mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-10-14 17:40:37 +02:00
7eea9d8214fec00dfde32bda7fcf9b20a428e330
280
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 DottaandPaperclip
|
433d94ee0b |
refactor(maps): generate indexes from local story and feature metadata (#16214)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Feature recipes and Storybook help contributors find behavior, examples, and verification steps. > - Independent feature changes currently update shared catalogs, indexes, and review hashes. > - Those shared files cause merge conflicts and repeated bookkeeping during parallel work. > - This pull request stores metadata in each feature recipe and story, then generates the combined views. > - Contributors can merge independent work without editing a common index. Git and PR evidence retain change and review history. ## Linked Issues or Issue Description **What existing behavior does this improve?** Maintaining the product, agent-access, and Storybook maps while multiple agents change different features. **Current behavior** A story or recipe change can update `catalog.json`, `INDEX.md`, review hashes, verification tables, and tracked generated navigation. Two unrelated changes then conflict in the same files. **Proposed behavior** Each story declares capability links and classification in `parameters.paperclip`. Each feature recipe declares its navigation and optional verification guidance. Startup, build, and UI typechecking discover these sources and generate ignored indexes and Storybook pages. **Reason and benefit** A routine change edits its own source files. Aggregate metadata is rebuilt from the merged checkout. There is no sidecar registry, shared review journal, or hash acknowledgment to maintain. **Breaking changes** The tracked Storybook catalog and index paths are retired. Consumers use `ui/storybook/generated/` or `maps/generated/` after generation. Contributor instructions and the existing feature-gap browser suite use the new paths. Story and overview IDs remain stable. ## What Changed - Move the existing annotations into 262 story files. Preserve classifications, capability associations, exports, and explicit IDs. - Discover all 35 feature recipes. Store section/order beside each recipe and move durable verification routes out of the shared table. - Remove tracked catalogs, inventories, overview pages, and inline preview ordering. Keep authored preview behavior in `preview-base.tsx`. - Generate the Storybook guide, feature/access Markdown indexes, gap report, page-reference inventory, and preview wrapper automatically. - Update the map contracts and maintenance skills to use Git history and revision-specific PR/CI evidence. - Add schema, identity, regeneration, and actual Git merge tests. Run these through the existing UI Vitest suite. Add focused browser navigation checks. This is one coordinated migration. Most of the 367 changed files contain only moved metadata or deleted generated content. Review the generator scripts, map contracts, Storybook configuration, and tests first. No product API or authorization behavior changes. ## Verification Passed: - `node scripts/check-maps.mjs`: 35 paired areas and 175 capabilities. - `node scripts/storybook-catalog.mjs --check`: 262 suites and 2,485 authored stories after incorporating current master. - `node --test scripts/check-maps.test.mjs scripts/storybook-catalog.test.mjs scripts/storybook-feature-index.test.mjs`: 28 tests, including independent branches merged in both orders with identical generated output and no tracked changes. - `pnpm --filter @paperclipai/ui exec vitest run storybook/map-tooling.test.ts`: the CI entrypoint runs those map tests. - `pnpm check:token-gates`. - `pnpm -r typecheck` and `pnpm build` before the final master rebase. - `pnpm build-storybook`: all 2,517 original story/docs URLs retained. Current master contributes exactly four additional recovery stories. - Focused Playwright navigation checks: search and open a feature without examples; expand verification guidance and check source links; retain capability order and follow a related Foundations suite. The final clean Storybook build passed after deleting every ignored map output. Post-rebase UI typechecking and both browser tests passed. The working tree stays clean after generation. The concurrent-cleanup regression fails with `ENOENT` without the fix and passes with it. All GitHub CI gates passed on `00fc7ec18e`, which also received Greptile 5/5 with no unresolved findings. The final merge commit `1c3c5143a6` incorporates master and resolves only the two modify/delete conflicts by retaining removal of the aggregate index and catalog. Master’s new workspace feature and access guidance is preserved. Map validation, catalog generation, overview generation, all 28 map tests, and diff checks pass after conflict resolution. The maintainer explicitly requested merging without another Greptile review. CI has not been rerun to completion on this merge commit. The local repository-wide `pnpm test:run` was stopped before completion after the earlier CI matrix passed; it is not reported as a local pass. No screenshot baselines or production acceptance are claimed. To repeat the browser check against an owned Storybook server: ```sh PAPERCLIP_GAP_STORYBOOK_URL=http://127.0.0.1:6136 pnpm exec playwright test --config tests/storybook-visual/feature-gap-stories.config.ts map-navigation.spec.ts ``` ## Risks - Existing branches need a one-time rebase to move their catalog changes into local annotations. The PR incorporates the recovery changes from current master. - Changing the same story or capability can still produce a meaningful conflict. This removes the shared aggregate bottleneck. - The generator uses Storybook's existing CSF parser. Literal-only annotations and parser regression tests protect the current contract. - Generated Markdown is available after running the generator; the published Storybook provides a browsable guide. - Shared source changes still require review. Removing hashes removes mechanical acknowledgments; it does not establish runtime parity. ## Model Used OpenAI Codex, based on GPT-6, with repository inspection, code execution, and browser-test tools. The exact deployment model ID and context window were 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 on the previously reviewed head `00fc7ec18e`; final conflict-resolution checks are documented above - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups on `00fc7ec18e`; another review was waived by the maintainer - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing> |
||
|
DottaandPaperclip
|
c8efdbfba4 |
test(storybook): add production examples for feature map UI gaps (#16196)
## Thinking Path > - Paperclip manages AI agents and their work. > - The feature map records the user-facing capabilities. > - Storybook uses the same feature index. > - Step 2 found 49 UI capabilities with no authored examples. > - This pull request adds shipped-component examples with isolated fixtures. > - The catalog records each example's states and remaining production checks. ## Linked Issues or Issue Description Refs: #16167. The verification inventory is merged; this follow-up now targets master. ## What Changed - Add 37 suites and 257 scenarios for all 49 UI capabilities from the step-2 inventory. Keep existing stories and IDs. - Use shipped pages and components. Simulate API replies, sockets, props, and callbacks at their boundaries. - Activate story API fixtures before the application providers read data. Block unregistered API mutations and restore owned storage/fetch state. - Add browser checks for rendering, declared play assertions, fixture reset, and selected mobile/theme states. Update the catalog and verification inventory. ## Verification - `pnpm -r typecheck`: passed. - `pnpm build`: passed. - UI Vitest suite: 730 files and 8,208 tests passed. Fixture boundary tests: 4 passed. - Map/catalog checks, 27 generator/map tests, and token gates: passed. - `pnpm build-storybook`: passed. All 2,248 previous built entry IDs remain present. - Pre-reconciliation static browser suite: 260 checks passed (257 scenarios, token fixture reset, and two mobile/theme cases). All non-play stories assert an explicit subject state; 129 play functions passed. - `pnpm test:run` could not complete on this Mac. Embedded PostgreSQL exhausted host shared-memory allocation. The run also reported native-runner test timeouts. Only this task's verified runner was stopped; other jobs and host settings were preserved. - Reconciled onto merged master `252d9b5077`. The six draft stories and new same-browser reset regression passed (7 checks); 16 draft-persistence tests and UI typecheck passed. Static merge verification: 32 affected-subject/draft checks passed, including same-browser reset. Rebuilt Storybook retains all 2,248 original IDs in its 2,517-entry index. Four additional play-result checks passed: visible onboarding reset, pending probe, filtered-empty runs, and optimistic queued-response removal. UI typecheck and 27 catalog/map tests also passed. Final static browser suite on `3fab35df8d912935fa86ce0de7d32d07e2b5f4c3`: all 261 checks passed (257 scenarios plus fixture-reset and mobile checks). Latest head `3fab35df8d912935fa86ce0de7d32d07e2b5f4c3`: all 55 CI/status checks passed; the two optional Storybook workflow jobs were skipped. Greptile 5/5 with no unresolved threads. - No pinned Linux visual-baseline comparison or real provider journey is claimed. ## Risks Fixtures can drift from production contracts. The catalog records inspected sources and their fingerprints. Capability links provide initial isolated UI coverage; they do not certify every recipe variant, real permissions, persistence, or provider behavior. The new examples expose existing UI limits. Plugin discovery failure stays on Loading. Document and environment-list reads lack dedicated failure feedback; Cases and Inbox fall back to empty views after errors. Goal alignment has display views but no assignment control. These findings remain visible in the inventory. ## Model Used OpenAI GPT-6 via Codex. The exact runtime deployment ID and context window are not exposed in this session. Used code generation, shell execution, and browser verification. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing> |
||
|
DottaandPaperclip
|
aded4197e5 |
fix: make multiplayer task toasts personal (#16153)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - A company can have several human users and shared agents. > - Live task events currently produce toasts for any user who can read the task. > - This makes unrelated work interrupt other users. > - This pull request checks each user's task participation before it permits a toast. > - Users receive relevant task notifications while company views continue to refresh. ## Linked Issues or Issue Description **What happened?** Company task activity and agent failures produce noisy toasts for users who have no involvement in the task. **Expected behavior** A task qualifies when the viewer created it, commented on it, is its assigned user, deliberately acted on it under the Mine rules, or has an explicit user mention in its description or a non-deleted comment. Viewing, agent ownership, responsible-user attribution, and parent participation alone do not qualify. **Steps to reproduce** 1. Sign in as two users in the same company. 2. Have the second user create and update a task that does not involve the first user. 3. Observe a task toast in the first user's company view before this fix. The duplicate PR search found no existing change for personal task-toast eligibility. ## What Changed - Extract the existing Mine participation predicate without changing Mine behavior. - Compute task eligibility from stored tasks, comments, and run associations after WebSocket access checks. Use an exact indexed comment-mention lookup with `LIMIT 1`. - Add optional `toastEligible` metadata to each viewer's event copy. Keep it off the shared event bus. - Require eligibility for live task activity and task-linked run errors. Suppress generic agent errors. - Continue cache updates for quiet events. Refetch visible comments when authenticated events omit hydration details. Ignore stale socket callbacks after account or company changes. - Document toast semantics and add feature-map and agent-access-map coverage. - Add persisted-data, socket, UI, and authenticated browser regression coverage. ## Verification - Final commit: `1dc4f9402c5883744738cfe236ad00fa0bb5ca4c`. - All 55 current-head checks passed. Two Storybook checks were skipped because this change does not affect that coverage. - Greptile approved this exact commit with 5/5. The security scan passed. Both review threads are resolved. - Local `pnpm build`, `pnpm -r typecheck`, `pnpm check:token-gates`, and `node scripts/check-maps.mjs` passed. - The focused socket/UI suite passed 123 tests. The persisted eligibility suite passed 9 tests, including long history, exact viewer matching, and regex escaping. The existing Mine service suite previously passed 140 tests. - The named browser case `task toasts follow personal involvement in multiplayer` passed against the final commit in an isolated authenticated instance. It used two real sessions, real WebSocket delivery, and persisted tasks, edits, comments, and mentions. It verified quiet unrelated activity, viewing alone, first and historical mentions, own-action suppression, visible-task suppression, and live cache refresh. - A prior-head server shard passed its single rerun after a fixture-cleanup deadlock. The final-head CI run passed without a rerun. - The broad local run remained in progress when CI completed the full test suite. Local focused checks and CI provide the completed test evidence. ## Risks - This intentionally reduces live notifications. A new client stays quiet against an older server that omits eligibility. - Eligibility queries add work to live event delivery. A lookup failure suppresses the toast and still delivers the authorized event. - Deleted mentions cease to qualify unless another participation rule applies. Historical comment authorship retains the existing Mine behavior. - No database migration or notification-settings change is required. ## Model Used OpenAI Codex with GPT-6 assisted with implementation, tests, documentation, and PR preparation. It used repository tools, shell commands, and browser automation. The runtime did not expose an exact backend revision 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> |
||
|
DottaandPaperclip
|
d67e3507b2 |
feat(runner): qualify Codex platform packages and cache hosted builds (#16028)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Native execution needs a compatible installed daemon and provider dependency. > - The Codex-default work found missing platform packages and clean-install startup failures. > - Release builds also repeat dependency compilation and run preparation serially. > - This prerequisite packages four daemon targets and verifies installed native startup. > - It also caches hosted Cargo dependencies and overlaps JavaScript preparation with compilation. > - Agent creation defaults and experimental gates stay at the current master behavior. ## Linked Issues or Issue Description Refs #15683. Refs #15555. Refs #15422. Refs #15926. Refs #15932. Extract runtime and installation support from #15683. This prerequisite has 65 changed files. Creation, onboarding, imports, UI runner selection and graduation remain in the dependent PR. Feature/access maps and the Storybook source catalog stay synchronized. Existing agents keep their execution choices. ## What Changed - Correct the existing runner test fixtures. Reserve owned credential quorum listeners through the existing bounded fixture helper. Keep foreign listeners intact, run actual credential staging once, and preserve its rejection and unchanged-auth assertions. Reuse the durable-resume outer-limit correction. Wait for actual warm-completion and held-authorization callback entry under the existing recovery deadline and surface early request errors. Preserve every semantic assertion. - Retain bounded installation failure diagnostics through the existing qualification receipt upload. Keep the original error, 10-minute deadline and all success checks. - Keep startup ownership until credential preparation and registration drain. Reject duplicate and post-close startup/resume work. Observe shutdown during normal and adopted authentication readiness. Preserve the primary failure and retain private state when cleanup is unconfirmed. - Package Linux x64/ARM64 and macOS Apple Silicon/Intel daemons. Verify target headers, source identities, manifests, and hashes before assembly and installation. - Reuse the existing release producer/consumer workflows. Cache Cargo dependencies by target, OS, compiler, lockfile, and contract inputs. Rebuild workspace binaries. Permit trusted cache writes only for canonical exact-source master pushes. - Overlap JavaScript preparation with native compilation. Join both commands and failure/cancellation cleanup before artifact verification. - Preserve shell positional arguments in the shared SSH runner and apply environment assignments correctly. Reject environment option keys. Six before/after controls and two real SSH subprocess paths pass with zero provider calls; this fix lands before both Codex and Claude defaults. - Admit verified suspended SSH backups during cold controller continuation, using the same full-scope, integrity and lifecycle checks as sandbox targets. Two positive SSH cases fail before; all 14 positive/negative matrix cases pass afterward. Active ownership and corrupt/malformed/nonempty state remain rejected. - Record measured sandbox platform facts through the existing explicit environment probe. Bind facts to the company, effective provider configuration, immutable OCI image and actual captured image binding. Check the returned cleanup receipt. Reject client-authored proof and stale or named boot identities. Creation and discovery allocate nothing. Preserve connection-only behavior. - Resolve the actual remote Codex target and preserve same-host development overrides. Preserve runtime artifact verification. Use actual protocol/model compatibility rather than a numerical CLI version fence. - Resolve the installed Codex login dependency on 64-bit Linux and Mac independently of the daemon libc baseline. Preserve account homes and safe errors. - Fix actual clean-install TOML table comparison. Preserve strict semantic checks, comments, private writes, and malformed-input rejection. Preserve primary startup failures and bounded cleanup. - Document GNU libc 2.39+ and stock Ubuntu sandbox prerequisites. Qualify ARM startup with a scoped distribution profile and unchanged global restrictions. Preserve Windows and Alpine deferral. - Preserve selected and saved native Codex reasoning effort in the existing UI builder, while excluding it from other providers. This small shared correction prevents import edits higher in the stack from dropping effort. - Reuse existing installed-package checks and assertions. Paperclip tarballs contain no Codex native payloads. Official npm dependencies supply the consumer's Codex binaries. All Docker and native builds stay remote. ## Verification Candidate: `271d434c170e74bdedde65d0b13059a55419c943`. It includes current master `e168512f7bdbb6af6ea01954c6d7ed80b91e903e` and preserves prior candidates through ordinary commits. Current [full CI](https://github.com/paperclipai/paperclip/actions/runs/38346601686) is successful on attempt 2. GitHub reports 54 successful checks and four conditional skips, including required verify and browser aggregates, workspace typecheck/tests/build, Linux DB controls, both runner shards and [isolated native compilation](https://github.com/paperclipai/paperclip/actions/runs/38346601609). Fresh current-head Greptile is 5/5 with all four threads resolved. The passing build's clean Grok/Codex report records CI merge source `7a82a37438e6e448abc7cc5caa60dc2519a97be0`, 18 installed packages, omitted Codex payloads, official host-only npm dependencies and zero provider calls. Pi setup and its no-prompt lease verification also pass. The first attempt's single 60-second Node archive download timeout remains retained; its DNS/TLS/download cause remains unknown. One unchanged-source retry was requested through the normal Build-job dialog with debug logging disabled. GitHub's attempt 2 graph reports the other CI jobs as well; no second retry or source/deadline relaxation was made. The [final exact-source package campaign](https://github.com/paperclipai/paperclip/actions/runs/38347027535) is successful on literal `271d434c170e74bdedde65d0b13059a55419c943`. It passes all four native producers, public Linux package assembly and clean installed consumers on Apple Silicon, Intel Mac and Linux ARM64. The nine qualification-mode skips are intentional; full CI above covers their ordinary gates. Native builds and Docker assembly ran remotely. The predecessor [`dae808` package campaign](https://github.com/paperclipai/paperclip/actions/runs/38342104102) remains literal historical evidence. Only tests and the dated record differ from that source; runtime, package and workflow code is unchanged. The reused credential fixture correction passes all 42 canonical Node 24 controls with synthetic data and independent matching-source review, and the current hosted runner shard passes. Production credential behavior is unchanged. **Merge hold:** current-source CI, fresh 5/5 review and exact-source package qualification pass. Actual code-owner approval and normal protected merge remain pending. No slice has merged or deployed. GitHub CLI authentication needs refresh; the normal signed-in embedded GitHub UI provided this status without credential workarounds. - The master merge preserves both Storybook source-review appendices and the guarded test-home cleanup. All six existing cleanup controls pass without skips. Master's isolated-home helper/test/setup are byte-identical. The two existing whitespace lines in master's unrelated privacy test remain outside this PR's diff. - Canonical Node 24 passes all 24 existing public-install helper tests. Three narrow added cases prove bounded/redacted failure metadata, symlink exclusions, original exception identity, failed diagnostic writes and no false failure on success. The Mac installer now uses `--timing`; at most two 16 KiB tails and 32 structured entries per tail enter the existing receipt upload. Raw argv, URLs, environment, error text and stacks are omitted. A failed receipt explicitly remains FAILED/unqualified/runtime-not-attempted. The 600,000 ms install deadline and every real package/hash/payload/lock/lifecycle/runtime oracle are unchanged. - Canonical Node 24 reproduces the durable-resume outer timeout under controlled fake latency. Only its outer test limit changes to 15 seconds; internal 500 ms/5 second deadlines and usage/effect assertions remain. Controlled warm-recovery and before-bootstrap authorization scheduling delays reproduce their callback polling failures, while the explicit entry signals pass. Early recovery errors surface unchanged. Independent review is clear. Historical mock binaries support the fixture controls; fresh full hosted CI remains decisive. The original hosted callback failure cause is inconclusive. - The composed runner/surfaces/server/E2E TypeScript checks pass. Map checks pass 35 areas/171 capability IDs. Token gates pass. The existing Storybook catalog passes 223 files/2,210 stories; story IDs and classifications remain intact. The current master had 25 inherited stale fingerprints from three changed map recipes. Only those guarded fingerprints and a source-only review note change; all 92 non-map story/component/fixture inputs remain unchanged. Existing classifications are retained. This proves source structure, not visual or live acceptance. - The 65-file contribution audit has no code file crossing from below 1,000 lines to above the limit. Earlier comment cleanup preserves executable emissions, parsed workflows and action pins. Independent cleanup/catalog and three-file reporting reviews are clear. No new workflow, suite, grader or local native/Docker build was added. **Prior `dae808` gate evidence:** fresh Greptile is 5/5 with four resolved threads, isolated native compilation and the browser aggregate pass. Its first runner shard passes the previous two corrections but fails a different held-authorization cell at the implicit one-second polling deadline. It records 1,672 passes/one failure/three skips. This candidate applies the verified entry-signal correction without changing production deadlines or any semantic assertions. Its original hosted cause remains inconclusive until fresh CI. **Previous-source evidence, kept literal:** the [exact `16a532` package campaign](https://github.com/paperclipai/paperclip/actions/runs/38338806076) passes all four native producers, public Linux package assembly, Apple Silicon, Intel Mac and Linux ARM64 installed consumers. Its fresh review is 5/5 with all four threads resolved. Full CI records 52 successful checks, four conditional skips and the two fixture failures corrected here. This is not a green full-CI candidate or proof for the new source. `64c074fb8da1b31f8d6042c4fef48dc4164e759b` passed [full CI](https://github.com/paperclipai/paperclip/actions/runs/38332726938), 54 checks/four conditional skips, [isolated native compilation](https://github.com/paperclipai/paperclip/actions/runs/38332726787/job/115085895328), and fresh Greptile 5/5/all four resolved threads. The hosted transport suite passed 246 tests and startup trust passed 22, closing that source's local fake-binary limitation. These are historical after reconciliation. The [previous exact-source package campaign](https://github.com/paperclipai/paperclip/actions/runs/38332921463) built all four platform daemons and passed public Linux package assembly plus Apple Silicon and Linux ARM64 installed consumers. **Intel Mac failed:** its initial scripts-disabled npm install timed out before lifecycle/runtime assertions. The underlying download/resolution/host cause is unknown because the old helper deleted the npm logs. This is the concrete baseline for the diagnostic change. The failed campaign remains failed; no all-platform signoff or automatic retry is claimed. The earlier `a200495` [four-target campaign](https://github.com/paperclipai/paperclip/actions/runs/38283695248) and [scoped ARM qualification](https://github.com/paperclipai/paperclip/actions/runs/38291535914) remain component evidence. Cargo restores were cold misses; no warm-cache speedup is claimed. Paperclip tarballs contain no Codex payloads. Official npm dependencies supply Codex on the user's platform. Current-source full workspace typecheck/tests/build, Linux DB controls, static/Rust/native tests, all browser shards and exact-source package consumers must pass. New-agent defaults and final managed onboarding belong to #15683. Actual private Cloud composition, warm/cold signup, task/follow-up and rollback compatibility remain later release gates. Source audits found that ordinary managed onboarding does not run the saved platform probe and Cloud distributes named snapshots without a verified final boot-image binding. These dependent release blockers remain open; prequalified E2E fixtures do not close them. Master adds task-workspace migrations; the final image/migrator and previous-image checks must include them. ARM paid task/follow-up and ordinary OS APT installation are not proven. ## Risks - Multi-target packages require source and header agreement. Missing or mismatched artifacts fail explicitly. Existing execution choices remain unchanged. - Linux requires GNU libc 2.39+ and compatible sandbox prerequisites. The scoped hosted ARM preparation does not qualify arbitrary containers or kernels. Windows, 32-bit ARM, and Alpine remain deferred. - Only dependency crates are cached. Preview jobs cannot write trusted caches. Concurrent command cleanup must preserve the primary failure. - Native-free Paperclip packaging retains official Codex npm dependencies. No Codex payload bundling, schema migration, automatic agent migration, or production deployment is included. ## Model Used OpenAI Codex, GPT-6 family, with reasoning, repository tools, code execution, and parallel agents. The exact serving model snapshot and context-window size are not exposed. ## 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> |
||
|
Dotta
|
4a641d0980 |
fix(ui): default human task replies to the latest assigning agent (#15594)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Tasks let agents ask a person for input. > - The reply composer needs a useful default recipient. > - A recent comment does not identify the agent that assigned the task. > - The old fallback can select the person who is writing the reply. > - This change uses the latest agent assignment and keeps manual choices. ## Linked Issues or Issue Description **What happened?** When an agent assigns a task to a person, the reply composer can select that person or a different commenter. A data refresh can also replace a manual selection. **Expected behavior** For a task assigned to the current person, select the latest agent that assigned it to them. If no such assignment exists, use the latest other commenter. If neither exists, leave the recipient empty. Keep explicit choices during refreshes. **Steps to reproduce** 1. Have agent Alpha assign a task to a person. 2. Assign it to agent Beta, then have Beta assign it to the same person. 3. Open the task as that person. 4. Check that the reply composer selects Beta. 5. Select another recipient. Refresh task data. Check that the selection stays. Related work: #15091 shares task composer controls. This change fixes recipient defaults. ## What Changed - Read real assignment changes from REST and native runner task activity, in time order. - Record human assignee fields in native create and reassign activity. - Ignore unchanged assignment fields and assignments to other people. - Use the assigning agent before comment hints for human-owned tasks. - Connect the suggestion to current and classic task composers and pipeline replies. - Keep manual selections when suggestions change. - Add regression tests and document the fallback. - Use tasks with no assignee in the attachment receipt tests. This keeps the tests on the comment route. Dismiss announcements through the real UI. - Record human and agent assignees in REST creation receipts. Include child creation in the assignment history resolver. ## Verification - Focused tests cover assignment order, creation, other recipients, unchanged fields, fallback, and manual selections. - Browser fixture uses the real composer and assignment resolver. It selects Beta and keeps a manual human selection after history refresh. - Passed: 223 focused tests across four suites. - Passed: `pnpm --filter @paperclipai/ui typecheck`. - Passed: `pnpm --filter @paperclipai/ui build`. - Passed: `pnpm check:token-gates`. - The initial CI run passed full build, typecheck, Rust, unit tests and seven E2E shards. The attachment shard exposed tests that relied on the old self-selection default. The tests now select the recipient explicitly. - Native assignment regression tests and resolver tests pass: 40 tests. - Attachment E2E suite: 10 passed; one page-load timing failure passed on an isolated rerun. All 11 cases passed across the suite and rerun. - Previous full CI passed at |
||
|
DottaandPaperclip
|
f329b24ee1 |
feat: give tasks durable project-optional workspaces (#15749)
Give tasks durable company-scoped workspace bindings independent of project assignment, channel defaults and authorized repository preparation. Reuse verified input seeds and sparse output recovery while preserving trust, privacy and controller provisioning boundaries.
Full CI and E2E, Superagent, legacy checks and Greptile Apex 5/5 passed on reviewed head
|
||
|
DottaandPaperclip
|
f0e12c8519 |
Add managed Slack setup with an independent own-app path (#15679)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Slack connects a person to an agent through an installed app and a verified identity. > - Independent installations must remain usable without Paperclip Cloud or manager credentials. > - Approved Cloud deployments can use Slack manager grants to create and install each agent's app. > - Both paths should share credential storage, identity checks, recovery, and the existing runtime. > - This pull request adds gated managed setup and keeps independent app setup under Advanced. > - It also makes ongoing connection settings and personal test messages easier to use. ## Linked Issues or Issue Description **Subsystem affected** Slack setup, connection settings, tenant credential storage, and the Cloud connector handoff. **Problem or motivation** Approved deployments need an installation flow without pasted configuration tokens. Open-source users must retain their independent Slack app flow. A connection manager also needs a simple way to check a bot from Settings. **Proposed solution** Use the managed path when the instance is configured to support it. Choose agent and Connect are the two visible stops. Continue starts authorization or installation. Use your own app remains under Advanced before creation. Save personal manager grants by company, Paperclip user, Slack user, workspace, and manager app. Reuse only verified identities for test messages. Unknown identities must complete a private Slack connection challenge before linking and receiving the test DM. **Alternatives considered** A shared bot would change each agent's Slack identity. Requiring Slack CLI or a hosted service for self-hosted users would remove independent installation. **Roadmap alignment** This maintainer-requested change improves Connected Apps and experimental Agent Chat. It adds provisioning and management controls to the existing Slack runtime. **Additional context** The companion Cloud broker profile is a separate deployment prerequisite. Managed setup remains gated. Existing-app adoption is deferred. ## What Changed - Extract Slack registration, provider requests, completion, customer-owned setup, managed setup, and personal manager grants into focused services. Preserve the compatibility facade and independent removal cleanup. - Add company-scoped manager grants and a registration reference through an additive, idempotent migration after current master. Keep runtime credentials separate from app-registration secrets. - Add authenticated manager authorization, sealed handoff, serialized refresh and revocation, app creation, managed installation, and installer-bound OAuth fallback. - Preserve creation intent, block automatic uncertain recreation, save credentials before downstream checks, and validate app, workspace, bot, scopes, and installer identity. - Add the two-stop production wizard and ordered stories. Keep the own-app, manual, existing-app, and legacy-draft paths. - Simplify Settings. Open Slack configuration targets the saved app. The test-message action has its own row. Remove the old manual-avatar section, channel-message section, and broken permissions link. - Add paginated account discovery and a private connection challenge for unknown accounts. Expired invitations stop waiting and offer a new private invitation. Save send receipts before provider dispatch and preserve confirmed delivery when activity logging fails. - Reinstall the saved managed app on explicit reconnect, replace revoked credentials, and resume completion. Persist reconnect intent and duplicate-request receipts without creating another app. - Update provider browser tests, recovery tests, secret redaction, setup documentation, and the agent prompt. Preserve current master's durable verification scheduling. ## Verification - Full workspace typecheck and repository build passed on `56d389d47a`. The subsequent reconnect retry fix in `288364eada` also passed UI typecheck and UI build. - 114 focused Slack registration cases and 13 production managed-wizard cases passed, including fresh-token reconnect, retry after installation failure, and duplicate reconnect requests. - All nine affected Slack browser cases passed against the production UI and a disposable fixture server. They cover managed setup, automatic setup, own-app selection, refresh, recovery, mobile behavior, and connection settings. - Eight focused real-database test-message cases passed. They cover a private ownership challenge, saved grant reuse, account pagination, revoked and conflicting links, workspace mismatch, disabled DMs, revoked membership, audit failure, ambiguous dispatch, and secret canaries. - UI token gates and the production Storybook build passed. - Greptile reviewed exact head `288364eada5d9c114fad991ff634612639d06672` at 5/5 with no actionable findings or unresolved review threads. - The full repository test suite and current-head CI are running. Their final results will replace this line before merge. - Earlier live feature previews created two bots in the authorized Paperclip Slack workspace and reused one personal manager grant. Local managed Continue created and installed a bot without a configuration token or a separate Add to Slack action. Avatars, welcome DMs, signed callbacks, and direct replies were observed. A Settings test DM also arrived in the signed-in user's Slack account. - Earlier staging thread qualification required manual publication recovery for one bot. Current-head live qualification remains required before enabling the production default. Fixture results do not establish Slack approval behavior in other workspaces. ## Risks - Personal manager tokens can create apps. They stay in scoped vault entries. The manager client secret stays at the broker. Company, actor/session, origin, and app identity checks apply throughout setup. - The additive migration must also work on qualification instances that applied earlier branch migrations. Table, column, index, and constraint creation is idempotent. - Creation and message timeouts can leave uncertain outcomes. Saved request IDs prevent automatic duplicate dispatch. - Unknown Slack identities must receive and complete their private challenge while signed in. Account selection alone does not grant Paperclip permissions. Existing revoked or conflicting links are not overwritten. - A development-only manager transport uses an explicitly configured private credential file for local qualification. Production ignores this transport; no manager credentials are bundled with open source. - Managed rollout requires Slack approval, the companion broker deployment, configured secrets, and final live qualification. Removing a connection does not delete its Slack app. ## Model Used OpenAI Codex, GPT-6 family, with reasoning, code execution, and browser tools. The session does not expose the exact serving 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 - [ ] 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> |
||
|
Dotta
|
a9830414c7 |
Preserve repository dependencies when importing GitHub skills (#15731)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Its Skills library imports reusable instructions from GitHub. > - Some skills depend on shared files and sibling skills outside their folders. > - Directory-only imports lose those dependencies. > - This pull request keeps repository files together and lets users select which skills appear in the library. > - Agents receive the original files and paths through the existing skill delivery system. ## Linked Issues or Issue Description Refs #14713. Related: #13656. **Current behavior** GitHub imports copy independent skill directories. Shared scripts, policies, helper skills, and credit files can be omitted. One shared-file error can block every skill. **Proposed behavior** New imports keep repository files together at the scanned commit. Show all skills with their folders and select every skill by default. Collapse individual package files. Omit unsupported or oversized files with a warning. Import available content without repair choices or an extra confirmation. Keep warnings on the saved source. **Reason and benefit** Skills can read their shared repository files after Paperclip delivers them to an agent. Original instructions stay unchanged. Users can inspect included files and understand omissions before and after import. ## What Changed - Store immutable company-scoped repository snapshots and associate them with skill versions. Regenerate the migration after merging master. - Preserve original bytes, binary encoding, and executable modes. Shared-file changes version each usable selected skill. Pinned versions retain their original files. - Deliver a discovery wrapper with the original tree under `.paperclip-repository/`. Preserve invocation policy when present. Fork and create-from-existing retain repository files. - Keep repository files together for new UI imports. Show every skill, select all by default, and collapse package files. Remove the packaging-mode menu. Keep the mobile import footer visible. - Warn about symlinks, submodules, oversized files, missing references, and invalid optional manifests. A malformed skill remains selected with a Needs setup warning. Usable skills still publish, and its original file remains repository support content. Source warnings persist through refresh. Unsafe execution and secret-disclosure findings omit the affected files before snapshot publication. - Expose saved repository files in the installed skill viewer, including binary encoding and executable flags. Reads use the immutable company-scoped snapshot; relative instruction links resolve from their original repository directory. - Audit delivered inventories and derive trust from all repository files. Accept evaluation prose while retaining dynamic-execution findings. Read blobs in one bounded Git batch and check budgets before reading support files. Imports never execute setup commands. - Add scanner, database, delivery, UI, and browser regressions. Update Storybooks, screenshots, and documentation. ## Verification - 69 focused scanner, Git snapshot, delivery, and PostgreSQL lifecycle tests passed. They cover partial imports, warning persistence, missing references, binary files, executable modes, copies, pinned versions, cancellation, company isolation, and batched Git reads. - 110 import, skill-detail, selection-tree, saved-file link, and Markdown renderer tests passed. A file-switch regression failed before the resolver fix and passed afterward. Browser walkthroughs cover the all-selected open tree, repository preview, non-blocking warnings, missing references, setup problems, warning persistence, and mobile layout. - Full workspace typecheck and build passed. Runner E2E TypeScript checks and design-token gates passed. The full serial local suite was attempted and stopped after over an hour. The existing 40,000-file Git streaming stress test failed after 303 seconds on macOS; the broad local suite is not counted as passed. All 55 applicable PR checks passed on the final commit, including the full sharded CI suite. Two optional Storybook workflows were skipped; the five local Storybook walkthroughs passed. - On October 12, live campaigns imported the private Poteto repository through the production GitHub Sources UI, selected architect and bro, and invoked them with native Codex on local and Daytona. The source connection was disabled before invocation. Independent filesystem inspections matched every supported Git blob, size, and executable mode. Both tasks completed and cleanup passed. Campaigns: `local-2026-10-12T15-07-39-504Z` (both environments), `local-2026-10-12T16-08-39-682Z` (local), and `local-2026-10-12T16-03-33-938Z` (Daytona). Each of the two selected skills received all 234 supported repository files. Later changes only affect the installed-file viewer and documentation. This qualifies skill delivery and instruction reads, not every Poteto workflow or adapter. - A manual source-checkout test drive imported a synthetic private GitHub repository with a symlink, an oversized file, a missing reference, and malformed skill metadata. Available skills published with their shared checklist. The walkthrough found duplicate warning text after import; the final UI fix removes that duplicate. The file viewer exposes saved repository dependencies and resolves authored relative links without changing the instructions. A follow-up live refresh omitted unsafe helper files with warnings, preserved every safe file byte, and survived a server restart. Screenshots below use the production UI with Storybook fixtures. They do not replace the live GitHub and runtime checks. <details> <summary>All skills visible and selected by default</summary>  </details> <details> <summary>Import stays available with warnings</summary>  </details> <details> <summary>Repository file inspector</summary>  </details> <details> <summary>Mobile import</summary>  </details> ## Risks - Each selected skill carries a repository copy in the runtime. The database stores each snapshot once. Runtime transfer and storage increase with the number of assigned skills. - Runtime budgets remain: 9,990 repository entries, 1 MiB per file, and 61 MiB total. File omissions are recorded as warnings. Source-access or download failures retain installed versions. - Import success does not prove that every skill can run. Environment dependencies, credentials, delegation tools, and schedules still need configuration. Imported setup scripts are not executed. - Live runtime coverage is native Codex on local and Daytona. Other adapters use the shared delivery path but were not exercised in these campaigns. The roadmap marks Skills Manager as shipped. This extends the existing importer. Related pull requests were checked. ## Model Used OpenAI Codex, based on GPT-6, with repository inspection, code execution, automated tests, and browser tools. The exact deployment identifier and context-window size were 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 - [ ] 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 |
||
|
DottaandPaperclip
|
ce08872dfb |
refactor(heartbeat): extract instruction working-copy lifecycle (#15984)
## Thinking Path > - Paperclip runs agent tasks and preserves their managed agent files. > - Heartbeat must prepare a private copy, collect stopped-provider edits, and retain ownership during warm-session handoff. > - That lifecycle is spread across preparation, adapter callbacks, and cleanup. > - A per-run controller can own the copy and receipt while the executor retains teardown ordering. > - This PR moves that coordination into a dedicated module. > - Live getters preserve updated state and partially acquired resources. ## Linked Issues or Issue Description **What existing behavior does this improve?** Maintenance of heartbeat instruction preparation. This is the second and final PR in this batch, originally stacked on #15980. That dependency is now merged; this PR is rebased onto its squash merge with an identical patch and identical touched-file contents. Related-PR search found no duplicate extraction. **Current behavior** After #15980, `heartbeat.ts` has 4,215 lines and 173,657 bytes. It coordinates instruction-copy preparation, save receipts, warm handoffs, and deferred cleanup inline. **Proposed behavior** `heartbeat/instruction-working-copy.ts` owns the per-run lifecycle in 233 lines. `heartbeat.ts` becomes 4,055 lines and 162,520 bytes. The executor retains the outer release order, unavailable-copy reporting, and environment/service cleanup policy. **Reason and benefit** The copy, save receipt, and warm ownership are readable together. The remaining executor names preparation and dispatch phases without obscuring teardown decisions. **Breaking changes** None intended. All 140 named public heartbeat exports remain unchanged. ## What Changed - Extract copy preparation, save/checkpoint callbacks, warm reservation/adoption, prompt guidance, and the deferred-release closure. - Read the executor's current run row through a callback; expose current copies, receipts, and acquired cleanup handles through live getters. - Keep cleanup handles available after preparation failure, and preserve release-before-retry on invalidated warm reuse. - Add four public-path characterization tests with real disposable PostgreSQL and files, plus four direct boundary tests. - Add isolated browser acceptance with a real process that edits instructions, completes its task, and reads the saved bytes on its next task. - Document the boundary and opt-in acceptance command. ## Verification - **Before extraction:** four new public-path tests pass on the original implementation, as do 108 existing instruction-copy/directory/native-cleanup tests. The two-task browser journey also passes on the baseline server. - **After extraction:** all 112 baseline tests pass; all four new boundary tests pass; 12 selected native-session ownership/retirement cases pass (the other 670 cases were outside this focused selection). - **Browser acceptance:** the fresh extracted-code server passes the full two-task journey (25.9 seconds): real child-process edits, saved/unchanged receipts, canonical bytes through the agent-file API, next-task restore, completed task UI, and copy cleanup. - `pnpm -r typecheck`, final server typecheck, and `pnpm build` pass. Module-boundary and public-export checks pass. - Normalized syntax comparison confirms all moved bodies and the reconstructed executor match the base, accounting explicitly for live run getters and delegation. - Final rebased head: `a08872c97e587a21ffc0fc6b78f34b81e484e7b0`. Combined entry-point and boundary regressions pass again (12/12); fresh Greptile review is 5/5 with no findings. All 55 current-head checks pass (two configured skips), including the hosted full-suite tests, build, typecheck, and all eight browser shards. There are no open review threads. ## Risks - Acquisition can succeed before preparation throws. Boundary tests verify that both the reservation and a transferred copy remain visible to the cleanup owner. - Callbacks can replace copy/save state during execution. Public tests verify saved receipts; direct tests verify the current run row, warm checkpoint receipt, and permission-root preservation. - Missing edit authorization and cleanup failure must remain nonfatal. Characterization tests revoke actual membership after dispatch admission and inject a cleanup error while preserving the saved result. - The browser uses a test-launcher-only instruction-capable wrapper around the real process adapter. Production adapter capabilities are unchanged. No live provider calls are made; native warm ownership is covered by focused module and native-session tests rather than a live provider browser run. ## Model Used OpenAI Codex, based on GPT-6, assisted with reasoning, code edits, tool execution, and verification. 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> |
||
|
DottaandPaperclip
|
1e0cfcb4fc |
test: retire redundant suites and consolidate owner coverage (#15978)
Retire duplicate ACPX and Codex proof after migrating unique assertions to their behavioral owners. Consolidate repeated fixtures and exact case matrices while preserving lifecycle, protocol, company, credential, approval, and ordering contracts. Remove the unused runtime-controls compatibility path and document test ownership and preservation evidence. Co-Authored-By: Paperclip <noreply@paperclip.ing> |
||
|
DottaandPaperclip
|
94e4218310 |
refactor(heartbeat): extract runtime service coordination (#15980)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Heartbeat runs start workspace services and receive service reports from adapters. > - Service context updates and readiness notices are spread through the executor. > - These steps share a clear responsibility, while process and lease ownership already live elsewhere. > - This pull request puts service coordination in one module. > - The executor retains the same dispatch and cleanup order. ## Linked Issues or Issue Description **What existing behavior does this improve?** Maintenance of heartbeat execution. This is the first of two final focused extractions after #15973. Related #15653 changes runtime callback origins; this PR preserves that policy. **Current behavior** `heartbeat.ts` has 4,372 lines and 178,459 bytes. It validates service intents, starts services, persists adapter reports and primary URLs, and posts readiness notices inline. **Proposed behavior** `heartbeat/runtime-services.ts` owns those steps in 212 lines. `heartbeat.ts` becomes 4,215 lines and 173,657 bytes. Process registries and leases stay in `workspace-runtime.ts`. The executor still releases services in its original cleanup path. **Reason and benefit** Service coordination has named preparation and result phases. The execution path is easier to read without changing service lifetime or moving cleanup policy. **Breaking changes** None intended. All 140 named public heartbeat exports remain available, including `postWorkspaceReadyComment`. ## What Changed - Move service-intent validation, startup, adapter-result persistence, and readiness notices into one module. - Preserve mutable run context, primary URL selection, notice error handling, and release ordering. - Add four public-path tests using disposable PostgreSQL, real HTTP service processes, and a fixture adapter. - Extend browser recovery acceptance to fetch the actual service URL, check the readiness notice, and verify listener cleanup. - Update the module map and acceptance instructions. ## Verification - Before extraction: all five tests pass, including the four new characterization cases and existing notice formatting test. - After extraction: all 17 tests pass across service coordination, notice formatting, output recording, and runtime authorization. - Structural comparison confirms that all moved bodies and the reconstructed executor match the baseline. Module boundary checks pass. - `pnpm -r typecheck` and `pnpm build` pass. - Extended isolated browser acceptance: **2/2 pass** (3.7 minutes), covering actual service readiness, recovery, bounded failure, and cleanup. At `8e33e2032de681082f128470eb8ab0711b382afe`, all 55 current-head checks pass (two configured skips), including hosted full-suite tests. Greptile is 5/5 with no findings or review threads. ## Risks - Service context must be persisted before adapter dispatch and before run completion. The tests inspect both phases and preserve the first service URL when adapter reports arrive. - Notice failures must remain nonfatal. The public-path test checks both startup and result notices. - Shared services must survive run cleanup; ephemeral services must stop after success or failure. Tests use actual processes and HTTP requests. - The fixture supplies UUID service report IDs, as required by the database. The existing generated-ID fallback for reports without IDs is outside this extraction. - Test adapters and services are local fixtures; these tests make no live provider calls. ## Model Used OpenAI Codex, based on GPT-6, assisted with reasoning, code edits, tool execution, and verification. 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> |
||
|
DottaandPaperclip
|
37913e4907 |
refactor(heartbeat): extract run output recording (#15969)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Heartbeat runs stream adapter output and persist execution results. > - Output recording currently sits inside the executor beside admission and cleanup. > - Log handles, sequence numbers, progress writes, and excerpt buffers share one attempt lifetime. > - This pull request moves that state and its callbacks into a per-attempt recorder. > - The executor keeps dispatch and finalization visible, while finalization reads live output values. ## Linked Issues or Issue Description **What existing behavior does this improve?** Maintenance of heartbeat execution. This PR follows #15966, which is now merged. The branch is rebased onto `master`; `git range-diff` confirms that its extraction patch is unchanged. **Current behavior** `heartbeat.ts` has 4,740 lines and 195,258 bytes. It directly owns log handles, excerpt buffers, output sequence numbers, progress flushes, and adapter event callbacks. **Proposed behavior** `run-output.ts` owns the per-attempt recorder. The main file has 4,561 lines and 188,950 bytes; the recorder has 209 lines and 7,757 bytes. **Reason and benefit** Output state has one explicit lifetime and interface. The shared log store and finalization policy retain their original owners. Related open output work includes #12539 and #15524; this PR does not change redaction policy. **Breaking changes** None intended. Public flush constants and log formatting exports remain available from `heartbeat.ts`. ## What Changed - Move log initialization, redaction, excerpts, progress persistence, live delivery, and adapter callbacks into `createHeartbeatRunOutput`. - Preserve the acquired log handle if later setup fails. Bind callbacks to the execution-start run row. - Pass live excerpt getters to success and failure completion so output arriving during finalization remains visible. - Add three real-database public-path tests. Extend browser acceptance to inspect persisted worker stdout and output byte counts. - Update the module map. ## Verification - Before extraction: 23 tests pass, including all three new output characterization cases. - After extraction: 45 tests pass across output, log formatting, event sequencing, and run completion. No skips. - `pnpm -r typecheck` and `pnpm build` pass. - Normalized syntax comparison confirms the moved bodies and reconstructed executor match. Reviewed the factory ownership, callback binding, getter wiring, and constant re-exports separately. - Isolated browser acceptance: 2/2 pass, including persisted worker stdout and matching final byte counts. The process worker completes after recovery; persistent timeouts stop after three attempts. Both terminal states survive reload. - Hosted full-suite CI passes on `d32c8fc40e72b9766bdd9e191d777e8dc554e3f2`; all 55 reported checks are successful. Greptile is 5/5 with zero review threads. - The initial chat shard timed out waiting for GitHub mention admission. Its fixture mocks heartbeat wakeup and never calls the output recorder. Both parameterized cases passed locally; the unchanged shard passed on one rerun. No test or timeout changes. - Merge preparation: all seven session-preparation and run-output regression tests pass after rebasing onto `master`. Fresh full CI passes for `60e2a49ce2879645a9f618a801e0ba0903ede161`: 55 successful checks and two optional Storybook skips, including all eight browser shards, typecheck, tests, and build. Greptile is 5/5 on this exact commit with zero review threads. ## Risks - A stale excerpt snapshot could lose output that arrives while finalization awaits I/O. Passing-before/passing-after tests exercise this for both successful and failed runs. - Per-attempt state must not become service-wide. Each executor constructs its own recorder and keeps the existing shared store. - Browser acceptance uses a real process fixture and disposable data; it makes no live provider calls. ## Model Used OpenAI Codex, based on GPT-6, assisted with reasoning, code edits, tool execution, and verification. 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> |
||
|
DottaandPaperclip
|
ce15fe7c73 |
refactor(heartbeat): extract task context preparation (#15872)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Heartbeat execution prepares task context before it selects an environment and starts an adapter. > - This preparation still occupied 319 lines inside the executor after the earlier extractions. > - It combines continuation summaries, comments, prompt variants, communication guidance, and redaction. > - This pull request moves that responsibility into one typed module under `services/heartbeat/`. > - The executor keeps admission, resource ownership, dispatch, and cleanup ordering together. > - The result makes the preparation phase easier to find and test without changing execution behavior. ## Linked Issues or Issue Description Refs #15825, #15807. This continues the incremental heartbeat extraction series. A search found no duplicate task-context extraction. **What existing behavior does this improve?** Maintenance and review of heartbeat task context preparation. **Current behavior** The executor assembles prompts and trust-filtered context inline. This hides its execution phases among preparation details. **Proposed behavior** Call `prepareHeartbeatTaskContext` at the same point in execution. Preserve statement order, prompt contents, public exports, and the shared run context object. ## What Changed - Move task context assembly to `server/src/services/heartbeat/task-context.ts`. Inputs group task state, policy, and two existing service methods. Results preserve the continuation and wake values used by later runtime selection and dispatch. - Keep company-scoped loading, quarantined-content filtering, secret redaction, and revision hashing in their original order. Add no execution resource acquisition. - Add four public-path integration tests before the move. Cover prompt variants and redacted revisions, quarantined summaries/comments, a mixed-company wake batch, and stale caller fields. - Extend the real process worker in the opt-in browser suite to check persisted prompt variants and the description revision before it completes its task. - Update the module map and acceptance-test documentation. - Reduce `heartbeat.ts` from 5,314 lines / 220,784 bytes to 4,989 lines / 206,650 bytes. The new module has 376 lines / 15,912 bytes. ## Verification - Before the move: 11 existing prompt tests and all four new characterization tests passed against the inline implementation. - Normalized syntax comparison passed for all 319 moved lines and the remaining orchestrator, including public exports. Imports and the typed boundary were reviewed separately. - `pnpm -r typecheck` passed. - `pnpm build` passed. - The clean post-move focused run passed all 26 tests in five files, with no skips: task-context characterization, task-markdown, Slack invitation, accepted-plan workspace refresh, and run-preparation. - The local `pnpm test:run` attempt was interrupted after database failures while the Mac exhausted its shared-memory slots. All 15 affected native warm-ownership database cases passed in an isolated rerun after the browser instance stopped; the other 666 cases in that file were excluded by the test-name filter. The interrupted command is not a full-suite pass. Full CI passed on `6bf86cfdc07e7fe34015f7b719218639f4232510`: 55 successful checks and two optional Storybook checks skipped. Greptile reviewed the latest commit at 5/5; its one earlier worker-test finding is fixed and resolved. - Browser E2E passed both scenarios on the final code: persistent timeouts stop after three runs and survive reload; one timeout recovers without manual Retry, verifies task-context prompt variants/revision and preserved workspace files in a real process, then completes through the run-scoped API. The first recovery attempt exposed an incorrect new test assertion because the fixture title equals its description. The worker now checks the description section specifically; the corrected recovery scenario passed in 55.9 seconds. The original failure trace was preserved. These tests use a deterministic process adapter and make no live model calls. ## Risks This is a behavior-preserving extraction. The main risks are changed closure bindings, missing return values, or changed preparation order. Typed inputs, public-path tests, and syntax comparison cover those risks. The run context is still the same mutable object. The helper acquires no leases or processes. It introduces no schema, API, or prompt policy changes. The first post-move database run skipped cases due to host resource exhaustion. All 26 focused cases passed on the subsequent clean run. Browser E2E passed after the worker assertion fix. The full local suite remains incomplete. All 15 native warm-ownership database cases passed on their isolated rerun; The full CI test suite passed on the final commit. ## Model Used OpenAI Codex, based on GPT-6, with reasoning, repository inspection, code execution, and test tools. The host 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> |
||
|
DottaandPaperclip
|
762d680daf |
feat(ui): upload files directly in task artifacts (#15964)
## Thinking Path > - Paperclip helps people manage agent work and retain its context. > - Task documents and attachments keep that context with the task. > - The Artifacts panel showed output but could not accept a new file. > - Uploading through a message can require resuming a paused task. > - Existing document and attachment APIs can save files directly. > - This PR adds direct uploads and a drop target to the task panel. > - People can add context while keeping work paused and unassigned. ## Linked Issues or Issue Description **What existing behavior does this improve?** The task Artifacts panel and its existing document and attachment APIs. **Subsystem affected** ui/ — React board UI. No server, schema, or API changes. **Current behavior** The Artifacts panel cannot upload a file. It also excludes files uploaded by people. The message composer can require a task to resume before it submits attachments. **Proposed behavior** Use the upload icon or drop files anywhere in the open Artifacts panel. The target includes the header, padding, and existing cards. Files save directly to the task without a message or a pause change. **Reason and benefit** People can prepare a handoff on a paused, unassigned task without starting agent work. Markdown becomes a task document. Other supported files use attachment storage. **Breaking changes** Files from people now appear in Artifacts alongside agent output. Promoted attachments still appear once. A repeated Markdown filename creates a separate document instead of replacing an existing revision. Existing APIs and limits stay the same. **Additional context** Related upload API work: Refs #7472 and Refs #7248. This PR adds the missing task-panel entry point. ROADMAP.md lists Artifacts and Work Products as available; this is a scoped UI improvement. ## What Changed - Add an upload icon with no visible label or background. - Accept file drops across the full task panel, including the desktop portal header and mobile tabs. - Show per-file progress and inline Retry and Dismiss actions. - Import Markdown under a new document key and retain existing revisions. - Include files from people in Artifacts and dedupe promoted attachments. - Add component and task-journey stories for empty, populated, loading, error, mobile, and drag-over states. - Add real browser tests for persistence, pause preservation, duplicate document names, full-panel drops, and partial failure recovery. ## Verification - Five Playwright tests passed against an isolated instance started by the source `test-drive` command. The document API, attachment storage, pause holds, downloads, and task UI were real. Only the explicit upload failure was injected. - The browser tests verified desktop and mobile uploads, document reading, persistence after reload, no task comments or runs, header drops, preservation of original and hidden internal documents, reserved filename handling, and upload retry. - 163 focused UI tests passed. - `pnpm -r typecheck` passed. - `pnpm build` passed. - `pnpm check:token-gates` passed. - The full Vitest suite is running after repair of an exhausted local PostgreSQL shared-memory pool. The initial run failed to initialize PostgreSQL. Six unattached segments had no living creator or last-user process; removing them restored free slots. - CI and the current-head Greptile review are pending. ## Risks - Artifacts now includes user files, so existing tasks can show more cards. - Uploads retain the server's authorization, file-type, size, and revision checks. No migration is needed. - Binary attachment uploads use the existing API. A transport failure with an unknown save outcome can retain the existing API's retry ambiguity. ## Model Used OpenAI GPT-6 through Codex. The exact runtime snapshot ID and context-window size were not exposed to this session. The model used repository inspection, code editing, shell tools, and browser automation. ## 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> |
||
|
DottaandPaperclip
|
88b7bbb5e2 |
Stabilize task lifecycle browser fixtures (#15878)
## Thinking Path > - Paperclip manages agents and their tasks. > - Browser and runner tests check task recovery and user actions. > - Some fixtures act before a prior request or run has settled. > - Those races can report a product failure before the intended assertion runs. > - This PR binds each check to the exact request, run, or geometry snapshot it needs. > - The tests retain their existing budgets and negative assertions. ## Linked Issues or Issue Description Refs: #15813, #15804. The draft stack is master → [fixture prerequisite #15878](https://github.com/paperclipai/paperclip/pull/15878) → [runtime prerequisite #15880](https://github.com/paperclipai/paperclip/pull/15880) → [Boat core #15813](https://github.com/paperclipai/paperclip/pull/15813) → [UI #15804](https://github.com/paperclipai/paperclip/pull/15804). GitHub confirms 5, 63, 97, and 75 changed files respectively, each below the 100-file limit. Existing commits and PR URLs remain intact. [Historical evidence](https://github.com/paperclipai/paperclip/tree/5909bfac9fa41405beb3fe8a65253dc28ba52835/doc/plans/assets/2026-10-10-boat) remains pinned to its original commit; current proof files stay with the UI PR. This is the test-only prerequisite extracted from the experimental Boat work. It contains five existing test-file changes. It does not add the Boat adapter or change task admission. ## What Changed - Wait for the exact signoff fixture run and each replacement run to succeed before applying the next stage decision. - Wait for the inbox Retry response for the exact failed run before navigating away. - Compare task planning time with the first run that actually started, instead of assuming the first list item started. - Read the touch target, container, and scroll position in one browser evaluation. Keep strict containment and native gesture checks. - Bind the native recovery fixture to its disposable fake Codex executable so installed provider binaries cannot override it. ## Verification Draft branch: `codex/boat-fixture-prerequisite`, commit `e318850909c0777565b43644a4d8114c6006da60`. Base: master `e733bddc45e00efb1819fffa8677f7b0d07802c5`. Five changed files. The isolated fixture-plus-runtime stack passed 24 browser cases. Six legacy recovery cases could not reach their assertions because the fixture requires embedded PostgreSQL metadata. A normal embedded PostgreSQL attempt then failed during cluster setup on this host. These are not six passing cases. No test seam, timeout increase, or product-database fixture was used. The fixture-only commit has not yet had a separate complete local browser run. All six legacy cases subsequently passed on this exact fixture commit in PR CI browser shard 8 (20/20 total, job114470999277). The original local setup failures remain recorded. The full-stack typecheck/build results belong to the assembled fixture-plus-runtime tree and are not claimed as independent qualification of this smaller commit. Review the exact run/request filters and the unchanged rejection assertions. Run the four changed Playwright specs and the native-session-resume suite through the repository's normal fixture setup. At 13:03:24 UTC, this exact head had 53 successful checks and two skips, with no pending checks or failures. All eight browser shards passed. Greptile is 5/5 on the exact head with no unresolved threads. [Exact-head legacy browser proof](https://github.com/paperclipai/paperclip/blob/9eacca2c5321bb63f061eef4bb775b6951d5846d/doc/plans/assets/2026-10-10-boat/evidence/prerequisite-legacy-browser-ci-proof.json). Feature acceptance stays in the downstream report. Deployment29 verified `05f3725af838b5a074707df1d6ed1e193bdfe49e` at 12:23:23.944 UTC. Native Claude cold execution passed at 12:39:57.782 after 14m56s of first-use preparation. Warm continuation passed at 12:42:09.943 with the same owner, boot and session identities. Normal retirement and archive followed. The ordinary saved post-idle turn then failed: its primary attempt reported the closed `LINK_COUNT` module fence at `turn_ownership_verified` (3,711ms), and same-run recovery settled failed at 12:52:09 with identity/authority errors. Natural archive completed at 12:52:21. Numeric link counts and their direction are not yet proven. A narrower failure-only diagnostic and a bounded read-only probe are under review; neither establishes a fix for this live failure. Prior staging27/28 failures remain preserved. Local complete lifecycle passes and staging Codex/computer/HMR passes remain separate source-bound evidence. No session, quarantine, provider stop or migration history was reset. These live observations do not qualify this prerequisite by themselves. ## Risks - Waiting for the wrong run could hide a task race. The fixtures match task, agent, and replacement-run identity before proceeding. - A geometry helper could weaken touch coverage. This change preserves containment and gesture assertions and only makes their inputs one snapshot. - The six legacy browser cases passed in exact-head CI; their local PostgreSQL setup limitation remains recorded. No live Boat acceptance result follows from this test-only change. Documentation impact: no product command or behavior changes. This description records fixture scope and validation limits. ## Model Used OpenAI Codex (GPT-6 family) assisted with code, test execution, and review. The host does not expose the exact primary model ID or context window. The work used tools for source inspection and local execution. Prior architecture work used `gpt-6-astra`; an independent design review used `gpt-6.1-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 issue id or instance-derived details - [ ] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge Co-authored-by: Paperclip <noreply@paperclip.ing> |
||
|
DottaandPaperclip
|
30e338fba6 |
refactor(heartbeat): extract environment selection (#15825)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Heartbeat execution selects an environment before it prepares a workspace and starts an agent. > - Workspace preparation now has its own module, but its selection policy still occupies the executor. > - Environment defaults, recovery bindings, chat isolation, and workspace contention must retain their order. > - This pull request moves that selection phase behind one typed function. > - The executor keeps dispatch gates and lease cleanup. Tests cover the public path and the new boundary. ## Linked Issues or Issue Description Refs #15807. This continues the heartbeat extraction series after workspace preparation. **Current behavior** The 5,599-line heartbeat service contains a 301-line environment selection phase inside run execution. **Proposed behavior** Move that phase to `heartbeat/environment-selection.ts`. Keep the same policy, statement order, errors, and public exports. **Reason and benefit** Readers can find selection policy in one module and follow the executor's phases without reading each policy branch. ## What Changed - Add `selectHeartbeatEnvironment` with typed run, task, policy, configuration, and service inputs. Return the values needed by configuration and workspace preparation. - Preserve native recovery bindings, environment precedence, managed sandbox enforcement, Kubernetes provisioning, native chat isolation, and shared workspace contention. - Reduce `heartbeat.ts` from 5,599 lines / 234,599 bytes to 5,314 lines / 220,784 bytes. The new module is 402 lines / 18,215 bytes. - Add six public-path characterization cases before moving production code and six boundary cases. Repair plugin-test teardown to drain active execution and call the database cleanup helper. - Assert the selected local environment in the browser fixture's real worker and document the new boundary. ## Verification - Before the move: 71 tests passed, including all six new public-path cases. Three plugin tests skipped when the host could not start their database probe. - After the move: all 112 focused tests passed across eight files, with no skips. These cover environment policy, local and plugin execution, contention, recovery bindings, workspace preparation, chat isolation, and low-trust directories. - Passed `pnpm -r typecheck` and `pnpm build`. - A normalized TypeScript AST comparison confirms the 301 moved lines and remaining executor statements are unchanged, apart from the new call and imports. - Browser acceptance: the task UI recovered automatically and the worker verified its selected local environment, preserved uncommitted files, and completed the task. The persistent-failure case passed in isolation: three total runs, then a blocked task that remained blocked after reload. - The first persistent-failure browser attempt missed the retry banner within five seconds, despite a persisted scheduled retry. Its unchanged isolated rerun passed. The trace is retained; the intermittent UI failure is not yet attributed to a root cause. No assertion or timeout was relaxed. - Greptile reviewed `20953dd164decb565bc8d85081aad31a23fd33e5`: 5/5, no actionable findings. - Hosted CI passed on `20953dd164decb565bc8d85081aad31a23fd33e5`: 52 successful checks and two intentionally skipped Storybook checks, with no pending or failing checks. This includes all general and serialized test groups, Runner verification, eight browser shards, typecheck, and build. - The duplicate local `pnpm test:run` was interrupted after hosted CI completed. It is not reported as a local full-suite pass. Local completed checks are the 112 focused tests, typecheck, build, and browser cases described above. ## Risks - This selection phase enforces execution restrictions. A wrong input or import could select the wrong environment or change retry behavior. Public-path tests cover refusal, redirect, contention, and dispatch; boundary tests cover recovery and isolation. - The helper can provision a managed environment row and add concurrency notes to the supplied task context. It acquires no execution lease. The executor retains its catch/finally boundaries and resource ownership. - Kubernetes selection is tested with real database state and bootstrap settings. These checks do not claim execution against a live Kubernetes cluster or hosted sandbox provider. - No schema, migration, API contract, or intended behavior change. ## Model Used OpenAI Codex (GPT-6), with repository inspection, code editing, compiler checks, database integration tests, and browser automation. The exact serving model ID and context-window size are not exposed in this session. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [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> |
||
|
Devin FoleyandPaperclip
|
4f680bc85c |
fix(release): retry verified canary tarball 404s (#15768)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Canary releases test the published npm packages through a clean onboarding install. > - A package can be announced in registry metadata while a fresh install gets a tarball 404. > - The existing ETARGET retry does not cover that distinct error. > - This pull request retries only a verified public canary tarball acquisition failure. > - Permanent errors still fail, and onboarding runs once after acquisition succeeds. ## Linked Issues or Issue Description Refs: #15743 **What happened?** The [Release run](https://github.com/paperclipai/paperclip/actions/runs/37998601578) published canary `2026.1009.0-canary.17`. Its registry verification and publisher install passed. The separate fresh onboarding install then failed with a final npm E404 for that exact `@paperclipai/server` tarball. The tarball was available on a later read. This is a separate failure from ETARGET; it does not prove the cause of the registry visibility difference. **Expected behavior** Allow a bounded acquisition retry when the effective registry is public npm and fresh primary metadata announces the exact released canary tarball. Keep other E404, authentication, configuration, and onboarding errors fatal. **Steps to reproduce** 1. Run the offline helper fixture with a first-attempt E404 for an allowlisted package at the requested canary version. 2. Return canonical effective npm registry configuration and matching primary metadata. 3. Make the second install succeed. Confirm two installs and one onboarding invocation. 4. Keep the tarball unavailable. Confirm three installs, a final failure, and no onboarding invocation. **Paperclip version or commit** The observed run used commit `ce024457f3d747657501fbcfe8eac71f6772150f`. This fix builds on the merged acquisition helper and current master. **Deployment mode** Other: the published npm canary onboarding check in release CI. ## What Changed - Add a canary-only classifier for one unambiguous final E404 at the canonical tarball URL of a CI-published package from the existing release manifest. - Query effective npm registry configuration in the failed install's prefix, environment, and working directory. Keep bounded configuration output in memory without logging it. Respect scoped registry precedence. - Require fresh primary metadata to match the package, version, tarball URL, and valid SHA512 integrity syntax. Reject redirects, conflicting errors, truncated logs, other artifacts, and unknown or custom effective registries. - Share one five-second configuration and metadata deadline within the existing two-minute acquisition budget. Keep three install attempts, refreshed retry metadata, process cleanup, and one onboarding invocation. - Bound metadata header and body waits even if transport abort propagation stalls. Cancel the reader and any late response body without waiting for cancellation acknowledgements. - Preserve the existing ETARGET classifier and its character-based stderr tail. Add offline subprocess, actual npm configuration, body cancellation, budget, identity, and failure tests. Document the scope and limits. ## Verification - `node --test scripts/__tests__/release-verify-workflow.test.mjs scripts/cloud-source-verification.test.mjs scripts/standard-image-contract.test.mjs`: 73 passed, no skips, under Node 22 on the PR head. - `pnpm test:release-registry`: 153 passed, no skips, on the PR head. This includes the existing real Playwright cleanup and startup timeout tests. - [Hosted CI](https://github.com/paperclipai/paperclip/actions/runs/38011028296) passed on this head. The rollup has 53 successful checks and two expected Storybook skips. This includes typecheck, build, the full general and serialized test suites, E2E, and Canary Dry Run. - The new tests use fixture-owned npm configuration and local HTTP servers. No published canary tarballs were downloaded or installed for this change. No release or deployment was triggered. - `pnpm test:run` was not run locally. The full split test suites passed in hosted CI. Independent source checks on this head passed 46 committed tests, 22 boundary checks, and six negative controls. Greptile scored this head 5/5 with no unresolved threads. - The source diff and PR text were checked for secrets, private identifiers, and unintended artifacts. ## Risks - The new retry is conservative. A configuration capture over 4 KiB, metadata over 64 KiB, or a check that exceeds five seconds denies retry. A persistent tarball failure still fails after three installs. - Matching primary metadata proves the announced artifact identity and integrity syntax. It does not independently verify tarball bytes. The subsequent npm install retains its integrity check. - Registry checks use npm's resolved global and applicable scope values. They do not add credentials or change npm configuration. Existing ETARGET behavior, onboarding assertions, and overall startup deadlines remain unchanged. ## Model Used OpenAI GPT-6 (Codex). The exact model variant and context window are not exposed in this session. Used reasoning, code execution, offline fixtures, and GitHub API tools. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge Co-authored-by: Paperclip <noreply@paperclip.ing> |
||
|
DottaandPaperclip
|
07fee85eaf |
refactor(heartbeat): extract workspace preparation (#15807)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - The heartbeat service prepares the workspace and dispatches each agent run. > - After the runtime extraction, `heartbeat.ts` still had 6,417 lines. > - Workspace setup occupied one contiguous 857-line block inside `executeRun`. > - This pull request moves that block into one workspace preparation module. > - The executor keeps dispatch gates and terminal cleanup. Reviewers can inspect workspace setup as one phase. ## Linked Issues or Issue Description Refs #15803 and #15578. This continues the heartbeat refactor series. The search found no open duplicate workspace preparation extraction. **What existing behavior does this improve?** It makes heartbeat workspace preparation easier to maintain. It does not change the workspace policy or execution behavior. **Current behavior** `executeRun` contains workspace resolution, freshness decisions, provisioning, persistence, issue binding, environment acquisition, and realization inline. **Proposed behavior** `prepareHeartbeatWorkspace` owns that sequence in `server/src/services/heartbeat/workspace-preparation.ts`. `heartbeat.ts` calls it at the same point and uses its returned workspace, lease, target, and metadata. **Reason and benefit** The main file falls from 6,417 to 5,597 lines. The workspace phase has a typed boundary and direct regression tests. **Breaking changes** None. There are no schema, API, feature-flag, or execution-policy changes. ## What Changed - Extract the 857-line workspace preparation block without changing its operations or their order. - Preserve native recovery bindings, workspace persistence failure cleanup, issue rebinding after realization, and the cloned restore lease. - Keep environment selection, dispatch admission, terminalization, and final lease release in `heartbeat.ts`. - Add 12 boundary tests with disposable PostgreSQL, real Git repositories, and real local environment leases. - Make the existing Stop and plan-only recovery tests await executor completion instead of short polling deadlines. Assert exactly one continuation for the specific plan-only source run. - Keep server-only Node preload hooks out of the deterministic process adapter used by Stop browser acceptance. - Refresh workspace recovery browser acceptance for the current task composer, and give its disposable test-drive an explicit 10-second snapshot deadline. Production snapshot settings stay unchanged. - Document the workspace preparation boundary in `doc/DEVELOPING.md`. ## Verification - AST comparison: all 857 moved lines match the original block. The remaining module body differs only at the extraction call. - `pnpm build`: passed. - `pnpm -r typecheck`: passed. - Focused regression coverage: 651 distinct cases across eight suites passed across targeted runs, including all 12 new boundary tests. The complete 400-test recovery suite passed together on the final commit. - Workspace bootstrap browser acceptance: both journeys passed (4.2 minutes), including preserved source edits, ignored-file exclusion, bounded retries, and persistence across reload. - Stop/queue browser acceptance: both process and native runner journeys passed (2.2 minutes), covering queueing, Stop, subtree pause/cancel, resume, and unrelated-task isolation. - [Full repository CI](https://github.com/paperclipai/paperclip/actions/runs/38062408589): all 47 jobs passed, including the general and serialized test suites, eight browser shards, build, typecheck, native runner checks, and canary dry run. - The local `pnpm test:run` was interrupted to prioritize the recovery regression; the complete repository suite was verified in CI. - Greptile: 5/5 on `c28e698b885cf5fd12f36f7b4052e7a2e6f879d7`, with no open review threads. ## Risks - This code writes durable workspace bindings and acquires environment leases. A changed operation order could break recovery or cleanup after partial setup. The extraction preserves the original statements and exception boundaries. - The new tests cover creation, reuse, immutable recovery bindings, persistence failure, acquisition and realization failure, controller ownership loss, isolation, execution policy, and lease snapshot independence. - Browser acceptance uses real application services with deterministic local workers and a fake Codex protocol provider. It does not qualify live cloud providers. ## Model Used OpenAI GPT-6 through Codex, with code editing, shell execution, and test tools. 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> |
||
|
DottaandPaperclip
|
1fb3f9746e |
refactor(heartbeat): extract prepared runtime execution (#15803)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Heartbeat prepares, dispatches, and completes each agent run. > - After the runtime-selection extraction, the main service still had 7,295 lines. > - Provider dispatch and workspace finalization formed one large block with shared cleanup rules. > - This pull request moves that block into a typed runtime-execution module. > - The service now has 6,417 lines. Readers can follow admission and outer cleanup without reading the provider execution details. ## Linked Issues or Issue Description Follow-up to #15746. I searched open heartbeat PRs and issues. I found no competing runtime-execution extraction. **What existing behavior does this improve?** The organization and test coverage of native and legacy heartbeat execution. **Current behavior** The heartbeat service contains a 912-line block for provider dispatch, usage capture, workspace finalization, and instruction cleanup. **Proposed behavior** Move that block to `server/src/services/heartbeat/runtime-execution.ts`. Keep the atomic dispatch gate, admission, terminal run status, and outer lease cleanup in the service. Preserve run behavior. **Reason and benefit** This gives runtime execution a named boundary and direct tests. It removes 878 lines from the main service in one bounded change. **Breaking changes** None intended. There are no schema, API, or policy changes. ## What Changed - Add `executeHeartbeatRuntime` for prepared native and legacy execution, usage capture, workspace finalization, and gateway/instruction cleanup. - Return an explicit dispatch result. Update outer ownership state through immediate callbacks, including before exceptions. Read instruction state through live getters. - Move the two internal recovery error classes with their existing behavior. The caller imports the same classes for `instanceof` checks. - Add 15 database-backed execution tests. Keep the existing heartbeat regression suites. - Repair the native Stop acceptance fixture: installed Codex now takes precedence over `PATH`. A test-only loader pins the fake provider. An isolated home and dummy key keep readiness offline. Add four loader tests. - Document the module boundary and fixture setup. ## Verification - Passed: eight focused heartbeat suites (483 distinct tests, including 15 new execution tests). The boundary suite passed again after adding the failed-restore retention case from review. - Passed: `node --test tests/e2e/fixtures/composer-stop-codex-loader.test.mjs` (four tests). - Passed: `pnpm -r typecheck` and `pnpm build`. - Passed: AST comparison of all 912 moved lines after the explicit boundary substitutions. SQL template text, recovery class bodies, public exports, and the rest of the executor match the baseline. - Passed: browser Stop journeys for legacy process and native Paperclip Runner (two tests). The native fixture log proves provider `turn/start` before Stop and `turn/interrupt` after Stop. - Passed: all three ACP continuation browser journeys (same-session queued input, no replay of an interrupted write, and a new direction after composer Stop). Five relevant browser journeys passed in total. - Passed: the full CI test groups, including all server, chat, workspace, serialized-server, runner, and browser shards. - Local full-suite limitation: `pnpm test:run` first hit the macOS shared-memory segment limit while starting embedded PostgreSQL. After releasing only this task’s unused acceptance-server segments, the retry progressed without reported failures. I stopped that duplicate run after the full CI test groups passed. - Passed: all 56 PR checks/statuses on `8694c116e8d43ed8ac11bc4c58623ea3af34a675`. Greptile is 5/5 with no unresolved review threads. ## Risks - Cleanup depends on state written before an error. The module reports dispatch, retention, and recovery ownership immediately. Tests cover early returns and exceptional cleanup. - Instruction callbacks can replace saved metadata during execution. Live getters preserve those changes. - Native acceptance uses a real server, database, browser, and Rust runner with a deterministic provider. It does not verify a live provider service. ## Model Used OpenAI Codex, GPT-6 family, with reasoning and repository/tool access. The exact serving model ID and context-window limit were 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> |
||
|
DottaandPaperclip
|
3ec7309d91 |
feat(voice): add experimental Speko task connection runtime (#15727)
First PR: runtime. UI: #15728. Qualification: #15729.
## Thinking Path
> - Paperclip manages agent work through tasks and governed connections.
> - Chat connections already bind external conversations to those tasks.
> - Speko handles voice and telephony, while the selected Paperclip
agent does the work.
> - A call needs durable session authority, ordered follow-ups, and safe
result delivery.
> - This PR adds an explicit voice transport to the existing connection
runtime.
> - The UI and qualification suites follow in linked PRs. Speko stays
experimental.
## Linked Issues or Issue Description
**Problem or motivation**
Phone and browser voice conversations cannot use the chat connection
task lifecycle. A separate voice runtime is needed to preserve task
authority, retries, and reply history.
**Proposed solution**
Add company-scoped voice sessions, signed callbacks, durable replies,
inbound intake, and an agent-facing outbound-call tool. Reuse existing
tasks, queues, secrets, and publications.
**Roadmap alignment**
This extends the experimental chat connector entry points under Agent
Chat and Connected Apps. The project owner requested this feature.
Refs #11418 for the original provider catalog proposal. This
implementation uses the newer chat connection infrastructure rather than
an MCP catalog-only integration. Refs #15721 for remote OpenCode
startup.
## What Changed
- Add additive voice schema, shared contracts, session APIs, and
provider callbacks.
- Bind browser, inbound, and outbound sessions to an endpoint, task, and
selected agent.
- Add low-trust guest intake in an explicitly selected sandbox and keep
ordinary approval rules.
- Submit task work through session-scoped tools and push approved
replies through Speko POST /v1/calls/{id}/messages.
- Distinguish provider acceptance from confirmed spoken playback.
Reconcile reports without downloading recordings.
- Add protocol, migration, persistence, provider, and
delivery-diagnostic tests.
## Verification
- Master
|
||
|
Devin FoleyandPaperclip
|
935fb63ed5 |
fix(release): retry incomplete canary dependency publications (#15743)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Release checks must test the exact package that a new user installs. > - The canary onboarding smoke uses a fresh npm dependency graph. > - An upstream package can reference a dependency before that version is available. > - The smoke then exits before Paperclip onboarding starts. > - This pull request retries only that npm acquisition failure within the existing startup limit. > - Onboarding still runs once, and all other errors remain visible. ## Linked Issues or Issue Description **What happened?** [Release run 37986221440](https://github.com/paperclipai/paperclip/actions/runs/37986221440) published `2026.1009.0-canary.13`, then failed the onboarding smoke. The retained server log contains npm `ETARGET` for `@aws-sdk/credential-provider-env@^3.972.73`. The upstream parent package was published before this dependency. The missing version became available during the smoke startup. Paperclip onboarding never ran. **Expected behavior** Retry a short dependency publication window before onboarding starts. Stop on a permanent install failure. Never repeat onboarding to hide a startup failure. **Steps to reproduce** 1. Start the exact-version canary smoke with an empty npm cache. 2. Make the first npm install return `ETARGET` because a dependency version is not available. 3. Make the next install succeed after registry metadata changes. 4. Confirm that onboarding starts once. Repeat with permanent `ETARGET` and an unrelated failure; onboarding must not start. **Paperclip version or commit** The observed release source was `cb291bf1298ab484a2792c05eb977f3440f1f351`. **Deployment mode** Linux release CI. The change affects the canary smoke harness. Related: #15712 fixes a separate lockfile mismatch in the smoke's repository dependency install. This change covers the fresh published-package npm install. ## What Changed - Separate npm package acquisition from the onboarding command. - Retry only the final npm `ETARGET` error, up to three attempts with online metadata and clean temporary prefixes. - Share a two-minute acquisition budget across attempts and backoff. Keep the existing five-minute Playwright startup limit. - Run the installed exact-version CLI once. Preserve authentication, network, lifecycle, and onboarding failures. - Stop owned process groups on cancellation and remove owned install prefixes. Keep server logs and instance data for diagnostics. - Keep dependency-free helper subprocess tests in the required policy lane. Run real Playwright lifecycle tests in the required release-registry lane after its dependencies are installed. - Document the bounded behavior in the release runbook. ## Verification - `node --test scripts/__tests__/release-verify-workflow.test.mjs`: 24 passed in a clean source snapshot with no `node_modules`. These cover transient and permanent missing versions, other npm errors, nested error codes, onboarding failure, deadline expiry, and cancellation. - `pnpm test:release-registry`: 153 passed, including real Playwright teardown with a descendant that ignores SIGTERM and startup-timeout cleanup of a detached npm installer. - `pnpm -r typecheck`: passed. - `pnpm build`: passed. - `pnpm test:run`: deliberately stopped after complete hosted CI passed; this is not a local full-suite pass. The run's 15 warm-runtime real-DB cases failed before assertions because the local macOS PostgreSQL package lacked library symlinks after installation with `--ignore-scripts`. After running the package's local hydration step, all 15 affected cases passed in a targeted rerun. The remaining aggregate was stopped with exact owned-process cleanup. - [Hosted CI](https://github.com/paperclipai/paperclip/actions/runs/37994486323) is complete and green at `1c80e6f`: all tests, build, typecheck, policy, release registry, E2E, and canary dry run passed. Greptile scored the same head 5/5 with no unresolved comments. - Independent review covered all seven changed files and the exact policy and release-registry commands. It also used real npm 11.9 against a loopback registry: a required version was absent, then became available. The retry refreshed metadata and started the installed exact-version CLI once. The one-attempt negative control failed. - The new subprocess tests use local npm and CLI fixtures. They do not contact a registry or start a real Paperclip instance. - The patch preserves the exact-version clean-install check. It adds no dependency pins, credentials, or workflow reruns. ## Risks The install phase now has a two-minute budget inside the existing five-minute startup limit. An unusually slow valid install can still fail the smoke. Permanent missing versions remain failures after the bounded retry. The lifecycle tests cover the Linux release runner behavior; Playwright does not support graceful SIGTERM on Windows. No application, database, or deployment behavior changes. ## Model Used OpenAI GPT-6 through Codex, with reasoning and code execution tools. The exact service variant and context window 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> |
||
|
DottaandPaperclip
|
ed2c22ea8c |
feat(connections): simplify dedicated GitHub App setup (#15416)
## Thinking Path > - Paperclip manages agent work and the tools each agent can use. > - GitHub bots need their own App identity and restricted repository access. > - Manual App configuration and repeated setup gates make that connection hard to finish. > - GitHub can create an App from a manifest, but people must approve creation and repository access. > - Each Paperclip stack should own configuration, credentials, signature verification, and task admission. > - This change uses Cloud as an encrypted callback and event gateway, then completes setup in the stack. > - GitHub review bots have their own experimental setting. Chat connector opt-in does not control them. ## Linked Issues or Issue Description **What existing behavior does this improve?** Dedicated GitHub App setup, bot settings, and task-scoped GitHub replies. **Current behavior** Users must configure an App, copy credentials, repeat repository selection, and complete manual verification gates. Review settings are hard to scan. Mentions in descriptions can be missed, and automatic completion text can produce an extra GitHub comment. **Proposed behavior** Choose an agent and connect GitHub under a personal account or organization. GitHub asks for creation and installation consent. Paperclip resumes the same draft, stores secrets locally, imports access, verifies delivery, and opens Settings. Each accepted request has one editable App-owned comment for progress and results. Review assessments produce deterministic checks for the reviewed commit. **Breaking changes** GitHub bots require their own default-off experimental opt-in. The setup-method and delegated-agent screens are removed. Per-person automatic-run flags remain readable but are replaced by author filters. Existing connections, direct webhooks, saved restrictions, and manual existing-App recovery remain supported. Companion gateway: https://github.com/paperclipai/paperclip-cloud/pull/688 (merged). The roadmap and related PRs were checked; no duplicate dedicated-App wizard was found. ## What Changed - Add an independent **GitHub review bots** setting across the catalog, routes, identity admission, and task controls. Existing bots continue running when the UI setting is off. - Replace setup with Choose agent and Connect GitHub. Support personal and organization owners, inline low-trust conversion, saved drafts, known organization suggestions, automatic completion, and same-App recovery. - Keep manifests, OAuth PKCE, credential exchange, vault storage, installation verification, and original webhook-signature validation in the stack. Use the Cloud sealed gateway for public callbacks and outbound local delivery. - Add resumable owner metadata in migration 0323. Retry a failed registration renewal through the same durable replacement rather than creating another App route. - Support authorized mentions in issue and PR bodies, comments, inline comments, and review summaries. Preserve attachments, edited-source identity, duplicate protection, and lifecycle invalidation. Filter requests explicitly addressed to another connected bot. - Give agents task-scoped review, comment, and update tools. Update one working comment through progress and final output. Close coalesced requests and recover delayed acknowledgements, including deleted earlier working comments. Preserve automatic replies for legacy connections without saved review configuration. Preserve partial publication evidence and quarantine uncertain automatic fallbacks without blocking Board messages or questions. - Reorganize Settings and Access with rich slash-skill instructions, numeric passing scores, clear automation controls, formal-review tooltips, member and contributor sections, and verified App branding links. Preserve invalid score drafts and automation choices across tabs. - Paginate repositories in 20-row batches with search and a true connection-wide toggle. Batch verification at GitHub's 500-ID token limit. Keep saved repository overrides while hiding their editor. - Give each review a detail URL that remains usable beyond the newest 100 records. Synchronize the manager OpenAPI contracts and add recovery, authorization, UI, and browser regressions. - Reconcile the current master branch and retain its agent avatar, feature catalog, and extracted heartbeat preparation code. Preserve a saved test-drive port and recover from an occupied high port. ## Verification - Focused UI, independent experimental-setting, and CLI tests: 199 passed. - `pnpm -r typecheck`, `pnpm build`, and `pnpm check:token-gates` passed. The broad local Vitest attempt was interrupted after resource timeouts and stale expectations; the affected regressions passed focused reruns. The latest-head full CI matrix passed, including all browser shards, server/chat suites, builds, typechecking, canary packaging, and Docker context integrity. A Docker Hub 429 required a CI retry; it passed without changing the code. - Final review repairs: 127 attachment/event tests and server typecheck passed. All 13 final integration regressions passed under the normal CI timeout, covering legacy reply compatibility, deleted coalesced comments, inline-only review completion, progress edits, and native final recovery. Restart-safe description/review attachments passed the attachment suite. - Final regressions: four reply/lifecycle tests, both native GitHub wait tests, 171 feature-gate/reply-contract tests, the routed review preview, and five scheduler/reply regressions passed. The final fixture repair also passed all six setup-continuation cases and all three complete chat-test shards in CI, covering terminal receipts and retries under the normal CI timeout. One loaded-host receipt run exceeded its local timeout; the exact case passed in an isolated rerun and the complete CI shard. - GitHub integration tests cover personal and organization setup, retry recovery, edited mentions, attachment provenance, coalesced requests, delayed acknowledgements, partial review writes, old review URLs, and company boundaries. - Browser qualification: both GitHub journeys, all five provider setup/management journeys, and the GitHub uncertain-send recovery journey passed. GitHub setup, reconnect, and task replies run with chat disabled; chat enabled alone cannot expose GitHub bots. The disposable qualification database was removed after testing. - Earlier live qualification verified App-owned issue replies, native slash-skill invocation, progress comment edits, and a 5/5 PR review with a passing current-head check in the dedicated permissions-smoke repository. These live checks did not use personal credentials as bot execution authority. ## Risks - Deploy the merged Cloud gateway protocol before the stack update. Each callback and encrypted event must retain the original instance and tenant binding. - Migration 0323 uses idempotent column additions for test installations that already applied the earlier draft migration number. - A verified connection does not prove runtime isolation or a completed review. Runtime checks remain separate. - Required merge checks must be configured in GitHub. A passing numeric score does not formally approve a PR; approval and request-changes tools remain opt-in. - Existing-App credentials cannot silently renew an uncertain manifest exchange. Recovery preserves the existing App, draft, connection, and agent. - Repository changes save immediately. Global toggles affect all currently available repositories, including unloaded rows, without granting new installation access. - A failed or uncertain tool write suppresses automatic fallback text; the governed outbox retains its evidence. Deleted or replaced response comments are not recreated through a personal credential fallback. - GitHub logo upload remains an optional human action in GitHub App settings. Runtime provisioning, delegated setup, screenshot publication, and production push delivery remain deferred. ## Model Used OpenAI Codex, based on GPT-6, with tool use and code execution. The exact runtime model identifier and context 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 references) - [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 (focused suites; complete test matrix is checked in CI) - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing> |
||
|
DottaandPaperclip
|
b6b3cb3761 |
Fix unavailable workspace branches with an inline repair and retry (#15726)
## Thinking Path > - Paperclip manages AI agents and their work. > - Isolated workspaces must resolve a starting Git ref before an agent starts. > - A task can explicitly select a branch that the repository does not have. > - The current recovery notice calls this a missing secret and offers no branch repair. > - This pull request explains the branch failure and adds a task-scoped repair action. > - Operators can correct the branch and request a guarded retry from the task thread. ## Linked Issues or Issue Description Related: Refs #11892 added unresolved-ref recovery. Refs #15719 added bounded failure diagnostics. This change uses that recovery path and adds its operator repair UI. **What happened?** A task that selects `main` in a repository with only `master` stops before the adapter starts. The task shows a missing-secret message and a generic retry. Repeating the run cannot fix the stored branch setting. **Expected behavior** Explain that the starting ref could not be resolved. Offer a verified repository default, or let the operator enter a branch. Save only the task's starting branch and retry its recorded owner through the existing admission gates. **Steps to reproduce** 1. Create an isolated-workspace task in a repository with `master` and no `main`. 2. Set the task's base ref to `main` and assign an agent. 3. Wait for the configuration failure. 4. Use the inline branch repair and confirm the agent completes in a worktree based on `master`. ## What Changed - Replace the missing-secret diagnosis for unresolved workspace refs. Keep uncertain fetch/access failures described as uncertain. - Read the remote's advertised default branch with the existing Git credentials and a bounded timeout. Do not guess or silently change the branch. - Add an atomic branch repair to the existing recovery resolution endpoint. Check company access, board runtime permission, incident identity, current owner, task/project state, dependencies, interactions, approvals, budget, and active execution before requesting a retry. - Preserve the effective inherited workspace setup when saving the task branch override, and attach one repair notice per failed run even when the incident is reused. - Bind the shared repair card to the exact recovery notice and failed run in both task-thread renderers. Validate branch syntax and prevent duplicate submissions. - Add Storybook examples, regression tests, and a documented local acceptance fixture with a real Git repository and process adapter. ## Verification - Red/green regressions cover the repair endpoint and preservation of inherited agent setup. The regression failed before each fix and passed afterward. - Focused integration suite: 162 tests passed; task-thread/card suite: 230 passed. After review refinements, all 13 repair-route tests, 10 card tests, 77 recovery-action tests, and the repeated-failure heartbeat regression passed locally. - Real browser acceptance passed for suggested-branch and custom-entry repairs. Invalid syntax left the task blocked. Both valid repairs ran the authenticated worker in a real isolated worktree and reached Done; reload preserved the result. - Repeated failures reused the recovery incident and retained an actionable notice on the latest run. The inherited-setup journey verified the provisioned file, agent branch template, worktree parent directory, and actual Git commit before completing. [Before/after screenshots](https://github.com/paperclipai/paperclip/pull/15726#issuecomment-6088734666). - Full local typecheck and build passed; server typecheck passed again after review fixes. Token gates passed. - The monolithic local Vitest run was stopped after resource-contention timeouts and stale assertions. Targeted regressions were rerun; the full CI matrix passed on final revision `26c543ff490bec29ddc77a49ee532c7f84fb96dc`. One signoff E2E worker-cancellation failure passed on a rerun without code changes. The two opt-in Storybook workflow jobs were skipped; the Storybook journey was checked manually. - Repeat the live journey with `tests/e2e/workspace-base-ref/README.md`. Storybook examples use simulated callbacks and are not the live acceptance proof. ## Risks - Default-branch discovery can add up to 10 seconds to an unresolved-ref failure. Lookup failure leaves manual entry available. - A valid branch name can still be absent or inaccessible. The retried workspace preparation remains authoritative and can block again with new evidence. - Retry remains subject to normal admission gates. The repair changes only the task override; it does not alter project or agent defaults. - No database migration or new dependency. ## Model Used OpenAI GPT-6 through Codex, with tool execution, repository analysis, and browser testing. The exact serving 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> |
||
|
DottaandPaperclip
|
0726a00e80 |
feat(apps): qualify Bitly, Context7, Hugging Face and Resend MCP (#15686)
## Thinking Path > - Paperclip lets people manage AI agents and govern their tools. > - Apps already supports provider-hosted MCP servers. > - Useful providers still need real setup and read proof before Browse exposure. > - Browser testing found a Bitly token-format failure and an OAuth callback that replaced an explicit empty agent selection. > - This PR qualifies four provider methods and fixes those shared OAuth paths. > - Providers that still need login or approval remain withheld from new Browse listings. ## Linked Issues or Issue Description Refs: #15621, the merged hosted MCP qualification batch. Searches found no duplicate Bitly or Context7 implementation PR. **What existing behavior does this improve?** Apps setup, provider MCP discovery, token exchange, and saved agent access through an OAuth callback. **Subsystem affected** Shared Apps definitions, the server tool-access service, and the UI setup/recovery route. **Current behavior** Bitly's callback can fail with `oauth_access_token_missing` when its token response is not JSON. Curated MCP callbacks can treat an explicitly saved empty install set as access for all agents. Context7 is hidden and Hugging Face lacks a curated anonymous method. Saved drafts for hidden providers cannot finish setup through their catalog wizard. **Proposed behavior** Request JSON token responses. Record explicit remote MCP install choices in the install transaction and preserve them at callback. Keep managed subject/default access when no choice was saved. Expose the qualified Bitly and Context7 methods, add anonymous Hugging Face Hub access, and record Resend qualification. Resume hidden providers only through an exact matching company-visible saved draft. **Reason and benefit** People can connect useful hosted tools through the existing Apps flow. An explicit zero-agent selection survives authorization. Public documentation lookups need no OAuth app, account, or key. **Breaking changes** Explicitly saved empty MCP install choices now remain empty. Existing managed defaults without a saved choice retain their behavior. No schema migration or API shape change. ## What Changed - Qualify Bitly OAuth, Context7 public MCP, Hugging Face public MCP, and Resend OAuth with real browser setup, useful UI reads, and reload checks. - Negotiate JSON OAuth token responses and preserve explicitly saved MCP agent reach with a transactional config marker. - Add durable provider overrides, permission reviews, dated text-only evidence, and official branding provenance. Remove all seven evidence images and their report references. - Restore Finish setup for hidden-provider drafts with company/application/provider checks; keep fresh setup withheld. Preserve success after the exact resumed draft becomes active, and restore valid completed URLs to that exact saved Permissions page; reject initially active, disabled, or archived resume targets. Align the Context7 route assertion with its new qualified availability. - Retain hidden ClickUp, Klaviyo, and monday.com research with exact login/approval gates. monday.com requires provider callback allowlisting. ## Verification - Connector service suite: 420 passed, including default/empty/agent/company reach and managed OAuth lifecycle coverage. - Shared catalog: 36 passed. Override tests: 3 passed. Brand checks: 101 identities passed. - Focused UI setup/recovery, Browse, and OAuth-helper suites: 306 passed. Actual hidden-draft resume/reload passed; a public Context7 draft seeded in the isolated app completed through the active-state refetch and persisted with zero agents after reload. The completed URL refresh and View connection open the exact saved Permissions page. Fresh hidden setup, normal initially active resume, disabled/archived status, and provider mismatch are rejected; a draft at the completion stage stays in setup. - Recursive typecheck and build passed again after rebase. The full local Vitest run began before rebase and was cancelled as superseded while still in the general-server phase; it is not a completed pass. Exact-head CI supplies broad coverage. The focused connector service suite passed against the final code. UI typecheck, build, and token gates passed again after the draft-recovery fix. - Targeted mock MCP Playwright journey: 1 passed (34.9s). It now verifies View connection reaches the exact saved Permissions route, both discovered actions, and reload persistence. This replaces the stale Browse expectation found by CI. - All CI gates passed on final commit `32bb4c6422411eee632486950e45e2735102d1b3`. The inherited-pause test timed out in the cleanup run and passed on one retry without code changes; the entire file also passed locally, 36/36. Its exact timing cause remains unresolved. A signoff timeout on the preceding production-code commit also passed on its single retry. Greptile reviewed the final commit at 5/5 with no open findings. - Actual UI reads: Bitly current-user read; Resend List Domains including a fresh setup after the final callback refinement; Context7 React docs; Hugging Face public docs search. No provider writes or real agent runtimes ran. - [Text-only qualification report](https://github.com/paperclipai/paperclip/blob/32bb4c6422411eee632486950e45e2735102d1b3/doc/connections/easy-mcp-batch-2-2026-10-09.md) include evidence limits and exact blockers. Account/profile/domain results are omitted. ## Risks - Bitly `mcp.all` and Resend `full_access` remain broad provider grants. Qualification kept writes Off and selected no agents. Read proof does not establish write behavior or refresh rotation. - The explicit-choice marker applies to new install saves; older unmarked flows keep their existing defaults. Its JSONB merge avoids overwriting concurrent config fields. - Public provider catalogs and rate limits can change. Unqualified providers remain withheld from new Browse entries; retained connections remain available for recovery. ## Model Used OpenAI Codex, based on GPT-6, plus OpenAI `gpt-6-luna` subagents for provider research, browser testing, and review. The exact primary serving variant and context-window size are not exposed by this runtime. Used reasoning, 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 - [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> |
||
|
Nicky LeachandPaperclip
|
2dd9811e8b |
Own agent hiring and termination in a lifecycle module (#15631)
## Thinking Path > - Paperclip manages AI agents and their work. > - Agent creation, approval, pause, and termination change whether an agent can work. > - These changes currently use separate service and database paths. > - Some agents need setup after their record exists and before their harness can run. > - This PR adds one module that owns those state changes and their transactions. > - The module records progress and retries incomplete work after a server restart. ## Linked Issues or Issue Description **Problem or motivation** A hire can become active before its execution environment is ready. Direct agent state writes also bypass one common lifecycle boundary. Termination does not have a durable step for resource cleanup. **Proposed solution** Use agent lifecycle commands for hiring, approval, pause, resume, and termination. Keep proposed hires pending until approval. Prepare each approved hire, test its saved harness configuration, and then permit work. Wait for required plugin work before completing a step. **Alternatives considered** A general database commit hook would expose transaction details to callers. A timer alone would delay each new hire. This module owns each command transaction and starts its worker after commit. A periodic scan recovers work after a process stops. **Roadmap alignment** This change adds the lifecycle boundary for the existing agent and plugin systems. It does not add a user interface or a provider implementation. It replaces the lifecycle delivery approach in #15391. Related proposals include #11475 and #13099; this change does not add their external executor protocols. ## What Changed - Add durable approval, preparation, verification, pause, resume, stop, and cleanup states. - Keep agent creation, lifecycle state, configuration writes, and agent record deletion behind `modules/agent-lifecycle`. Keep validation, credential rules, reads, onboarding, invitations, general approvals, and company data deletion in their services. - Commit a hire before the remaining onboarding or invitation work. Serialize requests with the existing dedicated database connection helper. Reuse the hire after a failed attempt. - Keep accepted work in the run queue during setup. Require execution and cleanup evidence before completing pause or termination. - Retain the original credential owner when approving migrated hires. - Start lifecycle work after each command commits. Use database leases and revision checks for retries and late results. - Add a generic required plugin method and capability. Store the required plugin IDs for each agent. Track host and plugin completion separately. - Keep harness verification and credential rules in services. Supply their results to lifecycle through explicit ports. Reject failed logins and incomplete probes. - Remove reverse imports from lifecycle adapters into services. Share record queries and validation below both layers. - Use one hire decision path for agent IDs and approval IDs. Resolve the approval and agent change in one transaction. Expose policy reconciliation on the command object. - Save configuration and verification invalidation through one module operation. Ordinary commands own their transaction. Restrict the shared transaction integration to its listed callers. Reject identity, company, accounting, timestamp, and unknown fields. - Require completed termination before deleting agent records. The company deletion service calls the module through a separate deletion interface. - Save an approved secret before applying its agent binding. A failed binding leaves the secret approved. A retry reuses it. - Remove old permission and metadata export files. Move hire configuration rules out of lifecycle persistence. - Report failed worker steps and scans with operation context and known error codes. Omit provider messages, stacks, and configuration values. Document ordinary application use and extension rules. - Recover expired native owners only after execution stops. Retry cleanup of failed retained leases. Wait for setup in the live smoke script. - Keep manual, budget, and company pause reasons separate. Guard execution status writes with the ready state. - Add a migration, boundary checks, regression tests, and a lifecycle guide. Keep the current UI. - Limit periodic policy checks to 100 eligible agents per minute. Continue from the last agent ID. Exclude pending hires and agents in termination or a final state. Keep explicit company and budget updates immediate. ## Verification - Latest head `ccc3c86b0` aligns the shared status update schema with the PATCH route. All 15 shared tests, 104 server route/OpenAPI tests, 2 CLI tests, and shared/server/CLI TypeScript checks pass. The Greptile comment is fixed. CI is running; no new Apex review was requested for this small fix. - Rebase `75708ac94` rebases onto master at `2eb5187e4`. The backup test uses the shared 90-second timeout from master; the older timeout commit was removed. The affected backup test passes. - Agent budget edits now pass the target agent ID through enforcement. All 50 affected tests, server TypeScript, and 11 boundary tests pass. Both configuration update paths have regression coverage. CI is running on the latest head. No new Apex review was requested for these small fixes. - Rebase `9b568666a` preserves the run-control extraction and delivery-work startup changes from master. All 559 affected tests, server TypeScript, and 11 boundary tests pass. CI and Apex review are running on the final head. - The policy scan fix passes 56 lifecycle and diagnostic tests, 24 policy and caller tests, and 11 boundary tests. A regression test checks the page limit, interval, excluded states, and cursor wraparound. - Rebase `fd4698750` passes all 611 tests in eight affected lifecycle, route, and heartbeat suites. Server TypeScript and all 11 module boundary tests pass. The company deletion rollback and concurrent hire tests are included. - Follow-up `00aac7646` fixes the failed decision deletion test and the public update schema. All 126 affected server tests, 8 shared tests, 2 CLI tests, and 11 boundary tests pass. Shared, server, CLI, and UI TypeScript checks pass. - Server TypeScript passes: `pnpm --filter @paperclipai/server exec tsc --noEmit`. - All 11 boundary tests pass: `node --test scripts/check-module-boundaries.test.mjs`. The repository boundary scan also passes. - All 68 lifecycle, failure diagnostic, and harness verification tests pass. Tests reject forbidden fields through the root command, combined transition command, and restricted transaction integration. They also check invalid fields returned by configuration preparation. - Failure tests cover host work, plugin work, claims, renewals, deferrals, and scans. Log tests check known error codes and exclusion of private error contents. - All 355 tests in 10 existing caller suites pass. These tests cover secret approval, pairing, pending hires, credentials, company import, built-in agents, managed agents, instructions, and skills. - The branch is rebased onto `origin/master` at `2eb5187e4`. The queue guards and cancellation lock fix use the extracted heartbeat queue. Agent cancellation uses the extracted run-control file. The source diff scan found no secrets or private URLs. - Earlier checks cover approval retries, rollback, late verification results, policy holds, deletion rollback, concurrent company deletion, and queue admission during setup. - Before the rebase, CI passed on `00aac7646` and Greptile Apex rated it 5/5 with no open comments. CI and a new Apex review are pending for the rebased commit. The branch has no merge conflicts. - The full local build and native Dot suite were not run. The host has no Cargo. No live provider test was run. ## Risks - Background policy recovery takes more than one minute when more than 100 agents are eligible. Explicit company and budget updates still reconcile immediately. - The restricted configuration integration keeps an agent reference and its dependent records in one transaction. It cannot change a budget or invoke a lifecycle transition. A periodic scan starts pending setup after that transaction commits. - Secret approval and binding use separate transactions. A failed binding can leave an approved secret with no agent binding. - New approved hires remain unavailable until setup and verification complete. Existing clients see `paused` during these steps. This PR does not change the UI. - Migration `0320_daily_onslaught.sql` maps existing statuses and pause reasons. It does not create external resources or claim that an existing harness passed verification. - Use a coordinated server update for this migration. Older server versions can write legacy status without the new lifecycle checks. - A failed onboarding or invitation request can leave a committed hire. A retry reuses that hire and completes the remaining records. - Deletion requires completed termination. Company deletion can require another request while cleanup is pending. - Required plugins must make repeated calls safe and reject older revisions. A disabled or removed required plugin blocks completion until it is restored. - A new hire can run a second harness test after the existing UI test. Some adapters can charge for this test. - No live provider test was run. Provider implementation and resource backfill remain separate work. ## Model Used OpenAI GPT-6 through Codex, with reasoning, code tools, and local 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 described the issue in this PR with the feature request field labels - [x] I have not referenced internal or instance-local issues or links - [x] My branch name describes the change - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation - [x] I have considered and documented risks - [x] Targeted local tests pass - [x] All Paperclip CI gates are green on the new commit - [x] Greptile Apex is 5/5 with no open comments on the new commit - [x] I will address review comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing> |
||
|
DottaandPaperclip
|
57e977be72 |
feat: integrate Pi 1.0 into the experimental Runner (#14921)
## Thinking Path > - Paperclip manages AI agents and their work. > - The experimental Runner owns provider processes and durable sessions. > - Pi needs working task execution and human controls. > - The five-PR stack must preserve changes already on master. > - Each layer now carries the complete integrated source for a safe sequential fallback. > - This PR belongs to native GitHub stack #15602, ending at #14956. ## Linked Issues or Issue Description Refs #14436, #14631, #14743 and #14956. Ship Pi 1.0 through the experimental Paperclip Runner. The five PRs are #14921, #14922, #14923, #14924 and #14956. The user authorized the complete merge after checks pass. Existing `pi_local` execution is unchanged. Accounting and wider provider/platform qualification remain deferred. ## What Changed - Recover missing final replies after workspace finalization changes owners, using accepted-turn evidence without rerunning work or granting external-chat publication. - Preserve the admitted Pi instruction root across warm runs, while retaining changed-root rejection. - Give Pi a bounded 15-second default shutdown grace so stop, drain acknowledgement and durable suspension can complete. Explicit deadlines and other providers retain their existing behavior. - Integrate the Pi 1.0 runtime and master contracts. - Use Pi profile 22. Preserve explicit caller-selected models and exact native thinking levels. Keep Pi's wrapper, helper, extension and question/control behavior unchanged from the qualified profile-19 runtime. - Preserve master's Dot lifecycle and consent fields, configured task environment, status guards and current Codex/Claude dependency versions. Cursor stays qualified. Copilot stays pending; profile 17 binds the changed shared protocol validation sources. - Exclude general AWS IAM credentials from Pi static/custom provider bindings and selected task projections; preserve the provider-scoped Bedrock bearer key. Profile 21 is retained as historical provenance. Rust and cloud install probes use the current declaration. - Patch bundled brace-expansion 5.0.9 to the exact official 5.0.12 payload. Pin the patch and complete runtime closures. Include the patch in normal installed setup tooling. Keep the upstream Pi shrinkwrap as provenance and permit only this exact security correction. - Include current attestation files in the Docker build context. Keep the repository lockfile unchanged from master. CI and private image builds resolve manifest changes before their frozen installation. ## Verification - Full local `pnpm -r typecheck` passes, including Runner Rust, server and UI. Focused integration checks pass: 194 Runner admission/environment tests, 63 profile/credential tests with one expected skip, 152 Dot/UI configuration tests, and Pi transcript/notice tests. - Full local `pnpm build` passes on the final source. - Fresh final-source checks pass: all 698 Rust workspace tests (32 binaries), 156 credential/profile/controller tests with one expected skip, Runner TypeScript typecheck, and 20 package/setup/sandbox tests. - The profile-21 Pi materializer passes on the native host with the official pinned Node 24.21.0 and its npm. It verifies all 150 locked packages, the patched dependency and the exact closure. Setup/package bundle tests and UI token gates pass. - The old hashes were reproduced for all three supported targets before calculating the patched graph. New closure hashes are darwin-arm64 `282022db10150c6632b3444df421342e7d534bdf5d5fb1097a2e79d0625a2bcf`, darwin-x64 `64e251e19009f755c0b04f73ce2138246faab71a961b0f13d75ebfcc34bef12e`, and linux-x64 `713b1fdff42fb56a1518bdc084f181d70bee8ebadc3e4b1d76321ed9108c8410`. Independent native platform execution is separate from graph identity reproduction. - Historical cloud qualification remains unchanged: all seven core cases pass on shipping source `10dc43c9ec65d88c2f782d62afb296d09494f215`, harness `1a4408a48cfb5a1f094a311141c257c92cd7a893`, image `sha256:5b3a775b383591bda1b0c1889e509acc70ce7f37c53f09733c81d59037f02280`, and accepted Sonnet 4.6/low fixture. All 215 canonical files and all seven cleanup checks pass independent verification. These are profile-19 results and are not relabeled as fresh profile-22 runs. - Current Pi digest: `sha256:e92078bee3c23bec4100aa589013a44613d054cd686826534025d8019e9f39a9`. [The readiness plan](https://github.com/paperclipai/paperclip/blob/codex/pi-production-readiness/doc/plans/2026-10-02-pi-production-readiness.md) preserves campaign and failed-attempt provenance. - Merge only after every PR's current-head CI and fresh review pass. Linux CI covers the full suites, build and browser tests. The local embedded Postgres API-authority suite cannot start on this macOS/Node 26 host, so Linux CI must confirm that suite. ### Fresh profile-22 core qualification — 2026-10-08 All seven accepted core cases pass canonically on Pi profile 22, with `openrouter/anthropic/claude-sonnet-4.6` and native-confirmed low thinking. This model is a fixture; production accepts the caller's explicit Pi provider/model. Runtime/install source: `3241a992f2a7703e59e97ed0fd3e5d6405de4401`. Frozen accepted harness: `1a4408a48cfb5a1f094a311141c257c92cd7a893`. Immutable cloud image: `ghcr.io/paperclipai/paperclip-daytona-runner@sha256:506f22db7edd78f37c0c40bec1cc084af1850455026dbf467194bfbb8fcef141`. Pi digest: `sha256:e92078bee3c23bec4100aa589013a44613d054cd686826534025d8019e9f39a9`. [Hosted Linux image and clean-install verification](https://github.com/paperclipai/paperclip/actions/runs/37868328023) passes, including all 20 source-bound archives, normal CLI/Pi setup, companion import and the production pack reader. This exact installation source includes the latest master integration and the corrected Pi warm instruction-root fence. Full local typecheck/build and current-head hosted CI verify the final stack. All 13 focused real-root regressions pass. The full local executor suite passed 662 tests; 15 database tests could not start the Mac embedded PostgreSQL service. Hosted Linux CI passes the full required verification and E2E checks. These fresh results keep their own source identity; profile-19 results remain historical. | Core path | Canonical campaign | Retained archive SHA-256 | | --- | --- | --- | | File edit, validation, download and Done | `pi-core22-replyfix-0-1791511228` | 23 files; `a473e8603a3dd4737863291f8d3d1e392391f0b16d433c3e0e0e9d8baf7a97b0` | | Pending question and controller restart | `pi-core22-replyfix-1-1791511376` | 33 files; `6b829c4eb74e1f32a89c692a4ae7130dbfc1c6d3cf13915effe2103d9e242c8e` | | Three-turn session/process/workspace continuity | `pi-core22-replyfix-2-1791511587` | 23 files; `7a87021f8f9a3fdd3c58bb4467f8d82c635e3ea4795d6e75f144d9aa14818df8` | | Four typed questions and browser reconnects | `pi-core22-replyfix-3-1791511881` | 42 files; `9e31755252be1f4f9cb0626c984c142d4d1ae5f5bee3a7af08444db8d12c280a` | | Plan approval and completion | `pi-core22-replyfix-4-1791512031` | 22 files; `a0383ce1aab38e7b5a25ce0e9dd3bebea5c037ebd96ae6b29dae19015da2ae2c` | | Same-turn steering and permission denial | `pi-core22-replyfix-5-1791512261` | 39 files; `c929b8c7070f0b66aedc17e65ca46e6beab1e363926ac9f7e2a75fb250f05949` | | Stop during pending permission | `pi-core22-replyfix-6-1791512390` | 33 files; `7f0a58ae0f4d5bfc76149435f4e322537089c5bd16e7ffe9b5ad71f10a621a07` | All 215 canonical files (28714587 bytes) are independently hash-verified. All seven cleanup grades pass, with no owned runtime process or temporary root after each case. Automatic retries are zero. The owned cloud host stopped normally after retention. The prior profile-22 warm attempt remains failed and separately retained: archive SHA-256 `1e54eba5ec72b50cee1534b23d1d1d4f21a090006b8a64501ba70db972abfde5`. Its original canonical classification is preserved. Diagnosis reproduced a product bug comparing an agent-files root against an unset checkpoint-only field. The fix stores the admitted physical root separately from the adopted per-run collection capability. The real-root regression fails before the fix and passes afterward, including rejection of a changed physical root. Fixture, grader, model and all seven accepted case IDs are unchanged; this fresh campaign tests final-reply publication after file registration first. The intermediate restart attempt also remains failed and retained: archive SHA-256 `5dcaefdf1d17cf4cd54fd4cf810f45e736667392339b8ce7caf08bb4e225277f`. Its original canonical classification is preserved. Pi resumed, wrote the verified answer and completed its task; exact runner suspension was proven, but idle stop consumed about 5.2s and left under 3s for the drain acknowledgement. The Pi-only default shutdown grace is now 15s, preserving a full 5s drain round trip and a finite suspension reserve. Explicit caller deadlines, other provider defaults, literal drain receipts and exact suspension identity checks remain unchanged. The timing regression fails before this correction and passes afterward; all 18 focused settlement tests and Runner typecheck pass. The final-source file attempt is also preserved as failed (`candidate_failure`), archive SHA-256 `db6767b6773ea618997927ac77bdb005a5ac81492c7b9c0ffbc900449f829bc9`. Native edit, validation, exact downloadable artifact and Done/succeeded all passed, and the exact final reply was durably recorded. A workspace recovery owner completed before the live heartbeat reached presentation, leaving that reply absent from task chat. Recovery now materializes only a completed final reply from the accepted turn of an ordinary internal Done task, preserving issue/run/contract binding, suppression, external-chat authorization and same-run deduplication. The database regression covers the generated file-preparation receipt, suppression, unapproved external continuation and replay. Server typecheck and all 49 response-selection tests pass; hosted Linux verifies the database regression because embedded PostgreSQL cannot start on this Mac. The delayed-final-answer database regression passes on [the final root-source Linux server shard](https://github.com/paperclipai/paperclip/actions/runs/37868262553/job/113628594152), alongside 1,108 passing tests. The first root Runner shard had one unchanged durable-resume test exceed its 5-second timeout; the identical top-source shard and the isolated exact test passed. One rerun of that failed job and its required aggregate passed without source or test changes. The original failed job log and the single-rerun receipt remain retained. ### October 9 merge verification Current merge head: `5a8fe63512a7166aaef5cf50065a25008aa8b44b`. All current-head checks pass, including `ci / verify` and `ci / e2e`; exact-head Greptile review is 5/5 with no unresolved threads. Current master conflicts are resolved. The user authorized the maintainer override of the code-owner review gate after these checks. The seven retained live core cases remain bound to source `3241a992f2a7703e59e97ed0fd3e5d6405de4401` and its recorded cloud image. ## Risks - The security correction changes the dependency closure and profile identity. Old sessions must reopen on the new profile. Exact identities and credential bindings fail closed. - The runner remains experimental and requires explicit selection. Legacy Pi Local is unchanged. Caller model IDs pass through; the E2E model is a fixture. - Accounting and the broad platform/provider matrix remain deferred. This merge does not publish a release or deploy a service. ## Model Used OpenAI GPT-6 through Codex assisted with reasoning, repository inspection, editing and tool use. The exact serving ID and context window are not exposed in this session. Final live qualification uses Pi 1.0.0 with `openrouter/anthropic/claude-sonnet-4.6` and native-confirmed low thinking. ## 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> |
||
|
DottaandPaperclip
|
2b688a8fe3 |
feat(connections): add verified MCP providers and setup fixes (#15621)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Apps give agents governed access to external tools. > - Several provider MCP servers lacked a supported catalog entry or failed during setup. > - Real browser tests identified specific registration, session, and form defects. > - This pull request adds seven catalog entries and fixes the shared paths used by eleven verified providers. > - Users can connect these providers through the existing Apps flow and control each action. ## Linked Issues or Issue Description **What existing behavior does this improve?** The Apps catalog and remote MCP setup, discovery, and action tester. **Subsystem affected** Shared app definitions, the server tool services, and the Apps UI. **Current behavior** Seven providers lack a catalog entry. Airtable can select an advertised client-metadata flow that fails. Calendly rejects the registration name. Tavily needs an initialized session before a call. Firecrawl exposes invalid defaults for optional nested form objects. HTTPS setup can display a callback that differs from the server callback. **Proposed behavior** Add Calendly, Exa, Firecrawl, GSC Wizard, Parallel Search, Tavily, and Windsor.ai. Preserve Airtable, Linear, Make, and PostHog. Use reviewed provider options through the shared MCP and OAuth paths. Display the callback supplied by the server. Omit untouched optional object inputs. **Reason and benefit** Eleven providers passed bounded reads through the real Paperclip browser action tester. This PR includes that verified set and its required shared fixes. Unfinished providers remain outside this change. AgentMail keeps its existing integration. **Breaking changes** No database migration. Existing OAuth credentials and action policies keep their ownership and access rules. Airtable's reviewed method re-registers a retained client-metadata binding through DCR. Tavily's reviewed method initializes sessions before dispatch. The existing customer, managed, and Vercel OAuth gateway paths now refresh on upstream 401 and return `oauth_refreshed_retry_required` (409), requiring an explicit caller retry. They do not replay the rejected call automatically; the next invocation initializes a fresh credential-scoped session when required. Related catalog work: #15545. This branch preserves current master catalog entries and does not add another Google Workspace integration. Open and closed provider PRs and public MCP issues were searched. No duplicate for this verified set was found. The change extends the shipped Connected Apps roadmap item. ## What Changed - Add seven catalog entries with official provider branding and reviewed permissions. - Update Airtable, Linear, and Make metadata and show Make in Apps. - Add authoritative provider source overrides that use the existing generation and review checks. - Add the reviewed Airtable DCR option and compatible Calendly registration names. - Initialize Tavily sessions before discovery and calls, including retained connections. Keep credential-scoped session caching and single call dispatch. - Use the server's callback URL in the OAuth setup UI. - Omit untouched optional object defaults; keep supplied empty strings, false, zero, and object values intact in the action tester, with strict required-child validation. - Require an explicit retry after OAuth refresh instead of replaying a tools/call with missing session headers. - Record all eleven successful reads, write policies, auth-method limits, and qualification caveats. Omit credentials and private account data. - Find chat connector cards through catalog search in browser tests, so pagination does not hide Slack or other later entries. ## Verification - Real browser qualification: eleven bounded reads passed. Catalog refresh and reload proof are recorded in `doc/connections/verified-mcp-qualification-2026-10-08.md`. - Provider writes and actual agent-adapter sessions were not run. Alternative documented auth methods and expiry refresh remain unqualified. - `pnpm -r typecheck`: passed. - `pnpm build`: passed. - Focused shared/catalog tests: 41 passed. Source override tests: 3 passed. Catalog regeneration fixture suite: 9 passed. Latest form regression suites: 31 passed. Gateway suite: 38 passed. Other focused UI suites passed before these last fixes. - UI token gates and both token sync checks: passed. - The catalog regeneration fixture includes the authoritative provider overrides; its full suite passes. The focused OAuth socket case passed on isolated rerun. - Complete local UI suite: 7,866 passed. CLI suite: 511 passed, 6 skipped. Complete shared suite: 892 passed. - The unchanged AgentMail/ClickUp discovery fallback suite passes all 45 cases. An OpenAI login test passed on isolated rerun. - Local broad database coverage is limited by macOS PostgreSQL shared-memory exhaustion (`shmget: No space left on device`, not disk space). The broad run was interrupted after diagnosis; no host settings or other running services were changed. - CI found that the Slack browser test assumed its catalog card was on the first page. The test now uses catalog search; the Slack case passes locally. Adjacent GitHub and iMessage cases could not start locally because embedded PostgreSQL initialization failed before browser assertions. - Final commit [`febe4520e`](https://github.com/paperclipai/paperclip/commit/febe4520e13d4b3a4121eafc3d22540c2b11379d): all 54 checks passed, with none pending or failed. [CI run](https://github.com/paperclipai/paperclip/actions/runs/37847182065) passed typecheck, build, all general and serialized test suites, all eight browser shards, runner checks, canary dry run, and the aggregate verification gate. - Greptile reviewed that exact final commit at 2026-10-08 21:33 UTC and returned 5/5 with no outstanding findings or unresolved threads. - PR UI preview against the existing local test server: Calendly catalog/setup observed; Firecrawl read passed after expanding More options with nested optional inputs untouched. This retest proves frontend behavior, not the revised OAuth backend against a live provider. <details> <summary>Browser evidence</summary>    </details> ## Risks - Provider registration and consent behavior can change. Airtable's DCR option is explicit and keeps the existing issuer, resource, redirect, and PKCE checks. - Tavily uses initialized sessions without automatic call retries. After a successful OAuth refresh following 401, callers now receive a retry-required result. A later explicit retry can still require reauthorization if the provider rejects the refreshed token. Provider writes are not live-qualified. - Optional object cleanup affects the shared action tester. Regression tests cover absent objects, required children, defaults, and populated values. - GSC Wizard's underlying Google data scopes and Google flow completion were not independently verified. Its account reported paid/trial metadata of unknown origin. No purchase was performed. - No database migration, new AgentMail integration, or change to existing action grants is included. ## Model Used OpenAI GPT-6 through Codex assisted with implementation, research, tool use, and code execution. The root backend model ID and context window are not exposed in this session. The cheaper subagents used OpenAI `gpt-6-luna`. No model context size is inferred. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [ ] I have run tests locally and they pass — targeted checks and complete UI/CLI/shared suites passed; the broad local database run was blocked by the macOS PostgreSQL startup limitation documented above. The full database/workspace suite passed in CI. - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing> |
||
|
DottaandPaperclip
|
428b617fc9 |
test(evals): qualify native question resume paths (#15616)
## Thinking Path > - Paperclip lets agents pause tasks for human answers and continue the work. > - Native questions can yield a run or pause inside the provider's running turn. > - Those paths have different run identities and different forms. > - The documentation-placement test requires a semantic three-turn journey. > - A valid provider question therefore needs separate behavioral qualification. > - This pull request adds an opt-in two-answer journey with exact source and resume checks. > - Qualification exposed a Vite startup crash in idle-handler traversal, so the branch also distinguishes Connect mount paths from Express Route objects. ## Linked Issues or Issue Description **What existing behavior does this improve?** Product E2E evaluation of native task questions and answer delivery. **Current behavior** The semantic documentation case rejects the provider adapter's optional Other field before answering. Its three-run expectation also cannot prove a provider question that resumes within the same run. **Proposed behavior** Keep that semantic test intact. Add a separate opt-in case that classifies each recorded question by authoritative identities. Accept the optional Other field only for a verified provider question. Require both user answers, the correct continuation, and one saved final document. Related: #15564 added strict lifecycle checks. #15522 introduced idle-request tracking; this PR corrects its Connect/Vite compatibility after reproducing the startup crash. #14591 changes ACP question drafts and provider support; this PR has no overlapping files with that change. ## What Changed - Add the explicit-only `question-resume` suite for native Codex and ACPX Claude. Reuse the existing neutral choice-then-text task request. - Bind each question to its company, task, agent and run. Require an applied semantic tool receipt or the exact provider request identity. - Require a provider answer to continue the same run. Require a semantic answer to start one new run with the matching interaction and source-run wake fields. - Preserve question forms and both real board answers through the final checkpoint. Reject missing inputs, duplicate answers, extra runs and substituted identities. - Keep the existing lifecycle, output, task ownership and budget checks. Limit the new case to one attempt and one to three runs. - Add mutation calibrations and document the separate qualification claims. Keep production guidance, scheduling, provider code and the historical semantic case unchanged. - Fix startup with Vite middleware: treat Connect string mount paths separately from Express Route objects when traversing idle-request handlers. A real-Vite regression verifies startup and retained async work through an idle hold. ## Verification - 81 focused continuation, question and calibration tests passed before review. After the reference-preservation correction, all 50 question/resume tests pass, including two new negative cases that failed against the previous grader. - Final eval support suite passes: 1,921 Vitest tests and 128 Node tests, with one intentional skip. - Eval and workspace typechecks pass. Workspace build passes. - Catalog discovery finds only the two declared opt-in cells. Existing continuation remains 23 cells; default paid scope is unchanged. - Original [campaign 37831726391](https://github.com/paperclipai/paperclip/actions/runs/37831726391), source `1ac4b2873466896ff2892f49be82904927b6c57d`, failed during server startup before any test or provider run. Its original `transient_infrastructure` result and `cleanup: not_started` are preserved. Local reproduction identifies the Connect string route traversal crash; the question grader was never reached. - Setup-corrected [campaign 37833872898](https://github.com/paperclipai/paperclip/actions/runs/37833872898) measures source `9781a772389d41421df55759004676e1b905e512` with trusted workflow `8e59efc50b162126f33816841e06509634eba65c`. The workflow bytes are unchanged from the first dispatch. Same single selected native Claude cell, one attempt, at most three runs, ten-minute cell deadline, and 1,000-cent company/agent hard stops. Original result **PASS**, 24/24 checks and cleanup pass. Exactly three successful native Claude runs: two applied Paperclip `request_human_input` questions and one finishing run. Both real board answers persist, exact interaction/source-run response wakes match, one revision-1 task document contains Afternoon and the supplied reference, and final task state is done with no active lock, retry, recovery, monitor, pending interaction or child task. No model retry. - Current review head `3c08cb7d26e7f9ac16469eeb07d1f31d828ec02e` differs from the measured source only in the question/resume grader and its tests (11 insertions, 3 deletions). The saved document must contain the complete submitted reference, including its prefix and punctuation. Separate provider-free replay of the retained successful campaign passes all 24 continuation/lifecycle checks under this stricter grader. The original result and its measured source remain unchanged; no new provider run was made. - Observed paths were **semantic → semantic**. The provider built-in question/optional Other path was not exercised by this new live attempt. Its form acceptance has retained-original calibration; same-run answer/resume has deterministic positive/negative calibration. This neutral-task pass alone does not qualify the provider path; the subsequent explicit bridge trial below is separate evidence. Neither trial regrades the old Claude failure or establishes a causal behavior/performance comparison. - Subsequent explicit provider-path [campaign 37841107684](https://github.com/paperclipai/paperclip/actions/runs/37841107684) measures the final PR source `3c08cb7d26e7f9ac16469eeb07d1f31d828ec02e`, using trusted workflow `2a5f65c9ae501b49b2a38ce7edd04209b806c9d0`. Exact cell: `continuation.runner-acpx-claude.local.provider-question-bridge`, Claude `claude-sonnet-5`, suite fingerprint `fc77203bf85fd99b06ebc53cd52982186c0ae0dc369fcc38a9ec3c737e9a31e5`. **Original PASS, 15/15 checks, cleanup passed, one actual provider run and zero eval rerolls.** The built-in question produced one choice plus its optional Other companion. The browser selected the requested reference, left Other blank, and submitted. Exact runtime request/response IDs and the selected option match the saved interaction; the same paused native run created one revision-1 document and finished Done with no pending interaction, lock, retry, recovery, monitor or child task. Independent evidence and runtime-receipt audits pass; marked initial/final screenshots were visually checked. [Original public report](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-37841107684-1/index.html). - This separate provider-directed trial qualifies one choice-answer bridge and traversal of an empty optional Other field. It does not establish natural tool selection, a typed Other answer, two consecutive built-in questions, free-text-only input, restart recovery or general reliability. No production, prompt or grader change was made for this dispatch. The old failure and the separate neutral semantic-path result retain their original grades. - Preserve within-run friction: one `write_task_document` input-schema rejection and two HTTP 409 “Document does not exist yet” responses preceded a successful `write_document` call. These are three unsuccessful tool calls inside the same run, not three extra provider runs; no flawless document-tool behavior is claimed. Billing reports token usage but remains unpriced/incomplete, so actual charges are unknown and local/hosted runtime is unmetered. Both company and agent hard stops were 1,000 cents, with one attempt, one selected cell, concurrency one and a ten-minute cell deadline. - Billing records all three model runs with token usage, but no priced dollar receipt (`unpriced`, `complete: false`). Actual charges are unknown; local/hosted runtime is unmetered. Numeric zero reported cost does not mean free. - Startup repair: real-Vite reproduction passes; 35 targeted idle-tracking tests pass, 34 database-dependent checks skip because embedded PostgreSQL is unavailable locally. Workspace typecheck and build pass again after the repair. - Full local repository database tests were not repeated because embedded PostgreSQL was unavailable in the preceding workspace verification. Full Linux CI now passes on the final review head. - Final-head [CI run 37837804284](https://github.com/paperclipai/paperclip/actions/runs/37837804284) passes. Complete current-head audit: 53 successful check-runs, two intentional Storybook skips, and separate Snyk success. The ready transition’s contributor and security checks also pass (security scan: no findings). [Fresh review](https://github.com/paperclipai/paperclip/pull/15616#issuecomment-6068092601) is 5/5 on `3c08cb7d26e7f9ac16469eeb07d1f31d828ec02e`; zero unresolved threads and no merge conflicts. ## Risks This is a new behavioral definition. The neutral two-question trial records semantic-tool use; the separate provider-directed trial records one built-in question. They do not establish consistent tool selection, documentation placement, default hiring, remote environments, crash recovery or general reliability. The separate explicit bridge trial covers one provider choice, an empty optional Other companion and same-run completion. Typed Other, two consecutive built-in questions and free-text-only provider input remain unqualified. The observed document-tool schema rejection and two 409 responses are retained as a separate follow-up, without attributing their cause. The historical case and its original grades remain intact. The reference question must still be text-only; the oracle does not turn an arbitrary extra question into an optional companion. Missing or unfamiliar identity evidence fails closed. The only production change distinguishes Connect string mount paths from Express route objects during idle-handler traversal. Unknown route objects still fail closed. No API, schema, migration or workflow change is included. ## Model Used OpenAI Codex, GPT-6-based, with tool use and code execution. The exact serving model ID and context-window size are not exposed in this session. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [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> |
||
|
Devin FoleyandPaperclip
|
0ac194450a |
fix: make Copilot provider-pack wrappers portable (#15586)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Container images include a movable provider pack for agent execution. > - pnpm executable wrappers can contain the temporary build directory. > - New optional Copilot packages add wrappers that the build does not replace. > - This pull request gives those installed wrappers relative executable paths. > - Image publication can finish while the existing path check remains enforced. ## Linked Issues or Issue Description Refs #15572 and #15560. The small portability loop comes from cryppadotta's larger Copilot runtime PR #15560. This separate fix repairs image publication without waiting for that feature's qualification and runtime changes. That PR can remove its duplicate loop after this lands. **What happened?** The standard Docker build stops with `Provider pack shim copilot-linux-x64 retains its temporary build path`. The failure occurred before and after #15522. See [the failed master build](https://github.com/paperclipai/paperclip/actions/runs/37802065316). **Expected behavior** Installed native Copilot wrappers resolve their pinned executable after the provider pack moves. Optional packages that are absent do not gain a command. The builder still rejects wrappers with temporary paths. **Steps to reproduce** 1. Run the provider-pack build from the affected master revision on Linux x64. 2. Let `pnpm deploy --prod` install the optional Copilot package. 3. The wrapper scan rejects its temporary `NODE_PATH`. **Paperclip version or commit** Master `3367b75ccce34d02f355cda1f1ed3fe0b34cf93d`. **Deployment mode** Docker and provider-pack builds. ## What Changed - Replace installed Copilot platform wrappers with relative native executable launchers. - Move the existing executable wrapper writer into an importable helper. Retain the same launch behavior for Node, Claude and OpenCode. - Test relocation, argument handling, exit status, absent optional packages and missing executable packages. Register the tests in the existing Runner test preparation command. - Hash the helper in Daytona image identity and prove that helper changes invalidate the image cache. - Document the packaging rule. Keep dependencies, provider qualification and the final temporary-path check unchanged. ## Verification - 17 Node packaging tests passed across the new wrapper tests, provider-pack release tests and candidate selection tests. - Six existing bundled remote-provider-pack tests passed using the Runner Vitest configuration. - Nine Daytona image identity tests and Runner E2E typecheck passed after the cache-input correction. - `pnpm -r typecheck`: passed. - `pnpm build`: passed. - Real `pnpm deploy --prod` reproduction on macOS ARM64: the original Copilot wrapper contained the temporary path. After the rewrite and directory relocation, the actual executable returned Copilot CLI 1.0.88 with exit code zero using only `/usr/bin:/bin` in `PATH`. - Syntax checks, `git diff --check` and the pre-push secret scan passed. - The full local `pnpm test:run` reproduced the same five skill/connector fixture failures observed earlier in this workspace. It was stopped after current-head clean-checkout CI passed; later local phases were not run. This local run is not claimed as passing. Focused packaging tests, workspace typecheck/build and all hosted CI passed. - [Hosted Docker verification passed](https://github.com/paperclipai/paperclip/actions/runs/37804902678): Linux AMD64 and ARM64 image builds, multi-architecture publication and the process-reaping smoke check. This run tested `779d94989c54d9abbeba0838194c951186af66a6`; the only later changes are Daytona cache identity and its regression test. Provider-pack build code is identical. Local Docker did not respond within the bounded probe. - Current head `db2c19e270b8d5a7bab5db39d3de0e4761cf57c3`: 54 successful checks, two conditional skips, no failures and no merge conflicts. Apex is 5/5 with no unresolved comments. ## Risks The helper uses each installed package's exported executable. An installed wrapper with a missing package still fails the build. This change does not execute Copilot during image construction, alter dependency pins, change runtime admission or weaken the temporary-path check. ## Model Used OpenAI GPT-6 via Codex, with reasoning, repository inspection, tool use and code execution. The exact serving model identifier and context window 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 and contains no internal Paperclip ticket id or instance-derived details - [x] I have run focused tests locally and they pass; the full local-suite limitation is documented above - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing> |
||
|
|
941a3fa991 |
Pin Copilot native dependencies with the maintained lockfile refresh (#15572)
Pin the three optional GitHub Copilot 1.0.88 native packages for Runner and server using the maintained lockfile workflow. Synchronize the package contract and bound initial render readiness in the deliberately throttled browser fixture. Current-head CI and focused checks pass. Co-Authored-By: Dotta <cryppadotta@users.noreply.github.com> Co-Authored-By: lockfile-bot <lockfile-bot@users.noreply.github.com> Co-Authored-By: Paperclip <noreply@paperclip.ing> |
||
|
DottaandPaperclip
|
24a15c5afa |
test(evals): verify durable waiting across continuation checkpoints (#15564)
## Thinking Path > - Paperclip manages agents and durable tasks across provider runs. > - Human questions must preserve task ownership and stop work until a real answer arrives. > - The continuation eval checks the final work, but its lifecycle oracle misses several broken waiting states. > - A correct final answer can hide a stale execution lock or a lost intermediate answer receipt. > - This pull request checks each wait and retains every question and run identity. > - A source audit records which waiting operations belong to native runtimes and which still require legacy API calls. ## Linked Issues or Issue Description **What existing behavior does this improve?** The existing Product E2E continuation oracle for human question and approval journeys. **Current behavior** A pending interaction can pass the waiting check even when its task has the wrong status, a stale lock, or a retry. Only the first pending question and first run receipts are checked at the final checkpoint. **Proposed behavior** Require a healthy wait on the same task and assignee. Preserve all intermediate run receipts and every pending question's answered identity. Allow a paused native provider question only when its pending runtime request identifies the running native run and execution lock. Related: #15548 and #15554 cover earlier bookkeeping slices. #15544 changes production continuation summaries; this PR changes the eval oracle and does not overlap that fix. ## What Changed - Check waiting state, execution ownership, and all answer/run identities in the existing lifecycle oracle. - Add negative calibrations for broken records and positive coverage for both semantic waits and paused provider questions. - Retain task activity at each checkpoint for inspection of successful persisted mutations. - Verify 1,000-cent company and agent budget limits before continuation work. Disable automatic cell rerolls. - Document runtime ownership, existing coverage, and the remaining instruction decision. Keep production instructions unchanged. ## Verification - `pnpm test:e2e:runner:unit`: 1,867 Vitest tests pass, one skips; 128 Node tests pass. - `pnpm test:e2e:runner:typecheck`: passes. - `pnpm -r typecheck`: passes. - `pnpm build`: passes. - Negative calibration: 27 added cases fail against the prior oracle and pass with these checks. - Four existing local continuation cells are selected for a separate bounded live canary. Live results are pending; no behavioral pass is claimed here. - The full local `pnpm test:run` suite was not repeated because embedded PostgreSQL was unavailable in the preceding workspace verification. Required Linux PR CI must pass before readiness. ## Risks The stronger oracle can expose existing product or fixture defects. A paused provider question and a terminal semantic wait have distinct valid states. The four-cell canary does not qualify approval/review, dependency unblock, crash races, remote execution, or general task quality. Task activity records successful persisted writes, not failed API attempts; repeated progress comments are not automatically defects. Historical eval grades remain unchanged. No production scheduling, prompt, tool, schema or migration changes. ## Model Used OpenAI Codex, GPT-6-based, with tool use and code execution. The exact serving model ID and context-window size are not exposed in this session. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [ ] All Paperclip CI gates are green - [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing> |
||
|
DottaandPaperclip
|
2f0c485dec |
fix(skills): ship the completion helper with the installed skill (#15554)
## Thinking Path > - Paperclip manages work for AI agents. > - Legacy agents use the Paperclip skill to save task status and comments. > - The skill names a script relative to the task workspace. > - That script exists only in the Paperclip source repository. > - Agents in other workspaces can hit a missing command or search for it. > - This PR ships the helper inside the skill and uses the installed skill path. > - The repository command remains available through a forwarding wrapper. ## Linked Issues or Issue Description Fixes #9527. Refs #15548 for the preceding runtime checkout guidance. Related: #6052 addresses LF line endings for the repository helper; this change addresses helper delivery and path resolution. ## What Changed - Bundle the existing issue update helper with the Paperclip skill. Preserve its HTTP checks, echoed-status check and two-attempt limit. - Resolve the command from the installed skill directory. Use a verified PATCH when that path is unavailable, without searching the filesystem. - Keep the repository command as a wrapper that works from any directory. - Test shell execution and exact status/comment payloads through both provider skill-home layouts, including paths with spaces. - Add helper sources and existing verification tests to stock-harness admission. Record an absent historical helper explicitly. Add the missing declaration for the admission fingerprint export. ## Verification - Complete directly affected source suites: 30 tests pass. They cover skill delivery, preserved multiline comments and links, authentication headers, empty responses, mismatched status, transient retries and definitive rejections. - Product E2E typecheck passes. Support suites: 1,835 Vitest tests pass, one is skipped; 128 Node tests pass. - Full local build and workspace typecheck pass. - Full local repository tests are not claimed as passed. Embedded PostgreSQL was unavailable in this worktree during the preceding task; Linux CI will run the repository gates. - The authorized matched Codex/Claude comparison is pending. It uses the existing assigned-skill case and original oracle, one initial attempt per profile and variant. - CI and a fresh Greptile review are pending. Keep this PR in draft until readiness gates complete. ## Risks - Correct path resolution depends on the harness supplying the installed skill path. The instructions use verified PATCH when that path is unavailable. - The helper still requires Bash, curl and jq. Its existing retry and response-verification behavior is unchanged. - Tests use the shared skill-directory symlink mechanism and an HTTP fixture. Real provider completion behavior still requires the bounded live comparison. - This fix does not redesign native completion, legacy recovery or ambiguous transport handling. ## Model Used OpenAI Codex, GPT-6 family. The exact model build and context window are not exposed in this session. Used 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 - [ ] All Paperclip CI gates are green - [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing> |
||
|
DottaandPaperclip
|
71cd0a2621 |
fix(skills): honor the current run harness checkout (#15548)
## Thinking Path > - Paperclip manages work for AI agents. > - The runtime claims eligible assigned tasks before it starts an agent. > - The wake tells the agent when the runtime already holds that claim. > - The legacy skill still requires another checkout in every case. > - This PR makes the skill honor the current task and run claim. > - Manual checkout and server ownership checks remain in place for other cases. ## Linked Issues or Issue Description **Where is the issue?** `skills/paperclip/SKILL.md`, in the scoped wake procedure and Step 5. **What's wrong?** The wake can say that the harness already checked out the issue. The skill still tells the agent that it must call checkout. These instructions conflict. **Suggested fix** Skip the second checkout only when the runtime wake explicitly confirms the claim for this issue and run. Retain manual checkout when that statement is absent or the agent selects another task. Refs #14948 for the existing shared prompt reduction. ## What Changed - Honor the explicit runtime claim in the scoped wake procedure and Step 5. - Keep context reads, status writes, deliverable handling and conflict rules. - Add checks for normal and resumed wake text and excluded automatic claims. - Retain successful checkout HTTP activity for legacy stock-task evals. Bind each receipt to the exact company, task, agent and run. Keep this observation separate from the original task grades. ## Verification - Checkout observation calibration: nine tests pass. - Focused skill, wake and database ownership tests: in progress. - Full repository build, typecheck and tests: in progress. - Planned live comparison: the existing assigned-skill document case on legacy Codex and Claude. One attempt per variant and profile. No automatic retries. The baseline and candidate share the observation code and task oracle. - Live results are pending. This draft does not claim behavioral qualification. ## Risks - Agents may misread prompt guidance. The API still enforces ownership; the text grants no new authority. - The exception is specific to the current issue and run. It does not remove ordinary legacy completion writes or authorize another task. - Activity measures successful checkout HTTP calls. Failed attempts require separate run-log inspection. Missing or mismatched observations cannot count as zero calls. - One trial per profile cannot establish general reliability, speed or cost trends. ## Model Used OpenAI Codex, GPT-6 family. The exact model build and context window are not exposed in this session. Used 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 - [ ] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [ ] All Paperclip CI gates are green - [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing> |
||
|
DottaandPaperclip
|
d66acb7ac1 |
feat: automate Slack bot app setup and installation (#15413)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Chat connectors give each agent a customer-owned bot and task-backed conversations. > - Manual Slack setup requires app creation and copying durable credentials. > - Operators need a shorter setup that an assisting agent can use safely. > - This pull request creates the app through Slack's Manifest API and installs it through OAuth. > - Durable registration state supports recovery without creating another app. > - A four-screen wizard, automatic avatar upload, and OAuth account linking reduce setup work. > - Connector settings and per-turn tool guidance support daily use after installation. ## Linked Issues or Issue Description **Subsystem affected** Native Slack bot setup, company secret storage, chat connector management, and agent tool guidance. **Problem or motivation** New Slack bots require manual app creation and copying a signing secret and bot token. Interrupted setup can create duplicate apps. The setup and management screens contain unnecessary controls. Agents also need guidance for native questions, files, thread replies, and governed Slack actions. **Proposed solution** Use a temporary app-configuration access token to create a customer-owned app. Save durable secrets in the vault. Bind OAuth to the initiating actor, company, endpoint, registration revision, scopes, and configured origins. Preserve manual and existing-app recovery. Link the installing user's account, send a welcome DM, and advance from saved server evidence. Keep request-URL recovery instructions available if automatic connection detection waits. **Alternatives considered** The Slack CLI adds installation requirements. Socket Mode changes transport. A shared Paperclip-owned app changes app ownership. These alternatives are outside this change. **Roadmap alignment** This extends existing chat connectors and secrets capabilities. Related public work: #14037 and #13954 cover Slack MCP prerequisites and user OAuth. No duplicate bot-registration PR was found. ## What Changed - Share one reviewed manifest builder between automatic registration and manual setup. - Add replay-safe migration 0318 and company-bound registration state with vault references and uncertain-creation recovery. - Add registration, installation, callback, and resume APIs with short-lived, single-use OAuth state. - Save installation credentials before downstream checks and preserve bot identity constraints. - Reduce automatic setup to four screens. Keep advanced app details, manual recovery, and existing-app setup. - Upload the agent avatar with the Paperclip dark background. Link the OAuth installer's account and send setup DMs. - Show agent and connector-owner avatars. Simplify settings, access, and conversation screens. - Discover joined Slack channels and enable them by default. Start a task from a bare mention and admit same-thread follow-ups. - Refresh Slack tool guidance each turn. Add native-form, file, approval, and delivery regressions plus manual model probe definitions and sanitized acceptance records. - Update deployment/database docs, OpenAPI, redaction, removal cleanup, production Storybook stories, and provider browser tests. - Merge current master and move the registration migration after its latest migration without rewriting published commits. The completed Slack success view intentionally has a single centered **Done** action and no **Save & exit**, as explicitly requested by the product owner. `DESIGN.md` records this exception; unfinished setup steps retain the aligned wizard footer. ## Verification - Passed after the master merge: repository typecheck, full build, Storybook build, design-token gates, module-boundary gates, and migration generation. - Passed: all 352 focused Slack deterministic tests and all 14 affected provider browser tests. Browser tests use controlled provider fixtures and a separate throwaway instance. - Passed on current head `c5d01e0e2`: the complete GitHub test matrix (general server, chat, all workspaces, serialized server, and Runner), all eight browser shards, typecheck/release registry, build, canary dry run, security checks, and policy gates. There are 52 passing checks and no pending or failing checks. - Greptile completed on the exact current head with 5/5 and no actionable findings or open review threads. - Local repair verification passed 93 focused tests, including same-app reinstall after revocation and rejection of consent started before revocation, the AgentMail browser journey, and repository typecheck. Local build and Storybook build also passed. The redundant local full-suite rerun was stopped after the complete current-head CI matrix passed. - Real Slack setup and agent replies were exercised in the authorized isolated test drive during the setup iteration. - The ten additional model probes were attempted with legacy `codex_local`, `gpt-5.6-sol`: five passed, two failed, and three were partly verified. Native runtime is not qualified. See `server/src/services/connectors/slack/evals/2026-10-08-acceptance.md` for evidence and limits. - Passing model probes cover native forms, downloaded file bytes, bare mentions with thread replies, explicit posts/reactions, and saved approval denial. - The controlled uncertain-write probe found wrong delivery-check IDs. The canvas fallback attempt used an invented tool name. Search pagination/native search, a private-source denied-tool receipt, and distinct board/webhook origins remain unqualified. Reviewer path: enable Chat connectors, start Slack chat setup, select an agent, enter an app-configuration access token, and approve Slack installation. Send a message to the bot and confirm that setup advances to success. Inspect settings and allowed channels. See `doc/connections/SLACK-AUTOMATIC-SETUP.md` for deployment and recovery. ## Risks - Slack app creation has no provider idempotency guarantee. A timeout after dispatch stays uncertain until the operator checks Slack. - OAuth needs a stable public HTTPS board origin. Webhook ingress may use a separate configured HTTPS origin. Workspace policy can delay installation. - Migration 0318 can replay safely on instances that applied the earlier development migration. - OAuth installation now links the installer to the initiating Paperclip user. Identity checks and company access rules still apply. - Joined channels now enable bot responses by default. Linked-user authorization and per-action approval rules still apply. - Model behavior has the documented delivery-check and canvas fallback failures. A passing CI run does not establish that every model probe passed. - Removing the connection does not delete the customer's Slack app. No new first-party telemetry is added. ## Model Used OpenAI Codex, GPT-6 family, with reasoning, repository tools, code execution, and browser verification. The runtime does not expose a more specific authoring model ID or context-window size. The live bot probes used OpenAI `gpt-5.6-sol` through `codex_local` in legacy mode. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing> |
||
|
DottaandPaperclip
|
b5342febe5 |
fix(runner): require current-turn completion after connection continuations (#15514)
## Thinking Path > - Paperclip manages agents, tasks, permissions, and execution budgets. > - Native tasks can resume after a connection decision in the same provider conversation. > - Each turn still needs an accepted completion report. > - Compact continuation messages did not explain that reports from earlier turns cannot finish the new turn. > - The connection evaluator could also grade before the final reply was stored or reject valid unavailable-access wording. > - This PR clarifies the current-turn report requirement and fixes those observation boundaries. > - The original connection instructions and strict native completion gate stay in place. ## Linked Issues or Issue Description Refs #15489. The reduction remains draft while this separate repair is qualified. Refs #15471 for the earlier connection continuation work. ## What Changed - Add a current-turn completion reminder to compact continuation inputs. - Keep final prose insufficient for completion. Preserve permissions and retry policy. - Wait for the final successful task run's saved, attributed decline reply within the existing deadline. - Use one bounded explanation matcher for both decline checks. - Wait for a recorded tool-action rejection to dispatch its bound continuation, with strict company, task, agent and source-run checks. - Retain the exact grading input before later API refreshes. - Add failure and delay regressions and update the Runner and evaluator docs. ## Verification The fresh comparison has **15/15 original passes on each variant**: 15 unchanged pass pairs, zero new failures, and no pending pair. There are 30 case attempts and **65 actual agent runs** (baseline 33; candidate 32). All runs succeeded. All 30 cleanups passed. No model attempt was retried. | Profile | Baseline | Candidate | | --- | --- | --- | | Native Codex `gpt-5.6-sol` | 5/5 | 5/5 | | ACPX Claude `claude-sonnet-5` | 5/5 | 5/5 | | OpenCode `openrouter/deepseek/deepseek-v4-flash-0731` | 5/5 | 5/5 | Each profile covers service approval, service decline, connection decline, provider decline, and selection of the second provider. The saved replies, approved briefings, decisions, fixture observations, final task states, and native completion records were inspected. All 18 saved decline-grade snapshots match their original captured inputs and checks. Result, API snapshot, and final ledger run sets agree. - [Candidate campaign](https://github.com/paperclipai/paperclip/actions/runs/37711658378) · [public candidate report](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-37711658378-1/index.html) - [Baseline campaign](https://github.com/paperclipai/paperclip/actions/runs/37711675579) · [public baseline report](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-37711675579-1/index.html) - Candidate source: `79905343bba280d462765faad19a26e7f179259e`. Baseline source: `7c5e120158f1385a1fc5f20be41f66c58a605534`. Both use master context `fc6304dfe5f2e446e09bd052a7b45f51e930f250`. The trusted workflow source is separately frozen at `dd777f4b7343305c4e6f44c422f44a1d78e12e4f`. - Both variants use the same evaluator, fixtures, models, permissions, 720-second cell deadline, and 1,000-cent company and agent hard stops. The only production difference is the compact continuation reminder. - Suite hash: `aee30b74b4d38ada08777798db0932fbc64e368bb427d29caa8cfd86c7f59747`. Definition hash: `ea9e17f54fe0af1acbb2337ddfab8a7e92db8488bd0f59510a63095ca0229b60`. - Provider-free transport capture: startup/resume input stays at 55,726 bytes. Compact continuation input grows from 53,334 to 53,535 bytes. The 42-tool catalog stays unchanged. These are Paperclip input bytes, not complete vendor prompt tokens. - Focused evaluator tests: 31 pass. Native contract, transport delivery, and session tests: 194 pass. Evaluator support: 1,819 TypeScript tests and 128 Node tests pass, with one intentional skip. - Full build, workspace typecheck, and evaluator typecheck pass. Current-head CI passes all required gates. The current rollup has 51 successful check runs, two intentional Storybook skips, and a successful Snyk status. Review is 5/5 with zero unresolved threads. - CI attempt 1 had one initial runtime-fixture health timeout. The exact test and its full 164-test file pass locally. One CI shard retry passed. The original CI failure, its dependent verify failure, and the retry remain visible in [CI history](https://github.com/paperclipai/paperclip/actions/runs/37711235060). - The broad local `pnpm test:run` attempt was interrupted after about 49 minutes (exit 130). It recorded one failure in the unchanged Zep memory-connector disabled-setting test. That test and the full 388-test tool-access file pass in separate local checks; current-head CI also passes. The local cause is not established, and this broad local attempt is **not** claimed as passing. Three earlier local failures also pass in their isolated checks; their original logs remain retained. - The first two setup admissions were cancelled before provider jobs to include the review correction. They made no provider calls. The completed campaigns above are the first and only model attempts for these corrected variants. Cost evidence stays separate from behavior. Original result summaries report only OpenCode amounts: baseline $0.039192096 and candidate $0.063221620. Final run ledgers also retain estimates for Claude (baseline $1.232439000; candidate $1.333611200) and Codex (baseline $2.340324400; candidate $2.129335600). These estimates do not replace the original summaries. Local and GitHub runtime are unmetered here. Invoices are unknown. This is not a cheaper or faster claim. ## Risks - A single matched trial cannot prove general equivalence or causation. The reminder is an instruction change, not a new completion enforcement rule. - Candidate OpenCode service-decline finished within one continuous run; its baseline used two. That pair passed the task outcome, but it does not qualify the reminder on a resumed decline turn. No extra paid run was used to replace it. - The text matcher is bounded evidence of an explanation. It does not prove reasoning or consumption of feedback. Bounded stdout excerpts do not prove that every extra attempted tool call is absent. - Missing saved replies or continuations still fail at the original deadline. Failed native completion remains a failure even when final prose is correct. - The unresolved local-suite discrepancy above remains a validation limit. Full remote CI and both focused local reproductions pass. - The original connection instructions stay in place. These results do not qualify the reduction in #15489. Its original 11/15 versus 12/15 grades and two new failing pairs remain unchanged. ## Model Used OpenAI Codex, based on GPT-6. The exact deployment ID and context window are not exposed in this session. Capabilities used: reasoning, repository editing, code execution, test inspection and eval analysis. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either linked existing issues or described the issue in-PR - [x] I have not referenced internal/instance-local Paperclip issues or links - [x] My branch name describes the change and contains no internal Paperclip ticket id or instance-derived details - [x] I have run the focused local tests listed above and they pass; the interrupted broad local run is disclosed above - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing> |
||
|
DottaandPaperclip
|
ae6f95ed7a |
feat: add personal primary agents (#15470)
Add a personal primary agent per company and user. Initialize it from the first human-created agent, expose profile-only switching with confirmation, and use it after recent choices for task and Chat defaults. Persist authenticated preferences, preserve lifecycle and membership rules, keep selections out of shared audit events, and document the API contract. Include the reviewed Storybook surfaces and regression coverage for concurrent choices, onboarding, cross-device updates, and browser journeys. Co-Authored-By: Paperclip <noreply@paperclip.ing> |
||
|
|
ceabc3bc88 |
fix(e2e): wait on the server's own deferral signal in the signoff wakeup helper (#15345)
## Thinking Path > - Paperclip coordinates work for AI agents through server-managed tasks and heartbeats > - Signoff policy tests exercise stage transitions that wake the next participant > - A stage transition can defer a wake while the previous run still holds the issue execution lock > - The test helper used a fixed wait and could fail before the server released that lock > - This pull request waits on the server deferral signal and verifies the returned run identity > - The benefit is a stable test with clear failure details and no repeated wake request ## Linked Issues or Issue Description **What happened?** The signoff policy end-to-end spec failed intermittently with `No issue-bound heartbeat run became available for agent <id>`. The server had deferred the wake while another run held the issue execution lock. **Expected behavior** The test helper waits for the named blocking run to finish, then reads and verifies the new run for the requested agent and issue. **Steps to reproduce** 1. Run `npx playwright test --config tests/e2e/playwright.config.ts tests/e2e/signoff-policy.spec.ts`. 2. Exercise a signoff stage transition while the previous stage run still holds the issue execution lock. 3. Confirm that the helper waits on the server deferral signal and returns only a matching run. This change relates to [PR #11299](https://github.com/paperclipai/paperclip/pull/11299), which also touches the signoff policy end-to-end spec. ## What Changed - Call the wakeup endpoint that reports the server deferral reason. - Wait for the named blocking run instead of using a fixed delay. - Verify that each returned run belongs to the requested agent and issue. - Bound read and wait loops and report the last server signal and lock fields on failure. - Keep one wakeup request per helper call. ## Verification - `npx playwright test --config tests/e2e/playwright.config.ts tests/e2e/signoff-policy.spec.ts` passed locally. - All five signoff policy cases passed locally. - The spec keeps all 60 assertions. - The diff contains only `tests/e2e/signoff-policy.spec.ts`. - The full CI end-to-end shards must pass before merge. ## Risks - The helper now depends on the wakeup endpoint's deferral fields. - A server change to those fields can fail the test with a named diagnostic. - The change affects end-to-end test behavior only. ## Model Used OpenAI GPT-5 Codex, exact runtime model `gpt-5-codex`, with tool use and code review assistance. The runtime does not expose a separate context-window value. ## 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: nickyleach <331803+nickyleach@users.noreply.github.com> Co-authored-by: Paperclip <noreply@paperclip.ing> |
||
|
DottaandPaperclip
|
1640c5b6ab |
feat(ui): render HTML artifacts in a secure sandbox (#15447)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Agents deliver reports as task attachments and workspace files. > - The board already renders Markdown, but it shows HTML reports as source or rejects their preview. > - Reports can need inline scripts to build charts and tables. > - Artifact scripts must not read board cookies, storage, or the parent page. > - This pull request adds an opaque-origin HTML preview and view controls beside Download. > - Users can explore a report, inspect its source, and download the original file. ## Linked Issues or Issue Description **What existing behavior does this improve?** The task attachment panel and workspace file viewers. **Subsystem affected** ui/ and the server workspace file preview service. **Current behavior** HTML attachments show source text. Workspace HTML files cannot be previewed. **Proposed behavior** Render self-contained HTML reports in a sandboxed iframe. Place eye and code controls beside Download. Preserve the original file for raw view and download. **Reason and benefit** Users can read and filter agent reports in Paperclip without giving artifact scripts access to the board session. **Breaking changes** HTML previews now open rendered. Scripts and styles must be embedded in the report. Remote resources, API requests, forms, popups, and host navigation are blocked. Workspace HTML content uses the existing bounded UTF-8 JSON response. **Additional context** Related closed proposals: #3293 and #4857. This change uses the current attachment and workspace viewers and adds no report-serving endpoint. The Artifacts and Work Products roadmap item is complete; this improves its existing preview behavior. ## What Changed - Add a shared HTML iframe renderer with `sandbox="allow-scripts"` and no `allow-same-origin`. - Install a restrictive CSP before artifact markup. Keep inline report scripts and styles. - Add shared rendered/raw icon controls beside Download in the attachment panel, workspace panel, and file sheet. - Return workspace HTML as bounded text inside JSON. Keep download and path-access protections. - Add Storybooks for reports, security probes, workspace viewers, a task journey, and mobile layouts. - Document the security boundary and browser test command. ## Verification - `pnpm -r typecheck` and `pnpm build` pass. - Token gates and the static Storybook build pass. - Four browser tests pass. They cover report filters, raw mode, task entry, workspace viewers, cookies, storage, host DOM, resource requests, forms, popups, and host navigation. - The focused UI suite passes 26 tests. The file-resource server suite passes 36 tests. - Local full-stack acceptance passes with an actual 52 KB HTML report. Its chart and filter render. Raw mode preserves the source. Download bytes match the original file. - The complete local UI suite passes: 698 files and 7,754 tests. - `pnpm test:run` was attempted. Its server group recorded two unrelated timeouts and eight connector failures. All failed cases pass in isolated reruns, including the complete 388-test connector suite. The remaining local run was stopped after the full CI test coverage passed, to release test database resources. The full local command did not complete cleanly. - The separate local CLI group passes 511 tests. Three worktree database cases fail to start embedded PostgreSQL because this Mac has exhausted its shared-memory allocation. One isolated rerun fails at the same database startup step. No CLI code was changed. The corresponding CI test jobs pass. - All 56 PR checks are clean on `c771255f1a2e86bd8825f22eafb5d14a5e342cce`. Greptile gives 5/5 with no actionable findings. The security scan passes. The branch has no merge conflict. - Review the **HTML artifacts** section in Storybook. Run `pnpm exec playwright test --config tests/html-preview/playwright.config.ts` for the browser checks. ## Risks - Never add `allow-same-origin` to this iframe. Its opaque origin is the cookie, storage, and host-DOM boundary. - Reports that depend on CDN assets need to embed their dependencies. - The frame can navigate itself. Sandbox restrictions remain after navigation. This is not full network isolation. - Inline scripts can consume browser resources. This change does not isolate CPU or memory use. - No database migrations or API shape changes are required. ## Model Used OpenAI Codex, based on GPT-6, with reasoning, repository editing, code execution, and browser tool use. The runtime does not expose a more specific 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 - [ ] I have run tests locally and they pass — feature and UI checks pass; the full local run has the infrastructure limits recorded above. All CI test jobs pass. - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge Co-authored-by: Paperclip <noreply@paperclip.ing> |
||
|
DottaandPaperclip
|
d0db8820db |
fix(connections): repair native baseline and approval continuations (#15420)
## Thinking Path > - Paperclip manages AI agents and the tools they may use. > - Connection setup separates provider preference from permission to use a tool. > - The first native connection baseline could not exercise its intended decisions. > - The browser used mutable task titles, and the provider fixture already granted access. > - Native provider-choice instructions also disagreed with the preferred question format. Schema rejection gave no field guidance. > - This pull request repairs those test preconditions and native guidance, then fixes restart/approval defects exposed by the corrected baseline. It also restores missing OpenCode tool-error evidence. > - The benefit is an inspectable baseline before any further instruction reduction. ## Linked Issues or Issue Description Refs #15407. The original 15-cell baseline remains 0 PASS / 15 FAIL. Ten cells stopped on stale titles, two Codex cells had schema denials, two OpenCode cells used already-granted tools, and one Claude cell returned no native result. No intended user decisions were submitted. The exact invalid Codex field and underlying Claude failure cause remain unknown. [Original campaign](https://github.com/paperclipai/paperclip/actions/runs/37562577199) · [Original report](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-37562577199-1/index.html) ## What Changed - Match the browser's task route and visible identifier instead of a title the agent can change. - Start native provider-choice fixtures with no agent tool access. Verify the public effective-access records. - In the positive case, select Arcade, then grant its exact HubSpot tool through the real access card. Require both saved decisions and exactly one observed call. - Return a canonical `providerQuestionSet` for native input and retain the equivalent legacy `providerQuestion`. - Keep invalid input rejected. Return bounded schema locations and required field names without submitted values. - Preserve Claude's exact session/content identity while allowing authenticated registered instruction-copy paths to rotate on a new run. - Reject duplicate approval reports for an existing exact tool-action card before they create another human review. - Wait for a recorded service-approval continuation within the existing deadline; retain missing or failed continuation grades. - Forward OpenCode tool activity through the runner facade, preserving bounded errors and execution-part identity without inventing host-call joins or exposing arguments. - Preserve original grades, costs, scope limits and diagnoses in the dated repair report. ## Verification - Eval typecheck passes. Support suite: 1,801 PASS, one intentional skip; Node checks: 128 PASS. - Connection/schema tests: 51 PASS. Real-server public fixture setup: one PASS with zero providers. - Browser support regression: five PASS, including renamed and wrong tasks. - Focused Rust safe-feedback test: one PASS. - Repository typecheck and build pass before the latest master replay. Post-replay connection/shared/real-server fixture checks: 52 PASS; eval typecheck passes. The browser review fix additionally passes all five browser checks and seven suite checks. - The full local repository run was interrupted incomplete after about 45 minutes, with five integration failures retained. All five pass in a separate targeted invocation (1,250 unrelated tests skipped). No full local-suite pass or root cause for the initial local failures is claimed. - Corrected frozen source `162cc90fdabe7f505b88ae095044531b82784c92`: **10 PASS / 5 FAIL** across the [passing Codex canary](https://github.com/paperclipai/paperclip/actions/runs/37575158761) and [remaining 14 cells](https://github.com/paperclipai/paperclip/actions/runs/37576261807). The canary passes all 17 checks. Claude's two provider-choice continuations fail on restart, Claude service approval exposes an early evaluator rejection, Codex service approval creates a duplicate approval, and OpenCode provider-second times out after both decisions with no HubSpot call. No original result is regraded. - Final ledgers count 31 actual runs: 27 succeeded, two failed, two cancelled during cleanup. All 15 cleanup/budget checks pass. The late Claude continuation is absent from its earlier workflow snapshot; it remains in the result/API/final ledger. Original evidence retains 279 hashes. Recorded LLM subtotal $0.04553787 is incomplete billing, not actual total cost; local runtime is unmetered. - New repair regressions reproduce the Claude attach failure, duplicate approval acceptance and dropped OpenCode tool events before their respective fixes. Nine Rust attachment checks, 127 ACPX host/adapter tests, 33 completion/control-plane checks, nine eval deadline tests, 59 OpenCode proxy/driver tests, one Rust tool-error/redaction check, and TypeScript/Rust composer parity pass. Eval typecheck, repository typecheck and build pass. Existing support coverage is 1,802 PASS plus 128 Node PASS, one intentional support skip; two additional deadline tests also pass. - New-source full CI/review and live canaries are pending. The next bounded selection is Claude provider-decline, Codex service-approve and one OpenCode provider-second diagnostic with repaired event evidence. No broader campaign or instruction-reduction qualification is claimed. - Initial corrected campaign [37574251834](https://github.com/paperclipai/paperclip/actions/runs/37574251834) was cancelled during shared build after review found the breadcrumb whitespace assumption. Its matrix job has zero steps and no provider execution. The real adjacent-span browser regression now reproduces the old failure and passes after the fix. ## Risks - The corrected baseline remains 10/15. The new restart/approval fixes require live qualification; OpenCode evidence forwarding does not itself establish or fix its prior behavioral failure. - The positive provider case now expects three runs, including separate access approval. Its new results are distinct from the original invalid fixture. - The old Claude missing-result cause and rejected Codex field are unknown. These repairs do not retroactively explain or erase either failure. - Path rotation must preserve prompt, custom instruction, skill/content identity and protected provider settings; regression checks reject stale or changed content. No connection authorization, JSON schema, budget, cleanup, or final-result requirement is relaxed. Historical Everyday prompts and gateway setup remain unchanged. ## Model Used OpenAI Codex, GPT-6. The exact deployment variant and context window are not exposed in this session. Used repository inspection, code editing, test execution and retained-evidence analysis. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [ ] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [ ] All Paperclip CI gates are green - [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing> |
||
|
DottaandPaperclip
|
caf120105c |
test: prepare neutral native connection guidance evals (#15407)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Agents need to discover connections, obtain consent, and continue from saved decisions. > - We want to reduce repeated instructions only when measured behavior supports the change. > - The existing decline tasks tell the model not to retry. One provider-decline check can pass without an explanation or an observed service counter. > - This PR adds neutral tasks and stricter saved-evidence checks before any connection instruction reduction. > - Production instructions remain unchanged. The new cells are configured, not live-qualified. ## Linked Issues or Issue Description Refs #15218. Refs #15389. **What existing behavior does this improve?** The Product E2E connection workflow evaluation and its instruction measurement provenance. **Current behavior** Some decline prompts supply the policy they intend to test. The provider-decline workflow does not require a saved post-decision explanation. Its old no-call check can use a missing fixture counter as zero. OpenCode has no connection cases in the original Everyday matrix. **Proposed behavior** Add an explicit-only suite with five connection stories on native Codex, ACPX Claude, and OpenCode. Require an explanation attributed by exact run ID after a saved decline. Observe the provider fixture counter. Preserve the original cases and grades. ## What Changed - Add fifteen configured cells with one attempt, twelve-minute deadlines, and verified 1,000-cent company and agent budget stops. - Remove procedure hints from the three new decline prompts. Keep a user-permitted explanation fallback and the existing positive controls. - Require saved decline state, one decision, unchanged connections, observed zero service calls where applicable, and a post-decision explanation from a successful run on the same task. - Add negative grader calibration and test the actual fixture budget payloads. Exclude the suite from default and generic selection. - Extend the existing full-catalog measurement source manifest with connection descriptions and schemas. Add an audit of fixed text, tool descriptions, returned instructions, and unqualified behavior. - Rebase on master `a6306ba606eb87c89b9ef0344e9fe8e0025580f9` and preserve its new Cursor suites. No production, credential, workflow, or lockfile change. ## Verification - Before rebase: Product E2E support passed 1,424 TypeScript tests and 128 Node checks. Six catalog measurement tests, repository typecheck/build, Product E2E typecheck, and exact fifteen-cell discovery passed. - The full pre-rebase repository test run was stopped when master advanced. Its partial result is not a pass. - After rebase and the review correction: repository build/typecheck, Product E2E typecheck, 1,799 TypeScript support tests (one skipped), 128 Node checks, six measurement tests, and exact fifteen-cell discovery pass. The duplicate local full-suite run was stopped incomplete after about 20 minutes once complete CI passed; no local full-suite pass is claimed. - Review found that the initial grader read `runId` instead of public `createdByRunId`. A regression calibration reproduced both rejection of valid public comments and acceptance of the wrong alias. The fix uses the actual field and binds the evidence type to the shared `IssueComment` contract. A subsequent type-only import path correction passes Product E2E typecheck. - Final source `0de306b9664bfbdebb6709ddb54c95152740d1ad` passes [complete CI](https://github.com/paperclipai/paperclip/actions/runs/37560250545): 51 successful checks and two intentional Storybook skips, plus separate Snyk success. Fresh Greptile review is 5/5 with the single review thread resolved and no new findings. The PR is clean and mergeable. - Local commands: `pnpm build`, `pnpm -r typecheck`, `pnpm test:e2e:runner:unit`, `pnpm test:e2e:runner:typecheck`, and `pnpm test:e2e:runner -- --list --suite native-connection-guidance`. The measurement uses `PAPERCLIP_NATIVE_PROCEDURE_MEASUREMENT=/tmp/connection-measurement.json pnpm exec vitest run --project @paperclipai/server server/src/__tests__/native-procedure-measurement.test.ts`. Validation used pinned pnpm 9.15.4. - No paid provider campaign was started. There is no baseline/candidate behavior result for these new cells. - The audit records 654 UTF-8 bytes of fixed connection guidance. A clean capture at `a04b8c6a452315625014888335d45670a2094fb6` confirms 41 supplied tools, 53,341 normalized bytes at start/resume, 50,949 at compact continuation, and a 48,195-byte authenticated OpenCode MCP catalog. These are byte counts, not tokens, bills, vendor-private prompt sizes, or savings from this PR. ## Risks - This is eval preparation. Passing support tests do not establish live model behavior or qualify an instruction reduction. - The explanation oracle checks attributed saved output. It does not prove cognition or arbitrary prose truthfulness. One saved interaction also does not prove the absence of repeated idempotent tool calls. - Successful new authentication and tool refresh, existing-connection agent grants, independent work while waiting, explicit retry after decline, and blocking when mandatory work remains still need separate coverage. - Notion setup decline does not execute a real Notion service. Positive service approval uses an already installed deterministic service; it does not qualify new connection creation. - The original historical failures remain unchanged. Future comparisons must freeze source, fixture, model, input, and grading controls and retain every actual attempt. ## Model Used OpenAI Codex, GPT-6 family, with reasoning, repository tools, and code execution. The exact serving model ID and context-window size were not exposed in this session; they are not inferred. No model provider was invoked by the eval suite in this PR preparation. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing> |
||
|
DottaandPaperclip
|
a6306ba606 |
feat(runner): consolidate Cursor production integration (#15075)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - The native Runner keeps provider sessions under company authority, approvals, budgets and durable recovery. > - Cursor work was spread across candidate branches. The published branch lacked later plan, permission and cleanup fixes. > - Production also needs public installation and matching runtime assets for local and Daytona execution. > - This pull request consolidates Cursor onto current mainline recovery behavior and completes that installation path. > - The installed v11 release passed focused local and Daytona qualification after the generic mode and lifecycle cleanup. The later model-selection correction and current mainline merge produce v14 artifacts that need matching release qualification. > - Cursor admission is enabled in source; publish only an artifact combination with matching qualification. Native AskQuestion and complete per-run dollar accounting remain excluded. ## Linked Issues or Issue Description Refs: #14435, #14631, #14669, #14699, #14724. This completes the Cursor implementation by @cryppadotta from combined source `22c78242a4e0c2369fecf0c2dc4e7600fbad6706`. It preserves newer mainline recovery, completion and warm-directory behavior. Pi and Copilot remain gated. ## What Changed - Generate named Rust and TypeScript ACPX release profiles from one manifest. Share runtime pins with packaging and server verification. Preserve vendor runtime versions; bind the updated ACPX patch to Cursor profile v14 and reject stale generated declarations at build/typecheck. - Remove ACPX model allowlists, including the former Codex and Pi restrictions and the duplicate developer test-drive gate. Send any explicit model ID unchanged to its provider and verify the effective selection before prompting. The bundled ACPX package forwards unlisted IDs, rejects mismatched acknowledgements, and restores the exact selection after session load. It does not expand Cursor model aliases. Provider rejection, mismatch, or missing model controls fails without a fallback. Model examples live in evaluation fixtures, outside runtime declarations. - Add pinned Cursor execution, contained instructions, exact model verification and Agent/Plan/Ask modes. - Carry an opaque generic `mode` identifier in shared native execution, sidecar, Rust and recovery contracts. The provider adapter owns supported modes, defaults, native translation and acknowledgement. - Keep native RPC recognition, accepted-plan interpretation and permission evidence behind provider adapters. Shared settlement and recovery verify normalized facts and their committed evidence. - Replace the Cursor-only warm-attachment branch with a runner-owned capability. Only Cursor opts into it. Move profile compatibility and optional usage parsing into provider metadata and adapters. - Write generic plan-wait receipts. Read exact historical Cursor receipts through a separate compatibility decoder. Reject mixed formats and preserve existing authority checks. - Carry native plans, semantic questions, todos, child activity, permission identities and partial usage diagnostics through the Runner. - Preserve durable response delivery, cancellation, warm ownership and process retirement. - Finish accepted planning runs successfully. Keep their tasks open for explicit direction. Acceptance does not start implementation. - Ship `paperclipai runtime setup cursor` and its provisioner through the public package. npm installation does not download Cursor. Setup uses the OS account's closure-keyed cache so system-wide npm packages can remain read-only. Run it as the Paperclip service account. - Include Cursor in normal provider packs and Daytona images for macOS ARM64/x64 and Linux x64. - Reject stale release packs by source revision and current ACPX/Cursor pins before assembly writes files. Verify current Cursor version/profile/closure again at runtime. - Ship all three daemon targets and the expected Linux image-pack identity. A macOS controller uses its packaged Linux daemon for Daytona. Image mismatches fail before provider launch. - Use the vendored Runner boundary for installed readiness probes. Verify the actual installed Cursor probe. - Verify compiled public Daytona plugins and their release versions in installed smokes. - Record exact artifacts, the acceptance matrix, retained failures, supported capabilities and rollback behavior in the [readiness report](https://github.com/paperclipai/paperclip/blob/codex/cursor-production-readiness/doc/plans/2026-10-03-cursor-production-readiness.md). ## Verification - Current head `f7ec5cc1f0e30c62a829c016ff2013a2a9d79037` merges mainline `faa8e452c73bae5e044dd6379179a00106abb131`. It keeps Cursor plan and cancellation guards alongside mainline historical-question filtering. The evaluation catalog includes both Cursor and expanded adapter accounting cases (683 total). Recursive typecheck, full build, 696 lifecycle/recovery tests, 45 fixture tests and fixture typecheck passed. Current-head CI passed: 56 successful checks, one neutral and four skipped. [Complete CI](https://github.com/paperclipai/paperclip/actions/runs/37557996535). The fresh Base Greptile review is 5/5 on this exact head, with 304 files reviewed, zero new comments and zero unresolved threads. The user authorized overriding the CODEOWNER review gate after checks passed; no failing checks are overridden. Prior results below retain their own head identities. - Corrective head `3d2b168366258036f6b6a6fccb382c49138cc601` fixes the post-merge Apex finding. Automatic-review and new-evidence reconciliation preserve pending child results and recheck delivery under the status lock before completing. Account repair now excludes unrelated secret consumers and requires the failed agent's identity. Regression coverage includes the commit race, delivery statuses, current-run/current-intent exclusions, repeated reconciliation, both database reconciliation paths, and credential consumer boundaries. All 184 affected tests, server typecheck and server build passed. Current-head Base Greptile review is 5/5, with 304 files reviewed, zero new comments and zero unresolved threads. Current-head CI passed: 56 successful checks, one neutral and four skipped. [Complete CI](https://github.com/paperclipai/paperclip/actions/runs/37535994724). This Base review is distinct from the earlier Apex review. - Merge head `5957c257a` reconciles mainline `b508a05c4`. It preserves both accepted-plan waits and pending-child-completion checks, current provider selectors, task-creation response identities, and mainline ACPX missing-file handling. The combined patch is bound to Cursor profile v14; historical records keep their original identities. - Merge head `5957c257a` passed recursive typecheck, full build, 43 installed ACPX/package contracts, 107 provider UI and plan/recovery tests, 593 database-backed lifecycle tests, 49 profile/native contract tests, 45 Product E2E fixture tests, fixture typecheck, token gates, three provider-free browser task-creation cases, and Runner conformance/replay checks. Its complete CI passed (55 successful checks, one neutral and four skipped), while Apex returned 2/5 with a child-delivery finding addressed below. - The local full-suite attempt again failed the unchanged Git streaming test (360-second timeout) and was stopped. The concurrent local Rust attempt failed four unchanged Codex process/deadline tests; all four passed serially without code changes in 7.29 seconds after removing the competing test load. These failed commands are retained and are not reported as full-suite passes; the fresh Linux CI runs are tracked separately. - The previous head `907bdb2a2778c7ffeb4a662a91460c9d1ddfc9c5` earned Apex 5/5 with zero comments after fixing all three findings: per-user install cache, stale release-pack rejection, and public Linux smoke account/home handling. Its real built installer passed from read-only public packages on macOS ARM64 and Linux x64. All 137 release-registry checks and 64 ACPX package contracts passed. That review does not cover this mainline reconciliation. - Prior `beadd3654` passed the full CI matrix; its one unchanged chat test failure and successful single retry remain in the [CI history](https://github.com/paperclipai/paperclip/actions/runs/37521449327). Historical results below remain attributed to their original builds. - Fixture follow-up `dd59d7e82b103a88b7cbd7d2c38b612c0fbbff7a` removes provider-specific model choices from generic offline ACPX tests. The fake sidecar preserves the model and session identity selected at open through suspension. Affected verification passed: 106 Rust tests and 73 TypeScript tests. This commit changes test code only; the production-code checks below retain their recorded identities. Its CI and Greptile review later passed; those results belong to that historical head. - Model-selection cleanup `9a070808b48960a41fdfd369ae0636b95af82459`: 252 focused Runner tests passed (six platform skips), covering all six ACPX agents, native model acknowledgement, rejected selections, installation integrity and recovery identity. The merged branch passed recursive typecheck, full build, token gates, server admission (19 tests), and the Product E2E catalog (45 tests). The acceptance catalog passed all four tests. The full Rust suite passed: 643 tests, 2 ignored. It verifies sidecar acknowledgement of unlisted models and rejection of model mismatches. The final commits only update Rust tests; production sources match the verified build at `65ec3279ac50185e3cda109b5cfd9b4f56105de0`. No new paid provider calls were made. - The merge preserves both Cursor and the new mainline public-MCP fixture cases. Auto-merge remains disabled; the latest follow-up status is recorded above. The local `pnpm test:run` attempt hit the unchanged Git streaming test's 300-second timeout and was interrupted before merging mainline. The broad Runner attempt found obsolete single-model assertions plus three macOS fixture-path failures caused by a `/private/tmp` override. The assertions are corrected; affected TypeScript checks passed with the standard macOS temporary directory, and the complete Rust suite passed. Neither interrupted command is a full-suite pass. - Earlier declaration-cleanup head `6f4a5e9e2` passed recursive typecheck, build, Rust and focused tests. Its CI later exposed a test expecting duplicated Grok digest literals. The current source fixes that assertion to compare launcher bytes with the shared manifest. Historical successes and failed attempts are retained; no new live provider qualification is claimed. - Previous head `e75fde6098b0ddd8cec765bfb6ecaeecb88a26a6` passed complete CI (56 successful checks, one neutral, four skipped) and Greptile 5/5. [Historical complete CI](https://github.com/paperclipai/paperclip/actions/runs/37489112305). Those results are not claimed for the cleanup head. - Frozen live application: `d7b696f9b8f79095233e9e3d56d23e6a6018dd48`. Public package version: `0.0.0-cursor-verify.3d0c9b7761c6`. The declaration cleanup preserves release pins and does not relabel that tested artifact as a build of the new source. Mainline through `e34abee670` was reconciled while preserving accepted-plan waits, provider-capacity handling, and both Cursor and public-MCP fixtures. - Clean normal installation, explicit Cursor setup and daemon resolution passed on macOS ARM64, macOS x64 under Rosetta, and Linux x64. npm lifecycle hooks ran without silently downloading Cursor. - Historical v11 live matrix: **18/18 passed with cleanup** (nine local, nine Daytona) after the generic mode and lifecycle cleanup. The campaign has 23 attempts; all five failures and their diagnoses remain recorded. Exact case identities, hashes and limits are in the readiness report. All provider calls are real, use the explicit Luna model and company-bound credentials, and run without qualification or runtime-asset overrides. - The immutable Daytona image is `ghcr.io/paperclipai/paperclip-daytona-runner@sha256:d6259b6bba094702c13fc2283bd85550849c1c53145b656fb2746778f9fa1747`. The public Daytona plugin is installed independently and its version is checked. - Recursive typecheck, full build, token gates and Runner contract/conformance/replay checks passed on the frozen application. Its complete Linux CI suite passed. The duplicate local full-suite command was incomplete after timing failures; affected repeats passed, but that command is not reported as a clean pass. - Qualification fixtures passed typecheck, 1,675 Vitest tests (one skip), 128 Node checks, three provider-free browser tests, and 150 focused lifecycle tests after the final diagnostic correction. The affected legacy Cursor command file also passed all five tests after removing its shorter 10-second override; it now inherits the suite’s standard 15-second timeout. Greptile is 5/5 on `e75fde609` with no unresolved review threads. CI results above are recorded separately from historical build results. ## Risks - Cursor v14 includes the updated ACPX dependency patch and release identity. The v11 live matrix and image below remain historical evidence. They do not certify new v14 package/image artifacts. - ACPX accepts models beyond the qualification fixtures. Availability and entitlement depend on the provider. Successful configuration is not a claim of live qualification for every model. - Shared mode is an opaque identifier. Provider adapters own its meaning. Incompatible historical sessions remain fenced; exact committed plan waits and task history remain inspectable. - Native AskQuestion is excluded. Paperclip semantic questions are supported. Authoritative per-run dollar accounting is unavailable; partial counters remain diagnostics and unknown cost is not zero. - Image input, detailed native diffs, deeper child transcripts and native plan-file export remain follow-ups. - macOS x64 has clean-install and daemon-startup proof under Rosetta, not a separate live campaign on Intel hardware. - Release only the tested package/image combination. Merging this PR does not publish npm packages or deploy that image. Later builds need their own release verification. Rollback disables new Cursor admission while preserving records and recovery inspection. - A model can fail an exact instruction: one cancelled-plan attempt returned the wrong summary marker despite correct cancellation. The unchanged repeat passed; both results remain in the report. > ROADMAP.md was checked. This completes existing native Runner/Cursor work; it does not add an independent core feature proposal. ## Model Used OpenAI Codex, GPT-6. The exact serving variant and context window are not exposed in this session. The agent used reasoning, repository inspection, code execution, protocol tests and browser-backed Product E2E tools. Cursor acceptance uses the explicit `gpt-5.6-luna[context=272k,reasoning=medium,fast=false]` model. That is the evaluated provider model. ## 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 — affected suites passed; full CI and the retained local failed attempts are recorded separately 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 — 56 successful checks, one neutral and four skipped on `f7ec5cc1f0e30c62a829c016ff2013a2a9d79037` - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups — fresh Base review passed on `f7ec5cc1f0e30c62a829c016ff2013a2a9d79037`; zero new comments and no unresolved threads. The earlier Apex finding remains fixed. - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing> |
||
|
DottaandPaperclip
|
2d0c138122 |
Expand direct assistant MCP tools for work and configuration (#15380)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - People also use assistants in Codex, Claude, and other MCP clients. > - The existing assistant connection can read work and create tasks or comments. > - It cannot edit tasks, exchange files, or manage normal agent and project settings. > - These operations must retain the person's permissions and Paperclip's execution rules. > - This pull request adds an explicit operation registry and separately consented configuration access. > - Assistants can manage work without receiving credentials or runner authority. ## Linked Issues or Issue Description **Subsystem affected** Cross-cutting: assistant MCP, domain routes, consent UI, storage, and Product E2E. **Problem or motivation** A connected assistant cannot update tasks, maintain documents, attach files, or configure existing agents, projects, and skills. Users must leave the assistant for these routine actions. **Proposed solution** Add named tools and a restricted API registry to direct connections. Require separate configuration consent. Reuse domain routes and retry receipts. File uploads save the attachment when the byte transfer succeeds. **Alternatives considered** Arbitrary REST forwarding would expose administration and credential operations. Runner impersonation would bypass execution ownership. Separate upload completion calls add unnecessary client state. **Roadmap alignment** Checked ROADMAP.md and related MCP pull requests. This extends the human-authorized connection from #14933. It does not replace the runner or introduce agent impersonation. Companion Cloud routing and directory isolation: https://github.com/paperclipai/paperclip-cloud/pull/678. ## What Changed - Add task editing, finish/block, documents/revisions, deliverables, agent settings/instructions, projects/repositories, and skills/files. - Add an allowlisted API search/call registry with identical field restrictions, scopes, and retry identities. - Add unchecked configuration consent. Existing write grants retain their current authority. - Add hashed, expiring file transfer tickets and atomic upload receipts. No completion call is required. - Preserve company boundaries, human attribution, active native execution ownership, and execution review gates. - Add protocol/domain tests, consent stories, and eight paid Product E2E workflows. - Repair two CI fixture races: await cold route setup before assertions, and wait for asynchronously loaded connection copy. Both fixture suites pass (24 + 48 tests). ## Verification - Consent revision: one write-access checkbox controls requested work and configuration permissions in browser and device flows. All 16 consent tests, UI typecheck/build and token gates pass. Updated interactive stories cover default approval, opt-out and viewer restrictions. The paid browser helper uses the new exact label. Real GPT-5.4 Mini Product E2E passes 2/2 at `64f96373118eb190f8cba1c2ab17cb979555f3ad` (configuration + permission denial), campaign `local-2026-10-07T00-51-14-337Z`, no automatic retries, cleanup passed; $0.04149375 estimated assistant cost plus unpriced worker usage. Raw results, usage and source fingerprints are retained in the worktree. UI and Product E2E typechecks pass. - Prior head `2f246d4b74f1f98c75ebcb37ae6753a748237fac`: all 52 checks pass; two optional Storybook checks skip. Greptile 5/5 on that head, no unresolved review threads. Final consent head `64f96373118eb190f8cba1c2ab17cb979555f3ad` also has all checks passing and Greptile 5/5 with no unresolved threads. The unchanged Cursor sandbox test had one 10-second timeout, passed in local isolation, and passed its single CI rerun; the failed attempt remains in [the CI run](https://github.com/paperclipai/paperclip/actions/runs/37554106934). The existing chat retry-denial browser test had one visibility failure; its single rerun passes, and the failed attempt remains in [the CI run](https://github.com/paperclipai/paperclip/actions/runs/37542735691). - Full workspace `pnpm -r typecheck` and `pnpm build` pass at final runtime source `b2196fae1`. UI token gates pass. - 139 MCP/OAuth/transfer/privacy tests and 76 grader calibration tests pass, including one-connection PostgreSQL OAuth and concurrent upload retries. - Paid Product E2E: all eight expanded cases qualified across Mini, Haiku and Sonnet. A merged-source repeat passed 23/24; one Haiku cell timed out before application startup. Final affected-case qualification passes 9/9 on all three models with grader v16, including the failed cell. Automatic retries disabled; failures, costs, source hashes and independent durable-state/file assertions are retained in [the verification record](doc/plans/2026-10-06-expanded-assistant-mcp-verification.md). - Actual Codex CLI, Claude Code and OpenCode clients completed local reads/mutations. Codex wrote a report, Claude updated it in a later conversation, and OpenCode uploaded/downloaded a file with matching SHA-256 and registered the attachment. Revoking the CLI grant rejects subsequent bridge initialization. - Butter staging is verified on final runtime `b2196fae1` ([deployment](https://github.com/paperclipai/paperclip-cloud/actions/runs/37538432138)). A fresh OpenCode workspace fetched the copied invitation, configured remote MCP, started OAuth and reached real consent with configuration unchecked. Invalid transfer tickets return 403 through Cloud. Human approval for the new persistent staging grant is pending; hosted task/file success is not yet claimed. The final transaction fix is deployed. - Full local `pnpm test:run` passed 15,614 general-server tests but stopped on two macOS timeouts. The heartbeat test passed in isolation; the existing 40,000-file Git stress fixture timed out again. Its Linux CI lane passes. Later local full-suite phases did not run after the timeout; this is not an all-green local full-suite claim. - Instructions and security limits are in `doc/public-mcp.md`; the saved plan is `doc/plans/2026-10-06-expanded-assistant-mcp-tools.md`. ## Risks - This expands the experimental direct MCP surface. Explicit schemas and domain permissions must stay synchronized. - Migration 0311 adds transfer tickets and upload receipts. Expired orphan cleanup must not remove committed attachments. - Configuration requires a new consent request containing that scope; the single write-access choice controls it alongside work mutations. Refreshing an old grant does not add it. - The public directory keeps its original ten tools through the companion Cloud change. - Hosted consent/work proof remains the final delivery gate. The PR stays draft while approval of the new staging grant is pending; code checks and review are green. Merging is a separate action. ## Model Used OpenAI Codex (GPT-6, tool use and code execution). The exact serving model ID and context window are not exposed in this session. Paid evaluation models: gpt-5.4-mini, claude-haiku-4-5-20251001; 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 (focused suites; full-suite macOS limitation disclosed above) - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing> |
||
|
Devin FoleyandPaperclip
|
3ebd7bc0c9 |
test: isolate accounting fixtures and include all adapter suites (#14989)
Co-Authored-By: Paperclip <noreply@paperclip.ing> |
||
|
DottaandPaperclip
|
fe9d865250 |
fix(native): wake parents after revised child completions (#15372)
## Thinking Path > - Paperclip manages agents and the tasks they perform. > - A parent needs a new notification when a child finishes requested revisions. > - Native completion currently identifies that wake by the parent and child only. > - An already consumed notification can suppress the child's next completion. > - This PR binds ordinary child notifications to the committed status decision. > - A replay keeps the same identity, while a new completion can wake the parent. > - Live evaluation then exposed new child results being swallowed by an active parent. > - The repair preserves that input for a fresh turn and prevents premature Done from discarding it. ## Linked Issues or Issue Description Refs: #15218. The procedure experiments remain unshipped. This fixes native completion wake identity and durable delivery to a busy parent. Related open work: #10559 and #4507 address legacy wake deduplication, #11179 addresses delivery during an active parent run, and #13044 addresses watchdog signals. This PR changes native committed-decision keys and their delivery to an active parent, while preserving exact watchdog behavior. **What happened?** A native child completed, its parent consumed the notification, and feedback reopened the child. The second completion found the old completed wake and created no new notification. **Expected behavior** Each new ordinary child completion can notify the parent. Replaying the same committed completion must not add a notification. If the parent is already running, the new result must remain available for a fresh turn; an unread result must survive a parent Done claim. **Steps to reproduce** Complete a native child, consume its parent wake, reopen and complete that same child, then inspect the parent wakes. The regression fails on unchanged master because only one wake exists after two completions. **Paperclip version or commit** Baseline: `0fe47882cfcb12082035113c59ca96091c46ebfc`. **Deployment mode** Native runner with the standard server and PostgreSQL control plane. ## What Changed - Include the durable status-decision ID in ordinary child completion wake keys. - Defer new ordinary native child completions behind an active parent, carrying the committed decision identity and revised summary. - Keep a parent in progress while that result is still queued, claimed or deferred; recheck before the status commit. Use the existing continuation without reviving cancelled tasks. - Lock the parent before ordinary child status writes, making the notification/Done ordering explicit without upgrading an implicit foreign-key lock. - Cover exact sequential delivery, dispatcher replay, and queued/claimed/deferred versus consumed/current-run completion identities in database tests. - Apply it when the child is also a dependency and when it is only a child. - Preserve the stable key for exact `task_watchdog` origins to avoid repeated watchdog loops. - Extend real database conformance coverage for both relationships, ordinary and near-match origins, watchdogs, revised summaries, and replay. - Reconcile the working checklist with the merged guidance PRs and record the bounded next step. - Reuse the current composer helper for Everyday task creation: capture the returned task ID, preserve the exact prompt and chosen assignee/project, and cover the setup with paused-agent browser tests. The same setup correction is present in both comparison variants. ## Verification **Ready for review and merge at `e2fc0c8e3ddb84dd9bc045704c3d1ecb23ee3447`: both original live cases pass, zero new failures against the frozen baseline, all checks green, CLEAN/MERGEABLE and out of draft. Not merged.** | Profile | Original baseline | Initial candidate | Fixed candidate | | --- | --- | --- | --- | | native Codex / `gpt-5.6-sol` | PASS | FAIL | PASS | | ACPX Claude / `claude-sonnet-5` | FAIL | PASS | PASS | One new pass, one unchanged pass, zero new failures and no pending pairs against the original baseline. The earlier failed candidate is preserved; it was fixed and measured at a new source, not regraded or rerolled unchanged. ### Current source and live evidence - [Completed campaign 37523025407](https://github.com/paperclipai/paperclip/actions/runs/37523025407) and [public report with original screenshots](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-37523025407-1/index.html). Report and screenshots return HTTP 200; screenshot bytes match original retained evidence. - Measured candidate `e2fc0c8e3ddb84dd9bc045704c3d1ecb23ee3447`; reused frozen baseline `7d700f43e93e89e4c196f8799b0aa3cef41d20da`. Trusted workflow `88ff98b83d15eaa6640ee1848df4f0ad9bc82af3` is distinct from measured sources; workflow blob `0600886144d3e22ea2e4a38329a79177882f3948`. Prompts, fixture, oracle, model/profile and input controls are unchanged. Both variants include the same composer setup repair. - Both original candidate grades PASS: all 31 checks per cell, parent and child Done, independently tested revised ZIPs, successful cleanup. Exactly one first attempt per profile on this source: 10 actual runs, no retries. Reusing nine baseline runs gives 19 matched runs; the baseline was not rerun. - Claude directly exercised the repair: its revised child completed while the parent was active, the parent's Done claim became InProgress with `native_child_completion_pending`, and a fresh parent turn then completed with the revised artifact. - Both persisted final provider comments refer to the same attachment whose parent-registration hash matches the revised ZIP tested by the original oracle; native final evidence also references that attachment. Codex provides a clickable download link. Claude describes the new `--max-length` behavior but uses a backticked attachment ID, without a clickable URL in the final prose. The artifact is registered on the parent and independently downloaded/tested; prose-link usability remains a presentation limit outside the original oracle. Artifact identity and observed execution do not prove cognitive review. - 68 focused scheduling/conformance/arbiter tests pass. Four regressions fail against the original production files while four controls pass. The database scheduler test proves one sequential continuation with the revised summary and replay deduplication. It uses a mock adapter and is separate from the live proof. - Full local `pnpm -r typecheck` and `pnpm build` pass. [Exact-head full CI 37522126627](https://github.com/paperclipai/paperclip/actions/runs/37522126627): 51 successful checks, two intentional skips, separate Snyk success. Fresh exact-head Greptile [5/5](https://github.com/paperclipai/paperclip/pull/15372#issuecomment-6022179172), no new actionable findings; all review threads resolved. - Ready-transition Contributor trust and Superagent Security Scan both pass. The security scan completed at 2026-10-06T20:26:53Z with zero annotations. Final total: 53 successful check runs, two intentional skips and separate Snyk success; aggregate SUCCESS, source unchanged, zero unresolved threads. - The explicit parent lock precedes child writes. Its controlled PostgreSQL ordering also passes on previous production through an implicit foreign-key lock; this is hardening, not a reproduced additional live failure. The four original failing regressions remain the before/after proof of the active-parent repair. ### Preserved failures and accounting - Initial candidate `a2ae2324ce7692e704fc43e99904b076d6246fee`: Codex PASS → FAIL, Claude FAIL → PASS. Equal totals concealed a new failure and did not qualify that source. Its Codex parent ended Blocked after the revised child result coalesced into the active parent; there was no retained later parent execution and the independent ZIP oracle was never reached. A later server backstop log did not prove recovery. - In the initial Claude cells, both parent finals referenced an earlier parent ZIP while the oracle tested the revised child's ZIP. The original candidate PASS did not establish latest-artifact delivery. Earlier parent ZIP bytes are absent, so different hashes alone do not prove missing functionality. Those original grades and content findings are unchanged. - Original baseline [report](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-37509893406-1/index.html); original candidate Claude [artifact](https://github.com/paperclipai/paperclip/actions/runs/37509916344/artifacts/11434353106); failed candidate Codex [campaign](https://github.com/paperclipai/paperclip/actions/runs/37513070706). The original cohort contains 17 actual runs, no retries, successful cleanup. - Campaign 37509916344 was cancelled after its Codex job waited over 16 minutes without a runner or steps. Completed Claude evidence was preserved; only the missing Codex first trial was dispatched in 37513070706. The trusted workflow revision differs but workflow bytes are identical. The cancelled campaign has no published HTML. Earlier campaigns 37506546098 / 37506550087 retain four composer setup failures, zero agent runs; the identical fixture-only repair restored setup without changing the prompt or outcome oracle. - Intermediate `3c1cf6830ce9db4123b834ffb99c594c383a8986` [campaign 37518652522](https://github.com/paperclipai/paperclip/actions/runs/37518652522) was cancelled after a concurrency review finding. Both paid-cell steps started and both tasks were created. Only invocation policies survived; no grade, run inventory or cleanup receipt. Provider activity and charges are unknown: two incomplete attempts, not passes or zero-provider setup failures. - Cumulative accounting: **27 known actual runs** (17 original + 10 fixed-candidate), plus unknown activity in those two cancelled intermediate attempts. The 19-run matched comparison reuses nine baseline runs and is not additional execution. Reported LLM amounts are zero with original billing `complete=true`; actual charges are unknown and local/hosted runtime is unmetered. No free-run, speed or cost claim. - Original and new results pass the canonical result validator. Retained source, input, result/API/story/final-ledger/usage run identities and artifact hashes were audited. Each downloaded package omits the pre-upload-declared `playwright-output/.last-run.json`; primary result, API, final ledger, story, screenshots and reached ZIP oracles are retained. No full-package completeness claim. - The initial redundant local full test invocation was stopped after 2,492.5 seconds once that head's CI passed; completed groups recorded 23,045 passes and 87 skips. That local invocation remains incomplete. Current full CI is the repository-wide test evidence. ## Risks A revised completion can schedule another sequential parent run and its normal budget use. A parent Done claim remains non-terminal while a newer native child result awaits delivery. Company scope, governance, workspace-finalization, terminal cancellation and exact watchdog behavior remain enforced. This changes native completion authority and scheduling, so the durable identity, replay and concurrent-commit controls matter. The two live trials qualify the observed revised-child handoff, not broad task quality or causal/general equivalence. Claude's final prose still gives an attachment ID without a clickable URL, although the registered revised artifact passes the original download oracle. Completion before any new child result exists, removal of unfinished dependencies and broader instruction reduction remain separate questions. There is no schema or prompt change. ## Model Used OpenAI Codex, GPT-6 family, with repository inspection, shell execution and code editing. The exact serving model ID, reasoning setting and context window 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> |
||
|
DottaandPaperclip
|
2ca0d26a99 |
fix(connections): recover missing personal AI credentials in chat (#15376)
Co-Authored-By: Paperclip <noreply@paperclip.ing> |
||
|
DottaandPaperclip
|
e38d6d16b6 |
feat(connections): add advanced provider setup and live browser qualification (#15341)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Users connect accounts and choose an agent harness and model. > - The runtime change in #14970 supports custom providers on those connections. > - Normal setup must stay simple while advanced users can choose a compatible gateway. > - Shared connector rows and access controls keep these choices consistent. > - This pull request refines the agent setup UI and adds review stories and repeatable browser qualification. > - The qualification checks real tools and downloaded outputs, not only a successful run status. ## Linked Issues or Issue Description Refs #14970, #37, #13083, #14104, #14565, #12692. The core implementation in #14970 is merged. This branch incorporates its squash commit and targets `master`. Both PRs contain our implementation. #14016 is a reference only and is not a dependency. This PR has 96 changed files. ## What Changed - Complete model-provider connector presentation beside other connectors. Each row uses the existing Connect action and connection list. Tags are stored without category UI. The base PR includes the provider forms and routes. - Show persistent Subscription, API Key, and Advanced choices. Label Advanced as Custom Gateway. Reuse provider logos, connection lists, and permissions controls. Default access to the organization and all agents when permitted; keep narrowing controls under Advanced. - Keep Configure reachable before subscription sign-in, so users can select a supported environment when the default cannot sign in. Testing and saving still require a connection. Show the execution environment in Configure. Preserve the confirmed Connect choice. Editing a method, credential, saved account, or advanced choice requires that current choice to connect before testing or saving. Use matching model and thinking-effort dropdowns and retain connection icons in selected values. - Preserve the new harness model default when switching an existing OpenCode agent to Codex or Claude, and resolve user-selected model names with the effective harness. - Load popular OpenRouter models through the shared connection-model discovery path. Keep explicit model lists and manual model entry available. - Group onboarding, connection setup, agent runtime, management, recovery, and production-component stories under AI Connections / Provider routing. - Add an explicit-only provider-connections browser suite for managed local or existing local/staging targets. Use private browser profiles and credential handoffs. Support human-assisted subscription sign-in without sharing passwords or tokens in reports. - Verify persisted connection identity, runtime probes, tool execution, exact artifact bytes, completion, and context-dependent follow-up. Retain source/model provenance, cost bounds, closed error diagnostics, original failures, and cleanup evidence. - Add Gemini startup-model and skill-root fixes, Grok private-history detection, ACP filesystem regression fixtures, selected-workspace handling for local Hermes, and artifact-helper workspace fallback. - Keep managed Grok runtime homes disposable. Remove host-side transcript retention/restoration because private file modes do not isolate same-user agent processes. Ignore earlier development archives and use a fresh task handoff when history is unavailable. Verify the absence of restored transcripts with a separate same-user process. - Capture stopped-run diagnostics before deleting an attached-company fixture agent. Track creation and owned sign-in receipts; revoke only this attempt's accounts and never adopt a concurrent campaign's newly created account. Preserve failure signals and final status through cleanup. - Require the requested environment in the saved agent and every run, including follow-ups. Reject a forced incompatible target. Keep one cancellation state through startup, every cell, reporting, and teardown for SIGINT, SIGTERM, and SIGHUP. Stop further paid cells after interruption. Document qualification limits. ## Verification - Current head `b3bb3e94d577d43d9965a6b9daba039f599b2e49` includes master `d9f600043`. The security fix in `a758fde31` passes full workspace typecheck, production build, and 119 connection/Grok regressions. The unchanged UI passes all 126 configuration/model-discovery tests and token gates. The final published-guide correction passes Grok adapter typecheck. Earlier head `eebd8225c` passed the complete deterministic runner suite (1,404 Vitest tests and 128 Node tests) and all CI jobs. Current-head CI run `37520147514` passed all 47 jobs, including the full sharded Vitest and browser matrix, production build, and canary dry run. All 55 checks completed: 53 successes and two expected skips. The current-head security scan passed, Greptile is 5/5, and no review threads remain open. - A separate same-user process reproduced reading a restored Grok transcript before the security fix. The regression now finds no transcript. Existing fresh-session fallback and ordinary session metadata behavior pass. - The final account-choice and cleanup fixes pass 85 setup tests and 26 qualification-harness tests. Regressions verify that editing a connection invalidates confirmation, Configure remains reachable before sign-in, diagnostics are captured before fixture deletion, and concurrent campaigns cannot adopt or revoke each other's accounts. UI and E2E typechecks pass. - The Storybook build and actual Chromium production-component stories passed during this change. Review the neighboring AI Connections / Provider routing stories, regular connector rows, three connection modes, model discovery, and the single execution-environment control in Configure. - Cancellation smoke verified authenticated cleanup before browser close for SIGINT, SIGTERM, and SIGHUP. Regressions cover interruption during startup and reporting, missing-file ACP resource errors, and preserved permission denials. Both ACP runtime versions and 54 ACPX/Grok regressions passed. The deterministic connection-intent browser suite passed two tests. - Historical local qualification retained 43 passing API/gateway cells out of 46, with downloaded outputs and follow-up receipts. These attempts span earlier builds; they do not qualify this exact commit or staging. Subscription combinations, Gemini overloads, and the unresolved follow-up failure remain recorded rather than counted as passing. - Use `pnpm test:e2e:runner -- --list --suite provider-connections` to inspect the matrix. Follow `tests/runner-e2e/PROVIDER-CONNECTIONS.md` for credentials, target URL, sign-in assistance, budget, evidence, and cleanup. Paid live tests remain opt-in. ## Risks - The core implementation in #14970 is merged. This PR adds no database migration of its own. - Subscription login needs an interactive provider session. Dedicated accounts and staging qualification remain follow-up work; this PR does not certify every login combination for production. - Managed Grok transcript resume is deferred until provider history has an OS isolation or authorized broker solution. Follow-ups start fresh with Paperclip task context; earlier live Grok results do not qualify this behavior. - Gemini CLI 0.58.0 has an upstream ACP new-file error conversion defect. Live overloads and one unresolved follow-up timeout remain recorded. The stock CLI is unchanged, and those cases are not marked as passing. - Real-provider tests spend credits and use private credential/evidence directories. The launcher requires explicit selection and checks target ownership. It must not attach to a developer's database by accident. - OpenClaw Gateway, Hermes Gateway, Claude Managed, AWS AgentCore, Process, HTTP, and legacy ACPX local remain outside custom provider setup. ## Model Used OpenAI GPT-6 through Codex, with reasoning, repository tools, code execution, and browser testing. The exact deployment model ID and context window size were 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> |
||
|
DottaandPaperclip
|
a7a2ed63a0 |
fix(ui): restore wheel and touch scrolling in task selectors (#15374)
Restore wheel and touch scrolling in nested task selectors and keep mobile picker controls reachable above the keyboard. Stabilize the affected server route test harnesses for Vitest 5. Co-Authored-By: Paperclip <noreply@paperclip.ing> |
||
|
DottaandPaperclip
|
22a3ea3414 |
Invite assistants from Connections with scoped browser and device consent (#14933)
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Public MCP lets people use their organization from an external assistant. > - Operators need a visible control for this experimental access. > - Hosted users should select an organization once and then approve its permissions. > - This pull request adds the setting, invitation-first setup, and browser or device consent. > - Connections provides a copyable invitation with public instructions that grant no access. > - Users reach browser consent from their assistant and return to inspect or revoke access. ## Linked Issues or Issue Description Builds on merged foundation #14846. This PR now targets master. Related settings convention: #13905. **Current behavior** The preview uses an environment variable to enable MCP. Hosted consent repeats organization selection. Assistant access has no entry in Connections, so users must already know the endpoint and how to reach consent. **Proposed behavior** An administrator enables Settings → Experimental → Assistant connections (MCP). A hosted connection shows the selected organization and its icon, then asks for permissions. Requested write access starts checked when the user’s role permits it; the user can opt out before connecting. Direct instance connections show an organization picker with the first available organization selected. The selection stays fixed across refetches and still requires an explicit Connect action. Connections includes Assistant Connection (MCP). Its setup page explains the canonical endpoint, client configuration, browser authentication, and connected access. It connects as the current person and does not select or impersonate an agent. **Reason and benefit** Operators manage access with the other experiments. Users select one organization, and both the UI and server enforce that choice. **Breaking changes** The old enable variable has no effect. Preview operators must enable the setting once. Apply the additive consent-request migration before deploying the tenant, then deploy the compatible Cloud broker. Existing direct requests and grants keep their behavior. ## What Changed - Simplify OAuth and device consent: show the Paperclip logo beside “Connect {client} to Paperclip”, fall back to “your assistant”, and show the identifying origin plus its favicon below, with the callback URL also visible when different. Remove the hosted-organization creation action. Default to the first available organization without silently changing it on refetch; preserve company restrictions and write opt-outs. Keep the button row contained on narrow screens. - Make Copy invitation the primary action, using the shared animated AgentSetupPrompt and a collapsed manual setup section with icon-labeled line tabs. Remove redundant link actions, copy-status text, the extra first-prompt well and revocation explanation from the setup page. Serve shared version-aware HTML and Markdown instructions without private organization data. - Support guarded Client ID Metadata Documents alongside dynamic registration, and include authorization response issuer identification. - Add RFC 8628 device authorization with separately hashed codes, expiry, shared request quotas, persistent polling backoff and atomic redemption. Reuse human consent, role checks, scoped grants, audit and revocation. - Add CLI device login and a local stdio bridge. Store credentials separately with private permissions and serialize rotating refreshes. - Add device consent stories and five cold-start paid Product E2E cases with independent grant, configuration and durable-work assertions. - Add `enablePublicMcp` to the settings validator, normalizer, feature catalog, and toggle UI. Check it live for OAuth, tools, subscriptions, and event delivery. Keep connection management and revocation available while disabled. - Default the MCP origin to the existing auth public URL, with strict validation and an explicit override. - Persist the optional OAuth `company_id` restriction. Describe only that company and reject approval for any other company, even if the person belongs to both. Keep active-membership and role checks. - Show the Paperclip icon and a large organization icon during consent. Return the saved company logo through the company-scoped request response and reuse the standard fallback icon. Use the requested concise permission labels: “Read all of your Paperclip data” and “Allow write access and creating tasks as me”. Use concise permission copy, retain a compact client and callback-origin disclosure, and remove the footer link. - Default requested write access on for eligible roles. Preserve opt-out across organization changes and refetch, reset defaults for a new request, and submit read-only access when the request or role does not allow writes. Align the shared checkbox with its label. - Use organization wording in consent, management, settings, and walkthroughs. Keep the organization fixed for hosted requests and retain direct-instance choice. - Add an Assistant Connection (MCP) card to the Connectors catalog, a setup page in the app shell, and a return link from Experimental settings. Include Codex, Claude Code, OpenCode, and generic remote MCP instructions. - Read the live gate and canonical server URL through authenticated setup metadata. Show only the current person’s grants for the selected organization, refresh after consent, and support revocation. Surface catalog status failures with an explicit retry action; do not present them as an empty connection list. Opening setup grants no authority. - Start the eight guided chapters in Connections. Keep presenter notes and chapter controls around real product pages in the app shell. Explain the terminal, consent, delegation, retrieval, and revocation handoffs. Mark conversation examples as illustrative. Cover first use, client setup, connected, loading, and error states. Keep the existing consent and management stories. - Keep the paid-eval setup and browser helper aligned with the setting and consent button. ## Verification - Warm-standby integration fix `ec64ea05e`: public MCP ingress now follows the Cloud claim guard; MCP and discovery paths return 503 instead of SPA HTML while unclaimed. Event polling checks the in-memory claim before reading the persisted experimental setting. All 97 focused OAuth/Cloud tests and server typecheck pass, including new request and timer regressions for idle-before-claim and resume-after-claim behavior. Fresh review is 5/5 with no unresolved threads, and all security scans pass on this final head. All browser shards, typecheck, build, canary installation and other test groups passed on the first attempt. The unchanged Cursor sandbox default-command test timed out at 10 seconds; the exact test passed locally without edits in 587 ms. The single failed-job retry passed, with the original failure retained in workflow 37500711895. All 54 final-head checks pass on `ec64ea05e9a03e2179d4e2f84c2de03761f7ce26` (two optional Storybook jobs are intentionally skipped). - Final master integration `8457828fc`: merged foundation #14846 and current master, preserving the invitation changes and all 33 files from the two newer upstream changes. No migration renumbering was required. All 95 focused OAuth/Cloud integration tests, full recursive typecheck and token gates pass. All CI gates passed on that integration head; review identified the warm-standby issue fixed above. - Security-review fix `8c1d0b696`: commit shared global/per-source admission before outbound CIMD work, preserve failed-attempt receipts, and validate resource/scope before fetching. Added migration `0305_chubby_vin_gonzales.sql` and six concurrent/adversarial regression cases. All 69 OAuth/metadata tests, 26 migration checks, full recursive typecheck and production build pass. The security scanner passed that commit. Follow-up `87f9658e7` limits only actual cache-miss fetches; 18 authorization requests sharing one proxy across two service instances use just two fetches. All 70 OAuth/metadata tests and server typecheck pass after that refinement. Final follow-up `8ebeae84c` reports admission-storage failures as retryable HTTP 503 instead of invalid client metadata. Its regression proves no outbound request before admission and successful retry after storage recovers. All 71 OAuth/metadata tests and server typecheck pass. Final-head security scanning passes; Greptile is 5/5 with no unresolved findings. CI passed all browser shards, typecheck, build, token gates and canary installation. One unchanged adapter-utils bridge test raced a response-file write (expected a JSON error, received the safe file-changed error). The exact test passed locally without edits. The single failed-job retry passed; the original failure is retained in workflow 37490609192. All 54 checks now pass on final head `8ebeae84ca77c0cf7ac12c2006f0f8743fe50e0b`, with security scan and fresh Greptile 5/5 and no unresolved threads. Foundation #14846 subsequently merged as `e34abee670069cca84afb2efb86041bce7dccbec`; the final integration above now targets master. - Integration with current master: preserved the new Connections source filters and pagination, kept all eval suites, and regenerated the consent/device snapshots as migrations 0303/0304. All four MCP migration SQL hashes are unchanged from the staging versions. Full recursive typecheck and production build, 132 focused UI tests (including catalog filtering), 89 server authorization/settings tests, 26 migration tests, 120 eval calibration tests and token gates pass. Review follow-up `4820ce74c` also keeps active assistant grants in Installed, with pending/error recovery and revocation/company-isolation coverage. All 76 setup/catalog tests, UI typecheck and token gates pass after that fix. The unchanged signoff browser test timed out waiting for a heartbeat in CI at `4820ce74c`; the exact test passed locally without code changes, and the preceding CI head passed that shard. That same unchanged test failed at the reviewer stage in the next CI run. All five signoff tests passed three times locally (15/15), without test changes. All eight browser shards pass at final head `8ebeae84c`; no browser-test edits or failed-browser-job retries were needed. - Setup-page refinement at `9ab009178`: all 17 focused setup/consent tests pass, along with UI typecheck, production build, Storybook build and token gates. Browser exercised the shared prompt preview and client tab switching, and the updated InvitationCopied Storybook interaction checks its clipboard fixture. All final-head CI checks pass at `9ab009178`, with no unresolved review findings. Deployed successfully to Butter in https://github.com/paperclipai/paperclip-cloud/actions/runs/37475189524. Verified the actual page, tab switching and line styling, removed actions/copy, and successful native copy/paste of the complete Butter invitation into a local-only test field. The existing Claude grant was left intact. - Consent follow-up at `dc8e9fd11`: all 10 consent tests and token gates pass. UI typecheck and production build passed again at `4e4d5e4d9`; Storybook build and eval-helper typecheck passed for `28101cf91`. Follow-ups let the primary button wrap on narrow screens, preserve a distinct callback URL, and use only bundled icons to avoid pre-consent requests to client-selected sites. Browser-verified the real consent component in desktop and 320px mobile stories, including default selection, write access and preserved opt-out. Updated E2E heading/default-selection helpers. All CI checks passed at `dc8e9fd11`, with review 5/5 and no unresolved threads. The Butter preview publication needed a retry because npm initially accepted the DB package before making it visible; the retry succeeded and `dc8e9fd11` deployed. Verified a fresh, unapproved native Codex CIMD request on Butter: default organization/write selection, known-client heading and icon, distinct callback origin, and removed creation action. No grant was approved for this UI check. Prior paid runs below retain their exact source provenance; this UI-only follow-up did not rerun paid qualification. - Source-pinned paid matrix at `2992ef2710f47230e7f484c709c6ba02524f884c`: **15/15 passed**, five cases each on GPT-5.4 Mini, Claude Haiku and Sonnet. Campaign `local-2026-10-06T02-41-14-462Z`. Covers cold start, existing config, unavailable host, denied consent and reconnect/later retrieval, with independent configuration/grant/task/run/document assertions. Original failures, transcripts, source fingerprints and billing remain retained. - Final instruction follow-up `cda8178af`: **3/3 cold starts passed** on Mini, Haiku and Sonnet. Campaign `local-2026-10-06T02-58-30-041Z`. Latest `0637b9f1c` shares that same guidance across HTML, Markdown and manual UI after review; generated Markdown is verified byte-identical to the paid-evaluated version. Shared build, server/UI typechecks, token gates and 63 auth/metadata tests passed again. Every CI gate passed at prior HEAD `0637b9f1c`, with review 5/5 and no unresolved threads. - Other focused checks: 11 CLI credential/refresh-lock tests, 120 eval calibration tests, server/UI/eval typechecks, token gates and Storybook build passed. Full recursive typecheck and production build passed during implementation; CI also passed them at `2992ef271`. - Local full-suite limitations: a large-file Git streaming test times out on this Mac, and broader CLI/route runs hit DB hook timeouts. Fresh MCP reruns passed, and the corresponding CI groups passed. No claim that the local full suite is green. - Actual clients: Codex 0.153.4 and Claude Code 2.1.245 reach CIMD consent; device CLI reaches verification/consent. New grants await human approval. Existing local OpenCode retrieved a saved result in a fresh conversation through its previously approved grant. - Fresh OpenCode 1.18.17 on Butter: started with no MCP config, received the exact copied invitation, read public setup, configured its server and started PKCE consent. Its shell command timed out; background retry reached the client's own callback deadline while approval remained pending. Latest instructions cover that handoff. **No completed Butter read/delegation/result retrieval is claimed.** - Cloud companion https://github.com/paperclipai/paperclip-cloud/pull/672 passes checks/review and deployed. Anonymous setup and device-protocol routing verified. Core `2992ef271` deployed successfully and the actual Claude web flow now reaches consent. Its extra JWT-bearer metadata is filtered to implemented grants; unsupported token grants remain rejected. Final `0637b9f1c` deployed successfully to Butter in https://github.com/paperclipai/paperclip-cloud/actions/runs/37409195300; live HTML and Markdown both contain the final guidance. The superseded instruction-only build was canceled before deployment. This is a core-only staging preview; private Cloud plugins are omitted. ChatGPT web is signed out, so browser connector use is unverified. - Screenshot gallery begins at Butter's dashboard and distinguishes real setup/pending consent from local reuse and fixtures. It records the timeout finding. New persistent access needs human confirmation before the remaining actual-client acceptance work. - Manual path: Connectors → Assistant Connection (MCP) → Copy invitation → paste into assistant → configure and start authorization → sign in and approve → verify `paperclip_connection` → delegate → retrieve the saved report later. - Plan and instructions: `doc/plans/2026-10-05-assistant-invitations.md` and `doc/public-mcp.md`. ## Risks - Apply additive, replay-safe migration `0304_curvy_shadow_king.sql` before using device authorization. The public setup link carries no credential. Device codes and tokens stay private; neither sharing instructions nor installing a plugin authorizes access. - Apply additive migration `0305_chubby_vin_gonzales.sql` before deploying the shared metadata admission gate. It retains at most 60 short-lived, hashed-source receipts per instance and rejects excess attempts with 429. - CIMD metadata fetching is a new external-input boundary. It requires HTTPS, exact client ID and redirect validation, bounded responses and guarded DNS/network access. Client names remain self-reported. - Device support is per-instance. The central Cloud broker retains its existing grant support. Host installation and tool reload capabilities vary by client; instructions describe manual settings and restart requirements. - Consent names the registered client in its heading and displays its identifying origin below. Known-origin icons are bundled; all other origins show a neutral site icon without contacting client-selected sites. Client names are self-reported; the callback origin is the recipient check. The Cloud chooser also displays the original client and receiving origin before tenant handoff. - A user who accepts the preselected write permission can create tasks and comments. Task creation and comments can start or wake agents and use execution budget; the consent label uses the concise wording explicitly requested by the maintainer. Scope requests, role checks, and the final Connect action still apply. - Migration `0303_supreme_garia.sql` adds one nullable UUID column with `IF NOT EXISTS`. Requests without a company restriction keep the direct-instance picker. The binding stays recorded if its company is deleted; consent then fails closed. - Deploy tenant support before the Cloud broker sends `company_id`. Unknown or inaccessible organizations must never fall back to a different company. - The setting defaults off. Disabling access does not cancel work already delegated. Existing tokens and unexpired subscriptions can resume when enabled again; revocation remains separate. - The catalog entry is visible for discovery while the feature is off. Setup instructions, OAuth, and tool execution remain gated. No access is granted by viewing the entry. - Assistant sign-in starts in the external client so it owns PKCE and callback state. Client command syntax can change and links to official setup documentation are included. - An authenticated instance and valid public URL are required. Hosting, paid execution, and store publication remain separate rollout steps. ## Model Used OpenAI GPT-6 in Codex, with tool use and code execution. The exact serving model version and context window 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 checks pass; unrelated local full-suite timeouts are explicitly recorded above) - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing> |
||
|
DottaandPaperclip
|
e34abee670 |
feat(mcp): connect assistants to a team with user OAuth (#14846)
## Thinking Path > - Paperclip gives teams durable tasks, agent execution, budgets, and approvals. > - People also use assistants in Codex, Claude, and other MCP clients. > - Those assistants need a scoped connection that preserves the person’s permissions and attribution. > - Delegating a task must not turn the assistant into the assigned agent. > - This PR adds opt-in user OAuth, ten first-party tools, browser consent, and workflow packages. > - Paid product evals verify the resulting tasks, documents, attribution, retries, and access boundaries. > - The team keeps working after the assistant conversation ends. ## Linked Issues or Issue Description **Problem or motivation** A person cannot connect an external assistant to an existing team through browser consent and safely delegate durable work as themselves. **Proposed solution** Expose an opt-in `/mcp/paperclip` endpoint with individually described first-party operations. Bind every connection to a person, client, company, resource, and scopes. Reuse domain authorization and scheduling. Package shared team-review, delegation, and follow-up workflows for OpenAI/Codex and Claude. **Alternatives considered** Related PRs #9393 and #12549 cover earlier remote MCP and board-operator approaches. This change uses user OAuth and a bounded public catalog. It does not expose a generic executor, operator administration, static shared board credentials, or external agent execution. Registry listing work in #9851 is a separate distribution step. **Roadmap alignment** This maintainer-requested implementation extends the governed MCP gateway, activity attribution, durable work products, and hosted deployment direction in `ROADMAP.md`. It implements the first release of the saved design plan; external agent participation and granted third-party tools remain later releases. ## What Changed - Add MCP 2.0 discovery and task status/comment/document Events on the same authenticated endpoint. Persist subscriptions and delivery receipts, verify HTTPS callbacks, sign Standard Webhooks, encrypt callback material, recheck permissions/Cloud membership, and bound retries/expiry. Older MCP clients keep their existing tools. - Add discovery, dynamic client registration, S256 PKCE, resource validation, rotating refresh tokens, revocation, and company consent. Store credentials as hashes and recheck membership at execution. - Add tools for connection identity, agents/projects, task search/read/create, human comments, documents/deliverables, and pending-approval links. Preserve current domain permissions and scheduling. - Add durable mutation receipts across reconnects. Matching retries replay results; uncertain outcomes keep the same request ID and require inspection. - Add consent and connection-management pages, OAuth log redaction, shared plugin workflows, and separate OpenAI/Codex and Claude package outputs. - Add eight paid Product E2E cases across three models, independent durable-state grading, usage evidence, cleanup, and report integration. Add task-document guidance and regenerate the runner capability inventories. - Add migrations 0301 and 0302, the dated implementation plan, result notes, and direct-client setup instructions in `doc/public-mcp.md`. ## Verification - Merge integration `e180b1948`: resolved conflicts with current master, preserved both eval registries, regenerated capability catalogs, and regenerated migrations as 0301/0302 while keeping the original replay-safe SQL byte-identical. Local migration safety/snapshot tests (26), MCP/OAuth tests (38), redaction/OpenAPI tests (71), and eval catalog/grading tests (198) pass. Token and capability gates pass. Full recursive typecheck passed. Fresh Greptile review is 5/5 with no unresolved findings. CI is green on this exact head (55 successes, two intentional skips, one neutral result): one unchanged Cursor sandbox test timed out at 10 seconds, then passed locally in 856 ms. A single retry of that failed shard and the aggregate workflow passed. Merge remains blocked on the repository code-owner approval rule. Earlier checks passed at `6aa0962d4fb715f2190bb7bb22efacab2e58495d`: 55 successes, two intentional skips and one neutral result. [The earlier CI run](https://github.com/paperclipai/paperclip/actions/runs/36901592350) includes all test shards, browser tests, typecheck, build and canary dry run. Greptile was 5/5 on that commit with no unresolved review threads. GitHub still requires code-owner review under the repository merge rules; passing checks do not bypass that approval. Paid source fingerprints remain separate below and in the dated result note. - Paid Events qualification passes **3/3**: GPT-5.4 Mini, Claude Haiku 4.5 and Claude Sonnet 4.6. Each uses a real public HTTPS callback, signature verification and report retrieval in a fresh conversation. A final Mini regression passes after the quota/status fixes. All evidence validates. Bounded tunnel startup retries occur before provider calls and remain visible; failed earlier attempts retain their original grades. - The earlier complete seven-case matrix passes **21/21**, with a separate **3/3** delegation regression. Two preceding matrices also passed 21/21 each. A complete 24-cell matrix including Events has not been run. [The dated results](doc/plans/2026-10-01-public-mcp-paid-eval-results.md) retain exact source fingerprints, failures, model IDs and partial costs. - Node 24: repository-wide `pnpm -r typecheck` and `pnpm build` pass after merging master. Server typecheck passes after the final quota/status changes. Eval typecheck and all 892 eval-support tests pass. - All 33 real MCP/OAuth tests pass. The preceding combined MCP, redaction, private-address and DNS-rebinding run passed 129 tests; two later MCP regressions cover quota reuse and unchanged-status suppression. All 28 adjacent issue-tree/stale-lock route tests pass. CI then found a null checkout result in the existing concurrent-workspace path; logging now uses optional status access. All 12 closed-workspace tests and all 33 MCP tests pass after that correction. The exact-start event calibration exposed a timestamp gap; scanning now includes the subscription start, with all 33 MCP tests and server typecheck passing. These two narrow corrections follow the paid regression. - A real Core → Cloud → Core authority round trip passes OAuth, MCP 2.0 subscription/delivery, current membership loss, unsubscribe, legacy SDK tools, refresh and revocation. Its callback transport is a fixture with independent HMAC verification. The paid Events campaigns separately prove public HTTPS delivery. - Earlier component qualification passed UI 7,117 tests, CLI 502, shared 832, skills catalog 20, database 160 and OpenAPI 10. Token gates, module boundaries, migration order and plugin regeneration passed. CI covers general/serialized suites, eight browser shards, runner checks, typecheck, build and canary dry run. - **Local full-suite limitation:** the earlier monolithic run was not clean. It encountered overlapping schema rebuilding, Mac database shared-memory limits and isolated CLI/fixture failures. Targeted reruns passed. The existing >32 MiB Git filename stress test still hit its 300-second Mac timeout. The additional serialized sweep stopped after 62 passing suites once CI passed. Original failures and partial logs remain; this PR does not claim a wholly green local monolithic run. - Local Codex CLI and Claude Code OAuth login and MCP SDK interoperability were verified. Public-store installation, actual ChatGPT Work Cloud Events UI, staging HTTPS client behavior and hosted newcomer provisioning remain release gates. Enablement is moving to **Settings → Experimental → Assistant connections (MCP)** in the stacked follow-up [#14933](https://github.com/paperclipai/paperclip/pull/14933). Merge both for the intended setup experience. This foundation branch alone still uses `PAPERCLIP_PUBLIC_MCP_ENABLED=true`. After deployment, set `PAPERCLIP_PUBLIC_URL` to the authenticated instance's HTTPS origin, and connect to `/mcp/paperclip`. Select a team and allow writes in browser consent. Configure an available agent and budget, then delegate and retrieve results later. For Events, rescan the deployed plugin catalog in ChatGPT Work Cloud; the host supplies its webhook credentials when the user asks to watch a task. See [the setup runbook](doc/public-mcp.md). ## Risks - Events are at-least-once and may arrive out of order. No replay cursor is advertised. Clients must refresh finite subscriptions, read current state and avoid comment feedback loops. Callback material uses the instance secrets master key; hosted subscriptions require the updated Cloud broker and are bounded to five minutes/the access proof expiry. - ChatGPT Work Cloud/dot event UI, plugin rescan and a hosted staging subscription remain deployment gates. Local signed-webhook and paid model evidence does not claim those surfaces have been exercised. - Disabled by default. Merging adds schema and opt-in code; it does not deploy a public endpoint, publish a store listing, create a team, or start paid agents. - Migrations 0301 and 0302 are additive and idempotent. Their SQL is unchanged from the earlier preview numbers, so hash-aware upgrade reconciliation preserves prior staging applications. Normal instance upgrades must apply it before enabling MCP. - Task creation and comments can schedule paid agent work. Consent and tool descriptions disclose that effect. Revocation blocks future calls but does not undo delegated work. - Public deployments need edge rate limits and credential-safe logging. Internal dispatch is restricted to the closed catalog and carries a request-local verified actor. - Hosted onboarding requires the companion Cloud broker, encryption-key configuration, and tenant rollout. Self-hosted direct connections can use this PR alone. - Store acceptance and agent-mode participation are not claimed. Checked-in plugin endpoints are development defaults; rebuild packages for a real deployment before installation. ## Model Used OpenAI GPT-6 in Codex, with reasoning, tool use, and code execution. A more specific serving version and context-window size were not exposed by the session. Paid eval models: `gpt-5.4-mini-2026-03-17`, `claude-haiku-4-5-20251001`, 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 (targeted/component checks; full local-run limitations are recorded above) - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing> |
||
|
DottaandPaperclip
|
16b7db35ff |
Shorten planning skills and measure task decomposition (#15296)
## Thinking Path > - Paperclip manages work for AI agents. > - Planning guidance helps agents choose owners and dependencies. > - The runtime skill favors few tasks, but the catalog skill requires a child-task breakdown. > - Both add repeated process instructions that can distract from the requested outcome. > - This change keeps the ownership and dependency rules and removes the required matrix and repeated checklist. > - A bounded Product E2E comparison measures saved outcomes and task handoffs before qualification. ## Linked Issues or Issue Description Refs #11057. Related measurement work: #15218. **What existing behavior does this improve?** Planning and delegation through the runtime plan-to-tasks and bundled task-planning skills. **Current behavior** The two skills contain about 1,900 words and conflicting guidance on whether plans require child tasks. **Proposed behavior** Keep cohesive work with one owner. Split only for a real owner, parallel output, dependency, independent review, or follow-up lifecycle. Preserve existing authorization and planning mechanics. ## What Changed - Shorten both skills to about 400 words combined. Preserve their keys and installed-version behavior. - Remove the duplicate operational-skill pointer and regenerate affected source metadata. - Add twelve explicit Product E2E cells: four scenarios with current, short and disabled planning skills. - Use the current task composer and actual create-response ID; calibrate public skill APIs and browser creation without providers. - Eliminate an observed collision in chat-test company prefixes with a per-suite sequence. - Grade saved documents, exact author/run attribution, child count, prerequisite execution order, review boundaries and completion handoffs. - Retain current skill bytes and report source, selections, run accounting and failures. ## Verification - `pnpm test:e2e:runner:typecheck`: pass. - `pnpm test:e2e:runner:unit`: 1,287 Vitest tests and 128 Node checks pass. - `pnpm test:e2e:runner -- --list --suite plan-task-guidance`: twelve local Codex cells. - Archived current skills match master `72ff3a9f27e581a27acb49771e8658bbb0bbaa47` exactly. - Corrected fixture: three real public-API/database calibrations pass with zero provider runs; all 35 evaluator checks and Product E2E typecheck pass. - Setup campaign [37399550253](https://github.com/paperclipai/paperclip/actions/runs/37399550253) was canceled after source review found unsupported bundled edits and automatic core reinstallation. Its paid-cell step was skipped: zero provider runs, no behavioral grade. - The next setup [37401094799](https://github.com/paperclipai/paperclip/actions/runs/37401094799) failed before task creation on the old title-field selector: zero actual runs, original FAIL retained, cleanup passed. A real browser/API calibration of the new helper passes with paused non-provider agents and zero runs. - Full local typecheck/build pass. Full local tests retain one unchanged five-minute Git streaming timeout (also fails isolated), 9,591 passes and 5,796 skips. CI's chat failure was a proven random fixture-prefix collision; five affected cases pass after the test-only repair. - Paid behavior comparison and new-head CI/review remain pending. This PR remains a draft. ## Risks - The shorter text may change delegation decisions. Live outcomes are not yet qualified. - The initial comparison uses one profile and one attempt per cell. It cannot establish cross-model reliability or cost trends. - Disabled means unassigned company-owned copies; the company library remains discoverable. This does not qualify global removal, automatic accepted-plan wiring changes, or installed-copy migration. - Skill availability does not prove a model read or cognitively used it. - No provider/tool protocol, permission, timeout or runtime lifecycle behavior changes in production. ## Model Used OpenAI Codex (GPT-6), with repository inspection, code editing and tool use. The exact backend model ID and context-window size are not exposed in this session. The declared eval model is native Codex `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 - [ ] 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> |
