typechecks passed. - **All 54 PR checks passed on final head `db6f775df`**, including repository typecheck, build, tests, browser shards, and canary dry run. The canary job required one retry after its runner received a shutdown signal. On the earlier core proof head, two timing-sensitive tests passed in isolation and on a single CI retry. - Final UI regression checks: 5 passed; UI typecheck and token gates passed. Updated eval oracle/catalog: 40 passed; eval typecheck passed. - Final version-9 two-provider campaign: **2/2 passed, 2/2 cleanup passed**, including the browser assertion that the quarantined historical run never regains Try again. [Final campaign](https://github.com/paperclipai/paperclip/actions/runs/35747416013), source `db6f775dfff405e1514ec02fedb0450d42c7dad2`, definition hash `bf5abf1cc45cb6dad4e082fbf818b8fa0f4d8c282776a7e98762b22919eadab7`. [Final public evidence report](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-35747416013-1/). Final screenshots and retained state inspected for both providers; cost coverage remains partial. ## Risks - Missing or conflicting stop evidence keeps the conversation blocked. This change does not kill an unverified process. - This qualifies new user input after local worker loss. It does not enable automatic replay, exact-session recovery, remote crash recovery, or native onboarding defaults. - Old action outcomes remain part of the continuation. A process exit is not proof that an action did not happen. - No schema migration or production prompt change. ## Model Used OpenAI Codex, GPT-6. The runtime does not expose a more specific model identifier or context-window size. Used reasoning, repository inspection, code editing, shell tools, and test execution. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>	2026-09-22 13:01:45 -05:00
DottaandPaperclip	5842185e4f	fix: surface native cleanup quarantine and add chat qualification evals (#13775) ... ## Thinking Path > - Paperclip lets people manage AI agents and their work. > - Agent Chat needs reliable native execution before native runners become the onboarding default. > - Existing stories covered idle reassignment and controller restart, but not an executing worker handoff or worker process loss. > - Status answer tests also need to reject stale claims and invented facts. > - This pull request adds six opt-in full-stack cells with independent state assertions and retained evidence. > - The probes exposed a misleading Retry across server projection and recovery-banner paths; the fix reports the blocked recovery honestly. > - The tests preserve failures without changing recovery policy, production prompts, or onboarding defaults. ## Linked Issues or Issue Description Refs: #13762. Related: #13765 (Retry targets the latest failed attempt), #13753 (task context ownership), #13746 (native recovery work). ## What Changed - Add active reassignment with saved draft and plan preservation, old-worker cancellation, and successor completion checks. - Preserve recovery-needed projection when native cleanup fails before its coordinator exists, refuse a generic retry that would immediately fail again, and replace the recovery banner's misleading Retry with Inspect run. - Add verified local worker process loss with a required successful continuation; retain a failing qualification result when recovery is unavailable, while independently verifying the UI/API refuse doomed retries. - Add two-turn factual answer checks for current blockers, stale claims, inactive backlog work, and unknown facts. Retain prose for separate semantic review. - Add positive and negative oracle calibration and document fault isolation, cleanup, billing, and qualification limits. ## Verification - Eval TypeScript check passes. - All 442 eval support tests pass locally. The 89 focused server tests and server typecheck pass. Six recovery-banner UI tests and token gates pass. - Initial new-cell campaign: https://github.com/paperclipai/paperclip/actions/runs/35657128077. All six results are retained; four failed on fixture-contract issues and two exposed real worker cleanup quarantine. - All 26 existing native onboarding cells: https://github.com/paperclipai/paperclip/actions/runs/35656761484 (26/26 passed on master 846336e5a, all cleanup passed). - Intermediate handoff/fault campaign: https://github.com/paperclipai/paperclip/actions/runs/35657945095 (four retained failures: two overly strict draft oracles, two real crash quarantines). - Final active handoff: https://github.com/paperclipai/paperclip/actions/runs/35659014397 (2/2 passed on cf6d4ae3a; both cleanup passed). - Clarified answer-quality fixtures: https://github.com/paperclipai/paperclip/actions/runs/35658262695 (2/2 passed on 4a26f10be; both cleanup passed; all four answers semantically reviewed). - Quarantine guard regression campaign: https://github.com/paperclipai/paperclip/actions/runs/35659580100 (both API requests correctly refused with 409/no second run, but exposed a separate misleading Retry in the recovery banner and a fixture wait on a non-admitted run). - Final quarantine guard verification: https://github.com/paperclipai/paperclip/actions/runs/35661067305 (147e42f7e: both providers verify Inspect run/no Retry, HTTP 409, one retained run, unchanged saved plan, and successful disposable cleanup. Both evals intentionally remain red with `worker_crash_recovery_unqualified`; no successful continuation exists). The preceding campaign 35658772755 never ran provider cases because GitHub artifact finalization returned HTTP 403. - Full repository CI passes on 147e42f7e: typecheck, tests, build, and browser gates. One unchanged local-service-supervisor readiness test failed initially; its six-test file passed in isolation and the failed shard passed on its single rerun. Latest-head rollup: 54 successful, 2 intentionally skipped, no failed or pending checks. Greptile is 5/5 with zero unresolved findings. - See tests/runner-e2e/QUALIFICATION-2026-09-21.md for retained attempts and semantic review. Published reports: [onboarding](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-35656761484-1/), [handoff](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-35659014397-1/), [grounded answers](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-35658262695-1/), [crash guards and unqualified recovery](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-35661067305-1/). ## Risks - Paid cells are explicit-only and local-only. The fault fixture signals only the exact native run PID after checking its identity. - Live worker-loss probes currently fail on cleanup quarantine for both providers. The eval must remain red until there is a usable recovery, even when preservation and refusal checks pass. Verified cleanup with a fresh attempt versus exact-session resume remains a product decision. - Structured facts alone do not qualify prose quality; semantic review remains separate. - Onboarding uses the existing runtime switch after the real wizard and before provider execution. Native UI selection and public defaults remain unchanged. ## Model Used OpenAI GPT-6 through Codex, with reasoning, tool use, and code execution. The exact served snapshot and context-window size are not exposed in this session. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>	2026-09-21 18:13:01 -05:00
DottaandPaperclip	846336e5a0	test: harden agent chat setup, interruptions and restart evals (#13762) ... ## Thinking Path > - Paperclip lets people manage agents through ongoing conversations. > - Chat users can change instructions while a provider is already working. > - Existing chat evals wait for each turn to settle before the next message. > - They cannot prove delivery during active work or the saved effect of a correction. > - Existing fixtures also enable Agent Chat through the API rather than the settings UI. > - This PR adds bounded browser workflows and checks their persisted outcomes. ## Linked Issues or Issue Description Refs #13741, #13752, #13750. **What happened?** The chat suites cover planning, delegation, status, and recovery. They lack active-turn follow-ups and the experimental settings lifecycle. A sequential conversation can pass even if messages sent during work are lost. **Expected behavior** A follow-up submitted during a provider turn survives and affects the final reply. A changed launch day appears in the saved plan. Disabling Agent Chat rejects new messages while preserving history; re-enabling resumes the same conversation. **Steps to reproduce** Run the explicit `agent-chat-stories` suite. It selects three local cases for each native Claude and Codex profile. An ordinary provider command waits for a fixture brief file so the browser can send the follow-up at an observed active-run boundary. ## What Changed - Add six opt-in Product E2E cells for settings, active follow-ups, and plan corrections. - Drive experimental settings through the UI and verify disabled sends are rejected by the public API. - Use a bounded file wait in the actual isolated agent workspace, with provider-written readiness and an undisclosed brief reference. - Grade persisted user messages, final replies, native run outcomes, and exact saved plan fields. - Accept active-turn steering or one queued successor; reject lost input, duplicate input, and stale outputs. - Allow one steered run or two sequential runs throughout the shared harness, while preserving exact counts for other cases. - Require a single marker-bearing response attributed to the final provider run. - Unload the development browser client before restarting the server, avoiding reconnect/navigation races without weakening the post-restart memory check. - Add browser regressions for restart isolation and asynchronously saved settings switches. - Document prepared-agent setup, native onboarding limits, and the separate API-tool rollout gate. ## Verification - Eval TypeScript check passed. - Eval support suite: 436 tests passed in 39 files. - New oracle calibration: six tests passed, including plausible invalid outcomes. - Browser support regressions: seven tests passed; the restart regression was observed failing before the fix. - Catalog discovery selects exactly six local native cases and leaves default paid selection unchanged. - [Consolidated existing native chat report](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-35643286055-1/): master `b82661b56`, 33/34 passed, all cleanup passed. The failure was a browser navigation timeout across restart; the page request returned 200 and the chat rendered. - [Nine targeted restart/replay cells](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-35645850088-1/) passed on `1fe2fe275`, including the original failure, across native Claude/Codex and local/Daytona; all cleanup passed. - [Initial six-story campaign](https://github.com/paperclipai/paperclip/actions/runs/35644832817) retained all six failures: asynchronous switch assertions, unavailable fixture paths, and rich-text escaping in raw command comparisons. The corrected fixtures preserve the same behavioral assertions. - [Six-story campaign v2](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-35646270035-1/) on `8232773a0`: 4/6 passed (both settings cases and both Claude interruptions). Codex could not see the host-temp fixture outside its workspace; this failed before follow-up delivery was exercised. - [Four affected interruption cases](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-35647760635-1/) all passed, including cleanup, on definition v3 / `ad6ac0545`. Files live inside the actual agent workspace and the observed run workspace is verified. Both providers saved Friday in the real plan with the undisclosed brief reference; follow-ups persisted while the original run was active. Together with both unchanged settings cases from v2, all six new scenario variants have passing live evidence. - Final head `ad6ac05456646c09d3452e320279457625353948`: 54 successful checks, two intentional skips, zero pending/failing checks; mergeable and clean. Fresh Greptile 5/5, zero unresolved findings. - Full typecheck, tests, build, and browser CI passed remotely. One earlier head encountered a signoff-policy browser timing failure; the final head passed that shard. - Local pnpm wrapper could not fetch its version/signature metadata in the restricted environment; local eval checks used the installed Node executables. Repo-wide validation was completed by GitHub Actions. ## Risks These are eval-only changes. The file wait is a timing fixture in the isolated agent workspace, not a production runner hook. Native Codex host-filesystem isolation stays unchanged. It has a two-minute limit and is released in `finally`. The prepared-agent settings case is not full native onboarding: the wizard currently offers legacy adapters. The disabled-entry assertion uses full document navigation, which clears the prior React Query cache; preserved history is checked through the public API and re-enabled chat. No production prompt, rollout default, adapter behavior, or credential policy changes. Active-task reassignment and worker-crash recovery remain outside these new cases. ## Model Used OpenAI Codex, GPT-6, with repository tools and code execution. The exact deployment model ID and context window are not exposed in this task. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>	2026-09-21 16:18:06 -05:00
3 people	3790ca2f13	fix(runner): repair approval and Stop races and eval infrastructure (#13750) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Runner tasks must continue after approval and stop when the user presses Stop. > - Live evals found races at approval delivery and provider startup. > - Browser readiness and CI setup errors also hid the actual task results. > - This pull request fixes those races and the related test infrastructure. > - Regression tests and saved live reports show which cases now pass. ## Linked Issues or Issue Description Companion eval definitions PR: https://github.com/paperclipai/paperclip-evals/pull/25 (AgentCore paused and provider/environment infrastructure). Related: #13741 now supplies the late-startup Stop fence and warm-attachment recovery; this PR retains that fence and extends startup tracking and regression coverage to both native backend paths. #13539 introduced queued approvals during active runs. #13738 fixes child assignment, task replies, and warm process continuity and is already in the base. #13291 concerns automatic continuation of interrupted legacy sandbox runs; this PR fixes native startup cancellation and does not change that recovery policy. **What happened?** An accepted service approval could wait after its source run stopped. Stop could return success before the provider handle existed. Work could then start after Stop, or a cancelled run could be recorded as failed. Some E2E tests also failed on unloaded browser content or irrelevant reply wording. Runner CI could fail before model work because of dependency or sandbox setup. **Expected behavior** Deliver each settled approval once after its source run stops. Do not start work after an acknowledged Stop. Preserve the audited cancellation. Test the intended product behavior with a ready browser and verified runtime dependencies. **Steps to reproduce** 1. Approve a service request while its source run is active. Let the run finish. Check that its result starts one continuation. 2. Delay provider startup. Press Stop before its handle is available. Check cancellation, then submit `/new`. 3. Run the browser, warm-workspace, and Stop-and-redirect cases from the linked report. **Paperclip version or commit** The branch includes master at `9d19f98b5`. The report records the original source for each focused attempt. **Deployment mode** Isolated local development instances and disposable Daytona sandboxes. ## What Changed - Deliver settled tool-action results for the exact company and source run during final cleanup. Keep the existing idempotent receipt and periodic recovery sweep. - Wait for startup to hand off its provider handle before acknowledging Stop. Reject first-turn admission after cancellation. Preserve a matching audited pending or acknowledged cancellation. - Wait for mounted task history and connector controls in browser tests. Record failure evidence. Grade workspace contents and process continuity separately from exact reply wording. Require each warm-turn marker once and in order, allowing surrounding prose. - Stop-and-redirect now checks that the source file exists and work is active before Stop. - Resolve target dependency locks in an uncredentialed CI job. Verify the lock artifact hash. Keep orchestration and publication on the trusted workflow revision. - Materialize the pinned OpenCode executable and configure the exact Codex executable's user-namespace profile before provider credentials are available. - Compress Daytona directory uploads with gzip. Preserve files, executable modes, symlinks, empty directories, and confinement checks. - Classify file-transfer RPC deadlines as infrastructure. Keep unrelated runner RPC failures visible. ## Verification - [Focused live report with screenshots and original attempts](https://pages.paperclip.ing/runner-reliability-20260921/): 14 of 15 selected Product E2E cases pass across the recorded revisions. Claude and Codex Stop → `/new`, Claude service approval, delegation, both hiring/reuse cases, and native Daytona warm continuity pass. - Two credentialed Runner smoke cases pass. These are not full protocol coverage. - E2E harness after the master merge: 429 tests pass. E2E and server TypeScript checks pass. - Daytona plugin: 239 tests pass, 6 skipped. Plugin TypeScript build passes. The compression test fails against the old code and passes with the change. - Runner backend/runtime regression group: 161 tests pass. Cancellation/startup selection: 26 tests pass. Approval delivery: 34 real-database tests pass. - Workflow security: 7 tests pass. Both edited workflows pass actionlint. Runner TypeScript and Rust builds pass. - After merging master, all 389 native executor tests pass, including both native backend paths and late startup after the Stop deadline. - Post-merge `pnpm -r typecheck` and `pnpm build` pass. The monolithic local `pnpm test:run` was interrupted to integrate master and is inconclusive. The [hosted CI test partitions](https://github.com/paperclipai/paperclip/actions/runs/35620461738) pass on `50a3e43822bcba1e0d07b1b45b0be91cbf9312da`. An unchanged sandbox callback schema test initially received HTTP 503. It passed five isolated local runs, its full local test file, and one failed-job CI retry. No assertion was weakened. ## Risks - Stop can wait for the bounded startup handoff. If it cannot settle, the existing pending-recovery state remains instead of a false acknowledgement. - Immediate approval delivery must remain idempotent across cleanup and recovery sweeps. Tests cover duplicate delivery and company/run boundaries. - The workflow changes still need hosted Linux verification. They retain the trusted workflow and credential boundaries. - Gzip reduces the observed provider upload from about 1.8 GB to 663 MB. It does not yet fix the remaining Claude Daytona transfer timeout. That recovery test never reached Claude, so recovery remains unverified. Use a matching image with the verified provider package preinstalled for the next recovery test; retain cold-upload coverage separately. - The report preserves diagnostic runs with missing source metadata and marks them as such. It does not claim a new full-suite pass. - This PR adds no new prompt policy or historical status reconciliation. ## Model Used OpenAI GPT-6 through Codex performed the primary implementation and review. The exact primary backend model ID is not exposed in this session. OpenAI `gpt-5.6-luna` assisted with bounded infrastructure work and verification. The agents used repository tools, code execution, and browser tests. The exact backend revision and context-window size are not exposed in this session. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing> Co-authored-by: OpenAI GPT-6 <noreply@openai.com>	2026-09-21 12:50:50 -05:00
DottaandPaperclip	0103cb2292	test: use neutral references in chat hiring evals (#13752) ... ## Thinking Path > - Paperclip helps people manage agents and their work. > - The agent chat hiring eval checks delegation, saved output, and worker reuse. > - It asks a worker to include a unique reference in each document. > - The open wording let the worker choose a credential-style label. > - The existing redactor removed that reference and failed the coordination check. > - This PR specifies a neutral reference line while keeping the same grading checks. ## Linked Issues or Issue Description Refs #13741. **What happened?** The Codex hiring eval saved a checklist with `Tracking token: [REDACTED]`. The runner treats the chosen label as credential syntax. The previous prompt only asked for the identifier and did not choose its label. This tests a redaction boundary unrelated to hiring and reuse. **Expected behavior** The coordination fixture requests ordinary business content with a neutral reference label. The grader still requires the exact identifier in the saved output. **Steps to reproduce** Run `agent-chat-hardening.runner-codex.local.hire-delegate-reuse` with the previous fixture. The retained failing attempt is in [campaign 35617045456](https://github.com/paperclipai/paperclip/actions/runs/35617045456). ## What Changed - Request `Reference: ...` in the checklist and review documents. - Increment the hardening suite definition to version 5 and record the reference format. - Document the fixture boundary. Production redaction and all grading checks stay unchanged. ## Verification - `pnpm test:e2e:runner:typecheck` passed. - `pnpm test:e2e:runner:unit` passed: 424 tests in 37 files. - The catalog lists exactly the Codex and Claude local hiring cells for the selected case. - [Live campaign 35620731321](https://github.com/paperclipai/paperclip/actions/runs/35620731321) passed both selected local cells on `d8d7afe21`: native Codex (`gpt-5.6-sol`) and Claude (`claude-sonnet-5`). Both passed on attempt 1, including cleanup. [Published eval report](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-35620731321-1/). - Inspected saved evidence: each provider preserved both exact reference lines, used the same hired worker for checklist and review, and completed the final status query. Definition version 5 and hash `2c1c9f754c049c3e7cafd6c8d0a137e7ca06d546ce1e7b07ad5b7823f0f28db9` distinguish these results from the prior prompt. - [PR CI 35620741101](https://github.com/paperclipai/paperclip/actions/runs/35620741101): full build, type checks, and test partitions passed. One unrelated Telegram integration test initially failed because two random fixture company IDs produced the same seven-character issue prefix. The failed shard passed on one retry; no test code was changed. All latest-head merge checks are green. - Greptile reviewed `d8d7afe21` at 5/5 with no review threads. ## Risks The live models can still fail the coordination workflow. This change does not qualify or change credential-redaction policy. Earlier failed attempts remain part of the evidence; the new fixture has a distinct definition version. ## Model Used OpenAI Codex, GPT-6, with repository tools and code execution. The exact deployment model ID and context window are not exposed in this task. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge Co-authored-by: Paperclip <noreply@paperclip.ing>	2026-09-21 12:49:52 -05:00
DottaandPaperclip	9d19f98b50	fix: harden native chat recovery and add coordination evals (#13741) ... ## Thinking Path > - Paperclip helps people manage AI agents and their work. > - Agent chat uses native runner sessions to plan, delegate, and track that work. > - A user can press Stop while the native session is still starting. > - The server can acknowledge that Stop without dispatching it, then let the session submit a turn. > - This leaves chat recovery waiting for an execution that the user expected to stop. > - This PR waits for the startup handle, dispatches cancellation, and prevents a late startup from submitting a turn. > - New full-stack evals check the resulting records and outputs across Claude and Codex. > - Those evals also exposed missing ACPX readiness fields, unbounded polling, and an old-run identity check that rejected valid warm handoffs. ## Linked Issues or Issue Description **What happened?** Stop during native startup could record an acknowledged cancellation with `dispatched: false`. The provider could then begin work. A subsequent `/new` stayed queued. A remote Claude follow-up also exhausted the command journal while probing warm-session readiness: ACPX never returned the readiness fields required by the shared transport. Once readiness worked, attachment incorrectly compared the next run descriptor against the old run ID. The 25 ms polling loop could issue 4,800 commands during its two-minute wait, beyond the 500-command bound. The existing chat eval treated lifecycle logs as proof of an active provider turn, so it did not distinguish startup cancellation from active-turn cancellation. **Expected behavior** A Stop during startup must reach the pending session. A late session must not submit a prompt after Stop. Recovery must retain control when startup exceeds the bounded wait. Chat evals must check saved task state, document contents, worker identity, account binding, and duplicate effects. **Steps to reproduce** 1. Start a native Claude or Codex chat turn. 2. Press Stop after process startup is requested but before the provider turn starts. 3. Send `/new`, then send a fresh message. 4. On the affected base, cancellation can be acknowledged without dispatch and the reset stays queued. **Paperclip version or commit** The live Claude baseline reproduced this on `29d6b3509`. The branch also includes master commit `0f5fafe16`. Related work: #13678, #13686, #13693, #13291, #13738. A separate runner reliability branch also contains a startup-wait fix. Its overlap must be reconciled before merging; this branch additionally prevents prompt submission after a late startup. ## What Changed - Wait for a pending native startup before acknowledging a run-scoped Stop. Preserve the existing recovery error when that wait expires. - Keep a Stop guard on startup. Cancel a late handle before it can submit a provider turn. - Add regression tests for normal handle publication and publication after the Stop deadline. - Back off blocked warm-attachment probes. Keep the fast two-snapshot barrier, fail closed, and record changed blockers. - Add red/green tests for delayed readiness, persistent blockers, alternating readiness, and readiness near the deadline. - Publish ACPX readiness and blockers. Preserve the old authority’s event acknowledgement barrier; only settled sessions can proceed to attachment. - Bind warm ACPX descriptors to the validated next authority while retaining old-run event correlation until activation. Preserve session identity and provider profile checks. - Exercise two consecutive run rotations through a qualified fake sidecar, verifying checkpointing, provider identity, pre-activation rejection, and new-run work admission. - Separate startup and active-turn cancellation checkpoints in the browser eval. - Add 18 explicit native chat eval cells: 12 local and 6 Daytona cells across Claude and Codex. - Cover hiring and reuse through managed AI accounts, source-based review, current blocked-task status, request replay after a lost HTTP acknowledgement, server restart continuity, and Stop/reset continuity. - Use ordinary production agent instructions. Enable API tools only for the two coordination cases that need them. - Calibrate the matchers with invalid records and outputs. Require remembered context after restart and a structured status snapshot that distinguishes the current blocker from history and task status from active execution. Compare the public issue mutation contract and relationships during read-only reporting. Preserve before/after source records in failed eval evidence. - Fix the lost-ack browser harness and verify it against a real HTTP server. Check the chat composer after restart instead of waiting for an unrelated document lifecycle event. - Document the scope and limits of each case. ## Verification - The startup regression failed on the unfixed executor and passed after the fix. - `pnpm test:e2e:runner:typecheck` passed. - `pnpm test:e2e:runner:unit` passed: 424 tests in 37 files. - `pnpm exec vitest run server/src/services/native-runtime/native-session-executor.test.ts` passed: 385 tests. - [Baseline live campaign](https://github.com/paperclipai/paperclip/actions/runs/35608208868): Claude Stop reproduced the bug. Codex Stop and Claude hire/reuse passed. Codex delegation was blocked by provider capacity. - [Eval-only startup campaign](https://github.com/paperclipai/paperclip/actions/runs/35609479786): both providers failed as expected. Both persisted `dispatched: false` and left `/new` queued. - [First fixed campaign](https://github.com/paperclipai/paperclip/actions/runs/35610533706) on `c9e95797d`: 10/18 cells passed. Startup Stop passed for both providers. Failed cases exposed eval harness defects and remote continuity failures. All attempts remain available. - [Original workflows and stronger memory checks](https://github.com/paperclipai/paperclip/actions/runs/35611896649) on `c04324fab`: 9/12 passed. Reassignment, local restart memory, and startup Stop passed for both providers; Codex remote restart passed. Claude remote restart exposed the missing readiness contract. Two Codex planning cells hit provider capacity. - [Unchanged-model retry](https://github.com/paperclipai/paperclip/actions/runs/35613854548): Codex planning and backlog creation both passed. - [18-cell campaign with ACPX readiness](https://github.com/paperclipai/paperclip/actions/runs/35614586963) on `6a98ef743`: 16/18 passed, including all local/remote Stop and committed-send cases. Claude remote continuity exposed the next-authority check, now fixed. Codex hiring produced its checklist, but the runner redacted the requested marker after it appeared as “Tracking token: …”. That content-redaction policy is unchanged and remains an explicit limitation. - [Structured status grading](https://github.com/paperclipai/paperclip/actions/runs/35614954725) on `50448c228`: both providers passed on their first attempt, including cleanup. - [Complete read-only state grading](https://github.com/paperclipai/paperclip/actions/runs/35616089011) on `551e13892`: both providers passed. - [Final ACPX handoff and hiring retry](https://github.com/paperclipai/paperclip/actions/runs/35617045456) on `cbd637587`: all three Claude Daytona cases passed (restart continuity, active Stop/reset, and lost-ack replay). Codex hiring reproduced the content-redaction failure: the saved checklist contained `Tracking token: [REDACTED]` instead of the required business marker. All four cases completed cleanup successfully. [Published report](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-35617045456-1/). The only subsequent commit adds the qualified-sidecar integration test; production code is identical to this live proof. - `pnpm test:e2e:runner:browser-support` passed: 5 browser tests without paid models. - Runner TypeScript typecheck passed. All 5 warm-readiness tests pass; two failed with the prior fixed-rate loop, and the late-readiness test failed before the pacing correction. - ACPX readiness and warm-identity regressions each failed before their fixes. All 292 runner-core Rust library tests passed. The qualified-sidecar integration test passes. Rust formatting is checked. - Status-grader regressions for misleading historical mentions and previously unchecked mutations each failed before tightening the oracle and pass now. - [Latest-head CI](https://github.com/paperclipai/paperclip/actions/runs/35617522307) passed on `a4093c8f1`: full build, type checks, test partitions, browser E2E, and native runner checks. Two unrelated tests initially failed (Sentry fixture release attribution and local-service fixture readiness); both passed locally together (35 passed, 5 optional SDK tests skipped) and on the failed-job retry. No changes were made to those tests. - Greptile reviewed `a4093c8f1` at 5/5; both earlier findings are fixed and all review threads are resolved. - The paid live suite is not fully green: the reproducible content-redaction case remains red. This is separate from the passing PR merge checks. No production content-redaction, prompt, model, or completion-policy change is included. - Managed-account hiring and review cases explicitly enable API tools; these do not qualify default new-user onboarding. ## Risks - Stop can wait up to 30 seconds for startup, then use the existing pending-recovery path. This does not prove that remote cleanup has finished. - Blocked warm readiness adds up to 750 ms between later probes with the two-minute remote budget, or about 32 ms with the default five-second budget. Ready sessions retain the short second barrier. - Paid evals can fail because of provider capacity or agent decisions. Each failure needs evidence-based classification. - The HTTP request replay case checks comment idempotency and duplicate effects. It does not prove replay safety for an ambiguous provider tool call. - The new suite is opt-in. It does not increase the default paid campaign. - No production prompts or model selection change. Review-handoff behavior and content-redaction policy remain separate product decisions. The latter can remove harmless business content that looks like credential syntax; the failing attempt is retained. ## Model Used OpenAI Codex, GPT-6, with repository tools and code execution. The exact deployment model ID and context window are not exposed in this task. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>	2026-09-21 10:35:38 -05:00
DottaandPaperclip	0f5fafe16b	fix(runner): preserve task replies and warm process continuity (#13738) ... ## Thinking Path > - Paperclip lets people manage AI agents and their work. > - The Runner connects provider sessions to task state, replies, and delegated work. > - Full-stack tests found lost final replies, rejected helper calls that stopped the parent, and unnecessary process restarts. > - A completed child could also receive a new assignment wake that the scheduler then cancelled. > - This change fixes those boundaries and gives agents clearer teammate instructions. > - The tests retain strict completion and process-continuity requirements. ## Linked Issues or Issue Description **What happened?** A generated attachment comment could suppress an agent's final reply. A known Codex helper could stop its parent when it requested a Paperclip tool. Native Daytona processes restarted between turns because Paperclip minted an unused GitHub broker token. Reassigning a completed child queued a run that immediately cancelled. Revision instructions also allowed agents to do work assigned to a named teammate themselves. **Expected behavior** Keep the final reply. Reject helper tool requests without borrowing parent authority or stopping the parent. Keep an unconfigured sandbox process alive between turns. Treat assignment-only changes to completed tasks as metadata changes. Preserve explicit teammate assignments during revisions. **Steps to reproduce** Run the retained Runner E2E cases for file handoff, teammate reuse, Daytona warm continuity, and Legacy Claude interview/plan acceptance. The focused regression tests reproduce the reply, helper, process-lifetime, and assignment-wake defects without provider calls. **Paperclip version or commit** The live lifetime and completion campaign used `db3857807`. This PR replays the changes on master `c65fc9e3c`. See Verification for the limits of that evidence. **Deployment mode** Isolated local instances and native Runner sessions in Daytona sandboxes. Related work: #13546 handles a different queued-run issue after an issue-lock compare-and-set failure. This PR prevents the unnecessary assignment wake earlier. #13410 covers retained user services; this PR covers the provider process. No duplicate fix was found. ## What Changed - Exclude generated deliverable-binding comments from final-reply deduplication. Preserve the attachment and explicit user-facing replies. - Reject Paperclip tool and input requests from known Codex helper threads without terminating the parent. Keep unknown-thread rejection intact. - Explain how to hire or reuse a persistent teammate and preserve named delegation on revisions. Update generated protocol fixtures. - Use stable, token-free GitHub wrappers for unconfigured native sandboxes. Preserve credential isolation, configured-account rotation, and cleanup after partial staging failures. - Do not queue assignment-only wakes for done or cancelled tasks. Keep explicit reopening behavior. - Make warm-continuity fixtures create real review cards. Read the persisted final response selected by production presentation logic. Missing selected evidence still fails. ## Verification - Before rebase: 560 focused route, native-executor, and launcher tests passed. The new regressions were reproduced before their fixes. - Live E2E: Legacy Claude interview/plan acceptance passed 3/3 repetitions. Daytona warm continuity passed 2/3 full repetitions. Each successful run retained one process and provider session for all three turns. - The remaining Daytona repetition stopped after a same-URL browser reload left the page blank. Both completed turns retained the same process. Its failed verdict remains unchanged; this PR does not claim the blank-page cause is fixed. - Reports: https://pages.paperclip.ing/runner-e2e-lifetime-race-20260920/investigation.html and https://pages.paperclip.ing/runner-e2e-behavior-followups-20260919-results/investigation.html - Post-rebase `pnpm build` and `pnpm -r typecheck` passed. All 414 Runner E2E harness unit tests and its typecheck passed. Codex protocol tests: 88 passed, 2 ignored. - Latest-head CI: 55 successful checks and 2 intentional skips. Greptile: 5/5 with no review threads. The unchanged workspace exposure tests hit a fixed-port collision on the first CI attempt; their local suite passed (25 tests, 3 platform skips), and the CI shard passed on one retry. - The duplicate local `pnpm test:run` was stopped after the full hosted general and serialized test shards passed. It did not finish locally and is not counted as a local full-suite pass. ## Risks Configured GitHub accounts retain run-scoped credential rotation and can still restart warm processes. That limitation requires a separate design. Known provider helpers cannot use Paperclip coordination tools directly; they must return findings to the parent. The delegation prompt is an instruction, not an enforced guarantee; Codex Mini hiring/reuse failures remain open. No schema or workflow changes are included. ## Model Used OpenAI GPT-6 through Codex, with repository tools, code execution, and parallel coding agents. The exact deployment suffix and context-window size are not exposed in this session. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub issues and shared reports) - [x] My branch name describes the change and contains no internal Paperclip ticket id or instance-derived details - [x] I have run focused tests locally and they pass; full hosted test shards also pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>	2026-09-21 08:56:35 -05:00
DottaandPaperclip	7bc03e0acd	feat(runner): default harnesses to full auto and support task reassignment (#13686) ... ## Thinking Path > - Paperclip lets people manage AI agents and their work. > - Agent Chat uses native runners to save plans and coordinate tasks. > - Provider defaults differed across harnesses and could stop unattended work at a second permission gate. > - Agents also lacked a dedicated tool to move existing work to another agent safely. > - This change defaults native providers to full automatic permission for provider tools and connected tools. > - A guarded reassignment tool preserves task identity, stops the previous run, and schedules the new owner once. > - Codex and Claude chat acceptance tests now use production permission defaults. ## Linked Issues or Issue Description **Subsystem affected** Native runner, ACPX Claude permission policy, task authority, and Agent Chat acceptance tests. **Problem or motivation** A user can authorize an agent to save a plan or create a task, but Claude's default provider gate can still stop that action. Reassignment needs a dedicated operation that preserves context and avoids concurrent owners or unintended recovery runs. **Proposed solution** Default Claude/ACPX to `approve-all`, OpenCode to `allow`, and Codex to `never`. Apply the defaults at configuration, execution, fresh-session, resume, driver, and proxy boundaries. Keep explicit permission settings and server-side company, claim, task-mode, and approval checks. Add `reassign_task` with version checks, durable idempotency, audited cancellation, and guarded successor scheduling. **Alternatives considered** A Paperclip-only allowlist still blocks provider tools and other connections during unattended work. Full automatic permission is the requested product default. Recreating a task discards its identity and history. Updating assignment without stopping the previous run can leave two agents working on the same task. **Roadmap alignment** This extends the existing planning, delegated work, governed tool access, and recovery features. It adds no new service or schema migration. Recent related tasks and open PRs were checked for duplicate work. **Additional context** Related: #13678 (Agent Chat tools and recovery), #13677 (remote runner startup). The stacked legacy-adapter companion is #13693. This also fixes the deployed-server artifact fallback needed to stage the current runner binary. ## What Changed - Default Claude/ACPX to `approve-all`, OpenCode to `allow`, and Codex to `never`, including missing settings at direct driver and proxy entry points. These defaults cover provider tools and connected tools. Preserve explicitly configured restrictive modes. - Include assigned approval reads using canonical side-effect classifications, so verifying a recorded approval does not trigger another provider gate. Paperclip approval decisions still enforce controller authority. - Carry the new permission mode through server configuration, execution contracts, recovery identity, TypeScript, and Rust. Keep `approve-paperclip` as an optional restricted mode, with exact SDK rules and closed unknown requests. It is not a default. - Add `reassign_task` to the semantic catalog, controller, mock authority, and generated contracts. - Guard reassignment with company authorization, expected owner and version, protected-state checks, and durable retry receipts. - Honor explicit backlog task creation atomically with the initial plan, without scheduling a wake. Preserve backlog holds regardless of dependency readiness. - Stop active work before changing ownership. Restore the prior owner through a guarded, idempotent wake if final handoff validation fails. Keep intentional reassignment stops out of failure recovery. Preserve backlog and blocked states without waking them early. - Add authorization, concurrency, replay, stop, and permission boundary regressions. Add Codex and Claude chat reassignment cases and run native chat cases with production defaults. - Clarify shared runner guidance: save plans and Paperclip documents directly with `write_document`; create and register a local file only when a downloadable file is requested. - Document provider defaults and the operator choices for existing agents. ## Verification - Current head `d82fbb0f03546d27cecf072250e4172e0b1ee662`: **55 checks passed**, with two intentional skips. [PR checks](https://github.com/paperclipai/paperclip/pull/13686/checks). - Greptile reviewed that exact head at **5/5**. The security reviewer acknowledged the intended full-auto default, and the acknowledged discussions are resolved. - Full workspace `pnpm -r typecheck` and `pnpm build` passed locally after rebasing onto current master. Targeted adapter/server, runner, API, default/resume, and heartbeat configuration tests passed. - **All six real-provider acceptance cases passed on their first attempt, with cleanup passing:** plan handoff, task reassignment, and backlog creation/status, each on native Claude and Codex. Evidence records Claude's effective `approve-all` mode. [Campaign and downloadable evidence](https://github.com/paperclipai/paperclip/actions/runs/35469926548). - The live campaign tested combined revision `a37881c824dcd7170380fc4b788732fc743e5da7`. The final PR heads add only a heartbeat test expectation correction; application code is unchanged from that live-tested revision. - The campaign's result-enforcement job passed. Its separate report publisher failed because the trusted workflow's `patchedDependencies` configuration differs from its frozen lockfile. All six results and screenshots remain available as GitHub artifacts. The overall manual workflow is red for this publishing failure. - Full-suite coverage is supplied by the passing CI partitions. The separate unsharded local run was stopped after the corresponding CI partitions passed; it is not counted as a completed local run. - Reassignment tests cover stale state, cross-company access, denied authority, cancellation failure, compensating wake, and idempotent retries. Backlog tests verify the original creation audit, saved plan, exact task count, and absence of task-bound runs. ## Risks - Agents with no explicit permission mode now receive full provider tool permission, including connected tools. This is a deliberate broad default. Existing explicit restrictive modes still apply. Controller authorization, company isolation, workspace boundaries, and Paperclip governance remain in force. - Reassignment crosses run cancellation and task ownership transactions. Durable stop intent, revalidation, audit receipts, and guarded queue dispatch cover interruptions and retries. - The new permission enum requires a current runner artifact. The remote artifact fallback uses the same resolved controller binary for upload and execution. - Live provider behavior remains subject to the selected model. Targeted live results do not qualify the full catalog. ## Model Used OpenAI Codex, based on GPT-6, with code execution and repository tools. The exact deployment model ID and context-window size are not exposed in this session. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [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>	2026-09-19 16:49:18 -05:00
DottaandPaperclip	04546c82d5	fix(runner): reconnect Daytona sessions after controller restart (#13691) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - The native runner can execute a task inside a Daytona sandbox. > - The sandbox can keep running when the Paperclip controller restarts. > - Recovery treated sandbox process IDs as local process IDs and selected the wrong recovery path. > - Live verification also found races between startup, shutdown, and queued task cleanup. > - This pull request verifies the existing remote owner and orders those transitions. > - Users can continue the same task and provider session after a controller restart. ## Linked Issues or Issue Description **What happened?** The Daytona `recover-controller` cases failed with `runner_state_identity_mismatch`. Remote process IDs can be absent on the controller or collide with unrelated local processes. Recovery then looked for remote state in the local runner directory. Later turns could also start before the previous executor released its sandbox resources. **Expected behavior** Reconnect to the original sandbox and authenticated runner. Preserve the task, provider session, and queued comments. Reject a replacement sandbox or mismatched identity. Do not start another provider during reattachment. **Steps to reproduce** Run the `everyday-workflows` `recover-controller` case for `runner-codex` or `runner-acpx-claude` in Daytona. The browser creates a Python tool, requests a revision, restarts the controller during execution, and queues another revision. It then downloads and tests the final ZIP. Related: #13682 is the preceding operational fix. #13291 addresses legacy sandbox conversation recovery, a different execution path. #13666 includes broader run-capacity work; this change guards cleanup of an existing native task executor. ## What Changed - Add remote runner recovery without interpreting sandbox PIDs on the controller. - Verify the original provider lease, remote workspace, durable state, process marker, and authenticated PRP authority before adoption. - Compare the process marker with live Linux boot identity and start ticks to reject PID reuse. Read virtual proc files through the guaranteed Node runtime; unavailable proof blocks adoption without blocking a fresh launch. - Make the E2E supervisor own the actual server process so forced restart cannot leave a late database closer behind. - Scope the chat delivery lease test to its own fixture instead of draining other tests’ pending deliveries. - Preserve provider-attempt counts and recorded evidence during reattachment. - Serialize an idle-session checkpoint with admission of the next native turn. - Wait for an in-progress startup to acknowledge restart detachment. Fail after a bounded deadline if it cannot. - Keep a queued comment waiting until the previous native task executor releases its resources. Allow unrelated tasks to continue. - Update the Daytona image's resolved lock digest to match current dependency manifests. - Add classifier, ownership, process, startup, checkpoint, and queued-admission regression tests. Document recovery behavior. ## Verification - 415 focused tests passed across native execution, restart recovery, workspace synchronization, queued admission, and real-process restart tests. The final Node-based fingerprint change passed all 375 native-session tests. - Runner harness unit tests: 394 passed. Chat integration shard 2: 335 passed after fixture isolation. - The exact fingerprint command succeeded twice in a disposable Daytona sandbox and returned the same identity; the sandbox was deleted. - 11 real-process restart integration tests passed, including absent and colliding remote PIDs. - Repository typecheck and final build passed. Broad local checks found machine-dependent database startup and timing failures; focused retries passed. The final-revision PR pipeline is green. One unrelated browser shard hit a five-second blank-page timeout on the first run and passed its targeted retry. - Final-revision local headed browser E2E: `everyday-workflows.runner-acpx-claude.daytona.recover-controller` passed on attempt 1 in 4.7 minutes, **40/40 checks**. Manual browser inspection confirmed Done, all three ZIPs, and delivery of the queued follow-up. All three runs succeeded using the same provider session. The harness downloaded and independently tested the final artifact. - Final-revision Daytona campaign: https://github.com/paperclipai/paperclip/actions/runs/35463999611 — **Codex passed first attempt (4.8 minutes); ACPX Claude passed first attempt (6.1 minutes)**. Campaign aggregation/publication is finishing; both test jobs succeeded. - Greptile reviewed `beb08d8493b3286f5bb988dead369ff8c96a395d`: **5/5**, no open findings. - Staging browser verification is pending selection of a disposable staging instance and removal of a Chrome extension UI block. ## Risks - Recovery now depends on the original sandbox remaining available. A replacement or mismatched identity still blocks adoption. - Shutdown waits up to 30 seconds for a native startup to reach a safe detach point. An unfinished startup returns a clear failure instead of a false detach receipt. - Queued native work on the same task waits for cleanup. Unrelated tasks remain eligible. - The image digest update rebuilds the Daytona runtime image. No database migration or public API change is included. ## Model Used OpenAI Codex, GPT-6, with repository inspection, code execution, and browser tools. The runtime does not expose the exact deployed model ID or context-window size. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>	2026-09-19 16:13:34 -05:00
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 c1f6c3310. **Deployment mode** Native runner and Runner E2E harness, local and Daytona. ## What Changed - Add up to three schema locations and missing field names to rejected completion-tool feedback. Limit the message to 512 bytes. Do not echo input values or unknown input keys. - Preserve generic errors for other or unauthorized tools. - Exempt only expected cancellation, shutdown, and process-loss outcomes in fault-injection tests. Apply the same rule while polling and grading. - Fail promptly when persisted review timestamps prove the required blocked-parent ordering was not exercised. Wait when separately fetched snapshots lack that evidence. Keep the boundary requirement. - Use the CLI export from the declared Playwright test dependency. - Add red/green regressions and document the interruption rule. ## Verification - 393 Runner E2E harness tests pass. - 291 runner-core library tests pass. - Harness typecheck and runner TypeScript build pass; Rust formatting and git diff checks pass. - The baseline completion regression and three lifecycle assertions failed before the fix and pass after it. - Fresh worker-setup rerun: https://github.com/paperclipai/paperclip/actions/runs/35449301275 (7/8 passed). Mini completed the child review and both tasks, but did not enter the blocked-parent-before-review ordering required by that case. The new diagnostic identifies this unexercised boundary promptly; it does not turn the case into a pass. - Candidate Mini rerun: https://github.com/paperclipai/paperclip/actions/runs/35449686308. The recording has one rejected completion followed by success, compared with 12 validation errors in the baseline. The case still fails because it does not hire the requested teammate, despite delivering a ZIP that passes artifact checks. This is not a behavioral pass claim. - Updated report: https://pages.paperclip.ing/runner-e2e-operational-35444497313/investigation.html. - All 55 PR checks are successful or skipped on 4d2c91869, including repository typecheck, build, tests, native Runner checks, and Greptile 5/5. The reviewer withdrew the diagnostic finding after confirming the conservative behavior avoids false rejection from non-atomic snapshots. Local verification was limited to the affected harness and runner. ## Risks Schema feedback must remain bounded and exclude submitted values. Stricter fault grading can expose previously hidden failures. The Daytona restart identity bug and remaining behavior failures are not fixed here. Runtime authorization, completion validation, and production prompts remain unchanged. ## Model Used OpenAI GPT-6 via Codex, with repository inspection, code editing, and test execution. The exact deployment identifier and context-window size are not exposed in this session. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>	2026-09-19 10:51:22 -05:00
DottaandPaperclip	c1f6c3310a	fix(runner): repair catalog runtime and grading boundaries (#13676) ... ## Thinking Path > - Paperclip manages tasks across persistent agent sessions. > - The full Runner E2E catalog exposed failures in session restoration, tool validation, and test controls. > - These failures prevented valid work from resuming or made a valid interaction fail the test. > - Invalid completion reports also reached finalization before the provider received useful feedback. > - This pull request repairs those boundaries without changing production prompts or approval policy. > - Focused regressions and fresh paid cases verify each fix. ## Linked Issues or Issue Description Follow-up to #13655. Stacked on the trusted worker prerequisite fix in #13674. **What happened?** Read-only skill uploads failed in resumed Daytona sandboxes. Invalid criterion IDs escaped tool validation. A progress event could park a run before its tool response settled. Partial question forms hid required answers. Two test assumptions rejected valid plan keys or failed to navigate an optional question page. **What did you expect to happen?** Resume identical skill bundles, give repairable feedback for malformed completion calls, preserve in-flight tool responses, show all required questions, and test the rendered workflow accurately. **Steps to reproduce** Inspect the failed cases in https://github.com/paperclipai/paperclip/actions/runs/35417932353. Fresh campaigns: https://github.com/paperclipai/paperclip/actions/runs/35444497313 and https://github.com/paperclipai/paperclip/actions/runs/35445327618. The later backup cleanup is tested in https://github.com/paperclipai/paperclip/actions/runs/35446477285. Combined report: https://pages.paperclip.ing/runner-e2e-operational-35444497313/investigation.html. ## What Changed - Compare immutable archives before reusing read-only Daytona bundles. Reject corrupted content and preserve unrelated files. - Validate exact criterion IDs before accepting completion. OpenCode returns a tool error instead of emitting a result that terminates runnerd. - Complete the activity item for rejected OpenCode calls. - Remove retired read-only harness backups without altering live files or following symlinks. A fresh paid rerun exposed this later checkpoint-cleanup failure. - Exclude progress messages from the governed-wait completion boundary. - Reject newly created question forms that omit questions or contradict their stored answer semantics. Keep historical rows readable. - Navigate all rendered question pages and recognize revision-bound descriptive plan keys in the continuation suite. ## Verification - Harness unit suite: 383 tests pass. Harness typecheck passes. - Native session executor and status corpus: 381 tests pass. - Shared question and interaction-service tests: 42 pass; native question bridge and executor: 360 pass. Daytona sync: 21 pass, including foreign-owner archives and corrupted immutable content. - OpenCode driver: 29 tests pass, including wrong, missing, and duplicate criterion IDs followed by a valid retry. - Repository typecheck and build pass. The later OpenCode activity fix also passes its package build. - The latest commit passes all 52 PR checks and Greptile 5/5. The backup-cleanup fix also passes 351 related local tests and server typecheck. Local full-suite coverage completed across runs. adapter-auth-signal-routes and pipelines-routes encountered transient socket resets; both pass on retry, and all remaining 24 serialized files pass. Paid reruns are complete: 27 of 29 unique cases pass using the latest recording per case. Both Daytona controller-restart cases still fail with runner_state_identity_mismatch; the report describes this remaining runtime issue. Eight affected cells need #13674 on master before their rerun. ## Risks Creation rejects inconsistent dual question representations but does not change historical records. Immutable bundle comparison must verify bytes before skipping extraction. Completion feedback must use the contract bound to the current run. Durable suspension and approval checks remain enforced. Production prompts are unchanged. ## Model Used OpenAI GPT-6 via Codex, with repository inspection, code editing, and test execution. The exact API model ID and context-window size are not exposed in this session. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [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>	2026-09-19 09:27:48 -05:00
DottaandPaperclip	4cfc0e3f6c	fix(runner-e2e): provision complete worker prerequisites (#13674) ... ## Thinking Path > - Paperclip manages work performed by AI agents. > - Runner E2E tests verify that work in local and remote environments. > - The full catalog exposed setup failures before agents could execute tasks. > - ACPX Codex missed sandbox provisioning, and new artifact cases missed Docker preparation. > - A host Claude version probe also stopped native Claude stories that use a packaged provider. > - This pull request repairs trusted worker setup and keeps its selectors covered by catalog tests. > - The resulting reruns can measure behavior instead of missing prerequisites. ## Linked Issues or Issue Description Follow-up to #13655. Full-catalog campaign: https://github.com/paperclipai/paperclip/actions/runs/35417932353. **What happened?** ACPX Codex could not start its sandbox. New artifact stories missed Docker preparation. Native Claude stories tried to spawn an unrelated host CLI. The report job failed on trusted lockfile drift. **What did you expect to happen?** Prepare each worker's required capabilities before paid execution and publish the retained results from trusted code. **Steps to reproduce** Run local ACPX Codex, everyday agent-review-handoff, or native Claude everyday cells in the full-stack workflow at 43acbcc39. ## What Changed - Include local ACPX Codex in exact-binary sandbox provisioning and preflight. - Prepare the pinned artifact oracle for agent-review-handoff. Do not require it for skill creation. - Remove host CLI version probes from native everyday stories. - Retry GitHub actor lookup up to three times, with a deadline, while retaining all authorization checks. - Resolve reporter dependencies from the trusted checkout before its frozen install. - Test worker selections against the catalog and document the default-branch requirement. ## Verification - `pnpm test:e2e:runner:unit`: 383 tests pass. - `pnpm test:e2e:runner:typecheck`: passes. - PR checks: 54 passed, two intentionally skipped. Greptile: 5/5, no inline findings. - The paid workflow reads trusted setup from master. These setup changes need to land before the affected Linux cells can verify them. Runtime fixes and other affected reruns are on a separate branch. ## Risks The setup selectors decide which workers receive sandbox policy and Docker preparation. Catalog coverage checks their scope. Actor lookup still fails closed. Reporter dependency resolution uses only the trusted checkout; target branch code does not receive publication credentials. No production prompt changes. ## Model Used OpenAI GPT-6 via Codex, with repository inspection, code editing, and test execution. The exact API model ID and context-window size are not exposed in this session. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [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>	2026-09-19 09:27:15 -05:00
DottaandPaperclip	43acbcc398	fix(runner): preserve sessions and complete question and approval continuations (#13655) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - The native runner connects task state to provider sessions. > - Follow-up turns must retain provider memory and carry new user direction. > - Lost session IDs caused repeated context and extra input tokens. > - Native question answers and approval races could leave valid work blocked. > - This pull request repairs those paths and adds regression coverage. > - Agents can continue accepted work without repeating the conversation or losing the user's answer. ## Linked Issues or Issue Description Refs #13574. That merged PR shortened continuation prompts and moved question instructions into tool documentation. This change preserves sessions and fixes failures exposed by broader testing. Related runtime work: #13408 and #13410. **What happened?** Native follow-up turns could lose the provider session ID. Completion guidance could replace the original task with its latest comment. Claude native questions could remain pending after the user answered. Approval during a running tool call could suspend the run before the tool response arrived. Onboarding and chat handoff instructions also caused repeated planning or missing plan documents. **Expected behavior** Reuse a valid provider session. Send only new events when that session already has the history. Preserve the task requirements and apply later user direction. Store the question answer and deliver it to the waiting run. Finish governed tool responses before suspending. Execute the accepted plan without asking for the same approval again. **Steps to reproduce** Run the continuation, local-session-integrity, first-task, and agent-chat suites with native Codex and Claude. Include provider-question-bridge, accept-while-running, and plan-handoff. **Paperclip version or commit** This branch is based on master d54b75011. The active full catalog run tests 4e75881db. Later review fixes have separate regression coverage. **Deployment mode** Isolated local instances and Daytona sandboxes in the existing Runner full-stack E2E harness. ## What Changed - Retain provider session identity across turns and late usage snapshots. Send new continuation events on session reuse, with full context available for a fresh session. - Preserve task requirements and later direction in completion guidance. Return the current contract revision after a stale completion submission. - Bridge native Claude questions to saved Paperclip cards. Submit answers through the saved card and resume the same run. - Delay governed suspension until tool results settle. Add a deterministic test barrier for approval during an active run. - Clarify free-text question examples, explicit onboarding plans, and execution of accepted chat plans. - Fix continuation readiness, verified output evidence, and declared screenshot collection. - Qualify the legacy Claude test CLI at 2.1.277. The old 2.1.19 CLI did not discover mounted skills. Update the existing workflow pin and isolated launcher together. - Refresh the Daytona image lockfile integrity pin after reviewing master patch updates. - Carry continuation mode as runtime metadata instead of inferring it from user-visible text. Install the test Claude CLI without lifecycle scripts. ## Verification - Targeted paid verification: 20/20 cases passed across local-environment campaigns before the rebase. [Report](https://pages.paperclip.ing/runner-e2e-seven-fixes-35397904249/). - Harness checks: 379 unit tests passed; harness typecheck passed. - Latest-head PR checks: 55 passed, two intentionally skipped. Greptile is 5/5; the security scan passes. - Review regressions: 350 executor tests and 204 session/driver tests passed. A script-free Claude install was verified with the actual CLI. - Full catalog, including the explicit-only everyday suite: [run 35417932353](https://github.com/paperclipai/paperclip/actions/runs/35417932353). Completed: **164/205 passed; 41 failed**. [Full dashboard and failure investigation](https://pages.paperclip.ing/runner-e2e-full-catalog-35417932353/). Includes 204 case artifacts and one pre-case GitHub authorization timeout; missing evidence is not scored as a pass. The full run tested `4e75881db`; Final-head metadata/CLI smoke cases both passed. In the separate [six infrastructure retries](https://github.com/paperclipai/paperclip/actions/runs/35419769343), the GitHub timeout case passed and all five Docker preflight failures repeated. [Follow-up dashboard](https://pages.paperclip.ing/runner-e2e-full-catalog-35417932353/follow-up/). - Full local typecheck and build passed on the rebased branch. The full local unit run completed with 657 passing files, two test timeouts and one suite setup timeout. All three affected files passed when rerun in isolation (84 tests). The first full local run was not clean. - Focused regression coverage includes the live question bridge, same-run response delivery, UI routing, stale revisions, approval overlap, and session reuse. ## Full-catalog follow-ups - Test infrastructure: 14 Claude everyday cells probe an absent host CLI; six cells failed pre-task GitHub/Docker qualification (GitHub passes on retry; all five Docker cases repeat; the workflow preflight allowlist omits their case IDs); five ACPX Codex cells cannot create sandbox namespaces. - Runtime: four OpenCode completion-criteria mismatches masked by shutdown errors, one service-approval suspension failure; three Daytona recovery failures encounter existing skill files; one duplicate completion wake. - Confirmed test defects: question pagination and a noncanonical plan document key. - Product/behavior: mismatched visible/required question sets, an attachment instead of the requested task document, one lone-option onboarding question, early completion instead of review, and a Codex Mini completion-schema failure. - The report job itself fails on trusted master’s stale patch/lock configuration. The linked report is rebuilt with the shared renderer from original cell results and public fixture screenshots; it excludes private snapshots, logs and traces. These are investigated follow-ups, not silently regraded passes. First-task passed 51/52. The PR checks are green independently of the broader catalog’s behavioral/infrastructure failures. ## Risks - Session reuse depends on a valid provider identity and context coverage. Fresh-session fallback and reset tests cover this boundary. - Native question delivery spans saved interaction state and a live provider run. Tests cover duplicate events, closed runs, and same-run answers. - Provider behavior varies. The full paid catalog may expose failures beyond these targeted fixes; those results will be reported without relaxing valid approval or output checks. - The legacy Claude version update is limited to test infrastructure. No database migration is included. ## Model Used OpenAI Codex, GPT-6 family, with repository inspection, code execution, and browser/E2E tools. The exact runtime model identifier and context-window size are not exposed in this session. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass (targeted checks and all three timeout-file reruns pass; full-run timeout caveat 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>	2026-09-19 07:42:57 -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
DottaandPaperclip	e26d787928	Shorten continuation prompts and verify question tool guidance (#13574) ... ## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Agents must continue tasks using user answers without losing earlier requirements or approval gates. > - The wake prompt mixed human decisions with prior tool evidence and repeated detailed question instructions. > - Those instructions belong with the question tool, with a short routing hint in the wake. > - The Runner evals need to prove that answers, approvals, and completed work survive later turns. > - This PR shortens the prompts, separates authenticated answers, and adds continuation tests with useful screenshots. ## Linked Issues or Issue Description Refs #13517. This is a follow-up to the merged onboarding skill and Runner E2E work. Related #13539 covers responses received while a run is active; this PR preserves its cases and adds continuation coverage. Existing continuation/recovery and question PRs were searched; none covers this prompt/documentation and eval change. **What existing behavior does this improve?** The instructions sent when an agent continues a task, the native human-input tool documentation, and the evidence captured by Runner full-stack E2E. **Current behavior** The wake repeats a long question-tool guide. Human answers appear alongside untrusted prior results. Screenshot capture can finish at DOM load while the task still shows a spinner, even when backend behavior checks pass. **Proposed behavior** Keep earlier requirements unless the user changes them. Treat clarification as distinct from approval. Give authenticated human responses a scoped field. Keep tool and agent results as evidence. Put detailed question behavior in the tool descriptor and retain one routing sentence in the native wake. Wait for the correct task and loaded conversation before taking screenshots. **Reason and benefit** Reduce repeated prompt text and make authority boundaries clear. Test that real question cards, later answers, approval gates, and completed child tasks still work. Make screenshots useful for human review. ## What Changed - Shorten shared continuation instructions for legacy and native runners. Separate authenticated user responses from tool results and agent summaries. - Remove the detailed question guide from native wake prompts. Keep its behavior in the canonical `request_human_input` descriptor and existing payload schema. Regenerate semantic contracts and fixture hashes. - Add five continuation cases across four local profiles. Add a dedicated choice-then-text case for native Codex and native Claude. All 22 cells join the shared full E2E campaign. - Cover revised scope, clarification without approval, hostile instructions in a handoff file, and reuse of a completed child after restart. Keep production instructions and fixed user facts. - Capture continuation screenshots only when the intended task and conversation have rendered. Add provider-free browser regressions for loaders and wrong-task capture. - Preserve current master’s extra tool and onboarding cases. The default campaign now contains 166 cells; 35 manual everyday cells remain separate. ## Verification - `pnpm -r typecheck`: passed after replay on current master. - `pnpm test:e2e:runner:unit`: 340 passed. Harness typecheck passed. - `PAPERCLIP_PLAYWRIGHT_CHANNEL=chrome pnpm test:e2e:runner:browser-support`: 4 passed. These tests failed against immediate screenshot capture and passed after the fix. - Focused continuation and native-input tests: 36 passed locally. The tool-authority suite could not initialize embedded PostgreSQL locally, including one isolated retry; its 17 assertions did not run locally. The full remote server shards passed on this PR commit. - `pnpm build`: passed after replay on current master. `pnpm test:run` was attempted locally but hit the same embedded PostgreSQL initialization failure; the remaining local run was stopped after complete remote CI passed. This is not claimed as a full local test pass. - [Full PR CI](https://github.com/paperclipai/paperclip/actions/runs/35232755685): passed on `6a22128c14f4552d0613a6d9a25955db4a1ed02f`. All server/chat/workspace/serialized shards, browser shards, Runner checks, typecheck, build, canary and policy checks passed. The isolated native Runner build and security checks also passed: 57 successful checks, with two expected Storybook skips. - Greptile reviewed the exact PR head at 5/5, with no findings or unresolved review threads. The PR has no merge conflicts. - [Live question-docs report](https://pages.paperclip.ing/runner-e2e-question-docs-35227647794/): 3/3 passed at source `83dd132f2` before replay on master. Native Codex and Claude each asked a choice, waited, asked a text question, and saved both answers. Claude also passed a completed-child restart case. All three native turns are checked for absence of the old question block. - [Earlier continuation report](https://pages.paperclip.ing/runner-e2e-continuation-35154943615/): all five continuation cases passed on native Claude. The report retains campaign and revision provenance and separately shows two unresolved onboarding behavior failures. - [Before/after prompt report](https://pages.paperclip.ing/runner-prompt-comparison-20260917/): full text, current recorded Claude inputs, and reproducible reference-token counts. The controlled wake comparison removes 401 reference tokens; the net counted input reduction is 339 after charging the larger tool description. These are text-size estimates, not measured billing savings. ## Risks - Prompt wording affects model behavior. Live results cover the stated cases, not every provider or conversation. Legacy profiles are registered but were not rerun for this change. - The optional continuation field changes prompt data only; there is no database migration or new production API. - Authenticated answer projection excludes generated summaries and agent-resolved interactions. It preserves the answer’s question or approval scope. - The screenshot guard can expose UI loading failures that earlier runs hid. Backend grading alone no longer makes those captures valid. - The two prior onboarding failures remain separate product issues: work before acceptance and a missing saved plan. This PR does not claim the entire onboarding suite passes. ## Model Used OpenAI Codex, GPT-6, with reasoning, repository tools, code execution, and browser verification. The exact deployed model identifier and context-window size are not exposed in this session. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass — targeted tests above; the full local database-startup limit is documented - [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 09:32:54 -05:00