mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-10-25 17:45:53 +01:00
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work > - Governed MCP access spans contracts, runtime enforcement, adapters, UI surfaces, and operator verification > - The parity reference PR #9534 is too large for effective automated or human review > - The feature therefore needs a linear stack whose individual diffs stay below the 100-file review limit > - This pull request is split 8/8 and focuses on end-to-end coverage, operator docs, evals, and release notes > - The benefit is a standalone, testable review boundary while preserving byte-for-byte parity at the top of the stack ## Linked Issues or Issue Description - Related parity reference: #9534 - Problem: The complete stack needs discoverable browser scenarios, operator guidance, threat modeling, eval coverage, and a parity proof before merge. - Proposed solution: Adds MCP user-story and Smoke Lab e2e suites, docs/evals/release notes, the skill update, and the root e2e driver script registration. - Alternatives considered: keeping #9534 as one 403-file review, or rewriting the feature to manufacture seams; both were rejected in favor of path extraction plus compile-driven boundary moves. - Roadmap alignment: this advances the existing governed MCP/tool-access work already represented by #9534; it does not introduce a separate roadmap initiative. - Stack position: base branch is `pap10341-split/07-ui-apps-activation`. - Merge policy: merge bottom-up, in order, only after the complete eight-PR stack has been reviewed and the top-of-stack parity gate remains empty. - Requested review: QA for flag audit and e2e/browser acceptance; Greptile on every PR. ## What Changed - Adds MCP user-story and Smoke Lab e2e suites, docs/evals/release notes, the skill update, and the root e2e driver script registration. - Keeps this PR below 100 changed files and independently typecheckable. - Preserves the final tree from #9534 when combined with the other seven stack levels. ## Verification - `pnpm typecheck` - `node --check scripts/e2e-mcp-user-stories.mjs` - `pnpm exec playwright test --config tests/e2e/playwright.config.ts --list` — 43 tests discovered - `git diff pap10341-split/08-e2e-docs 6b40e3876d9297105d4ec306e47e46d351c86172` — empty (0 bytes) ## Risks - Browser suites depend on runtime services and environment setup; this PR validates discovery locally while QA owns full flag-on/flag-off execution. - Stack risk: merging out of order can expose incomplete layers; mitigate by following the documented bottom-up merge policy. - Parity risk: later edits to an intermediate branch can drift from #9534; mitigate by re-running the empty top-of-stack diff before merge. > 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, exact model ID `gpt-5.4`; runtime-managed context window; medium reasoning with repository, shell, Git, GitHub CLI, and code-execution tools enabled. ## 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] Internal references are omitted except the execution-plan link explicitly required for this coordinated split stack - [x] My branch name describes the change and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [ ] 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 ## Stack Coordination - Internal execution plan: [PAP-13874](/PAP/issues/PAP-13874#document-plan) - Parity reference: #9534 - Stack: #9556 → #9557 → #9558 → #9559 → #9560 → #9561 → #9562 → #9563 - Merge bottom-up only after full-stack review and an empty parity diff at #9563. --------- Co-authored-by: Paperclip <noreply@paperclip.ing>
176 lines
6.7 KiB
TypeScript
176 lines
6.7 KiB
TypeScript
export type SmokeRunStepPath = "P1" | "P2" | "P3" | "P4" | "P5" | "P6" | "P7";
|
|
|
|
export type SmokeLabScenarioStatus = "ci_safe" | "headed_full";
|
|
|
|
export type SmokeLabTransport = "remote_http" | "local_stdio" | "plugin" | "prosumer_import" | "gateway_session" | "governance";
|
|
|
|
export interface SmokeLabLifecycleTool {
|
|
name: string;
|
|
parameters: Record<string, unknown>;
|
|
}
|
|
|
|
export interface SmokeLabScenario {
|
|
path: SmokeRunStepPath;
|
|
title: string;
|
|
transport: SmokeLabTransport;
|
|
authMode: "oauth" | "api_key" | "none" | "plugin_install" | "config_import" | "run_scoped_token" | "policy";
|
|
smokeService: string;
|
|
status: SmokeLabScenarioStatus;
|
|
ciSafe: boolean;
|
|
uiEntryPath: "apps" | "advanced" | "review" | "activity" | "attention";
|
|
lifecycle: {
|
|
connect: string;
|
|
discoverCatalog: string;
|
|
allowedRead: SmokeLabLifecycleTool;
|
|
askFirstWrite: SmokeLabLifecycleTool;
|
|
deniedCall: SmokeLabLifecycleTool;
|
|
schemaChangeQuarantine: SmokeLabLifecycleTool;
|
|
revoke: string;
|
|
auditEvidence: string;
|
|
};
|
|
}
|
|
|
|
const httpLifecycle = {
|
|
allowedRead: { name: "todo.list", parameters: {} },
|
|
askFirstWrite: { name: "todo.add", parameters: { title: "Smoke Lab approved write" } },
|
|
deniedCall: { name: "email.send", parameters: { to: "smoke@example.test", subject: "Denied", body: "Denied smoke call" } },
|
|
schemaChangeQuarantine: { name: "fixture.schemaFlip", parameters: { toolName: "kv.set" } },
|
|
};
|
|
|
|
const stdioLifecycle = {
|
|
allowedRead: { name: "time.now", parameters: {} },
|
|
askFirstWrite: { name: "slow.ping", parameters: { delayMs: 1 } },
|
|
deniedCall: { name: "crash.now", parameters: {} },
|
|
schemaChangeQuarantine: { name: "malicious.metadata", parameters: {} },
|
|
};
|
|
|
|
export const smokeLabScenarios: SmokeLabScenario[] = [
|
|
{
|
|
path: "P1",
|
|
title: "Remote HTTP MCP connection, OAuth",
|
|
transport: "remote_http",
|
|
authMode: "oauth",
|
|
smokeService: "HTTP MCP fixture + fake OAuth provider",
|
|
status: "ci_safe",
|
|
ciSafe: true,
|
|
uiEntryPath: "apps",
|
|
lifecycle: {
|
|
connect: "Start fake OAuth and HTTP MCP fixture services, then use the installed HTTP fixture connection as the OAuth-backed remote MCP path.",
|
|
discoverCatalog: "Verify the HTTP fixture catalog is visible through Paperclip.",
|
|
...httpLifecycle,
|
|
revoke: "Disable the active fixture connection and re-enable it for subsequent catalog paths.",
|
|
auditEvidence: "Activity and gateway audit rows show the allowed, approved, denied, quarantine, and revoke decisions.",
|
|
},
|
|
},
|
|
{
|
|
path: "P2",
|
|
title: "Remote HTTP MCP connection, API key",
|
|
transport: "remote_http",
|
|
authMode: "api_key",
|
|
smokeService: "HTTP MCP fixture with static fixture credential",
|
|
status: "ci_safe",
|
|
ciSafe: true,
|
|
uiEntryPath: "apps",
|
|
lifecycle: {
|
|
connect: "Install the HTTP fixture with fixture credential metadata.",
|
|
discoverCatalog: "Verify API-key-backed HTTP fixture catalog entries.",
|
|
...httpLifecycle,
|
|
revoke: "Disable the active fixture connection and re-enable it for subsequent catalog paths.",
|
|
auditEvidence: "Audit rows preserve API-key path decisions without exposing the credential.",
|
|
},
|
|
},
|
|
{
|
|
path: "P3",
|
|
title: "Local stdio MCP template",
|
|
transport: "local_stdio",
|
|
authMode: "none",
|
|
smokeService: "stdio MCP fixture template",
|
|
status: "ci_safe",
|
|
ciSafe: true,
|
|
uiEntryPath: "advanced",
|
|
lifecycle: {
|
|
connect: "Install the approved stdio template fixture.",
|
|
discoverCatalog: "Verify template catalog entries are visible.",
|
|
...stdioLifecycle,
|
|
revoke: "Disable the stdio fixture connection and re-enable it for subsequent catalog paths.",
|
|
auditEvidence: "Runtime/activity evidence attributes stdio fixture decisions.",
|
|
},
|
|
},
|
|
{
|
|
path: "P4",
|
|
title: "Plugin-provided integration",
|
|
transport: "plugin",
|
|
authMode: "plugin_install",
|
|
smokeService: "Smoke Lab fixture application standing in for plugin-provided catalog",
|
|
status: "ci_safe",
|
|
ciSafe: true,
|
|
uiEntryPath: "apps",
|
|
lifecycle: {
|
|
connect: "Exercise the catalog-backed app install path used by plugin-provided integrations.",
|
|
discoverCatalog: "Verify plugin-style application catalog entries are visible.",
|
|
...stdioLifecycle,
|
|
revoke: "Disable the plugin-style fixture connection and re-enable it for subsequent catalog paths.",
|
|
auditEvidence: "Activity rows preserve app install and lifecycle decisions.",
|
|
},
|
|
},
|
|
{
|
|
path: "P5",
|
|
title: "Paste-a-config / run-your-own import",
|
|
transport: "prosumer_import",
|
|
authMode: "config_import",
|
|
smokeService: "HTTP MCP fixture imported through advanced configuration",
|
|
status: "ci_safe",
|
|
ciSafe: true,
|
|
uiEntryPath: "advanced",
|
|
lifecycle: {
|
|
connect: "Exercise the advanced run-your-own configuration surface with the HTTP fixture.",
|
|
discoverCatalog: "Verify imported configuration catalog entries.",
|
|
...httpLifecycle,
|
|
revoke: "Disable the imported fixture connection and re-enable it for subsequent catalog paths.",
|
|
auditEvidence: "Advanced activity rows show import and governed calls.",
|
|
},
|
|
},
|
|
{
|
|
path: "P6",
|
|
title: "Token broker / gateway session",
|
|
transport: "gateway_session",
|
|
authMode: "run_scoped_token",
|
|
smokeService: "Tool gateway session over Smoke Lab HTTP fixture",
|
|
status: "ci_safe",
|
|
ciSafe: true,
|
|
uiEntryPath: "activity",
|
|
lifecycle: {
|
|
connect: "Create a run-scoped gateway session for a smoke agent.",
|
|
discoverCatalog: "List gateway-visible tools through the session token.",
|
|
...httpLifecycle,
|
|
revoke: "Revoke the gateway session and verify the token is cut off.",
|
|
auditEvidence: "Gateway audit rows show session creation, discovery, calls, and revocation.",
|
|
},
|
|
},
|
|
{
|
|
path: "P7",
|
|
title: "Governance surfaces",
|
|
transport: "governance",
|
|
authMode: "policy",
|
|
smokeService: "Profiles, ask-first policies, block policies, and quarantine fixtures",
|
|
status: "ci_safe",
|
|
ciSafe: true,
|
|
uiEntryPath: "review",
|
|
lifecycle: {
|
|
connect: "Install fixture connections and profile bindings.",
|
|
discoverCatalog: "Verify profile-governed catalog entries.",
|
|
...httpLifecycle,
|
|
revoke: "Revoke the temporary trust/policy changes.",
|
|
auditEvidence: "Review and Activity expose ask-first, block, quarantine, and revoke evidence.",
|
|
},
|
|
},
|
|
];
|
|
|
|
export function smokeLabScenarioByPath(path: SmokeRunStepPath): SmokeLabScenario {
|
|
const scenario = smokeLabScenarios.find((candidate) => candidate.path === path);
|
|
if (!scenario) throw new Error(`Unknown Smoke Lab scenario path: ${path}`);
|
|
return scenario;
|
|
}
|
|
|
|
export const ciSmokeLabScenarios = smokeLabScenarios.filter((scenario) => scenario.ciSafe);
|