paperclip/server/src/services/companies.ts

327 lines
12 KiB
TypeScript
Raw Normal View History

import { and, count, eq, gte, inArray, lt, sql } from "drizzle-orm";
import type { Db } from "@paperclipai/db";
import {
companies,
2026-03-16 09:25:39 -05:00
companyLogos,
assets,
agents,
agentApiKeys,
agentRuntimeState,
agentTaskSessions,
agentWakeupRequests,
issues,
issueComments,
projects,
goals,
heartbeatRuns,
heartbeatRunEvents,
costEvents,
financeEvents,
2026-04-07 18:20:35 -05:00
issueReadStates,
approvalComments,
approvals,
activityLog,
companySecrets,
joinRequests,
invites,
principalPermissionGrants,
companyMemberships,
2026-04-07 18:20:35 -05:00
companySkills,
[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>
2026-04-24 09:40:40 -05:00
documents,
} from "@paperclipai/db";
2026-03-16 09:25:39 -05:00
import { notFound, unprocessable } from "../errors.js";
Add sandbox environment support (#4415) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies. > - The environment/runtime layer decides where agent work executes and how the control plane reaches those runtimes. > - Today Paperclip can run locally and over SSH, but sandboxed execution needs a first-class environment model instead of one-off adapter behavior. > - We also want sandbox providers to be pluggable so the core does not hardcode every provider implementation. > - This branch adds the Sandbox environment path, the provider contract, and a deterministic fake provider plugin. > - That required synchronized changes across shared contracts, plugin SDK surfaces, server runtime orchestration, and the UI environment/workspace flows. > - The result is that sandbox execution becomes a core control-plane capability while keeping provider implementations extensible and testable. ## What Changed - Added sandbox runtime support to the environment execution path, including runtime URL discovery, sandbox execution targeting, orchestration, and heartbeat integration. - Added plugin-provider support for sandbox environments so providers can be supplied via plugins instead of hardcoded server logic. - Added the fake sandbox provider plugin with deterministic behavior suitable for local and automated testing. - Updated shared types, validators, plugin protocol definitions, and SDK helpers to carry sandbox provider and workspace-runtime contracts across package boundaries. - Updated server routes and services so companies can create sandbox environments, select them for work, and execute work through the sandbox runtime path. - Updated the UI environment and workspace surfaces to expose sandbox environment configuration and selection. - Added test coverage for sandbox runtime behavior, provider seams, environment route guards, orchestration, and the fake provider plugin. ## Verification - Ran locally before the final fixture-only scrub: - `pnpm -r typecheck` - `pnpm test:run` - `pnpm build` - Ran locally after the final scrub amend: - `pnpm vitest run server/src/__tests__/runtime-api.test.ts` - Reviewer spot checks: - create a sandbox environment backed by the fake provider plugin - run work through that environment - confirm sandbox provider execution does not inherit host secrets implicitly ## Risks - This touches shared contracts, plugin SDK plumbing, server runtime orchestration, and UI environment/workspace flows, so regressions would likely show up as cross-layer mismatches rather than isolated type errors. - Runtime URL discovery and sandbox callback selection are sensitive to host/bind configuration; if that logic is wrong, sandbox-backed callbacks may fail even when execution succeeds. - The fake provider plugin is intentionally deterministic and test-oriented; future providers may expose capability gaps that this branch does not yet cover. ## Model Used - OpenAI Codex coding agent on a GPT-5-class backend in the Paperclip/Codex harness. Exact backend model ID is not exposed in-session. Tool-assisted workflow with shell execution, file editing, git history inspection, and local test 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 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 - [x] 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
2026-04-24 12:15:53 -07:00
import { environmentService } from "./environments.js";
export function companyService(db: Db) {
const ISSUE_PREFIX_FALLBACK = "CMP";
Add sandbox environment support (#4415) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies. > - The environment/runtime layer decides where agent work executes and how the control plane reaches those runtimes. > - Today Paperclip can run locally and over SSH, but sandboxed execution needs a first-class environment model instead of one-off adapter behavior. > - We also want sandbox providers to be pluggable so the core does not hardcode every provider implementation. > - This branch adds the Sandbox environment path, the provider contract, and a deterministic fake provider plugin. > - That required synchronized changes across shared contracts, plugin SDK surfaces, server runtime orchestration, and the UI environment/workspace flows. > - The result is that sandbox execution becomes a core control-plane capability while keeping provider implementations extensible and testable. ## What Changed - Added sandbox runtime support to the environment execution path, including runtime URL discovery, sandbox execution targeting, orchestration, and heartbeat integration. - Added plugin-provider support for sandbox environments so providers can be supplied via plugins instead of hardcoded server logic. - Added the fake sandbox provider plugin with deterministic behavior suitable for local and automated testing. - Updated shared types, validators, plugin protocol definitions, and SDK helpers to carry sandbox provider and workspace-runtime contracts across package boundaries. - Updated server routes and services so companies can create sandbox environments, select them for work, and execute work through the sandbox runtime path. - Updated the UI environment and workspace surfaces to expose sandbox environment configuration and selection. - Added test coverage for sandbox runtime behavior, provider seams, environment route guards, orchestration, and the fake provider plugin. ## Verification - Ran locally before the final fixture-only scrub: - `pnpm -r typecheck` - `pnpm test:run` - `pnpm build` - Ran locally after the final scrub amend: - `pnpm vitest run server/src/__tests__/runtime-api.test.ts` - Reviewer spot checks: - create a sandbox environment backed by the fake provider plugin - run work through that environment - confirm sandbox provider execution does not inherit host secrets implicitly ## Risks - This touches shared contracts, plugin SDK plumbing, server runtime orchestration, and UI environment/workspace flows, so regressions would likely show up as cross-layer mismatches rather than isolated type errors. - Runtime URL discovery and sandbox callback selection are sensitive to host/bind configuration; if that logic is wrong, sandbox-backed callbacks may fail even when execution succeeds. - The fake provider plugin is intentionally deterministic and test-oriented; future providers may expose capability gaps that this branch does not yet cover. ## Model Used - OpenAI Codex coding agent on a GPT-5-class backend in the Paperclip/Codex harness. Exact backend model ID is not exposed in-session. Tool-assisted workflow with shell execution, file editing, git history inspection, and local test 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 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 - [x] 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
2026-04-24 12:15:53 -07:00
const environmentsSvc = environmentService(db);
2026-03-16 09:25:39 -05:00
const companySelection = {
id: companies.id,
name: companies.name,
description: companies.description,
status: companies.status,
issuePrefix: companies.issuePrefix,
issueCounter: companies.issueCounter,
budgetMonthlyCents: companies.budgetMonthlyCents,
spentMonthlyCents: companies.spentMonthlyCents,
[codex] Split backend control-plane QoL slice (#4700) ## Thinking Path > - Paperclip is the control plane for autonomous AI companies, so backend task ownership, recovery, review visibility, and company-scoped limits need to stay enforceable without UI-only coupling. > - Closed PR #4692 bundled those backend changes with UI workflow, docs, skills, workflow, and lockfile churn. > - PAP-2694 asks for a clean backend/control-plane slice from that closed branch. > - This branch starts from current `master` and mines only the `cli`, `packages/db`, `packages/shared`, and `server` contracts/tests needed for the backend behavior. > - It explicitly excludes UI workflow/performance work, `.github/workflows/pr.yml`, `pnpm-lock.yaml`, docs, skills, package-script, adapter UI build-config, and perf fixture script changes; the only UI files are fixture/test updates required by the tightened shared `Company` contract. > - The benefit is a smaller reviewable PR that preserves the control-plane fixes while staying under Greptile s 100-file review limit. ## What Changed - Added company-scoped attachment-size limits through DB schema/migrations, shared company portability contracts, CLI import/export coverage, and server attachment upload enforcement. - Added productivity review service/API behavior for no-comment streak, long-active, and high-churn review issues, including request-depth clamping and issue summary exposure. - Hardened issue ownership and recovery/control-plane paths: peer-agent mutation denial, issue tree pause/resume behavior, stranded recovery origins, and related activity/test coverage. - Preserved related backend contract updates for routine timestamp variables and managed agent instruction bundles because they live in shared/server contracts from the source branch. - Addressed Greptile feedback by making `Company.attachmentMaxBytes` non-optional, simplifying review request-depth clamping, fixing the migration final newline, and enforcing the process-level attachment cap as the final ceiling for uploads. - Added minimal company fixtures needed for repo-wide typecheck/build and kept the PR to 66 changed files with forbidden/non-slice paths excluded. ## Verification - `pnpm install --frozen-lockfile` - `git diff --check origin/master..HEAD` - `git diff --name-only origin/master..HEAD | wc -l` -> 66 files - `git diff --name-only origin/master..HEAD -- .github/workflows/pr.yml pnpm-lock.yaml package.json doc skills .agents scripts packages/adapters` -> no output - `pnpm exec vitest run --config vitest.config.ts packages/shared/src/validators/issue.test.ts packages/shared/src/routine-variables.test.ts packages/shared/src/adapter-types.test.ts cli/src/__tests__/company-import-export-e2e.test.ts cli/src/__tests__/company.test.ts server/src/__tests__/productivity-review-service.test.ts server/src/__tests__/issue-tree-control-service.test.ts server/src/__tests__/issue-tree-control-routes.test.ts server/src/__tests__/issue-agent-mutation-ownership-routes.test.ts server/src/__tests__/issue-attachment-routes.test.ts server/src/__tests__/heartbeat-process-recovery.test.ts server/src/__tests__/issues-service.test.ts` -> 12 files, 147 tests passed - `pnpm exec vitest run --config vitest.config.ts cli/src/__tests__/company-delete.test.ts cli/src/__tests__/company-import-export-e2e.test.ts server/src/__tests__/productivity-review-service.test.ts` -> 3 files, 18 tests passed - `pnpm exec vitest run --config vitest.config.ts server/src/__tests__/issue-attachment-routes.test.ts` -> 1 file, 6 tests passed - `pnpm --filter @paperclipai/db typecheck && pnpm --filter @paperclipai/shared typecheck && pnpm --filter @paperclipai/server typecheck && pnpm --filter paperclipai typecheck` - `pnpm --filter @paperclipai/server typecheck` - `pnpm --filter @paperclipai/ui typecheck && pnpm --filter @paperclipai/ui build` ## Risks - Includes migrations `0073_shiny_salo.sql` and `0074_striped_genesis.sql`; merge ordering matters if another PR adds migrations first. - This is intentionally backend-only apart from fixture/test updates forced by shared type correctness; UI affordances from PR #4692 are not present here and should land in separate UI slices. - The worktree install emitted plugin SDK bin-link warnings for unbuilt plugin packages, but the targeted tests and package typechecks completed successfully. > 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 coding agent, tool-enabled terminal/GitHub workflow. Exact runtime context window was not exposed by the harness. ## 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 - [x] If this change affects the UI, I have included before/after screenshots - [x] 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>
2026-04-28 16:46:45 -05:00
attachmentMaxBytes: companies.attachmentMaxBytes,
2026-03-16 09:25:39 -05:00
requireBoardApprovalForNewAgents: companies.requireBoardApprovalForNewAgents,
feedbackDataSharingEnabled: companies.feedbackDataSharingEnabled,
feedbackDataSharingConsentAt: companies.feedbackDataSharingConsentAt,
feedbackDataSharingConsentByUserId: companies.feedbackDataSharingConsentByUserId,
feedbackDataSharingTermsVersion: companies.feedbackDataSharingTermsVersion,
2026-03-16 09:25:39 -05:00
brandColor: companies.brandColor,
logoAssetId: companyLogos.assetId,
createdAt: companies.createdAt,
updatedAt: companies.updatedAt,
};
function enrichCompany<T extends { logoAssetId: string | null }>(company: T) {
return {
...company,
logoUrl: company.logoAssetId ? `/api/assets/${company.logoAssetId}/content` : null,
};
}
function currentUtcMonthWindow(now = new Date()) {
const year = now.getUTCFullYear();
const month = now.getUTCMonth();
return {
start: new Date(Date.UTC(year, month, 1, 0, 0, 0, 0)),
end: new Date(Date.UTC(year, month + 1, 1, 0, 0, 0, 0)),
};
}
async function getMonthlySpendByCompanyIds(
companyIds: string[],
database: Pick<Db, "select"> = db,
) {
if (companyIds.length === 0) return new Map<string, number>();
const { start, end } = currentUtcMonthWindow();
const rows = await database
Sync/master post pap1497 followups 2026 04 15 (#3779) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - The board depends on issue, inbox, cost, and company-skill surfaces to stay accurate and fast while agents are actively working > - The PAP-1497 follow-up branch exposed a few rough edges in those surfaces: stale active-run state on completed issues, missing creator filters, oversized issue payload scans, and placeholder issue-route parsing > - Those gaps make the control plane harder to trust because operators can see misleading run state, miss the right subset of work, or pay extra query/render cost on large issue records > - This pull request tightens those follow-ups across server and UI code, and adds regression coverage for the affected paths > - The benefit is a more reliable issue workflow, safer high-volume cost aggregation, and clearer board/operator navigation ## What Changed - Added the `v2026.415.0` release changelog entry. - Fixed stale issue-run presentation after completion and reused the shared issue-path parser so literal route placeholders no longer become issue links. - Added creator filters to the Issues page and Inbox, including persisted filter-state normalization and regression coverage. - Bounded issue detail/list project-mention scans and trimmed large issue-list payload fields to keep issue reads lighter. - Hardened company-skill list projection and cost/finance aggregation so large markdown blobs and large summed values do not leak into list responses or overflow 32-bit casts. - Added targeted server/UI regression tests for company skills, costs/finance, issue mention scanning, creator filters, inbox normalization, and issue reference parsing. ## Verification - `pnpm exec vitest run server/src/__tests__/company-skills-service.test.ts server/src/__tests__/costs-service.test.ts server/src/__tests__/issues-goal-context-routes.test.ts server/src/__tests__/issues-service.test.ts ui/src/lib/inbox.test.ts ui/src/lib/issue-filters.test.ts ui/src/lib/issue-reference.test.ts` - `gh pr checks 3779` Current pass set on the PR head: `policy`, `verify`, `e2e`, `security/snyk (cryppadotta)`, `Greptile Review` ## Risks - Creator filter options are derived from the currently loaded issue/agent data, so very sparse result sets may not surface every historical creator until they appear in the active dataset. - Cost/finance aggregate casts now use `double precision`; that removes the current overflow risk, but future schema changes should keep large-value aggregation behavior under review. - Issue detail mention scanning now skips comment-body scans on the detail route, so any consumer that relied on comment-only project mentions there would need to fetch them separately. ## Model Used - OpenAI Codex, GPT-5-based coding agent with terminal tool use and local code execution in the Paperclip workspace. Exact internal model ID/context-window exposure is not surfaced in this session. ## 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 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 - [x] 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>
2026-04-15 21:13:56 -05:00
.select({
companyId: costEvents.companyId,
spentMonthlyCents: sql<number>`coalesce(sum(${costEvents.costCents}), 0)::double precision`,
})
.from(costEvents)
.where(
and(
inArray(costEvents.companyId, companyIds),
gte(costEvents.occurredAt, start),
lt(costEvents.occurredAt, end),
),
)
.groupBy(costEvents.companyId);
return new Map(rows.map((row) => [row.companyId, Number(row.spentMonthlyCents ?? 0)]));
}
async function hydrateCompanySpend<T extends { id: string; spentMonthlyCents: number }>(
rows: T[],
database: Pick<Db, "select"> = db,
) {
const spendByCompanyId = await getMonthlySpendByCompanyIds(rows.map((row) => row.id), database);
return rows.map((row) => ({
...row,
spentMonthlyCents: spendByCompanyId.get(row.id) ?? 0,
}));
}
2026-03-16 09:25:39 -05:00
function getCompanyQuery(database: Pick<Db, "select">) {
return database
.select(companySelection)
.from(companies)
.leftJoin(companyLogos, eq(companyLogos.companyId, companies.id));
}
function deriveIssuePrefixBase(name: string) {
const normalized = name.toUpperCase().replace(/[^A-Z]/g, "");
return normalized.slice(0, 3) || ISSUE_PREFIX_FALLBACK;
}
function suffixForAttempt(attempt: number) {
if (attempt <= 1) return "";
return "A".repeat(attempt - 1);
}
function isIssuePrefixConflict(error: unknown) {
const constraint = typeof error === "object" && error !== null && "constraint" in error
? (error as { constraint?: string }).constraint
: typeof error === "object" && error !== null && "constraint_name" in error
? (error as { constraint_name?: string }).constraint_name
: undefined;
return typeof error === "object"
&& error !== null
&& "code" in error
&& (error as { code?: string }).code === "23505"
&& constraint === "companies_issue_prefix_idx";
}
async function createCompanyWithUniquePrefix(data: typeof companies.$inferInsert) {
const base = deriveIssuePrefixBase(data.name);
let suffix = 1;
while (suffix < 10000) {
const candidate = `${base}${suffixForAttempt(suffix)}`;
try {
const rows = await db
.insert(companies)
.values({ ...data, issuePrefix: candidate })
.returning();
return rows[0];
} catch (error) {
if (!isIssuePrefixConflict(error)) throw error;
}
suffix += 1;
}
throw new Error("Unable to allocate unique issue prefix");
}
return {
list: async () => {
const rows = await getCompanyQuery(db);
const hydrated = await hydrateCompanySpend(rows);
return hydrated.map((row) => enrichCompany(row));
},
getById: async (id: string) => {
const row = await getCompanyQuery(db)
.where(eq(companies.id, id))
.then((rows) => rows[0] ?? null);
if (!row) return null;
const [hydrated] = await hydrateCompanySpend([row], db);
return enrichCompany(hydrated);
},
2026-03-16 09:25:39 -05:00
create: async (data: typeof companies.$inferInsert) => {
const created = await createCompanyWithUniquePrefix(data);
Add sandbox environment support (#4415) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies. > - The environment/runtime layer decides where agent work executes and how the control plane reaches those runtimes. > - Today Paperclip can run locally and over SSH, but sandboxed execution needs a first-class environment model instead of one-off adapter behavior. > - We also want sandbox providers to be pluggable so the core does not hardcode every provider implementation. > - This branch adds the Sandbox environment path, the provider contract, and a deterministic fake provider plugin. > - That required synchronized changes across shared contracts, plugin SDK surfaces, server runtime orchestration, and the UI environment/workspace flows. > - The result is that sandbox execution becomes a core control-plane capability while keeping provider implementations extensible and testable. ## What Changed - Added sandbox runtime support to the environment execution path, including runtime URL discovery, sandbox execution targeting, orchestration, and heartbeat integration. - Added plugin-provider support for sandbox environments so providers can be supplied via plugins instead of hardcoded server logic. - Added the fake sandbox provider plugin with deterministic behavior suitable for local and automated testing. - Updated shared types, validators, plugin protocol definitions, and SDK helpers to carry sandbox provider and workspace-runtime contracts across package boundaries. - Updated server routes and services so companies can create sandbox environments, select them for work, and execute work through the sandbox runtime path. - Updated the UI environment and workspace surfaces to expose sandbox environment configuration and selection. - Added test coverage for sandbox runtime behavior, provider seams, environment route guards, orchestration, and the fake provider plugin. ## Verification - Ran locally before the final fixture-only scrub: - `pnpm -r typecheck` - `pnpm test:run` - `pnpm build` - Ran locally after the final scrub amend: - `pnpm vitest run server/src/__tests__/runtime-api.test.ts` - Reviewer spot checks: - create a sandbox environment backed by the fake provider plugin - run work through that environment - confirm sandbox provider execution does not inherit host secrets implicitly ## Risks - This touches shared contracts, plugin SDK plumbing, server runtime orchestration, and UI environment/workspace flows, so regressions would likely show up as cross-layer mismatches rather than isolated type errors. - Runtime URL discovery and sandbox callback selection are sensitive to host/bind configuration; if that logic is wrong, sandbox-backed callbacks may fail even when execution succeeds. - The fake provider plugin is intentionally deterministic and test-oriented; future providers may expose capability gaps that this branch does not yet cover. ## Model Used - OpenAI Codex coding agent on a GPT-5-class backend in the Paperclip/Codex harness. Exact backend model ID is not exposed in-session. Tool-assisted workflow with shell execution, file editing, git history inspection, and local test 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 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 - [x] 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
2026-04-24 12:15:53 -07:00
await environmentsSvc.ensureLocalEnvironment(created.id);
2026-03-16 09:25:39 -05:00
const row = await getCompanyQuery(db)
.where(eq(companies.id, created.id))
.then((rows) => rows[0] ?? null);
if (!row) throw notFound("Company not found after creation");
const [hydrated] = await hydrateCompanySpend([row], db);
return enrichCompany(hydrated);
2026-03-16 09:25:39 -05:00
},
2026-03-16 09:25:39 -05:00
update: (
id: string,
data: Partial<typeof companies.$inferInsert> & { logoAssetId?: string | null },
) =>
db.transaction(async (tx) => {
const existing = await getCompanyQuery(tx)
.where(eq(companies.id, id))
.then((rows) => rows[0] ?? null);
if (!existing) return null;
const { logoAssetId, ...companyPatch } = data;
if (logoAssetId !== undefined && logoAssetId !== null) {
const nextLogoAsset = await tx
.select({ id: assets.id, companyId: assets.companyId })
.from(assets)
.where(eq(assets.id, logoAssetId))
.then((rows) => rows[0] ?? null);
if (!nextLogoAsset) throw notFound("Logo asset not found");
if (nextLogoAsset.companyId !== existing.id) {
throw unprocessable("Logo asset must belong to the same company");
}
}
const updated = await tx
.update(companies)
.set({ ...companyPatch, updatedAt: new Date() })
.where(eq(companies.id, id))
.returning()
.then((rows) => rows[0] ?? null);
if (!updated) return null;
if (logoAssetId === null) {
await tx.delete(companyLogos).where(eq(companyLogos.companyId, id));
} else if (logoAssetId !== undefined) {
await tx
.insert(companyLogos)
.values({
companyId: id,
assetId: logoAssetId,
})
.onConflictDoUpdate({
target: companyLogos.companyId,
set: {
assetId: logoAssetId,
updatedAt: new Date(),
},
});
}
if (logoAssetId !== undefined && existing.logoAssetId && existing.logoAssetId !== logoAssetId) {
await tx.delete(assets).where(eq(assets.id, existing.logoAssetId));
}
const [hydrated] = await hydrateCompanySpend([{
2026-03-16 09:25:39 -05:00
...updated,
logoAssetId: logoAssetId === undefined ? existing.logoAssetId : logoAssetId,
}], tx);
return enrichCompany(hydrated);
2026-03-16 09:25:39 -05:00
}),
archive: (id: string) =>
2026-03-16 09:25:39 -05:00
db.transaction(async (tx) => {
const updated = await tx
.update(companies)
.set({ status: "archived", updatedAt: new Date() })
.where(eq(companies.id, id))
.returning()
.then((rows) => rows[0] ?? null);
if (!updated) return null;
const row = await getCompanyQuery(tx)
.where(eq(companies.id, id))
.then((rows) => rows[0] ?? null);
if (!row) return null;
const [hydrated] = await hydrateCompanySpend([row], tx);
return enrichCompany(hydrated);
2026-03-16 09:25:39 -05:00
}),
remove: (id: string) =>
db.transaction(async (tx) => {
// Delete from child tables in dependency order
await tx.delete(heartbeatRunEvents).where(eq(heartbeatRunEvents.companyId, id));
await tx.delete(agentTaskSessions).where(eq(agentTaskSessions.companyId, id));
2026-04-07 18:20:35 -05:00
await tx.delete(activityLog).where(eq(activityLog.companyId, id));
await tx.delete(heartbeatRuns).where(eq(heartbeatRuns.companyId, id));
await tx.delete(agentWakeupRequests).where(eq(agentWakeupRequests.companyId, id));
await tx.delete(agentApiKeys).where(eq(agentApiKeys.companyId, id));
await tx.delete(agentRuntimeState).where(eq(agentRuntimeState.companyId, id));
await tx.delete(issueComments).where(eq(issueComments.companyId, id));
await tx.delete(costEvents).where(eq(costEvents.companyId, id));
await tx.delete(financeEvents).where(eq(financeEvents.companyId, id));
await tx.delete(approvalComments).where(eq(approvalComments.companyId, id));
await tx.delete(approvals).where(eq(approvals.companyId, id));
await tx.delete(companySecrets).where(eq(companySecrets.companyId, id));
await tx.delete(joinRequests).where(eq(joinRequests.companyId, id));
await tx.delete(invites).where(eq(invites.companyId, id));
await tx.delete(principalPermissionGrants).where(eq(principalPermissionGrants.companyId, id));
await tx.delete(companyMemberships).where(eq(companyMemberships.companyId, id));
2026-04-07 18:20:35 -05:00
await tx.delete(companySkills).where(eq(companySkills.companyId, id));
await tx.delete(issueReadStates).where(eq(issueReadStates.companyId, id));
[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>
2026-04-24 09:40:40 -05:00
await tx.delete(documents).where(eq(documents.companyId, id));
await tx.delete(issues).where(eq(issues.companyId, id));
2026-03-16 09:25:39 -05:00
await tx.delete(companyLogos).where(eq(companyLogos.companyId, id));
await tx.delete(assets).where(eq(assets.companyId, id));
await tx.delete(goals).where(eq(goals.companyId, id));
await tx.delete(projects).where(eq(projects.companyId, id));
await tx.delete(agents).where(eq(agents.companyId, id));
const rows = await tx
.delete(companies)
.where(eq(companies.id, id))
.returning();
return rows[0] ?? null;
}),
stats: () =>
Promise.all([
db
.select({ companyId: agents.companyId, count: count() })
.from(agents)
.groupBy(agents.companyId),
db
.select({ companyId: issues.companyId, count: count() })
.from(issues)
.groupBy(issues.companyId),
]).then(([agentRows, issueRows]) => {
const result: Record<string, { agentCount: number; issueCount: number }> = {};
for (const row of agentRows) {
result[row.companyId] = { agentCount: row.count, issueCount: 0 };
}
for (const row of issueRows) {
if (result[row.companyId]) {
result[row.companyId].issueCount = row.count;
} else {
result[row.companyId] = { agentCount: 0, issueCount: row.count };
}
}
return result;
}),
};
}