[codex] Improve transient recovery and Codex model refresh (#4383)

## 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>
This commit is contained in:
Dotta 2026-04-24 09:40:40 -05:00 committed by GitHub
parent 4fdbbeced3
commit 8f1cd0474f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
25 changed files with 1455 additions and 48 deletions

View file

@ -7,8 +7,11 @@ import {
companies,
companySkills,
createDb,
documents,
documentRevisions,
heartbeatRuns,
issueComments,
issueDocuments,
issueExecutionDecisions,
issueReadStates,
issues,
@ -43,6 +46,8 @@ describeEmbeddedPostgres("cleanup removal services", () => {
await db.delete(issueReadStates);
await db.delete(issueComments);
await db.delete(issueExecutionDecisions);
await db.delete(documentRevisions);
await db.delete(documents);
await db.delete(companySkills);
await db.delete(heartbeatRuns);
await db.delete(issues);
@ -148,6 +153,8 @@ describeEmbeddedPostgres("cleanup removal services", () => {
it("removes issue read states and activity rows before deleting the company", async () => {
const { companyId, issueId, runId } = await seedFixture();
const documentId = randomUUID();
const revisionId = randomUUID();
await db.insert(issueReadStates).values({
id: randomUUID(),
@ -177,11 +184,47 @@ describeEmbeddedPostgres("cleanup removal services", () => {
details: {},
});
await db.insert(documents).values({
id: documentId,
companyId,
title: "Run summary",
latestBody: "body",
latestRevisionId: revisionId,
latestRevisionNumber: 1,
createdByAgentId: null,
createdByUserId: "user-1",
updatedByAgentId: null,
updatedByUserId: "user-1",
});
await db.insert(issueDocuments).values({
id: randomUUID(),
companyId,
issueId,
documentId,
key: "summary",
});
await db.insert(documentRevisions).values({
id: revisionId,
companyId,
documentId,
revisionNumber: 1,
title: "Run summary",
format: "markdown",
body: "body",
createdByAgentId: null,
createdByUserId: "user-1",
createdByRunId: runId,
});
const removed = await companyService(db).remove(companyId);
expect(removed?.id).toBe(companyId);
await expect(db.select().from(companies).where(eq(companies.id, companyId))).resolves.toHaveLength(0);
await expect(db.select().from(issues).where(eq(issues.id, issueId))).resolves.toHaveLength(0);
await expect(db.select().from(documents).where(eq(documents.id, documentId))).resolves.toHaveLength(0);
await expect(db.select().from(documentRevisions).where(eq(documentRevisions.id, revisionId))).resolves.toHaveLength(0);
await expect(db.select().from(issueReadStates).where(eq(issueReadStates.companyId, companyId))).resolves.toHaveLength(0);
await expect(db.select().from(activityLog).where(eq(activityLog.companyId, companyId))).resolves.toHaveLength(0);
});