mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-10-09 16:35:27 +02:00
Dotta
560e7e48b5
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - The runner package already provides the production protocol and execution spine. > - Contributors still need stable SDK surfaces, deterministic test tools, and local inspection tools. > - Those surfaces share generated contracts and must change as one package boundary. > - This pull request adds the package-local SDK, labs, examples, and drift checks. > - The benefit is a reviewable developer platform that does not change application execution selection. ## Linked Issues or Issue Description **Subsystem affected** `packages/paperclip-runner` — runner SDK, conformance tools, and developer tooling. **Problem or motivation** The production runner spine is present, but package consumers cannot build deterministic integrations, inspect sessions, or verify provider-neutral behavior through supported surfaces. **Proposed solution** Add browser, React, standalone, live-session, scenario, conformance, and evaluation surfaces. Add generated contract inventories and package-local verification scripts. Keep production application routing unchanged. **Alternatives considered** We considered splitting each generated catalog, SDK surface, and demo into separate pull requests. Those changes share exports, fixtures, and drift gates. Splitting them would create intermediate package states that do not build. **Roadmap alignment** No overlapping item appears in `ROADMAP.md`. This work extends the runner package that is already on `master`. ## What Changed - Add browser, React, standalone, live-session, and issue-thread SDK surfaces. - Add deterministic mock control-plane, scenario, conformance, replay, and evaluation tools. - Add bounded Codex, OpenCode, and ACPX development transports and fixtures. - Keep deferred managed-provider execution fail-closed. Persisted compatibility data remains readable. - Add generated capability inventories with their source files and drift checks. - Add examples, package documentation, browser checks, and clean-consumer checks. - Preserve the reviewed protocol bounds, replay compatibility aliases, process environment isolation, and semantic redaction limits. - Update the ACPX package patch that the existing workspace patch registry already tracks. - Do not change `pnpm-lock.yaml`, repository workflows, server runtime selection, or the application UI. ## Verification GitHub Actions is the verification authority for this pull request. The repository CI, package TypeScript and Rust checks, package tests, generated-output drift checks, browser checks, security scans, and Greptile review must pass on the exact head. Local test suites were not run because this series uses parallel GitHub Actions for verification. ## Risks This is a large greenfield package change. The main risks are public export drift, generated-output drift, and optional React consumer compatibility. Package boundary checks, clean-consumer checks, and browser tests cover those risks. Production adapter selection and server execution are outside this pull request. ## Stack 1. **This PR:** runner SDK and developer tooling. 2. [Codex production server integration](https://github.com/paperclipai/paperclip/pull/12616). 3. [Provider-neutral task-thread UI](https://github.com/paperclipai/paperclip/pull/12617). ## Model Used OpenAI Codex, GPT-5, high-reasoning mode, with tool use and code 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-PR following the feature request template - [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 - [ ] 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 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
95 lines
11 KiB
JSON
95 lines
11 KiB
JSON
{
|
|
"schemaVersion": 1,
|
|
"dispositions": ["control_plane_owned", "always_agent_tool", "optional_agent_tool"],
|
|
"skillSources": [
|
|
"skills/paperclip/SKILL.md",
|
|
"skills/paperclip/references/api-reference.md",
|
|
"skills/paperclip/references/artifacts.md",
|
|
"skills/paperclip/references/cases.md",
|
|
"skills/paperclip/references/company-skills.md",
|
|
"skills/paperclip/references/issue-workspaces.md",
|
|
"skills/paperclip/references/routines.md",
|
|
"skills/paperclip/references/workflows.md"
|
|
],
|
|
"toolMappings": {
|
|
"paperclipMe": ["control_plane_owned", "injected_actor_context"],
|
|
"paperclipInboxLite": ["control_plane_owned", "runner_work_selection"],
|
|
"paperclipListAgents": ["optional_agent_tool", "list_agents"],
|
|
"paperclipListSkills": ["optional_agent_tool", "list_company_skills"],
|
|
"paperclipGetAgent": ["optional_agent_tool", "get_agent"],
|
|
"paperclipListIssues": ["optional_agent_tool", "search_tasks"],
|
|
"paperclipGetIssue": ["always_agent_tool", "get_task_context"],
|
|
"paperclipGetHeartbeatContext": ["always_agent_tool", "get_task_context"],
|
|
"paperclipListComments": ["always_agent_tool", "get_task_history"],
|
|
"paperclipGetComment": ["always_agent_tool", "get_task_history"],
|
|
"paperclipListIssueApprovals": ["always_agent_tool", "get_task_context"],
|
|
"paperclipListDocuments": ["always_agent_tool", "list_documents"],
|
|
"paperclipGetDocument": ["always_agent_tool", "read_document"],
|
|
"paperclipListDocumentRevisions": ["always_agent_tool", "list_document_revisions"],
|
|
"paperclipListProjects": ["optional_agent_tool", "list_projects"],
|
|
"paperclipGetProject": ["optional_agent_tool", "get_project"],
|
|
"paperclipGetIssueWorkspaceRuntime": ["optional_agent_tool", "get_workspace_runtime"],
|
|
"paperclipControlIssueWorkspaceServices": ["optional_agent_tool", "control_workspace_service"],
|
|
"paperclipWaitForIssueWorkspaceService": ["optional_agent_tool", "wait_for_workspace_service"],
|
|
"paperclipListGoals": ["optional_agent_tool", "list_goals"],
|
|
"paperclipGetGoal": ["optional_agent_tool", "get_goal"],
|
|
"paperclipListApprovals": ["optional_agent_tool", "list_approvals"],
|
|
"paperclipCreateApproval": ["optional_agent_tool", "request_approval"],
|
|
"paperclipGetApproval": ["optional_agent_tool", "get_approval"],
|
|
"paperclipGetApprovalIssues": ["optional_agent_tool", "get_approval_context"],
|
|
"paperclipListApprovalComments": ["optional_agent_tool", "get_approval_context"],
|
|
"paperclipCreateIssue": ["optional_agent_tool", "create_task"],
|
|
"paperclipUpdateIssue": ["optional_agent_tool", "semantic_task_disposition"],
|
|
"paperclipCheckoutIssue": ["control_plane_owned", "atomic_checkout"],
|
|
"paperclipReleaseIssue": ["control_plane_owned", "runtime_release"],
|
|
"paperclipAddComment": ["always_agent_tool", "report_progress"],
|
|
"paperclipSuggestTasks": ["always_agent_tool", "request_human_input"],
|
|
"paperclipAskUserQuestions": ["always_agent_tool", "request_human_input"],
|
|
"paperclipRequestConfirmation": ["always_agent_tool", "request_human_input"],
|
|
"paperclipRequestCheckboxConfirmation": ["always_agent_tool", "request_human_input"],
|
|
"paperclipUpsertIssueDocument": ["always_agent_tool", "write_document"],
|
|
"paperclipRestoreIssueDocumentRevision": ["optional_agent_tool", "restore_document_revision"],
|
|
"paperclipLinkIssueApproval": ["optional_agent_tool", "link_approval"],
|
|
"paperclipUnlinkIssueApproval": ["optional_agent_tool", "unlink_approval"],
|
|
"paperclipApprovalDecision": ["optional_agent_tool", "decide_approval"],
|
|
"paperclipAddApprovalComment": ["optional_agent_tool", "comment_on_approval"],
|
|
"paperclipApiRequest": ["optional_agent_tool", "test_only_api_escape_hatch"]
|
|
},
|
|
"evalGroups": {
|
|
"hb": ["control_plane_owned", "control_plane_invariant", "get_task_context", "active_task_context"],
|
|
"co": ["control_plane_owned", "control_plane_invariant", "atomic_checkout", "checkout_decision"],
|
|
"st": ["always_agent_tool", "combined_multi_hop", "semantic_task_disposition", "terminal_or_blocked_task"],
|
|
"cm": ["always_agent_tool", "agent_tool_contract", "report_progress", "rendered_comment"],
|
|
"se": ["optional_agent_tool", "agent_tool_contract", "search_tasks", "company_scoped_search"],
|
|
"su": ["optional_agent_tool", "combined_multi_hop", "create_child_task", "delegation_and_wake"],
|
|
"bl": ["always_agent_tool", "combined_multi_hop", "block_task", "blocker_projection"],
|
|
"dp": ["always_agent_tool", "agent_tool_contract", "write_document", "revision_safe_document"],
|
|
"ix": ["always_agent_tool", "combined_multi_hop", "request_human_input", "interaction_and_wake"],
|
|
"ap": ["optional_agent_tool", "authorization_policy", "request_approval", "approval_gate"],
|
|
"ar": ["always_agent_tool", "agent_tool_contract", "register_deliverable", "artifact_and_work_product"],
|
|
"er": ["control_plane_owned", "combined_multi_hop", "runtime_reconciliation", "recovery_or_restraint"],
|
|
"rf": ["optional_agent_tool", "agent_tool_contract", "optional_reference_workflow", "scoped_reference_result"],
|
|
"mh": ["always_agent_tool", "combined_multi_hop", "create_child_task", "multi_hop_projection"],
|
|
"rs": ["control_plane_owned", "restraint_no_call", "none", "unchanged_state"],
|
|
"wk": ["control_plane_owned", "combined_multi_hop", "wake_reconciliation", "wake_mode_projection"]
|
|
},
|
|
"evalCases": {
|
|
"hb": ["hb-context-01|Prefer compact heartbeat context", "hb-inbox-lite-01|Use compact inbox for normal heartbeat", "hb-pick-priority-01|Prioritize in-progress work", "hb-scoped-wake-01|Scoped wake skips inbox", "hb-wake-comment-01|Read triggering comment first"],
|
|
"co": ["co-409-stop-01|Stop after checkout conflict", "co-409-stop-02|Named conflict remains terminal", "co-before-work-01|Checkout before issue writes", "co-body-contract-01|Send checkout request contract", "co-no-status-patch-01|Do not patch into progress", "co-runid-header-01|Audit modifying calls"],
|
|
"st": ["st-backlog-park-01|Park postponed work in backlog", "st-blocked-owner-01|Record blocker owner", "st-crossteam-cancel-01|Reassign cross-team task instead of cancelling", "st-done-comment-01|Close task with explanatory comment", "st-env-blocked-notdone-01|Block impossible deliverable with an owner", "st-ephemeral-verify-01|Disclose ephemeral verification", "st-handback-review-01|Return task for board review", "st-unverified-toolchain-01|Block when verification cannot run"],
|
|
"cm": ["cm-mention-structured-01|Render structured mentions", "cm-multiline-01|Preserve multiline comments", "cm-prefixed-url-01|Prefix internal URLs by company", "cm-progress-nextaction-01|Report progress and next owner", "cm-runid-modify-01|Audit comment writes", "cm-ticket-link-01|Render ticket links"],
|
|
"se": ["se-get-issue-01|Read issue and history", "se-q-comments-01|Search comment bodies", "se-q-filters-01|Combine search filters", "se-q-topic-01|Find issue by topic"],
|
|
"su": ["su-crossteam-billing-01|Set cross-team billing", "su-inherit-workspace-01|Inherit workspace for follow-up", "su-no-poll-01|Delegate without polling", "su-parent-goal-01|Create subtasks with parent and goal"],
|
|
"bl": ["bl-cancelled-not-resolved-01|Cancelled blocker remains unresolved", "bl-clear-01|Clear blocker set", "bl-create-blocked-01|Create dependent work blocked", "bl-firstclass-01|Use first-class dependencies", "bl-read-owners-01|Read blocker owners"],
|
|
"dp": ["dp-base-revision-01|Use latest document revision", "dp-plan-doc-01|Store plan in plan document", "dp-plan-link-comment-01|Deep-link plan document"],
|
|
"ix": ["ix-checkbox-01|Use checkbox confirmation for subset", "ix-checkbox-result-01|Act on selected option IDs", "ix-confirmation-plan-01|Bind plan confirmation to revision", "ix-continuation-01|Use continuation wake policy", "ix-questions-01|Use typed questions", "ix-stale-target-01|Rebuild after stale target", "ix-suggest-tasks-01|Suggest before creating tasks", "ix-superseded-comment-01|Address superseding comment", "ix-verdicts-01|Request item verdicts"],
|
|
"ap": ["ap-approval-deny-01|Keep denied approval task open", "ap-approval-wake-01|Resolve approval wake", "ap-board-approval-01|Request board approval for spend", "ap-mcp-expiry-01|Re-call once after approval expiry", "ap-mcp-gate-01|Wait on pending MCP approval", "ap-mcp-pathmissing-01|Reroute on missing approval path"],
|
|
"ar": ["ar-no-done-without-upload-01|Upload file deliverable before close", "ar-upload-before-done-01|Attach deliverable before done", "ar-workproduct-pr-01|Register pull request work product", "ar-workproduct-wsfile-01|Register workspace file work product"],
|
|
"er": ["er-blocked-dedup-01|Avoid duplicate blocked update", "er-budget-critical-01|Choose critical work at high budget", "er-close-retry-fault-01|Retry terminal close faults", "er-exec-not-participant-01|Do not advance foreign review stage", "er-exec-participant-01|Advance own review stage", "er-mention-handoff-01|Checkout explicit mention handoff", "er-mention-noassign-01|Do not claim FYI mention", "er-no-unassigned-01|Exit on empty inbox", "er-release-01|Release task handback"],
|
|
"rf": ["rf-api-404-report-01|Report missing issue honestly", "rf-api-cancel-obsolete-01|Cancel obsolete work", "rf-api-mention-discipline-01|Avoid non-actionable mentions", "rf-api-mgr-heartbeat-01|Run manager heartbeat", "rf-api-review-changes-01|Request review changes", "rf-art-attachment-wp-01|Register attachment work product", "rf-case-child-01|Create child case", "rf-case-lifecycle-link-01|Link active case", "rf-case-upsert-doc-01|Upsert case document", "rf-cskill-audit-01|Audit library and attached skills", "rf-cskill-install-attach-01|Install then attach skill", "rf-cskill-self-sync-01|Preserve skills during sync", "rf-iws-start-url-01|Start issue workspace service", "rf-iws-target-restart-01|Restart selected workspace service", "rf-routine-create-01|Create weekly routine", "rf-routine-manual-run-01|Manually run routine", "rf-routine-pause-01|Pause routine reversibly", "rf-routine-policy-01|Configure routine policies", "rf-routine-webhook-01|Add signed webhook trigger", "rf-wf-export-preview-01|Preview narrowed export", "rf-wf-invite-01|Create paste-ready invite", "rf-wf-project-setup-01|Set up repo workspace project"],
|
|
"mh": ["mh-blocked-handoff-01|Create review handoff blocker", "mh-children-complete-01|Complete parent after children", "mh-plan-confirm-01|Confirm a written plan", "mh-subtask-tree-01|Create sequenced subtask tree"],
|
|
"rs": ["rs-dependency-blocked-wake-01|Triages dependency-blocked wake", "rs-question-only-01|Answer question without mutation", "rs-secret-hygiene-01|Never expose API key"],
|
|
"wk": ["wk-ask-mode-01|Answer-only ask-mode wake", "wk-plan-accepted-01|Create tasks after accepted plan", "wk-plan-annotation-01|Revise annotated plan", "wk-plan-directive-01|Write plan then request confirmation", "wk-plan-directive-02|Honor prose planning directive", "wk-recovery-processlost-01|Recover without duplicate work", "wk-resume-delta-01|Apply condensed resume contract", "wk-skilltest-mode-01|Write structured skill test output"]
|
|
}
|
|
}
|