## 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
3.4 KiB
Live console: Run the Protocol Demo Server
What this is
This tutorial runs the Live console server layer. It has no browser UI yet. You can
use curl to act like the browser.
The server starts Codex. Codex login data stays on the server. The JSON replies must not contain a Paperclip key, an OpenAI key, or a bearer value.
Step 1: Run deterministic checks
From the repository root, run:
pnpm --filter @paperclipai/paperclip-runner exec vitest run \
src/drivers/codex/codex-app-server-driver.test.ts \
src/mock-core/live-console-demo-server.test.ts
Expected result: both files pass. The tests cover requests, goals, lineage, steering, interrupt races, reconnect, replay, and redaction.
Step 2: Start the server
Use an empty directory outside your Codex home:
liveConsole_workspace="$(mktemp -d)"
pnpm --filter @paperclipai/paperclip-runner demo:live-console -- \
--host 127.0.0.1 \
--port 4174 \
--working-directory "$liveConsole_workspace"
Keep this terminal open. The first output line is JSON. It names the host,
port, and server-owned working directory. It also says
"credentialsExposed":false.
Step 3: Check the boundary
In a second terminal, run:
curl -s http://127.0.0.1:4174/api/liveConsole/health \
-H 'Origin: http://127.0.0.1:4174' \
-H 'Sec-Fetch-Site: same-origin' | jq
Expected facts:
statusisok;boundaryispackage-local-mock-core;providerAuthenticationisserver-side; andcredentialsExposedisfalse.
Step 4: Start one safe session
curl -s -X POST http://127.0.0.1:4174/api/liveConsole/sessions \
-H 'Origin: http://127.0.0.1:4174' \
-H 'Sec-Fetch-Site: same-origin' \
-H 'content-type: application/json' \
--data '{"objective":"Create demo.txt with exactly: liveConsole demo","message":"Complete and verify the exact file task."}' \
| tee "$liveConsole_workspace/session.json" | jq
Copy sessionId and activeTurnId from the reply. The server ignores a
browser-supplied working directory and rejects browser-supplied credential
fields.
Step 5: Read live or replayed events
session_id="$(jq -r .sessionId "$liveConsole_workspace/session.json")"
curl -s "http://127.0.0.1:4174/api/liveConsole/sessions/$session_id/events?after=0" \
-H 'Origin: http://127.0.0.1:4174' \
-H 'Sec-Fetch-Site: same-origin' | jq
The reply contains canonical PRP events and a cursor. A later request can pass
that cursor as after. The same events go through the same reducer during live
view and replay.
For a live stream, run:
curl -N "http://127.0.0.1:4174/api/liveConsole/sessions/$session_id/stream?after=0" \
-H 'Origin: http://127.0.0.1:4174' \
-H 'Sec-Fetch-Site: same-origin'
Step 6: Reconnect the same session
curl -s -X POST \
"http://127.0.0.1:4174/api/liveConsole/sessions/$session_id/reconnect" \
-H 'Origin: http://127.0.0.1:4174' \
-H 'Sec-Fetch-Site: same-origin' \
-H 'content-type: application/json' --data '{}' | jq
Confirm that runId, normalizedSessionId, driverSessionId, and
providerSessionId did not change. The new events include session.resumed.
The repeated browser headers are intentional admission evidence. DNS-rebinding
Hosts, cross-origin or missing Fetch Metadata, wildcard binds, and simple
text/plain mutations are rejected. This protects the browser boundary, but
untrusted local processes can still make loopback requests; Codex sandbox and
approval policy remain the final execution boundary.