DottaandPaperclip
5e8e992df2
## Thinking Path > - Paperclip helps people manage AI agents and their work. > - The feature map describes user capabilities and verification recipes. > - Storybook holds isolated examples of those capabilities. > - Missing catalog links can hide existing examples. > - Some stories also expose shipped capabilities absent from the map. > - This pull request adds verified source associations and three paired map entries. > - Readers can find existing examples without changing their homes or URLs. ## Linked Issues or Issue Description Refs #16052, #16049 and #16046. **What existing behavior does this improve?** Storybook capability lookup and the feature/agent access maps. **Current behavior** Seventy capabilities have no example link. Some matching stories already exist. Primary-agent preferences and company decision/fast-response services appear only under broad neighboring capabilities. **Proposed behavior** Add source-supported links across 34 suites. Keep shared foundations in place while cross-listing them. Add primary-agent, decision-model and fast-response capabilities to both upstream maps. Retain explicit simulation and partial-example limits. **Reason and benefit** The catalog distinguishes missing associations from missing examples. The upstream map describes three existing product capabilities more precisely. **Breaking changes** None to product behavior, story exports, folders, sidebar titles or URLs. A shared foundation can declare a reasoned `home: "foundations"` override while referencing related capabilities. ## What Changed - Add 55 references across 34 suites. Replace primary-agent suites' reporting-line association with their own capability. - Add three source-reviewed capabilities and their API/actor boundaries to paired maps. - Preserve the shared Foundations home when cross-listing developer design examples. Add a validation regression test. - Record which exports demonstrate each association and what remains simulated or unverified. - Regenerate the catalog and capability data. Preserve all original 223 authored suites and 2,210 story IDs. Retain the two skill-removal stories added by current master, for 2,212 authored stories in total. - Reduce empty example lookups from 70 of 171 capabilities to 59 of 174. Links do not establish complete capability coverage. ## Verification - Passed: 27 catalog/generator/map tests, catalog validation, map structural checks, token gates and skill validation. - Passed: source inventory comparison preserves all authored files, titles, meta IDs and story IDs. - Passed: repository typecheck/build and Storybook build. Final built index has 2,248 entries and preserves all previous entries, including the two skills stories added by current master. - The broad local repository test run was interrupted before completion to resolve a new master conflict. A complete local suite pass is not claimed; fresh CI passed on the reconciled branch. - Browser: Design links to preserved Foundations stories; company-service sections link settings/history/journey suites; decision SetupToHistory passed 12 interaction steps; primary-agent ReplacePrimary passed four steps. No console errors in selected checks. - Greptile: 5/5 on final commit `805a8af62abe589907e7cc6ca1b415ce1e0cc3c0`, with no findings or unresolved threads. - Final-revision CI passed all 57 checks/statuses, including all eight browser shards, server and Runner tests, typecheck and build. The unchanged Cloud-auth mocked-response race seen on a superseded revision did not recur on the final commit. No test expectations were changed. - New agent-access evidence is source-only. Live provider and agent-credential verification is not established. ## Risks - Suite-level associations can represent only selected states. Notes retain those limits and existing review classifications. - In-memory connection drafts do not prove reload persistence. Resume-failure UI does not prove successful continuation. No-op budget controls do not prove relief or resumption. - Three map capabilities document existing behavior. No permission, API, provider or production component changes. ## Model Used OpenAI Codex, GPT-6 family, with reasoning, code execution and source inspection. The exact runtime model ID 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>
7.7 KiB
Companies and portability — agent access
Product map: Companies and portability.
Review date: 2026-10-12. Source commit: 58e16dbddfc9c8d0cf60867f9d9847f0feda055b.
Native REST transport reconciled in this change; see the
shared transport contract.
This is a source-reviewed baseline of representative operations and known gaps. Each capability needs operation-level review before its entire scope can be qualified. No live agent execution is claimed. Follow the map contract for format, permission checks, evidence and maintenance.
selection
Review: baseline.
API: present — representative operation IDs:
GET /api/companies/{companyId}.GET /api/companies.POST /api/companies.
Agent access: partial — Agent reads its bound company; CLI context chooses it; board
lists/creates companies.
Policy: Same-company CEO or board for identity/import operations; list/create/archive convenience endpoint is board-gated.
Evidence: source-only — implementation
at the reviewed commit above.
Verification: not-run — exercise a listed permitted operation with actual agent
credentials/run context; inspect its result and applicable persistence/attribution.
Assert the relevant denied actor, owner, company or mode from Policy. Review the
remaining operations before qualifying the whole capability.
Gaps: A worker cannot enumerate/create companies via its company agent key. Browser selection is local state.
identity
Review: baseline.
API: present — representative operation IDs:
PATCH /api/companies/{companyId}.PATCH /api/companies/{companyId}/branding.
Agent access: available — Same-company CEO REST / native call_api / CLI company.
Policy: Same-company CEO or board for identity/import operations; list/create/archive convenience endpoint is board-gated.
Evidence: source-only — implementation
at the reviewed commit above.
Verification: not-run — exercise a listed permitted operation with actual agent
credentials/run context; inspect its result and applicable persistence/attribution.
Assert the relevant denied actor, owner, company or mode from Policy. Review the
remaining operations before qualifying the whole capability.
Gaps: The CEO restriction is a real policy, not a missing API; ordinary employees need denial evidence.
archive
Review: baseline.
API: present — representative operation IDs:
POST /api/companies/{companyId}/archive.PATCH /api/companies/{companyId}.
Agent access: partial — Board archive endpoint; CEO company PATCH can express status
changes.
Policy: Same-company CEO or board for identity/import operations; list/create/archive convenience endpoint is board-gated.
Evidence: source-only — implementation
at the reviewed commit above.
Verification: not-run — exercise a listed permitted operation with actual agent
credentials/run context; inspect its result and applicable persistence/attribution.
Assert the relevant denied actor, owner, company or mode from Policy. Review the
remaining operations before qualifying the whole capability.
Gaps: Convenience archive and general company PATCH have different authorization. Review equivalence rather than declaring all archival human-only.
portability
Review: baseline.
API: present — representative operation IDs:
POST /api/companies/{companyId}/exports.POST /api/companies/{companyId}/imports/preview.POST /api/companies/{companyId}/imports/apply.
Agent access: partial — Same-company CEO REST / native call_api / CLI exports
and eligible same-company imports.
Policy: Same-company CEO or board for identity/import operations; list/create/archive convenience endpoint is board-gated.
Evidence: source-only — implementation
at the reviewed commit above.
Verification: not-run — exercise a listed permitted operation with actual agent
credentials/run context; inspect its result and applicable persistence/attribution.
Assert the relevant denied actor, owner, company or mode from Policy. Review the
remaining operations before qualifying the whole capability.
Gaps: Exports use inline credential delivery and encrypted mutation receipts. New-company/ZIP import flows retain their board and transport constraints.
decision-models
Review: baseline.
API: present — GET and PUT /api/companies/{companyId}/decision-model;
POST /api/companies/{companyId}/decision-model/test;
GET /api/companies/{companyId}/decision-model/availability;
GET /api/companies/{companyId}/decision-model/history.
Agent access: partial — same-company REST and admitted native call_api
availability/history reads where policy allows. Settings and the fixed Test
action require board identity. Native rollout/run gates follow the shared
transport contract.
Policy: Settings access requires board and company access; non-managers receive no settings or choices. Configuration and tests additionally require connection management authority (owner/admin, instance admin, or tools:manage_connections). History requires company_scope:read and redacts task/run links without issue:read. Background sponsorship and budget admission remain separate service checks.
Evidence: source-only — reviewed on 2026-10-13 at
60bc0d5fee9a6e48db08fc016521fee3d9f57d67:
routes,
service, and
connection authority.
Verification: not-run — read history with an allowed company actor and an actor
without task access; check link redaction. Reject agent configuration/tests and
board mutations without connection-management permission. Verify settings and
bounded test receipts with an owned simulated provider.
Gaps: No agent settings/test path; permitted history does not delegate management. Live native and agent-credential reads remain unverified.
fast-responses
Review: baseline.
API: present — GET and PUT /api/companies/{companyId}/fast-response;
GET /api/companies/{companyId}/fast-response/models;
GET /api/companies/{companyId}/fast-response/availability;
POST /api/companies/{companyId}/fast-response/test;
GET /api/companies/{companyId}/fast-response/history.
Agent access: partial — same-company REST and admitted native call_api history
reads where policy allows, subject to the shared
transport contract.
Settings, model selection, availability and test controls require board identity.
Policy: Board and company access gate configuration surfaces. Updates, models and tests additionally require connection-management authority. History requires company_scope:read; task/run links require issue:read. The experiment, provider account, sponsorship and budget controls still gate actual acknowledgements.
Evidence: source-only — reviewed on 2026-10-13 at
60bc0d5fee9a6e48db08fc016521fee3d9f57d67:
routes,
service, and
connection authority.
Verification: not-run — inspect history and redacted task links as an allowed
company actor. Reject agent settings/models/availability/tests and unauthorized
board mutations. Use a simulated provider to inspect a saved configuration,
success receipt, timeout and recorded usage.
Gaps: No agent configuration/test path. An acknowledgement is not completed task work. Live native, provider and agent access remain unverified.