## Thinking Path
> - Paperclip orchestrates AI agents for zero-human companies
> - Adapter execution and retry classification decide whether agent work
pauses, retries, or recovers automatically
> - Transient provider failures need to be classified precisely so
Paperclip does not convert retryable upstream conditions into false hard
failures
> - At the same time, operators need an up-to-date model list for
Codex-backed agents and prompts should nudge agents toward targeted
verification instead of repo-wide sweeps
> - This pull request tightens transient recovery classification for
Claude and Codex, updates the agent prompt guidance, and adds Codex
model refresh support end-to-end
> - The benefit is better automatic retry behavior plus fresher
operator-facing model configuration
## What Changed
- added Codex usage-limit retry-window parsing and Claude extra-usage
transient classification
- normalized the heartbeat transient-recovery contract across adapter
executions and heartbeat scheduling
- documented that deferred comment wakes only reopen completed issues
for human/comment-reopen interactions, while system follow-ups leave
closed work closed
- updated adapter-utils prompt guidance to prefer targeted verification
- added Codex model refresh support in the server route, registry,
shared types, and agent config form
- added adapter/server tests covering the new parsing, retry scheduling,
and model-refresh behavior
## Verification
- `pnpm exec vitest run --project @paperclipai/adapter-utils
packages/adapter-utils/src/server-utils.test.ts`
- `pnpm exec vitest run --project @paperclipai/adapter-claude-local
packages/adapters/claude-local/src/server/parse.test.ts`
- `pnpm exec vitest run --project @paperclipai/adapter-codex-local
packages/adapters/codex-local/src/server/parse.test.ts`
- `pnpm exec vitest run --project @paperclipai/server
server/src/__tests__/adapter-model-refresh-routes.test.ts
server/src/__tests__/adapter-models.test.ts
server/src/__tests__/claude-local-execute.test.ts
server/src/__tests__/codex-local-execute.test.ts
server/src/__tests__/heartbeat-process-recovery.test.ts
server/src/__tests__/heartbeat-retry-scheduling.test.ts`
## Risks
- Moderate behavior risk: retry classification affects whether runs
auto-recover or block, so mistakes here could either suppress needed
retries or over-retry real failures
- Low workflow risk: deferred comment wake reopening is intentionally
scoped to human/comment-reopen interactions so system follow-ups do not
revive completed issues unexpectedly
> 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-based coding agent with tool use and code execution
in the Codex CLI environment
## 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 run tests locally and they pass
- [x] I have added or updated tests where applicable
- [ ] If this change affects the UI, I have included before/after
screenshots
- [ ] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] I will address all Greptile and reviewer comments before
requesting merge
---------
Co-authored-by: Paperclip <noreply@paperclip.ing>
- Plugin loader: install/reload/remove/reinstall external adapters
from npm packages or local directories
- Plugin store persisted at ~/.paperclip/adapter-plugins.json
- Self-healing UI parser resolution with version caching
- UI: Adapter Manager page, dynamic loader, display registry
with humanized names for unknown adapter types
- Dev watch: exclude adapter-plugins dir from tsx watcher
to prevent mid-request server restarts during reinstall
- All consumer fallbacks use getAdapterLabel() for consistent display
- AdapterTypeDropdown uses controlled open state for proper close behavior
- Remove hermes-local from built-in UI (externalized to plugin)
- Add docs for external adapters and UI parser contract
Rename all workspace packages from @paperclip/* to @paperclipai/* and
the CLI binary from `paperclip` to `paperclipai` in preparation for
npm publishing. Bump CLI version to 0.1.0 and add package metadata
(description, keywords, license, repository, files). Update all
imports, documentation, user-facing messages, and tests accordingly.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Introduce testEnvironment() on ServerAdapterModule with structured
pass/warn/fail diagnostics for all four adapter types (claude_local,
codex_local, process, http). Adds POST test-environment endpoint,
shared types/validators, adapter test implementations, and UI API
client. Includes asset type foundations used by related features.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Introduce AdapterSessionCodec interface for structured session serialization,
deserialization, and display ID extraction. Implement codecs for claude_local
and codex_local adapters with cwd validation — sessions saved for a different
working directory are not resumed. Both adapters now return sessionParams and
sessionDisplayId alongside legacy sessionId.
Add isCodexUnknownSessionError detection and automatic retry with fresh session
for codex_local (matching existing claude_local behavior). Inject approval
context env vars (PAPERCLIP_APPROVAL_ID, PAPERCLIP_APPROVAL_STATUS,
PAPERCLIP_LINKED_ISSUE_IDS) into adapter environments.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Agent management: hire endpoint with permission gates and pending_approval status,
config revision tracking with rollback, agent duplicate route, permission CRUD.
Block pending_approval agents from auth, heartbeat, and assignments.
Approvals: revision request/resubmit flow, approval comments CRUD, issue-approval
linking, auto-wake agents on approval decisions with context snapshot.
Costs: per-agent breakdown, period filtering (month/week/day/all), cost by agent
list endpoint.
Adapters: agentConfigurationDoc on all adapters, /llms/agent-configuration.txt
reflection routes. Inject PAPERCLIP_APPROVAL_ID, PAPERCLIP_APPROVAL_STATUS,
PAPERCLIP_LINKED_ISSUE_IDS into adapter environments.
Sidebar badges endpoint for pending approval/inbox counts. Dashboard and company
settings extensions.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Extract claude-local and codex-local adapter code from cli/server/ui
into packages/adapters/ and packages/adapter-utils/. CLI, server, and
UI now import shared adapter logic instead of duplicating it. Removes
~1100 lines of duplicated code across packages. Register new packages
in pnpm workspace.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Refactor monolithic heartbeat service, AgentConfigForm, and CLI
heartbeat-run into a proper adapter registry pattern. Each adapter
type (process, claude-local, codex-local, http) gets its own module
with server-side execution logic, CLI invocation, and UI config form.
Significantly reduces file sizes and enables adding new adapters
without touching core code.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
