Files
PaperClipAI/maps/feature-map/companies.md
T
DottaandPaperclip 9ef434fe79 docs: expose feature map IDs and add a recipe index (#16987)
## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work.
> - Its feature map describes user journeys and their verification
paths.
> - The map already defines feature IDs and full capability IDs.
> - The README and child pages did not show those IDs consistently.
> - Readers need those IDs to connect issues, tests, stories, and
evidence.
> - This pull request adds a recipe index and displays the existing IDs.
> - The benefit is clear references across the product and agent access
maps.

## Linked Issues or Issue Description

**Issue type**

Missing documentation.

**Where is the issue?**

`maps/feature-map/README.md`, the child recipes, and their agent access
companions.

**What's wrong?**

The README sends readers to Storybook to browse features. Child pages
show local keys, such as `installation`, without the full
`plugins/installation` ID. Readers must inspect the generator to find
the full reference.

**Suggested fix**

List recipe links and existing IDs in the README. Show each feature ID
and full capability ID in its child pages. Explain capability IDs and
entry-point references. Keep the current keys and anchors.

Related work: Refs #15288. Refs #16052. Refs #15983. No duplicate open
PR or issue was found by title search.

## What Changed

- Add an index grouped by feature area. It lists every recipe, feature
ID, and full capability ID.
- Explain how IDs are formed and used in issues, tests, Storybook, and
evidence.
- Add feature IDs to all product recipes and agent access companions.
- Show full capability IDs beside recipe keys and below access and
Storybook guidance headings.
- Preserve existing keys, heading anchors, and generated ID values. Keep
the latest upstream company capability in the index.

## Verification

- `node scripts/check-maps.mjs` passes for 34 feature families and 175
capability IDs.
- `node --test scripts/check-maps.test.mjs
scripts/storybook-feature-index.test.mjs` passes all 17 tests.
- `node scripts/storybook-feature-index.mjs` passes on this checkout and
generates the feature indexes and overview inputs.
- `git diff --check` passes.
- A source comparison confirms that the README matches the recipe index.
After removal of the added ID labels, all 68 child pages match the
upstream prose and headings.
- Full workspace checks were attempted: `pnpm -r typecheck`, `pnpm
test:run`, and `pnpm build`. They could not start because the local pnpm
wrapper could not fetch and verify the pinned pnpm 9.15.4 release. This
checkout also has no workspace dependencies installed.
- `node scripts/storybook-catalog.mjs` could not run because
`storybook/internal/csf-tools` is not installed. The direct map and
index checks above pass without that dependency.
- Remote typecheck, release-registry, and full build checks passed. The
first attempts of [server shard
3/12](https://github.com/paperclipai/paperclip/actions/runs/39460473910/job/118758430448)
and [server shard
12/12](https://github.com/paperclipai/paperclip/actions/runs/39460473910/job/118758429932)
stopped after their runners received a shutdown signal. The test steps
were canceled. GitHub rejects the rerun request with HTTP 403: "The
workflow run containing this job is already running". Five other CI jobs
remain active. The next action is to rerun the two interrupted shards
after workflow 39460473910 ends. No application changes were made to
address these runner interruptions.
- To inspect the result, open the feature-map README, follow a recipe
link, and compare its full capability IDs with its access companion.

## Risks

- Low risk. The change updates map documentation only. It changes no
application code or ID schema.
- The readable README index and child labels repeat source IDs. Keep
them aligned when a capability changes.
- Generated capability descriptions now include the visible ID prefix.
Generated IDs, labels, navigation order, and verification fields remain
the same.
- Full local workspace checks and catalog generation remain unverified
for the environment reasons above.

> For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and
discuss it in `#dev` before opening the PR. Feature PRs that overlap
with planned core work may need to be redirected — check the roadmap
first. See `CONTRIBUTING.md`.

## Model Used

OpenAI Codex, model `gpt-6.1-sol`, with a 475,000-token context window
and `xhigh` reasoning effort. The model used local file tools, shell
commands, and GitHub CLI access.

## Checklist

- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [ ] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge

Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-10-20 12:00:36 -05:00

9.9 KiB

navigation
navigation
section sectionOrder order
Getting started and access 10 30

Companies and portability

An operator can switch between companies, change their identity and settings, archive them, and preview an import or export. Each company remains a separate scope for work and agents.

Feature ID: companies.

Implementation: companies, settings, import, export.

Agent access: companion.

Sub-features

  • selection: companies/selection — create/select a company and keep navigation in its scope.
  • identity: companies/identity — update company identity and configured settings.
  • decision-models: companies/decision-models — configure and test the company's decision model, then inspect invocation history and recorded usage.
  • prompt-injection-prevention: companies/prompt-injection-prevention — opt into a shared OpenRouter classifier for existing tool-result guards, test fixed samples, and recover unavailable selections.
  • fast-responses: companies/fast-responses — configure and test the experimental fast-response service, then inspect acknowledgement history, failures, and recorded usage.
  • agent-observability: companies/agent-observability — configure one company OTLP destination for Codex and Claude Code, test synthetic delivery, and disable export.
  • archive: companies/archive — archive and restore through the available controls without confusing archival with deletion.
  • portability: companies/portability — preview a company package and inspect imported agents, projects, skills, and conflicts.

How to get to it (user POV)

company-switcher

Use the company switcher or /companies, then enter company Settings.

package-transfer

Use /company/export and /company/import where enabled, or the corresponding CLI company commands.

company-ai-services

Use Settings → Connections (/company/settings/connections) for Decision model and Prompt Injection Prevention, independent of experimental flags. Fast response appears there only when its experiment is enabled. Open the Decisions and Fast responses tabs in Costs to inspect invocation history.

Driving it with Playwright and the Paperclip CLI

Preconditions: follow the baseline. Use two disposable companies and a small package fixture. Record cloud-managed restrictions and visible settings gates.

company-switcher

Automated: company list and archive UI cover UI behavior with mocks.

Manual: Create or select a company, rename it, and reload. Switch to the second company and back; verify tasks, agents, and settings follow the selection. Archive the disposable company and verify its visibility and offered restoration path.

package-transfer

Automated: portability routes and CLI import/export cover package and command behavior, not every external Git host.

Manual: Export a small company, inspect the package preview, and import into a disposable target. Verify counts, references, conflict choices, and agent configuration. Run one imported task after supplying its required local credentials. Confirm source company data is unchanged.

company-ai-services

Automated: decision settings, decision history, fast-response settings, decision service, and fast-response service cover component and service contracts with simulated providers.

Manual: As an authorized connection manager, select a disposable shared AI connection, save the provider/model and sponsorship options, reload, and run the bounded Test action. Inspect success and failure receipts and their history in Costs. Verify disabled or revoked connections remain clear and that a user without connection-management permission cannot configure or test the service. Use an owned provider fixture for failure states; record any actual provider usage.

Gotchas

  • Restore an archived company through /companies → its menu → Unarchive. Archiving pauses eligible agents and cancels active runs; restoration handles agents paused specifically for company archival.

  • Package presence does not prove a runnable imported company; credentials and environment bindings need separate verification.

  • Company deletion is a distinct gated operation; do not use it as the archive test.

  • Settings hidden in a managed deployment should be recorded as unavailable, not bypassed.

  • Decision tests and fast responses have different request and execution contracts. A fast-response receipt is an acknowledgement, not completed agent work. History visibility and connection-management authority are separate; task links in history also require access to the underlying task.

Storybook verification

selection

Capability ID: companies/selection.

Scope: ui Storybook: Company list/create/switcher; empty, loading, error, unavailable company and switched navigation. Production: Switch and reload between companies; verify tasks/agents/cache/routes remain scoped and unauthorized company requests fail. Sources: Source: Companies.tsx, CompanySwitcher.tsx, CompanyContext.tsx. Tests: Companies.test.tsx, CompanyContext.test.tsx, companies-route-cross-company-authz.test.ts

archive

Capability ID: companies/archive.

Scope: ui Storybook: Archive confirmation, pending/error and departure navigation; archived list entry and Unarchive action. Production: Archive eligible agents/runs without deleting history; restoration handles archival-specific pause and navigates to correct company. Sources: Source: CompanySettings.tsx, Companies.tsx, companies.ts. Tests: CompanySettingsArchive.test.tsx, Companies.test.tsx, companies-service.test.ts

portability

Capability ID: companies/portability.

Scope: ui Storybook: Import/export preview, conflict choice, warnings, async progress/failure/success and restricted managed deployment. Production: Apply real small package to disposable target; inspect counts/references/conflicts, source immutability and credential exclusions; imported task requires separate runnable-account proof. Sources: Source: CompanyImport.tsx, CompanyExport.tsx, companies.ts. Tests: CompanyImport.test.tsx, CompanyExport.test.tsx, company-portability-routes.test.ts, company-import-export-e2e.test.ts

Documentation scope: Company and instance administration

Core administration/import/export/operator workflows are mapped; cloud/self-hosted differences, migration/restore compatibility, and platform-specific service variants need deeper recipes.

agent-observability

Use Company Settings → General → Agent observability. Select Braintrust or Custom OTLP, save credentials and capture settings, then test the saved destination. Saving is offline; the test originates at the control plane and does not prove remote runner reachability.

Automated: shared validation, encrypted configuration service, receiver tests, runtime projection, and production settings stories cover their respective boundaries. Provider delivery requires a real run.

Manual: configure a disposable company, reload, test, run Codex and Claude Code locally and remotely, inspect their unique markers at the destination, then disable and verify a new marker is absent.

Storybook verification: agent-observability-01-settings, agent-observability-02-states, and agent-observability-03-journey mount production subjects with simulated APIs/providers.

prompt-injection-prevention

Capability ID: companies/prompt-injection-prevention.

Scope: ui, api, runtime Storybook: Production PromptInjectionPreventionSettingsView states under Companies and portability → Prompt Injection Prevention. Provider data is simulated. Automated: settings, service, gateway, guards including redaction that hides content still delivered under the existing return contract. Manual: Open Connections with Fast Responses off, save a shared OpenRouter connection/default model, reload, run both fixed samples, and inspect charges. Verify benign code reaches a gateway caller, malicious instructions are blocked, provider failure records regex fallback, and disabling makes no model call. Root results with concealed instruction text use input_redaction_mismatch fallback without model dispatch.