Files
PaperClipAI/packages/paperclip-runner/scripts/run-local-provider-smoke.mjs
T
DottaandClaude Opus 5.5 02a2299173 feat(codex): default Codex to gpt-6.1-sol, half the gpt-5.6-sol price (#19623)
## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work
> - Codex agents run through Paperclip Runner or the legacy
`codex_local` harness, and the runner E2E suites run paid Codex cells
> - The shared Codex default and many selections preferred `gpt-5.6-sol`
> - The reviewed OpenAI rate card in
`server/src/services/codex-pricing.ts` (`openai-standard-2026-09-30`)
prices `gpt-6.1-sol` at $2 input / $0.10 cached / $10 output per 1M
tokens, and `gpt-5.6-sol` at $4 / $0.40 / $20
> - So every default run and every paid Codex eval cell cost twice as
much as necessary
> - This pull request moves every place that prefers or selects
`gpt-5.6-sol` to `gpt-6.1-sol`, and keeps historical facts, rate cards
and compatibility fallbacks on `gpt-5.6-sol`
> - The benefit is half the token price for new default Codex agents and
for the Codex E2E and TestOps cells

## Linked Issues or Issue Description

**What existing behavior does this improve?**
The default Codex model for new agents and the Codex model that the
runner E2E suites and TestOps plans select.

**Subsystem affected**
Adapters (`adapter-utils`, `codex-local`), server native runtime
fallback, UI AI connection pools, Paperclip Runner devtools and live
evals, runner E2E catalog and TestOps mappings.

**Current behavior**
New Codex agents without an explicit model store `gpt-5.6-sol`. The
runner E2E `runner-codex` profile, the Reliability `queue-steer` plan
cell, the Product regression TestOps mapping and the ACPX Codex
qualification selection all use `gpt-5.6-sol`.

**Proposed behavior**
They use `gpt-6.1-sol`. Existing agents that store a model keep it.
`gpt-5.6-sol` stays selectable.

**Reason and benefit**
`gpt-6.1-sol` costs half as much per token on the in-repo reviewed rate
card. The current OpenAI pricing page (retrieved 2026-11-06) shows the
same short-context rates and also lists long-context rates of $4 / $0.20
/ $15 for `gpt-6.1-sol` against $8 / $0.80 / $30 for `gpt-5.6-sol`.

**Breaking changes**
None for stored configurations. See Risks.

## What Changed

Changed defaults and selections (all now `gpt-6.1-sol`):

- `PAPERCLIP_RUNNER_DEFAULT_MODELS.codex` in
`packages/adapter-utils/src/paperclip-runner-permissions.ts`. This also
changes `DEFAULT_CODEX_LOCAL_MODEL`,
`resolvePaperclipRunnerModel("codex", …)`, runner config normalization,
`codex_local` → Paperclip Runner conversion, the UI new-agent and
agent-config defaults, the composer default model and the public MCP
effort lookup.
- `codex-local` `models`: the 5.6 entry is now the literal
`gpt-5.6-sol`, because it used to be `DEFAULT_CODEX_LOCAL_MODEL`. The
list order and contents do not change.
- AI connection pool: a new OpenAI member profile uses
`PAPERCLIP_RUNNER_DEFAULT_MODELS.codex` instead of a hard-coded
`gpt-5.6-sol`.
- Paperclip Runner devtools ACPX Codex default and preset, the
`runner-codex-sol` local provider smoke, and the `acpx-codex-sol` live
workflow candidate.
- `tests/acpx-qualification-models.ts` Codex selection (runner E2E and
runner acceptance ACPX Codex profiles).
- Runner E2E: the `runner-codex` profile follows the default, so all
native Codex cells move. This includes the `runner-codex` cells among
the 52 standard `everyday-workflows` cells and the seven Codex
reliability cells. `runner-codex-mini` stays on `gpt-5.4-mini`. The
Reliability plan `queue-steer` `steeringProfile` is now
`['runner-codex', 'gpt-6.1-sol']`. Its executionId
(`everyday-workflows.runner-codex.daytona.queue-steer`), its fullName
and its TestOps case identity do not change. No separate profile is
necessary.
- `product-regression-testops.mjs`: the declared model for every
`runner-codex` case is now `gpt-6.1-sol` (it was already that for
`configured-repository`).
- `tests/runner-e2e/installed-cli.ts`: the credential-free installed
startup proof opens a session on the default model.
- `tests/runner-e2e/scheduled-prices.json`: add a `gpt-6.1-sol` price
(`openai-standard-2026-11-06`, including 30m/12h cache writes and
long-context rates from the OpenAI pricing page). The weekly scheduled
Codex cells need an exact price for their model, or admission fails
closed.
- Storybook: the composer model picker fixtures, the connection pool
stories and host, and the agent settings preview show `gpt-6.1-sol` as
the default.
- Docs: `doc/DEVELOPING.md` (the Codex conversion default) and
`tests/runner-e2e/EVERYDAY-WORKFLOWS.md` (local matrix, reliability
extras, `queue-steer` row).
- Tests that assert the default now expect `gpt-6.1-sol`. New
assertions: the default has the `0.159.0` CLI floor, the compatibility
fallback is floor-free, the `queue-steer` plan cell runs `runner-codex`
on `gpt-6.1-sol`, and all native Codex everyday cells (standard and
reliability) use `gpt-6.1-sol`.

Deliberately kept on `gpt-5.6-sol`:

- Rate cards: `server/src/services/codex-pricing.ts` and
`packages/paperclip-runner/src/evals/model-pricing.ts`. Old receipts
need them. (The runner eval rate card has no `gpt-6.1-sol` entry. An
unpriced candidate is reported as unpriced, not as zero. I did not add a
rate there because that card has its own version and source.)
- The remote Codex CLI compatibility fallback. A new
`CODEX_LOCAL_COMPATIBILITY_FALLBACK_MODEL = "gpt-5.6-sol"` replaces the
default in `codexModelFallbackCandidates`. `gpt-6.1-sol` needs Codex
0.159.0 or newer, so it cannot be the floor-free last resort. Fallback
behavior is unchanged.
- `tests/runner-e2e/provider-usage.ts`: the implicit request
cache-policy attribution stays qualified only for `gpt-5.6-sol`. I did
not verify that policy for `gpt-6.1-sol`. A `gpt-6.1-sol` response that
omits the write-TTL split keeps its cache-write cost unknown, which is
the existing behavior for unqualified models.
- `tests/runner-e2e/scheduled-measurements.json`: historical
`gpt-5.6-sol` measurements. They no longer match the current suite
definitions, so the forecast reports them as historical only. The
forecast tests now build their synthetic cohorts on the current
definition hash.
- Model catalogs that list `gpt-5.6-sol` as available (`codex-local`,
`cursor-local`, `opencode-local`, Speko voice diagnostics, Pi picker
fixture).
- The `gpt-5.6` → `gpt-5.6-sol` alias for old stored configs.
- Dated or evidence docs: `doc/plans/*`, `doc/adapter-model-audit-*`,
`QUALIFICATION-*`, `doc/connections/MEMORY.md`,
`doc/connections/TASK-REVIEWS-VERIFICATION.md`,
`tests/runner-e2e/CHAT-FEATURES.md`, the Slack eval evidence, and the
S49 soak signature text (the soak failure happened on `gpt-5.6-sol`).
- Test fixtures that parse, price, migrate or round-trip an existing
`gpt-5.6-sol` value (Rust runner tests, driver tests, pricing tests,
stored-config tests, stories that show an existing agent).

## Verification

- `npx vitest run` on every server, UI, adapter-utils and codex-local
test file that mentions `gpt-5.6-sol` or the default, plus all of
`packages/adapter-utils` and `packages/adapters/codex-local`: 5,483
passed. Three timeouts under load (`sandbox-managed-runtime`,
`acp.quota`) passed when rerun.
- `packages/paperclip-runner`: `vitest run` for `src/eval`, `src/evals`,
`src/drivers/acpx`, `src/drivers/codex`, `src/cli`, `src/contracts`,
`src/backends`: 2,641 passed.
- `node --test tests/runner-e2e/reliability-testops.test.mjs
tests/runner-e2e/product-regression-testops.test.mjs`: 28 passed.
- `node tests/runner-e2e/run-unit.mjs`: all model, catalog, reliability,
scheduled and TestOps tests pass. Failures remain only in
`copilot-protection-flow`, `denied-target-isolation-flow`,
`pi-controls-flow`, `workflow-target` and `unit-launcher`. These five
also fail on unmodified master in this local environment (filesystem
watch and git environment), and they do not touch models.
- `vitest run --config tests/runner-acceptance/vitest.config.ts`: 19
passed.
- `pnpm test:e2e:runner -- --list --suite everyday-workflows --group
reliability`: the seven `everyday-workflows.runner-codex.daytona.<case>`
cells show `gpt-6.1-sol` with `OPENAI_API_KEY,DAYTONA_API_KEY`.
`--matrix-json` gives 16 reliability cells with the same credentials as
before. `--list --all` shows no `gpt-5.6-sol` cell.
- Typecheck: `adapter-utils`, `adapter-codex-local`, `server`, `ui`,
`paperclip-runner` (TypeScript), and `pnpm test:e2e:runner:typecheck`.
- `pnpm check:token-gates`: clean.
- Not run: paid cells, Rust tests (no Rust change), the browser suites,
and the full `pnpm -r typecheck` / `pnpm build` (CI runs them).

## Risks

- Agents without an explicit model change model on their next save or
normalization, and Paperclip Runner rows with a blank model use
`gpt-6.1-sol` at execution. Stored models, including `gpt-5.6-sol`, are
never rewritten. No migration is necessary.
- `gpt-6.1-sol` needs Codex CLI 0.159.0 or newer with ChatGPT sign-in.
The runner pins `@openai/codex@0.160.0`. On a remote target with an
older image CLI, the existing compatibility check falls back to
`gpt-6-sol` and then `gpt-5.6-sol`, and that probe now runs for
default-model agents too. A legacy `codex_local` agent created with the
new default on a host with an older Codex CLI gets the existing
actionable "upgrade Codex" Test result.
- Qualification: the native Codex profile uses `adapter_constant` model
qualification, so it follows the default. No qualification gate is
dropped. The ACPX Codex qualification selection moves to `gpt-6.1-sol`.
Its next qualification run uses the new model. The provider-usage
cache-policy attribution stays limited to `gpt-5.6-sol`.
- Runner E2E history: the Codex cells change their suite definition
hashes, so earlier `gpt-5.6-sol` results are a separate cohort and do
not count as current.
- The `gpt-6.1-sol` scheduled price uses the file's existing `expiresAt`
(2026-11-19). It needs the same review as the other entries before then.
- No `.github/` change. The Reliability queue-steer cell keeps the
`runner-codex` profile id, so the existing workflow credential and setup
steps still match.

> 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

- Claude Opus 5.5 (Anthropic), model ID `claude-opus-5-5`, running in
Claude Code with tool use (shell, file edits, web fetch of the OpenAI
pricing page).

## 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 (e.g. `docs/...`, `fix/...`)
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
- [ ] 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

Related: #19604 (commits the Reliability TestOps identities; this PR
changes only `steeringProfile` in the same file).

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 15:35:34 -06:00

345 lines
11 KiB
JavaScript

#!/usr/bin/env node
import { access, mkdir, mkdtemp, readdir, rm, stat } from "node:fs/promises";
import { tmpdir } from "node:os";
import { basename, join, resolve } from "node:path";
import { withIsolatedProfileCredentials } from "./local-provider-smoke-environment.mjs";
const PROFILE_IDS = [
"runner-acpx-claude",
"runner-acpx-codex",
"runner-codex",
"runner-opencode",
];
function parseProfiles(args) {
const selected = [];
for (let index = 0; index < args.length; index += 1) {
if (args[index] !== "--profile" || !args[index + 1]) {
throw new Error(
`Usage: pnpm smoke:local-provider -- --profile <${PROFILE_IDS.join("|")}|all>`,
);
}
selected.push(args[++index]);
}
if (selected.length === 0) return ["runner-acpx-claude"];
const expanded = selected.flatMap((profile) =>
profile === "all" ? PROFILE_IDS : [profile],
);
for (const profile of expanded) {
if (!PROFILE_IDS.includes(profile)) {
throw new Error(`Unsupported local provider smoke profile: ${profile}`);
}
}
return [...new Set(expanded)];
}
function liveCandidate(id, candidateSlots) {
const candidates = candidateSlots.flatMap((slot) => slot.candidates);
if (id === "runner-acpx-claude") {
return candidates.find(
(candidate) => candidate.id === "acpx-claude-sonnet",
);
}
if (id === "runner-acpx-codex") {
return candidates.find((candidate) => candidate.id === "acpx-codex-sol");
}
if (id === "runner-codex") {
const source = candidates.find(
(candidate) => candidate.id === "codex-luna",
);
return (
source && {
...source,
id: "runner-codex-sol",
model: "gpt-6.1-sol",
}
);
}
const source = candidates.find(
(candidate) => candidate.id === "opencode-kimi",
);
return (
source && {
...source,
id: "runner-opencode-deepseek",
model: "openrouter/deepseek/deepseek-v4-flash-0731",
}
);
}
function failedChecks(observation) {
const smokeChecks = new Set([
"terminal-authority",
"first-visible-progress",
"substantive-response",
"expected-assistant-text",
"no-empty-comment",
"terminal-presentation",
]);
return [...observation.lifecycle.checks, ...observation.presentation.checks]
.filter((check) => smokeChecks.has(check.id) && !check.passed)
.map((check) => check.id);
}
function safeErrorMessage(error, credentialValues) {
let message = error instanceof Error ? error.message : String(error);
for (const credential of credentialValues) {
if (credential.length > 0)
message = message.split(credential).join("[REDACTED]");
}
return message
.replace(/\bsk-[A-Za-z0-9_-]{8,}\b/g, "[REDACTED]")
.replace(/\bBearer\s+\S+/gi, "Bearer [REDACTED]")
.replace(/\bAKIA[0-9A-Z]{16}\b/g, "[REDACTED]")
.slice(0, 1_000);
}
async function filesUnder(directory, include, skipDirectory = () => false) {
const files = [];
for (const entry of await readdir(directory, { withFileTypes: true })) {
const path = join(directory, entry.name);
if (entry.isDirectory()) {
if (!skipDirectory(path)) {
files.push(...(await filesUnder(path, include, skipDirectory)));
}
} else if (entry.isFile() && include(path)) {
files.push(path);
}
}
return files;
}
async function assertArtifactsFresh(label, sources, artifacts) {
const sourceTimes = await Promise.all(
sources.map(async (source) => (await stat(source)).mtimeMs),
);
const artifactTimes = await Promise.all(
artifacts.map(async (artifact) => (await stat(artifact)).mtimeMs),
);
if (Math.max(...sourceTimes) > Math.min(...artifactTimes)) {
throw new Error(
`${label} smoke artifacts are older than their source. Rebuild the targeted artifacts before running the smoke.`,
);
}
}
const profiles = parseProfiles(process.argv.slice(2));
const packageRoot = resolve(import.meta.dirname, "..");
const runnerd = resolve(
packageRoot,
"runner",
"target",
"debug",
process.platform === "win32" ? "paperclip-runnerd.exe" : "paperclip-runnerd",
);
const requiredArtifacts = [
runnerd,
resolve(packageRoot, "dist", "eval", "index.js"),
...(profiles.some((profile) => profile.startsWith("runner-acpx-"))
? [resolve(packageRoot, "dist", "cli", "acpx-runtime-sidecar.cjs")]
: []),
...(profiles.includes("runner-opencode")
? [resolve(packageRoot, "dist", "cli", "opencode-app-server-proxy.cjs")]
: []),
];
await Promise.all(requiredArtifacts.map((artifact) => access(artifact))).catch(
() => {
throw new Error(
"Local provider smoke artifacts are missing. Run build:typescript and build:runner-binaries once.",
);
},
);
const typescriptSources = await filesUnder(
resolve(packageRoot, "src"),
(path) => path.endsWith(".ts") && !path.endsWith(".test.ts"),
(path) =>
/\/(?:browser|devtools|issue-thread|react|scenarios|standalone)$/u.test(
path,
),
);
await assertArtifactsFresh(
"TypeScript",
[
resolve(packageRoot, "package.json"),
resolve(packageRoot, "tsconfig.json"),
...typescriptSources,
],
requiredArtifacts.filter((artifact) => artifact !== runnerd),
);
const rustSources = await filesUnder(
resolve(packageRoot, "runner"),
(path) =>
path.endsWith(".rs") ||
path.endsWith("Cargo.toml") ||
path.endsWith("Cargo.lock"),
(path) => /\/(?:target|tests|benches|examples)$/u.test(path),
);
await assertArtifactsFresh("runnerd", rustSources, [runnerd]);
const smokeRoot = await mkdtemp(
join(tmpdir(), "paperclip-local-provider-smoke-"),
);
if (!basename(smokeRoot).startsWith("paperclip-local-provider-smoke-")) {
throw new Error("Refusing an unrecognized local provider smoke root");
}
await Promise.all(
["tmp", "home", "paperclip-home", "codex-home", "claude-home"].map(
(directory) => mkdir(join(smokeRoot, directory), { recursive: true }),
),
);
const ambientEnvironment = { ...process.env };
for (const name of Object.keys(process.env)) delete process.env[name];
for (const name of [
"PATH",
"SystemRoot",
"ComSpec",
"PATHEXT",
"LANG",
"LC_ALL",
"LC_CTYPE",
"TZ",
"SSL_CERT_FILE",
"SSL_CERT_DIR",
"NODE_EXTRA_CA_CERTS",
]) {
if (ambientEnvironment[name] !== undefined) {
process.env[name] = ambientEnvironment[name];
}
}
Object.assign(process.env, {
TMPDIR: join(smokeRoot, "tmp"),
HOME: join(smokeRoot, "home"),
PAPERCLIP_HOME: join(smokeRoot, "paperclip-home"),
CODEX_HOME: join(smokeRoot, "codex-home"),
CLAUDE_CONFIG_DIR: join(smokeRoot, "claude-home"),
NO_BROWSER: "1",
PAPERCLIP_OPEN_ON_LISTEN: "false",
});
let cleanupPromise;
const cleanup = () => {
cleanupPromise ??= rm(smokeRoot, { recursive: true, force: true });
return cleanupPromise;
};
const exitAfterCleanup = (status) => {
void cleanup().finally(() => process.exit(status));
};
process.once("SIGINT", () => exitAfterCleanup(130));
process.once("SIGTERM", () => exitAfterCleanup(143));
let failed = false;
try {
// Import only after the disposable homes are authoritative so no provider
// module can snapshot the developer's normal Paperclip or provider state.
const {
RUNNER_LIVE_CANDIDATE_SLOTS,
executeLiveRunnerWorkflow,
runnerWorkflowCase,
} = await import("../dist/eval/index.js");
const candidates = new Map(
profiles.map((profile) => [
profile,
liveCandidate(profile, RUNNER_LIVE_CANDIDATE_SLOTS),
]),
);
const credentialsByProfile = new Map();
for (const [profile, candidate] of candidates) {
if (!candidate) throw new Error(`Missing live candidate for ${profile}`);
const missingCredentials = [];
const profileCredentials = {};
for (const name of candidate.qualification.requiredEnvironment) {
const value = ambientEnvironment[name]?.trim();
if (value) profileCredentials[name] = value;
else missingCredentials.push(name);
}
if (missingCredentials.length > 0) {
throw new Error(
`${profile} requires ${missingCredentials.join(", ")} in the smoke process environment`,
);
}
credentialsByProfile.set(profile, profileCredentials);
}
const providerCredentialNames = new Set(
[...credentialsByProfile.values()].flatMap((credentials) =>
Object.keys(credentials),
),
);
const credentialValues = new Set(
[...credentialsByProfile.values()].flatMap((credentials) =>
Object.values(credentials),
),
);
const evalCase = runnerWorkflowCase("completion-robustness");
for (const profile of profiles) {
const candidate = candidates.get(profile);
const workspace = join(smokeRoot, `workspace-${profile}`);
await mkdir(workspace, { recursive: true });
const entry = {
// Avoid a three-segment dotted identity: durable redaction correctly
// treats that shape as a possible JWT and refuses to rewrite IDs.
executionId: `local-smoke-${profile}-${String(Date.now())}`,
caseId: evalCase.id,
candidateId: candidate.id,
slotId: candidate.slotId,
repetition: 1,
providerTrace: "raw",
budget: candidate.budget,
};
try {
const observation = await withIsolatedProfileCredentials({
environment: process.env,
providerCredentialNames,
profileCredentials: credentialsByProfile.get(profile),
run: () =>
executeLiveRunnerWorkflow({
entry,
candidate,
evalCase,
workingDirectory: workspace,
// This smoke proves the provider launch/message/semantic-terminal path.
// Usage conformance remains covered by the dedicated eval campaign.
allowMissingUsage: true,
expectedAssistantText: "PAPERCLIP_LOCAL_PROVIDER_SMOKE_OK",
promptOverride:
"Reply with exactly PAPERCLIP_LOCAL_PROVIDER_SMOKE_OK and no other text. Do not call tools.",
runnerBinary: runnerd,
}),
});
const failures = failedChecks(observation);
const passed = failures.length === 0;
failed ||= !passed;
process.stdout.write(
`${JSON.stringify({
profile,
status: passed ? "passed" : "failed",
classification: passed
? "message_completed"
: observation.classification,
settlementMs: observation.metrics.settlementMs ?? null,
totalTokens: observation.metrics.totalTokens ?? null,
costUsd: observation.metrics.costUsd ?? null,
failedChecks: failures,
failureCode: observation.failure?.code ?? null,
})}\n`,
);
} catch (error) {
failed = true;
process.stderr.write(
`${JSON.stringify({
profile,
status: "failed",
infrastructureError: safeErrorMessage(error, credentialValues),
})}\n`,
);
}
}
} finally {
await cleanup();
}
if (failed) process.exitCode = 1;