## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - The Paperclip Runner provides durable, provider-neutral agent execution. > - The current stack supports qualified local providers but omits the managed provider paths from the integration branch. > - Claude Managed Agents and AWS AgentCore need explicit profile qualification, durable recovery, usage accounting, and cleanup controls. > - This pull request adds those managed backends as the third part of the Runner parity stack. > - The benefit is managed execution without weakening the default-off Runner rollout gate. ## Linked Issues or Issue Description **Subsystem affected** Cross-cutting: Runner, server orchestration, database profiles, CLI, and adapter configuration UI. **Problem or motivation** The current Runner stack cannot select or execute the managed Claude Agents API or AWS Bedrock AgentCore Harness backends. It also lacks qualified profile storage and recovery checks for those remote resources. **Proposed solution** Add qualified managed and remote profiles, API and CLI management, exact provider selection, durable lifecycle handling, cumulative usage accounting, bounded cleanup, and retention acknowledgement. Keep `enableNativeRunner` default-off. **Alternatives considered** A direct copy of the old integration branch was rejected because its provider contracts, model values, credential flow, and migration history no longer match the current base. A single large parity pull request was also rejected because stacked review keeps each subsystem bounded. **Roadmap alignment** This continues the existing Runner architecture and rollout work. It does not introduce a separate execution system. **Additional context** This pull request is based on the merged #12691 and #12685 stack. It also closes the delayed security-review findings reported on #12691 by binding qualified ACPX and OpenCode launch artifacts to the bytes actually executed. A GitHub search for managed agent, AgentCore, and Claude managed work found no duplicate public issue or pull request. ## What Changed - Add Claude Managed Agents and AWS AgentCore provider executors to runnerd. - Add qualified managed and remote profile storage, routes, OpenAPI contracts, CLI commands, and migration 0237. - Validate profile ownership, enabled state, exact qualified revision, model, agent version, and secret binding before persistence and recovery. - Persist durable provider session and owned skill state for restart-safe cleanup. - Reconcile uncertain create responses and delete remote sessions before owned skills. - Track cumulative provider usage and enforce positive session spend caps. - Recover interrupted AgentCore usage at the next turn boundary by charging the prior invocation ceiling exactly once; keep the session gated until an explicit monotonic budget raise. - Isolate AgentCore AWS configuration from host profiles and credential-process/SSO configuration while preserving workload identity. - Require OpenCode 1.18.17 and fixed build-owned provider-pack artifact paths; remove the ambient executable override. - Snapshot and content-verify ACPX and OpenCode commands, scripts, and provider executables before launch. Linux executes sealed inherited descriptors; macOS uses authenticated private snapshots with retry-safe rematerialization at the spawn boundary. - Persist canonical ACPX and OpenCode launch-profile digests, reject drift across fresh recovery, and make recovery failures sticky. - Close and journal unsafe ACPX active-turn recovery before any provider bootstrap or reconnect. - Add managed provider fields to the Runner configuration UI and permission projection. - Preserve the default-off `enableNativeRunner` experimental flag. ## Verification - `pnpm -r typecheck` - `pnpm build` - Focused managed server, database, CLI, Runner TypeScript, Rust, Claude, AgentCore, ACPX, OpenCode, process-supervisor, and durable-recovery tests passed. - `cargo test -p paperclip-runner-core --lib --locked` (160 tests) - `cargo check --workspace --all-targets --locked` - Native Codex integration tests passed (60 tests); native provider tests passed (7 tests); server native-runtime tests passed (87 tests). - Verified-launch replacement, nested-spawn retry, exact-version, profile-drift, sticky-failure, and no-bootstrap active-recovery tests passed. - `git diff --check` - The PR changes 91 files. `pnpm-lock.yaml` is unchanged. The Rust workspace lockfile adds the approved `rustix` dependency used for safe descriptor handling while `#![forbid(unsafe_code)]` remains enabled. ## Risks - The provider APIs can change while they are in beta. Exact qualification and fail-closed recovery checks limit drift. - Remote cleanup can fail after a partial create. Durable ownership inventories and retry-safe deletion preserve recovery state. - Migration 0237 adds profile tables. The generated migration and snapshot pass the repository migration checks. - Managed execution can incur provider cost. Positive default spend caps and explicit retention acknowledgement limit accidental use. - An interrupted AgentCore invocation without final metadata is conservatively charged to its active session ceiling. This can overstate cost, but cannot undercount it; later work requires an explicit budget increase. - Linux qualified launches use sealed memory descriptors. macOS lacks executable-descriptor APIs, so the runner uses owner-only private snapshots and minimizes linked-path lifetime; hostile same-UID processes remain outside the documented local-host trust boundary. - The global Runner feature remains default-off. > 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, GPT-5, with tool use, code execution, and subagent review. ## 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 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
9.0 KiB
Paperclip Runner compatibility and rollout
- Status: Proposed
- Date: 2026-08-24
- Parent decision: Paperclip Runner architecture
Purpose
This document defines compatibility rules for introducing the experimental Paperclip Runner. These rules are acceptance criteria for each implementation change. They are not a migration plan for existing adapters.
Compatibility invariants
- Existing adapter selection is authoritative. A direct adapter stays direct.
- A non-runner run must not start runnerd or open PRP.
- A non-runner run must not create native result, finalization, status-decision, or runner-transport records.
- A non-runner run must not invoke native status arbitration.
- Direct adapters keep their current transcript, interaction, cancellation, result, and finalization behavior.
- Runner-only UI controls depend on persisted runtime facts and are absent from direct runs.
- The rollout flag controls fresh runner selection and fresh runner starts.
- A flag change does not rewrite an agent profile or a persisted run choice.
- Persisted native data remains readable after the flag is disabled.
- Recovery may finish an already persisted native run while fresh native starts remain blocked.
Runtime selection
The server resolves and persists the runtime once, before provider launch.
| Persisted runtime | Adapter | Flag | Result |
|---|---|---|---|
| none | Any direct adapter | off or on | Use the existing direct path. |
| none | paperclip_runner with any qualified provider |
off | Reject the fresh start with a stable rollout-disabled error. |
| none | paperclip_runner with a qualified provider |
on | Use PRP v1 and the provider's persisted runnerd backend. |
| none | paperclip_runner with an incomplete or unqualified profile |
on | Reject the profile before runnerd starts. |
| direct | Any | changed later | Keep the persisted direct path. |
| native | Any | changed later | Keep the persisted native path for read, cancel, recovery, and finalization. |
The server must not fall back from a selected paperclip_runner start to
codex_local. A configuration or rollout error must be visible. Silent fallback
would hide the runtime that executed the task.
Direct adapter boundary
This rule applies to every built-in and plugin direct adapter. It includes:
codex_local;claude_local;opencode_local;- other local CLI or session adapters;
- process and HTTP adapters;
- gateway adapters; and
- external adapter plugins.
Adding Paperclip Runner must not add runner imports or runner branches inside a direct adapter implementation. The heartbeat coordinator may select the explicit runner adapter at one narrow seam. All other adapters continue through their existing code.
For a flag-off codex_local heartbeat, compatibility proof must show:
- one direct invocation;
- the same normalized result and finalization bytes as the approved baseline;
- zero runner processes;
- zero PRP connections; and
- zero native rows.
Configuration behavior
When the rollout flag is off:
- creation UI does not offer
paperclip_runner; - edit UI does not offer switching to
paperclip_runner; - server creation and import reject a new
paperclip_runnerselection; - the server rejects a fresh start for an existing runner-configured agent;
- read and export preserve an existing runner configuration;
- unrelated edits to an existing runner-configured agent do not erase its configuration; and
- switching that agent to a direct adapter remains allowed.
When the rollout flag is on:
- creation, import, and edit accept
paperclip_runneronly with a qualified Codex, OpenCode, Claude Managed, AWS AgentCore, or Claude/Codex ACPX profile; - switching from a direct adapter affects only future unresolved runs; and
- switching away from the runner affects only future unresolved runs.
Server validation is the authority in both states. Import files and API clients cannot bypass the flag or provider allowlist.
Persisted native runs
The following data remains readable independent of the current flag:
- the persisted runtime selection and reason;
- run, runner, session, turn, and provider identity;
- ordered runner and provider events;
- accepted result and evidence assessment;
- finalization coordinator and status decision;
- usage, cost, cancellation, and terminal details; and
- durable interactions and final task-thread reply.
If the flag is disabled during an in-flight native run, the server may reconnect, cancel, reconcile, and finalize that same run. It must not use that recovery as authority to start a new native run.
Recovery must remain idempotent. Repeating it cannot add a second final reply, interaction, wake, status decision, or application effect.
Task-page compatibility
The task page uses one provider-neutral thread projection. Runtime facts may add runner event groups, semantic receipts, usage, and structured questions. They must not replace classic direct-adapter content.
Direct-adapter coverage must include:
- an active run;
- a settled run;
- an empty transcript;
- a pending interaction;
- a resolved interaction; and
- the classic interface state.
The existing composer remains usable for direct adapters. A direct run does not show reconnect, runner cancel, semantic receipt, or other runner-only controls. Final replies continue to use the existing issue-comment behavior.
Structured input compatibility
New structured questions use paperclip.question_set.v1 and the matching
response contract. Provider-specific question objects remain inside their
drivers.
Legacy unstructured interaction records remain readable and resolvable. A structured form fails closed when its required schema, question mode, question ID, option ID, or response value is invalid. The implementation must not silently convert malformed structured input to a legacy text prompt.
Protocol version compatibility
PRP wire versions, fixture versions, event schema versions, and typed schema discriminators are independently versioned.
- Peers negotiate the highest common PRP version.
- No common required version fails closed before command or provider execution.
- An unknown required fixture or event schema version fails closed.
- An unknown required typed discriminator fails closed.
- Additive optional properties remain compatible only when an old v1 consumer can ignore them without changing behavior.
- Unknown object properties must survive validation when the owning schema permits additive fields.
Breaking meaning requires a new required version. A provider error is not a protocol negotiation result.
Semantic action compatibility
Catalog generation and production authorization are separate steps.
- A catalog entry does not authorize production use.
- An operation without a production binding is undiscoverable.
- An operation denied to the run is undiscoverable unless the protocol explicitly defines a safe denied receipt for that discovery mode.
- A duplicate call with the same idempotency key and canonical input returns the original safe receipt.
- Reusing the key with different input returns a conflict and performs no second effect.
- Receipts redact credentials, private provider payloads, and hidden identity.
Required compatibility matrix
Each runner-related pull request updates only rows that it can execute. The complete first-wave matrix must cover:
| Area | Required cases |
|---|---|
| Runtime selection | Every built-in direct adapter, explicit runner selection, unsupported provider, flag on, and flag off. |
| Direct regression | Flag-off codex_local invocation count, byte-stable result/finalization, and zero native rows. |
| Configuration | Enabled and disabled create, import, edit, read, export, and adapter switch. |
| Recovery | Persisted native run after flag disable, reconnect, duplicate event, duplicate command, cancellation, and server restart. |
| Protocol security | Cross-company binding, ticket replay, ticket expiry, malformed frame, unsupported version, and revoked lease. |
| Semantic actions | Discovery denial, unbound action, duplicate call, conflicting retry, redaction, and governed action. |
| Task page | Active, settled, empty transcript, interaction, and classic direct-adapter states. |
| Structured input | Valid response, malformed response, stale response, duplicate response, provider loss, and cancellation. |
Pull request acceptance
Every implementation pull request must:
- build and work against its declared base;
- keep its changed-file count below 100;
- update manifests and exports only for implemented surfaces;
- run the smallest relevant tests before the repository handoff gate;
- run typecheck, tests, and build for handoff;
- run protocol parity, Cargo, clean-consumer, migration, token, and browser gates when those areas change;
- contain no unexplained failed, cancelled, or path-skipped verification; and
- resolve actionable review and security findings before it is ready.
Generated files land with their source and a drift check. pnpm-lock.yaml is
owned by CI and is not part of these pull requests.